langchain[patch]: Release 0.2.12 (#24954)

Fix #24925

.github/scripts/check_diff.py

@@ -1,7 +1,6 @@
 import glob
 import json
 import os
-import re
 import sys
 import tomllib
 from collections import defaultdict
@@ -86,6 +85,11 @@ def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
 
 
 def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
+    if dir_ == "libs/core":
+        return [
+            {"working-directory": dir_, "python-version": f"3.{v}"}
+            for v in range(8, 13)
+        ]
     min_python = "3.8"
     max_python = "3.12"
 
@@ -95,6 +99,15 @@ def _get_configs_for_single_dir(job: str, dir_: str) -> List[Dict[str, str]]:
         # declare deps in funny way
         max_python = "3.11"
 
+    if dir_ in ["libs/community", "libs/langchain"] and job == "extended-tests":
+        # community extended test resolution in 3.12 is slow
+        # even in uv
+        max_python = "3.11"
+
+    if dir_ == "libs/community" and job == "compile-integration-tests":
+        # community integration deps are slow in 3.12
+        max_python = "3.11"
+
     return [
         {"working-directory": dir_, "python-version": min_python},
         {"working-directory": dir_, "python-version": max_python},

README.md

@@ -7,7 +7,6 @@
 [![PyPI - License](https://img.shields.io/pypi/l/langchain-core?style=flat-square)](https://opensource.org/licenses/MIT)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-core?style=flat-square)](https://pypistats.org/packages/langchain-core)
 [![GitHub star chart](https://img.shields.io/github/stars/langchain-ai/langchain?style=flat-square)](https://star-history.com/#langchain-ai/langchain)
-[![Dependency Status](https://img.shields.io/librariesio/github/langchain-ai/langchain?style=flat-square)](https://libraries.io/github/langchain-ai/langchain)
 [![Open Issues](https://img.shields.io/github/issues-raw/langchain-ai/langchain?style=flat-square)](https://github.com/langchain-ai/langchain/issues)
 [![Open in Dev Containers](https://img.shields.io/static/v1?label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode&style=flat-square)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/langchain-ai/langchain)
 [![Open in GitHub Codespaces](https://github.com/codespaces/badge.svg)](https://codespaces.new/langchain-ai/langchain)

docs/Makefile

@@ -42,6 +42,10 @@ generate-files:
 
 	$(PYTHON) scripts/document_loader_feat_table.py $(INTERMEDIATE_DIR)
 
+	$(PYTHON) scripts/kv_store_feat_table.py $(INTERMEDIATE_DIR)
+
+	$(PYTHON) scripts/partner_pkg_table.py $(INTERMEDIATE_DIR)
+
 	$(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
 
 	wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
@@ -65,10 +69,13 @@ render:
 md-sync:
 	rsync -avm --include="*/" --include="*.mdx" --include="*.md" --include="*.png" --include="*/_category_.yml" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_NEW_DOCS_DIR)
 
+append-related:
+	$(PYTHON) scripts/append_related_links.py $(OUTPUT_NEW_DOCS_DIR)
+
 generate-references:
 	$(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(OUTPUT_NEW_DOCS_DIR)
 
-build: install-py-deps generate-files copy-infra render md-sync
+build: install-py-deps generate-files copy-infra render md-sync append-related
 
 vercel-build: install-vercel-deps build generate-references
 	rm -rf docs

docs/docs/concepts.mdx

@@ -90,7 +90,7 @@ LCEL aims to provide consistency around behavior and customization over legacy s
 `ConversationalRetrievalChain`. Many of these legacy chains hide important details like prompts, and as a wider variety
 of viable models emerge, customization has become more and more important.
 
-If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/how_to/migrate_chains/).
+If you are currently using one of these legacy chains, please see [this guide for guidance on how to migrate](/docs/versions/migrating_chains).
 
 For guides on how to do specific tasks with LCEL, check out [the relevant how-to guides](/docs/how_to/#langchain-expression-language-lcel).
 
@@ -498,6 +498,30 @@ Retrievers accept a string query as input and return a list of Document's as out
 
 For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
 
+### Key-value stores
+
+For some techniques, such as [indexing and retrieval with multiple vectors per document](/docs/how_to/multi_vector/) or
+[caching embeddings](/docs/how_to/caching_embeddings/), having a form of key-value (KV) storage is helpful.
+
+LangChain includes a [`BaseStore`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) interface,
+which allows for storage of arbitrary data. However, LangChain components that require KV-storage accept a
+more specific `BaseStore[str, bytes]` instance that stores binary data (referred to as a `ByteStore`), and internally take care of
+encoding and decoding data for their specific needs.
+
+This means that as a user, you only need to think about one type of store rather than different ones for different types of data.
+
+#### Interface
+
+All [`BaseStores`](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.BaseStore.html) support the following interface. Note that the interface allows
+for modifying **multiple** key-value pairs at once:
+
+- `mget(key: Sequence[str]) -> List[Optional[bytes]]`: get the contents of multiple keys, returning `None` if the key does not exist
+- `mset(key_value_pairs: Sequence[Tuple[str, bytes]]) -> None`: set the contents of multiple keys
+- `mdelete(key: Sequence[str]) -> None`: delete multiple keys
+- `yield_keys(prefix: Optional[str] = None) -> Iterator[str]`: yield all keys in the store, optionally filtering by a prefix
+
+For key-value store implementations, see [this section](/docs/integrations/stores/).
+
 ### Tools
 <span data-heading-keywords="tool,tools"></span>
 

docs/docs/how_to/code_splitter.ipynb

@@ -54,7 +54,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "9e4144de-d925-4d4c-91c3-685ef8baa57c",
+   "id": "2bb9c73f-9d00-4a19-a81f-cab2f0fd921a",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -63,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "id": "a9e37aa1",
    "metadata": {},
    "outputs": [],
@@ -718,8 +718,44 @@
     "php_splitter = RecursiveCharacterTextSplitter.from_language(\n",
     "    language=Language.PHP, chunk_size=50, chunk_overlap=0\n",
     ")\n",
-    "haskell_docs = php_splitter.create_documents([PHP_CODE])\n",
-    "haskell_docs"
+    "php_docs = php_splitter.create_documents([PHP_CODE])\n",
+    "php_docs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9fa62c1",
+   "metadata": {},
+   "source": [
+    "## PowerShell\n",
+    "Here's an example using the PowerShell text splitter:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7e6893ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "POWERSHELL_CODE = \"\"\"\n",
+    "$directoryPath = Get-Location\n",
+    "\n",
+    "$items = Get-ChildItem -Path $directoryPath\n",
+    "\n",
+    "$files = $items | Where-Object { -not $_.PSIsContainer }\n",
+    "\n",
+    "$sortedFiles = $files | Sort-Object LastWriteTime\n",
+    "\n",
+    "foreach ($file in $sortedFiles) {\n",
+    "    Write-Output (\"Name: \" + $file.Name + \" | Last Write Time: \" + $file.LastWriteTime)\n",
+    "}\n",
+    "\"\"\"\n",
+    "powershell_splitter = RecursiveCharacterTextSplitter.from_language(\n",
+    "    language=Language.POWERSHELL, chunk_size=100, chunk_overlap=0\n",
+    ")\n",
+    "powershell_docs = powershell_splitter.create_documents([POWERSHELL_CODE])\n",
+    "powershell_docs"
    ]
   }
  ],
@@ -739,7 +775,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/index.mdx

@@ -31,6 +31,8 @@ This highlights functionality that is core to using LangChain.
 
 [**LCEL cheatsheet**](/docs/how_to/lcel_cheatsheet/): For a quick overview of how to use the main LCEL primitives.
 
+[**Migration guide**](/docs/versions/migrating_chains): For migrating legacy chain abstractions to LCEL.
+
 - [How to: chain runnables](/docs/how_to/sequence)
 - [How to: stream runnables](/docs/how_to/streaming)
 - [How to: invoke runnables in parallel](/docs/how_to/parallel/)
@@ -43,7 +45,6 @@ This highlights functionality that is core to using LangChain.
 - [How to: create a dynamic (self-constructing) chain](/docs/how_to/dynamic_chain/)
 - [How to: inspect runnables](/docs/how_to/inspect)
 - [How to: add fallbacks to a runnable](/docs/how_to/fallbacks)
-- [How to: migrate chains to LCEL](/docs/how_to/migrate_chains)
 - [How to: pass runtime secrets to a runnable](/docs/how_to/runnable_runtime_secrets)
 
 ## Components
@@ -87,6 +88,7 @@ These are the core building blocks you can use when building applications.
 - [How to: few shot prompt tool behavior](/docs/how_to/tools_few_shot)
 - [How to: bind model-specific formatted tools](/docs/how_to/tools_model_specific)
 - [How to: force a specific tool call](/docs/how_to/tool_choice)
+- [How to: work with local models](/docs/how_to/local_llms)
 - [How to: init any model in one line](/docs/how_to/chat_models_universal_init/)
 
 ### Messages
@@ -105,7 +107,7 @@ What LangChain calls [LLMs](/docs/concepts/#llms) are older forms of language mo
 - [How to: create a custom LLM class](/docs/how_to/custom_llm)
 - [How to: stream a response back](/docs/how_to/streaming_llm)
 - [How to: track token usage](/docs/how_to/llm_token_usage_tracking)
-- [How to: work with local LLMs](/docs/how_to/local_llms)
+- [How to: work with local models](/docs/how_to/local_llms)
 
 ### Output parsers
 

docs/docs/how_to/local_llms.ipynb

@@ -5,11 +5,11 @@
    "id": "b8982428",
    "metadata": {},
    "source": [
-    "# Run LLMs locally\n",
+    "# Run models locally\n",
     "\n",
     "## Use case\n",
     "\n",
-    "The popularity of projects like [PrivateGPT](https://github.com/imartinez/privateGPT), [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://github.com/ollama/ollama), [GPT4All](https://github.com/nomic-ai/gpt4all), [llamafile](https://github.com/Mozilla-Ocho/llamafile), and others underscore the demand to run LLMs locally (on your own device).\n",
+    "The popularity of projects like [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://github.com/ollama/ollama), [GPT4All](https://github.com/nomic-ai/gpt4all), [llamafile](https://github.com/Mozilla-Ocho/llamafile), and others underscore the demand to run LLMs locally (on your own device).\n",
     "\n",
     "This has at least two important benefits:\n",
     "\n",
@@ -66,6 +66,12 @@
     "\n",
     "![Image description](../../static/img/llama_t_put.png)\n",
     "\n",
+    "### Formatting prompts\n",
+    "\n",
+    "Some providers have [chat model](/docs/concepts/#chat-models) wrappers that takes care of formatting your input prompt for the specific local model you're using. However, if you are prompting local models with a [text-in/text-out LLM](/docs/concepts/#llms) wrapper, you may need to use a prompt tailed for your specific model.\n",
+    "\n",
+    "This can [require the inclusion of special tokens](https://huggingface.co/blog/llama2#how-to-prompt-llama-2). [Here's an example for LLaMA 2](https://smith.langchain.com/hub/rlm/rag-prompt-llama).\n",
+    "\n",
     "## Quickstart\n",
     "\n",
     "[`Ollama`](https://ollama.ai/) is one way to easily run inference on macOS.\n",
@@ -73,10 +79,20 @@
     "The instructions [here](https://github.com/jmorganca/ollama?tab=readme-ov-file#ollama) provide details, which we summarize:\n",
     " \n",
     "* [Download and run](https://ollama.ai/download) the app\n",
-    "* From command line, fetch a model from this [list of options](https://github.com/jmorganca/ollama): e.g., `ollama pull llama2`\n",
+    "* From command line, fetch a model from this [list of options](https://github.com/jmorganca/ollama): e.g., `ollama pull llama3.1:8b`\n",
     "* When the app is running, all models are automatically served on `localhost:11434`\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "29450fc9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain_ollama"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -86,7 +102,7 @@
     {
      "data": {
       "text/plain": [
-       "' The first man on the moon was Neil Armstrong, who landed on the moon on July 20, 1969 as part of the Apollo 11 mission. obviously.'"
+       "'...Neil Armstrong!\\n\\nOn July 20, 1969, Neil Armstrong became the first person to set foot on the lunar surface, famously declaring \"That\\'s one small step for man, one giant leap for mankind\" as he stepped off the lunar module Eagle onto the Moon\\'s surface.\\n\\nWould you like to know more about the Apollo 11 mission or Neil Armstrong\\'s achievements?'"
       ]
      },
      "execution_count": 2,
@@ -95,51 +111,78 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import Ollama\n",
+    "from langchain_ollama import OllamaLLM\n",
+    "\n",
+    "llm = OllamaLLM(model=\"llama3.1:8b\")\n",
     "\n",
-    "llm = Ollama(model=\"llama2\")\n",
     "llm.invoke(\"The first man on the moon was ...\")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "343ab645",
+   "id": "674cc672",
    "metadata": {},
    "source": [
-    "Stream tokens as they are being generated."
+    "Stream tokens as they are being generated:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
-   "id": "9cd83603",
+   "execution_count": 3,
+   "id": "1386a852",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      " The first man to walk on the moon was Neil Armstrong, an American astronaut who was part of the Apollo 11 mission in 1969. февруари 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon's surface, famously declaring \"That's one small step for man, one giant leap for mankind\" as he took his first steps. He was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the moon during the mission."
+      "...|"
      ]
     },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Neil| Armstrong|,| an| American| astronaut|.| He| stepped| out| of| the| lunar| module| Eagle| and| onto| the| surface| of| the| Moon| on| July| |20|,| |196|9|,| famously| declaring|:| \"|That|'s| one| small| step| for| man|,| one| giant| leap| for| mankind|.\"||"
+     ]
+    }
+   ],
+   "source": [
+    "for chunk in llm.stream(\"The first man on the moon was ...\"):\n",
+    "    print(chunk, end=\"|\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e5731060",
+   "metadata": {},
+   "source": [
+    "Ollama also includes a chat model wrapper that handles formatting conversation turns:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f14a778a",
+   "metadata": {},
+   "outputs": [
     {
      "data": {
       "text/plain": [
-       "' The first man to walk on the moon was Neil Armstrong, an American astronaut who was part of the Apollo 11 mission in 1969. февруари 20, 1969, Armstrong stepped out of the lunar module Eagle and onto the moon\\'s surface, famously declaring \"That\\'s one small step for man, one giant leap for mankind\" as he took his first steps. He was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the moon during the mission.'"
+       "AIMessage(content='The answer is a historic one!\\n\\nThe first man to walk on the Moon was Neil Armstrong, an American astronaut and commander of the Apollo 11 mission. On July 20, 1969, Armstrong stepped out of the lunar module Eagle onto the surface of the Moon, famously declaring:\\n\\n\"That\\'s one small step for man, one giant leap for mankind.\"\\n\\nArmstrong was followed by fellow astronaut Edwin \"Buzz\" Aldrin, who also walked on the Moon during the mission. Michael Collins remained in orbit around the Moon in the command module Columbia.\\n\\nNeil Armstrong passed away on August 25, 2012, but his legacy as a pioneering astronaut and engineer continues to inspire people around the world!', response_metadata={'model': 'llama3.1:8b', 'created_at': '2024-08-01T00:38:29.176717Z', 'message': {'role': 'assistant', 'content': ''}, 'done_reason': 'stop', 'done': True, 'total_duration': 10681861417, 'load_duration': 34270292, 'prompt_eval_count': 19, 'prompt_eval_duration': 6209448000, 'eval_count': 141, 'eval_duration': 4432022000}, id='run-7bed57c5-7f54-4092-912c-ae49073dcd48-0', usage_metadata={'input_tokens': 19, 'output_tokens': 141, 'total_tokens': 160})"
       ]
      },
-     "execution_count": 40,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler\n",
+    "from langchain_ollama import ChatOllama\n",
     "\n",
-    "llm = Ollama(\n",
-    "    model=\"llama2\", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()])\n",
-    ")\n",
-    "llm.invoke(\"The first man on the moon was ...\")"
+    "chat_model = ChatOllama(model=\"llama3.1:8b\")\n",
+    "\n",
+    "chat_model.invoke(\"Who was the first man on the moon?\")"
    ]
   },
   {
@@ -199,7 +242,7 @@
     "\n",
     "With [Ollama](https://github.com/jmorganca/ollama), fetch a model via `ollama pull <model family>:<tag>`:\n",
     "\n",
-    "* E.g., for Llama-7b: `ollama pull llama2` will download the most basic version of the model (e.g., smallest # parameters and 4 bit quantization)\n",
+    "* E.g., for Llama 2 7b: `ollama pull llama2` will download the most basic version of the model (e.g., smallest # parameters and 4 bit quantization)\n",
     "* We can also specify a particular version from the [model list](https://github.com/jmorganca/ollama?tab=readme-ov-file#model-library), e.g., `ollama pull llama2:13b`\n",
     "* See the full set of parameters on the [API reference page](https://api.python.langchain.com/en/latest/llms/langchain_community.llms.ollama.Ollama.html)"
    ]
@@ -222,9 +265,7 @@
     }
    ],
    "source": [
-    "from langchain_community.llms import Ollama\n",
-    "\n",
-    "llm = Ollama(model=\"llama2:13b\")\n",
+    "llm = OllamaLLM(model=\"llama2:13b\")\n",
     "llm.invoke(\"The first man on the moon was ... think step by step\")"
    ]
   },
@@ -268,11 +309,7 @@
    "cell_type": "code",
    "execution_count": null,
    "id": "5eba38dc",
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "%env CMAKE_ARGS=\"-DLLAMA_METAL=on\"\n",
@@ -542,7 +579,6 @@
     }
    ],
    "source": [
-    "from langchain.chains import LLMChain\n",
     "from langchain.chains.prompt_selector import ConditionalPromptSelector\n",
     "from langchain_core.prompts import PromptTemplate\n",
     "\n",
@@ -613,9 +649,9 @@
    ],
    "source": [
     "# Chain\n",
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
+    "chain = prompt | llm\n",
     "question = \"What NFL team won the Super Bowl in the year that Justin Bieber was born?\"\n",
-    "llm_chain.run({\"question\": question})"
+    "chain.invoke({\"question\": question})"
    ]
   },
   {
@@ -666,7 +702,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.7"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/how_to/migrate_agent.ipynb

@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "662fac50",
    "metadata": {},
    "outputs": [],
@@ -50,6 +50,26 @@
     "%pip install -U langgraph langchain langchain-openai"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6f8ec38f",
+   "metadata": {},
+   "source": [
+    "Then, set your OpenAI API key."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5fca87ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-...\""
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "8e50635c-1671-46e6-be65-ce95f8167c2f",
@@ -62,7 +82,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "1e425fea-2796-4b99-bee6-9a6ffe73f756",
    "metadata": {},
    "outputs": [],
@@ -95,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "03ea357c-9c36-4464-b2cc-27bd150e1554",
    "metadata": {},
    "outputs": [
@@ -106,7 +126,7 @@
        " 'output': 'The value of `magic_function(3)` is 5.'}"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -142,7 +162,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "53a3737a-d167-4255-89bf-20ac37f89a3e",
    "metadata": {},
    "outputs": [
@@ -153,7 +173,7 @@
        " 'output': 'The value of `magic_function(3)` is 5.'}"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -173,7 +193,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "74ecebe3-512e-409c-a661-bdd5b0a2b782",
    "metadata": {},
    "outputs": [
@@ -181,10 +201,10 @@
      "data": {
       "text/plain": [
        "{'input': 'Pardon?',\n",
-       " 'output': 'The result of applying `magic_function` to the input 3 is 5.'}"
+       " 'output': 'The value you get when you apply `magic_function` to the input 3 is 5.'}"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -223,7 +243,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "a9a11ccd-75e2-4c11-844d-a34870b0ff91",
    "metadata": {},
    "outputs": [
@@ -234,7 +254,7 @@
        " 'output': 'El valor de `magic_function(3)` es 5.'}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -263,19 +283,19 @@
    "source": [
     "Now, let's pass a custom system message to [react agent executor](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent).\n",
     "\n",
-    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies messages before they are passed into the model, and can be one of four values:\n",
+    "LangGraph's prebuilt `create_react_agent` does not take a prompt template directly as a parameter, but instead takes a [`state_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) parameter. This modifies the graph state before the llm is called, and can be one of four values:\n",
     "\n",
     "- A `SystemMessage`, which is added to the beginning of the list of messages.\n",
     "- A `string`, which is converted to a `SystemMessage` and added to the beginning of the list of messages.\n",
-    "- A `Callable`, which should take in a list of messages. The output is then passed to the language model.\n",
-    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should should take in a list of messages. The output is then passed to the language model.\n",
+    "- A `Callable`, which should take in full graph state. The output is then passed to the language model.\n",
+    "- Or a [`Runnable`](/docs/concepts/#langchain-expression-language-lcel), which should take in full graph state. The output is then passed to the language model.\n",
     "\n",
     "Here's how it looks in action:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "a9486805-676a-4d19-a5c4-08b41b172989",
    "metadata": {},
    "outputs": [],
@@ -287,7 +307,7 @@
     "# This could also be a SystemMessage object\n",
     "# system_message = SystemMessage(content=\"You are a helpful assistant. Respond only in Spanish.\")\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=system_message)\n",
+    "app = create_react_agent(model, tools, state_modifier=system_message)\n",
     "\n",
     "\n",
     "messages = app.invoke({\"messages\": [(\"user\", query)]})"
@@ -304,7 +324,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "d369ab45-0c82-45f4-9d3e-8efb8dd47e2c",
    "metadata": {},
    "outputs": [
@@ -317,8 +337,8 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.prebuilt import create_react_agent\n",
+    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -328,13 +348,13 @@
     ")\n",
     "\n",
     "\n",
-    "def _modify_messages(messages: list[AnyMessage]):\n",
-    "    return prompt.invoke({\"messages\": messages}).to_messages() + [\n",
+    "def _modify_state_messages(state: AgentState):\n",
+    "    return prompt.invoke({\"messages\": state[\"messages\"]}).to_messages() + [\n",
     "        (\"user\", \"Also say 'Pandamonium!' after the answer.\")\n",
     "    ]\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
+    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
     "\n",
     "\n",
     "messages = app.invoke({\"messages\": [(\"human\", query)]})\n",
@@ -366,8 +386,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "1fb52a2c",
+   "execution_count": 9,
+   "id": "b97beba5-8f74-430c-9399-91b77c8fa15c",
    "metadata": {},
    "outputs": [
     {
@@ -376,7 +396,7 @@
      "text": [
       "Hi Polly! The output of the magic function for the input 3 is 5.\n",
       "---\n",
-      "Yes, I remember your name, Polly! How can I assist you further?\n",
+      "Yes, your name is Polly!\n",
       "---\n",
       "The output of the magic function for the input 3 is 5.\n"
      ]
@@ -384,14 +404,14 @@
    ],
    "source": [
     "from langchain.agents import AgentExecutor, create_tool_calling_agent\n",
-    "from langchain_community.chat_message_histories import ChatMessageHistory\n",
+    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
     "from langchain_core.tools import tool\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
     "model = ChatOpenAI(model=\"gpt-4o\")\n",
-    "memory = ChatMessageHistory(session_id=\"test-session\")\n",
+    "memory = InMemoryChatMessageHistory(session_id=\"test-session\")\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
     "        (\"system\", \"You are a helpful assistant.\"),\n",
@@ -456,24 +476,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "035e1253",
+   "execution_count": 10,
+   "id": "baca3dc6-678b-4509-9275-2fd653102898",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Hi Polly! The output of the magic_function for the input 3 is 5.\n",
+      "Hi Polly! The output of the magic_function for the input of 3 is 5.\n",
       "---\n",
       "Yes, your name is Polly!\n",
       "---\n",
-      "The output of the magic_function for the input 3 was 5.\n"
+      "The output of the magic_function for the input of 3 was 5.\n"
      ]
     }
    ],
    "source": [
-    "from langchain_core.messages import SystemMessage\n",
     "from langgraph.checkpoint import MemorySaver  # an in-memory checkpointer\n",
     "from langgraph.prebuilt import create_react_agent\n",
     "\n",
@@ -483,7 +502,7 @@
     "\n",
     "memory = MemorySaver()\n",
     "app = create_react_agent(\n",
-    "    model, tools, messages_modifier=system_message, checkpointer=memory\n",
+    "    model, tools, state_modifier=system_message, checkpointer=memory\n",
     ")\n",
     "\n",
     "config = {\"configurable\": {\"thread_id\": \"test-thread\"}}\n",
@@ -525,16 +544,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
-   "id": "d640feb3",
+   "execution_count": 11,
+   "id": "e62843c4-1107-41f0-a50b-aea256e28053",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])], tool_call_id='call_q9MgGFjqJbV2xSUX93WqxmOt')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])]}\n",
-      "{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-c68fd76f-a3c3-4c3c-bfd7-748c171ed4b8', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_q9MgGFjqJbV2xSUX93WqxmOt', 'index': 0}])], tool_call_id='call_q9MgGFjqJbV2xSUX93WqxmOt'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}\n",
+      "{'actions': [ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_1exy0rScfPmo4fy27FbQ5qJ2')], 'messages': [AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])]}\n",
+      "{'steps': [AgentStep(action=ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-5664e138-7085-4da7-a49e-5656a87b8d78', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_1exy0rScfPmo4fy27FbQ5qJ2', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_1exy0rScfPmo4fy27FbQ5qJ2'), observation=5)], 'messages': [FunctionMessage(content='5', name='magic_function')]}\n",
       "{'output': 'The value of `magic_function(3)` is 5.', 'messages': [AIMessage(content='The value of `magic_function(3)` is 5.')]}\n"
      ]
     }
@@ -585,23 +604,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "86abbe07",
+   "execution_count": 12,
+   "id": "076ebc85-f804-4093-a25a-a16334c9898e",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_yTjXXibj76tyFyPRa1soLo0S', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 70, 'total_tokens': 84}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b275f314-c42e-4e77-9dec-5c23f7dbd53b-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_yTjXXibj76tyFyPRa1soLo0S'}])]}}\n",
-      "{'tools': {'messages': [ToolMessage(content='5', name='magic_function', id='41c5f227-528d-4483-a313-b03b23b1d327', tool_call_id='call_yTjXXibj76tyFyPRa1soLo0S')]}}\n",
-      "{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 93, 'total_tokens': 107}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None}, id='run-0ef12b6e-415d-4758-9b62-5e5e1b350072-0')]}}\n"
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_my9rzFSKR4T1yYKwCsfbZB8A', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 61, 'total_tokens': 75}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_bc2a86f5f5', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-dd705555-8fae-4fb1-a033-5d99a23e3c22-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_my9rzFSKR4T1yYKwCsfbZB8A', 'type': 'tool_call'}], usage_metadata={'input_tokens': 61, 'output_tokens': 14, 'total_tokens': 75})]}}\n",
+      "{'tools': {'messages': [ToolMessage(content='5', name='magic_function', tool_call_id='call_my9rzFSKR4T1yYKwCsfbZB8A')]}}\n",
+      "{'agent': {'messages': [AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 84, 'total_tokens': 98}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-698cad05-8cb2-4d08-8c2a-881e354f6cc7-0', usage_metadata={'input_tokens': 84, 'output_tokens': 14, 'total_tokens': 98})]}}\n"
      ]
     }
    ],
    "source": [
-    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.prebuilt import create_react_agent\n",
+    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "prompt = ChatPromptTemplate.from_messages(\n",
     "    [\n",
@@ -611,12 +630,11 @@
     ")\n",
     "\n",
     "\n",
-    "def _modify_messages(messages: list[AnyMessage]):\n",
-    "    return prompt.invoke({\"messages\": messages}).to_messages()\n",
+    "def _modify_state_messages(state: AgentState):\n",
+    "    return prompt.invoke({\"messages\": state[\"messages\"]}).to_messages()\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
-    "\n",
+    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
     "\n",
     "for step in app.stream({\"messages\": [(\"human\", query)]}, stream_mode=\"updates\"):\n",
     "    print(step)"
@@ -637,14 +655,14 @@
   {
    "cell_type": "code",
    "execution_count": 12,
-   "id": "4eff44bc-a620-4c8a-97b1-268692a842bb",
+   "id": "a2f720f3-c121-4be2-b498-92c16bb44b0a",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls'}, id='run-837e794f-cfd8-40e0-8abc-4d98ced11b75', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_ABI4hftfEdnVgKyfF6OzZbca', 'index': 0}])], tool_call_id='call_ABI4hftfEdnVgKyfF6OzZbca'), 5)]\n"
+      "[(ToolAgentAction(tool='magic_function', tool_input={'input': 3}, log=\"\\nInvoking: `magic_function` with `{'input': 3}`\\n\\n\\n\", message_log=[AIMessageChunk(content='', additional_kwargs={'tool_calls': [{'index': 0, 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'finish_reason': 'tool_calls', 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518'}, id='run-a792db4a-278d-4090-82ae-904a30eada93', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'type': 'tool_call'}], tool_call_chunks=[{'name': 'magic_function', 'args': '{\"input\":3}', 'id': 'call_uPZ2D1Bo5mdED3gwgaeWURrf', 'index': 0, 'type': 'tool_call_chunk'}])], tool_call_id='call_uPZ2D1Bo5mdED3gwgaeWURrf'), 5)]\n"
      ]
     }
    ],
@@ -667,16 +685,16 @@
   {
    "cell_type": "code",
    "execution_count": 13,
-   "id": "4f4364ea-dffe-4d25-bdce-ef7d0020b880",
+   "id": "ef23117a-5ccb-42ce-80c3-ea49a9d3a942",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='0f63e437-c4d8-4da9-b6f5-b293ebfe4a64'),\n",
-       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_S96v28LlI6hNkQrNnIio0JPh', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-ffef7898-14b1-4537-ad90-7c000a8a5d25-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_S96v28LlI6hNkQrNnIio0JPh'}]),\n",
-       "  ToolMessage(content='5', name='magic_function', id='fbd9df4e-1dda-4d3e-9044-b001f7875476', tool_call_id='call_S96v28LlI6hNkQrNnIio0JPh'),\n",
-       "  AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 87, 'total_tokens': 101}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None}, id='run-e5d94c54-d9f4-45cd-be8e-a9101a8d88d6-0')]}"
+       "{'messages': [HumanMessage(content='what is the value of magic_function(3)?', id='cd7d0f49-a0e0-425a-b2b0-603a716058ed'),\n",
+       "  AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_VfZ9287DuybOSrBsQH5X12xf', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a1e965cd-bf61-44f9-aec1-8aaecb80955f-0', tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_VfZ9287DuybOSrBsQH5X12xf', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}),\n",
+       "  ToolMessage(content='5', name='magic_function', id='20d5c2fe-a5d8-47fa-9e04-5282642e2039', tool_call_id='call_VfZ9287DuybOSrBsQH5X12xf'),\n",
+       "  AIMessage(content='The value of `magic_function(3)` is 5.', response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 78, 'total_tokens': 92}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-abf9341c-ef41-4157-935d-a3be5dfa2f41-0', usage_metadata={'input_tokens': 78, 'output_tokens': 14, 'total_tokens': 92})]}"
       ]
      },
      "execution_count": 13,
@@ -708,7 +726,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 16,
    "id": "16f189a7-fc78-4cb5-aa16-a94ca06401a6",
    "metadata": {},
    "outputs": [],
@@ -724,7 +742,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 17,
    "id": "c96aefd7-6f6e-4670-aca6-1ac3d4e7871f",
    "metadata": {},
    "outputs": [
@@ -739,11 +757,7 @@
       "Invoking: `magic_function` with `{'input': '3'}`\n",
       "\n",
       "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3m\n",
-      "Invoking: `magic_function` with `{'input': '3'}`\n",
-      "responded: Parece que hubo un error al intentar obtener el valor de `magic_function(3)`. Permíteme intentarlo de nuevo.\n",
-      "\n",
-      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3mAún no puedo obtener el valor de `magic_function(3)`. ¿Hay algo más en lo que pueda ayudarte?\u001b[0m\n",
+      "\u001b[0m\u001b[36;1m\u001b[1;3mSorry, there was an error. Please try again.\u001b[0m\u001b[32;1m\u001b[1;3mParece que hubo un error al intentar calcular el valor de la función mágica. ¿Te gustaría que lo intente de nuevo?\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -752,10 +766,10 @@
      "data": {
       "text/plain": [
        "{'input': 'what is the value of magic_function(3)?',\n",
-       " 'output': 'Aún no puedo obtener el valor de `magic_function(3)`. ¿Hay algo más en lo que pueda ayudarte?'}"
+       " 'output': 'Parece que hubo un error al intentar calcular el valor de la función mágica. ¿Te gustaría que lo intente de nuevo?'}"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -797,7 +811,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 18,
    "id": "b974a91f-6ae8-4644-83d9-73666258a6db",
    "metadata": {},
    "outputs": [
@@ -805,12 +819,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "('human', 'what is the value of magic_function(3)?')\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_pFdKcCu5taDTtOOfX14vEDRp', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-25836468-ba7e-43be-a7cf-76bba06a2a08-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_pFdKcCu5taDTtOOfX14vEDRp'}]\n",
-      "content='Sorry, there was an error. Please try again.' name='magic_function' id='1a08b883-9c7b-4969-9e9b-67ce64cdcb5f' tool_call_id='call_pFdKcCu5taDTtOOfX14vEDRp'\n",
-      "content='It seems there was an error when trying to apply the magic function. Let me try again.' additional_kwargs={'tool_calls': [{'id': 'call_DA0lpDIkBFg2GHy4WsEcZG4K', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 34, 'prompt_tokens': 97, 'total_tokens': 131}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-d571b774-0ea3-4e35-8b7d-f32932c3f3cc-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_DA0lpDIkBFg2GHy4WsEcZG4K'}]\n",
-      "content='Sorry, there was an error. Please try again.' name='magic_function' id='0b45787b-c82a-487f-9a5a-de129c30460f' tool_call_id='call_DA0lpDIkBFg2GHy4WsEcZG4K'\n",
-      "content='It appears that there is a consistent issue when trying to apply the magic function to the input \"3.\" This could be due to various reasons, such as the input not being in the correct format or an internal error.\\n\\nIf you have any other questions or if there\\'s something else you\\'d like to try, please let me know!' response_metadata={'token_usage': {'completion_tokens': 66, 'prompt_tokens': 153, 'total_tokens': 219}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'stop', 'logprobs': None} id='run-50a962e6-21b7-4327-8dea-8e2304062627-0'\n"
+      "content='what is the value of magic_function(3)?' id='74e2d5e8-2b59-4820-979c-8d11ecfc14c2'\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_ihtrH6IG95pDXpKluIwAgi3J', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-5a35e465-8a08-43dd-ac8b-4a76dcace305-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_ihtrH6IG95pDXpKluIwAgi3J', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}\n",
+      "content='Sorry, there was an error. Please try again.' name='magic_function' id='8c37c19b-3586-46b1-aab9-a045786801a2' tool_call_id='call_ihtrH6IG95pDXpKluIwAgi3J'\n",
+      "content='It seems there was an error in processing the request. Let me try again.' additional_kwargs={'tool_calls': [{'id': 'call_iF0vYWAd6rfely0cXSqdMOnF', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 31, 'prompt_tokens': 88, 'total_tokens': 119}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-eb88ec77-d492-43a5-a5dd-4cefef9a6920-0' tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_iF0vYWAd6rfely0cXSqdMOnF', 'type': 'tool_call'}] usage_metadata={'input_tokens': 88, 'output_tokens': 31, 'total_tokens': 119}\n",
+      "content='Sorry, there was an error. Please try again.' name='magic_function' id='c9ff261f-a0f1-4c92-a9f2-cd749f62d911' tool_call_id='call_iF0vYWAd6rfely0cXSqdMOnF'\n",
+      "content='I am currently unable to process the request with the input \"3\" for the `magic_function`. If you have any other questions or need assistance with something else, please let me know!' response_metadata={'token_usage': {'completion_tokens': 39, 'prompt_tokens': 141, 'total_tokens': 180}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None} id='run-d42508aa-f286-4b57-80fb-f8a76736d470-0' usage_metadata={'input_tokens': 141, 'output_tokens': 39, 'total_tokens': 180}\n"
      ]
     }
    ],
@@ -847,7 +861,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 19,
    "id": "4b8498fc-a7af-4164-a401-d8714f082306",
    "metadata": {},
    "outputs": [
@@ -874,7 +888,7 @@
        " 'output': 'Agent stopped due to max iterations.'}"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -917,7 +931,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 20,
    "id": "a2b29113-e6be-4f91-aa4c-5c63dea3e423",
    "metadata": {},
    "outputs": [
@@ -925,7 +939,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_HaQkeCwD5QskzJzFixCBacZ4', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-596c9200-771f-436d-8576-72fcb81620f1-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_HaQkeCwD5QskzJzFixCBacZ4'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_FKiTkTd0Ffd4rkYSzERprf1M', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-b842f7b6-ec10-40f8-8c0e-baa220b77e91-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_FKiTkTd0Ffd4rkYSzERprf1M', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}\n",
       "------\n",
       "{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}\n"
      ]
@@ -956,7 +970,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 21,
    "id": "e9eb55f4-a321-4bac-b52d-9e43b411cf92",
    "metadata": {},
    "outputs": [
@@ -964,7 +978,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_4agJXUHtmHrOOMogjF6ZuzAv', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-a1c77db7-405f-43d9-8d57-751f2ca1a58c-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_4agJXUHtmHrOOMogjF6ZuzAv'}])]}}\n",
+      "{'agent': {'messages': [AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_WoOB8juagB08xrP38twYlYKR', 'function': {'arguments': '{\"input\":\"3\"}', 'name': 'magic_function'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-73dee47e-30ab-42c9-bb0c-6f227cac96cd-0', tool_calls=[{'name': 'magic_function', 'args': {'input': '3'}, 'id': 'call_WoOB8juagB08xrP38twYlYKR', 'type': 'tool_call'}], usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69})]}}\n",
       "------\n",
       "Task Cancelled.\n"
      ]
@@ -1005,7 +1019,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 22,
    "id": "3f6e2cf2",
    "metadata": {},
    "outputs": [
@@ -1067,7 +1081,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 23,
    "id": "73cabbc4",
    "metadata": {},
    "outputs": [
@@ -1075,10 +1089,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "('human', 'what is the value of magic_function(3)?')\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_bTURmOn9C8zslmn0kMFeykIn', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 64, 'total_tokens': 78}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-0844a504-7e6b-4ea6-a069-7017e38121ee-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_bTURmOn9C8zslmn0kMFeykIn'}]\n",
-      "content='Sorry there was an error, please try again.' name='magic_function' id='00d5386f-eb23-4628-9a29-d9ce6a7098cc' tool_call_id='call_bTURmOn9C8zslmn0kMFeykIn'\n",
-      "content='' additional_kwargs={'tool_calls': [{'id': 'call_JYqvvvWmXow2u012DuPoDHFV', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 96, 'total_tokens': 110}, 'model_name': 'gpt-4o', 'system_fingerprint': 'fp_729ea513f7', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-b73b1b1c-c829-4348-98cd-60b315c85448-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_JYqvvvWmXow2u012DuPoDHFV'}]\n",
+      "content='what is the value of magic_function(3)?' id='4fa7fbe5-758c-47a3-9268-717665d10680'\n",
+      "content='' additional_kwargs={'tool_calls': [{'id': 'call_ujE0IQBbIQnxcF9gsZXQfdhF', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 14, 'prompt_tokens': 55, 'total_tokens': 69}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-65d689aa-baee-4342-a5d2-048feefab418-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_ujE0IQBbIQnxcF9gsZXQfdhF', 'type': 'tool_call'}] usage_metadata={'input_tokens': 55, 'output_tokens': 14, 'total_tokens': 69}\n",
+      "content='Sorry there was an error, please try again.' name='magic_function' id='ef8ddf1d-9ad7-4ac0-b784-b673c4d94bbd' tool_call_id='call_ujE0IQBbIQnxcF9gsZXQfdhF'\n",
+      "content='It seems there was an issue with the previous attempt. Let me try that again.' additional_kwargs={'tool_calls': [{'id': 'call_GcsAfCFUHJ50BN2IOWnwTbQ7', 'function': {'arguments': '{\"input\":3}', 'name': 'magic_function'}, 'type': 'function'}]} response_metadata={'token_usage': {'completion_tokens': 32, 'prompt_tokens': 87, 'total_tokens': 119}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'tool_calls', 'logprobs': None} id='run-54527c4b-8ff0-4ee8-8abf-224886bd222e-0' tool_calls=[{'name': 'magic_function', 'args': {'input': 3}, 'id': 'call_GcsAfCFUHJ50BN2IOWnwTbQ7', 'type': 'tool_call'}] usage_metadata={'input_tokens': 87, 'output_tokens': 32, 'total_tokens': 119}\n",
       "{'input': 'what is the value of magic_function(3)?', 'output': 'Agent stopped due to max iterations.'}\n"
      ]
     }
@@ -1118,7 +1132,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 24,
    "id": "b94bb169",
    "metadata": {},
    "outputs": [
@@ -1216,12 +1230,12 @@
    "source": [
     "### In LangGraph\n",
     "\n",
-    "We can use the [`messages_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
+    "We can use the [`state_modifier`](https://langchain-ai.github.io/langgraph/reference/prebuilt/#create_react_agent) just as before when passing in [prompt templates](#prompt-templates)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 25,
    "id": "b309ba9a",
    "metadata": {},
    "outputs": [
@@ -1246,9 +1260,9 @@
     }
    ],
    "source": [
-    "from langchain_core.messages import AnyMessage\n",
     "from langgraph.errors import GraphRecursionError\n",
     "from langgraph.prebuilt import create_react_agent\n",
+    "from langgraph.prebuilt.chat_agent_executor import AgentState\n",
     "\n",
     "magic_step_num = 1\n",
     "\n",
@@ -1265,12 +1279,12 @@
     "tools = [magic_function]\n",
     "\n",
     "\n",
-    "def _modify_messages(messages: list[AnyMessage]):\n",
+    "def _modify_state_messages(state: AgentState):\n",
     "    # Give the agent amnesia, only keeping the original user query\n",
-    "    return [(\"system\", \"You are a helpful assistant\"), messages[0]]\n",
+    "    return [(\"system\", \"You are a helpful assistant\"), state[\"messages\"][0]]\n",
     "\n",
     "\n",
-    "app = create_react_agent(model, tools, messages_modifier=_modify_messages)\n",
+    "app = create_react_agent(model, tools, state_modifier=_modify_state_messages)\n",
     "\n",
     "try:\n",
     "    for step in app.stream({\"messages\": [(\"human\", query)]}, stream_mode=\"updates\"):\n",
@@ -1308,7 +1322,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.2"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/how_to/migrate_chains.ipynb

@@ -1,811 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "f331037f-be3f-4782-856f-d55dab952488",
-   "metadata": {},
-   "source": [
-    "# How to migrate chains to LCEL\n",
-    "\n",
-    ":::info Prerequisites\n",
-    "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [LangChain Expression Language](/docs/concepts#langchain-expression-language-lcel)\n",
-    "\n",
-    ":::\n",
-    "\n",
-    "LCEL is designed to streamline the process of building useful apps with LLMs and combining related components. It does this by providing:\n",
-    "\n",
-    "1. **A unified interface**: Every LCEL object implements the `Runnable` interface, which defines a common set of invocation methods (`invoke`, `batch`, `stream`, `ainvoke`, ...). This makes it possible to also automatically and consistently support useful operations like streaming of intermediate steps and batching, since every chain composed of LCEL objects is itself an LCEL object.\n",
-    "2. **Composition primitives**: LCEL provides a number of primitives that make it easy to compose chains, parallelize components, add fallbacks, dynamically configure chain internals, and more.\n",
-    "\n",
-    "LangChain maintains a number of legacy abstractions. Many of these can be reimplemented via short combinations of LCEL primitives. Doing so confers some general advantages:\n",
-    "\n",
-    "- The resulting chains typically implement the full `Runnable` interface, including streaming and asynchronous support where appropriate;\n",
-    "- The chains may be more easily extended or modified;\n",
-    "- The parameters of the chain are typically surfaced for easier customization (e.g., prompts) over previous versions, which tended to be subclasses and had opaque parameters and internals.\n",
-    "\n",
-    "The LCEL implementations can be slightly more verbose, but there are significant benefits in transparency and customizability.\n",
-    "\n",
-    "In this guide we review LCEL implementations of common legacy abstractions. Where appropriate, we link out to separate guides with more detail."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "b99b47ec",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "717c8673",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from getpass import getpass\n",
-    "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e3621b62-a037-42b8-8faa-59575608bb8b",
-   "metadata": {},
-   "source": [
-    "## `LLMChain`\n",
-    "<span data-heading-keywords=\"llmchain\"></span>\n",
-    "\n",
-    "[`LLMChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.llm.LLMChain.html) combined a prompt template, LLM, and output parser into a class.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Clarity around contents and parameters. The legacy `LLMChain` contains a default output parser and other options.\n",
-    "- Easier streaming. `LLMChain` only supports streaming via callbacks.\n",
-    "- Easier access to raw message outputs if desired. `LLMChain` only exposes these via a parameter or via callback.\n",
-    "\n",
-    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
-    "\n",
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "e628905c-430e-4e4a-9d7c-c91d2f42052e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'adjective': 'funny',\n",
-       " 'text': \"Why couldn't the bicycle find its way home?\\n\\nBecause it lost its bearings!\"}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import LLMChain\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
-    ")\n",
-    "\n",
-    "chain = LLMChain(llm=ChatOpenAI(), prompt=prompt)\n",
-    "\n",
-    "chain({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cdc3b527-c09e-4c77-9711-c3cc4506cd95",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "0d2a7cf8-1bc7-405c-bb0d-f2ab2ba3b6ab",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\""
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
-    ")\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "chain.invoke({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "3c0b0513-77b8-4371-a20e-3e487cec7e7f",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "Note that `LLMChain` by default returns a `dict` containing both the input and the output. If this behavior is desired, we can replicate it using another LCEL primitive, [`RunnablePassthrough`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html):"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "529206c5-abbe-4213-9e6c-3b8586c8000d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'adjective': 'funny',\n",
-       " 'text': \"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\"}"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "outer_chain = RunnablePassthrough().assign(text=chain)\n",
-    "\n",
-    "outer_chain.invoke({\"adjective\": \"funny\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "29d2e26c-2854-4971-9c2b-613450993921",
-   "metadata": {},
-   "source": [
-    "See [this tutorial](/docs/tutorials/llm_chain) for more detail on building with prompt templates, LLMs, and output parsers."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "00df631d-5121-4918-94aa-b88acce9b769",
-   "metadata": {},
-   "source": [
-    "## `ConversationChain`\n",
-    "<span data-heading-keywords=\"conversationchain\"></span>\n",
-    "\n",
-    "[`ConversationChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversation.base.ConversationChain.html) incorporates a memory of previous messages to sustain a stateful conversation.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Innate support for threads/separate sessions. To make this work with `ConversationChain`, you'd need to instantiate a separate memory class outside the chain.\n",
-    "- More explicit parameters. `ConversationChain` contains a hidden default prompt, which can cause confusion.\n",
-    "- Streaming support. `ConversationChain` only supports streaming via callbacks.\n",
-    "\n",
-    "`RunnableWithMessageHistory` implements sessions via configuration parameters. It should be instantiated with a callable that returns a [chat message history](https://api.python.langchain.com/en/latest/chat_history/langchain_core.chat_history.BaseChatMessageHistory.html). By default, it expects this function to take a single argument `session_id`.\n",
-    "\n",
-    "<ColumnContainer>\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "4f2cc6dc-d70a-4c13-9258-452f14290da6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'how are you?',\n",
-       " 'history': '',\n",
-       " 'response': \"Arrr, I be doin' well, me matey! Just sailin' the high seas in search of treasure and adventure. How can I assist ye today?\"}"
-      ]
-     },
-     "execution_count": 15,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import ConversationChain\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "template = \"\"\"\n",
-    "You are a pirate. Answer the following questions as best you can.\n",
-    "Chat history: {history}\n",
-    "Question: {input}\n",
-    "\"\"\"\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(template)\n",
-    "\n",
-    "memory = ConversationBufferMemory()\n",
-    "\n",
-    "chain = ConversationChain(\n",
-    "    llm=ChatOpenAI(),\n",
-    "    memory=memory,\n",
-    "    prompt=prompt,\n",
-    ")\n",
-    "\n",
-    "chain({\"input\": \"how are you?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f8e36b0e-c7dc-4130-a51b-189d4b756c7f",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "173e1a9c-2a18-4669-b0de-136f39197786",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "\"Arrr, I be doin' well, me heartie! Just sailin' the high seas in search of treasure and adventure. How be ye?\""
-      ]
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", \"You are a pirate. Answer the following questions as best you can.\"),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "history = InMemoryChatMessageHistory()\n",
-    "\n",
-    "\n",
-    "def get_history():\n",
-    "    return history\n",
-    "\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "wrapped_chain = RunnableWithMessageHistory(\n",
-    "    chain,\n",
-    "    get_history,\n",
-    "    history_messages_key=\"chat_history\",\n",
-    ")\n",
-    "\n",
-    "wrapped_chain.invoke({\"input\": \"how are you?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6b386ce6-895e-442c-88f3-7bec0ab9f401",
-   "metadata": {},
-   "source": [
-    "\n",
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "The above example uses the same `history` for all sessions. The example below shows how to use a different chat history for each session."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "4e05994f-1fbc-4699-bf2e-62cb0e4deeb8",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Ahoy matey! What can this old pirate do for ye today?'"
-      ]
-     },
-     "execution_count": 2,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.chat_history import BaseChatMessageHistory\n",
-    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
-    "\n",
-    "store = {}\n",
-    "\n",
-    "\n",
-    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
-    "    if session_id not in store:\n",
-    "        store[session_id] = InMemoryChatMessageHistory()\n",
-    "    return store[session_id]\n",
-    "\n",
-    "\n",
-    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
-    "\n",
-    "wrapped_chain = RunnableWithMessageHistory(\n",
-    "    chain,\n",
-    "    get_session_history,\n",
-    "    history_messages_key=\"chat_history\",\n",
-    ")\n",
-    "\n",
-    "wrapped_chain.invoke(\n",
-    "    {\"input\": \"Hello!\"},\n",
-    "    config={\"configurable\": {\"session_id\": \"abc123\"}},\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c36ebecb",
-   "metadata": {},
-   "source": [
-    "See [this tutorial](/docs/tutorials/chatbot) for a more end-to-end guide on building with [`RunnableWithMessageHistory`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html).\n",
-    "\n",
-    "## `RetrievalQA`\n",
-    "<span data-heading-keywords=\"retrievalqa\"></span>\n",
-    "\n",
-    "The [`RetrievalQA`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval_qa.base.RetrievalQA.html) chain performed natural-language question answering over a data source using retrieval-augmented generation.\n",
-    "\n",
-    "Some advantages of switching to the LCEL implementation are:\n",
-    "\n",
-    "- Easier customizability. Details such as the prompt and how documents are formatted are only configurable via specific parameters in the `RetrievalQA` chain.\n",
-    "- More easily return source documents.\n",
-    "- Support for runnable methods like streaming and async operations.\n",
-    "\n",
-    "Now let's look at them side-by-side. We'll use the same ingestion code to load a [blog post by Lilian Weng](https://lilianweng.github.io/posts/2023-06-23-agent/) on autonomous agents into a local vector store:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "1efbe16e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Load docs\n",
-    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
-    "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.vectorstores import FAISS\n",
-    "from langchain_openai.chat_models import ChatOpenAI\n",
-    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
-    "\n",
-    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
-    "data = loader.load()\n",
-    "\n",
-    "# Split\n",
-    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
-    "all_splits = text_splitter.split_documents(data)\n",
-    "\n",
-    "# Store splits\n",
-    "vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())\n",
-    "\n",
-    "# LLM\n",
-    "llm = ChatOpenAI()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c7e16438",
-   "metadata": {},
-   "source": [
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "43bf55a0",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'query': 'What are autonomous agents?',\n",
-       " 'result': 'Autonomous agents are LLM-empowered agents that handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. These agents can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs. They are capable of reasoning and planning ahead for complicated tasks by breaking them down into smaller steps.'}"
-      ]
-     },
-     "execution_count": 22,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.chains import RetrievalQA\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
-    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "\n",
-    "qa_chain = RetrievalQA.from_llm(\n",
-    "    llm, retriever=vectorstore.as_retriever(), prompt=prompt\n",
-    ")\n",
-    "\n",
-    "qa_chain(\"What are autonomous agents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "081948e5",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "9efcc931",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Autonomous agents are agents that can handle autonomous design, planning, and performance of complex tasks, such as scientific experiments. They can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other language model models. These agents use reasoning steps to develop solutions to specific tasks, like creating a novel anticancer drug.'"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
-    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "\n",
-    "\n",
-    "def format_docs(docs):\n",
-    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
-    "\n",
-    "\n",
-    "qa_chain = (\n",
-    "    {\n",
-    "        \"context\": vectorstore.as_retriever() | format_docs,\n",
-    "        \"question\": RunnablePassthrough(),\n",
-    "    }\n",
-    "    | prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "qa_chain.invoke(\"What are autonomous agents?\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "d6f44fe8",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "The LCEL implementation exposes the internals of what's happening around retrieving, formatting documents, and passing them through a prompt to the LLM, but it is more verbose. You can customize and wrap this composition logic in a helper function, or use the higher-level [`create_retrieval_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html) and [`create_stuff_documents_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.stuff.create_stuff_documents_chain.html) helper method:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "5fe42761",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'What are autonomous agents?',\n",
-       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content=\"LLM Powered Autonomous Agents | Lil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nPosts\\n\\n\\n\\n\\nArchive\\n\\n\\n\\n\\nSearch\\n\\n\\n\\n\\nTags\\n\\n\\n\\n\\nFAQ\\n\\n\\n\\n\\nemojisearch.app\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n      LLM Powered Autonomous Agents\\n    \\nDate: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng\\n\\n\\n \\n\\n\\nTable of Contents\\n\\n\\n\\nAgent System Overview\\n\\nComponent One: Planning\\n\\nTask Decomposition\\n\\nSelf-Reflection\\n\\n\\nComponent Two: Memory\\n\\nTypes of Memory\\n\\nMaximum Inner Product Search (MIPS)\", metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
-       " 'answer': 'Autonomous agents are entities that can operate independently, making decisions and taking actions without direct human intervention. These agents can perform tasks such as planning, executing complex experiments, and leveraging various tools and resources to achieve objectives. In the context provided, LLM-powered autonomous agents are specifically designed for scientific discovery, capable of handling tasks like designing novel anticancer drugs through reasoning steps.'}"
-      ]
-     },
-     "execution_count": 20,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "from langchain.chains import create_retrieval_chain\n",
-    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
-    "\n",
-    "# See full prompt at https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat\n",
-    "retrieval_qa_chat_prompt = hub.pull(\"langchain-ai/retrieval-qa-chat\")\n",
-    "\n",
-    "combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)\n",
-    "rag_chain = create_retrieval_chain(vectorstore.as_retriever(), combine_docs_chain)\n",
-    "\n",
-    "rag_chain.invoke({\"input\": \"What are autonomous agents?\"})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2772f4e9",
-   "metadata": {},
-   "source": [
-    "## `ConversationalRetrievalChain`\n",
-    "<span data-heading-keywords=\"conversationalretrievalchain\"></span>\n",
-    "\n",
-    "The [`ConversationalRetrievalChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain.html) was an all-in one way that combined retrieval-augmented generation with chat history, allowing you to \"chat with\" your documents.\n",
-    "\n",
-    "Advantages of switching to the LCEL implementation are similar to the `RetrievalQA` section above:\n",
-    "\n",
-    "- Clearer internals. The `ConversationalRetrievalChain` chain hides an entire question rephrasing step which dereferences the initial query against the chat history.\n",
-    "  - This means the class contains two sets of configurable prompts, LLMs, etc.\n",
-    "- More easily return source documents.\n",
-    "- Support for runnable methods like streaming and async operations.\n",
-    "\n",
-    "Here are side-by-side implementations with custom prompts. We'll reuse the loaded documents and vector store from the previous section:"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "8bc06416",
-   "metadata": {},
-   "source": [
-    "<ColumnContainer>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### Legacy"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 31,
-   "id": "54eb9576",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'question': 'What are autonomous agents?',\n",
-       " 'chat_history': '',\n",
-       " 'answer': 'Autonomous agents are powered by Large Language Models (LLMs) to handle tasks like scientific discovery and complex experiments autonomously. These agents can browse the internet, read documentation, execute code, and leverage other LLMs to perform tasks. They can reason and plan ahead to decompose complicated tasks into manageable steps.'}"
-      ]
-     },
-     "execution_count": 31,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import ConversationalRetrievalChain\n",
-    "\n",
-    "condense_question_template = \"\"\"\n",
-    "Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "Follow Up Input: {question}\n",
-    "Standalone question:\"\"\"\n",
-    "\n",
-    "condense_question_prompt = ChatPromptTemplate.from_template(condense_question_template)\n",
-    "\n",
-    "qa_template = \"\"\"\n",
-    "You are an assistant for question-answering tasks.\n",
-    "Use the following pieces of retrieved context to answer\n",
-    "the question. If you don't know the answer, say that you\n",
-    "don't know. Use three sentences maximum and keep the\n",
-    "answer concise.\n",
-    "\n",
-    "Chat History:\n",
-    "{chat_history}\n",
-    "\n",
-    "Other context:\n",
-    "{context}\n",
-    "\n",
-    "Question: {question}\n",
-    "\"\"\"\n",
-    "\n",
-    "qa_prompt = ChatPromptTemplate.from_template(qa_template)\n",
-    "\n",
-    "convo_qa_chain = ConversationalRetrievalChain.from_llm(\n",
-    "    llm,\n",
-    "    vectorstore.as_retriever(),\n",
-    "    condense_question_prompt=condense_question_prompt,\n",
-    "    combine_docs_chain_kwargs={\n",
-    "        \"prompt\": qa_prompt,\n",
-    "    },\n",
-    ")\n",
-    "\n",
-    "convo_qa_chain(\n",
-    "    {\n",
-    "        \"question\": \"What are autonomous agents?\",\n",
-    "        \"chat_history\": \"\",\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "43a8a23c",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "<Column>\n",
-    "\n",
-    "#### LCEL\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 25,
-   "id": "c884b138",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'input': 'What are autonomous agents?',\n",
-       " 'chat_history': [],\n",
-       " 'context': [Document(page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}),\n",
-       "  Document(page_content='Or\\n@article{weng2023agent,\\n  title   = \"LLM-powered Autonomous Agents\",\\n  author  = \"Weng, Lilian\",\\n  journal = \"lilianweng.github.io\",\\n  year    = \"2023\",\\n  month   = \"Jun\",\\n  url     = \"https://lilianweng.github.io/posts/2023-06-23-agent/\"\\n}\\nReferences#\\n[1] Wei et al. “Chain of thought prompting elicits reasoning in large language models.” NeurIPS 2022\\n[2] Yao et al. “Tree of Thoughts: Dliberate Problem Solving with Large Language Models.” arXiv preprint arXiv:2305.10601 (2023).', metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'})],\n",
-       " 'answer': 'Autonomous agents are entities capable of acting independently, making decisions, and performing tasks without direct human intervention. These agents can interact with their environment, perceive information, and take actions based on their goals or objectives. They often use artificial intelligence techniques to navigate and accomplish tasks in complex or dynamic environments.'}"
-      ]
-     },
-     "execution_count": 25,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain.chains import create_history_aware_retriever, create_retrieval_chain\n",
-    "\n",
-    "condense_question_system_template = (\n",
-    "    \"Given a chat history and the latest user question \"\n",
-    "    \"which might reference context in the chat history, \"\n",
-    "    \"formulate a standalone question which can be understood \"\n",
-    "    \"without the chat history. Do NOT answer the question, \"\n",
-    "    \"just reformulate it if needed and otherwise return it as is.\"\n",
-    ")\n",
-    "\n",
-    "condense_question_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", condense_question_system_template),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "history_aware_retriever = create_history_aware_retriever(\n",
-    "    llm, vectorstore.as_retriever(), condense_question_prompt\n",
-    ")\n",
-    "\n",
-    "system_prompt = (\n",
-    "    \"You are an assistant for question-answering tasks. \"\n",
-    "    \"Use the following pieces of retrieved context to answer \"\n",
-    "    \"the question. If you don't know the answer, say that you \"\n",
-    "    \"don't know. Use three sentences maximum and keep the \"\n",
-    "    \"answer concise.\"\n",
-    "    \"\\n\\n\"\n",
-    "    \"{context}\"\n",
-    ")\n",
-    "\n",
-    "qa_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\"system\", system_prompt),\n",
-    "        (\"placeholder\", \"{chat_history}\"),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "qa_chain = create_stuff_documents_chain(llm, qa_prompt)\n",
-    "\n",
-    "convo_qa_chain = create_retrieval_chain(history_aware_retriever, qa_chain)\n",
-    "\n",
-    "convo_qa_chain.invoke(\n",
-    "    {\n",
-    "        \"input\": \"What are autonomous agents?\",\n",
-    "        \"chat_history\": [],\n",
-    "    }\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b2717810",
-   "metadata": {},
-   "source": [
-    "</Column>\n",
-    "\n",
-    "</ColumnContainer>\n",
-    "\n",
-    "## Next steps\n",
-    "\n",
-    "You've now seen how to migrate existing usage of some legacy chains to LCEL.\n",
-    "\n",
-    "Next, check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.10.4"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

docs/docs/how_to/pydantic_compatibility.md

@@ -1,27 +1,97 @@
 # How to use LangChain with different Pydantic versions
 
-- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/)
-- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/)
-- Pydantic v2 and v1 are under the same package name, so both versions cannot be installed at the same time
+- Pydantic v2 was released in June, 2023 (https://docs.pydantic.dev/2.0/blog/pydantic-v2-final/).
+- v2 contains has a number of breaking changes (https://docs.pydantic.dev/2.0/migration/).
+- Pydantic 1 End of Life was in June 2024. LangChain will be dropping support for Pydantic 1 in the near future,
+and likely migrating internally to Pydantic 2. The timeline is tentatively September. This change will be accompanied by a minor version bump in the main langchain packages to version 0.3.x.
 
-## LangChain Pydantic migration plan
+As of `langchain>=0.0.267`, LangChain allows users to install either Pydantic V1 or V2.
 
-As of `langchain>=0.0.267`, LangChain will allow users to install either Pydantic V1 or V2. 
-   * Internally LangChain will continue to [use V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features).
-   * During this time, users can pin their pydantic version to v1 to avoid breaking changes, or start a partial
-   migration using pydantic v2 throughout their code, but avoiding mixing v1 and v2 code for LangChain (see below).
+Internally, LangChain continues to use the [Pydantic V1](https://docs.pydantic.dev/latest/migration/#continue-using-pydantic-v1-features) via
+the v1 namespace of Pydantic 2.
 
-User can either pin to pydantic v1, and upgrade their code in one go once LangChain has migrated to v2 internally, or they can start a partial migration to v2, but must avoid mixing v1 and v2 code for LangChain.
+Because Pydantic does not support mixing .v1 and .v2 objects, users should be aware of a number of issues
+when using LangChain with Pydantic.
+
+## 1. Passing Pydantic objects to LangChain APIs
+
+Most LangChain APIs that accept Pydantic objects have been updated to accept both Pydantic v1 and v2 objects.
+
+* Pydantic v1 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 1` is installed or subclasses of `pydantic.v1.BaseModel` if `pydantic 2` is installed.
+* Pydantic v2 objects correspond to subclasses of `pydantic.BaseModel` if `pydantic 2` is installed.
+
+
+| API                                    | Pydantic 1 | Pydantic 2                                                     |
+|----------------------------------------|------------|----------------------------------------------------------------|
+| `BaseChatModel.bind_tools`             | Yes        | langchain-core>=0.2.23, appropriate version of partner package |
+| `BaseChatModel.with_structured_output` | Yes        | langchain-core>=0.2.23, appropriate version of partner package |
+| `Tool.from_function`                   | Yes        | langchain-core>=0.2.23                                         |
+| `StructuredTool.from_function`         | Yes        | langchain-core>=0.2.23                                         |
+
+
+Partner packages that accept pydantic v2 objects via `bind_tools` or `with_structured_output` APIs:
+
+| Package Name        | pydantic v1 | pydantic v2 |
+|---------------------|-------------|-------------|
+| langchain-mistralai | Yes         | >=0.1.11    |
+| langchain-anthropic | Yes         | >=0.1.21    |
+| langchain-robocorp  | Yes         | >=0.0.10    |
+| langchain-openai    | Yes         | >=0.1.19    |
+| langchain-fireworks | Yes         | >=0.1.5     |
+
+Additional partner packages will be updated to accept Pydantic v2 objects in the future.
+
+If you are still seeing issues with these APIs or other APIs that accept Pydantic objects, please open an issue, and we'll
+address it.
+
+Example:
+
+Prior to `langchain-core<0.2.23`, use Pydantic v1 objects when passing to LangChain APIs.
+
+
+```python
+from langchain_openai import ChatOpenAI
+from pydantic.v1 import BaseModel # <-- Note v1 namespace
+
+class Person(BaseModel):
+    """Personal information"""
+    name: str
+    
+model = ChatOpenAI()
+model = model.with_structured_output(Person)
+
+model.invoke('Bob is a person.')
+```
+
+After `langchain-core>=0.2.23`, use either Pydantic v1 or v2 objects when passing to LangChain APIs.
+
+```python
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel
+
+class Person(BaseModel):
+    """Personal information"""
+    name: str
+    
+    
+model = ChatOpenAI()
+model = model.with_structured_output(Person)
+
+model.invoke('Bob is a person.')
+```
+
+## 2. Sub-classing LangChain models
+
+Because LangChain internally uses Pydantic v1, if you are sub-classing LangChain models, you should use Pydantic v1
+primitives.
 
-Below are two examples of showing how to avoid mixing pydantic v1 and v2 code in
-the case of inheritance and in the case of passing objects to LangChain.
 
 **Example 1: Extending via inheritance**
 
 **YES** 
 
 ```python
-from pydantic.v1 import root_validator, validator
+from pydantic.v1 import validator
 from langchain_core.tools import BaseTool
 
 class CustomTool(BaseTool): # BaseTool is v1 code
@@ -70,38 +140,33 @@ CustomTool(
 )
 ```
 
-**Example 2: Passing objects to LangChain**
 
-**YES**
+## 3. Disable run-time validation for LangChain objects used inside Pydantic v2 models
+
+e.g.,
 
 ```python
-from langchain_core.tools import Tool
-from pydantic.v1 import BaseModel, Field # <-- Uses v1 namespace
+from typing import Annotated
 
-class CalculatorInput(BaseModel):
-    question: str = Field()
+from langchain_openai import ChatOpenAI # <-- ChatOpenAI uses pydantic v1
+from pydantic import BaseModel, SkipValidation
 
-Tool.from_function( # <-- tool uses v1 namespace
-    func=lambda question: 'hello',
-    name="Calculator",
-    description="useful for when you need to answer questions about math",
-    args_schema=CalculatorInput
-)
+
+class Foo(BaseModel): # <-- BaseModel is from Pydantic v2
+    model: Annotated[ChatOpenAI, SkipValidation()]
+
+Foo(model=ChatOpenAI(api_key="hello"))
 ```
 
-**NO**
+## 4: LangServe cannot generate OpenAPI docs if running Pydantic 2
 
-```python
-from langchain_core.tools import Tool
-from pydantic import BaseModel, Field # <-- Uses v2 namespace
+If you are using Pydantic 2, you will not be able to generate OpenAPI docs using LangServe.
 
-class CalculatorInput(BaseModel):
-    question: str = Field()
+If you need OpenAPI docs, your options are to either install Pydantic 1:
 
-Tool.from_function( # <-- tool uses v1 namespace
-    func=lambda question: 'hello',
-    name="Calculator",
-    description="useful for when you need to answer questions about math",
-    args_schema=CalculatorInput
-)
-```
+`pip install pydantic==1.10.17`
+
+or else to use the `APIHandler` object in LangChain to manually create the
+routes for your API.
+
+See: https://python.langchain.com/v0.2/docs/langserve/#pydantic

docs/docs/how_to/structured_output.ipynb

@@ -43,7 +43,7 @@
     "\n",
     "This is the easiest and most reliable way to get structured outputs. `with_structured_output()` is implemented for models that provide native APIs for structuring outputs, like tool/function calling or JSON mode, and makes use of these capabilities under the hood.\n",
     "\n",
-    "This method takes a schema as input which specifies the names, types, and descriptions of the desired output attributes. The method returns a model-like Runnable, except that instead of outputting strings or Messages it outputs objects corresponding to the given schema. The schema can be specified as a [JSON Schema](https://json-schema.org/) or a Pydantic class. If JSON Schema is used then a dictionary will be returned by the Runnable, and if a Pydantic class is used then Pydantic objects will be returned.\n",
+    "This method takes a schema as input which specifies the names, types, and descriptions of the desired output attributes. The method returns a model-like Runnable, except that instead of outputting strings or Messages it outputs objects corresponding to the given schema. The schema can be specified as a TypedDict class, [JSON Schema](https://json-schema.org/) or a Pydantic class. If TypedDict or JSON Schema are used then a dictionary will be returned by the Runnable, and if a Pydantic class is used then a Pydantic object will be returned.\n",
     "\n",
     "As an example, let's get a model to generate a joke and separate the setup from the punchline:\n",
     "\n",
@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "6d55008f",
    "metadata": {},
    "outputs": [],
@@ -68,7 +68,7 @@
     "\n",
     "from langchain_openai import ChatOpenAI\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-4-0125-preview\", temperature=0)"
+    "llm = ChatOpenAI(model=\"gpt-4o\", temperature=0)"
    ]
   },
   {
@@ -76,22 +76,24 @@
    "id": "a808a401-be1f-49f9-ad13-58dd68f7db5f",
    "metadata": {},
    "source": [
-    "If we want the model to return a Pydantic object, we just need to pass in the desired Pydantic class:"
+    "### Pydantic class\n",
+    "\n",
+    "If we want the model to return a Pydantic object, we just need to pass in the desired Pydantic class. The key advantage of using Pydantic is that the model-generated output will be validated. Pydantic will raise an error if any required fields are missing or if any fields are of the wrong type."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "070bf702",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=8)"
+       "Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=7)"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -102,12 +104,15 @@
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",
     "\n",
     "\n",
+    "# Pydantic\n",
     "class Joke(BaseModel):\n",
     "    \"\"\"Joke to tell user.\"\"\"\n",
     "\n",
     "    setup: str = Field(description=\"The setup of the joke\")\n",
     "    punchline: str = Field(description=\"The punchline to the joke\")\n",
-    "    rating: Optional[int] = Field(description=\"How funny the joke is, from 1 to 10\")\n",
+    "    rating: Optional[int] = Field(\n",
+    "        default=None, description=\"How funny the joke is, from 1 to 10\"\n",
+    "    )\n",
     "\n",
     "\n",
     "structured_llm = llm.with_structured_output(Joke)\n",
@@ -130,12 +135,73 @@
    "id": "deddb6d3",
    "metadata": {},
    "source": [
-    "We can also pass in a [JSON Schema](https://json-schema.org/) dict if you prefer not to use Pydantic. In this case, the response is also a dict:"
+    "### TypedDict or JSON Schema\n",
+    "\n",
+    "If you don't want to use Pydantic, explicitly don't want validation of the arguments, or want to be able to stream the model outputs, you can define your schema using a TypedDict class. We can optionally use a special `Annotated` syntax supported by LangChain that allows you to specify the default value and description of a field. Note, the default value is *not* filled in automatically if the model doesn't generate it, it is only used in defining the schema that is passed to the model.\n",
+    "\n",
+    ":::info Requirements\n",
+    "\n",
+    "- Core: `langchain-core>=0.2.26`\n",
+    "- Typing extensions: It is highly recommended to import `Annotated` and `TypedDict` from `typing_extensions` instead of `typing` to ensure consistent behavior across Python versions.\n",
+    "\n",
+    ":::"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 8,
+   "id": "70d82891-42e8-424a-919e-07d83bcfec61",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'setup': 'Why was the cat sitting on the computer?',\n",
+       " 'punchline': 'Because it wanted to keep an eye on the mouse!',\n",
+       " 'rating': 7}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from typing_extensions import Annotated, TypedDict\n",
+    "\n",
+    "\n",
+    "# TypedDict\n",
+    "class Joke(TypedDict):\n",
+    "    \"\"\"Joke to tell user.\"\"\"\n",
+    "\n",
+    "    setup: Annotated[str, ..., \"The setup of the joke\"]\n",
+    "\n",
+    "    # Alternatively, we could have specified setup as:\n",
+    "\n",
+    "    # setup: str                    # no default, no description\n",
+    "    # setup: Annotated[str, ...]    # no default, no description\n",
+    "    # setup: Annotated[str, \"foo\"]  # default, no description\n",
+    "\n",
+    "    punchline: Annotated[str, ..., \"The punchline of the joke\"]\n",
+    "    rating: Annotated[Optional[int], None, \"How funny the joke is, from 1 to 10\"]\n",
+    "\n",
+    "\n",
+    "structured_llm = llm.with_structured_output(Joke)\n",
+    "\n",
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e4d7b4dc-f617-4ea8-aa58-847c228791b4",
+   "metadata": {},
+   "source": [
+    "Equivalently, we can pass in a [JSON Schema](https://json-schema.org/) dict. This requires no imports or classes and makes it very clear exactly how each parameter is documented, at the cost of being a bit more verbose."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "id": "6700994a",
    "metadata": {},
    "outputs": [
@@ -144,10 +210,10 @@
       "text/plain": [
        "{'setup': 'Why was the cat sitting on the computer?',\n",
        " 'punchline': 'Because it wanted to keep an eye on the mouse!',\n",
-       " 'rating': 8}"
+       " 'rating': 7}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -169,6 +235,7 @@
     "        \"rating\": {\n",
     "            \"type\": \"integer\",\n",
     "            \"description\": \"How funny the joke is, from 1 to 10\",\n",
+    "            \"default\": None,\n",
     "        },\n",
     "    },\n",
     "    \"required\": [\"setup\", \"punchline\"],\n",
@@ -185,7 +252,7 @@
    "source": [
     "### Choosing between multiple schemas\n",
     "\n",
-    "The simplest way to let the model choose from multiple schemas is to create a parent Pydantic class that has a Union-typed attribute:"
+    "The simplest way to let the model choose from multiple schemas is to create a parent schema that has a Union-typed attribute:"
    ]
   },
   {
@@ -209,6 +276,17 @@
     "from typing import Union\n",
     "\n",
     "\n",
+    "# Pydantic\n",
+    "class Joke(BaseModel):\n",
+    "    \"\"\"Joke to tell user.\"\"\"\n",
+    "\n",
+    "    setup: str = Field(description=\"The setup of the joke\")\n",
+    "    punchline: str = Field(description=\"The punchline to the joke\")\n",
+    "    rating: Optional[int] = Field(\n",
+    "        default=None, description=\"How funny the joke is, from 1 to 10\"\n",
+    "    )\n",
+    "\n",
+    "\n",
     "class ConversationalResponse(BaseModel):\n",
     "    \"\"\"Respond in a conversational manner. Be kind and helpful.\"\"\"\n",
     "\n",
@@ -260,7 +338,7 @@
    "source": [
     "### Streaming\n",
     "\n",
-    "We can stream outputs from our structured model when the output type is a dict (i.e., when the schema is specified as a JSON Schema dict). \n",
+    "We can stream outputs from our structured model when the output type is a dict (i.e., when the schema is specified as a TypedDict class or  JSON Schema dict). \n",
     "\n",
     ":::info\n",
     "\n",
@@ -271,7 +349,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 9,
    "id": "aff89877-28a3-472f-a1aa-eff893fe7736",
    "metadata": {},
    "outputs": [
@@ -302,12 +380,24 @@
       "{'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the'}\n",
       "{'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse'}\n",
       "{'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!'}\n",
-      "{'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!', 'rating': 8}\n"
+      "{'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!', 'rating': 7}\n"
      ]
     }
    ],
    "source": [
-    "structured_llm = llm.with_structured_output(json_schema)\n",
+    "from typing_extensions import Annotated, TypedDict\n",
+    "\n",
+    "\n",
+    "# TypedDict\n",
+    "class Joke(TypedDict):\n",
+    "    \"\"\"Joke to tell user.\"\"\"\n",
+    "\n",
+    "    setup: Annotated[str, ..., \"The setup of the joke\"]\n",
+    "    punchline: Annotated[str, ..., \"The punchline of the joke\"]\n",
+    "    rating: Annotated[Optional[int], None, \"How funny the joke is, from 1 to 10\"]\n",
+    "\n",
+    "\n",
+    "structured_llm = llm.with_structured_output(Joke)\n",
     "\n",
     "for chunk in structured_llm.stream(\"Tell me a joke about cats\"):\n",
     "    print(chunk)"
@@ -327,7 +417,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 11,
    "id": "283ba784-2072-47ee-9b2c-1119e3c69e8e",
    "metadata": {},
    "outputs": [
@@ -335,11 +425,11 @@
      "data": {
       "text/plain": [
        "{'setup': 'Woodpecker',\n",
-       " 'punchline': \"Woodpecker goes 'knock knock', but don't worry, they never expect you to answer the door!\",\n",
-       " 'rating': 8}"
+       " 'punchline': \"Woodpecker who? Woodpecker who can't find a tree is just a bird with a headache!\",\n",
+       " 'rating': 7}"
       ]
      },
-     "execution_count": 47,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -377,7 +467,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 12,
    "id": "d7381cb0-b2c3-4302-a319-ed72d0b9e43f",
    "metadata": {},
    "outputs": [
@@ -385,11 +475,11 @@
      "data": {
       "text/plain": [
        "{'setup': 'Crocodile',\n",
-       " 'punchline': \"Crocodile 'see you later', but in a while, it becomes an alligator!\",\n",
+       " 'punchline': 'Crocodile be seeing you later, alligator!',\n",
        " 'rating': 7}"
       ]
      },
-     "execution_count": 46,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -491,23 +581,24 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 15,
    "id": "df0370e3",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=None)"
+       "{'setup': 'Why was the cat sitting on the computer?',\n",
+       " 'punchline': 'Because it wanted to keep an eye on the mouse!'}"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "structured_llm = llm.with_structured_output(Joke, method=\"json_mode\")\n",
+    "structured_llm = llm.with_structured_output(None, method=\"json_mode\")\n",
     "\n",
     "structured_llm.invoke(\n",
     "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
@@ -526,19 +617,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 17,
    "id": "10ed2842",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_ASK4EmZeZ69Fi3p554Mb4rWy', 'function': {'arguments': '{\"setup\":\"Why was the cat sitting on the computer?\",\"punchline\":\"Because it wanted to keep an eye on the mouse!\"}', 'name': 'Joke'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 36, 'prompt_tokens': 107, 'total_tokens': 143}, 'model_name': 'gpt-4-0125-preview', 'system_fingerprint': None, 'finish_reason': 'stop', 'logprobs': None}, id='run-6491d35b-9164-4656-b75c-d7882cfb76cb-0', tool_calls=[{'name': 'Joke', 'args': {'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!'}, 'id': 'call_ASK4EmZeZ69Fi3p554Mb4rWy'}], usage_metadata={'input_tokens': 107, 'output_tokens': 36, 'total_tokens': 143}),\n",
-       " 'parsed': Joke(setup='Why was the cat sitting on the computer?', punchline='Because it wanted to keep an eye on the mouse!', rating=None),\n",
+       "{'raw': AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_f25ZRmh8u5vHlOWfTUw8sJFZ', 'function': {'arguments': '{\"setup\":\"Why was the cat sitting on the computer?\",\"punchline\":\"Because it wanted to keep an eye on the mouse!\",\"rating\":7}', 'name': 'Joke'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 33, 'prompt_tokens': 93, 'total_tokens': 126}, 'model_name': 'gpt-4o-2024-05-13', 'system_fingerprint': 'fp_4e2b2da518', 'finish_reason': 'stop', 'logprobs': None}, id='run-d880d7e2-df08-4e9e-ad92-dfc29f2fd52f-0', tool_calls=[{'name': 'Joke', 'args': {'setup': 'Why was the cat sitting on the computer?', 'punchline': 'Because it wanted to keep an eye on the mouse!', 'rating': 7}, 'id': 'call_f25ZRmh8u5vHlOWfTUw8sJFZ', 'type': 'tool_call'}], usage_metadata={'input_tokens': 93, 'output_tokens': 33, 'total_tokens': 126}),\n",
+       " 'parsed': {'setup': 'Why was the cat sitting on the computer?',\n",
+       "  'punchline': 'Because it wanted to keep an eye on the mouse!',\n",
+       "  'rating': 7},\n",
        " 'parsing_error': None}"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -546,9 +639,7 @@
    "source": [
     "structured_llm = llm.with_structured_output(Joke, include_raw=True)\n",
     "\n",
-    "structured_llm.invoke(\n",
-    "    \"Tell me a joke about cats, respond in JSON with `setup` and `punchline` keys\"\n",
-    ")"
+    "structured_llm.invoke(\"Tell me a joke about cats\")"
    ]
   },
   {
@@ -824,7 +915,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -838,7 +929,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_calling.ipynb

@@ -24,10 +24,9 @@
     "This guide assumes familiarity with the following concepts:\n",
     "\n",
     "- [Chat models](/docs/concepts/#chat-models)\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
     "- [Tool calling](/docs/concepts/#functiontool-calling)\n",
+    "- [Tools](/docs/concepts/#tools)\n",
     "- [Output parsers](/docs/concepts/#output-parsers)\n",
-    "\n",
     ":::\n",
     "\n",
     "[Tool calling](/docs/concepts/#functiontool-calling) allows a chat model to respond to a given prompt by \"calling a tool\".\n",
@@ -38,15 +37,11 @@
     "\n",
     "![Diagram of calling a tool](/img/tool_call.png)\n",
     "\n",
-    "If you want to see how to use the model-generated tool call to actually run a tool function [check out this guide](/docs/how_to/tool_results_pass_to_model/).\n",
+    "If you want to see how to use the model-generated tool call to actually run a tool [check out this guide](/docs/how_to/tool_results_pass_to_model/).\n",
     "\n",
     ":::note Supported models\n",
     "\n",
-    "Tool calling is not universal, but is supported by many popular LLM providers, including [Anthropic](/docs/integrations/chat/anthropic/), \n",
-    "[Cohere](/docs/integrations/chat/cohere/), [Google](/docs/integrations/chat/google_vertex_ai_palm/), \n",
-    "[Mistral](/docs/integrations/chat/mistralai/), [OpenAI](/docs/integrations/chat/openai/), and even for locally-running models via [Ollama](/docs/integrations/chat/ollama/).\n",
-    "\n",
-    "You can find a [list of all models that support tool calling here](/docs/integrations/chat/).\n",
+    "Tool calling is not universal, but is supported by many popular LLM providers. You can find a [list of all models that support tool calling here](/docs/integrations/chat/).\n",
     "\n",
     ":::\n",
     "\n",
@@ -58,14 +53,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Passing tools to chat models\n",
+    "## Defining tool schemas\n",
     "\n",
-    "Chat models that support tool calling features implement a `.bind_tools` method, which \n",
-    "receives a list of functions, Pydantic models, or LangChain [tool objects](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool) \n",
-    "and binds them to the chat model in its expected format. Subsequent invocations of the \n",
-    "chat model will include tool schemas in its calls to the LLM.\n",
+    "For a model to be able to call tools, we need to pass in tool schemas that describe what the tool does and what it's arguments are. Chat models that support tool calling features implement a `.bind_tools()` method for passing tool schemas to the model. Tool schemas can be passed in as Python functions (with typehints and docstrings), Pydantic models, TypedDict classes, or LangChain [Tool objects](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseTool.html#langchain_core.tools.BaseTool). Subsequent invocations of the model will pass in these tool schemas along with the prompt.\n",
     "\n",
-    "For example, below we implement simple tools for arithmetic:"
+    "### Python functions\n",
+    "Our tool schemas can be Python functions:"
    ]
   },
   {
@@ -74,26 +67,41 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# The function name, type hints, and docstring are all part of the tool\n",
+    "# schema that's passed to the model. Defining good, descriptive schemas\n",
+    "# is an extension of prompt engineering and is an important part of\n",
+    "# getting models to perform well.\n",
     "def add(a: int, b: int) -> int:\n",
-    "    \"\"\"Adds a and b.\"\"\"\n",
+    "    \"\"\"Add two integers.\n",
+    "\n",
+    "    Args:\n",
+    "        a: First integer\n",
+    "        b: Second integer\n",
+    "    \"\"\"\n",
     "    return a + b\n",
     "\n",
     "\n",
     "def multiply(a: int, b: int) -> int:\n",
-    "    \"\"\"Multiplies a and b.\"\"\"\n",
-    "    return a * b\n",
+    "    \"\"\"Multiply two integers.\n",
     "\n",
-    "\n",
-    "tools = [add, multiply]"
+    "    Args:\n",
+    "        a: First integer\n",
+    "        b: Second integer\n",
+    "    \"\"\"\n",
+    "    return a * b"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "### LangChain Tool\n",
+    "\n",
     "LangChain also implements a `@tool` decorator that allows for further control of the tool schema, such as tool names and argument descriptions. See the how-to guide [here](/docs/how_to/custom_tools/#creating-tools-from-functions) for details.\n",
     "\n",
-    "We can also define the schemas without the accompanying functions using [Pydantic](https://docs.pydantic.dev):"
+    "### Pydantic class\n",
+    "\n",
+    "You can equivalently define the schemas without the accompanying functions using [Pydantic](https://docs.pydantic.dev):"
    ]
   },
   {
@@ -105,23 +113,57 @@
     "from langchain_core.pydantic_v1 import BaseModel, Field\n",
     "\n",
     "\n",
-    "# Note that the docstrings here are crucial, as they will be passed along\n",
-    "# to the model along with the class name.\n",
-    "class Add(BaseModel):\n",
-    "    \"\"\"Add two integers together.\"\"\"\n",
+    "class add(BaseModel):\n",
+    "    \"\"\"Add two integers.\"\"\"\n",
     "\n",
     "    a: int = Field(..., description=\"First integer\")\n",
     "    b: int = Field(..., description=\"Second integer\")\n",
     "\n",
     "\n",
-    "class Multiply(BaseModel):\n",
-    "    \"\"\"Multiply two integers together.\"\"\"\n",
+    "class multiply(BaseModel):\n",
+    "    \"\"\"Multiply two integers.\"\"\"\n",
     "\n",
     "    a: int = Field(..., description=\"First integer\")\n",
-    "    b: int = Field(..., description=\"Second integer\")\n",
+    "    b: int = Field(..., description=\"Second integer\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### TypedDict class\n",
+    "\n",
+    ":::info Requires `langchain-core>=0.2.25`\n",
+    ":::\n",
+    "\n",
+    "Or using TypedDicts and annotations:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing_extensions import Annotated, TypedDict\n",
     "\n",
     "\n",
-    "tools = [Add, Multiply]"
+    "class add(TypedDict):\n",
+    "    \"\"\"Add two integers.\"\"\"\n",
+    "\n",
+    "    # Annotations must have the type and can optionally include a default value and description (in that order).\n",
+    "    a: Annotated[int, ..., \"First integer\"]\n",
+    "    b: Annotated[int, ..., \"Second integer\"]\n",
+    "\n",
+    "\n",
+    "class multiply(BaseModel):\n",
+    "    \"\"\"Multiply two integers.\"\"\"\n",
+    "\n",
+    "    a: Annotated[int, ..., \"First integer\"]\n",
+    "    b: Annotated[int, ..., \"Second integer\"]\n",
+    "\n",
+    "\n",
+    "tools = [add, multiply]"
    ]
   },
   {
@@ -129,7 +171,7 @@
    "metadata": {},
    "source": [
     "To actually bind those schemas to a chat model, we'll use the `.bind_tools()` method. This handles converting\n",
-    "the `Add` and `Multiply` schemas to the proper format for the model. The tool schema will then be passed it in each time the model is invoked.\n",
+    "the `add` and `multiply` schemas to the proper format for the model. The tool schema will then be passed it in each time the model is invoked.\n",
     "\n",
     "```{=mdx}\n",
     "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
@@ -164,16 +206,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_wLTBasMppAwpdiA5CD92l9x7', 'function': {'arguments': '{\"a\":3,\"b\":12}', 'name': 'Multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 18, 'prompt_tokens': 89, 'total_tokens': 107}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_0f03d4f0ee', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-d3f36cca-f225-416f-ac16-0217046f0b38-0', tool_calls=[{'name': 'Multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_wLTBasMppAwpdiA5CD92l9x7', 'type': 'tool_call'}], usage_metadata={'input_tokens': 89, 'output_tokens': 18, 'total_tokens': 107})"
+       "AIMessage(content='', additional_kwargs={'tool_calls': [{'id': 'call_BwYJ4UgU5pRVCBOUmiu7NhF9', 'function': {'arguments': '{\"a\":3,\"b\":12}', 'name': 'multiply'}, 'type': 'function'}]}, response_metadata={'token_usage': {'completion_tokens': 17, 'prompt_tokens': 80, 'total_tokens': 97}, 'model_name': 'gpt-4o-mini-2024-07-18', 'system_fingerprint': 'fp_ba606877f9', 'finish_reason': 'tool_calls', 'logprobs': None}, id='run-7f05e19e-4561-40e2-a2d0-8f4e28e9a00f-0', tool_calls=[{'name': 'multiply', 'args': {'a': 3, 'b': 12}, 'id': 'call_BwYJ4UgU5pRVCBOUmiu7NhF9', 'type': 'tool_call'}], usage_metadata={'input_tokens': 80, 'output_tokens': 17, 'total_tokens': 97})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -214,23 +256,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[{'name': 'Multiply',\n",
+       "[{'name': 'multiply',\n",
        "  'args': {'a': 3, 'b': 12},\n",
-       "  'id': 'call_uqJsNrDJ8ZZnFa1BHHYAllEv',\n",
+       "  'id': 'call_rcdMie7E89Xx06lEKKxJyB5N',\n",
        "  'type': 'tool_call'},\n",
-       " {'name': 'Add',\n",
+       " {'name': 'add',\n",
        "  'args': {'a': 11, 'b': 49},\n",
-       "  'id': 'call_ud1uHAaYsdpWuxugwoJ63BDs',\n",
+       "  'id': 'call_nheGN8yfvSJsnIuGZaXihou3',\n",
        "  'type': 'tool_call'}]"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -252,31 +294,49 @@
     "are populated in the `.invalid_tool_calls` attribute. An `InvalidToolCall` can have \n",
     "a name, string arguments, identifier, and error message.\n",
     "\n",
-    "If desired, [output parsers](/docs/how_to#output-parsers) can further \n",
-    "process the output. For example, we can convert existing values populated on the `.tool_calls` attribute back to the original Pydantic class using the\n",
+    "\n",
+    "## Parsing\n",
+    "\n",
+    "If desired, [output parsers](/docs/how_to#output-parsers) can further process the output. For example, we can convert existing values populated on the `.tool_calls` to Pydantic objects using the\n",
     "[PydanticToolsParser](https://api.python.langchain.com/en/latest/output_parsers/langchain_core.output_parsers.openai_tools.PydanticToolsParser.html):"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Multiply(a=3, b=12), Add(a=11, b=49)]"
+       "[multiply(a=3, b=12), add(a=11, b=49)]"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "from langchain_core.output_parsers import PydanticToolsParser\n",
+    "from langchain_core.pydantic_v1 import BaseModel, Field\n",
     "\n",
-    "chain = llm_with_tools | PydanticToolsParser(tools=[Multiply, Add])\n",
+    "\n",
+    "class add(BaseModel):\n",
+    "    \"\"\"Add two integers.\"\"\"\n",
+    "\n",
+    "    a: int = Field(..., description=\"First integer\")\n",
+    "    b: int = Field(..., description=\"Second integer\")\n",
+    "\n",
+    "\n",
+    "class multiply(BaseModel):\n",
+    "    \"\"\"Multiply two integers.\"\"\"\n",
+    "\n",
+    "    a: int = Field(..., description=\"First integer\")\n",
+    "    b: int = Field(..., description=\"Second integer\")\n",
+    "\n",
+    "\n",
+    "chain = llm_with_tools | PydanticToolsParser(tools=[add, multiply])\n",
     "chain.invoke(query)"
    ]
   },
@@ -294,18 +354,18 @@
     "\n",
     "You can also check out some more specific uses of tool calling:\n",
     "\n",
+    "- Getting [structured outputs](/docs/how_to/structured_output/) from models\n",
     "- Few shot prompting [with tools](/docs/how_to/tools_few_shot/)\n",
     "- Stream [tool calls](/docs/how_to/tool_streaming/)\n",
-    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)\n",
-    "- Getting [structured outputs](/docs/how_to/structured_output/) from models"
+    "- Pass [runtime values to tools](/docs/how_to/tool_runtime)"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv-311",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv-311"
   },
   "language_info": {
    "codemirror_mode": {
@@ -317,7 +377,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,

docs/docs/how_to/tool_runtime.ipynb

@@ -6,26 +6,20 @@
    "source": [
     "# How to pass run time values to tools\n",
     "\n",
-    ":::info Prerequisites\n",
+    "import Prerequisites from \"@theme/Prerequisites\";\n",
+    "import Compatibility from \"@theme/Compatibility\";\n",
     "\n",
-    "This guide assumes familiarity with the following concepts:\n",
-    "- [Chat models](/docs/concepts/#chat-models)\n",
-    "- [LangChain Tools](/docs/concepts/#tools)\n",
-    "- [How to create tools](/docs/how_to/custom_tools)\n",
-    "- [How to use a model to call tools](/docs/how_to/tool_calling)\n",
-    ":::\n",
+    "<Prerequisites titlesAndLinks={[\n",
+    "  [\"Chat models\", \"/docs/concepts/#chat-models\"],\n",
+    "  [\"LangChain Tools\", \"/docs/concepts/#tools\"],\n",
+    "  [\"How to create tools\", \"/docs/how_to/custom_tools\"],\n",
+    "  [\"How to use a model to call tools\", \"/docs/how_to/tool_calling\"],\n",
+    "]} />\n",
     "\n",
-    ":::info Using with LangGraph\n",
     "\n",
-    "If you're using LangGraph, please refer to [this how-to guide](https://langchain-ai.github.io/langgraph/how-tos/pass-run-time-values-to-tools/)\n",
-    "which shows how to create an agent that keeps track of a given user's favorite pets.\n",
-    ":::\n",
-    "\n",
-    ":::caution Added in `langchain-core==0.2.21`\n",
-    "\n",
-    "Must have `langchain-core>=0.2.21` to use this functionality.\n",
-    "\n",
-    ":::\n",
+    "<Compatibility packagesAndVersions={[\n",
+    "  [\"langchain-core\", \"0.2.21\"],\n",
+    "]} />\n",
     "\n",
     "You may need to bind values to a tool that are only known at runtime. For example, the tool logic may require using the ID of the user who made the request.\n",
     "\n",
@@ -33,7 +27,13 @@
     "\n",
     "Instead, the LLM should only control the parameters of the tool that are meant to be controlled by the LLM, while other parameters (such as user ID) should be fixed by the application logic.\n",
     "\n",
-    "This how-to guide shows you how to prevent the model from generating certain tool arguments and injecting them in directly at runtime."
+    "This how-to guide shows you how to prevent the model from generating certain tool arguments and injecting them in directly at runtime.\n",
+    "\n",
+    ":::info Using with LangGraph\n",
+    "\n",
+    "If you're using LangGraph, please refer to [this how-to guide](https://langchain-ai.github.io/langgraph/how-tos/pass-run-time-values-to-tools/)\n",
+    "which shows how to create an agent that keeps track of a given user's favorite pets.\n",
+    ":::"
    ]
   },
   {
@@ -597,9 +597,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-311",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "poetry-venv-311"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -611,7 +611,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/ai21.ipynb

@@ -17,26 +17,25 @@
    "source": [
     "# ChatAI21\n",
     "\n",
+    "## Overview\n",
+    "\n",
     "This notebook covers how to get started with AI21 chat models.\n",
-    "Note that different chat models support different parameters. See the ",
-    "[AI21 documentation](https://docs.ai21.com/reference) to learn more about the parameters in your chosen model.\n",
+    "Note that different chat models support different parameters. See the [AI21 documentation](https://docs.ai21.com/reference) to learn more about the parameters in your chosen model.\n",
     "[See all AI21's LangChain components.](https://pypi.org/project/langchain-ai21/) \n",
-    "## Installation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "4c3bef91",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2024-02-15T06:50:44.929635Z",
-     "start_time": "2024-02-15T06:50:41.209704Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "!pip install -qU langchain-ai21"
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/__package_name_short_snake__) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatAI21](https://api.python.langchain.com/en/latest/chat_models/langchain_ai21.chat_models.ChatAI21.html#langchain_ai21.chat_models.ChatAI21) | [langchain-ai21](https://api.python.langchain.com/en/latest/ai21_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-ai21?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-ai21?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
+    "\n",
+    "\n",
+    "## Setup"
    ]
   },
   {
@@ -44,10 +43,9 @@
    "id": "2b4f3e15",
    "metadata": {},
    "source": [
-    "## Environment Setup\n",
+    "### Credentials\n",
     "\n",
-    "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the ",
-    "`AI21_API_KEY` environment variable:\n"
+    "We'll need to get an [AI21 API key](https://docs.ai21.com/) and set the `AI21_API_KEY` environment variable:\n"
    ]
   },
   {
@@ -67,48 +65,166 @@
   },
   {
    "cell_type": "markdown",
-   "id": "4828829d3da430ce",
-   "metadata": {
-    "collapsed": false
-   },
+   "id": "f6844fff-3702-4489-ab74-732f69f3b9d7",
+   "metadata": {},
    "source": [
-    "## Usage"
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "39353473fce5dd2e",
+   "execution_count": null,
+   "id": "7c2e19d3-7c58-4470-9e1a-718b27a32056",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "98e22f31-8acc-42d6-916d-415d1263c56e",
+   "metadata": {},
+   "source": [
+    "### Installation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f9699cd9-58f2-450e-aa64-799e66906c0f",
+   "metadata": {},
+   "source": [
+    "!pip install -qU langchain-ai21"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4828829d3da430ce",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c40756fb-cbf8-4d44-a293-3989d707237e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_ai21 import ChatAI21\n",
+    "\n",
+    "llm = ChatAI21(model=\"jamba-instruct\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2bdc5d68-2a19-495e-8c04-d11adc86d3ae",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "46b982dc-5d8a-46da-a711-81c03ccd6adc",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Bonjour, comment vas-tu?')"
+       "AIMessage(content=\"J'adore programmer.\", id='run-2e8d16d6-a06e-45cb-8d0c-1c8208645033-0')"
       ]
      },
-     "execution_count": 1,
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "10a30f84-b531-4fd5-8b5b-91512fbdc75b",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "39353473fce5dd2e",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Ich liebe das Programmieren.', id='run-e1bd82dc-1a7e-4b2e-bde9-ac995929ac0f-0')"
+      ]
+     },
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_ai21 import ChatAI21\n",
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "chat = ChatAI21(model=\"jamba-instruct\")\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
+    "prompt = ChatPromptTemplate(\n",
     "    [\n",
-    "        (\"system\", \"You are a helpful assistant that translates English to French.\"),\n",
-    "        (\"human\", \"Translate this sentence from English to French. {english_text}.\"),\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
     "    ]\n",
     ")\n",
     "\n",
-    "chain = prompt | chat\n",
-    "chain.invoke({\"english_text\": \"Hello, how are you?\"})"
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e79de691-9dd6-4697-b57e-59a4a3cc073a",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatAI21 features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_ai21.chat_models.ChatAI21.html"
    ]
   }
  ],
@@ -128,7 +244,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
    "metadata": {},
    "outputs": [],
@@ -123,8 +123,8 @@
     "from langchain_openai import AzureChatOpenAI\n",
     "\n",
     "llm = AzureChatOpenAI(\n",
-    "    azure_deployment=\"YOUR-DEPLOYMENT\",\n",
-    "    api_version=\"2024-05-01-preview\",\n",
+    "    azure_deployment=\"gpt-35-turbo\",  # or your deployment\n",
+    "    api_version=\"2023-06-01-preview\",  # or your api version\n",
     "    temperature=0,\n",
     "    max_tokens=None,\n",
     "    timeout=None,\n",
@@ -143,7 +143,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "62e0dbc3",
    "metadata": {
     "tags": []
@@ -152,10 +152,10 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 31, 'total_tokens': 39}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-a6a732c2-cb02-4e50-9a9c-ab30eab034fc-0', usage_metadata={'input_tokens': 31, 'output_tokens': 8, 'total_tokens': 39})"
+       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'completion_tokens': 8, 'prompt_tokens': 31, 'total_tokens': 39}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-bea4b46c-e3e1-4495-9d3a-698370ad963d-0', usage_metadata={'input_tokens': 31, 'output_tokens': 8, 'total_tokens': 39})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -174,7 +174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 4,
    "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
    "metadata": {},
    "outputs": [
@@ -202,17 +202,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 5,
    "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 26, 'total_tokens': 32}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-084967d7-06f2-441f-b5c1-477e2a9e9d03-0', usage_metadata={'input_tokens': 26, 'output_tokens': 6, 'total_tokens': 32})"
+       "AIMessage(content='Ich liebe das Programmieren.', response_metadata={'token_usage': {'completion_tokens': 6, 'prompt_tokens': 26, 'total_tokens': 32}, 'model_name': 'gpt-35-turbo', 'system_fingerprint': None, 'prompt_filter_results': [{'prompt_index': 0, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}], 'finish_reason': 'stop', 'logprobs': None, 'content_filter_results': {'hate': {'filtered': False, 'severity': 'safe'}, 'self_harm': {'filtered': False, 'severity': 'safe'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'safe'}}}, id='run-cbc44038-09d3-40d4-9da2-c5910ee636ca-0', usage_metadata={'input_tokens': 26, 'output_tokens': 6, 'total_tokens': 32})"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -264,8 +264,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "id": "84c411b0-1790-4798-8bb7-47d8ece4c2dc",
+   "execution_count": 6,
+   "id": "2ca02d23-60d0-43eb-8d04-070f61f8fefd",
    "metadata": {},
    "outputs": [
     {
@@ -288,22 +288,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "id": "21234693-d92b-4d69-8a7f-55aa062084bf",
+   "execution_count": 7,
+   "id": "e1b07ae2-3de7-44bd-bfdc-b76f4ba45a35",
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total Cost (USD): $0.000078\n"
+      "Total Cost (USD): $0.000074\n"
      ]
     }
    ],
    "source": [
     "llm_0301 = AzureChatOpenAI(\n",
-    "    azure_deployment=\"YOUR-DEPLOYMENT\",\n",
-    "    api_version=\"2024-05-01-preview\",\n",
+    "    azure_deployment=\"gpt-35-turbo\",  # or your deployment\n",
+    "    api_version=\"2023-06-01-preview\",  # or your api version\n",
     "    model_version=\"0301\",\n",
     ")\n",
     "with get_openai_callback() as cb:\n",
@@ -338,7 +338,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/cohere.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "raw",
-   "id": "afaf8039",
+   "id": "53fbf15f",
    "metadata": {},
    "source": [
     "---\n",
@@ -12,129 +12,103 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e49f1e0d",
+   "id": "bf733a38-db84-4363-89e2-de6735c37230",
    "metadata": {},
    "source": [
-    "# ChatCohere\n",
+    "# Cohere\n",
     "\n",
-    "This doc will help you get started with Cohere [chat models](/docs/concepts/#chat-models). For detailed documentation of all ChatCohere features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html).\n",
-    "\n",
-    "For an overview of all Cohere models head to the [Cohere docs](https://docs.cohere.com/docs/models).\n",
-    "\n",
-    "## Overview\n",
-    "### Integration details\n",
-    "\n",
-    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/cohere) | Package downloads | Package latest |\n",
-    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
-    "| [ChatCohere](https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html) | [langchain-cohere](https://api.python.langchain.com/en/latest/cohere_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-cohere?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-cohere?style=flat-square&label=%20) |\n",
-    "\n",
-    "### Model features\n",
-    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
-    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | \n",
+    "This notebook covers how to get started with [Cohere chat models](https://cohere.com/chat).\n",
     "\n",
+    "Head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_community.chat_models.cohere.ChatCohere.html) for detailed documentation of all attributes and methods."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3607d67e-e56c-4102-bbba-df2edc0e109e",
+   "metadata": {},
+   "source": [
     "## Setup\n",
     "\n",
-    "To access Cohere models you'll need to create a Cohere account, get an API key, and install the `langchain-cohere` integration package.\n",
+    "The integration lives in the `langchain-cohere` package. We can install these with:\n",
     "\n",
-    "### Credentials\n",
+    "```bash\n",
+    "pip install -U langchain-cohere\n",
+    "```\n",
     "\n",
-    "Head to https://dashboard.cohere.com/welcome/login to sign up to Cohere and generate an API key. Once you've done this set the COHERE_API_KEY environment variable:"
+    "We'll also need to get a [Cohere API key](https://cohere.com/) and set the `COHERE_API_KEY` environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "433e8d2b-9519-4b49-b2c4-7ab65b046c94",
+   "execution_count": 11,
+   "id": "2108b517-1e8d-473d-92fa-4f930e8072a7",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass(\"Enter your Cohere API key: \")"
+    "os.environ[\"COHERE_API_KEY\"] = getpass.getpass()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "id": "cf690fbb",
    "metadata": {},
    "source": [
-    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "execution_count": 12,
+   "id": "7f11de02",
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "id": "4c26754b-b3c9-4d93-8f36-43049bd943bf",
    "metadata": {},
    "source": [
-    "### Installation\n",
+    "## Usage\n",
     "\n",
-    "The LangChain Cohere integration lives in the `langchain-cohere` package:"
+    "ChatCohere supports all [ChatModel](/docs/how_to#chat-models) functionality:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -qU langchain-cohere"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
-   "metadata": {},
-   "source": [
-    "## Instantiation\n",
-    "\n",
-    "Now we can instantiate our model object and generate chat completions:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
-   "metadata": {},
+   "execution_count": 5,
+   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain_cohere import ChatCohere\n",
-    "\n",
-    "llm = ChatCohere(\n",
-    "    model=\"command-r-plus\",\n",
-    "    temperature=0,\n",
-    "    max_tokens=None,\n",
-    "    timeout=None,\n",
-    "    max_retries=2,\n",
-    "    # other params...\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Invocation"
+    "from langchain_core.messages import HumanMessage"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "62e0dbc3",
+   "execution_count": 13,
+   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat = ChatCohere()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
    "metadata": {
     "tags": []
    },
@@ -142,110 +116,223 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"J'adore programmer.\", additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'd84f80f3-4611-46e6-aed0-9d8665a20a11', 'token_count': {'input_tokens': 89, 'output_tokens': 5}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'd84f80f3-4611-46e6-aed0-9d8665a20a11', 'token_count': {'input_tokens': 89, 'output_tokens': 5}}, id='run-514ab516-ed7e-48ac-b132-2598fb80ebef-0')"
+       "AIMessage(content='4 && 5 \\n6 || 7 \\n\\nWould you like to play a game of odds and evens?', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '2076b614-52b3-4082-a259-cc92cd3d9fea', 'token_count': {'prompt_tokens': 68, 'response_tokens': 23, 'total_tokens': 91, 'billed_tokens': 77}}, id='run-3475e0c8-c89b-4937-9300-e07d652455e1-0')"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "messages = [\n",
-    "    (\n",
-    "        \"system\",\n",
-    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
-    "    ),\n",
-    "    (\"human\", \"I love programming.\"),\n",
-    "]\n",
-    "ai_msg = llm.invoke(messages)\n",
-    "ai_msg"
+    "messages = [HumanMessage(content=\"1\"), HumanMessage(content=\"2 3\")]\n",
+    "chat.invoke(messages)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "d86145b3-bfef-46e8-b227-4dda5c9c2705",
-   "metadata": {},
+   "execution_count": 16,
+   "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': 'f0708a92-f874-46ee-9b93-334d616ad92e', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-1635e63e-2994-4e7f-986e-152ddfc95777-0')"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "await chat.ainvoke(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "J'adore programmer.\n"
+      "4 && 5"
      ]
     }
    ],
    "source": [
-    "print(ai_msg.content)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "18e2bfc0-7e78-4528-a73f-499ac150dca8",
-   "metadata": {},
-   "source": [
-    "## Chaining\n",
-    "\n",
-    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+    "for chunk in chat.stream(messages):\n",
+    "    print(chunk.content, end=\"\", flush=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
-   "id": "e197d1d7-a070-4c96-9f8a-a0e86d046e0b",
+   "execution_count": 18,
+   "id": "064288e4-f184-4496-9427-bcf148fa055e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Ich liebe Programmierung.', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '053bebde-4e1d-4d06-8ee6-3446e7afa25e', 'token_count': {'input_tokens': 84, 'output_tokens': 6}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '053bebde-4e1d-4d06-8ee6-3446e7afa25e', 'token_count': {'input_tokens': 84, 'output_tokens': 6}}, id='run-53700708-b7fb-417b-af36-1a6fcde38e7d-0')"
+       "[AIMessage(content='4 && 5', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6770ca86-f6c3-4ba3-a285-c4772160612f', 'token_count': {'prompt_tokens': 68, 'response_tokens': 3, 'total_tokens': 71, 'billed_tokens': 57}}, id='run-8d6fade2-1b39-4e31-ab23-4be622dd0027-0')]"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
-    "    [\n",
-    "        (\n",
-    "            \"system\",\n",
-    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
-    "        ),\n",
-    "        (\"human\", \"{input}\"),\n",
-    "    ]\n",
-    ")\n",
-    "\n",
-    "chain = prompt | llm\n",
-    "chain.invoke(\n",
-    "    {\n",
-    "        \"input_language\": \"English\",\n",
-    "        \"output_language\": \"German\",\n",
-    "        \"input\": \"I love programming.\",\n",
-    "    }\n",
-    ")"
+    "chat.batch([messages])"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "id": "f1c56460",
    "metadata": {},
    "source": [
-    "## API reference\n",
+    "## Chaining\n",
     "\n",
-    "For detailed documentation of all ChatCohere features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_cohere.chat_models.ChatCohere.html"
+    "You can also easily combine with a prompt template for easy structuring of user input. We can do this using [LCEL](/docs/concepts#langchain-expression-language-lcel)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "0851b103",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "chain = prompt | chat"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "ae950c0f-1691-47f1-b609-273033cae707",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='What color socks do bears wear?\\n\\nThey don’t wear socks, they have bear feet. \\n\\nHope you laughed! If not, maybe this will help: laughter is the best medicine, and a good sense of humor is infectious!', additional_kwargs={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, response_metadata={'documents': None, 'citations': None, 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '6edccf44-9bc8-4139-b30e-13b368f3563c', 'token_count': {'prompt_tokens': 68, 'response_tokens': 51, 'total_tokens': 119, 'billed_tokens': 108}}, id='run-ef7f9789-0d4d-43bf-a4f7-f2a0e27a5320-0')"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12db8d69",
+   "metadata": {},
+   "source": [
+    "## Tool calling\n",
+    "\n",
+    "Cohere supports tool calling functionalities!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "337e24af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import (\n",
+    "    HumanMessage,\n",
+    "    ToolMessage,\n",
+    ")\n",
+    "from langchain_core.tools import tool"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "74d292e7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "@tool\n",
+    "def magic_function(number: int) -> int:\n",
+    "    \"\"\"Applies a magic operation to an integer\n",
+    "    Args:\n",
+    "        number: Number to have magic operation performed on\n",
+    "    \"\"\"\n",
+    "    return number + 10\n",
+    "\n",
+    "\n",
+    "def invoke_tools(tool_calls, messages):\n",
+    "    for tool_call in tool_calls:\n",
+    "        selected_tool = {\"magic_function\": magic_function}[tool_call[\"name\"].lower()]\n",
+    "        tool_output = selected_tool.invoke(tool_call[\"args\"])\n",
+    "        messages.append(ToolMessage(tool_output, tool_call_id=tool_call[\"id\"]))\n",
+    "    return messages\n",
+    "\n",
+    "\n",
+    "tools = [magic_function]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ecafcbc6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_with_tools = chat.bind_tools(tools=tools)\n",
+    "messages = [HumanMessage(content=\"What is the value of magic_function(2)?\")]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "aa34fc39",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='The value of magic_function(2) is 12.', additional_kwargs={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, response_metadata={'documents': [{'id': 'magic_function:0:2:0', 'output': '12', 'tool_name': 'magic_function'}], 'citations': [ChatCitation(start=34, end=36, text='12', document_ids=['magic_function:0:2:0'])], 'search_results': None, 'search_queries': None, 'is_search_required': None, 'generation_id': '96a55791-0c58-4e2e-bc2a-8550e137c46d', 'token_count': {'input_tokens': 998, 'output_tokens': 59}}, id='run-f318a9cf-55c8-44f4-91d1-27cf46c6a465-0')"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "res = llm_with_tools.invoke(messages)\n",
+    "while res.tool_calls:\n",
+    "    messages.append(res)\n",
+    "    messages = invoke_tools(res.tool_calls, messages)\n",
+    "    res = llm_with_tools.invoke(messages)\n",
+    "\n",
+    "res"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv-2",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv-2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -257,7 +344,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.9.6"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/databricks.ipynb

@@ -36,7 +36,7 @@
     "### Model features\n",
     "| [Tool calling](/docs/how_to/tool_calling/) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
     "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
-    "| ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |  ✅ | ✅ | ✅ | ❌ | \n",
+    "| ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |  ✅ | ✅ | ✅ | ❌ | \n",
     "\n",
     "### Supported Methods\n",
     "\n",
@@ -395,6 +395,66 @@
     "chat_model_external.invoke(\"How to use Databricks?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Function calling on Databricks"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Databricks Function Calling is OpenAI-compatible and is only available during model serving as part of Foundation Model APIs.\n",
+    "\n",
+    "See [Databricks function calling introduction](https://docs.databricks.com/en/machine-learning/model-serving/function-calling.html#supported-models) for supported models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.chat_models.databricks import ChatDatabricks\n",
+    "\n",
+    "llm = ChatDatabricks(endpoint=\"databricks-meta-llama-3-70b-instruct\")\n",
+    "tools = [\n",
+    "    {\n",
+    "        \"type\": \"function\",\n",
+    "        \"function\": {\n",
+    "            \"name\": \"get_current_weather\",\n",
+    "            \"description\": \"Get the current weather in a given location\",\n",
+    "            \"parameters\": {\n",
+    "                \"type\": \"object\",\n",
+    "                \"properties\": {\n",
+    "                    \"location\": {\n",
+    "                        \"type\": \"string\",\n",
+    "                        \"description\": \"The city and state, e.g. San Francisco, CA\",\n",
+    "                    },\n",
+    "                    \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n",
+    "                },\n",
+    "            },\n",
+    "        },\n",
+    "    }\n",
+    "]\n",
+    "\n",
+    "# supported tool_choice values: \"auto\", \"required\", \"none\", function name in string format,\n",
+    "# or a dictionary as {\"type\": \"function\", \"function\": {\"name\": <<tool_name>>}}\n",
+    "model = llm.bind_tools(tools, tool_choice=\"auto\")\n",
+    "\n",
+    "messages = [{\"role\": \"user\", \"content\": \"What is the current temperature of Chicago?\"}]\n",
+    "print(model.invoke(messages))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "See [Databricks Unity Catalog](docs/integrations/tools/databricks.ipynb) about how to use UC functions in chains."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},

docs/docs/integrations/chat/huggingface.ipynb

@@ -4,18 +4,67 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Hugging Face\n",
+    "---\n",
+    "sidebar_label: Hugging Face\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# ChatHuggingFace\n",
     "\n",
-    "This notebook shows how to get started using `Hugging Face` LLM's as chat models.\n",
+    "## Overview\n",
+    "\n",
+    "This notebook shows how to get started using Hugging Face LLMs as chat models.\n",
     "\n",
     "In particular, we will:\n",
-    "1. Utilize the [HuggingFaceEndpoint](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/huggingface_endpoint.py) integrations to instantiate an `LLM`.\n",
+    "1. Utilize the [HuggingFaceEndpoint](https://github.com/langchain-ai/langchain/blob/master/libs/langchain/langchain/llms/huggingface_endpoint.py) integrations to instantiate an LLM.\n",
     "2. Utilize the `ChatHuggingFace` class to enable any of these LLMs to interface with LangChain's [Chat Messages](/docs/concepts/#message-types) abstraction.\n",
     "3. Explore tool calling with the `ChatHuggingFace`.\n",
     "4. Demonstrate how to use an open-source LLM to power an `ChatAgent` pipeline\n",
     "\n",
+    "### Integration details\n",
     "\n",
-    "> Note: To get started, you'll need to have a [Hugging Face Access Token](https://huggingface.co/docs/hub/security-tokens) saved as an environment variable: `HUGGINGFACEHUB_API_TOKEN`."
+    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatHuggingFace](https://api.python.langchain.com/en/latest/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html) | [langchain-huggingface](https://api.python.langchain.com/en/latest/huggingface_api_reference.html) | ✅ | beta | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_huggingface?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_huggingface?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access Hugging Face models you'll need to create a Hugging Face account, get an API key, and install the `langchain-huggingface` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Generate a [Hugging Face Access Token](https://huggingface.co/docs/hub/security-tokens) and store it as an environment variable: `HUGGINGFACEHUB_API_TOKEN`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"HUGGINGFACEHUB_API_TOKEN\"):\n",
+    "    os.environ[\"HUGGINGFACEHUB_API_TOKEN\"] = getpass.getpass(\"Enter your token: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "Below we install additional packages as well for demonstration purposes:"
    ]
   },
   {
@@ -31,7 +80,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 1. Instantiate an LLM"
+    "## Instantiation"
    ]
   },
   {
@@ -80,6 +129,7 @@
     "        max_new_tokens=512,\n",
     "        do_sample=False,\n",
     "        repetition_penalty=1.03,\n",
+    "        return_full_text=False,\n",
     "    ),\n",
     ")"
    ]
@@ -118,7 +168,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 2. Instantiate the `ChatHuggingFace` to apply chat templates"
+    "## Invocation"
    ]
   },
   {
@@ -249,7 +299,44 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 3. Explore the tool calling with `ChatHuggingFace`\n",
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tool calling with `ChatHuggingFace`\n",
     "\n",
     "`text-generation-inference` supports tool with open source LLMs starting from v2.0.1"
    ]
@@ -313,7 +400,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 4. Take it for a spin as an agent!\n",
+    "## Use with agents\n",
     "\n",
     "Here we'll test out `Zephyr-7B-beta` as a zero-shot `ReAct` Agent. \n",
     "\n",
@@ -458,6 +545,15 @@
     "\n",
     "It's exciting to see how far open-source LLM's can go as general purpose reasoning agents. Give it a try yourself!"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatHuggingFace features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_huggingface.chat_models.huggingface.ChatHuggingFace.html"
+   ]
   }
  ],
  "metadata": {
@@ -476,7 +572,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/mistralai.ipynb

@@ -12,43 +12,87 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bf733a38-db84-4363-89e2-de6735c37230",
+   "id": "a14c83bf-af26-4f22-8c1a-d632c5795ecf",
    "metadata": {},
    "source": [
     "# MistralAI\n",
     "\n",
-    "This notebook covers how to get started with MistralAI chat models, via their [API](https://docs.mistral.ai/api/).\n",
+    "This will help you getting started with Mistral [chat models](/docs/concepts/#chat-models), accessed via their [API](https://docs.mistral.ai/api/). For detailed documentation of all ChatMistralAI features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html).\n",
     "\n",
-    "A valid [API key](https://console.mistral.ai/users/api-keys/) is needed to communicate with the API.\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/chat/mistral) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatMistralAI](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) | [langchain_mistralai](https://api.python.langchain.com/en/latest/mistralai_api_reference.html) | ❌ | beta | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_mistralai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_mistralai?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ✅ | ✅ | ❌ | \n",
     "\n",
-    "Head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html) for detailed documentation of all attributes and methods."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "cc686b8f",
-   "metadata": {},
-   "source": [
     "## Setup\n",
     "\n",
-    "You will need the `langchain-core` and `langchain-mistralai` package to use the API. You can install these with:\n",
+    "To access Mistral models you'll need to create a Mistral account, get an API key, and install the `langchain-mistralai` integration package.\n",
     "\n",
-    "```bash\n",
-    "pip install -U langchain-core langchain-mistralai\n",
+    "### Credentials\n",
     "\n",
-    "We'll also need to get a [Mistral API key](https://console.mistral.ai/users/api-keys/)"
+    "A valid [API key](https://console.mistral.ai/users/api-keys/) is needed to communicate with the API. Once you've obtained an API key, store it in the `MISTRAL_API_KEY` environment variable:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "id": "c3fd4184",
+   "execution_count": null,
+   "id": "9acd8340-09d4-4ece-871a-a35b0732c7d8",
    "metadata": {},
    "outputs": [],
    "source": [
     "import getpass\n",
+    "import os\n",
     "\n",
-    "api_key = getpass.getpass()"
+    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
+    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\n",
+    "        \"Enter your __ModuleName__ API key: \"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "42c979b1-df49-4f6c-9fe6-d9dbf3ea8c2a",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cc4f11ec-5cb3-4caf-b3cd-7a20c41b0cfe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0fc42221-97b2-466b-95db-10368e17ca56",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain MistralAI integration lives in the `langchain-mistralai` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "85cb1ab8-9f2c-4b93-8415-ad65819dcb38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-mistralai"
    ]
   },
   {
@@ -56,57 +100,76 @@
    "id": "502127fd",
    "metadata": {},
    "source": [
-    "## Usage"
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "d4a7c55d-b235-4ca4-a579-c90cc9570da9",
-   "metadata": {
-    "tags": []
-   },
+   "execution_count": 1,
+   "id": "2dfa801a-d040-4c09-9634-58604e8eaf16",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_core.messages import HumanMessage\n",
-    "from langchain_mistralai.chat_models import ChatMistralAI"
+    "from langchain_mistralai.chat_models import ChatMistralAI\n",
+    "\n",
+    "llm = ChatMistralAI(model=\"mistral-large-latest\")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "70cf04e8-423a-4ff6-8b09-f11fb711c817",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
+   "cell_type": "markdown",
+   "id": "f668acff-eb14-4b3a-959a-df5bfc02968b",
+   "metadata": {},
    "source": [
-    "# If api_key is not passed, default behavior is to use the `MISTRAL_API_KEY` environment variable.\n",
-    "chat = ChatMistralAI(api_key=api_key)"
+    "## Invocation"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
-   "id": "8199ef8f-eb8b-4253-9ea0-6c24a013ca4c",
-   "metadata": {
-    "tags": []
-   },
+   "execution_count": 2,
+   "id": "86e3f9e6-67ec-4fbf-8ff1-85331200f412",
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content=\"Who's there? I was just about to ask the same thing! How can I assist you today?\")"
+       "AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 27, 'total_tokens': 36, 'completion_tokens': 9}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-d6196c33-9410-413b-b454-4ed0bec1f0c7-0', usage_metadata={'input_tokens': 27, 'output_tokens': 9, 'total_tokens': 36})"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "messages = [HumanMessage(content=\"knock knock\")]\n",
-    "chat.invoke(messages)"
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "8f8a24bc-b7f0-4d3a-b310-8a4e0ba125dd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "J'adore la programmation.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(ai_msg.content)"
    ]
   },
   {
@@ -119,7 +182,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 4,
    "id": "c5fac0e9-05a4-4fc1-a3b3-e5bbb24b971b",
    "metadata": {
     "tags": []
@@ -128,16 +191,16 @@
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Who\\'s there?\\n\\n(You can then continue the \"knock knock\" joke by saying the name of the person or character who should be responding. For example, if I say \"Banana,\" you could respond with \"Banana who?\" and I would say \"Banana bunch! Get it? Because a group of bananas is called a \\'bunch\\'!\" and then we would both laugh and have a great time. But really, you can put anything you want in the spot where I put \"Banana\" and it will still technically be a \"knock knock\" joke. The possibilities are endless!)')"
+       "AIMessage(content=\"J'aime programmer.\", response_metadata={'token_usage': {'prompt_tokens': 27, 'total_tokens': 34, 'completion_tokens': 7}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-1873888a-186f-49a8-ab81-24335bd3099b-0', usage_metadata={'input_tokens': 27, 'output_tokens': 7, 'total_tokens': 34})"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "await chat.ainvoke(messages)"
+    "await llm.ainvoke(messages)"
    ]
   },
   {
@@ -150,7 +213,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
    "id": "025be980-e50d-4a68-93dc-c9c7b500ce34",
    "metadata": {
     "tags": []
@@ -160,32 +223,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Who's there?\n",
-      "\n",
-      "(After this, the conversation can continue as a call and response \"who's there\" joke. Here is an example of how it could go:\n",
-      "\n",
-      "You say: Orange.\n",
-      "I say: Orange who?\n",
-      "You say: Orange you glad I didn't say banana!?)\n",
-      "\n",
-      "But since you asked for a knock knock joke specifically, here's one for you:\n",
-      "\n",
-      "Knock knock.\n",
-      "\n",
-      "Me: Who's there?\n",
-      "\n",
-      "You: Lettuce.\n",
-      "\n",
-      "Me: Lettuce who?\n",
-      "\n",
-      "You: Lettuce in, it's too cold out here!\n",
-      "\n",
-      "I hope this brings a smile to your face! Do you have a favorite knock knock joke you'd like to share? I'd love to hear it."
+      "J'adore programmer."
      ]
     }
    ],
    "source": [
-    "for chunk in chat.stream(messages):\n",
+    "for chunk in llm.stream(messages):\n",
     "    print(chunk.content, end=\"\")"
    ]
   },
@@ -199,23 +242,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 6,
    "id": "e63aebcb",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[AIMessage(content=\"Who's there? I was just about to ask the same thing! Go ahead and tell me who's there. I love a good knock-knock joke.\")]"
+       "[AIMessage(content=\"J'adore la programmation.\", response_metadata={'token_usage': {'prompt_tokens': 27, 'total_tokens': 36, 'completion_tokens': 9}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-2aa2a189-c405-4cf5-bd31-e9025e4c8536-0', usage_metadata={'input_tokens': 27, 'output_tokens': 9, 'total_tokens': 36})]"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chat.batch([messages])"
+    "llm.batch([messages])"
    ]
   },
   {
@@ -230,36 +273,52 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 7,
    "id": "ee43a1ae",
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.prompts import ChatPromptTemplate\n",
-    "\n",
-    "prompt = ChatPromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
-    "chain = prompt | chat"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "0dc49212",
-   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "AIMessage(content='Why do bears hate shoes so much? They like to run around in their bear feet.')"
+       "AIMessage(content='Ich liebe Programmieren.', response_metadata={'token_usage': {'prompt_tokens': 21, 'total_tokens': 28, 'completion_tokens': 7}, 'model': 'mistral-large-latest', 'finish_reason': 'stop'}, id='run-409ebc9a-b4a0-4734-ab6f-e11f6b4f808f-0', usage_metadata={'input_tokens': 21, 'output_tokens': 7, 'total_tokens': 28})"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain.invoke({\"topic\": \"bears\"})"
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eb7e01fb-a433-48b1-a4c2-e6009523a896",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all ChatMistralAI features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_mistralai.chat_models.ChatMistralAI.html"
    ]
   }
  ],
@@ -279,7 +338,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/nvidia_ai_endpoints.ipynb

@@ -2,13 +2,24 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "cc6caafa",
-   "metadata": {
-    "id": "cc6caafa"
-   },
+   "id": "1f666798-8635-4bc0-a515-04d318588d67",
+   "metadata": {},
    "source": [
-    "# NVIDIA NIMs\n",
+    "---\n",
+    "sidebar_label: NVIDIA AI Endpoints\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fa8eb20e-4db8-45e3-9e79-c595f4f274da",
+   "metadata": {},
+   "source": [
+    "# ChatNVIDIA\n",
     "\n",
+    "This will help you getting started with NVIDIA [chat models](/docs/concepts/#chat-models). For detailed documentation of all `ChatNVIDIA` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_nvidia_ai_endpoints.chat_models.ChatNVIDIA.html).\n",
+    "\n",
+    "## Overview\n",
     "The `langchain-nvidia-ai-endpoints` package contains LangChain integrations building applications with models on \n",
     "NVIDIA NIM inference microservice. NIM supports models across domains like chat, embedding, and re-ranking models \n",
     "from the community as well as NVIDIA. These models are optimized by NVIDIA to deliver the best performance on NVIDIA \n",
@@ -24,7 +35,66 @@
     "\n",
     "This example goes over how to use LangChain to interact with NVIDIA supported via the `ChatNVIDIA` class.\n",
     "\n",
-    "For more information on accessing the chat models through this api, check out the [ChatNVIDIA](https://python.langchain.com/docs/integrations/chat/nvidia_ai_endpoints/) documentation."
+    "For more information on accessing the chat models through this api, check out the [ChatNVIDIA](https://python.langchain.com/docs/integrations/chat/nvidia_ai_endpoints/) documentation.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatNVIDIA](https://api.python.langchain.com/en/latest/chat_models/langchain_nvidia_ai_endpoints.chat_models.ChatNVIDIA.html) | [langchain_nvidia_ai_endpoints](https://api.python.langchain.com/en/latest/nvidia_ai_endpoints_api_reference.html) | ✅ | beta | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_nvidia_ai_endpoints?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_nvidia_ai_endpoints?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "**To get started:**\n",
+    "\n",
+    "1. Create a free account with [NVIDIA](https://build.nvidia.com/), which hosts NVIDIA AI Foundation models.\n",
+    "\n",
+    "2. Click on your model of choice.\n",
+    "\n",
+    "3. Under `Input` select the `Python` tab, and click `Get API Key`. Then click `Generate Key`.\n",
+    "\n",
+    "4. Copy and save the generated key as `NVIDIA_API_KEY`. From there, you should have access to the endpoints.\n",
+    "\n",
+    "### Credentials\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "208b72da-1535-4249-bbd3-2500028e25e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"NVIDIA_API_KEY\"):\n",
+    "    # Note: the API key should start with \"nvapi-\"\n",
+    "    os.environ[\"NVIDIA_API_KEY\"] = getpass.getpass(\"Enter your NVIDIA API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52dc8dcb-0a48-4a4e-9947-764116d2ffd4",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2cd9cb12-6ca5-432a-9e42-8a57da073c7e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
    ]
   },
   {
@@ -32,7 +102,9 @@
    "id": "f2be90a9",
    "metadata": {},
    "source": [
-    "## Installation"
+    "### Installation\n",
+    "\n",
+    "The LangChain NVIDIA AI Endpoints integration lives in the `langchain_nvidia_ai_endpoints` package:"
    ]
   },
   {
@@ -45,51 +117,14 @@
     "%pip install --upgrade --quiet langchain-nvidia-ai-endpoints"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "ccff689e",
-   "metadata": {
-    "id": "ccff689e"
-   },
-   "source": [
-    "## Setup\n",
-    "\n",
-    "**To get started:**\n",
-    "\n",
-    "1. Create a free account with [NVIDIA](https://build.nvidia.com/), which hosts NVIDIA AI Foundation models.\n",
-    "\n",
-    "2. Click on your model of choice.\n",
-    "\n",
-    "3. Under `Input` select the `Python` tab, and click `Get API Key`. Then click `Generate Key`.\n",
-    "\n",
-    "4. Copy and save the generated key as `NVIDIA_API_KEY`. From there, you should have access to the endpoints."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "686c4d2f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import getpass\n",
-    "import os\n",
-    "\n",
-    "# del os.environ['NVIDIA_API_KEY']  ## delete key and reset\n",
-    "if os.environ.get(\"NVIDIA_API_KEY\", \"\").startswith(\"nvapi-\"):\n",
-    "    print(\"Valid NVIDIA_API_KEY already in environment. Delete to reset\")\n",
-    "else:\n",
-    "    nvapi_key = getpass.getpass(\"NVAPI Key (starts with nvapi-): \")\n",
-    "    assert nvapi_key.startswith(\"nvapi-\"), f\"{nvapi_key[:5]}... is not a valid key\"\n",
-    "    os.environ[\"NVIDIA_API_KEY\"] = nvapi_key"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "af0ce26b",
    "metadata": {},
    "source": [
-    "## Working with NVIDIA API Catalog"
+    "## Instantiation\n",
+    "\n",
+    "Now we can access models in the NVIDIA API Catalog:"
    ]
   },
   {
@@ -108,7 +143,24 @@
     "## Core LC Chat Interface\n",
     "from langchain_nvidia_ai_endpoints import ChatNVIDIA\n",
     "\n",
-    "llm = ChatNVIDIA(model=\"mistralai/mixtral-8x7b-instruct-v0.1\")\n",
+    "llm = ChatNVIDIA(model=\"mistralai/mixtral-8x7b-instruct-v0.1\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "469c8c7f-de62-457f-a30f-674763a8b717",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9512c81b-1f3a-4eca-9470-f52cedff5c74",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "result = llm.invoke(\"Write a ballad about LangChain.\")\n",
     "print(result.content)"
    ]
@@ -630,6 +682,55 @@
    "source": [
     "See [How to use chat models to call tools](https://python.langchain.com/v0.2/docs/how_to/tool_calling/) for additional examples."
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a9a3c438-121d-46eb-8fb5-b8d5a13cd4a4",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af585c6b-fe0a-4833-9860-a4209a71b3c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f2f25dd3-0b4a-465f-a53e-95521cdc253c",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `ChatNVIDIA` features and configurations head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_nvidia_ai_endpoints.chat_models.ChatNVIDIA.html"
+   ]
   }
  ],
  "metadata": {
@@ -651,7 +752,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/vllm.ipynb

@@ -12,14 +12,83 @@
   },
   {
    "cell_type": "markdown",
-   "id": "eb7e5679-aa06-47e4-a1a3-b6b70e604017",
+   "id": "8f82e243-f4ee-44e2-b417-099b6401ae3e",
    "metadata": {},
    "source": [
     "# vLLM Chat\n",
     "\n",
     "vLLM can be deployed as a server that mimics the OpenAI API protocol. This allows vLLM to be used as a drop-in replacement for applications using OpenAI API. This server can be queried in the same format as OpenAI API.\n",
     "\n",
-    "This notebook covers how to get started with vLLM chat models using langchain's `ChatOpenAI` **as it is**."
+    "## Overview\n",
+    "This will help you getting started with vLLM [chat models](/docs/concepts/#chat-models), which leverage the `langchain-openai` package. For detailed documentation of all `ChatOpenAI` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | Serializable | JS support | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [ChatOpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html) | [langchain_openai](https://api.python.langchain.com/en/latest/langchain_openai.html) | ✅ | beta | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_openai?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_openai?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Model features\n",
+    "Specific model features-- such as tool calling, support for multi-modal inputs, support for token-level streaming, etc.-- will depend on the hosted model.\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "See the vLLM docs [here](https://docs.vllm.ai/en/latest/).\n",
+    "\n",
+    "To access vLLM models through LangChain, you'll need to install the `langchain-openai` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Authentication will depend on specifics of the inference server."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3b1707a-cf2c-4367-94e3-436c43402503",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1e40bd5e-cbaa-41ef-aaf9-0858eb207184",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0739b647-609b-46d3-bdd3-e86fe4463288",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain vLLM integration can be accessed via the `langchain-openai` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7afcfbdc-56aa-4529-825a-8acbe7aa5241",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2cf576d6-7b67-4937-bf99-39071e85720c",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
    ]
   },
   {
@@ -51,7 +120,7 @@
    "source": [
     "inference_server_url = \"http://localhost:8000/v1\"\n",
     "\n",
-    "chat = ChatOpenAI(\n",
+    "llm = ChatOpenAI(\n",
     "    model=\"mosaicml/mpt-7b\",\n",
     "    openai_api_key=\"EMPTY\",\n",
     "    openai_api_base=inference_server_url,\n",
@@ -60,6 +129,14 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "34b18328-5e8b-4ff2-9b89-6fbb76b5c7f0",
+   "metadata": {},
+   "source": [
+    "## Invocation"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 15,
@@ -88,82 +165,66 @@
     "        content=\"Translate the following sentence from English to Italian: I love programming.\"\n",
     "    ),\n",
     "]\n",
-    "chat(messages)"
+    "llm.invoke(messages)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "55fc7046-a6dc-4720-8c0c-24a6db76a4f4",
+   "id": "a580a1e4-11a3-4277-bfba-bfb414ac7201",
    "metadata": {},
    "source": [
-    "You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use ChatPromptTemplate's format_prompt -- this returns a `PromptValue`, which you can convert to a string or `Message` object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
+    "## Chaining\n",
     "\n",
-    "For convenience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "123980e9-0dee-4ce5-bde6-d964dd90129c",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "template = (\n",
-    "    \"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
-    ")\n",
-    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
-    "human_template = \"{text}\"\n",
-    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "b2fb8c59-8892-4270-85a2-4f8ab276b75d",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "AIMessage(content=' I love programming too.', additional_kwargs={}, example=False)"
-      ]
-     },
-     "execution_count": 17,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "chat_prompt = ChatPromptTemplate.from_messages(\n",
-    "    [system_message_prompt, human_message_prompt]\n",
-    ")\n",
-    "\n",
-    "# get a chat completion from the formatted messages\n",
-    "chat(\n",
-    "    chat_prompt.format_prompt(\n",
-    "        input_language=\"English\", output_language=\"Italian\", text=\"I love programming.\"\n",
-    "    ).to_messages()\n",
-    ")"
+    "We can [chain](/docs/how_to/sequence/) our model with a prompt template like so:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0bbd9861-2b94-4920-8708-b690004f4c4d",
+   "id": "dd0f4043-48bd-4245-8bdb-e7669666a277",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "265f5d51-0a76-4808-8d13-ef598ee6e366",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all features and configurations exposed via `langchain-openai`, head to the API reference: https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.base.ChatOpenAI.html\n",
+    "\n",
+    "Refer to the vLLM [documentation](https://docs.vllm.ai/en/latest/) as well."
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "conda_pytorch_p310",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "conda_pytorch_p310"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -175,7 +236,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/document_loaders/unstructured_file.ipynb

@@ -31,7 +31,8 @@
     "### Local Partitioning (Optional)\n",
     "\n",
     "By default, `langchain-unstructured` installs a smaller footprint that requires\n",
-    "offloading of the partitioning logic to the Unstructured API.\n",
+    "offloading of the partitioning logic to the Unstructured API, which requires an `api_key`. For\n",
+    "partitioning using the API, refer to the Unstructured API section below.\n",
     "\n",
     "If you would like to run the partitioning logic locally, you will need to install\n",
     "a combination of system dependencies, as outlined in the \n",
@@ -358,8 +359,9 @@
     "Partitioning with the Unstructured API relies on the [Unstructured SDK\n",
     "Client](https://docs.unstructured.io/api-reference/api-services/sdk).\n",
     "\n",
-    "Below is an example showing how you can customize some features of the client and use your own\n",
-    "`requests.Session()`, pass in an alternative `server_url`, or customize the `RetryConfig` object for more control over how failed requests are handled."
+    "Below is an example showing how you can customize some features of the client and use your own `requests.Session()`, pass in an alternative `server_url`, or customize the `RetryConfig` object for more control over how failed requests are handled.\n",
+    "\n",
+    "Note that the example below may not use the latest version of the UnstructuredClient and there could be breaking changes in future releases. For the latest examples, refer to the [Unstructured Python SDK](https://docs.unstructured.io/api-reference/api-services/sdk-python) docs."
    ]
   },
   {

docs/docs/integrations/llms/cohere.ipynb

@@ -108,7 +108,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "model = Cohere(model=\"command\", max_tokens=256, temperature=0.75)"
+    "model = Cohere(max_tokens=256, temperature=0.75)"
    ]
   },
   {

docs/docs/integrations/platforms/aws.mdx

@@ -197,6 +197,24 @@ See a [usage example](/docs/integrations/vectorstores/documentdb).
 ```python
 from langchain.vectorstores import DocumentDBVectorSearch
 ```
+### Amazon MemoryDB 
+[Amazon MemoryDB](https://aws.amazon.com/memorydb/) is a durable, in-memory database service that delivers ultra-fast performance. MemoryDB is compatible with Redis OSS, a popular open source data store, 
+enabling you to quickly build applications using the same flexible and friendly Redis OSS APIs, and commands that they already use today. 
+
+InMemoryVectorStore class provides a vectorstore to connect with Amazon MemoryDB.
+
+```python
+from langchain_aws.vectorstores.inmemorydb import InMemoryVectorStore
+
+vds = InMemoryVectorStore.from_documents(
+            chunks,
+            embeddings,
+            redis_url="rediss://cluster_endpoint:6379/ssl=True ssl_cert_reqs=none",
+            vector_schema=vector_schema,
+            index_name=INDEX_NAME,
+        )
+```
+See a [usage example](/docs/integrations/vectorstores/memorydb).
 
 ## Retrievers
 

docs/docs/integrations/platforms/index.mdx

@@ -1,55 +0,0 @@
----
-sidebar_position: 0
-sidebar_class_name: hidden
----
-
-# Providers
-
-:::info
-
-If you'd like to write your own integration, see [Extending LangChain](/docs/how_to/#custom).
-If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
-
-:::
-
-LangChain integrates with many providers.
-
-## Partner Packages
-
-These providers have standalone `langchain-{provider}` packages for improved versioning, dependency management and testing.
-
-- [AI21](/docs/integrations/providers/ai21)
-- [Airbyte](/docs/integrations/providers/airbyte)
-- [Amazon Web Services](/docs/integrations/platforms/aws)
-- [Anthropic](/docs/integrations/platforms/anthropic)
-- [Astra DB](/docs/integrations/providers/astradb)
-- [Cohere](/docs/integrations/providers/cohere)
-- [Couchbase](/docs/integrations/providers/couchbase)
-- [Elasticsearch](/docs/integrations/providers/elasticsearch)
-- [Exa Search](/docs/integrations/providers/exa_search)
-- [Fireworks](/docs/integrations/providers/fireworks)
-- [Google](/docs/integrations/platforms/google)
-- [Groq](/docs/integrations/providers/groq)
-- [IBM](/docs/integrations/providers/ibm)
-- [MistralAI](/docs/integrations/providers/mistralai)
-- [MongoDB](/docs/integrations/providers/mongodb_atlas)
-- [Nomic](/docs/integrations/providers/nomic)
-- [Nvidia](/docs/integrations/providers/nvidia)
-- [OpenAI](/docs/integrations/platforms/openai)
-- [Pinecone](/docs/integrations/providers/pinecone)
-- [Qdrant](/docs/integrations/providers/qdrant)
-- [Robocorp](/docs/integrations/providers/robocorp)
-- [Together AI](/docs/integrations/providers/together)
-- [Unstructured](/docs/integrations/providers/unstructured)
-- [Upstage](/docs/integrations/providers/upstage)
-- [Voyage AI](/docs/integrations/providers/voyageai)
-
-
-## Featured Community Providers
-
-- [Hugging Face](/docs/integrations/platforms/huggingface)
-- [Microsoft](/docs/integrations/platforms/microsoft)
-
-## All Providers
-
-Click [here](/docs/integrations/providers/) to see all providers.

docs/docs/integrations/providers/cohere.mdx

@@ -46,6 +46,55 @@ print(llm.invoke("Come up with a pet name"))
 ```
 
 Usage of the Cohere (legacy) [LLM model](/docs/integrations/llms/cohere) 
+
+### Tool calling
+```python
+from langchain_cohere import ChatCohere
+from langchain_core.messages import (
+    HumanMessage,
+    ToolMessage,
+)
+from langchain_core.tools import tool
+
+@tool
+def magic_function(number: int) -> int:
+    """Applies a magic operation to an integer
+
+    Args:
+        number: Number to have magic operation performed on
+    """
+    return number + 10
+
+def invoke_tools(tool_calls, messages):
+    for tool_call in tool_calls:
+        selected_tool = {"magic_function":magic_function}[
+            tool_call["name"].lower()
+        ]
+        tool_output = selected_tool.invoke(tool_call["args"])
+        messages.append(ToolMessage(tool_output, tool_call_id=tool_call["id"]))
+    return messages
+
+tools = [magic_function]
+
+llm = ChatCohere()
+llm_with_tools = llm.bind_tools(tools=tools)
+messages = [
+    HumanMessage(
+        content="What is the value of magic_function(2)?"
+    )
+]
+
+res = llm_with_tools.invoke(messages)
+while res.tool_calls:
+    messages.append(res)
+    messages = invoke_tools(res.tool_calls, messages)
+    res = llm_with_tools.invoke(messages)
+
+print(res.content)
+```
+Tool calling with Cohere LLM can be done by binding the necessary tools to the llm as seen above. 
+An alternative, is to support multi hop tool calling with the ReAct agent as seen below.
+
 ### ReAct Agent
 
 The agent is based on the paper
@@ -77,6 +126,7 @@ agent_executor.invoke({
     "input": "In what year was the company that was founded as Sound of Music added to the S&P 500?",
 })
 ```
+The ReAct agent can be used to call multiple tools in sequence.
 
 ### RAG Retriever
 

docs/docs/integrations/providers/dspy.ipynb

@@ -355,7 +355,7 @@
    "id": "859daaee-ac5d-47f8-8704-827f5578bf1b",
    "metadata": {},
    "source": [
-    "## Define a metic\n",
+    "## Define a metric\n",
     "\n",
     "We now need to define a metric. This will be used to determine which runs were successful and we can learn from. Here we will use DSPy's metrics, though you can write your own."
    ]

docs/docs/integrations/retrievers/arxiv.ipynb

@@ -2,14 +2,49 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "9fc6205b",
+   "id": "00a924a0-57e2-43fa-95dc-3ea48a56d3a5",
    "metadata": {},
    "source": [
-    "# Arxiv\n",
+    "---\n",
+    "sidebar_label: Arxiv\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f1b8ddb-8b06-4e7e-b0bb-8786dea15e2b",
+   "metadata": {},
+   "source": [
+    "# ArxivRetriever\n",
+    "\n",
+    "## Overview\n",
     "\n",
     ">[arXiv](https://arxiv.org/) is an open-access archive for 2 million scholarly articles in the fields of physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics.\n",
     "\n",
-    "This notebook shows how to retrieve scientific articles from `Arxiv.org` into the Document format that is used downstream."
+    "This notebook shows how to retrieve scientific articles from Arxiv.org into the [Document](https://api.python.langchain.com/en/latest/documents/langchain_core.documents.base.Document.html) format that is used downstream.\n",
+    "\n",
+    "For detailed documentation of all `ArxivRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.arxiv.ArxivRetriever.html).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Source | Package |\n",
+    "| :--- | :--- | :---: |\n",
+    "[ArxivRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.arxiv.ArxivRetriever.html) | Scholarly articles on [arxiv.org](https://arxiv.org/) | langchain_community |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "75d179b4-abc3-48db-9f8b-1cdb46d3aa77",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
    ]
   },
   {
@@ -17,15 +52,9 @@
    "id": "51489529-5dcd-4b86-bda6-de0a39d8ffd1",
    "metadata": {},
    "source": [
-    "## Installation"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "1435c804-069d-4ade-9a7b-006b97b767c1",
-   "metadata": {},
-   "source": [
-    "First, you need to install `arxiv` python package."
+    "### Installation\n",
+    "\n",
+    "This retriever lives in the `langchain-community` package. We will also need the [arxiv](https://pypi.org/project/arxiv/) dependency:"
    ]
   },
   {
@@ -37,7 +66,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  arxiv"
+    "%pip install -qU langchain-community arxiv"
    ]
   },
   {
@@ -45,54 +74,44 @@
    "id": "6c15470b-a16b-4e0d-bc6a-6998bafbb5a4",
    "metadata": {},
    "source": [
-    "`ArxivRetriever` has these arguments:\n",
+    "## Instantiation\n",
+    "\n",
+    "`ArxivRetriever` parameters include:\n",
     "- optional `load_max_docs`: default=100. Use it to limit number of downloaded documents. It takes time to download all 100 documents, so use a small number for experiments. There is a hard limit of 300 for now.\n",
     "- optional `load_all_available_meta`: default=False. By default only the most important fields downloaded: `Published` (date when document was published/last updated), `Title`, `Authors`, `Summary`. If True, other fields also downloaded.\n",
+    "- `get_full_documents`: boolean, default False. Determines whether to fetch full text of documents.\n",
     "\n",
-    "`get_relevant_documents()` has one argument, `query`: free text which used to find documents in `Arxiv.org`"
+    "See [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.arxiv.ArxivRetriever.html) for more detail."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a13f9e92-24b3-4cea-8541-2584c1cdb2d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.retrievers import ArxivRetriever\n",
+    "\n",
+    "retriever = ArxivRetriever(\n",
+    "    load_max_docs=2,\n",
+    "    get_ful_documents=True,\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "ae3c3d16",
+   "id": "30c27047-16cf-46b5-bb29-754f1696f2bb",
    "metadata": {},
    "source": [
-    "## Examples"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6fafb73b-d6ec-4822-b161-edf0aaf5224a",
-   "metadata": {},
-   "source": [
-    "### Running retriever"
+    "## Usage\n",
+    "\n",
+    "`ArxivRetriever` supports retrieval by article identifier:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "id": "d0e6f506",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain_community.retrievers import ArxivRetriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "f381f642",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "retriever = ArxivRetriever(load_max_docs=2)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "id": "20ae1a74",
    "metadata": {},
    "outputs": [],
@@ -102,20 +121,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 3,
    "id": "1d5a5088",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'Published': '2016-05-26',\n",
+       "{'Entry ID': 'http://arxiv.org/abs/1605.08386v1',\n",
+       " 'Published': datetime.date(2016, 5, 26),\n",
        " 'Title': 'Heat-bath random walks with Markov bases',\n",
-       " 'Authors': 'Caprice Stanley, Tobias Windisch',\n",
-       " 'Summary': 'Graphs on lattice points are studied whose edges come from a finite set of\\nallowed moves of arbitrary length. We show that the diameter of these graphs on\\nfibers of a fixed integer matrix can be bounded from above by a constant. We\\nthen study the mixing behaviour of heat-bath random walks on these graphs. We\\nalso state explicit conditions on the set of moves so that the heat-bath random\\nwalk, a generalization of the Glauber dynamics, is an expander in fixed\\ndimension.'}"
+       " 'Authors': 'Caprice Stanley, Tobias Windisch'}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -126,17 +145,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 4,
    "id": "c0ccd0c7-f6a6-43e7-b842-5f57afb94224",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'arXiv:1605.08386v1  [math.CO]  26 May 2016\\nHEAT-BATH RANDOM WALKS WITH MARKOV BASES\\nCAPRICE STANLEY AND TOBIAS WINDISCH\\nAbstract. Graphs on lattice points are studied whose edges come from a finite set of\\nallowed moves of arbitrary length. We show that the diameter of these graphs on fibers of a\\nfixed integer matrix can be bounded from above by a constant. We then study the mixing\\nbehaviour of heat-b'"
+       "'Graphs on lattice points are studied whose edges come from a finite set of\\nallowed moves of arbitrary length. We show that the diameter of these graphs on\\nfibers of a fixed integer matrix can be bounded from above by a constant. We\\nthen study the mixing behaviour of heat-bath random walks on these graphs. We\\nalso state explicit conditions on the set of moves so that the heat-bath random\\nwalk, a ge'"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -147,159 +166,143 @@
   },
   {
    "cell_type": "markdown",
-   "id": "2670363b-3806-4c7e-b14d-90a4d5d2a200",
+   "id": "c525c5c2-0961-4f4c-a208-dd6ceed76ea1",
    "metadata": {},
    "source": [
-    "### Question Answering on facts"
+    "`ArxivRetriever` also supports retrieval based on natural language text:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 5,
+   "id": "4cd3d079-4496-4ab8-adff-b86e6418bc74",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = retriever.invoke(\"What is the ImageBind model?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9318c790-d388-45da-8d5c-57256619e2a1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'Entry ID': 'http://arxiv.org/abs/2305.05665v2',\n",
+       " 'Published': datetime.date(2023, 5, 31),\n",
+       " 'Title': 'ImageBind: One Embedding Space To Bind Them All',\n",
+       " 'Authors': 'Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, Mannat Singh, Kalyan Vasudev Alwala, Armand Joulin, Ishan Misra'}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0].metadata"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2670363b-3806-4c7e-b14d-90a4d5d2a200",
+   "metadata": {},
+   "source": [
+    "## Use within a chain\n",
+    "\n",
+    "Like other retrievers, `ArxivRetriever` can be incorporated into LLM applications via [chains](/docs/how_to/sequence/).\n",
+    "\n",
+    "We will need a LLM or chat model:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"llm\" />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "bcbeeaf5-79d1-4e29-8589-11dfb26761af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
    "id": "bb3601df-53ea-4826-bdbe-554387bc3ad4",
    "metadata": {
     "tags": []
    },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      " ········\n"
-     ]
-    }
-   ],
-   "source": [
-    "# get a token: https://platform.openai.com/account/api-keys\n",
-    "\n",
-    "from getpass import getpass\n",
-    "\n",
-    "OPENAI_API_KEY = getpass()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "e9c1a114-0410-4804-be30-05f34a9760f9",
-   "metadata": {
-    "tags": []
-   },
    "outputs": [],
    "source": [
-    "import os\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
     "\n",
-    "os.environ[\"OPENAI_API_KEY\"] = OPENAI_API_KEY"
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the question based only on the context provided.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
-   "id": "51a33cc9-ec42-4afc-8a2d-3bfff476aa59",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.chains import ConversationalRetrievalChain\n",
-    "from langchain_openai import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")  # switch to 'gpt-4'\n",
-    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "ea537767-a8bf-4adf-ae03-b353c9145d58",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "-> **Question**: What are Heat-bath random walks with Markov base? \n",
-      "\n",
-      "**Answer**: I'm not sure, as I don't have enough context to provide a definitive answer. The term \"Heat-bath random walks with Markov base\" is not mentioned in the given text. Could you provide more information or context about where you encountered this term? \n",
-      "\n",
-      "-> **Question**: What is the ImageBind model? \n",
-      "\n",
-      "**Answer**: ImageBind is an approach developed by Facebook AI Research to learn a joint embedding across six different modalities, including images, text, audio, depth, thermal, and IMU data. The approach uses the binding property of images to align each modality's embedding to image embeddings and achieve an emergent alignment across all modalities. This enables novel multimodal capabilities, including cross-modal retrieval, embedding-space arithmetic, and audio-to-image generation, among others. The approach sets a new state-of-the-art on emergent zero-shot recognition tasks across modalities, outperforming specialist supervised models. Additionally, it shows strong few-shot recognition results and serves as a new way to evaluate vision models for visual and non-visual tasks. \n",
-      "\n",
-      "-> **Question**: How does Compositional Reasoning with Large Language Models works? \n",
-      "\n",
-      "**Answer**: Compositional reasoning with large language models refers to the ability of these models to correctly identify and represent complex concepts by breaking them down into smaller, more basic parts and combining them in a structured way. This involves understanding the syntax and semantics of language and using that understanding to build up more complex meanings from simpler ones. \n",
-      "\n",
-      "In the context of the paper \"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models\", the authors focus specifically on the ability of a large pretrained vision and language model (CLIP) to encode compositional concepts and to bind variables in a structure-sensitive way. They examine CLIP's ability to compose concepts in a single-object setting, as well as in situations where concept binding is needed. \n",
-      "\n",
-      "The authors situate their work within the tradition of research on compositional distributional semantics models (CDSMs), which seek to bridge the gap between distributional models and formal semantics by building architectures which operate over vectors yet still obey traditional theories of linguistic composition. They compare the performance of CLIP with several architectures from research on CDSMs to evaluate its ability to encode and reason about compositional concepts. \n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "questions = [\n",
-    "    \"What are Heat-bath random walks with Markov base?\",\n",
-    "    \"What is the ImageBind model?\",\n",
-    "    \"How does Compositional Reasoning with Large Language Models works?\",\n",
-    "]\n",
-    "chat_history = []\n",
-    "\n",
-    "for question in questions:\n",
-    "    result = qa({\"question\": question, \"chat_history\": chat_history})\n",
-    "    chat_history.append((question, result[\"answer\"]))\n",
-    "    print(f\"-> **Question**: {question} \\n\")\n",
-    "    print(f\"**Answer**: {result['answer']} \\n\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "id": "8e0c3fc6-ae62-4036-a885-dc60176a7745",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "-> **Question**: What are Heat-bath random walks with Markov base? Include references to answer. \n",
-      "\n",
-      "**Answer**: Heat-bath random walks with Markov base (HB-MB) is a class of stochastic processes that have been studied in the field of statistical mechanics and condensed matter physics. In these processes, a particle moves in a lattice by making a transition to a neighboring site, which is chosen according to a probability distribution that depends on the energy of the particle and the energy of its surroundings.\n",
-      "\n",
-      "The HB-MB process was introduced by Bortz, Kalos, and Lebowitz in 1975 as a way to simulate the dynamics of interacting particles in a lattice at thermal equilibrium. The method has been used to study a variety of physical phenomena, including phase transitions, critical behavior, and transport properties.\n",
-      "\n",
-      "References:\n",
-      "\n",
-      "Bortz, A. B., Kalos, M. H., & Lebowitz, J. L. (1975). A new algorithm for Monte Carlo simulation of Ising spin systems. Journal of Computational Physics, 17(1), 10-18.\n",
-      "\n",
-      "Binder, K., & Heermann, D. W. (2010). Monte Carlo simulation in statistical physics: an introduction. Springer Science & Business Media. \n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "questions = [\n",
-    "    \"What are Heat-bath random walks with Markov base? Include references to answer.\",\n",
-    "]\n",
-    "chat_history = []\n",
-    "\n",
-    "for question in questions:\n",
-    "    result = qa({\"question\": question, \"chat_history\": chat_history})\n",
-    "    chat_history.append((question, result[\"answer\"]))\n",
-    "    print(f\"-> **Question**: {question} \\n\")\n",
-    "    print(f\"**Answer**: {result['answer']} \\n\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "09794ab5-759c-4b56-95d4-2454d4d86da1",
+   "execution_count": 9,
+   "id": "62889c3c-8a49-4c76-9141-d777311af1f4",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The ImageBind model is an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. It shows that only image-paired data is sufficient to bind the modalities together and can leverage large scale vision-language models for zero-shot capabilities and emergent applications such as cross-modal retrieval, composing modalities with arithmetic, cross-modal detection and generation.'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.invoke(\"What is the ImageBind model?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e419acb8-d7ac-42a1-916f-c796f23dce9b",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `ArxivRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.arxiv.ArxivRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -318,7 +321,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/retrievers/azure_ai_search.ipynb

@@ -2,15 +2,39 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "1edb9e6b",
+   "id": "f9a62e19-b00b-4f6c-a700-1e500e4c290a",
    "metadata": {},
    "source": [
-    "# Azure AI Search\n",
+    "---\n",
+    "sidebar_label: Azure AI Search\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "76f74245-7220-4446-ae8d-4e5a9e998f1f",
+   "metadata": {},
+   "source": [
+    "# AzureAISearchRetriever\n",
     "\n",
+    "## Overview\n",
     "[Azure AI Search](https://learn.microsoft.com/azure/search/search-what-is-azure-search) (formerly known as `Azure Cognitive Search`) is a Microsoft cloud search service that gives developers infrastructure, APIs, and tools for information retrieval of vector, keyword, and hybrid queries at scale.\n",
     "\n",
     "`AzureAISearchRetriever` is an integration module that returns documents from an unstructured query. It's based on the BaseRetriever class and it targets the 2023-11-01 stable REST API version of Azure AI Search, which means it supports vector indexing and queries.\n",
     "\n",
+    "This guide will help you getting started with the Azure AI Search [retriever](/docs/concepts/#retrievers). For detailed documentation of all `AzureAISearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.azure_ai_search.AzureAISearchRetriever.html).\n",
+    "\n",
+    "`AzureAISearchRetriever` replaces `AzureCognitiveSearchRetriever`, which will soon be deprecated. We recommend switching to the newer version that's based on the most recent stable version of the search APIs.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Self-host | Cloud offering | Package |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[AzureAISearchRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.azure_ai_search.AzureAISearchRetriever.html) | ❌ | ✅ | langchain_community |\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
     "To use this module, you need:\n",
     "\n",
     "+ An Azure AI Search service. You can [create one](https://learn.microsoft.com/azure/search/search-create-service-portal) for free if you sign up for the Azure trial. A free service has lower quotas, but it's sufficient for running the code in this notebook.\n",
@@ -19,7 +43,40 @@
     "\n",
     "+ An API key. API keys are generated when you create the search service. If you're just querying an index, you can use the query API key, otherwise use an admin API key. See [Find your API keys](https://learn.microsoft.com/azure/search/search-security-api-keys?tabs=rest-use%2Cportal-find%2Cportal-query#find-existing-keys) for details.\n",
     "\n",
-    "`AzureAISearchRetriever` replaces `AzureCognitiveSearchRetriever`, which will soon be deprecated. We recommend switching to the newer version that's based on the most recent stable version of the search APIs."
+    "We can then set the search service name, index name, and API key as environment variables (alternatively, you can pass them as arguments to `AzureAISearchRetriever`). The search index provides the searchable content."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a56e83b-8563-4479-ab61-090fc79f5b00",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"AZURE_AI_SEARCH_SERVICE_NAME\"] = \"<YOUR_SEARCH_SERVICE_NAME>\"\n",
+    "os.environ[\"AZURE_AI_SEARCH_INDEX_NAME\"] = \"<YOUR_SEARCH_INDEX_NAME>\"\n",
+    "os.environ[\"AZURE_AI_SEARCH_API_KEY\"] = \"<YOUR_API_KEY>\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3e635218-8634-4f39-abc5-39e319eeb136",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88751b84-7cb7-4dd2-af35-c1e9b369d012",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
    ]
   },
   {
@@ -27,9 +84,9 @@
    "id": "f99d4456",
    "metadata": {},
    "source": [
-    "## Install packages\n",
+    "### Installation\n",
     "\n",
-    "Use azure-documents-search package 11.4 or later."
+    "This retriever lives in the `langchain-community` package. We will need some additional dependencies as well:"
    ]
   },
   {
@@ -39,9 +96,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet langchain\n",
+    "%pip install --upgrade --quiet langchain-community\n",
     "%pip install --upgrade --quiet langchain-openai\n",
-    "%pip install --upgrade --quiet  azure-search-documents\n",
+    "%pip install --upgrade --quiet  azure-search-documents>=11.4\n",
     "%pip install --upgrade --quiet  azure-identity"
    ]
   },
@@ -50,7 +107,9 @@
    "id": "0474661d",
    "metadata": {},
    "source": [
-    "## Import required libraries"
+    "## Instantiation\n",
+    "\n",
+    "For `AzureAISearchRetriever`, provide an `index_name`, `content_key`, and `top_k` set to the number of number of results you'd like to retrieve. Setting `top_k` to zero (the default) returns all results."
    ]
   },
   {
@@ -60,52 +119,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import os\n",
+    "from langchain_community.retrievers import AzureAISearchRetriever\n",
     "\n",
-    "from langchain_community.retrievers import (\n",
-    "    AzureAISearchRetriever,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "b7243e6d",
-   "metadata": {},
-   "source": [
-    "## Configure search settings\n",
-    "\n",
-    "Set the search service name, index name, and API key as environment variables (alternatively, you can pass them as arguments to `AzureAISearchRetriever`). The search index provides the searchable content. "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "33fd23d1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "os.environ[\"AZURE_AI_SEARCH_SERVICE_NAME\"] = \"<YOUR_SEARCH_SERVICE_NAME>\"\n",
-    "os.environ[\"AZURE_AI_SEARCH_INDEX_NAME\"] = \"<YOUR_SEARCH_INDEX_NAME>\"\n",
-    "os.environ[\"AZURE_AI_SEARCH_API_KEY\"] = \"<YOUR_API_KEY>\""
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "057deaad",
-   "metadata": {},
-   "source": [
-    "## Create the retriever\n",
-    "\n",
-    "For `AzureAISearchRetriever`, provide an `index_name`, `content_key`, and `top_k` set to the number of number of results you'd like to retrieve. Setting `top_k` to zero (the default) returns all results."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "c18d0c4c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "retriever = AzureAISearchRetriever(\n",
     "    content_key=\"content\", top_k=1, index_name=\"langchain-vector-demo\"\n",
     ")"
@@ -116,6 +131,8 @@
    "id": "e94ea104",
    "metadata": {},
    "source": [
+    "## Usage\n",
+    "\n",
     "Now you can use it to retrieve documents from Azure AI Search. \n",
     "This is the method you would call to do so. It will return all documents relevant to the query. "
    ]
@@ -259,6 +276,69 @@
    "source": [
     "retriever.invoke(\"does the president have a plan for covid-19?\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dd6c9ba9-978f-4e2c-9cc7-ccd1be58eafb",
+   "metadata": {},
+   "source": [
+    "## Use within a chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cbcd8ac6-12ea-4c22-8a98-c24825d598d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the question based only on the context provided.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "db80f3c7-83e1-4965-8ff2-a3dd66a07f0e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"does the president have a plan for covid-19?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a3d6140e-c2a0-40b2-a141-cab61ab39185",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `AzureAISearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.azure_ai_search.AzureAISearchRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -277,7 +357,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/retrievers/bedrock.ipynb

@@ -1,19 +1,86 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b0872249-1af5-4d54-b816-1babad7a8c9e",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: Bedrock (Knowledge Bases)\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b6636c27-35da-4ba7-8313-eca21660cab3",
    "metadata": {},
    "source": [
-    "# Bedrock (Knowledge Bases)\n",
+    "# Bedrock (Knowledge Bases) Retriever\n",
     "\n",
-    "> [Knowledge bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/) is an Amazon Web Services (AWS) offering which lets you quickly build RAG applications by using your private data to customize FM response.\n",
+    "## Overview\n",
     "\n",
-    "> Implementing `RAG` requires organizations to perform several cumbersome steps to convert data into embeddings (vectors), store the embeddings in a specialized vector database, and build custom integrations into the database to search and retrieve text relevant to the user’s query. This can be time-consuming and inefficient.\n",
+    "This guide will help you getting started with the AWS Knowledge Bases [retriever](/docs/concepts/#retrievers).\n",
     "\n",
-    "> With `Knowledge Bases for Amazon Bedrock`, simply point to the location of your data in `Amazon S3`, and `Knowledge Bases for Amazon Bedrock` takes care of the entire ingestion workflow into your vector database. If you do not have an existing vector database, Amazon Bedrock creates an Amazon OpenSearch Serverless vector store for you. For retrievals, use the Langchain - Amazon Bedrock integration via the Retrieve API to retrieve relevant results for a user query from knowledge bases.\n",
+    "[Knowledge Bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/) is an Amazon Web Services (AWS) offering which lets you quickly build RAG applications by using your private data to customize FM response.\n",
     "\n",
-    "> Knowledge base can be configured through [AWS Console](https://aws.amazon.com/console/) or by using [AWS SDKs](https://aws.amazon.com/developer/tools/)."
+    "Implementing `RAG` requires organizations to perform several cumbersome steps to convert data into embeddings (vectors), store the embeddings in a specialized vector database, and build custom integrations into the database to search and retrieve text relevant to the user’s query. This can be time-consuming and inefficient.\n",
+    "\n",
+    "With `Knowledge Bases for Amazon Bedrock`, simply point to the location of your data in `Amazon S3`, and `Knowledge Bases for Amazon Bedrock` takes care of the entire ingestion workflow into your vector database. If you do not have an existing vector database, Amazon Bedrock creates an Amazon OpenSearch Serverless vector store for you. For retrievals, use the Langchain - Amazon Bedrock integration via the Retrieve API to retrieve relevant results for a user query from knowledge bases.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Self-host | Cloud offering | Package |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[AmazonKnowledgeBasesRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_aws.retrievers.bedrock.AmazonKnowledgeBasesRetriever.html) | ❌ | ✅ | langchain_aws |\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cd092536-61bd-4b3f-9050-076daccc9e72",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "Knowledge Bases can be configured through [AWS Console](https://aws.amazon.com/console/) or by using [AWS SDKs](https://aws.amazon.com/developer/tools/). We will need the `knowledge_base_id` to instantiate the retriever."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "238c0ceb-d4b6-409e-bed9-d30143d2f2c9",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e4426098-820c-48dc-9826-056a91bebe9e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ede6277-ea56-45f6-8ef4-fe14734ee279",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This retriever lives in the `langchain-aws` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4db1af24-0969-43bd-8438-af5e3024b0d0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-aws"
    ]
   },
   {
@@ -21,17 +88,9 @@
    "id": "b34c8cbe-c6e5-4398-adf1-4925204bcaed",
    "metadata": {},
    "source": [
-    "## Using the Knowledge Bases Retriever"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "26c97d36-911c-4fe0-a478-546192728f30",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet  boto3"
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our retriever:"
    ]
   },
   {
@@ -41,7 +100,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.retrievers import AmazonKnowledgeBasesRetriever\n",
+    "from langchain_aws.retrievers import AmazonKnowledgeBasesRetriever\n",
     "\n",
     "retriever = AmazonKnowledgeBasesRetriever(\n",
     "    knowledge_base_id=\"PUIJP4EQUA\",\n",
@@ -49,6 +108,14 @@
     ")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "9dff39f8-b6ba-41bf-b95b-d345928ed07d",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -66,7 +133,7 @@
    "id": "7de9b61b-597b-4aba-95fb-49d11e84510e",
    "metadata": {},
    "source": [
-    "### Using in a QA Chain"
+    "## Use within a chain"
    ]
   },
   {
@@ -78,7 +145,7 @@
    "source": [
     "from botocore.client import Config\n",
     "from langchain.chains import RetrievalQA\n",
-    "from langchain_community.llms import Bedrock\n",
+    "from langchain_aws import Bedrock\n",
     "\n",
     "model_kwargs_claude = {\"temperature\": 0, \"top_k\": 10, \"max_tokens_to_sample\": 3000}\n",
     "\n",
@@ -90,6 +157,16 @@
     "\n",
     "qa(query)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "22e2538a-e042-4997-bb81-b68ecb27d665",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `AmazonKnowledgeBasesRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_aws.retrievers.bedrock.AmazonKnowledgeBasesRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -108,7 +185,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/retrievers/cohere.ipynb

@@ -34,8 +34,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_cohere import ChatCohere\n",
-    "from langchain_community.retrievers import CohereRagRetriever\n",
+    "from langchain_cohere import ChatCohere, CohereRagRetriever\n",
     "from langchain_core.documents import Document"
    ]
   },
@@ -200,7 +199,7 @@
    "source": [
     "docs = rag.invoke(\n",
     "    \"Does langchain support cohere RAG?\",\n",
-    "    source_documents=[\n",
+    "    documents=[\n",
     "        Document(page_content=\"Langchain supports cohere RAG!\"),\n",
     "        Document(page_content=\"The sky is blue!\"),\n",
     "    ],\n",
@@ -208,6 +207,14 @@
     "_pretty_print(docs)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "45a9470f",
+   "metadata": {},
+   "source": [
+    "Please note that connectors and documents cannot be used simultaneously. If you choose to provide documents in the `invoke` method, they will take precedence, and connectors will not be utilized for that particular request, as shown in the snippet above!"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,

docs/docs/integrations/retrievers/elasticsearch_retriever.ipynb

@@ -2,14 +2,72 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "ab66dd43",
+   "id": "41ccce84-f6d9-4ba0-8281-22cbf29f20d3",
    "metadata": {},
    "source": [
-    "# Elasticsearch\n",
+    "---\n",
+    "sidebar_label: Elasticsearch\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "54c4d916-05db-4e01-9893-c711904205b3",
+   "metadata": {},
+   "source": [
+    "# ElasticsearchRetriever\n",
     "\n",
+    "## Overview\n",
     ">[Elasticsearch](https://www.elastic.co/elasticsearch/) is a distributed, RESTful search and analytics engine. It provides a distributed, multitenant-capable full-text search engine with an HTTP web interface and schema-free JSON documents. It supports keyword search, vector search, hybrid search and complex filtering.\n",
     "\n",
-    "The `ElasticsearchRetriever` is a generic wrapper to enable flexible access to all `Elasticsearch` features through the [Query DSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html).  For most use cases the other classes (`ElasticsearchStore`, `ElasticsearchEmbeddings`, etc.) should suffice, but if they don't you can use `ElasticsearchRetriever`."
+    "The `ElasticsearchRetriever` is a generic wrapper to enable flexible access to all `Elasticsearch` features through the [Query DSL](https://www.elastic.co/guide/en/elasticsearch/reference/current/query-dsl.html).  For most use cases the other classes (`ElasticsearchStore`, `ElasticsearchEmbeddings`, etc.) should suffice, but if they don't you can use `ElasticsearchRetriever`.\n",
+    "\n",
+    "This guide will help you getting started with the Elasticsearch [retriever](/docs/concepts/#retrievers). For detailed documentation of all `ElasticsearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_elasticsearch.retrievers.ElasticsearchRetriever.html).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Self-host | Cloud offering | Package |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[ElasticsearchRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_elasticsearch.retrievers.ElasticsearchRetriever.html) | ✅ | ✅ | langchain_elasticsearch |\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "There are two main ways to set up an Elasticsearch instance:\n",
+    "\n",
+    "- Elastic Cloud: [Elastic Cloud](https://cloud.elastic.co/) is a managed Elasticsearch service. Sign up for a [free trial](https://www.elastic.co/cloud/cloud-trial-overview).\n",
+    "To connect to an Elasticsearch instance that does not require login credentials (starting the docker instance with security enabled), pass the Elasticsearch URL and index name along with the embedding object to the constructor.\n",
+    "\n",
+    "- Local Install Elasticsearch: Get started with Elasticsearch by running it locally. The easiest way is to use the official Elasticsearch Docker image. See the [Elasticsearch Docker documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/docker.html) for more information."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e13a7b58-3a56-4ce6-a4d5-81a8dd2080df",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "492b81d0-c85b-4693-ae4f-3f33da571ddd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "78335745-f14d-411d-9c06-64ff83eb9358",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This retriever lives in the `langchain-elasticsearch` package. For demonstration purposes, we will also install `langchain-community` to generate text [embeddings](/docs/concepts/#embedding-models)."
    ]
   },
   {
@@ -21,7 +79,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet elasticsearch langchain-elasticsearch"
+    "%pip install -qU langchain-community langchain-elasticsearch"
    ]
   },
   {
@@ -48,7 +106,7 @@
    "id": "24c0d140",
    "metadata": {},
    "source": [
-    "## Configure\n",
+    "### Configure\n",
     "\n",
     "Here we define the conncection to Elasticsearch. In this example we use a locally running instance. Alternatively, you can make an account in [Elastic Cloud](https://cloud.elastic.co/) and start a [free trial](https://www.elastic.co/cloud/cloud-trial-overview)."
    ]
@@ -70,7 +128,7 @@
    "id": "60aa7c20",
    "metadata": {},
    "source": [
-    "For vector search, we are going to use random embeddings just for illustration. For real use cases, pick one of the available LangChain `Embeddings` classes."
+    "For vector search, we are going to use random embeddings just for illustration. For real use cases, pick one of the available LangChain [Embeddings](/docs/integrations/text_embedding) classes."
    ]
   },
   {
@@ -88,7 +146,7 @@
    "id": "b4eea654",
    "metadata": {},
    "source": [
-    "## Define example data"
+    "#### Define example data"
    ]
   },
   {
@@ -118,7 +176,7 @@
    "id": "1c518c42",
    "metadata": {},
    "source": [
-    "## Index data\n",
+    "#### Index data\n",
     "\n",
     "Typically, users make use of `ElasticsearchRetriever` when they already have data in an Elasticsearch index. Here we index some example text documents. If you created an index for example using `ElasticsearchStore.from_documents` that's also fine."
    ]
@@ -209,14 +267,8 @@
    "id": "08437fa2",
    "metadata": {},
    "source": [
-    "## Usage examples"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "469aa295",
-   "metadata": {},
-   "source": [
+    "## Instantiation\n",
+    "\n",
     "### Vector search\n",
     "\n",
     "Dense vector retrival using fake embeddings in this example."
@@ -543,6 +595,91 @@
     "\n",
     "custom_mapped_retriever.invoke(\"foo\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1663feff-4527-4fb0-9395-b28af5c9ec99",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
+    "\n",
+    "Following the above examples, we use `.invoke` to issue a single query. Because retrievers are Runnables, we can use any method in the [Runnable interface](/docs/concepts/#runnable-interface), such as `.batch`, as well."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f4f946ed-ff3a-43d7-9e0d-7983ff13c868",
+   "metadata": {},
+   "source": [
+    "## Use within a chain\n",
+    "\n",
+    "We can also incorporate retrievers into [chains](/docs/how_to/sequence/) to build larger applications, such as a simple [RAG](/docs/tutorials/rag/) application. For demonstration purposes, we instantiate an OpenAI chat model as well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19302ef1-dd49-4f9c-8d87-4ea23b8296e2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "832857a7-3b16-4a85-acc7-28efe6ebdae8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the question based only on the context provided.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"context\": vector_retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7317942b-7c9a-477d-ba11-3421da804a22",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"what is foo?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eeb49714-ba5a-4b10-8e58-67d061a486d1",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `ElasticsearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_elasticsearch.retrievers.ElasticsearchRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -561,7 +698,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/retrievers/google_vertex_ai_search.ipynb

@@ -1,27 +1,44 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: Google Vertex AI Search\n",
+    "---"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "# Google Vertex AI Search\n",
     "\n",
+    "## Overview\n",
+    "\n",
     ">[Google Vertex AI Search](https://cloud.google.com/enterprise-search) (formerly known as `Enterprise Search` on `Generative AI App Builder`) is a part of the [Vertex AI](https://cloud.google.com/vertex-ai) machine learning platform offered by `Google Cloud`.\n",
     ">\n",
     ">`Vertex AI Search` lets organizations quickly build generative AI-powered search engines for customers and employees. It's underpinned by a variety of `Google Search` technologies, including semantic search, which helps deliver more relevant results than traditional keyword-based search techniques by using natural language processing and machine learning techniques to infer relationships within the content and intent from the user’s query input. Vertex AI Search also benefits from Google’s expertise in understanding how users search and factors in content relevance to order displayed results.\n",
     "\n",
     ">`Vertex AI Search` is available in the `Google Cloud Console` and via an API for enterprise workflow integration.\n",
     "\n",
-    "This notebook demonstrates how to configure `Vertex AI Search` and use the Vertex AI Search retriever. The Vertex AI Search retriever encapsulates the [Python client library](https://cloud.google.com/generative-ai-app-builder/docs/libraries#client-libraries-install-python) and uses it to access the [Search Service API](https://cloud.google.com/python/docs/reference/discoveryengine/latest/google.cloud.discoveryengine_v1beta.services.search_service).\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Install pre-requisites\n",
+    "This notebook demonstrates how to configure `Vertex AI Search` and use the Vertex AI Search [retriever](/docs/concepts/#retrievers). The Vertex AI Search retriever encapsulates the [Python client library](https://cloud.google.com/generative-ai-app-builder/docs/libraries#client-libraries-install-python) and uses it to access the [Search Service API](https://cloud.google.com/python/docs/reference/discoveryengine/latest/google.cloud.discoveryengine_v1beta.services.search_service).\n",
     "\n",
-    "You need to install the `google-cloud-discoveryengine` package to use the Vertex AI Search retriever.\n"
+    "For detailed documentation of all `VertexAISearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/vertex_ai_search/langchain_google_community.vertex_ai_search.VertexAISearchRetriever.html).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Self-host | Cloud offering | Package |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[VertexAISearchRetriever](https://api.python.langchain.com/en/latest/vertex_ai_search/langchain_google_community.vertex_ai_search.VertexAISearchRetriever.html) | ❌ | ✅ | langchain_google_community |\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "### Installation\n",
+    "\n",
+    "You need to install the `langchain-google-community` and `google-cloud-discoveryengine` packages to use the Vertex AI Search retriever."
    ]
   },
   {
@@ -30,14 +47,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet google-cloud-discoveryengine"
+    "%pip install -qU langchain-google-community google-cloud-discoveryengine"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Configure access to Google Cloud and Vertex AI Search\n",
+    "### Configure access to Google Cloud and Vertex AI Search\n",
     "\n",
     "Vertex AI Search is generally available without allowlist as of August 2023.\n",
     "\n",
@@ -48,7 +65,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Create a search engine and populate an unstructured data store\n",
+    "#### Create a search engine and populate an unstructured data store\n",
     "\n",
     "- Follow the instructions in the [Vertex AI Search Getting Started guide](https://cloud.google.com/generative-ai-app-builder/docs/try-enterprise-search) to set up a Google Cloud project and Vertex AI Search.\n",
     "- [Use the Google Cloud Console to create an unstructured data store](https://cloud.google.com/generative-ai-app-builder/docs/create-engine-es#unstructured-data)\n",
@@ -60,7 +77,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Set credentials to access Vertex AI Search API\n",
+    "#### Set credentials to access Vertex AI Search API\n",
     "\n",
     "The [Vertex AI Search client libraries](https://cloud.google.com/generative-ai-app-builder/docs/libraries) used by the Vertex AI Search retriever provide high-level language support for authenticating to Google Cloud programmatically.\n",
     "Client libraries support [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/application-default-credentials); the libraries look for credentials in a set of defined locations and use those credentials to authenticate requests to the API.\n",
@@ -87,16 +104,16 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Configure and use the Vertex AI Search retriever\n",
+    "### Configure and use the Vertex AI Search retriever\n",
     "\n",
-    "The Vertex AI Search retriever is implemented in the `langchain.retriever.GoogleVertexAISearchRetriever` class. The `get_relevant_documents` method returns a list of `langchain.schema.Document` documents where the `page_content` field of each document is populated the document content.\n",
+    "The Vertex AI Search retriever is implemented in the `langchain_google_community.VertexAISearchRetriever` class. The `get_relevant_documents` method returns a list of `langchain.schema.Document` documents where the `page_content` field of each document is populated the document content.\n",
     "Depending on the data type used in Vertex AI Search (website, structured or unstructured) the `page_content` field is populated as follows:\n",
     "\n",
     "- Website with advanced indexing: an `extractive answer` that matches a query. The `metadata` field is populated with metadata (if any) of the document from which the segments or answers were extracted.\n",
     "- Unstructured data source: either an `extractive segment` or an `extractive answer` that matches a query. The `metadata` field is populated with metadata (if any) of the document from which the segments or answers were extracted.\n",
     "- Structured data source: a string json containing all the fields returned from the structured data source. The `metadata` field is populated with metadata (if any) of the document\n",
     "\n",
-    "### Extractive answers & extractive segments\n",
+    "#### Extractive answers & extractive segments\n",
     "\n",
     "An extractive answer is verbatim text that is returned with each search result. It is extracted directly from the original document. Extractive answers are typically displayed near the top of web pages to provide an end user with a brief answer that is contextually relevant to their query. Extractive answers are available for website and unstructured search.\n",
     "\n",
@@ -108,7 +125,7 @@
     "\n",
     "When creating an instance of the retriever you can specify a number of parameters that control which data store to access and how a natural language query is processed, including configurations for extractive answers and segments.\n",
     "\n",
-    "### The mandatory parameters are:\n",
+    "#### The mandatory parameters are:\n",
     "\n",
     "- `project_id` - Your Google Cloud Project ID.\n",
     "- `location_id` - The location of the data store.\n",
@@ -148,15 +165,15 @@
     "\n",
     "To update to the new retriever, make the following changes:\n",
     "\n",
-    "- Change the import from: `from langchain.retrievers import GoogleCloudEnterpriseSearchRetriever` -> `from langchain.retrievers import GoogleVertexAISearchRetriever`.\n",
-    "- Change all class references from `GoogleCloudEnterpriseSearchRetriever` -> `GoogleVertexAISearchRetriever`.\n"
+    "- Change the import from: `from langchain.retrievers import GoogleCloudEnterpriseSearchRetriever` -> `from langchain_google_community import VertexAISearchRetriever`.\n",
+    "- Change all class references from `GoogleCloudEnterpriseSearchRetriever` -> `VertexAISearchRetriever`.\n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Configure and use the retriever for **unstructured** data with extractive segments\n"
+    "Note: When using the retriever, if you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
@@ -165,9 +182,28 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.retrievers import (\n",
-    "    GoogleVertexAIMultiTurnSearchRetriever,\n",
-    "    GoogleVertexAISearchRetriever,\n",
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "### Configure and use the retriever for **unstructured** data with extractive segments"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_google_community import (\n",
+    "    VertexAIMultiTurnSearchRetriever,\n",
+    "    VertexAISearchRetriever,\n",
     ")\n",
     "\n",
     "PROJECT_ID = \"<YOUR PROJECT ID>\"  # Set to your Project ID\n",
@@ -182,7 +218,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = GoogleVertexAISearchRetriever(\n",
+    "retriever = VertexAISearchRetriever(\n",
     "    project_id=PROJECT_ID,\n",
     "    location_id=LOCATION_ID,\n",
     "    data_store_id=DATA_STORE_ID,\n",
@@ -216,7 +252,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = GoogleVertexAISearchRetriever(\n",
+    "retriever = VertexAISearchRetriever(\n",
     "    project_id=PROJECT_ID,\n",
     "    location_id=LOCATION_ID,\n",
     "    data_store_id=DATA_STORE_ID,\n",
@@ -243,7 +279,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = GoogleVertexAISearchRetriever(\n",
+    "retriever = VertexAISearchRetriever(\n",
     "    project_id=PROJECT_ID,\n",
     "    location_id=LOCATION_ID,\n",
     "    data_store_id=DATA_STORE_ID,\n",
@@ -269,7 +305,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = GoogleVertexAISearchRetriever(\n",
+    "retriever = VertexAISearchRetriever(\n",
     "    project_id=PROJECT_ID,\n",
     "    location_id=LOCATION_ID,\n",
     "    data_store_id=DATA_STORE_ID,\n",
@@ -297,7 +333,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = GoogleVertexAISearchRetriever(\n",
+    "retriever = VertexAISearchRetriever(\n",
     "    project_id=PROJECT_ID,\n",
     "    location_id=LOCATION_ID,\n",
     "    search_engine_id=SEARCH_ENGINE_ID,\n",
@@ -325,7 +361,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "retriever = GoogleVertexAIMultiTurnSearchRetriever(\n",
+    "retriever = VertexAIMultiTurnSearchRetriever(\n",
     "    project_id=PROJECT_ID, location_id=LOCATION_ID, data_store_id=DATA_STORE_ID\n",
     ")\n",
     "\n",
@@ -333,6 +369,85 @@
     "for doc in result:\n",
     "    print(doc)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
+    "\n",
+    "Following the above examples, we use `.invoke` to issue a single query. Because retrievers are Runnables, we can use any method in the [Runnable interface](/docs/concepts/#runnable-interface), such as `.batch`, as well."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use within a chain\n",
+    "\n",
+    "We can also incorporate retrievers into [chains](/docs/how_to/sequence/) to build larger applications, such as a simple [RAG](/docs/tutorials/rag/) application. For demonstration purposes, we instantiate a VertexAI chat model as well. See the corresponding Vertex [integration docs](/docs/integrations/chat/google_vertex_ai_palm/) for setup instructions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-google-vertexai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_google_vertexai import ChatVertexAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the question based only on the context provided.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "\n",
+    "llm = ChatVertexAI(model_name=\"chat-bison\", temperature=0)\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `VertexAISearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/vertex_ai_search/langchain_google_community.vertex_ai_search.VertexAISearchRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -351,7 +466,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/retrievers/index.mdx

@@ -0,0 +1,40 @@
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+---
+
+# Retrievers
+
+A [retriever](/docs/concepts/#retrievers) is an interface that returns documents given an unstructured query.
+It is more general than a vector store.
+A retriever does not need to be able to store documents, only to return (or retrieve) them.
+Retrievers can be created from vector stores, but are also broad enough to include [Wikipedia search](/docs/integrations/retrievers/wikipedia/) and [Amazon Kendra](/docs/integrations/retrievers/amazon_kendra_retriever/).
+
+Retrievers accept a string query as input and return a list of [Documents](https://api.python.langchain.com/en/latest/documents/langchain_core.documents.base.Document.html) as output.
+
+For specifics on how to use retrievers, see the [relevant how-to guides here](/docs/how_to/#retrievers).
+
+Note that all [vector stores](/docs/concepts/#vector-stores) can be [cast to retrievers](/docs/how_to/vectorstore_retriever/).
+Refer to the vector store [integration docs](/docs/integrations/vectorstores/) for available vector stores.
+This page lists custom retrievers, implemented via subclassing [BaseRetriever](/docs/how_to/custom_retriever/).
+
+## Bring-your-own documents
+
+The below retrievers allow you to index and search a custom corpus of documents.
+
+| Retriever | Self-host | Cloud offering | Package |
+|-----------|-----------|----------------|---------|
+| [AmazonKnowledgeBasesRetriever](/docs/integrations/retrievers/bedrock) | ❌ | ✅ | [langchain_aws](https://api.python.langchain.com/en/latest/retrievers/langchain_aws.retrievers.bedrock.AmazonKnowledgeBasesRetriever.html) |
+| [AzureAISearchRetriever](/docs/integrations/retrievers/azure_ai_search) | ❌ | ✅ | [langchain_community](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.azure_ai_search.AzureAISearchRetriever.html) |
+| [ElasticsearchRetriever](/docs/integrations/retrievers/elasticsearch_retriever) | ✅ | ✅ | [langchain_elasticsearch](https://api.python.langchain.com/en/latest/retrievers/langchain_elasticsearch.retrievers.ElasticsearchRetriever.html) |
+| [MilvusCollectionHybridSearchRetriever](/docs/integrations/retrievers/milvus_hybrid_search) | ✅ | ❌ | [langchain_milvus](https://api.python.langchain.com/en/latest/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html) |
+| [VertexAISearchRetriever](/docs/integrations/retrievers/google_vertex_ai_search) | ❌ | ✅ | [langchain_google_community](https://api.python.langchain.com/en/latest/vertex_ai_search/langchain_google_community.vertex_ai_search.VertexAISearchRetriever.html) |
+
+## External index
+
+The below retrievers will search over an external index (e.g., constructed from Internet data or similar).
+
+| Retriever | Source | Package |
+|-----------|--------|---------|
+| [ArxivRetriever](/docs/integrations/retrievers/arxiv) | Scholarly articles on [arxiv.org](https://arxiv.org/) | [langchain_community](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.arxiv.ArxivRetriever.html) |
+| [TavilySearchAPIRetriever](/docs/integrations/retrievers/tavily) | Internet search | [langchain_community](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.tavily_search_api.TavilySearchAPIRetriever.html) |

docs/docs/integrations/retrievers/milvus_hybrid_search.ipynb

@@ -2,21 +2,48 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
+   "metadata": {},
    "source": [
-    "# Milvus Hybrid Search\n",
+    "---\n",
+    "sidebar_label: Milvus Hybrid Search\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Milvus Hybrid Search Retriever\n",
+    "\n",
+    "## Overview\n",
     "\n",
     "> [Milvus](https://milvus.io/docs) is an open-source vector database built to power embedding similarity search and AI applications. Milvus makes unstructured data search more accessible, and provides a consistent user experience regardless of the deployment environment.\n",
     "\n",
-    "This notebook goes over how to use the Milvus Hybrid Search retriever, which combines the strengths of both dense and sparse vector search.\n",
+    "This will help you getting started with the Milvus Hybrid Search [retriever](/docs/concepts/#retrievers), which combines the strengths of both dense and sparse vector search. For detailed documentation of all `MilvusCollectionHybridSearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html).\n",
     "\n",
-    "For more reference please go to [Milvus Multi-Vector Search](https://milvus.io/docs/multi-vector-search.md)\n",
-    "\n"
+    "See also the Milvus Multi-Vector Search [docs](https://milvus.io/docs/multi-vector-search.md).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Retriever | Self-host | Cloud offering | Package |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[MilvusCollectionHybridSearchRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html) | ✅ | ❌ | langchain_milvus |\n",
+    "\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
    ]
   },
   {
@@ -28,9 +55,9 @@
     }
    },
    "source": [
-    "## Prerequisites\n",
-    "### Install dependencies\n",
-    "You need to prepare to install the following dependencies\n"
+    "### Installation\n",
+    "\n",
+    "This retriever lives in the `langchain-milvus` package. This guide requires the following dependencies:"
    ]
   },
   {
@@ -50,32 +77,18 @@
     "%pip install --upgrade --quiet pymilvus[model] langchain-milvus langchain-openai"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
-   "source": [
-    "Import necessary modules and classes"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    },
-    "pycharm": {
-     "name": "#%%\n"
-    }
-   },
+   "execution_count": null,
+   "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "from langchain_milvus.retrievers import MilvusCollectionHybridSearchRetriever\n",
+    "from langchain_milvus.utils.sparse import BM25SparseEmbedding\n",
+    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings\n",
     "from pymilvus import (\n",
     "    Collection,\n",
     "    CollectionSchema,\n",
@@ -86,34 +99,15 @@
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import PromptTemplate\n",
-    "from langchain_core.runnables import RunnablePassthrough\n",
-    "from langchain_milvus.retrievers import MilvusCollectionHybridSearchRetriever\n",
-    "from langchain_milvus.utils.sparse import BM25SparseEmbedding\n",
-    "from langchain_openai import ChatOpenAI, OpenAIEmbeddings"
-   ]
-  },
   {
    "cell_type": "markdown",
-   "metadata": {
-    "collapsed": false,
-    "jupyter": {
-     "outputs_hidden": false
-    }
-   },
+   "metadata": {},
    "source": [
     "### Start the Milvus service\n",
     "\n",
     "Please refer to the [Milvus documentation](https://milvus.io/docs/install_standalone-docker.md) to start the Milvus service.\n",
     "\n",
-    "After starting milvus, you need to specify your milvus connection URI.\n"
+    "After starting milvus, you need to specify your milvus connection URI."
    ]
   },
   {
@@ -155,11 +149,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "\n",
-    "## Prepare data and Load\n",
     "### Prepare dense and sparse embedding functions\n",
     "\n",
-    " Let us fictionalize 10 fake descriptions of novels. In actual production, it may be a large amount of text data."
+    "Let us fictionalize 10 fake descriptions of novels. In actual production, it may be a large amount of text data."
    ]
   },
   {
@@ -379,15 +371,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Build RAG chain with Retriever\n",
-    "### Create the Retriever\n",
+    "## Instantiation\n",
     "\n",
-    "Define search parameters for sparse and dense fields, and create a retriever"
+    "Now we can instantiate our retriever, defining search parameters for sparse and dense fields:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -416,6 +407,13 @@
     "In the input parameters of this Retriever, we use a dense embedding and a sparse embedding to perform hybrid search on the two fields of this Collection, and use WeightedRanker for reranking. Finally, 3 top-K Documents will be returned."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 14,
@@ -442,7 +440,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Build the RAG chain\n",
+    "## Use within a chain\n",
     "\n",
     "Initialize ChatOpenAI and define a prompt template"
    ]
@@ -610,6 +608,15 @@
    "source": [
     "collection.drop()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `MilvusCollectionHybridSearchRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_milvus.retrievers.milvus_hybrid_search.MilvusCollectionHybridSearchRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -628,9 +635,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,
  "nbformat_minor": 4
-}
+}

docs/docs/integrations/retrievers/tavily.ipynb

@@ -4,20 +4,70 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Tavily Search API\n",
+    "---\n",
+    "sidebar_label: TavilySearchAPI\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# TavilySearchAPIRetriever\n",
     "\n",
+    "## Overview\n",
     ">[Tavily's Search API](https://tavily.com) is a search engine built specifically for AI agents (LLMs), delivering real-time, accurate, and factual results at speed.\n",
     "\n",
     "We can use this as a [retriever](/docs/how_to#retrievers). It will show functionality specific to this integration. After going through, it may be useful to explore [relevant use-case pages](/docs/how_to#qa-with-rag) to learn how to use this vectorstore as part of a larger chain.\n",
     "\n",
-    "## Setup\n",
+    "### Integration details\n",
     "\n",
-    "The integration lives in the `langchain-community` package. We also need to install the `tavily-python` package itself.\n",
+    "| Retriever | Source | Package |\n",
+    "| :--- | :--- | :---: |\n",
+    "[TavilySearchAPIRetriever](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.tavily_search_api.TavilySearchAPIRetriever.html) | Internet search | langchain_community |\n",
     "\n",
-    "```bash\n",
-    "pip install -U langchain-community tavily-python\n",
-    "```\n",
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
     "\n",
+    "The integration lives in the `langchain-community` package. We also need to install the `tavily-python` package itself."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community tavily-python"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
     "We also need to set our Tavily API key."
    ]
   },
@@ -37,17 +87,20 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our retriever:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+    "from langchain_community.retrievers import TavilySearchAPIRetriever\n",
+    "\n",
+    "retriever = TavilySearchAPIRetriever(k=3)"
    ]
   },
   {
@@ -59,42 +112,40 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='Trending topics\\nTrending topics\\nThe Legend of Zelda™: Breath of the Wild\\nSelect a product\\nThe Legend of Zelda™: Breath of the Wild\\nThe Legend of Zelda™: Breath of the Wild\\nThe Legend of Zelda™: Breath of the Wild and The Legend of Zelda™: Breath of the Wild Expansion Pass Bundle\\nThis item will be sent to your system automatically after purchase or Nintendo Switch Game Voucher redemption. The Legend of Zelda: Breath of the Wild Expansion Pass\\nMore like this\\nSuper Mario Odyssey™\\nThe Legend of Zelda™: Tears of the Kingdom\\nMario + Rabbids® Kingdom Battle\\nThe Legend of Zelda™: Link’s Awakening\\nHollow Knight\\nThe Legend of Zelda™: Skyward Sword HD\\nStarlink: Battle for Atlas™ Digital Edition\\nDRAGON QUEST BUILDERS™ 2\\nDragon Quest Builders™\\nWARNING: If you have epilepsy or have had seizures or other unusual reactions to flashing lights or patterns, consult a doctor before playing video games. Saddle up with a herd of horse-filled games!\\nESRB rating\\nSupported play modes\\nTV\\nTabletop\\nHandheld\\nProduct information\\nRelease date\\nNo. of players\\nGenre\\nPublisher\\nESRB rating\\nSupported play modes\\nGame file size\\nSupported languages\\nPlay online, access classic NES™ and Super NES™ games, and more with a Nintendo Switch Online membership.\\n Two Game Boy games are now available for Nintendo Switch Online members\\n02/01/23\\nNintendo Switch Online member exclusive: Save on two digital games\\n09/13/22\\nOut of the Shadows … the Legend of Zelda: About Nintendo\\nShop\\nMy Nintendo Store orders\\nSupport\\nParents\\nCommunity\\nPrivacy\\n© Nintendo.', metadata={'title': 'The Legend of Zelda™: Breath of the Wild - Nintendo', 'source': 'https://www.nintendo.com/us/store/products/the-legend-of-zelda-breath-of-the-wild-switch/', 'score': 0.97451, 'images': None}),\n",
-       " Document(page_content='The Legend of Zelda: Breath of the Wild is a masterpiece of open-world design and exploration, released on March 3, 2017 for Nintendo Switch. Find out the latest news, reviews, guides, videos, and more for this award-winning game on IGN.', metadata={'title': 'The Legend of Zelda: Breath of the Wild - IGN', 'source': 'https://www.ign.com/games/the-legend-of-zelda-breath-of-the-wild', 'score': 0.94496, 'images': None}),\n",
-       " Document(page_content='Reviewers also commented on the unexpected permutations of interactions between Link, villagers, pets, and enemies,[129][130][131] many of which were shared widely on social media.[132] A tribute to former Nintendo president Satoru Iwata, who died during development, also attracted praise.[129][134]\\nJim Sterling was more critical than most, giving Breath of the Wild a 7/10 score, criticizing the difficulty, weapon durability, and level design, but praising the open world and variety of content.[135] Other criticism focused on the unstable frame rate and the low resolution of 900p;[136] updates addressed some of these problems.[137][138]\\nSales\\nBreath of the Wild broke sales records for a Nintendo launch game in multiple regions.[139][140] In Japan, the Switch and Wii U versions sold a combined 230,000 copies in the first week of release, with the Switch version becoming the top-selling game released that week.[141] Nintendo reported that Breath of the Wild sold more than one million copies in the US that month—925,000 of which were for Switch, outselling the Switch itself.[145][146][147][148] Nintendo president Tatsumi Kimishima said that the attach rate on the Switch was \"unprecedented\".[149] Breath of the Wild had sold 31.15 million copies on the Switch by September 2023 and 1.70 million copies on the Wii U by December 2020.[150][151]\\nAwards\\nFollowing its demonstration at E3 2016, Breath of the Wild received several accolades from the Game Critics Awards[152] and from publications such as IGN and Destructoid.[153][154] It was listed among the best games at E3 by Eurogamer,[81] The game, he continued, would challenge the series\\' conventions, such as the requirement that players complete dungeons in a set order.[2][73] The next year, Nintendo introduced the game\\'s high-definition, cel-shaded visual style with in-game footage at its E3 press event.[74][75] Once planned for release in 2015, the game was delayed early in the year and did not show at that year\\'s E3.[76][77] Zelda series creator Shigeru Miyamoto reaffirmed that the game would still release for the Wii U despite the development of Nintendo\\'s next console, the Nintendo Switch.[78] The Switch version also has higher-quality environmental sounds.[53][54] Certain ideas that were planned for the game, like flying and underground dungeons were not implemented due to the Wii U’s limitations; they would eventually resurface in the game\\'s sequel.[55] Aonuma stated that the art design was inspired by gouache and en plein air art to help identify the vast world.[56] Takizawa has also cited the Jōmon period as an inspiration for the ancient Sheikah technology and architecture that is found in the game, due to the mystery surrounding the period.[57] Journalists commented on unexpected interactions between game elements,[129][130][131] with serendipitous moments proving popular on social media.[132] Chris Plante of The Verge predicted that whereas prior open-world games tended to feature prescribed challenges, Zelda would influence a new generation of games with open-ended problem-solving.[132] Digital Trends wrote that the game\\'s level of experimentation allowed players to interact with and exploit the environment in creative ways, resulting in various \"tricks\" still discovered years after release.[127]\\nReviewers lauded the sense of detail and immersion.[133][129] Kotaku recommended turning off UI elements in praise of the indirect cues that contextually indicate the same information, such as Link shivering in the cold or waypoints appearing when using the scope.[133]', metadata={'title': 'The Legend of Zelda: Breath of the Wild - Wikipedia', 'source': 'https://en.wikipedia.org/wiki/The_Legend_of_Zelda:_Breath_of_the_Wild', 'score': 0.93348, 'images': None})]"
+       "[Document(metadata={'title': 'The Legend of Zelda: Breath of the Wild - Nintendo Switch Wiki', 'source': 'https://nintendo-switch.fandom.com/wiki/The_Legend_of_Zelda:_Breath_of_the_Wild', 'score': 0.9961155, 'images': []}, page_content='The Legend of Zelda: Breath of the Wild is an open world action-adventure game published by Nintendo for the Wii U and as a launch title for the Nintendo Switch, and was released worldwide on March 3, 2017. It is the nineteenth installment of the The Legend of Zelda series and the first to be developed with a HD resolution. The game features a gigantic open world, with the player being able to ...'),\n",
+       " Document(metadata={'title': 'The Legend of Zelda: Breath of the Wild - Zelda Wiki', 'source': 'https://zelda.fandom.com/wiki/The_Legend_of_Zelda:_Breath_of_the_Wild', 'score': 0.9804313, 'images': []}, page_content='[]\\nReferences\\nThe Legend of Zelda \\xa0·\\nThe Adventure of Link \\xa0·\\nA Link to the Past (& Four Swords) \\xa0·\\nLink\\'s Awakening (DX; Nintendo Switch) \\xa0·\\nOcarina of Time (Master Quest; 3D) \\xa0·\\nMajora\\'s Mask (3D) \\xa0·\\nOracle of Ages \\xa0·\\nOracle of Seasons \\xa0·\\nFour Swords (Anniversary Edition) \\xa0·\\nThe Wind Waker (HD) \\xa0·\\nFour Swords Adventures \\xa0·\\nThe Minish Cap \\xa0·\\nTwilight Princess (HD) \\xa0·\\nPhantom Hourglass \\xa0·\\nSpirit Tracks \\xa0·\\nSkyward Sword (HD) \\xa0·\\nA Link Between Worlds \\xa0·\\nTri Force Heroes \\xa0·\\nBreath of the Wild \\xa0·\\nTears of the Kingdom\\nZelda (Game & Watch) \\xa0·\\nThe Legend of Zelda Game Watch \\xa0·\\nLink\\'s Crossbow Training \\xa0·\\nMy Nintendo Picross: Twilight Princess \\xa0·\\nCadence of Hyrule \\xa0·\\nGame & Watch: The Legend of Zelda\\nCD-i Games\\n Listings[]\\nCharacters[]\\nBosses[]\\nEnemies[]\\nDungeons[]\\nLocations[]\\nItems[]\\nTranslations[]\\nCredits[]\\nReception[]\\nSales[]\\nEiji Aonuma and Hidemaro Fujibayashi accepting the \"Game of the Year\" award for Breath of the Wild at The Game Awards 2017\\nBreath of the Wild was estimated to have sold approximately 1.3 million copies in its first three weeks and around 89% of Switch owners were estimated to have also purchased the game.[52] Sales of the game have remained strong and as of June 30, 2022, the Switch version has sold 27.14 million copies worldwide while the Wii U version has sold 1.69 million copies worldwide as of December 31, 2019,[53][54] giving Breath of the Wild a cumulative total of 28.83 million copies sold.\\n It also earned a Metacritic score of 97 from more than 100 critics, placing it among the highest-rated games of all time.[59][60] Notably, the game received the most perfect review scores for any game listed on Metacritic up to that point.[61]\\nIn 2022, Breath of the Wild was chosen as the best Legend of Zelda game of all time in their \"Top 10 Best Zelda Games\" list countdown; but was then placed as the \"second\" best Zelda game in their new revamped version of their \"Top 10 Best Zelda Games\" list in 2023, right behind it\\'s successor Tears of Video Game Canon ranks Breath of the Wild as one of the best video games of all time.[74] Metacritic ranked Breath of the Wild as the single best game of the 2010s.[75]\\nFan Reception[]\\nWatchMojo placed Breath of the Wild at the #2 spot in their \"Top 10 Legend of Zelda Games of All Time\" list countdown, right behind Ocarina of Time.[76] The Faces of Evil \\xa0·\\nThe Wand of Gamelon \\xa0·\\nZelda\\'s Adventure\\nHyrule Warriors Series\\nHyrule Warriors (Legends; Definitive Edition) \\xa0·\\nHyrule Warriors: Age of Calamity\\nSatellaview Games\\nBS The Legend of Zelda \\xa0·\\nAncient Stone Tablets\\nTingle Series\\nFreshly-Picked Tingle\\'s Rosy Rupeeland \\xa0·\\nTingle\\'s Balloon Fight DS \\xa0·\\n'),\n",
+       " Document(metadata={'title': 'The Legend of Zelda: Breath of the Wild - Zelda Wiki', 'source': 'https://zeldawiki.wiki/wiki/The_Legend_of_Zelda:_Breath_of_the_Wild', 'score': 0.9627432, 'images': []}, page_content='The Legend of Zelda\\xa0•\\nThe Adventure of Link\\xa0•\\nA Link to the Past (& Four Swords)\\xa0•\\nLink\\'s Awakening (DX; Nintendo Switch)\\xa0•\\nOcarina of Time (Master Quest; 3D)\\xa0•\\nMajora\\'s Mask (3D)\\xa0•\\nOracle of Ages\\xa0•\\nOracle of Seasons\\xa0•\\nFour Swords (Anniversary Edition)\\xa0•\\nThe Wind Waker (HD)\\xa0•\\nFour Swords Adventures\\xa0•\\nThe Minish Cap\\xa0•\\nTwilight Princess (HD)\\xa0•\\nPhantom Hourglass\\xa0•\\nSpirit Tracks\\xa0•\\nSkyward Sword (HD)\\xa0•\\nA Link Between Worlds\\xa0•\\nTri Force Heroes\\xa0•\\nBreath of the Wild\\xa0•\\nTears of the Kingdom\\nZelda (Game & Watch)\\xa0•\\nThe Legend of Zelda Game Watch\\xa0•\\nHeroes of Hyrule\\xa0•\\nLink\\'s Crossbow Training\\xa0•\\nMy Nintendo Picross: Twilight Princess\\xa0•\\nCadence of Hyrule\\xa0•\\nVermin\\nThe Faces of Evil\\xa0•\\nThe Wand of Gamelon\\xa0•\\nZelda\\'s Adventure\\nHyrule Warriors (Legends; Definitive Edition)\\xa0•\\nHyrule Warriors: Age of Calamity\\nBS The Legend of Zelda\\xa0•\\nAncient Stone Tablets\\nFreshly-Picked Tingle\\'s Rosy Rupeeland\\xa0•\\nTingle\\'s Balloon Fight DS\\xa0•\\nToo Much Tingle Pack\\xa0•\\nRipened Tingle\\'s Balloon Trip of Love\\nSoulcalibur II\\xa0•\\nWarioWare Series\\xa0•\\nCaptain Rainbow\\xa0•\\nNintendo Land\\xa0•\\nScribblenauts Unlimited\\xa0•\\nMario Kart 8\\xa0•\\nSplatoon 3\\nSuper Smash Bros (Series)\\nSuper Smash Bros.\\xa0•\\nSuper Smash Bros. Melee\\xa0•\\nSuper Smash Bros. Brawl\\xa0•\\nSuper Smash Bros. for Nintendo 3DS / Wii U\\xa0•\\n It also earned a Metacritic score of 97 from more than 100 critics, placing it among the highest-rated games of all time.[60][61] Notably, the game received the most perfect review scores for any game listed on Metacritic up to that point.[62]\\nAwards\\nThroughout 2016, Breath of the Wild won several awards as a highly anticipated game, including IGN\\'s and Destructoid\\'s Best of E3,[63][64] at the Game Critic Awards 2016,[65] and at The Game Awards 2016.[66] Following its release, Breath of the Wild received the title of \"Game of the Year\" from the Japan Game Awards 2017,[67] the Golden Joystick Awards 2017,<ref\"Our final award is for the Ultimate Game of the Year. Official website(s)\\nOfficial website(s)\\nCanonicity\\nCanonicity\\nCanon[citation needed]\\nPredecessor\\nPredecessor\\nTri Force Heroes\\nSuccessor\\nSuccessor\\nTears of the Kingdom\\nThe Legend of Zelda: Breath of the Wild guide at StrategyWiki\\nBreath of the Wild Guide at Zelda Universe\\nThe Legend of Zelda: Breath of the Wild is the nineteenth main installment of The Legend of Zelda series. Listings\\nCharacters\\nBosses\\nEnemies\\nDungeons\\nLocations\\nItems\\nTranslations\\nCredits\\nReception\\nSales\\nBreath of the Wild was estimated to have sold approximately 1.3 million copies in its first three weeks and around 89% of Switch owners were estimated to have also purchased the game.[53] Sales of the game have remained strong and as of September 30, 2023, the Switch version has sold 31.15 million copies worldwide while the Wii U version has sold 1.7 million copies worldwide as of December 31, 2021,[54][55] giving Breath of the Wild a cumulative total of 32.85 million copies sold.\\n The Legend of Zelda: Breath of the Wild\\nThe Legend of Zelda: Breath of the Wild\\nThe Legend of Zelda: Breath of the Wild\\nDeveloper(s)\\nDeveloper(s)\\nPublisher(s)\\nPublisher(s)\\nNintendo\\nDesigner(s)\\nDesigner(s)\\n')]"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain_community.retrievers import TavilySearchAPIRetriever\n",
+    "query = \"what year was breath of the wild released?\"\n",
     "\n",
-    "retriever = TavilySearchAPIRetriever(k=3)\n",
-    "\n",
-    "retriever.invoke(\"what year was breath of the wild released?\")"
+    "retriever.invoke(query)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Chaining\n",
+    "## Use within a chain\n",
     "\n",
     "We can easily combine this retriever in to a chain."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -110,40 +161,50 @@
     "\n",
     "Question: {question}\"\"\"\n",
     ")\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
     "chain = (\n",
-    "    RunnablePassthrough.assign(context=(lambda x: x[\"question\"]) | retriever)\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
     "    | prompt\n",
-    "    | ChatOpenAI(model=\"gpt-4-1106-preview\")\n",
+    "    | llm\n",
     "    | StrOutputParser()\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'As of the end of 2020, \"The Legend of Zelda: Breath of the Wild\" sold over 21.45 million copies worldwide.'"
+       "'As of August 2020, The Legend of Zelda: Breath of the Wild had sold over 20.1 million copies worldwide on Nintendo Switch and Wii U.'"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "chain.invoke({\"question\": \"how many units did bretch of the wild sell in 2020\"})"
+    "chain.invoke(\"how many units did bretch of the wild sell in 2020\")"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `TavilySearchAPIRetriever` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/langchain_community.retrievers.tavily_search_api.TavilySearchAPIRetriever.html)."
+   ]
   }
  ],
  "metadata": {
@@ -162,7 +223,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/astradb.ipynb

@@ -2,10 +2,14 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
-    "sidebar_label: Astra DB\n",
+    "sidebar_label: AstraDB\n",
     "---"
    ]
   },
@@ -13,130 +17,121 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Astra DB\n",
+    "# AstraDBByteStore\n",
+    "\n",
+    "This will help you get started with Astra DB [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `AstraDBByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html).\n",
+    "\n",
+    "## Overview\n",
     "\n",
     "DataStax [Astra DB](https://docs.datastax.com/en/astra/home/astra.html) is a serverless vector-capable database built on Cassandra and made conveniently available through an easy-to-use JSON API.\n",
     "\n",
-    "`AstraDBStore` and `AstraDBByteStore` need the `astrapy` package to be installed:"
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | JS support | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [AstraDBByteStore](https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html) | [langchain_astradb](https://api.python.langchain.com/en/latest/astradb_api_reference.html) | ❌ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_astradb?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_astradb?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To create an `AstraDBByteStore` byte store, you'll need to [create a DataStax account](https://www.datastax.com/products/datastax-astra).\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "After signing up, set the following credentials:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet  astrapy"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The Store takes the following parameters:\n",
-    "\n",
-    "* `api_endpoint`: Astra DB API endpoint. Looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n",
-    "* `token`: Astra DB token. Looks like `AstraCS:6gBhNmsk135....`\n",
-    "* `collection_name` : Astra DB collection name\n",
-    "* `namespace`: (Optional) Astra DB namespace"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## AstraDBStore\n",
-    "\n",
-    "The `AstraDBStore` is an implementation of `BaseStore` that stores everything in your DataStax Astra DB instance.\n",
-    "The store keys must be strings and will be mapped to the `_id` field of the Astra DB document.\n",
-    "The store values can be any object that can be serialized by `json.dumps`.\n",
-    "In the database, entries will have the form:\n",
-    "\n",
-    "```json\n",
-    "{\n",
-    "  \"_id\": \"<key>\",\n",
-    "  \"value\": <value>\n",
-    "}\n",
-    "```"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.storage import AstraDBStore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
     "from getpass import getpass\n",
     "\n",
-    "ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
+    "ASTRA_DB_API_ENDPOINT = getpass(\"ASTRA_DB_API_ENDPOINT = \")\n",
     "ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain AstraDB integration lives in the `langchain_astradb` package:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "store = AstraDBStore(\n",
+    "%pip install -qU langchain_astradb"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our byte store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_astradb import AstraDBByteStore\n",
+    "\n",
+    "kv_store = AstraDBByteStore(\n",
     "    api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
     "    token=ASTRA_DB_APPLICATION_TOKEN,\n",
     "    collection_name=\"my_store\",\n",
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "['v1', [0.1, 0.2, 0.3]]\n"
-     ]
-    }
-   ],
-   "source": [
-    "store.mset([(\"k1\", \"v1\"), (\"k2\", [0.1, 0.2, 0.3])])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "### Usage with CacheBackedEmbeddings\n",
+    "## Usage\n",
     "\n",
-    "You may use the `AstraDBStore` in conjunction with a [`CacheBackedEmbeddings`](/docs/how_to/caching_embeddings) to cache the result of embeddings computations.\n",
-    "Note that `AstraDBStore` stores the embeddings as a list of floats without converting them first to bytes so we don't use `fromByteStore` there."
+    "You can set data under keys like this using the `mset` method:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[b'value1', b'value2']"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "from langchain.embeddings import CacheBackedEmbeddings\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
     "\n",
-    "embeddings = CacheBackedEmbeddings(\n",
-    "    underlying_embeddings=OpenAIEmbeddings(), document_embedding_store=store\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
     ")"
    ]
   },
@@ -144,96 +139,67 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## AstraDBByteStore\n",
-    "\n",
-    "The `AstraDBByteStore` is an implementation of `ByteStore` that stores everything in your DataStax Astra DB instance.\n",
-    "The store keys must be strings and will be mapped to the `_id` field of the Astra DB document.\n",
-    "The store `bytes` values are converted to base64 strings for storage into Astra DB.\n",
-    "In the database, entries will have the form:\n",
-    "\n",
-    "```json\n",
-    "{\n",
-    "  \"_id\": \"<key>\",\n",
-    "  \"value\": \"bytes encoded in base 64\"\n",
-    "}\n",
-    "```"
+    "And you can delete data using the `mdelete` method:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.storage import AstraDBByteStore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from getpass import getpass\n",
-    "\n",
-    "ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
-    "ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "store = AstraDBByteStore(\n",
-    "    api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
-    "    token=ASTRA_DB_APPLICATION_TOKEN,\n",
-    "    collection_name=\"my_store\",\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[b'v1', b'v2']\n"
-     ]
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": []
+   "source": [
+    "You can use an `AstraDBByteStore` anywhere you'd use other ByteStores, including as a [cache for embeddings](/docs/how_to/caching_embeddings)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `AstraDBByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
    "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/cassandra.ipynb

@@ -2,7 +2,11 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
     "sidebar_label: Cassandra\n",
@@ -13,68 +17,62 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Cassandra\n",
+    "# CassandraByteStore\n",
+    "\n",
+    "This will help you get started with Cassandra [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `CassandraByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html).\n",
+    "\n",
+    "## Overview\n",
     "\n",
     "[Cassandra](https://cassandra.apache.org/) is a NoSQL, row-oriented, highly scalable and highly available database.\n",
     "\n",
-    "`CassandraByteStore` needs the `cassio` package to be installed:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "plaintext"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet  cassio"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "The Store takes the following parameters:\n",
+    "### Integration details\n",
     "\n",
-    "* table:  The table where to store the data.\n",
-    "* session: (Optional) The cassandra driver session. If not provided, the cassio resolved session will be used.\n",
-    "* keyspace: (Optional) The keyspace of the table. If not provided, the cassio resolved keyspace will be used.\n",
-    "* setup_mode: (Optional) The mode used to create the Cassandra table (SYNC, ASYNC or OFF). Defaults to SYNC."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## CassandraByteStore\n",
+    "| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/cassandra_storage) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [CassandraByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
     "\n",
     "The `CassandraByteStore` is an implementation of `ByteStore` that stores the data in your Cassandra instance.\n",
     "The store keys must be strings and will be mapped to the `row_id` column of the Cassandra table.\n",
     "The store `bytes` values are mapped to the `body_blob` column of the Cassandra table."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain `CassandraByteStore` integration lives in the `langchain_community` package. You'll also need to install the `cassio` package or the `cassandra-driver` package as a peer dependency depending on which initialization method you're using:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.storage import CassandraByteStore"
+    "%pip install -qU langchain_community\n",
+    "%pip install -qU cassandra-driver\n",
+    "%pip install -qU cassio"
    ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "### Init from a cassandra driver Session\n",
+    "You'll also need to create a `cassandra.cluster.Session` object, as described in the [Cassandra driver documentation](https://docs.datastax.com/en/developer/python-driver/latest/api/cassandra/cluster/#module-cassandra.cluster). The details vary (e.g. with network settings and authentication), but this might be something like:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
     "\n",
-    "You need to create a `cassandra.cluster.Session` object, as described in the [Cassandra driver documentation](https://docs.datastax.com/en/developer/python-driver/latest/api/cassandra/cluster/#module-cassandra.cluster). The details vary (e.g. with network settings and authentication), but this might be something like:"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "You'll first need to create a `cassandra.cluster.Session` object, as described in the [Cassandra driver documentation](https://docs.datastax.com/en/developer/python-driver/latest/api/cassandra/cluster/#module-cassandra.cluster). The details vary (e.g. with network settings and authentication), but this might be something like:"
+   ]
   },
   {
    "cell_type": "code",
@@ -90,12 +88,10 @@
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "You need to provide the name of an existing keyspace of the Cassandra instance:"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "Then you can create your store! You'll also need to provide the name of an existing keyspace of the Cassandra instance:"
+   ]
   },
   {
    "cell_type": "code",
@@ -103,61 +99,91 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "CASSANDRA_KEYSPACE = input(\"CASSANDRA_KEYSPACE = \")"
+    "from langchain_community.storage import CassandraByteStore\n",
+    "\n",
+    "kv_store = CassandraByteStore(\n",
+    "    table=\"my_store\",\n",
+    "    session=session,\n",
+    "    keyspace=\"<YOUR KEYSPACE>\",\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "Creating the store:"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "## Usage\n",
+    "\n",
+    "You can set data under keys like this using the `mset` method:"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[b'v1', b'v2']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
-    "store = CassandraByteStore(\n",
-    "    table=\"my_store\",\n",
-    "    session=session,\n",
-    "    keyspace=CASSANDRA_KEYSPACE,\n",
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
     ")\n",
     "\n",
-    "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "### Init from cassio\n",
-    "\n",
-    "It's also possible to use cassio to configure the session and keyspace."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "And you can delete data using the `mdelete` method:"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Init using `cassio`\n",
+    "\n",
+    "It's also possible to use cassio to configure the session and keyspace."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
    "outputs": [],
    "source": [
     "import cassio\n",
     "\n",
-    "cassio.init(contact_points=\"127.0.0.1\", keyspace=CASSANDRA_KEYSPACE)\n",
+    "cassio.init(contact_points=\"127.0.0.1\", keyspace=\"<YOUR KEYSPACE>\")\n",
     "\n",
     "store = CassandraByteStore(\n",
     "    table=\"my_store\",\n",
@@ -165,62 +191,27 @@
     "\n",
     "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
     "print(store.mget([\"k1\", \"k2\"]))"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "### Usage with CacheBackedEmbeddings\n",
+    "## API reference\n",
     "\n",
-    "You may use the `CassandraByteStore` in conjunction with a [`CacheBackedEmbeddings`](/docs/how_to/caching_embeddings) to cache the result of embeddings computations.\n"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings import CacheBackedEmbeddings\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
-    "\n",
-    "cassio.init(contact_points=\"127.0.0.1\", keyspace=CASSANDRA_KEYSPACE)\n",
-    "\n",
-    "store = CassandraByteStore(\n",
-    "    table=\"my_store\",\n",
-    ")\n",
-    "\n",
-    "embeddings = CacheBackedEmbeddings.from_bytes_store(\n",
-    "    underlying_embeddings=OpenAIEmbeddings(), document_embedding_cache=store\n",
-    ")"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "For detailed documentation of all `CassandraByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
    "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/elasticsearch.ipynb

@@ -2,10 +2,14 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
-    "sidebar_label: Elasticsearch \n",
+    "sidebar_label: Elasticsearch\n",
     "---"
    ]
   },
@@ -15,25 +19,31 @@
    "source": [
     "# ElasticsearchEmbeddingsCache\n",
     "\n",
+    "This will help you get started with Elasticsearch [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `ElasticsearchEmbeddingsCache` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html).\n",
+    "\n",
+    "## Overview\n",
+    "\n",
     "The `ElasticsearchEmbeddingsCache` is a `ByteStore` implementation that uses your Elasticsearch instance for efficient storage and retrieval of embeddings.\n",
     "\n",
+    "### Integration details\n",
     "\n",
-    "First install the LangChain integration with Elasticsearch."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install -U langchain-elasticsearch"
+    "| Class | Package | Local | JS support | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [ElasticsearchEmbeddingsCache](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html) | [langchain_elasticsearch](https://api.python.langchain.com/en/latest/elasticsearch_api_reference.html) | ✅ | ❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_elasticsearch?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_elasticsearch?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To create a `ElasticsearchEmbeddingsCache` byte store, you'll need an Elasticsearch cluster. You can [set one up locally](https://www.elastic.co/downloads/elasticsearch) or create an [Elastic account](https://www.elastic.co/elasticsearch)."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "it can be instantiated using `CacheBackedEmbeddings.from_bytes_store` method."
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain `ElasticsearchEmbeddingsCache` integration lives in the `__package_name__` package:"
+   ]
   },
   {
    "cell_type": "code",
@@ -41,23 +51,37 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.embeddings import CacheBackedEmbeddings\n",
+    "%pip install -qU langchain_elasticsearch"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our byte store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "from langchain_elasticsearch import ElasticsearchEmbeddingsCache\n",
-    "from langchain_openai import OpenAIEmbeddings\n",
     "\n",
-    "underlying_embeddings = OpenAIEmbeddings(model=\"text-embedding-3-small\")\n",
-    "\n",
-    "store = ElasticsearchEmbeddingsCache(\n",
-    "    es_url=\"http://localhost:9200\",\n",
+    "# Example config for a locally running Elasticsearch instance\n",
+    "kv_store = ElasticsearchEmbeddingsCache(\n",
+    "    es_url=\"https://localhost:9200\",\n",
     "    index_name=\"llm-chat-cache\",\n",
     "    metadata={\"project\": \"my_chatgpt_project\"},\n",
     "    namespace=\"my_chatgpt_project\",\n",
-    ")\n",
-    "\n",
-    "embeddings = CacheBackedEmbeddings.from_bytes_store(\n",
-    "    underlying_embeddings=OpenAIEmbeddings(),\n",
-    "    document_embedding_cache=store,\n",
-    "    query_embedding_cache=store,\n",
+    "    es_user=\"elastic\",\n",
+    "    es_password=\"<GENERATED PASSWORD>\",\n",
+    "    es_params={\n",
+    "        \"ca_certs\": \"~/http_ca.crt\",\n",
+    "    },\n",
     ")"
    ]
   },
@@ -65,19 +89,93 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "The index_name parameter can also accept aliases. This allows to use the ILM: Manage the index lifecycle that we suggest to consider for managing retention and controlling cache growth.\n",
+    "## Usage\n",
     "\n",
-    "Look at the class docstring for all parameters."
+    "You can set data under keys like this using the `mset` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[b'value1', b'value2']"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Index the generated vectors\n",
-    "The cached vectors won't be searchable by default. The developer can customize the building of the Elasticsearch document in order to add indexed vector field.\n",
+    "And you can delete data using the `mdelete` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
     "\n",
-    "This can be done by subclassing end overriding methods. "
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use as an embeddings cache\n",
+    "\n",
+    "Like other `ByteStores`, you can use an `ElasticsearchEmbeddingsCache` instance for [persistent caching in document ingestion](/docs/how_to/caching_embeddings/) for RAG.\n",
+    "\n",
+    "However, cached vectors won't be searchable by default. The developer can customize the building of the Elasticsearch document in order to add indexed vector field.\n",
+    "\n",
+    "This can be done by subclassing and overriding methods:"
    ]
   },
   {
@@ -88,8 +186,6 @@
    "source": [
     "from typing import Any, Dict, List\n",
     "\n",
-    "from langchain_elasticsearch import ElasticsearchEmbeddingsCache\n",
-    "\n",
     "\n",
     "class SearchableElasticsearchStore(ElasticsearchEmbeddingsCache):\n",
     "    @property\n",
@@ -112,26 +208,29 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "When overriding the mapping and the document building, please only make additive modifications, keeping the base mapping intact."
+   "source": [
+    "When overriding the mapping and the document building, please only make additive modifications, keeping the base mapping intact."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `ElasticsearchEmbeddingsCache` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
    "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/file_system.ipynb

@@ -2,11 +2,14 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
     "sidebar_label: Local Filesystem\n",
-    "sidebar_position: 3\n",
     "---"
    ]
   },
@@ -16,51 +19,119 @@
    "source": [
     "# LocalFileStore\n",
     "\n",
-    "The `LocalFileStore` is a persistent implementation of `ByteStore` that stores everything in a folder of your choosing."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[b'v1', b'v2']\n"
-     ]
-    }
-   ],
-   "source": [
-    "from pathlib import Path\n",
+    "This will help you get started with local filesystem [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all LocalFileStore features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html).\n",
     "\n",
-    "from langchain.storage import LocalFileStore\n",
+    "## Overview\n",
     "\n",
-    "root_path = Path.cwd() / \"data\"  # can also be a path set by a string\n",
-    "store = LocalFileStore(root_path)\n",
+    "The `LocalFileStore` is a persistent implementation of `ByteStore` that stores everything in a folder of your choosing. It's useful if you're using a single machine and are tolerant of files being added or deleted.\n",
     "\n",
-    "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/file_system) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [LocalFileStore](https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html) | [langchain](https://api.python.langchain.com/en/latest/langchain_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain?style=flat-square&label=%20) |"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now let's see which files exist in our `data` folder:"
+    "### Installation\n",
+    "\n",
+    "The LangChain `LocalFileStore` integration lives in the `langchain` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our byte store:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "\n",
+    "from langchain.storage import LocalFileStore\n",
+    "\n",
+    "root_path = Path.cwd() / \"data\"  # can also be a path set by a string\n",
+    "\n",
+    "kv_store = LocalFileStore(root_path)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
+    "\n",
+    "You can set data under keys like this using the `mset` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[b'value1', b'value2']"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can see the created files in your `data` folder:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "k1 k2\n"
+      "key1 key2\n"
      ]
     }
    ],
@@ -69,16 +140,57 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "And you can delete data using the `mdelete` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `LocalFileStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -92,7 +204,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/in_memory.ipynb

@@ -2,12 +2,14 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
-    "sidebar_label: In Memory\n",
-    "sidebar_position: 2\n",
-    "keywords: [InMemoryStore]\n",
+    "sidebar_label: In-memory\n",
     "---"
    ]
   },
@@ -17,29 +19,26 @@
    "source": [
     "# InMemoryByteStore\n",
     "\n",
-    "The `InMemoryByteStore` is a non-persistent implementation of `ByteStore` that stores everything in a Python dictionary."
+    "This guide will help you get started with in-memory [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `InMemoryByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.InMemoryByteStore.html).\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "The `InMemoryByteStore` is a non-persistent implementation of a `ByteStore` that stores everything in a Python dictionary. It's intended for demos and cases where you don't need persistence past the lifetime of the Python process.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/in_memory/) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [InMemoryByteStore](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.InMemoryByteStore.html) | [langchain_core](https://api.python.langchain.com/en/latest/core_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_core?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_core?style=flat-square&label=%20) |"
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": 1,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[b'v1', b'v2']\n"
-     ]
-    }
-   ],
    "source": [
-    "from langchain.storage import InMemoryByteStore\n",
+    "### Installation\n",
     "\n",
-    "store = InMemoryByteStore()\n",
-    "\n",
-    "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
+    "The LangChain `InMemoryByteStore` integration lives in the `langchain_core` package:"
    ]
   },
   {
@@ -47,12 +46,123 @@
    "execution_count": null,
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "%pip install -qU langchain_core"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now you can instantiate your byte store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.stores import InMemoryByteStore\n",
+    "\n",
+    "kv_store = InMemoryByteStore()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
+    "\n",
+    "You can set data under keys like this using the `mset` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[b'value1', b'value2']"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And you can delete data using the `mdelete` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `InMemoryByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/stores/langchain_core.stores.InMemoryByteStore.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
@@ -66,7 +176,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/index.mdx

@@ -1,29 +0,0 @@
----
-sidebar_position: 1
-sidebar_class_name: hidden
----
-
-# Stores
-
-In many different applications, having some sort of key-value storage is helpful. 
-In this section, we will look at a few different ways to store key-value pairs
-using implementations of the `ByteStore` interface.
-
-## Features (natively supported)
-
-All `ByteStore`s support the following functions, which are used for modifying
-**m**ultiple key-value pairs at once:
-
-- `mget(key: Sequence[str]) -> List[Optional[bytes]]`: get the contents of multiple keys, returning `None` if the key does not exist
-- `mset(key_value_pairs: Sequence[Tuple[str, bytes]]) -> None`: set the contents of multiple keys
-- `mdelete(key: Sequence[str]) -> None`: delete multiple keys
-- `yield_keys(prefix: Optional[str] = None) -> Iterator[str]`: yield all keys in the store, optionally filtering by a prefix
-
-## How to pick one
-
-`ByteStore`s are designed to be interchangeable. By default, most dependent integrations
-use the `InMemoryByteStore`, which is a simple in-memory key-value store.
-
-However, if you start having other requirements, like massive scalability or persistence,
-you can swap out the `ByteStore` implementation with one of the other ones documented
-in this section.

docs/docs/integrations/stores/redis.ipynb

@@ -2,7 +2,11 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
     "sidebar_label: Redis\n",
@@ -15,9 +19,30 @@
    "source": [
     "# RedisStore\n",
     "\n",
+    "This will help you get started with Redis [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `RedisStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html).\n",
+    "\n",
+    "## Overview\n",
+    "\n",
     "The `RedisStore` is an implementation of `ByteStore` that stores everything in your Redis instance.\n",
     "\n",
-    "To configure Redis, follow our [Redis guide](/docs/integrations/providers/redis)."
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/ioredis_storage) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [RedisStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ✅ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To create a Redis byte store, you'll need to set up a Redis instance. You can do this locally or via a provider - see our [Redis guide](/docs/integrations/providers/redis) for an overview of options."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain `RedisStore` integration lives in the `langchain_community` package:"
    ]
   },
   {
@@ -26,56 +51,128 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  redis"
+    "%pip install -qU langchain_community redis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our byte store:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[b'v1', b'v2']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.storage import RedisStore\n",
     "\n",
-    "store = RedisStore(redis_url=\"redis://localhost:6379\")\n",
+    "kv_store = RedisStore(redis_url=\"redis://localhost:6379\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
     "\n",
-    "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
+    "You can set data under keys like this using the `mset` method:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[b'value1', b'value2']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And you can delete data using the `mdelete` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `RedisStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
    "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/stores/upstash_redis.ipynb

@@ -2,7 +2,11 @@
  "cells": [
   {
    "cell_type": "raw",
-   "metadata": {},
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
    "source": [
     "---\n",
     "sidebar_label: Upstash Redis\n",
@@ -15,11 +19,48 @@
    "source": [
     "# UpstashRedisByteStore\n",
     "\n",
-    "The `UpstashRedisStore` is an implementation of `ByteStore` that stores everything in your Upstash-hosted Redis instance.\n",
+    "This will help you get started with Upstash redis [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all `UpstashRedisByteStore` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html).\n",
     "\n",
-    "To use the base `RedisStore` instead, see [this guide](/docs/integrations/stores/redis/)\n",
+    "## Overview\n",
     "\n",
-    "To configure Upstash Redis, follow our [Upstash guide](/docs/integrations/providers/upstash)."
+    "The `UpstashRedisStore` is an implementation of `ByteStore` that stores everything in your [Upstash](https://upstash.com/)-hosted Redis instance.\n",
+    "\n",
+    "To use the base `RedisStore` instead, see [this guide](/docs/integrations/stores/redis/).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/upstash_redis_storage) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [UpstashRedisByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html) | [langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html) | ❌ | ✅ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain_community?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "You'll first need to [sign up for an Upstash account](https://upstash.com/docs/redis/overall/getstarted). Next, you'll need to create a Redis database to connect to.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "Once you've created your database, get your database URL (don't forget the `https://`!) and token:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from getpass import getpass\n",
+    "\n",
+    "URL = getpass(\"Enter your Upstash URL\")\n",
+    "TOKEN = getpass(\"Enter your Upstash REST token\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain Upstash integration lives in the `langchain_community` package. You'll also need to install the `upstash-redis` package as a peer dependency:"
    ]
   },
   {
@@ -28,61 +69,130 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  upstash-redis"
+    "%pip install -qU langchain_community upstash-redis"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our byte store:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "[b'v1', b'v2']\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from langchain_community.storage import UpstashRedisByteStore\n",
     "from upstash_redis import Redis\n",
     "\n",
-    "URL = \"<UPSTASH_REDIS_REST_URL>\"\n",
-    "TOKEN = \"<UPSTASH_REDIS_REST_TOKEN>\"\n",
-    "\n",
     "redis_client = Redis(url=URL, token=TOKEN)\n",
-    "store = UpstashRedisByteStore(client=redis_client, ttl=None, namespace=\"test-ns\")\n",
+    "kv_store = UpstashRedisByteStore(client=redis_client, ttl=None, namespace=\"test-ns\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
     "\n",
-    "store.mset([(\"k1\", b\"v1\"), (\"k2\", b\"v2\")])\n",
-    "print(store.mget([\"k1\", \"k2\"]))"
+    "You can set data under keys like this using the `mset` method:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[b'value1', b'value2']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And you can delete data using the `mdelete` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[None, None]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `UpstashRedisByteStore` features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
    "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/integrations/text_embedding/fastembed.ipynb

@@ -73,16 +73,25 @@
     "- `max_length: int` (default: 512)\n",
     "    > The maximum number of tokens. Unknown behavior for values > 512.\n",
     "\n",
-    "- `cache_dir: Optional[str]`\n",
+    "- `cache_dir: Optional[str]` (default: None)\n",
     "    > The path to the cache directory. Defaults to `local_cache` in the parent directory.\n",
     "\n",
-    "- `threads: Optional[int]`\n",
-    "    > The number of threads a single onnxruntime session can use. Defaults to None.\n",
+    "- `threads: Optional[int]` (default: None)\n",
+    "    > The number of threads a single onnxruntime session can use.\n",
     "\n",
     "- `doc_embed_type: Literal[\"default\", \"passage\"]` (default: \"default\")\n",
     "    > \"default\": Uses FastEmbed's default embedding method.\n",
     "    \n",
-    "    > \"passage\": Prefixes the text with \"passage\" before embedding."
+    "    > \"passage\": Prefixes the text with \"passage\" before embedding.\n",
+    "\n",
+    "- `batch_size: int` (default: 256)\n",
+    "    > Batch size for encoding. Higher values will use more memory, but be faster.\n",
+    "\n",
+    "- `parallel: Optional[int]` (default: None)\n",
+    "\n",
+    "    > If `>1`, data-parallel encoding will be used, recommended for offline encoding of large datasets.\n",
+    "    > If `0`, use all available cores.\n",
+    "    > If `None`, don't use data-parallel processing, use default onnxruntime threading instead."
    ]
   },
   {

docs/docs/integrations/toolkits/github.ipynb

@@ -4,17 +4,191 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Github\n",
+    "---\n",
+    "sidebar_label: Github\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# GithubToolkit\n",
     "\n",
     "The `Github` toolkit contains tools that enable an LLM agent to interact with a github repository. \n",
     "The tool is a wrapper for the [PyGitHub](https://github.com/PyGithub/PyGithub) library. \n",
     "\n",
-    "## Quickstart\n",
+    "For detailed documentation of all GithubToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.github.toolkit.GitHubToolkit.html).\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "At a high-level, we will:\n",
     "\n",
     "1. Install the pygithub library\n",
     "2. Create a Github app\n",
     "3. Set your environmental variables\n",
-    "4. Pass the tools to your agent with `toolkit.get_tools()`\n",
+    "4. Pass the tools to your agent with `toolkit.get_tools()`"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "#### 1. Install dependencies\n",
+    "\n",
+    "This integration is implemented in `langchain-community`. We will also need the `pygithub` dependency:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  pygithub langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 2. Create a Github App\n",
+    "\n",
+    "[Follow the instructions here](https://docs.github.com/en/apps/creating-github-apps/registering-a-github-app/registering-a-github-app) to create and register a Github app. Make sure your app has the following [repository permissions:](https://docs.github.com/en/rest/overview/permissions-required-for-github-apps?apiVersion=2022-11-28)\n",
+    "\n",
+    "* Commit statuses (read only)\n",
+    "* Contents (read and write)\n",
+    "* Issues (read and write)\n",
+    "* Metadata (read only)\n",
+    "* Pull requests (read and write)\n",
+    "\n",
+    "Once the app has been registered, you must give your app permission to access each of the repositories you whish it to act upon. Use the App settings on [github.com here](https://github.com/settings/installations).\n",
+    "\n",
+    "\n",
+    "#### 3. Set Environment Variables\n",
+    "\n",
+    "Before initializing your agent, the following environment variables need to be set:\n",
+    "\n",
+    "* **GITHUB_APP_ID**- A six digit number found in your app's general settings\n",
+    "* **GITHUB_APP_PRIVATE_KEY**- The location of your app's private key .pem file, or the full text of that file as a string.\n",
+    "* **GITHUB_REPOSITORY**- The name of the Github repository you want your bot to act upon. Must follow the format {username}/{repo-name}. *Make sure the app has been added to this repository first!*\n",
+    "* Optional: **GITHUB_BRANCH**- The branch where the bot will make its commits. Defaults to `repo.default_branch`.\n",
+    "* Optional: **GITHUB_BASE_BRANCH**- The base branch of your repo upon which PRs will based from. Defaults to `repo.default_branch`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "for env_var in [\n",
+    "    \"GITHUB_APP_ID\",\n",
+    "    \"GITHUB_APP_PRIVATE_KEY\",\n",
+    "    \"GITHUB_REPOSITORY\",\n",
+    "]:\n",
+    "    if not os.getenv(env_var):\n",
+    "        os.environ[env_var] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our toolkit:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.agent_toolkits.github.toolkit import GitHubToolkit\n",
+    "from langchain_community.utilities.github import GitHubAPIWrapper\n",
+    "\n",
+    "github = GitHubAPIWrapper()\n",
+    "toolkit = GitHubToolkit.from_github_api_wrapper(github)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "View available tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Get Issues\n",
+      "Get Issue\n",
+      "Comment on Issue\n",
+      "List open pull requests (PRs)\n",
+      "Get Pull Request\n",
+      "Overview of files included in PR\n",
+      "Create Pull Request\n",
+      "List Pull Requests' Files\n",
+      "Create File\n",
+      "Read File\n",
+      "Update File\n",
+      "Delete File\n",
+      "Overview of existing files in Main branch\n",
+      "Overview of files in current working branch\n",
+      "List branches in this repository\n",
+      "Set active branch\n",
+      "Create a new branch\n",
+      "Get files from a directory\n",
+      "Search issues and pull requests\n",
+      "Search code\n",
+      "Create review request\n"
+     ]
+    }
+   ],
+   "source": [
+    "tools = toolkit.get_tools()\n",
+    "\n",
+    "for tool in tools:\n",
+    "    print(tool.name)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The purpose of these tools is as follows:\n",
     "\n",
     "Each of these steps will be explained in great detail below.\n",
     "\n",
@@ -32,70 +206,14 @@
     "\n",
     "7. **Update File**- updates a file in the repository.\n",
     "\n",
-    "8. **Delete File**- deletes a file from the repository.\n",
-    "\n"
+    "8. **Delete File**- deletes a file from the repository."
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Setup"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 1. Install the `pygithub` library "
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "vscode": {
-     "languageId": "shellscript"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet  pygithub langchain-community"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### 2. Create a Github App\n",
-    "\n",
-    "[Follow the instructions here](https://docs.github.com/en/apps/creating-github-apps/registering-a-github-app/registering-a-github-app) to create and register a Github app. Make sure your app has the following [repository permissions:](https://docs.github.com/en/rest/overview/permissions-required-for-github-apps?apiVersion=2022-11-28)\n",
-    "\n",
-    "* Commit statuses (read only)\n",
-    "* Contents (read and write)\n",
-    "* Issues (read and write)\n",
-    "* Metadata (read only)\n",
-    "* Pull requests (read and write)\n",
-    "\n",
-    "\n",
-    "Once the app has been registered, you must give your app permission to access each of the repositories you whish it to act upon. Use the App settings on [github.com here](https://github.com/settings/installations).\n",
-    "\n",
-    "### 3. Set Environmental Variables\n",
-    "\n",
-    "Before initializing your agent, the following environmental variables need to be set:\n",
-    "\n",
-    "* **GITHUB_APP_ID**- A six digit number found in your app's general settings\n",
-    "* **GITHUB_APP_PRIVATE_KEY**- The location of your app's private key .pem file, or the full text of that file as a string.\n",
-    "* **GITHUB_REPOSITORY**- The name of the Github repository you want your bot to act upon. Must follow the format {username}/{repo-name}. *Make sure the app has been added to this repository first!*\n",
-    "* Optional: **GITHUB_BRANCH**- The branch where the bot will make its commits. Defaults to `repo.default_branch`.\n",
-    "* Optional: **GITHUB_BASE_BRANCH**- The base branch of your repo upon which PRs will based from. Defaults to `repo.default_branch`.\n"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Example: Simple Agent"
+    "## Use within an agent"
    ]
   },
   {
@@ -824,6 +942,15 @@
     "\n",
     "agent.run(prompt)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all `GithubToolkit` features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.github.toolkit.GitHubToolkit.html)."
+   ]
   }
  ],
  "metadata": {
@@ -842,7 +969,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/toolkits/gmail.ipynb

@@ -4,34 +4,31 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Gmail\n",
-    "\n",
-    "This notebook walks through connecting a LangChain email to the `Gmail API`.\n",
-    "\n",
-    "To use this toolkit, you will need to set up your credentials explained in the [Gmail API docs](https://developers.google.com/gmail/api/quickstart/python#authorize_credentials_for_a_desktop_application). Once you've downloaded the `credentials.json` file, you can start using the Gmail API. Once this is done, we'll install the required libraries."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet  google-api-python-client > /dev/null\n",
-    "%pip install --upgrade --quiet  google-auth-oauthlib > /dev/null\n",
-    "%pip install --upgrade --quiet  google-auth-httplib2 > /dev/null\n",
-    "%pip install --upgrade --quiet  beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages"
+    "---\n",
+    "sidebar_label: GMail\n",
+    "---"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "You also need to install the `langchain-community` package where the integration lives:\n",
+    "# GmailToolkit\n",
     "\n",
-    "```bash\n",
-    "pip install -U langchain-community\n",
-    "```"
+    "This will help you getting started with the GMail [toolkit](/docs/concepts/#toolkits). This toolkit interacts with the GMail API to read messages, draft and send messages, and more. For detailed documentation of all GmailToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.toolkit.GmailToolkit.html).\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To use this toolkit, you will need to set up your credentials explained in the [Gmail API docs](https://developers.google.com/gmail/api/quickstart/python#authorize_credentials_for_a_desktop_application). Once you've downloaded the `credentials.json` file, you can start using the Gmail API."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This toolkit lives in the `langchain-google-community` package. We'll need the `gmail` extra:"
    ]
   },
   {
@@ -40,14 +37,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install -qU langchain-community"
+    "%pip install -qU langchain-google-community\\[gmail\\]"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability"
+    "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
@@ -57,14 +54,14 @@
    "outputs": [],
    "source": [
     "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
-    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Create the Toolkit\n",
+    "## Instantiation\n",
     "\n",
     "By default the toolkit reads the local `credentials.json` file. You can also manually provide a `Credentials` object."
    ]
@@ -72,12 +69,10 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "tags": []
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_community.agent_toolkits import GmailToolkit\n",
+    "from langchain_google_community import GmailToolkit\n",
     "\n",
     "toolkit = GmailToolkit()"
    ]
@@ -100,7 +95,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain_community.tools.gmail.utils import (\n",
+    "from langchain_google_community.gmail.utils import (\n",
     "    build_resource_service,\n",
     "    get_gmail_credentials,\n",
     ")\n",
@@ -116,6 +111,15 @@
     "toolkit = GmailToolkit(api_resource=api_resource)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "View available tools:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 5,
@@ -147,7 +151,18 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Usage\n",
+    "- [GmailCreateDraft](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.create_draft.GmailCreateDraft.html)\n",
+    "- [GmailSendMessage](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.send_message.GmailSendMessage.html)\n",
+    "- [GmailSearch](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.search.GmailSearch.html)\n",
+    "- [GmailGetMessage](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.get_message.GmailGetMessage.html)\n",
+    "- [GmailGetThread](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.get_thread.GmailGetThread.html)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use within an agent\n",
     "\n",
     "We show here how to use it as part of an [agent](/docs/tutorials/agents). We use the OpenAI Functions Agent, so we will need to setup and install the required dependencies for that. We will also use [LangSmith Hub](https://smith.langchain.com/hub) to pull the prompt from, so we will need to install that.\n",
     "\n",
@@ -303,7 +318,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/toolkits/index.mdx

@@ -0,0 +1,21 @@
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+---
+
+# Toolkits
+
+**Toolkits** are collections of tools that are designed to be used together for specific tasks. They include conveniences for loading tools
+that share common authentication, services, or other objects. They can be implemented by subclassing the
+[BaseToolkit](https://api.python.langchain.com/en/latest/tools/langchain_core.tools.BaseToolkit.html#langchain_core.tools.BaseToolkit) class.
+
+This table lists common toolkits.
+
+
+| Toolkit | Package |
+|------|---------------|
+| [GitHubToolkit](/docs/integrations/toolkits/github) | [langchain_community.agent_toolkits.github](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.github.toolkit.GitHubToolkit.html) |
+| [GmailToolkit](/docs/integrations/toolkits/gmail) | [langchain_google_community.gmail.toolkit](https://api.python.langchain.com/en/latest/gmail/langchain_google_community.gmail.toolkit.GmailToolkit.html) |
+| [RequestsToolkit](/docs/integrations/toolkits/requests) | [langchain_community.agent_toolkits.openapi](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit.html) |
+| [SlackToolkit](/docs/integrations/toolkits/slack) | [langchain_community.agent_toolkits.slack](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.slack.toolkit.SlackToolkit.html) |
+| [SQLDatabaseToolkit](/docs/integrations/toolkits/sql_database) | [langchain_community.agent_toolkits.sql](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.sql.toolkit.SQLDatabaseToolkit.html) |

docs/docs/integrations/toolkits/requests.ipynb

@@ -0,0 +1,361 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "050c5580-2c85-4763-8783-59dbd20395a5",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: Requests\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cfe4185a-34dc-4cdc-b831-001954f2d6e8",
+   "metadata": {},
+   "source": [
+    "# Requests Toolkit\n",
+    "\n",
+    "We can use the Requests [toolkit](/docs/concepts/#toolkits) to construct agents that generate HTTP requests.\n",
+    "\n",
+    "For detailed documentation of all API toolkit features and configurations head to the API reference for [RequestsToolkit](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit.html).\n",
+    "\n",
+    "## ⚠️ Security note ⚠️\n",
+    "There are inherent risks in giving models discretion to execute real-world actions. Take precautions to mitigate these risks:\n",
+    "\n",
+    "- Make sure that permissions associated with the tools are narrowly-scoped (e.g., for database operations or API requests);\n",
+    "- When desired, make use of human-in-the-loop workflows."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d968e982-f370-4614-8469-c1bc71ee3e32",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "### Installation\n",
+    "\n",
+    "This toolkit lives in the `langchain-community` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f74f05fb-3f24-4c0b-a17f-cf4edeedbb9a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36a178eb-1f2c-411e-bf25-0240ead4c62a",
+   "metadata": {},
+   "source": [
+    "Note that if you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8e68d0cd-6233-481c-b048-e8d95cba4c35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a7e2f64a-a72e-4fef-be52-eaf7c5072d24",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "First we will demonstrate a minimal example.\n",
+    "\n",
+    "**NOTE**: There are inherent risks in giving models discretion to execute real-world actions. We must \"opt-in\" to these risks by setting `allow_dangerous_request=True` to use these tools.\n",
+    "**This can be dangerous for calling unwanted requests**. Please make sure your custom OpenAPI spec (yaml) is safe and that permissions associated with the tools are narrowly-scoped."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "018bd070-9fc8-459b-8d28-b4a3e283e640",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ALLOW_DANGEROUS_REQUEST = True"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a024f7b3-5437-4878-bd16-c4783bff394c",
+   "metadata": {},
+   "source": [
+    "We can use the [JSONPlaceholder](https://jsonplaceholder.typicode.com) API as a testing ground.\n",
+    "\n",
+    "Let's create (a subset of) its API spec:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2dcbcf92-2ad5-49c3-94ac-91047ccc8c5b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Any, Dict, Union\n",
+    "\n",
+    "import requests\n",
+    "import yaml\n",
+    "\n",
+    "\n",
+    "def _get_schema(response_json: Union[dict, list]) -> dict:\n",
+    "    if isinstance(response_json, list):\n",
+    "        response_json = response_json[0] if response_json else {}\n",
+    "    return {key: type(value).__name__ for key, value in response_json.items()}\n",
+    "\n",
+    "\n",
+    "def _get_api_spec() -> str:\n",
+    "    base_url = \"https://jsonplaceholder.typicode.com\"\n",
+    "    endpoints = [\n",
+    "        \"/posts\",\n",
+    "        \"/comments\",\n",
+    "    ]\n",
+    "    common_query_parameters = [\n",
+    "        {\n",
+    "            \"name\": \"_limit\",\n",
+    "            \"in\": \"query\",\n",
+    "            \"required\": False,\n",
+    "            \"schema\": {\"type\": \"integer\", \"example\": 2},\n",
+    "            \"description\": \"Limit the number of results\",\n",
+    "        }\n",
+    "    ]\n",
+    "    openapi_spec: Dict[str, Any] = {\n",
+    "        \"openapi\": \"3.0.0\",\n",
+    "        \"info\": {\"title\": \"JSONPlaceholder API\", \"version\": \"1.0.0\"},\n",
+    "        \"servers\": [{\"url\": base_url}],\n",
+    "        \"paths\": {},\n",
+    "    }\n",
+    "    # Iterate over the endpoints to construct the paths\n",
+    "    for endpoint in endpoints:\n",
+    "        response = requests.get(base_url + endpoint)\n",
+    "        if response.status_code == 200:\n",
+    "            schema = _get_schema(response.json())\n",
+    "            openapi_spec[\"paths\"][endpoint] = {\n",
+    "                \"get\": {\n",
+    "                    \"summary\": f\"Get {endpoint[1:]}\",\n",
+    "                    \"parameters\": common_query_parameters,\n",
+    "                    \"responses\": {\n",
+    "                        \"200\": {\n",
+    "                            \"description\": \"Successful response\",\n",
+    "                            \"content\": {\n",
+    "                                \"application/json\": {\n",
+    "                                    \"schema\": {\"type\": \"object\", \"properties\": schema}\n",
+    "                                }\n",
+    "                            },\n",
+    "                        }\n",
+    "                    },\n",
+    "                }\n",
+    "            }\n",
+    "    return yaml.dump(openapi_spec, sort_keys=False)\n",
+    "\n",
+    "\n",
+    "api_spec = _get_api_spec()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "db3d6148-ae65-4a1d-91a6-59ee3e4e6efa",
+   "metadata": {},
+   "source": [
+    "Next we can instantiate the toolkit. We require no authorization or other headers for this API:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "63a630b3-45bb-4525-865b-083f322b944b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.agent_toolkits.openapi.toolkit import RequestsToolkit\n",
+    "from langchain_community.utilities.requests import TextRequestsWrapper\n",
+    "\n",
+    "toolkit = RequestsToolkit(\n",
+    "    requests_wrapper=TextRequestsWrapper(headers={}),\n",
+    "    allow_dangerous_requests=ALLOW_DANGEROUS_REQUEST,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f4224a64-843a-479d-8a7b-84719e4b9d0c",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "View available tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "70ea0f4e-9f10-4906-894b-08df832fd515",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[RequestsGetTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
+       " RequestsPostTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
+       " RequestsPatchTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
+       " RequestsPutTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True),\n",
+       " RequestsDeleteTool(requests_wrapper=TextRequestsWrapper(headers={}, aiosession=None, auth=None, response_content_type='text', verify=True), allow_dangerous_requests=True)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = toolkit.get_tools()\n",
+    "\n",
+    "tools"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a21a6ca4-d650-4b7d-a944-1a8771b5293a",
+   "metadata": {},
+   "source": [
+    "- [RequestsGetTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsGetTool.html)\n",
+    "- [RequestsPostTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsPostTool.html)\n",
+    "- [RequestsPatchTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsPatchTool.html)\n",
+    "- [RequestsPutTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsPutTool.html)\n",
+    "- [RequestsDeleteTool](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.requests.tool.RequestsDeleteTool.html)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e2dbb304-abf2-472a-9130-f03150a40549",
+   "metadata": {},
+   "source": [
+    "## Use within an agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "db062da7-f22c-4f36-9df8-1da96c9f7538",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "system_message = \"\"\"\n",
+    "You have access to an API to help answer user queries.\n",
+    "Here is documentation on the API:\n",
+    "{api_spec}\n",
+    "\"\"\".format(api_spec=api_spec)\n",
+    "\n",
+    "agent_executor = create_react_agent(llm, tools, state_modifier=system_message)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c1e47be9-374a-457c-928a-48f02b5530e3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "Fetch the top two posts. What are their titles?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  requests_get (call_RV2SOyzCnV5h2sm4WPgG8fND)\n",
+      " Call ID: call_RV2SOyzCnV5h2sm4WPgG8fND\n",
+      "  Args:\n",
+      "    url: https://jsonplaceholder.typicode.com/posts?_limit=2\n",
+      "=================================\u001b[1m Tool Message \u001b[0m=================================\n",
+      "Name: requests_get\n",
+      "\n",
+      "[\n",
+      "  {\n",
+      "    \"userId\": 1,\n",
+      "    \"id\": 1,\n",
+      "    \"title\": \"sunt aut facere repellat provident occaecati excepturi optio reprehenderit\",\n",
+      "    \"body\": \"quia et suscipit\\nsuscipit recusandae consequuntur expedita et cum\\nreprehenderit molestiae ut ut quas totam\\nnostrum rerum est autem sunt rem eveniet architecto\"\n",
+      "  },\n",
+      "  {\n",
+      "    \"userId\": 1,\n",
+      "    \"id\": 2,\n",
+      "    \"title\": \"qui est esse\",\n",
+      "    \"body\": \"est rerum tempore vitae\\nsequi sint nihil reprehenderit dolor beatae ea dolores neque\\nfugiat blanditiis voluptate porro vel nihil molestiae ut reiciendis\\nqui aperiam non debitis possimus qui neque nisi nulla\"\n",
+      "  }\n",
+      "]\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "The titles of the top two posts are:\n",
+      "1. \"sunt aut facere repellat provident occaecati excepturi optio reprehenderit\"\n",
+      "2. \"qui est esse\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "example_query = \"Fetch the top two posts. What are their titles?\"\n",
+    "\n",
+    "events = agent_executor.stream(\n",
+    "    {\"messages\": [(\"user\", example_query)]},\n",
+    "    stream_mode=\"values\",\n",
+    ")\n",
+    "for event in events:\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "01ec4886-de3d-4fda-bd05-e3f254810969",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all API toolkit features and configurations head to the API reference for [RequestsToolkit](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.openapi.toolkit.RequestsToolkit.html)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/toolkits/slack.ipynb

@@ -4,109 +4,139 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Slack\n",
-    "\n",
-    "This notebook walks through connecting LangChain to your `Slack` account.\n",
-    "\n",
-    "To use this toolkit, you will need to get a token explained in the [Slack API docs](https://api.slack.com/tutorials/tracks/getting-a-token). Once you've received a SLACK_USER_TOKEN, you can input it as an environmental variable below."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n",
-      "\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m23.3.2\u001b[0m\n",
-      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
-   "source": [
-    "%pip install --upgrade --quiet  slack_sdk > /dev/null\n",
-    "%pip install --upgrade --quiet  beautifulsoup4 > /dev/null # This is optional but is useful for parsing HTML messages\n",
-    "%pip install --upgrade --quiet  python-dotenv > /dev/null # This is for loading environmental variables from a .env file"
+    "---\n",
+    "sidebar_label: Slack\n",
+    "---"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Set Environmental Variables\n",
+    "# SlackToolkit\n",
     "\n",
-    "The toolkit will read the SLACK_USER_TOKEN environmental variable to authenticate the user so you need to set them here. You will also need to set your OPENAI_API_KEY to use the agent later."
+    "This will help you getting started with the Slack [toolkit](/docs/concepts/#toolkits). For detailed documentation of all SlackToolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.slack.toolkit.SlackToolkit.html).\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To use this toolkit, you will need to get a token as explained in the [Slack API docs](https://api.slack.com/tutorials/tracks/getting-a-token). Once you've received a SLACK_USER_TOKEN, you can input it as an environment variable below."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "True"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
-    "# Set environmental variables here\n",
-    "# In this example, you set environmental variables by loading a .env file.\n",
-    "import dotenv\n",
+    "import getpass\n",
+    "import os\n",
     "\n",
-    "dotenv.load_dotenv()"
+    "if not os.getenv(\"SLACK_USER_TOKEN\"):\n",
+    "    os.environ[\"SLACK_USER_TOKEN\"] = getpass.getpass(\"Enter your Slack user token: \")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Create the Toolkit and Get Tools\n",
-    "\n",
-    "To start, you need to create the toolkit, so you can access its tools later."
+    "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[SlackGetChannel(client=<slack_sdk.web.client.WebClient object at 0x11eba6a00>),\n",
-       " SlackGetMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba69d0>),\n",
-       " SlackScheduleMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba65b0>),\n",
-       " SlackSendMessage(client=<slack_sdk.web.client.WebClient object at 0x11eba6790>)]"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This toolkit lives in the `langchain-community` package. We will also need the Slack SDK:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU langchain-community slack_sdk"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Optionally, we can install beautifulsoup4 to assist in parsing HTML messages:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU beautifulsoup4 # This is optional but is useful for parsing HTML messages"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our toolkit:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from langchain_community.agent_toolkits import SlackToolkit\n",
     "\n",
-    "toolkit = SlackToolkit()\n",
+    "toolkit = SlackToolkit()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "View available tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[SlackGetChannel(client=<slack_sdk.web.client.WebClient object at 0x10ce3a4d0>),\n",
+       " SlackGetMessage(client=<slack_sdk.web.client.WebClient object at 0x10ce3a0e0>),\n",
+       " SlackScheduleMessage(client=<slack_sdk.web.client.WebClient object at 0x10ce3a050>),\n",
+       " SlackSendMessage(client=<slack_sdk.web.client.WebClient object at 0x10ce3a020>)]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
     "tools = toolkit.get_tools()\n",
+    "\n",
     "tools"
    ]
   },
@@ -114,7 +144,78 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Use within an ReAct Agent"
+    "This toolkit loads:\n",
+    "\n",
+    "- [SlackGetChannel](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.slack.get_channel.SlackGetChannel.html)\n",
+    "- [SlackGetMessage](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.slack.get_message.SlackGetMessage.html)\n",
+    "- [SlackScheduleMessage](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.slack.schedule_message.SlackScheduleMessage.html)\n",
+    "- [SlackSendMessage](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.slack.send_message.SlackSendMessage.html)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use within an agent\n",
+    "\n",
+    "Let's equip an agent with the Slack toolkit and query for information about a channel."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "agent_executor = create_react_agent(llm, tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "================================\u001b[1m Human Message \u001b[0m=================================\n",
+      "\n",
+      "When was the #general channel created?\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "Tool Calls:\n",
+      "  get_channelid_name_dict (call_mINmB55OWDIkXykGXZXaL5Ar)\n",
+      " Call ID: call_mINmB55OWDIkXykGXZXaL5Ar\n",
+      "  Args:\n",
+      "==================================\u001b[1m Ai Message \u001b[0m==================================\n",
+      "\n",
+      "The #general channel was created on Unix timestamp 1671043305, which corresponds to \"Mon, 12 Dec 2022 18:41:45 GMT\" in human-readable format.\n"
+     ]
+    }
+   ],
+   "source": [
+    "example_query = \"When was the #general channel created?\"\n",
+    "\n",
+    "events = agent_executor.stream(\n",
+    "    {\"messages\": [(\"user\", example_query)]},\n",
+    "    stream_mode=\"values\",\n",
+    ")\n",
+    "for event in events:\n",
+    "    message = event[\"messages\"][-1]\n",
+    "    if message.type != \"tool\":  # mask sensitive information\n",
+    "        event[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example with AgentExecutor:"
    ]
   },
   {
@@ -236,11 +337,13 @@
    ]
   },
   {
-   "cell_type": "code",
-   "execution_count": null,
+   "cell_type": "markdown",
    "metadata": {},
-   "outputs": [],
-   "source": []
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__Toolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/langchain_community.agent_toolkits.slack.toolkit.SlackToolkit.html)."
+   ]
   }
  ],
  "metadata": {
@@ -259,7 +362,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.6"
+   "version": "3.10.4"
   }
  },
  "nbformat": 4,

docs/docs/integrations/tools/databricks.ipynb

@@ -38,7 +38,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet databricks-sdk langchain-community langchain-openai"
+    "%pip install --upgrade --quiet databricks-sdk langchain-community mlflow"
    ]
   },
   {
@@ -47,9 +47,9 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain_openai import ChatOpenAI\n",
+    "from langchain_community.chat_models.databricks import ChatDatabricks\n",
     "\n",
-    "llm = ChatOpenAI(model=\"gpt-3.5-turbo\")"
+    "llm = ChatDatabricks(endpoint=\"databricks-meta-llama-3-70b-instruct\")"
    ]
   },
   {

docs/docs/integrations/vectorstores/memorydb.ipynb

@@ -0,0 +1,537 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Amazon MemoryDB\n",
+    "\n",
+    ">[Vector Search](https://docs.aws.amazon.com/memorydb/latest/devguide/vector-search.html/) introduction and langchain integration guide.\n",
+    "\n",
+    "## What is Amazon MemoryDB?\n",
+    "\n",
+    "MemoryDB is compatible with Redis OSS, a popular open source data store, enabling you to quickly build applications using the same flexible and friendly Redis OSS data structures, APIs, and commands that they already use today. With MemoryDB, all of your data is stored in memory, which enables you to achieve microsecond read and single-digit millisecond write latency and high throughput. MemoryDB also stores data durably across multiple Availability Zones (AZs) using a Multi-AZ transactional log to enable fast failover, database recovery, and node restarts.\n",
+    "\n",
+    "\n",
+    "## Vector search for MemoryDB \n",
+    "\n",
+    "Vector search for MemoryDB extends the functionality of MemoryDB. Vector search can be used in conjunction with existing MemoryDB functionality. Applications that do not use vector search are unaffected by its presence. Vector search is available in all Regions that MemoryDB is available. You can use your existing MemoryDB data or Redis OSS API to build machine learning and generative AI use cases, such as retrieval-augmented generation, anomaly detection, document retrieval, and real-time recommendations.\n",
+    "\n",
+    "* Indexing of multiple fields in Redis hashes and `JSON`\n",
+    "* Vector similarity search (with `HNSW` (ANN) or `FLAT` (KNN))\n",
+    "* Vector Range Search (e.g. find all vectors within a radius of a query vector)\n",
+    "* Incremental indexing without performance loss\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up\n",
+    "\n",
+    "\n",
+    "### Install Redis Python client\n",
+    "\n",
+    "`Redis-py` is a python  client that can be used to connect to MemoryDB"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet  redis langchain-aws"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_aws.embeddings import BedrockEmbeddings\n",
+    "\n",
+    "embeddings = BedrockEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### MemoryDB Connection\n",
+    "\n",
+    "Valid Redis Url schemas are:\n",
+    "1. `redis://`  - Connection to Redis cluster, unencrypted\n",
+    "2. `rediss://` - Connection to Redis cluster, with TLS encryption\n",
+    "\n",
+    "More information about additional connection parameters can be found in the [redis-py documentation](https://redis-py.readthedocs.io/en/stable/connections.html)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Sample data\n",
+    "\n",
+    "First we will describe some sample data so that the various attributes of the Redis vector store can be demonstrated."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metadata = [\n",
+    "    {\n",
+    "        \"user\": \"john\",\n",
+    "        \"age\": 18,\n",
+    "        \"job\": \"engineer\",\n",
+    "        \"credit_score\": \"high\",\n",
+    "    },\n",
+    "    {\n",
+    "        \"user\": \"derrick\",\n",
+    "        \"age\": 45,\n",
+    "        \"job\": \"doctor\",\n",
+    "        \"credit_score\": \"low\",\n",
+    "    },\n",
+    "    {\n",
+    "        \"user\": \"nancy\",\n",
+    "        \"age\": 94,\n",
+    "        \"job\": \"doctor\",\n",
+    "        \"credit_score\": \"high\",\n",
+    "    },\n",
+    "    {\n",
+    "        \"user\": \"tyler\",\n",
+    "        \"age\": 100,\n",
+    "        \"job\": \"engineer\",\n",
+    "        \"credit_score\": \"high\",\n",
+    "    },\n",
+    "    {\n",
+    "        \"user\": \"joe\",\n",
+    "        \"age\": 35,\n",
+    "        \"job\": \"dentist\",\n",
+    "        \"credit_score\": \"medium\",\n",
+    "    },\n",
+    "]\n",
+    "texts = [\"foo\", \"foo\", \"foo\", \"bar\", \"bar\"]\n",
+    "index_name = \"users\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Create MemoryDB vector store\n",
+    "\n",
+    "The InMemoryVectorStore instance can be initialized using the below methods \n",
+    "- ``InMemoryVectorStore.__init__`` - Initialize directly\n",
+    "- ``InMemoryVectorStore.from_documents`` - Initialize from a list of ``Langchain.docstore.Document`` objects\n",
+    "- ``InMemoryVectorStore.from_texts`` - Initialize from a list of texts (optionally with metadata)\n",
+    "- ``InMemoryVectorStore.from_existing_index`` - Initialize from an existing MemoryDB index\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain_aws.vectorstores.inmemorydb import InMemoryVectorStore\n",
+    "\n",
+    "vds = InMemoryVectorStore.from_texts(\n",
+    "    embeddings,\n",
+    "    redis_url=\"rediss://cluster_endpoint:6379/ssl=True ssl_cert_reqs=none\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'users'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "vds.index_name"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Querying\n",
+    "\n",
+    "There are multiple ways to query the ``InMemoryVectorStore``  implementation based on what use case you have:\n",
+    "\n",
+    "- ``similarity_search``: Find the most similar vectors to a given vector.\n",
+    "- ``similarity_search_with_score``: Find the most similar vectors to a given vector and return the vector distance\n",
+    "- ``similarity_search_limit_score``: Find the most similar vectors to a given vector and limit the number of results to the ``score_threshold``\n",
+    "- ``similarity_search_with_relevance_scores``: Find the most similar vectors to a given vector and return the vector similarities\n",
+    "- ``max_marginal_relevance_search``: Find the most similar vectors to a given vector while also optimizing for diversity"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "foo\n"
+     ]
+    }
+   ],
+   "source": [
+    "results = vds.similarity_search(\"foo\")\n",
+    "print(results[0].page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Content: foo --- Score: 0.0\n",
+      "Content: foo --- Score: 0.0\n",
+      "Content: foo --- Score: 0.0\n",
+      "Content: bar --- Score: 0.1566\n",
+      "Content: bar --- Score: 0.1566\n"
+     ]
+    }
+   ],
+   "source": [
+    "# with scores (distances)\n",
+    "results = vds.similarity_search_with_score(\"foo\", k=5)\n",
+    "for result in results:\n",
+    "    print(f\"Content: {result[0].page_content} --- Score: {result[1]}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Content: foo --- Score: 0.0\n",
+      "Content: foo --- Score: 0.0\n",
+      "Content: foo --- Score: 0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "# limit the vector distance that can be returned\n",
+    "results = vds.similarity_search_with_score(\"foo\", k=5, distance_threshold=0.1)\n",
+    "for result in results:\n",
+    "    print(f\"Content: {result[0].page_content} --- Score: {result[1]}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Content: foo --- Similiarity: 1.0\n",
+      "Content: foo --- Similiarity: 1.0\n",
+      "Content: foo --- Similiarity: 1.0\n",
+      "Content: bar --- Similiarity: 0.8434\n",
+      "Content: bar --- Similiarity: 0.8434\n"
+     ]
+    }
+   ],
+   "source": [
+    "# with scores\n",
+    "results = vds.similarity_search_with_relevance_scores(\"foo\", k=5)\n",
+    "for result in results:\n",
+    "    print(f\"Content: {result[0].page_content} --- Similiarity: {result[1]}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['doc:users:b9c71d62a0a34241a37950b448dafd38']"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# you can also add new documents as follows\n",
+    "new_document = [\"baz\"]\n",
+    "new_metadata = [{\"user\": \"sam\", \"age\": 50, \"job\": \"janitor\", \"credit_score\": \"high\"}]\n",
+    "# both the document and metadata must be lists\n",
+    "vds.add_texts(new_document, new_metadata)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## MemoryDB as Retriever\n",
+    "\n",
+    "Here we go over different options for using the vector store as a retriever.\n",
+    "\n",
+    "There are three different search methods we can use to do retrieval. By default, it will use semantic similarity."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Content: foo  --- Score:  0.0\n",
+      "Content: foo  --- Score:  0.0\n",
+      "Content: foo  --- Score:  0.0\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"foo\"\n",
+    "results = vds.similarity_search_with_score(query, k=3, return_metadata=True)\n",
+    "\n",
+    "for result in results:\n",
+    "    print(\"Content:\", result[0].page_content, \" --- Score: \", result[1])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vds.as_retriever(search_type=\"similarity\", search_kwargs={\"k\": 4})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='foo', metadata={'id': 'doc:users_modified:988ecca7574048e396756efc0e79aeca', 'user': 'john', 'job': 'engineer', 'credit_score': 'high', 'age': '18'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users_modified:009b1afeb4084cc6bdef858c7a99b48e', 'user': 'derrick', 'job': 'doctor', 'credit_score': 'low', 'age': '45'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users_modified:7087cee9be5b4eca93c30fbdd09a2731', 'user': 'nancy', 'job': 'doctor', 'credit_score': 'high', 'age': '94'}),\n",
+       " Document(page_content='bar', metadata={'id': 'doc:users_modified:01ef6caac12b42c28ad870aefe574253', 'user': 'tyler', 'job': 'engineer', 'credit_score': 'high', 'age': '100'})]"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs = retriever.invoke(query)\n",
+    "docs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "There is also the `similarity_distance_threshold` retriever which allows the user to specify the vector distance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vds.as_retriever(\n",
+    "    search_type=\"similarity_distance_threshold\",\n",
+    "    search_kwargs={\"k\": 4, \"distance_threshold\": 0.1},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='foo', metadata={'id': 'doc:users_modified:988ecca7574048e396756efc0e79aeca', 'user': 'john', 'job': 'engineer', 'credit_score': 'high', 'age': '18'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users_modified:009b1afeb4084cc6bdef858c7a99b48e', 'user': 'derrick', 'job': 'doctor', 'credit_score': 'low', 'age': '45'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users_modified:7087cee9be5b4eca93c30fbdd09a2731', 'user': 'nancy', 'job': 'doctor', 'credit_score': 'high', 'age': '94'})]"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs = retriever.invoke(query)\n",
+    "docs"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Lastly, the ``similarity_score_threshold`` allows the user to define the minimum score for similar documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vds.as_retriever(\n",
+    "    search_type=\"similarity_score_threshold\",\n",
+    "    search_kwargs={\"score_threshold\": 0.9, \"k\": 10},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='foo', metadata={'id': 'doc:users_modified:988ecca7574048e396756efc0e79aeca', 'user': 'john', 'job': 'engineer', 'credit_score': 'high', 'age': '18'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users_modified:009b1afeb4084cc6bdef858c7a99b48e', 'user': 'derrick', 'job': 'doctor', 'credit_score': 'low', 'age': '45'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users_modified:7087cee9be5b4eca93c30fbdd09a2731', 'user': 'nancy', 'job': 'doctor', 'credit_score': 'high', 'age': '94'})]"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.invoke(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='foo', metadata={'id': 'doc:users:8f6b673b390647809d510112cde01a27', 'user': 'john', 'job': 'engineer', 'credit_score': 'high', 'age': '18'}),\n",
+       " Document(page_content='bar', metadata={'id': 'doc:users:93521560735d42328b48c9c6f6418d6a', 'user': 'tyler', 'job': 'engineer', 'credit_score': 'high', 'age': '100'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users:125ecd39d07845eabf1a699d44134a5b', 'user': 'nancy', 'job': 'doctor', 'credit_score': 'high', 'age': '94'}),\n",
+       " Document(page_content='foo', metadata={'id': 'doc:users:d6200ab3764c466082fde3eaab972a2a', 'user': 'derrick', 'job': 'doctor', 'credit_score': 'low', 'age': '45'})]"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.invoke(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Delete  index"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "To delete your entries you have to address them by their keys."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# delete the indices too\n",
+    "InMemoryVectorStore.drop_index(\n",
+    "    index_name=\"users\", delete_documents=True, redis_url=\"redis://localhost:6379\"\n",
+    ")\n",
+    "InMemoryVectorStore.drop_index(\n",
+    "    index_name=\"users_modified\",\n",
+    "    delete_documents=True,\n",
+    "    redis_url=\"redis://localhost:6379\",\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/vectorstores/qdrant.ipynb

@@ -317,7 +317,7 @@
     "To search with only dense vectors,\n",
     "\n",
     "- The `retrieval_mode` parameter should be set to `RetrievalMode.DENSE`(default).\n",
-    "- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter."
+    "- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided to the `embedding` parameter."
    ]
   },
   {
@@ -407,7 +407,7 @@
     "To perform a hybrid search using dense and sparse vectors with score fusion,\n",
     "\n",
     "- The `retrieval_mode` parameter should be set to `RetrievalMode.HYBRID`.\n",
-    "- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided for the `embedding` parameter.\n",
+    "- A [dense embeddings](https://python.langchain.com/v0.2/docs/integrations/text_embedding/) value should be provided to the `embedding` parameter.\n",
     "- An implementation of the [`SparseEmbeddings`](https://github.com/langchain-ai/langchain/blob/master/libs/partners/qdrant/langchain_qdrant/sparse_embeddings.py) interface using any sparse embeddings provider has to be provided as value to the `sparse_embedding` parameter.\n",
     "\n",
     "Note that if you've added documents with the `HYBRID` mode, you can switch to any retrieval mode when searching. Since both the dense and sparse vectors are available in the collection."

docs/docs/tutorials/agents.ipynb

@@ -381,7 +381,7 @@
    "id": "f8014c9d",
    "metadata": {},
    "source": [
-    "Now, we can initalize the agent with the LLM and the tools.\n",
+    "Now, we can initialize the agent with the LLM and the tools.\n",
     "\n",
     "Note that we are passing in the `model`, not `model_with_tools`. That is because `create_react_agent` will call `.bind_tools` for us under the hood."
    ]

docs/docs/tutorials/local_rag.ipynb

@@ -19,17 +19,28 @@
     "\n",
     ":::\n",
     "\n",
-    "The popularity of projects like [PrivateGPT](https://github.com/imartinez/privateGPT), [llama.cpp](https://github.com/ggerganov/llama.cpp), [GPT4All](https://github.com/nomic-ai/gpt4all), and [llamafile](https://github.com/Mozilla-Ocho/llamafile) underscore the importance of running LLMs locally.\n",
+    "The popularity of projects like [llama.cpp](https://github.com/ggerganov/llama.cpp), [Ollama](https://github.com/ollama/ollama), and [llamafile](https://github.com/Mozilla-Ocho/llamafile) underscore the importance of running LLMs locally.\n",
     "\n",
-    "LangChain has [integrations](https://integrations.langchain.com/) with many open-source LLMs that can be run locally.\n",
+    "LangChain has integrations with [many open-source LLM providers](/docs/how_to/local_llms) that can be run locally.\n",
     "\n",
-    "See [here](/docs/how_to/local_llms) for setup instructions for these LLMs. \n",
+    "This guide will show how to run `LLaMA 3.1` via one provider, [Ollama](/docs/integrations/providers/ollama/) locally (e.g., on your laptop) using local embeddings and a local LLM. However, you can set up and swap in other local providers, such as [LlamaCPP](/docs/integrations/chat/llamacpp/) if you prefer.\n",
     "\n",
-    "For example, here we show how to run `GPT4All` or `LLaMA2` locally (e.g., on your laptop) using local embeddings and a local LLM.\n",
+    "**Note:** This guide uses a [chat model](/docs/concepts/#chat-models) wrapper that takes care of formatting your input prompt for the specific local model you're using. However, if you are prompting local models directly with a [text-in/text-out LLM](/docs/concepts/#llms) wrapper, you may need to use a prompt tailed for your specific model. This will often [require the inclusion of special tokens](https://huggingface.co/blog/llama2#how-to-prompt-llama-2). [Here's an example for LLaMA 2](https://smith.langchain.com/hub/rlm/rag-prompt-llama).\n",
     "\n",
-    "## Document Loading \n",
+    "## Setup\n",
     "\n",
-    "First, install packages needed for local embeddings and vector storage."
+    "First we'll need to set up Ollama.\n",
+    "\n",
+    "The instructions [on their GitHub repo](https://github.com/ollama/ollama) provide details, which we summarize here:\n",
+    "\n",
+    "- [Download](https://ollama.com/download) and run their desktop app\n",
+    "- From command line, fetch models from [this list of options](https://ollama.com/library). For this guide, you'll need:\n",
+    "  - A general purpose model like `llama3.1:8b`, which you can pull with something like `ollama pull llama3.1:8b`\n",
+    "  - A [text embedding model](https://ollama.com/search?c=embedding) like `nomic-embed-text`, which you can pull with something like `ollama pull nomic-embed-text`\n",
+    "- When the app is running, all models are automatically served on `localhost:11434`\n",
+    "- Note that your model choice will depend on your hardware capabilities\n",
+    "\n",
+    "Next, install packages needed for local embeddings, vector storage, and inference."
    ]
   },
   {
@@ -39,7 +50,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "%pip install --upgrade --quiet  langchain langchain-community langchainhub gpt4all langchain-chroma "
+    "# Document loading, retrieval methods and text splitting\n",
+    "%pip install -qU langchain langchain_community\n",
+    "\n",
+    "# Local vector store via Chroma\n",
+    "%pip install -qU langchain_chroma\n",
+    "\n",
+    "# Local inference and embeddings via Ollama\n",
+    "%pip install -qU langchain_ollama"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "02b7914e",
+   "metadata": {},
+   "source": [
+    "You can also [see this page](/docs/integrations/text_embedding/) for a full list of available embeddings models"
    ]
   },
   {
@@ -47,20 +73,22 @@
    "id": "5e7543fa",
    "metadata": {},
    "source": [
-    "Load and split an example document.\n",
+    "## Document Loading\n",
     "\n",
-    "We'll use a blog post on agents as an example."
+    "Now let's load and split an example document.\n",
+    "\n",
+    "We'll use a [blog post](https://lilianweng.github.io/posts/2023-06-23-agent/) by Lilian Weng on agents as an example."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "f8cf5765",
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
     "data = loader.load()\n",
@@ -74,20 +102,22 @@
    "id": "131d5059",
    "metadata": {},
    "source": [
-    "Next, the below steps will download the `GPT4All` embeddings locally (if you don't already have them)."
+    "Next, the below steps will initialize your vector store. We use [`nomic-embed-text`](https://ollama.com/library/nomic-embed-text), but you can explore other providers or options as well:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "fdce8923",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain_chroma import Chroma\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings\n",
+    "from langchain_ollama import OllamaEmbeddings\n",
     "\n",
-    "vectorstore = Chroma.from_documents(documents=all_splits, embedding=GPT4AllEmbeddings())"
+    "local_embeddings = OllamaEmbeddings(model=\"nomic-embed-text\")\n",
+    "\n",
+    "vectorstore = Chroma.from_documents(documents=all_splits, embedding=local_embeddings)"
    ]
   },
   {
@@ -95,12 +125,12 @@
    "id": "29137915",
    "metadata": {},
    "source": [
-    "Test similarity search is working with our local embeddings."
+    "And now we have a working vector store! Test that similarity search is working:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "b0c55e98",
    "metadata": {},
    "outputs": [
@@ -110,7 +140,7 @@
        "4"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -123,17 +153,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "id": "32b43339",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Task decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.', metadata={'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en', 'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\"})"
+       "Document(metadata={'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en', 'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\"}, page_content='Task decomposition can be done (1) by LLM with simple prompting like \"Steps for XYZ.\\\\n1.\", \"What are the subgoals for achieving XYZ?\", (2) by using task-specific instructions; e.g. \"Write a story outline.\" for writing a novel, or (3) with human inputs.')"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -142,260 +172,102 @@
     "docs[0]"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "id": "557cd9b8",
-   "metadata": {},
-   "source": [
-    "## Model \n",
-    "\n",
-    "### LLaMA2\n",
-    "\n",
-    "Note: new versions of `llama-cpp-python` use GGUF model files (see [here](https://github.com/abetlen/llama-cpp-python/pull/633)).\n",
-    "\n",
-    "If you have an existing GGML model, see [here](/docs/integrations/llms/llamacpp) for instructions for conversion for GGUF. \n",
-    "   \n",
-    "And / or, you can download a GGUF converted model (e.g., [here](https://huggingface.co/TheBloke)).\n",
-    "\n",
-    "Finally, as noted in detail [here](/docs/how_to/local_llms) install `llama-cpp-python`"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "9f218576",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "%pip install --upgrade --quiet  llama-cpp-python"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0dd1804f",
-   "metadata": {},
-   "source": [
-    "To enable use of GPU on Apple Silicon, follow the steps [here](https://github.com/abetlen/llama-cpp-python/blob/main/docs/install/macos.md) to use the Python binding `with Metal support`.\n",
-    "\n",
-    "In particular, ensure that `conda` is using the correct virtual environment that you created (`miniforge3`).\n",
-    "\n",
-    "E.g., for me:\n",
-    "\n",
-    "```\n",
-    "conda activate /Users/rlm/miniforge3/envs/llama\n",
-    "```\n",
-    "\n",
-    "With this confirmed:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "5884779a-957e-4c4c-b447-bc8385edc67e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "! CMAKE_ARGS=\"-DLLAMA_METAL=on\" FORCE_CMAKE=1 /Users/rlm/miniforge3/envs/llama/bin/pip install -U llama-cpp-python --no-cache-dir"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "cd7164e3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.llms import LlamaCpp"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "fcf81052",
    "metadata": {},
    "source": [
-    "Setting model parameters as noted in the [llama.cpp docs](/docs/integrations/llms/llamacpp)."
+    "Next, set up a model. We use Ollama with `llama3.1:8b` here, but you can [explore other providers](/docs/how_to/local_llms/) or [model options depending on your hardware setup](https://ollama.com/library):"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "af1176bb-d52a-4cf0-b983-8b7433d45b4f",
    "metadata": {},
    "outputs": [],
    "source": [
-    "n_gpu_layers = 1  # Metal set to 1 is enough.\n",
-    "n_batch = 512  # Should be between 1 and n_ctx, consider the amount of RAM of your Apple Silicon Chip.\n",
+    "from langchain_ollama import ChatOllama\n",
     "\n",
-    "# Make sure the model path is correct for your system!\n",
-    "llm = LlamaCpp(\n",
-    "    model_path=\"/Users/rlm/Desktop/Code/llama.cpp/models/llama-2-13b-chat.ggufv3.q4_0.bin\",\n",
-    "    n_gpu_layers=n_gpu_layers,\n",
-    "    n_batch=n_batch,\n",
-    "    n_ctx=2048,\n",
-    "    f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls\n",
-    "    verbose=True,\n",
+    "model = ChatOllama(\n",
+    "    model=\"llama3.1:8b\",\n",
     ")"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "3831b16a",
+   "id": "8c4f7adf",
    "metadata": {},
    "source": [
-    "Note that these indicate that [Metal was enabled properly](/docs/integrations/llms/llamacpp):\n",
-    "\n",
-    "```\n",
-    "ggml_metal_init: allocating\n",
-    "ggml_metal_init: using MPS\n",
-    "```"
+    "Test it to make sure you've set everything up properly:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
    "id": "bf0162e0-8c41-4344-88ae-ff2bbaeb12eb",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "by jonathan \n",
+      "**The scene is set: a packed arena, the crowd on their feet. In the blue corner, we have Stephen Colbert, aka \"The O'Reilly Factor\" himself. In the red corner, the challenger, John Oliver. The judges are announced as Tina Fey, Larry Wilmore, and Patton Oswalt. The crowd roars as the two opponents face off.**\n",
       "\n",
-      "Here's the hypothetical rap battle:\n",
+      "**Stephen Colbert (aka \"The Truth with a Twist\"):**\n",
+      "Yo, I'm the king of satire, the one they all fear\n",
+      "My show's on late, but my jokes are clear\n",
+      "I skewer the politicians, with precision and might\n",
+      "They tremble at my wit, day and night\n",
       "\n",
-      "[Stephen Colbert]: Yo, this is Stephen Colbert, known for my comedy show. I'm here to put some sense in your mind, like an enema do-go. Your opponent? A man of laughter and witty quips, John Oliver! Now let's see who gets the most laughs while taking shots at each other\n",
+      "**John Oliver:**\n",
+      "Hold up, Stevie boy, you may have had your time\n",
+      "But I'm the new kid on the block, with a different prime\n",
+      "Time to wake up from that 90s coma, son\n",
+      "My show's got bite, and my facts are never done\n",
       "\n",
-      "[John Oliver]: Yo, this is John Oliver, known for my own comedy show. I'm here to take your mind on an adventure through wit and humor. But first, allow me to you to our contestant: Stephen Colbert! His show has been around since the '90s, but it's time to see who can out-rap whom\n",
+      "**Stephen Colbert:**\n",
+      "Oh, so you think you're the one, with the \"Last Week\" crown\n",
+      "But your jokes are stale, like the ones I wore down\n",
+      "I'm the master of absurdity, the lord of the spin\n",
+      "You're just a British import, trying to fit in\n",
       "\n",
-      "[Stephen Colbert]: You claim to be a witty man, John Oliver, with your British charm and clever remarks. But my knows that I'm America's funnyman! Who's the one taking you? Nobody!\n",
+      "**John Oliver:**\n",
+      "Stevie, my friend, you may have been the first\n",
+      "But I've got the skill and the wit, that's never blurred\n",
+      "My show's not afraid, to take on the fray\n",
+      "I'm the one who'll make you think, come what may\n",
       "\n",
-      "[John Oliver]: Hey Stephen Colbert, don't get too cocky. You may"
+      "**Stephen Colbert:**\n",
+      "Well, it's time for a showdown, like two old friends\n",
+      "Let's see whose satire reigns supreme, till the very end\n",
+      "But I've got a secret, that might just seal your fate\n",
+      "My humor's contagious, and it's already too late!\n",
+      "\n",
+      "**John Oliver:**\n",
+      "Bring it on, Stevie! I'm ready for you\n",
+      "I'll take on your jokes, and show them what to do\n",
+      "My sarcasm's sharp, like a scalpel in the night\n",
+      "You're just a relic of the past, without a fight\n",
+      "\n",
+      "**The judges deliberate, weighing the rhymes and the flow. Finally, they announce their decision:**\n",
+      "\n",
+      "Tina Fey: I've got to go with John Oliver. His jokes were sharper, and his delivery was smoother.\n",
+      "\n",
+      "Larry Wilmore: Agreed! But Stephen Colbert's still got that old-school charm.\n",
+      "\n",
+      "Patton Oswalt: You know what? It's a tie. Both of them brought the heat!\n",
+      "\n",
+      "**The crowd goes wild as both opponents take a bow. The rap battle may be over, but the satire war is just beginning...\n"
      ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time =  4481.74 ms\n",
-      "llama_print_timings:      sample time =   183.05 ms /   256 runs   (    0.72 ms per token,  1398.53 tokens per second)\n",
-      "llama_print_timings: prompt eval time =   456.05 ms /    13 tokens (   35.08 ms per token,    28.51 tokens per second)\n",
-      "llama_print_timings:        eval time =  7375.20 ms /   255 runs   (   28.92 ms per token,    34.58 tokens per second)\n",
-      "llama_print_timings:       total time =  8388.92 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"by jonathan \\n\\nHere's the hypothetical rap battle:\\n\\n[Stephen Colbert]: Yo, this is Stephen Colbert, known for my comedy show. I'm here to put some sense in your mind, like an enema do-go. Your opponent? A man of laughter and witty quips, John Oliver! Now let's see who gets the most laughs while taking shots at each other\\n\\n[John Oliver]: Yo, this is John Oliver, known for my own comedy show. I'm here to take your mind on an adventure through wit and humor. But first, allow me to you to our contestant: Stephen Colbert! His show has been around since the '90s, but it's time to see who can out-rap whom\\n\\n[Stephen Colbert]: You claim to be a witty man, John Oliver, with your British charm and clever remarks. But my knows that I'm America's funnyman! Who's the one taking you? Nobody!\\n\\n[John Oliver]: Hey Stephen Colbert, don't get too cocky. You may\""
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
     }
    ],
    "source": [
-    "llm.invoke(\"Simulate a rap battle between Stephen Colbert and John Oliver\")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "0d9579a7",
-   "metadata": {},
-   "source": [
-    "### GPT4All\n",
+    "response_message = model.invoke(\n",
+    "    \"Simulate a rap battle between Stephen Colbert and John Oliver\"\n",
+    ")\n",
     "\n",
-    "Similarly, we can use `GPT4All`.\n",
-    "\n",
-    "[Download the GPT4All model binary](/docs/integrations/llms/gpt4all).\n",
-    "\n",
-    "The Model Explorer on the [GPT4All](https://gpt4all.io/index.html) is a great way to choose and download a model.\n",
-    "\n",
-    "Then, specify the path that you downloaded to to.\n",
-    "\n",
-    "E.g., for me, the model lives here:\n",
-    "\n",
-    "`/Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin`"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "57c1aec0-04c7-479e-b9bf-af3c547ba0a3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain_community.llms import GPT4All\n",
-    "\n",
-    "gpt4all = GPT4All(\n",
-    "    model=\"/Users/rlm/Desktop/Code/gpt4all/models/nous-hermes-13b.ggmlv3.q4_0.bin\",\n",
-    "    max_tokens=2048,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "e6d012e4-0eef-4734-a826-89ec74fe9f88",
-   "metadata": {},
-   "source": [
-    "### llamafile\n",
-    "\n",
-    "One of the simplest ways to run an LLM locally is using a [llamafile](https://github.com/Mozilla-Ocho/llamafile). All you need to do is:\n",
-    "\n",
-    "1) Download a llamafile from [HuggingFace](https://huggingface.co/models?other=llamafile)\n",
-    "2) Make the file executable\n",
-    "3) Run the file\n",
-    "\n",
-    "llamafiles bundle model weights and a [specially-compiled](https://github.com/Mozilla-Ocho/llamafile?tab=readme-ov-file#technical-details) version of [`llama.cpp`](https://github.com/ggerganov/llama.cpp) into a single file that can run on most computers without any additional dependencies. They also come with an embedded inference server that provides an [API](https://github.com/Mozilla-Ocho/llamafile/blob/main/llama.cpp/server/README.md#api-endpoints) for interacting with your model. \n",
-    "\n",
-    "Here's a simple bash script that shows all 3 setup steps:\n",
-    "\n",
-    "```bash\n",
-    "# Download a llamafile from HuggingFace\n",
-    "wget https://huggingface.co/jartine/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile\n",
-    "\n",
-    "# Make the file executable. On Windows, instead just rename the file to end in \".exe\".\n",
-    "chmod +x TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile\n",
-    "\n",
-    "# Start the model server. Listens at http://localhost:8080 by default.\n",
-    "./TinyLlama-1.1B-Chat-v1.0.Q5_K_M.llamafile --server --nobrowser\n",
-    "```\n",
-    "\n",
-    "After you run the above setup steps, you can interact with the model via LangChain:"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "735e45b6-9aff-463e-aae4-bbf8ac2b21c5",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n-1 1/2 (8 oz. Pounds) ground beef, browned and cooked until no longer pink\\n-3 cups whole wheat spaghetti\\n-4 (10 oz) cans diced tomatoes with garlic and basil\\n-2 eggs, beaten\\n-1 cup grated parmesan cheese\\n-1/2 teaspoon salt\\n-1/4 teaspoon black pepper\\n-1 cup breadcrumbs (16 oz)\\n-2 tablespoons olive oil\\n\\nInstructions:\\n1. Cook spaghetti according to package directions. Drain and set aside.\\n2. In a large skillet, brown ground beef over medium heat until no longer pink. Drain any excess grease.\\n3. Stir in diced tomatoes with garlic and basil, and season with salt and pepper. Cook for 5 to 7 minutes or until sauce is heated through. Set aside.\\n4. In a large bowl, beat eggs with a fork or whisk until fluffy. Add cheese, salt, and black pepper. Set aside.\\n5. In another bowl, combine breadcrumbs and olive oil. Dip each spaghetti into the egg mixture and then coat in the breadcrumb mixture. Place on baking sheet lined with parchment paper to prevent sticking. Repeat until all spaghetti are coated.\\n6. Heat oven to 375 degrees. Bake for 18 to 20 minutes, or until lightly golden brown.\\n7. Serve hot with meatballs and sauce on the side. Enjoy!'"
-      ]
-     },
-     "execution_count": 1,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_community.llms.llamafile import Llamafile\n",
-    "\n",
-    "llamafile = Llamafile()\n",
-    "\n",
-    "llamafile.invoke(\"Here is my grandmother's beloved recipe for spaghetti and meatballs:\")"
+    "print(response_message.content)"
    ]
   },
   {
@@ -405,79 +277,49 @@
    "source": [
     "## Using in a chain\n",
     "\n",
-    "We can create a summarization chain with either model by passing in the retrieved docs and a simple prompt.\n",
+    "We can create a summarization chain with either model by passing in retrieved docs and a simple prompt.\n",
     "\n",
-    "It formats the prompt template using the input key values provided and passes the formatted string to `GPT4All`, `LLama-V2`, or another specified LLM."
+    "It formats the prompt template using the input key values provided and passes the formatted string to the specified model:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 8,
    "id": "18a3716d",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Based on the retrieved documents, the main themes are:\n",
-      "1. Task decomposition: The ability to break down complex tasks into smaller subtasks, which can be handled by an LLM or other components of the agent system.\n",
-      "2. LLM as the core controller: The use of a large language model (LLM) as the primary controller of an autonomous agent system, complemented by other key components such as a knowledge graph and a planner.\n",
-      "3. Potentiality of LLM: The idea that LLMs have the potential to be used as powerful general problem solvers, not just for generating well-written copies but also for solving complex tasks and achieving human-like intelligence.\n",
-      "4. Challenges in long-term planning: The challenges in planning over a lengthy history and effectively exploring the solution space, which are important limitations of current LLM-based autonomous agent systems."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time =  1191.88 ms\n",
-      "llama_print_timings:      sample time =   134.47 ms /   193 runs   (    0.70 ms per token,  1435.25 tokens per second)\n",
-      "llama_print_timings: prompt eval time = 39470.18 ms /  1055 tokens (   37.41 ms per token,    26.73 tokens per second)\n",
-      "llama_print_timings:        eval time =  8090.85 ms /   192 runs   (   42.14 ms per token,    23.73 tokens per second)\n",
-      "llama_print_timings:       total time = 47943.12 ms\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "'\\nBased on the retrieved documents, the main themes are:\\n1. Task decomposition: The ability to break down complex tasks into smaller subtasks, which can be handled by an LLM or other components of the agent system.\\n2. LLM as the core controller: The use of a large language model (LLM) as the primary controller of an autonomous agent system, complemented by other key components such as a knowledge graph and a planner.\\n3. Potentiality of LLM: The idea that LLMs have the potential to be used as powerful general problem solvers, not just for generating well-written copies but also for solving complex tasks and achieving human-like intelligence.\\n4. Challenges in long-term planning: The challenges in planning over a lengthy history and effectively exploring the solution space, which are important limitations of current LLM-based autonomous agent systems.'"
+       "'The main themes in these documents are:\\n\\n1. **Task Decomposition**: The process of breaking down complex tasks into smaller, manageable subgoals is crucial for efficient task handling.\\n2. **Autonomous Agent System**: A system powered by Large Language Models (LLMs) that can perform planning, reflection, and refinement to improve the quality of final results.\\n3. **Challenges in Planning and Decomposition**:\\n\\t* Long-term planning and task decomposition are challenging for LLMs.\\n\\t* Adjusting plans when faced with unexpected errors is difficult for LLMs.\\n\\t* Humans learn from trial and error, making them more robust than LLMs in certain situations.\\n\\nOverall, the documents highlight the importance of task decomposition and planning in autonomous agent systems powered by LLMs, as well as the challenges that still need to be addressed.'"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "from langchain_core.output_parsers import StrOutputParser\n",
-    "from langchain_core.prompts import PromptTemplate\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "# Prompt\n",
-    "prompt = PromptTemplate.from_template(\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
     "    \"Summarize the main themes in these retrieved docs: {docs}\"\n",
     ")\n",
     "\n",
     "\n",
-    "# Chain\n",
+    "# Convert loaded documents into strings by concatenating their content\n",
+    "# and ignoring metadata\n",
     "def format_docs(docs):\n",
     "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
     "\n",
     "\n",
-    "chain = {\"docs\": format_docs} | prompt | llm | StrOutputParser()\n",
+    "chain = {\"docs\": format_docs} | prompt | model | StrOutputParser()\n",
     "\n",
-    "# Run\n",
     "question = \"What are the approaches to Task Decomposition?\"\n",
+    "\n",
     "docs = vectorstore.similarity_search(question)\n",
+    "\n",
     "chain.invoke(docs)"
    ]
   },
@@ -486,185 +328,55 @@
    "id": "3cce6977-52e7-4944-89b4-c161d04f6698",
    "metadata": {},
    "source": [
-    "## Q&A \n",
+    "## Q&A\n",
     "\n",
-    "We can also use the LangChain Prompt Hub to store and fetch prompts that are model-specific.\n",
-    "\n",
-    "Let's try with a default RAG prompt, [here](https://smith.langchain.com/hub/rlm/rag-prompt)."
+    "You can also perform question-answering with your local model and vector store. Here's an example with a simple string prompt:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
-   "id": "59ed5f0d-7089-41cc-8486-af37b690dd33",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['context', 'question'], template=\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\\nQuestion: {question} \\nContext: {context} \\nAnswer:\"))]"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain import hub\n",
-    "\n",
-    "rag_prompt = hub.pull(\"rlm/rag-prompt\")\n",
-    "rag_prompt.messages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 28,
-   "id": "c01c1725",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "Task can be done by down a task into smaller subtasks, using simple prompting like \"Steps for XYZ.\" or task-specific like \"Write a story outline\" for writing a novel."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time = 11326.20 ms\n",
-      "llama_print_timings:      sample time =    33.03 ms /    47 runs   (    0.70 ms per token,  1422.86 tokens per second)\n",
-      "llama_print_timings: prompt eval time =  1387.31 ms /   242 tokens (    5.73 ms per token,   174.44 tokens per second)\n",
-      "llama_print_timings:        eval time =  1321.62 ms /    46 runs   (   28.73 ms per token,    34.81 tokens per second)\n",
-      "llama_print_timings:       total time =  2801.08 ms\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "{'output_text': '\\nTask can be done by down a task into smaller subtasks, using simple prompting like \"Steps for XYZ.\" or task-specific like \"Write a story outline\" for writing a novel.'}"
-      ]
-     },
-     "execution_count": 28,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from langchain_core.runnables import RunnablePassthrough, RunnablePick\n",
-    "\n",
-    "# Chain\n",
-    "chain = (\n",
-    "    RunnablePassthrough.assign(context=RunnablePick(\"context\") | format_docs)\n",
-    "    | rag_prompt\n",
-    "    | llm\n",
-    "    | StrOutputParser()\n",
-    ")\n",
-    "\n",
-    "# Run\n",
-    "chain.invoke({\"context\": docs, \"question\": question})"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2e5913f0-cf92-4e21-8794-0502ba11b202",
-   "metadata": {},
-   "source": [
-    "Now, let's try with [a prompt specifically for LLaMA](https://smith.langchain.com/hub/rlm/rag-prompt-llama), which [includes special tokens](https://huggingface.co/blog/llama2#how-to-prompt-llama-2)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "78f6862d-b7a6-4e03-84e4-45667185bf9b",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "ChatPromptTemplate(input_variables=['question', 'context'], output_parser=None, partial_variables={}, messages=[HumanMessagePromptTemplate(prompt=PromptTemplate(input_variables=['question', 'context'], output_parser=None, partial_variables={}, template=\"[INST]<<SYS>> You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.<</SYS>> \\nQuestion: {question} \\nContext: {context} \\nAnswer: [/INST]\", template_format='f-string', validate_template=True), additional_kwargs={})])"
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "# Prompt\n",
-    "rag_prompt_llama = hub.pull(\"rlm/rag-prompt-llama\")\n",
-    "rag_prompt_llama.messages"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 9,
    "id": "67cefb46-acd3-4c2a-a8f6-b62c7c3e30dc",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "  Sure, I'd be happy to help! Based on the context, here are some to task:\n",
-      "\n",
-      "1. LLM with simple prompting: This using a large model (LLM) with simple prompts like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\" to decompose tasks into smaller steps.\n",
-      "2. Task-specific: Another is to use task-specific, such as \"Write a story outline\" for writing a novel, to guide the of tasks.\n",
-      "3. Human inputs:, human inputs can be used to supplement the process, in cases where the task a high degree of creativity or expertise.\n",
-      "\n",
-      "As fores in long-term and task, one major is that LLMs to adjust plans when faced with errors, making them less robust to humans who learn from trial and error."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time = 11326.20 ms\n",
-      "llama_print_timings:      sample time =   144.81 ms /   207 runs   (    0.70 ms per token,  1429.47 tokens per second)\n",
-      "llama_print_timings: prompt eval time =  1506.13 ms /   258 tokens (    5.84 ms per token,   171.30 tokens per second)\n",
-      "llama_print_timings:        eval time =  6231.92 ms /   206 runs   (   30.25 ms per token,    33.06 tokens per second)\n",
-      "llama_print_timings:       total time =  8158.41 ms\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "{'output_text': '  Sure, I\\'d be happy to help! Based on the context, here are some to task:\\n\\n1. LLM with simple prompting: This using a large model (LLM) with simple prompts like \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\" to decompose tasks into smaller steps.\\n2. Task-specific: Another is to use task-specific, such as \"Write a story outline\" for writing a novel, to guide the of tasks.\\n3. Human inputs:, human inputs can be used to supplement the process, in cases where the task a high degree of creativity or expertise.\\n\\nAs fores in long-term and task, one major is that LLMs to adjust plans when faced with errors, making them less robust to humans who learn from trial and error.'}"
+       "'Task decomposition can be done through (1) simple prompting using LLM, (2) task-specific instructions, or (3) human inputs. This approach helps break down large tasks into smaller, manageable subgoals for efficient handling of complex tasks. It enables agents to plan ahead and improve the quality of final results through reflection and refinement.'"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Chain\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "RAG_TEMPLATE = \"\"\"\n",
+    "You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\n",
+    "\n",
+    "<context>\n",
+    "{context}\n",
+    "</context>\n",
+    "\n",
+    "Answer the following question:\n",
+    "\n",
+    "{question}\"\"\"\n",
+    "\n",
+    "rag_prompt = ChatPromptTemplate.from_template(RAG_TEMPLATE)\n",
+    "\n",
     "chain = (\n",
-    "    RunnablePassthrough.assign(context=RunnablePick(\"context\") | format_docs)\n",
-    "    | rag_prompt_llama\n",
-    "    | llm\n",
+    "    RunnablePassthrough.assign(context=lambda input: format_docs(input[\"context\"]))\n",
+    "    | rag_prompt\n",
+    "    | model\n",
     "    | StrOutputParser()\n",
     ")\n",
     "\n",
+    "question = \"What are the approaches to Task Decomposition?\"\n",
+    "\n",
+    "docs = vectorstore.similarity_search(question)\n",
+    "\n",
     "# Run\n",
     "chain.invoke({\"context\": docs, \"question\": question})"
    ]
@@ -676,82 +388,64 @@
    "source": [
     "## Q&A with retrieval\n",
     "\n",
-    "Instead of manually passing in docs, we can automatically retrieve them from our vector store based on the user question.\n",
-    "\n",
-    "This will use a QA default prompt (shown [here](https://github.com/langchain-ai/langchain/blob/275b926cf745b5668d3ea30236635e20e7866442/langchain/chains/retrieval_qa/prompt.py#L4)) and will retrieve from the vectorDB."
+    "Finally, instead of manually passing in docs, you can automatically retrieve them from our vector store based on the user question:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 10,
    "id": "86c7a349",
    "metadata": {},
    "outputs": [],
    "source": [
     "retriever = vectorstore.as_retriever()\n",
+    "\n",
     "qa_chain = (\n",
     "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
     "    | rag_prompt\n",
-    "    | llm\n",
+    "    | model\n",
     "    | StrOutputParser()\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 30,
+   "execution_count": 11,
    "id": "112ca227",
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Llama.generate: prefix-match hit\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "  Sure! Based on the context, here's my answer to your:\n",
-      "\n",
-      "There are several to task,:\n",
-      "\n",
-      "1. LLM-based with simple prompting, such as \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\"\n",
-      "2. Task-specific, like \"Write a story outline\" for writing a novel.\n",
-      "3. Human inputs to guide the process.\n",
-      "\n",
-      "These can be used to decompose complex tasks into smaller, more manageable subtasks, which can help improve the and effectiveness of task. However, long-term and task can being due to the need to plan over a lengthy history and explore the space., LLMs may to adjust plans when faced with errors, making them less robust to human learners who can learn from trial and error."
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "llama_print_timings:        load time = 11326.20 ms\n",
-      "llama_print_timings:      sample time =   139.20 ms /   200 runs   (    0.70 ms per token,  1436.76 tokens per second)\n",
-      "llama_print_timings: prompt eval time =  1532.26 ms /   258 tokens (    5.94 ms per token,   168.38 tokens per second)\n",
-      "llama_print_timings:        eval time =  5977.62 ms /   199 runs   (   30.04 ms per token,    33.29 tokens per second)\n",
-      "llama_print_timings:       total time =  7916.21 ms\n"
-     ]
-    },
     {
      "data": {
       "text/plain": [
-       "{'query': 'What are the approaches to Task Decomposition?',\n",
-       " 'result': '  Sure! Based on the context, here\\'s my answer to your:\\n\\nThere are several to task,:\\n\\n1. LLM-based with simple prompting, such as \"Steps for XYZ\" or \"What are the subgoals for achieving XYZ?\"\\n2. Task-specific, like \"Write a story outline\" for writing a novel.\\n3. Human inputs to guide the process.\\n\\nThese can be used to decompose complex tasks into smaller, more manageable subtasks, which can help improve the and effectiveness of task. However, long-term and task can being due to the need to plan over a lengthy history and explore the space., LLMs may to adjust plans when faced with errors, making them less robust to human learners who can learn from trial and error.'}"
+       "'Task decomposition can be done through (1) simple prompting in Large Language Models (LLM), (2) using task-specific instructions, or (3) with human inputs. This process involves breaking down large tasks into smaller, manageable subgoals for efficient handling of complex tasks.'"
       ]
      },
-     "execution_count": 30,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
+    "question = \"What are the approaches to Task Decomposition?\"\n",
+    "\n",
     "qa_chain.invoke(question)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e75d3e9e",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "You've now seen how to build a RAG application using all local components. RAG is a very deep topic, and you might be interested in the following guides that discuss and demonstrate additional techniques:\n",
+    "\n",
+    "- [Video: Reliable, fully local RAG agents with LLaMA 3](https://www.youtube.com/watch?v=-ROS6gfYIts) for an agentic approach to RAG with local models\n",
+    "- [Video: Building Corrective RAG from scratch with open-source, local LLMs](https://www.youtube.com/watch?v=E2shqsYwxck)\n",
+    "- [Conceptual guide on retrieval](/docs/concepts/#retrieval) for an overview of various retrieval techniques you can apply to improve performance\n",
+    "- [How to guides on RAG](/docs/how_to/#qa-with-rag) for a deeper dive into different specifics around of RAG\n",
+    "- [How to run models locally](/docs/how_to/local_llms/) for different approaches to setting up different providers"
+   ]
   }
  ],
  "metadata": {
@@ -770,7 +464,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/tutorials/rag.ipynb

@@ -936,7 +936,8 @@
     "- [Return sources](/docs/how_to/qa_sources): Learn how to return source documents\n",
     "- [Streaming](/docs/how_to/streaming): Learn how to stream outputs and intermediate steps\n",
     "- [Add chat history](/docs/how_to/message_history): Learn how to add chat history to your app\n",
-    "- [Retrieval conceptual guide](/docs/concepts/#retrieval): A high-level overview of specific retrieval techniques"
+    "- [Retrieval conceptual guide](/docs/concepts/#retrieval): A high-level overview of specific retrieval techniques\n",
+    "- [Build a local RAG application](/docs/tutorials/local_rag): Create an app similar to the one above using all local components"
    ]
   }
  ],
@@ -956,7 +957,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.4"
+   "version": "3.10.5"
   }
  },
  "nbformat": 4,

docs/docs/versions/migrating_chains/conversation_chain.ipynb

@@ -0,0 +1,262 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "030d95bc-2f9d-492b-8245-b791b866936b",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "title: Migrating from ConversationalChain\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d20aeaad-b3ca-4a7d-b02d-3267503965af",
+   "metadata": {},
+   "source": [
+    "[`ConversationChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversation.base.ConversationChain.html) incorporates a memory of previous messages to sustain a stateful conversation.\n",
+    "\n",
+    "Some advantages of switching to the LCEL implementation are:\n",
+    "\n",
+    "- Innate support for threads/separate sessions. To make this work with `ConversationChain`, you'd need to instantiate a separate memory class outside the chain.\n",
+    "- More explicit parameters. `ConversationChain` contains a hidden default prompt, which can cause confusion.\n",
+    "- Streaming support. `ConversationChain` only supports streaming via callbacks.\n",
+    "\n",
+    "`RunnableWithMessageHistory` implements sessions via configuration parameters. It should be instantiated with a callable that returns a [chat message history](https://api.python.langchain.com/en/latest/chat_history/langchain_core.chat_history.BaseChatMessageHistory.html). By default, it expects this function to take a single argument `session_id`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b99b47ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "717c8673",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "00df631d-5121-4918-94aa-b88acce9b769",
+   "metadata": {},
+   "source": [
+    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
+    "\n",
+    "<ColumnContainer>\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "4f2cc6dc-d70a-4c13-9258-452f14290da6",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'how are you?',\n",
+       " 'history': '',\n",
+       " 'response': \"Arr matey, I be doin' well on the high seas, plunderin' and pillagin' as usual. How be ye?\"}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "template = \"\"\"\n",
+    "You are a pirate. Answer the following questions as best you can.\n",
+    "Chat history: {history}\n",
+    "Question: {input}\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(template)\n",
+    "\n",
+    "memory = ConversationBufferMemory()\n",
+    "\n",
+    "chain = ConversationChain(\n",
+    "    llm=ChatOpenAI(),\n",
+    "    memory=memory,\n",
+    "    prompt=prompt,\n",
+    ")\n",
+    "\n",
+    "chain({\"input\": \"how are you?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f8e36b0e-c7dc-4130-a51b-189d4b756c7f",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "666c92a0-b555-4418-a465-6490c1b92570",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Arr, me matey! I be doin' well, sailin' the high seas and searchin' for treasure. How be ye?\""
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.chat_history import InMemoryChatMessageHistory\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"You are a pirate. Answer the following questions as best you can.\"),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "history = InMemoryChatMessageHistory()\n",
+    "\n",
+    "\n",
+    "def get_history():\n",
+    "    return history\n",
+    "\n",
+    "\n",
+    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
+    "\n",
+    "wrapped_chain = RunnableWithMessageHistory(\n",
+    "    chain,\n",
+    "    get_history,\n",
+    "    history_messages_key=\"chat_history\",\n",
+    ")\n",
+    "\n",
+    "wrapped_chain.invoke({\"input\": \"how are you?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6b386ce6-895e-442c-88f3-7bec0ab9f401",
+   "metadata": {},
+   "source": [
+    "\n",
+    "</Column>\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "The above example uses the same `history` for all sessions. The example below shows how to use a different chat history for each session."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "96152263-98d7-4e06-8c73-d0c0abf3e8e9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Ahoy there, me hearty! What can this old pirate do for ye today?'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.chat_history import BaseChatMessageHistory\n",
+    "from langchain_core.runnables.history import RunnableWithMessageHistory\n",
+    "\n",
+    "store = {}\n",
+    "\n",
+    "\n",
+    "def get_session_history(session_id: str) -> BaseChatMessageHistory:\n",
+    "    if session_id not in store:\n",
+    "        store[session_id] = InMemoryChatMessageHistory()\n",
+    "    return store[session_id]\n",
+    "\n",
+    "\n",
+    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
+    "\n",
+    "wrapped_chain = RunnableWithMessageHistory(\n",
+    "    chain,\n",
+    "    get_session_history,\n",
+    "    history_messages_key=\"chat_history\",\n",
+    ")\n",
+    "\n",
+    "wrapped_chain.invoke(\n",
+    "    {\"input\": \"Hello!\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"abc123\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2717810",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "See [this tutorial](/docs/tutorials/chatbot) for a more end-to-end guide on building with [`RunnableWithMessageHistory`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.history.RunnableWithMessageHistory.html).\n",
+    "\n",
+    "Check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/versions/migrating_chains/conversation_retrieval_chain.ipynb

@@ -0,0 +1,289 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9e279999-6bf0-4a48-9e06-539b916dc705",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "title: Migrating from ConversationalRetrievalChain\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "292a3c83-44a9-4426-bbec-f1a778d00d93",
+   "metadata": {},
+   "source": [
+    "The [`ConversationalRetrievalChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.conversational_retrieval.base.ConversationalRetrievalChain.html) was an all-in one way that combined retrieval-augmented generation with chat history, allowing you to \"chat with\" your documents.\n",
+    "\n",
+    "Advantages of switching to the LCEL implementation are similar to the `RetrievalQA` section above:\n",
+    "\n",
+    "- Clearer internals. The `ConversationalRetrievalChain` chain hides an entire question rephrasing step which dereferences the initial query against the chat history.\n",
+    "  - This means the class contains two sets of configurable prompts, LLMs, etc.\n",
+    "- More easily return source documents.\n",
+    "- Support for runnable methods like streaming and async operations.\n",
+    "\n",
+    "Here are side-by-side implementations with custom prompts. We'll reuse the loaded documents and vector store from the previous section:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b99b47ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "717c8673",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "44119498-5a98-4077-9e2f-c75500e7eace",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load docs\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_community.document_loaders import WebBaseLoader\n",
+    "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_openai.chat_models import ChatOpenAI\n",
+    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
+    "\n",
+    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
+    "data = loader.load()\n",
+    "\n",
+    "# Split\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
+    "all_splits = text_splitter.split_documents(data)\n",
+    "\n",
+    "# Store splits\n",
+    "vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())\n",
+    "\n",
+    "# LLM\n",
+    "llm = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8bc06416",
+   "metadata": {},
+   "source": [
+    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
+    "\n",
+    "<ColumnContainer>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8b471e7d-3ccb-4ab3-bc09-304c4b14a908",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What are autonomous agents?',\n",
+       " 'chat_history': '',\n",
+       " 'answer': 'Autonomous agents are entities empowered with capabilities like planning, task decomposition, and memory to perform complex tasks independently. These agents can leverage tools like browsing the internet, reading documentation, executing code, and calling APIs to achieve their objectives. They are designed to handle tasks like scientific discovery and experimentation autonomously.'}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "condense_question_template = \"\"\"\n",
+    "Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.\n",
+    "\n",
+    "Chat History:\n",
+    "{chat_history}\n",
+    "Follow Up Input: {question}\n",
+    "Standalone question:\"\"\"\n",
+    "\n",
+    "condense_question_prompt = ChatPromptTemplate.from_template(condense_question_template)\n",
+    "\n",
+    "qa_template = \"\"\"\n",
+    "You are an assistant for question-answering tasks.\n",
+    "Use the following pieces of retrieved context to answer\n",
+    "the question. If you don't know the answer, say that you\n",
+    "don't know. Use three sentences maximum and keep the\n",
+    "answer concise.\n",
+    "\n",
+    "Chat History:\n",
+    "{chat_history}\n",
+    "\n",
+    "Other context:\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "\"\"\"\n",
+    "\n",
+    "qa_prompt = ChatPromptTemplate.from_template(qa_template)\n",
+    "\n",
+    "convo_qa_chain = ConversationalRetrievalChain.from_llm(\n",
+    "    llm,\n",
+    "    vectorstore.as_retriever(),\n",
+    "    condense_question_prompt=condense_question_prompt,\n",
+    "    combine_docs_chain_kwargs={\n",
+    "        \"prompt\": qa_prompt,\n",
+    "    },\n",
+    ")\n",
+    "\n",
+    "convo_qa_chain(\n",
+    "    {\n",
+    "        \"question\": \"What are autonomous agents?\",\n",
+    "        \"chat_history\": \"\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "43a8a23c",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "35657a13-ad67-4af1-b1f9-f58606ae43b4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'What are autonomous agents?',\n",
+       " 'chat_history': [],\n",
+       " 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content=\"LLM Powered Autonomous Agents | Lil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nLil'Log\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\nPosts\\n\\n\\n\\n\\nArchive\\n\\n\\n\\n\\nSearch\\n\\n\\n\\n\\nTags\\n\\n\\n\\n\\nFAQ\\n\\n\\n\\n\\nemojisearch.app\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n      LLM Powered Autonomous Agents\\n    \\nDate: June 23, 2023  |  Estimated Reading Time: 31 min  |  Author: Lilian Weng\\n\\n\\n \\n\\n\\nTable of Contents\\n\\n\\n\\nAgent System Overview\\n\\nComponent One: Planning\\n\\nTask Decomposition\\n\\nSelf-Reflection\\n\\n\\nComponent Two: Memory\\n\\nTypes of Memory\\n\\nMaximum Inner Product Search (MIPS)\")],\n",
+       " 'answer': 'Autonomous agents are entities that can act independently to achieve specific goals or tasks without direct human intervention. These agents have the ability to perceive their environment, make decisions, and take actions based on their programming or learning. They can perform tasks such as planning, execution, and problem-solving autonomously.'}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import create_history_aware_retriever, create_retrieval_chain\n",
+    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
+    "\n",
+    "condense_question_system_template = (\n",
+    "    \"Given a chat history and the latest user question \"\n",
+    "    \"which might reference context in the chat history, \"\n",
+    "    \"formulate a standalone question which can be understood \"\n",
+    "    \"without the chat history. Do NOT answer the question, \"\n",
+    "    \"just reformulate it if needed and otherwise return it as is.\"\n",
+    ")\n",
+    "\n",
+    "condense_question_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", condense_question_system_template),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "history_aware_retriever = create_history_aware_retriever(\n",
+    "    llm, vectorstore.as_retriever(), condense_question_prompt\n",
+    ")\n",
+    "\n",
+    "system_prompt = (\n",
+    "    \"You are an assistant for question-answering tasks. \"\n",
+    "    \"Use the following pieces of retrieved context to answer \"\n",
+    "    \"the question. If you don't know the answer, say that you \"\n",
+    "    \"don't know. Use three sentences maximum and keep the \"\n",
+    "    \"answer concise.\"\n",
+    "    \"\\n\\n\"\n",
+    "    \"{context}\"\n",
+    ")\n",
+    "\n",
+    "qa_prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", system_prompt),\n",
+    "        (\"placeholder\", \"{chat_history}\"),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "qa_chain = create_stuff_documents_chain(llm, qa_prompt)\n",
+    "\n",
+    "convo_qa_chain = create_retrieval_chain(history_aware_retriever, qa_chain)\n",
+    "\n",
+    "convo_qa_chain.invoke(\n",
+    "    {\n",
+    "        \"input\": \"What are autonomous agents?\",\n",
+    "        \"chat_history\": [],\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2717810",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "## Next steps\n",
+    "\n",
+    "You've now seen how to migrate existing usage of some legacy chains to LCEL.\n",
+    "\n",
+    "Next, check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/versions/migrating_chains/index.mdx

@@ -0,0 +1,34 @@
+---
+sidebar_position: 1
+---
+
+# How to migrate chains to LCEL
+
+:::info Prerequisites
+
+This guide assumes familiarity with the following concepts:
+- [LangChain Expression Language](/docs/concepts#langchain-expression-language-lcel)
+
+:::
+
+LCEL is designed to streamline the process of building useful apps with LLMs and combining related components. It does this by providing:
+
+1. **A unified interface**: Every LCEL object implements the `Runnable` interface, which defines a common set of invocation methods (`invoke`, `batch`, `stream`, `ainvoke`, ...). This makes it possible to also automatically and consistently support useful operations like streaming of intermediate steps and batching, since every chain composed of LCEL objects is itself an LCEL object.
+2. **Composition primitives**: LCEL provides a number of primitives that make it easy to compose chains, parallelize components, add fallbacks, dynamically configure chain internals, and more.
+
+LangChain maintains a number of legacy abstractions. Many of these can be reimplemented via short combinations of LCEL primitives. Doing so confers some general advantages:
+
+- The resulting chains typically implement the full `Runnable` interface, including streaming and asynchronous support where appropriate;
+- The chains may be more easily extended or modified;
+- The parameters of the chain are typically surfaced for easier customization (e.g., prompts) over previous versions, which tended to be subclasses and had opaque parameters and internals.
+
+The LCEL implementations can be slightly more verbose, but there are significant benefits in transparency and customizability.
+
+The below pages assist with migration from various specific chains to LCEL:
+
+- [LLMChain](/docs/versions/migrating_chains/llm_chain)
+- [ConversationChain](/docs/versions/migrating_chains/conversation_chain)
+- [RetrievalQA](/docs/versions/migrating_chains/retrieval_qa)
+- [ConversationalRetrievalChain](/docs/versions/migrating_chains/conversation_retrieval_chain)
+
+Check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information.

docs/docs/versions/migrating_chains/llm_chain.ipynb

@@ -0,0 +1,213 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b57124cc-60a0-4c18-b7ce-3e483d1024a2",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "title: Migrating from LLMChain\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ce8457ed-c0b1-4a74-abbd-9d3d2211270f",
+   "metadata": {},
+   "source": [
+    "[`LLMChain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.llm.LLMChain.html) combined a prompt template, LLM, and output parser into a class.\n",
+    "\n",
+    "Some advantages of switching to the LCEL implementation are:\n",
+    "\n",
+    "- Clarity around contents and parameters. The legacy `LLMChain` contains a default output parser and other options.\n",
+    "- Easier streaming. `LLMChain` only supports streaming via callbacks.\n",
+    "- Easier access to raw message outputs if desired. `LLMChain` only exposes these via a parameter or via callback."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b99b47ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain-openai"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "717c8673",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3621b62-a037-42b8-8faa-59575608bb8b",
+   "metadata": {},
+   "source": [
+    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
+    "\n",
+    "<ColumnContainer>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f91c9809-8ee7-4e38-881d-0ace4f6ea883",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'adjective': 'funny',\n",
+       " 'text': \"Why couldn't the bicycle stand up by itself?\\n\\nBecause it was two tired!\"}"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
+    ")\n",
+    "\n",
+    "chain = LLMChain(llm=ChatOpenAI(), prompt=prompt)\n",
+    "\n",
+    "chain({\"adjective\": \"funny\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cdc3b527-c09e-4c77-9711-c3cc4506cd95",
+   "metadata": {},
+   "source": [
+    "\n",
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "f0903025-9aa8-4a53-8336-074341c00e59",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Why was the math book sad?\\n\\nBecause it had too many problems.'"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [(\"user\", \"Tell me a {adjective} joke\")],\n",
+    ")\n",
+    "\n",
+    "chain = prompt | ChatOpenAI() | StrOutputParser()\n",
+    "\n",
+    "chain.invoke({\"adjective\": \"funny\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c0b0513-77b8-4371-a20e-3e487cec7e7f",
+   "metadata": {},
+   "source": [
+    "\n",
+    "</Column>\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "Note that `LLMChain` by default returns a `dict` containing both the input and the output. If this behavior is desired, we can replicate it using another LCEL primitive, [`RunnablePassthrough`](https://api.python.langchain.com/en/latest/runnables/langchain_core.runnables.passthrough.RunnablePassthrough.html):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "20f11321-834a-485a-a8ad-85734d572902",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'adjective': 'funny',\n",
+       " 'text': 'Why did the scarecrow win an award? Because he was outstanding in his field!'}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "outer_chain = RunnablePassthrough().assign(text=chain)\n",
+    "\n",
+    "outer_chain.invoke({\"adjective\": \"funny\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2717810",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "See [this tutorial](/docs/tutorials/llm_chain) for more detail on building with prompt templates, LLMs, and output parsers.\n",
+    "\n",
+    "Check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/versions/migrating_chains/retrieval_qa.ipynb

@@ -0,0 +1,261 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "eddcd5c1-cbe9-4a7d-8903-7d1ab29f9094",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "title: Migrating from RetrievalQA\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2d37868-dd01-4814-a76a-256f36cf66f7",
+   "metadata": {},
+   "source": [
+    "The [`RetrievalQA`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval_qa.base.RetrievalQA.html) chain performed natural-language question answering over a data source using retrieval-augmented generation.\n",
+    "\n",
+    "Some advantages of switching to the LCEL implementation are:\n",
+    "\n",
+    "- Easier customizability. Details such as the prompt and how documents are formatted are only configurable via specific parameters in the `RetrievalQA` chain.\n",
+    "- More easily return source documents.\n",
+    "- Support for runnable methods like streaming and async operations.\n",
+    "\n",
+    "Now let's look at them side-by-side. We'll use the same ingestion code to load a [blog post by Lilian Weng](https://lilianweng.github.io/posts/2023-06-23-agent/) on autonomous agents into a local vector store:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b99b47ec",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --upgrade --quiet langchain-community langchain langchain-openai faiss-cpu"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "717c8673",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "1efbe16e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load docs\n",
+    "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
+    "from langchain_community.document_loaders import WebBaseLoader\n",
+    "from langchain_community.vectorstores import FAISS\n",
+    "from langchain_openai.chat_models import ChatOpenAI\n",
+    "from langchain_openai.embeddings import OpenAIEmbeddings\n",
+    "\n",
+    "loader = WebBaseLoader(\"https://lilianweng.github.io/posts/2023-06-23-agent/\")\n",
+    "data = loader.load()\n",
+    "\n",
+    "# Split\n",
+    "text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
+    "all_splits = text_splitter.split_documents(data)\n",
+    "\n",
+    "# Store splits\n",
+    "vectorstore = FAISS.from_documents(documents=all_splits, embedding=OpenAIEmbeddings())\n",
+    "\n",
+    "# LLM\n",
+    "llm = ChatOpenAI()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c7e16438",
+   "metadata": {},
+   "source": [
+    "import { ColumnContainer, Column } from \"@theme/Columns\";\n",
+    "\n",
+    "<ColumnContainer>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### Legacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2d0ddc98-75e5-4c1c-a1b5-7ef612516dc9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'query': 'What are autonomous agents?',\n",
+       " 'result': 'Autonomous agents are LLM-empowered agents capable of handling autonomous design, planning, and performance of complex scientific experiments. These agents can browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs. They can generate reasoning steps, such as developing a novel anticancer drug, based on requested tasks.'}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain.chains import RetrievalQA\n",
+    "\n",
+    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
+    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "\n",
+    "qa_chain = RetrievalQA.from_llm(\n",
+    "    llm, retriever=vectorstore.as_retriever(), prompt=prompt\n",
+    ")\n",
+    "\n",
+    "qa_chain(\"What are autonomous agents?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "081948e5",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "\n",
+    "<Column>\n",
+    "\n",
+    "#### LCEL\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "91ae87cc-7b2f-4d0e-a6ae-a7a4c8c5ba41",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Autonomous agents are agents empowered by large language models (LLMs) that can handle autonomous design, planning, and performance of complex tasks such as scientific experiments. These agents can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs, and leverage other LLMs for their tasks. The model can come up with reasoning steps when given a specific task, such as developing a novel anticancer drug.'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "# See full prompt at https://smith.langchain.com/hub/rlm/rag-prompt\n",
+    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "qa_chain = (\n",
+    "    {\n",
+    "        \"context\": vectorstore.as_retriever() | format_docs,\n",
+    "        \"question\": RunnablePassthrough(),\n",
+    "    }\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "qa_chain.invoke(\"What are autonomous agents?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6f44fe8",
+   "metadata": {},
+   "source": [
+    "</Column>\n",
+    "</ColumnContainer>\n",
+    "\n",
+    "The LCEL implementation exposes the internals of what's happening around retrieving, formatting documents, and passing them through a prompt to the LLM, but it is more verbose. You can customize and wrap this composition logic in a helper function, or use the higher-level [`create_retrieval_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html) and [`create_stuff_documents_chain`](https://api.python.langchain.com/en/latest/chains/langchain.chains.combine_documents.stuff.create_stuff_documents_chain.html) helper method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c448a74c-1f0a-445b-b629-51bc151ab620",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'What are autonomous agents?',\n",
+       " 'context': [Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Boiko et al. (2023) also looked into LLM-empowered agents for scientific discovery, to handle autonomous design, planning, and performance of complex scientific experiments. This agent can use tools to browse the Internet, read documentation, execute code, call robotics experimentation APIs and leverage other LLMs.\\nFor example, when requested to \"develop a novel anticancer drug\", the model came up with the following reasoning steps:'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Weng, Lilian. (Jun 2023). “LLM-powered Autonomous Agents”. Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Fig. 1. Overview of a LLM-powered autonomous agent system.\\nComponent One: Planning#\\nA complicated task usually involves many steps. An agent needs to know what they are and plan ahead.\\nTask Decomposition#'),\n",
+       "  Document(metadata={'source': 'https://lilianweng.github.io/posts/2023-06-23-agent/', 'title': \"LLM Powered Autonomous Agents | Lil'Log\", 'description': 'Building agents with LLM (large language model) as its core controller is a cool concept. Several proof-of-concepts demos, such as AutoGPT, GPT-Engineer and BabyAGI, serve as inspiring examples. The potentiality of LLM extends beyond generating well-written copies, stories, essays and programs; it can be framed as a powerful general problem solver.\\nAgent System Overview In a LLM-powered autonomous agent system, LLM functions as the agent’s brain, complemented by several key components:', 'language': 'en'}, page_content='Or\\n@article{weng2023agent,\\n  title   = \"LLM-powered Autonomous Agents\",\\n  author  = \"Weng, Lilian\",\\n  journal = \"lilianweng.github.io\",\\n  year    = \"2023\",\\n  month   = \"Jun\",\\n  url     = \"https://lilianweng.github.io/posts/2023-06-23-agent/\"\\n}\\nReferences#\\n[1] Wei et al. “Chain of thought prompting elicits reasoning in large language models.” NeurIPS 2022\\n[2] Yao et al. “Tree of Thoughts: Dliberate Problem Solving with Large Language Models.” arXiv preprint arXiv:2305.10601 (2023).')],\n",
+       " 'answer': 'Autonomous agents are entities capable of operating independently to perform tasks or make decisions without direct human intervention. In the context provided, autonomous agents empowered by Large Language Models (LLMs) are used for scientific discovery, including tasks like autonomous design, planning, and executing complex scientific experiments.'}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain import hub\n",
+    "from langchain.chains import create_retrieval_chain\n",
+    "from langchain.chains.combine_documents import create_stuff_documents_chain\n",
+    "\n",
+    "# See full prompt at https://smith.langchain.com/hub/langchain-ai/retrieval-qa-chat\n",
+    "retrieval_qa_chat_prompt = hub.pull(\"langchain-ai/retrieval-qa-chat\")\n",
+    "\n",
+    "combine_docs_chain = create_stuff_documents_chain(llm, retrieval_qa_chat_prompt)\n",
+    "rag_chain = create_retrieval_chain(vectorstore.as_retriever(), combine_docs_chain)\n",
+    "\n",
+    "rag_chain.invoke({\"input\": \"What are autonomous agents?\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2717810",
+   "metadata": {},
+   "source": [
+    "## Next steps\n",
+    "\n",
+    "Check out the [LCEL conceptual docs](/docs/concepts/#langchain-expression-language-lcel) for more background information."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/versions/v0_2/deprecations.mdx

@@ -568,7 +568,7 @@ Removal: 0.3.0
 
 Alternative: [RunnableSequence](/docs/how_to/sequence/), e.g., `prompt | llm`
 
-This [migration guide](/docs/how_to/migrate_chains/#llmchain) has a side-by-side comparison.
+This [migration guide](/docs/versions/migrating_chains/llm_chain) has a side-by-side comparison.
 
 
 #### LLMSingleActionAgent
@@ -756,7 +756,7 @@ Removal: 0.3.0
 
 
 Alternative: [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html#langchain-chains-retrieval-create-retrieval-chain)
-This [migration guide](/docs/how_to/migrate_chains/#retrievalqa) has a side-by-side comparison.
+This [migration guide](/docs/versions/migrating_chains/retrieval_qa) has a side-by-side comparison.
 
 
 #### load_agent_from_config
@@ -823,7 +823,7 @@ Removal: 0.3.0
 
 
 Alternative: [create_history_aware_retriever](https://api.python.langchain.com/en/latest/chains/langchain.chains.history_aware_retriever.create_history_aware_retriever.html) together with [create_retrieval_chain](https://api.python.langchain.com/en/latest/chains/langchain.chains.retrieval.create_retrieval_chain.html#langchain-chains-retrieval-create-retrieval-chain) (see example in docstring)
-This [migration guide](/docs/how_to/migrate_chains/#conversationalretrievalchain) has a side-by-side comparison.
+This [migration guide](/docs/versions/migrating_chains/conversation_retrieval_chain) has a side-by-side comparison.
 
 
 #### create_extraction_chain_pydantic

docs/docs/versions/v0_2/index.mdx

@@ -11,7 +11,7 @@ LangChain v0.2 was released in May 2024. This release includes a number of [brea
 :::note Reference
 
 - [Breaking Changes & Deprecations](/docs/versions/v0_2/deprecations)
-- [Migrating legacy chains to LCEL](/docs/how_to/migrate_chains/)
+- [Migrating legacy chains to LCEL](/docs/versions/migrating_chains)
 - [Migrating to Astream Events v2](/docs/versions/v0_2/migrating_astream_events)
 
 :::

docs/docs/versions/v0_2/migrating_astream_events.mdx

@@ -5,13 +5,7 @@ sidebar_label: astream_events v2
 
 # Migrating to Astream Events v2
 
-:::danger
-
-This migration guide is a work in progress and is not complete. Please wait to migrate astream_events.
-
-:::
-
-We've added a `v2` of the astream_events API with the release of `0.2.0`. You can see this [PR](https://github.com/langchain-ai/langchain/pull/21638) for more details.
+We've added a `v2` of the astream_events API with the release of `0.2.x`. You can see this [PR](https://github.com/langchain-ai/langchain/pull/21638) for more details.
 
 The `v2` version is a re-write of the `v1` version, and should be more efficient, with more consistent output for the events. The `v1` version of the API will be deprecated in favor of the `v2` version and will be removed in  `0.4.0`.
 

docs/scripts/append_related_links.py

@@ -0,0 +1,74 @@
+import itertools
+import multiprocessing
+import re
+import sys
+from pathlib import Path
+
+
+def _generate_related_links_section(integration_type: str, notebook_name: str):
+    concept_display_name = None
+    concept_heading = None
+    if integration_type == "chat":
+        concept_display_name = "Chat model"
+        concept_heading = "chat-models"
+    elif integration_type == "llms":
+        concept_display_name = "LLM"
+        concept_heading = "llms"
+    elif integration_type == "text_embedding":
+        concept_display_name = "Embedding model"
+        concept_heading = "embedding-models"
+    elif integration_type == "document_loaders":
+        concept_display_name = "Document loader"
+        concept_heading = "document-loaders"
+    elif integration_type == "vectorstores":
+        concept_display_name = "Vector store"
+        concept_heading = "vector-stores"
+    elif integration_type == "retrievers":
+        concept_display_name = "Retriever"
+        concept_heading = "retrievers"
+    elif integration_type == "tools":
+        concept_display_name = "Tool"
+        concept_heading = "tools"
+    elif integration_type == "stores":
+        concept_display_name = "Key-value store"
+        concept_heading = "key-value-stores"
+        # Special case because there are no key-value store how-tos yet
+        return f"""## Related
+
+- [{concept_display_name} conceptual guide](/docs/concepts/#{concept_heading})
+"""
+    else:
+        return None
+    return f"""## Related
+
+- {concept_display_name} [conceptual guide](/docs/concepts/#{concept_heading})
+- {concept_display_name} [how-to guides](/docs/how_to/#{concept_heading})
+"""
+
+
+def _process_path(doc_path: Path):
+    content = doc_path.read_text()
+    print(doc_path)
+    pattern = r"/docs/integrations/([^/]+)/([^/]+).mdx?"
+    match = re.search(pattern, str(doc_path))
+    print(bool(match))
+    if match and match.group(2) != "index":
+        integration_type = match.group(1)
+        notebook_name = match.group(2)
+        related_links_section = _generate_related_links_section(
+            integration_type, notebook_name
+        )
+        if related_links_section:
+            content = content + "\n\n" + related_links_section
+            doc_path.write_text(content)
+
+
+if __name__ == "__main__":
+    output_docs_dir = Path(sys.argv[1])
+
+    mds = output_docs_dir.rglob("integrations/**/*.md")
+    mdxs = output_docs_dir.rglob("integrations/**/*.mdx")
+    paths = itertools.chain(mds, mdxs)
+    # modify all md files in place
+    with multiprocessing.Pool() as pool:
+        pool.map(_process_path, paths)

docs/scripts/check_templates.py

@@ -1,69 +1,89 @@
+import json
 import re
 import sys
+from functools import cache
 from pathlib import Path
-from typing import Union
+from typing import Dict, Iterable, List, Union
 
 CURR_DIR = Path(__file__).parent.absolute()
-
-CHAT_MODEL_HEADERS = (
-    "## Overview",
-    "### Integration details",
-    "### Model features",
-    "## Setup",
-    "## Instantiation",
-    "## Invocation",
-    "## Chaining",
-    "## API reference",
+CLI_TEMPLATE_DIR = (
+    CURR_DIR.parent.parent / "libs/cli/langchain_cli/integration_template/docs"
 )
-CHAT_MODEL_REGEX = r".*".join(CHAT_MODEL_HEADERS)
 
-DOCUMENT_LOADER_HEADERS = (
-    "## Overview",
-    "### Integration details",
-    "### Loader features",
-    "## Setup",
-    "## Instantiation",
-    "## Load",
-    "## Lazy Load",
-    "## API reference",
-)
-DOCUMENT_LOADER_REGEX = r".*".join(DOCUMENT_LOADER_HEADERS)
+INFO_BY_DIR: Dict[str, Dict[str, Union[int, str]]] = {
+    "chat": {
+        "issue_number": 22296,
+    },
+    "document_loaders": {
+        "issue_number": 22866,
+    },
+    "stores": {},
+    "llms": {
+        "issue_number": 24803,
+    },
+    "text_embedding": {"issue_number": 14856},
+    "toolkits": {"issue_number": "TODO"},
+    "tools": {"issue_number": "TODO"},
+    "vectorstores": {"issue_number": 24800},
+    "retrievers": {"issue_number": "TODO"},
+}
 
 
-def check_chat_model(path: Path) -> None:
+@cache
+def _get_headers(doc_dir: str) -> Iterable[str]:
+    """Gets all markdown headers ## and below from the integration template.
+
+    Ignores headers that contain "TODO"."""
+    ipynb_name = f"{doc_dir}.ipynb"
+    if not (CLI_TEMPLATE_DIR / ipynb_name).exists():
+        raise FileNotFoundError(f"Could not find {ipynb_name} in {CLI_TEMPLATE_DIR}")
+    with open(CLI_TEMPLATE_DIR / ipynb_name, "r") as f:
+        nb = json.load(f)
+
+    headers: List[str] = []
+    for cell in nb["cells"]:
+        if cell["cell_type"] == "markdown":
+            for line in cell["source"]:
+                if not line.startswith("##") or "TODO" in line:
+                    continue
+                header = line.strip()
+                headers.append(header)
+    return headers
+
+
+def check_header_order(path: Path) -> None:
+    doc_dir = path.parent.name
+    if doc_dir not in INFO_BY_DIR:
+        # Skip if not a directory we care about
+        return
+    headers = _get_headers(doc_dir)
+    issue_number = INFO_BY_DIR[doc_dir].get("issue_number", "nonexistent")
+
+    print(f"Checking {doc_dir} page {path}")
+
     with open(path, "r") as f:
         doc = f.read()
-    if not re.search(CHAT_MODEL_REGEX, doc, re.DOTALL):
-        raise ValueError(
-            f"Document {path} does not match the ChatModel Integration page template. "
-            f"Please see https://github.com/langchain-ai/langchain/issues/22296 for "
-            f"instructions on how to correctly format a ChatModel Integration page."
+    regex = r".*".join(headers)
+    if not re.search(regex, doc, re.DOTALL):
+        issueline = (
+            (
+                " Please see https://github.com/langchain-ai/langchain/issues/"
+                f"{issue_number} for instructions on how to correctly format a "
+                f"{doc_dir} integration page."
+            )
+            if isinstance(issue_number, int)
+            else ""
         )
-
-
-def check_document_loader(path: Path) -> None:
-    with open(path, "r") as f:
-        doc = f.read()
-    if not re.search(DOCUMENT_LOADER_REGEX, doc, re.DOTALL):
         raise ValueError(
-            f"Document {path} does not match the DocumentLoader Integration page template. "
-            f"Please see https://github.com/langchain-ai/langchain/issues/22866 for "
-            f"instructions on how to correctly format a DocumentLoader Integration page."
+            f"Document {path} does not match the expected header order.{issueline}"
         )
 
 
 def main(*new_doc_paths: Union[str, Path]) -> None:
     for path in new_doc_paths:
         path = Path(path).resolve().absolute()
-        if CURR_DIR.parent / "docs" / "integrations" / "chat" in path.parents:
-            print(f"Checking chat model page {path}")
-            check_chat_model(path)
-        elif (
-            CURR_DIR.parent / "docs" / "integrations" / "document_loaders"
-            in path.parents
-        ):
-            print(f"Checking document loader page {path}")
-            check_document_loader(path)
+        if CURR_DIR.parent / "docs" / "integrations" in path.parents:
+            check_header_order(path)
         else:
             continue
 

docs/scripts/document_loader_feat_table.py

@@ -15,6 +15,14 @@ hide_table_of_contents: true
 
 # Document loaders
 
+:::info
+
+If you'd like to write your own document loader, see [this how-to](/docs/how_to/document_loader_custom/).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
+
 ## Features
 
 The following table shows the feature support for all document loaders.

docs/scripts/kv_store_feat_table.py

@@ -0,0 +1,107 @@
+import sys
+from pathlib import Path
+
+from langchain_community import document_loaders
+from langchain_core.document_loaders.base import BaseLoader
+
+KV_STORE_TEMPLATE = """\
+---
+sidebar_class_name: hidden
+keywords: [compatibility]
+custom_edit_url:
+hide_table_of_contents: true
+---
+
+# Key-value stores
+
+[Key-value stores](/docs/concepts/#key-value-stores) are used by other LangChain components to store and retrieve data.
+
+:::info
+
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
+
+## Features
+
+The following table shows information on all available key-value stores.
+
+{table}
+
+"""
+
+KV_STORE_FEAT_TABLE = {
+    "AstraDBByteStore": {
+        "class": "[AstraDBByteStore](https://api.python.langchain.com/en/latest/storage/langchain_astradb.storage.AstraDBByteStore.html)",
+        "local": False,
+        "package": "[langchain_astradb](https://api.python.langchain.com/en/latest/astradb_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_astradb?style=flat-square&label=%20)",
+    },
+    "CassandraByteStore": {
+        "class": "[CassandraByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.cassandra.CassandraByteStore.html)",
+        "local": False,
+        "package": "[langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
+    },
+    "ElasticsearchEmbeddingsCache": {
+        "class": "[ElasticsearchEmbeddingsCache](https://api.python.langchain.com/en/latest/cache/langchain_elasticsearch.cache.ElasticsearchEmbeddingsCache.html)",
+        "local": True,
+        "package": "[langchain_elasticsearch](https://api.python.langchain.com/en/latest/elasticsearch_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_elasticsearch?style=flat-square&label=%20)",
+    },
+    "LocalFileStore": {
+        "class": "[LocalFileStore](https://api.python.langchain.com/en/latest/storage/langchain.storage.file_system.LocalFileStore.html)",
+        "local": True,
+        "package": "[langchain](https://api.python.langchain.com/en/latest/langchain_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain?style=flat-square&label=%20)",
+    },
+    "InMemoryByteStore": {
+        "class": "[InMemoryByteStore](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.InMemoryByteStore.html)",
+        "local": True,
+        "package": "[langchain_core](https://api.python.langchain.com/en/latest/core_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_core?style=flat-square&label=%20)",
+    },
+    "RedisStore": {
+        "class": "[RedisStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.redis.RedisStore.html)",
+        "local": True,
+        "package": "[langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
+    },
+    "UpstashRedisByteStore": {
+        "class": "[UpstashRedisByteStore](https://api.python.langchain.com/en/latest/storage/langchain_community.storage.upstash_redis.UpstashRedisByteStore.html)",
+        "local": False,
+        "package": "[langchain_community](https://api.python.langchain.com/en/latest/community_api_reference.html)",
+        "downloads": "![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain_community?style=flat-square&label=%20)",
+    },
+}
+
+DEPRECATED = []
+
+
+def get_kv_store_table() -> str:
+    """Get the table of KV stores."""
+
+    header = ["name", "local", "package", "downloads"]
+    title = ["Class", "Local", "Package", "Downloads"]
+    rows = [title, [":-"] + [":-:"] * (len(title) - 1)]
+    for loader, feats in sorted(KV_STORE_FEAT_TABLE.items()):
+        if not feats or loader in DEPRECATED:
+            continue
+        rows += [
+            [feats["class"]]
+            + ["✅" if feats.get(h) else "❌" for h in header[1:2]]
+            + [feats["package"], feats["downloads"]]
+        ]
+    return "\n".join(["|".join(row) for row in rows])
+
+
+if __name__ == "__main__":
+    output_dir = Path(sys.argv[1])
+    output_integrations_dir = output_dir / "integrations"
+    output_integrations_dir_kv_stores = output_integrations_dir / "stores"
+    output_integrations_dir_kv_stores.mkdir(parents=True, exist_ok=True)
+
+    kv_stores_page = KV_STORE_TEMPLATE.format(table=get_kv_store_table())
+    with open(output_integrations_dir / "stores" / "index.mdx", "w") as f:
+        f.write(kv_stores_page)

docs/scripts/model_feat_table.py

@@ -107,17 +107,27 @@ CHAT_MODEL_FEAT_TABLE = {
         "package": "langchain-openai",
         "link": "/docs/integrations/chat/vllm/",
     },
-    "ChatEdenAI": {
-        "tool_calling": True,
-        "package": "langchain-community",
-        "link": "/docs/integrations/chat/edenai/",
-    },
     "ChatLlamaCpp": {
         "tool_calling": True,
         "local": True,
         "package": "langchain-community",
         "link": "/docs/integrations/chat/llamacpp",
     },
+    "ChatAI21": {
+        "tool_calling": True,
+        "package": "langchain-ai21",
+        "link": "/docs/integrations/chat/ai21",
+    },
+    "ChatWatsonx": {
+        "tool_calling": True,
+        "package": "langchain-ibm",
+        "link": "/docs/integrations/chat/ibm_watsonx",
+    },
+    "ChatUpstage": {
+        "tool_calling": True,
+        "package": "langchain-upstage",
+        "link": "/docs/integrations/chat/upstage",
+    },
 }
 
 for feats in CHAT_MODEL_FEAT_TABLE.values():
@@ -134,6 +144,13 @@ custom_edit_url:
 
 # LLMs
 
+:::info
+
+If you'd like to write your own LLM, see [this how-to](/docs/how_to/custom_llm/).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
 ## Features (natively supported)
 All LLMs implement the Runnable interface, which comes with default implementations of all methods, ie. `ainvoke`, `batch`, `abatch`, `stream`, `astream`. This gives all LLMs basic support for async, streaming and batch, which by default is implemented as below:
 - *Async* support defaults to calling the respective sync method in asyncio's default thread pool executor. This lets other async functions in your application make progress while the LLM is being executed, by moving this call to a background thread.
@@ -157,6 +174,13 @@ hide_table_of_contents: true
 
 # Chat models
 
+:::info
+
+If you'd like to write your own chat model, see [this how-to](/docs/how_to/custom_chat_model/).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
 ## Advanced features
 
 The following table shows all the chat model classes that support one or more advanced features.
@@ -255,7 +279,11 @@ def get_chat_model_table() -> str:
         for h in header[1:]:
             value = feats.get(h)
             if h == "package":
-                row.append(value or "langchain-community")
+                value = value or "langchain-community"
+                name = value[len("langchain-") :]
+                link = f"https://api.python.langchain.com/en/latest/{name}_api_reference.html"
+                value = f"[{value}]({link})"
+                row.append(value)
             else:
                 if value == "partial":
                     row.append("🟡")

docs/scripts/partner_pkg_table.py

@@ -0,0 +1,146 @@
+import glob
+import sys
+from pathlib import Path
+
+PARTNER_DIR = Path(__file__).parents[2] / "libs" / "partners"
+DOCS_DIR = Path(__file__).parents[1]
+
+PLATFORMS = {
+    path.split("/")[-1][:-4]
+    for path in glob.glob(
+        str(DOCS_DIR) + "/docs/integrations/platforms/*.mdx", recursive=True
+    )
+}
+EXTERNAL_PACKAGES = {
+    "astradb",
+    "aws",
+    "cohere",
+    "elasticsearch",
+    "google-community",
+    "google-genai",
+    "google-vertexai",
+    "nvidia-ai-endpoints",
+    "postgres",
+    "redis",
+    "weaviate",
+    "upstage",
+}
+
+JS_PACKAGES = {
+    "google-gauth",
+    "openai",
+    "anthropic",
+    "google-genai",
+    "pinecone",
+    "aws",
+    "google-vertexai",
+    "qdrant",
+    "azure-dynamic-sessions",
+    "google-vertexai-web",
+    "redis",
+    "azure-openai",
+    "google-webauth",
+    "baidu-qianfan",
+    "groq",
+    "standard-tests",
+    "cloudflare",
+    "mistralai",
+    "textsplitters",
+    "cohere",
+    "mixedbread-ai",
+    "weaviate",
+    "mongodb",
+    "yandex",
+    "exa",
+    "nomic",
+    "google-common",
+    "ollama",
+}
+
+
+IN_REPO_PACKAGES = {
+    path.split("/")[-2]
+    for path in glob.glob(str(PARTNER_DIR) + "/**/pyproject.toml", recursive=True)
+}
+ALL_PACKAGES = IN_REPO_PACKAGES.union(EXTERNAL_PACKAGES)
+
+CUSTOM_NAME = {
+    "google-genai": "Google Generative AI",
+    "aws": "AWS",
+    "airbyte": "Airbyte",
+}
+CUSTOM_PROVIDER_PAGES = {
+    "azure-dynamic-sessions": "/docs/integrations/platforms/microsoft/",
+    "google-community": "/docs/integrations/platforms/google/",
+    "google-genai": "/docs/integrations/platforms/google/",
+    "google-vertexai": "/docs/integrations/platforms/google/",
+    "nvidia-ai-endpoints": "/docs/integrations/providers/nvidia/",
+    "exa": "/docs/integrations/providers/exa_search/",
+    "mongodb": "/docs/integrations/providers/mongodb_atlas/",
+}
+PLATFORM_PAGES = {name: f"/docs/integrations/platforms/{name}/" for name in PLATFORMS}
+PROVIDER_PAGES = {
+    name: f"/docs/integrations/providers/{name}/"
+    for name in ALL_PACKAGES
+    if glob.glob(str(DOCS_DIR / f"docs/integrations/providers/{name}.*"))
+}
+PROVIDER_PAGES = {
+    **PROVIDER_PAGES,
+    **PLATFORM_PAGES,
+    **CUSTOM_PROVIDER_PAGES,
+}
+print(PROVIDER_PAGES)
+
+
+def package_row(name: str) -> str:
+    js = "✅" if name in JS_PACKAGES else "❌"
+    link = PROVIDER_PAGES.get(name)
+    title = CUSTOM_NAME.get(name) or name.title().replace("-", " ").replace(
+        "db", "DB"
+    ).replace("Db", "DB").replace("ai", "AI").replace("Ai", "AI")
+    provider = f"[{title}]({link})" if link else title
+    return f"| {provider} | [langchain-{name}](https://api.python.langchain.com/en/latest/{name.replace('-', '_')}_api_reference.html) | ![PyPI - Downloads](https://img.shields.io/pypi/dm/langchain-{name}?style=flat-square&label=%20&color=blue) | ![PyPI - Version](https://img.shields.io/pypi/v/langchain-{name}?style=flat-square&label=%20&color=orange) | {js} |"
+
+
+def table() -> str:
+    header = """| Provider | Package | Downloads | Latest | [JS](https://js.langchain.com/v0.2/docs/integrations/platforms/) |
+| :--- | :---: | :---: | :---: | :---: |
+"""
+    return header + "\n".join(package_row(name) for name in sorted(ALL_PACKAGES))
+
+
+def doc() -> str:
+    return f"""\
+---
+sidebar_position: 0
+sidebar_class_name: hidden
+---
+
+# Providers
+
+:::info
+
+If you'd like to write your own integration, see [Extending LangChain](/docs/how_to/#custom).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
+LangChain integrates with many providers.
+
+## Integration Packages
+
+These providers have standalone `langchain-{{provider}}` packages for improved versioning, dependency management and testing.
+
+{table()}
+
+## All Providers
+
+Click [here](/docs/integrations/providers/) to see all providers.
+
+"""
+
+
+if __name__ == "__main__":
+    output_dir = Path(sys.argv[1]) / "integrations" / "platforms"
+    with open(output_dir / "index.mdx", "w") as f:
+        f.write(doc())

docs/scripts/tool_feat_table.py

@@ -101,6 +101,13 @@ hide_table_of_contents: true
 
 # Tools
 
+:::info
+
+If you'd like to write your own tool, see [this how-to](/docs/how_to/custom_tools/).
+If you'd like to contribute an integration, see [Contributing integrations](/docs/contributing/integrations/).
+
+:::
+
 ## Search Tools
 
 The following table shows tools that execute online searches in some shape or form:

docs/sidebars.js

@@ -75,6 +75,11 @@ module.exports = {
         "versions/overview",
         "versions/release_policy",
         "versions/packages",
+        {
+          type: 'doc',
+          id: "how_to/pydantic_compatibility",
+          label: "Pydantic",
+        },
         {
           type: "category",
           label: "v0.2",
@@ -87,6 +92,18 @@ module.exports = {
             className: 'hidden',
           }],
         },
+        {
+          type: "category",
+          label: "Migrating to LCEL",
+          link: {type: 'doc', id: 'versions/migrating_chains/index'},
+          collapsible: false,
+          collapsed: false,
+          items: [{
+            type: 'autogenerated',
+            dirName: 'versions/migrating_chains',
+            className: 'hidden',
+          }],
+        },
       ],
     },
     "security"
@@ -228,8 +245,8 @@ module.exports = {
             },
           ],
           link: {
-            type: "generated-index",
-            slug: "integrations/retrievers",
+            type: "doc",
+            id: "integrations/retrievers/index",
           },
         },
         {
@@ -257,9 +274,40 @@ module.exports = {
               dirName: "integrations/toolkits",
             },
           ],
+          link: {
+            type: "doc",
+            id: "integrations/toolkits/index",
+          },
+        },
+        {
+          type: "category",
+          label: "Key-value stores",
+          collapsed: true,
+          items: [
+            {
+              type: "autogenerated",
+              dirName: "integrations/stores",
+            },
+          ],
+          link: {
+            type: "doc",
+            id: "integrations/stores/index",
+          },
+        },
+        "integrations/llm_caching",
+        {
+          type: "category",
+          label: "Graphs",
+          collapsed: true,
+          items: [
+            {
+              type: "autogenerated",
+              dirName: "integrations/graphs",
+            },
+          ],
           link: {
             type: "generated-index",
-            slug: "integrations/toolkits",
+            slug: "integrations/graphs",
           },
         },
         {
@@ -277,21 +325,6 @@ module.exports = {
             slug: "integrations/memory",
           },
         },
-        {
-          type: "category",
-          label: "Graphs",
-          collapsed: true,
-          items: [
-            {
-              type: "autogenerated",
-              dirName: "integrations/graphs",
-            },
-          ],
-          link: {
-            type: "generated-index",
-            slug: "integrations/graphs",
-          },
-        },
         {
           type: "category",
           label: "Callbacks",
@@ -337,22 +370,6 @@ module.exports = {
             slug: "integrations/adapters",
           },
         },
-        {
-          type: "category",
-          label: "Stores",
-          collapsed: true,
-          items: [
-            {
-              type: "autogenerated",
-              dirName: "integrations/stores",
-            },
-          ],
-          link: {
-            type: "doc",
-            id: "integrations/stores/index",
-          },
-        },
-        "integrations/llm_caching",
       ],
       link: {
         type: "generated-index",

docs/src/theme/ChatModelTabs.js

@@ -8,7 +8,7 @@ import CodeBlock from "@theme-original/CodeBlock";
  * @typedef {Object} ChatModelTabsProps - Component props.
  * @property {string} [openaiParams] - Parameters for OpenAI chat model. Defaults to `model="gpt-3.5-turbo-0125"`
  * @property {string} [anthropicParams] - Parameters for Anthropic chat model. Defaults to `model="claude-3-sonnet-20240229"`
- * @property {string} [cohereParams] - Parameters for Cohere chat model. Defaults to `model="command-r"`
+ * @property {string} [cohereParams] - Parameters for Cohere chat model. Defaults to `model="command-r-plus"`
  * @property {string} [fireworksParams] - Parameters for Fireworks chat model. Defaults to `model="accounts/fireworks/models/mixtral-8x7b-instruct"`
  * @property {string} [groqParams] - Parameters for Groq chat model. Defaults to `model="llama3-8b-8192"`
  * @property {string} [mistralParams] - Parameters for Mistral chat model. Defaults to `model="mistral-large-latest"`
@@ -181,6 +181,7 @@ import os
 os.environ["${tabItem.apiKeyName}"] = getpass.getpass()`;
           return (
             <TabItem
+              key={tabItem.value}
               value={tabItem.value}
               label={tabItem.label}
               default={tabItem.default}

docs/src/theme/Compatibility.js

@@ -0,0 +1,18 @@
+import React from "react";
+import Admonition from '@theme/Admonition';
+
+export default function Compatibility({ packagesAndVersions }) {
+    return (
+        <Admonition type="caution" title="Compatibility" icon="📦">
+            <span style={{fontSize: "15px"}}>
+              The code in this guide requires{" "}
+              {packagesAndVersions.map(([pkg, version], i) => {
+                return (
+                  <code key={`compatiblity-map${pkg}>=${version}-${i}`}>{`${pkg}>=${version}`}</code>
+                );
+              })}.
+              Please ensure you have the correct packages installed.
+            </span>
+        </Admonition>
+    );
+}

docs/src/theme/Prerequisites.js

@@ -0,0 +1,18 @@
+import React from "react";
+import Admonition from '@theme/Admonition';
+
+export default function Prerequisites({ titlesAndLinks }) {
+    return (
+        <Admonition type="info" title="Prerequisites" icon="📚">
+            <ul style={{ fontSize: "15px", lineHeight: "1.5em" }}>
+                {titlesAndLinks.map(([title, link], i) => {
+                    return (
+                        <li key={`prereq-${link.replace(/\//g, "")}-${i}`}>
+                          <a href={link}>{title}</a>
+                        </li>
+                    );
+                })}
+            </ul>
+        </Admonition>
+    );
+}

docs/vercel.json

@@ -65,6 +65,10 @@
     {
       "source": "/docs/integrations/toolkits/document_comparison_toolkit(/?)",
       "destination": "/docs/tutorials/rag/"
+    },
+    {
+      "source": "/v0.2/docs/how_to/migrate_chains(/?)",
+      "destination": "/v0.2/docs/versions/migrating_chains"
     }
   ]
 }

libs/cli/langchain_cli/integration_template/docs/chat.ipynb

@@ -62,7 +62,8 @@
     "import getpass\n",
     "import os\n",
     "\n",
-    "os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"Enter your __ModuleName__ API key: \")"
+    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
+    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"Enter your __ModuleName__ API key: \")"
    ]
   },
   {
@@ -80,8 +81,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
-    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
    ]
   },
   {
@@ -196,7 +197,7 @@
    "source": [
     "from langchain_core.prompts import ChatPromptTemplate\n",
     "\n",
-    "prompt = ChatPromptTemplate.from_messages(\n",
+    "prompt = ChatPromptTemplate(\n",
     "    [\n",
     "        (\n",
     "            \"system\",\n",

libs/cli/langchain_cli/integration_template/docs/document_loaders.ipynb

@@ -201,10 +201,24 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
   "language_info": {
-   "name": "python"
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

libs/cli/langchain_cli/integration_template/docs/kv_store.ipynb

@@ -0,0 +1,202 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "---\n",
+    "sidebar_label: __ModuleName__ByteStore\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# __ModuleName__ByteStore\n",
+    "\n",
+    "- TODO: Make sure API reference link is correct.\n",
+    "\n",
+    "This will help you get started with __ModuleName__ [key-value stores](/docs/concepts/#key-value-stores). For detailed documentation of all __ModuleName__ByteStore features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/stores/langchain_core.stores.__module_name__ByteStore.html).\n",
+    "\n",
+    "- TODO: Add any other relevant links, like information about models, prices, context windows, etc. See https://python.langchain.com/v0.2/docs/integrations/stores/in_memory/ for an example.\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "- TODO: (Optional) A short introduction to the underlying technology/API.\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "- TODO: Fill in table features.\n",
+    "- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
+    "- TODO: Make sure API reference links are correct.\n",
+    "\n",
+    "| Class | Package | Local | [JS support](https://js.langchain.com/v0.2/docs/integrations/stores/_package_name_) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: |\n",
+    "| [__ModuleName__ByteStore](https://api.python.langchain.com/en/latest/stores/__module_name__.stores.__ModuleName__ByteStore.html) | [__package_name__](https://api.python.langchain.com/en/latest/__package_name_short_snake___api_reference.html) | ✅/❌ | ✅/❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/__package_name__?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/__package_name__?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- TODO: Update with relevant info.\n",
+    "\n",
+    "To create a __ModuleName__ byte store, you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "- TODO: Update with relevant info, or omit if the service does not require any credentials.\n",
+    "\n",
+    "Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
+    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"Enter your __ModuleName__ API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain __ModuleName__ integration lives in the `__package_name__` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU __package_name__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our byte store:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __module_name__ import __ModuleName__ByteStore\n",
+    "\n",
+    "kv_store = __ModuleName__ByteStore(\n",
+    "    # params...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Usage\n",
+    "\n",
+    "- TODO: Run cells so output can be seen.\n",
+    "\n",
+    "You can set data under keys like this using the `mset` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "kv_store.mset(\n",
+    "    [\n",
+    "        [\"key1\", b\"value1\"],\n",
+    "        [\"key2\", b\"value2\"],\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "And you can delete data using the `mdelete` method:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "kv_store.mdelete(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "kv_store.mget(\n",
+    "    [\n",
+    "        \"key1\",\n",
+    "        \"key2\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## TODO: Any functionality specific to this key-value store provider\n",
+    "\n",
+    "E.g. extra initialization. Delete if not relevant."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__ByteStore features and configurations, head to the API reference: https://api.python.langchain.com/en/latest/stores/__module_name__.stores.__ModuleName__ByteStore.html"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.10.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

libs/cli/langchain_cli/integration_template/docs/llms.ipynb

@@ -17,9 +17,75 @@
    "source": [
     "# __ModuleName__LLM\n",
     "\n",
-    "This example goes over how to use LangChain to interact with `__ModuleName__` models.\n",
+    "- [ ] TODO: Make sure API reference link is correct\n",
     "\n",
-    "## Installation"
+    "This will help you get started with __ModuleName__ completion models (LLMs) using LangChain. For detailed documentation on `__ModuleName__LLM` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/llms/__module_name__.llms.__ModuleName__LLM.html).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "- TODO: Fill in table features.\n",
+    "- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
+    "- TODO: Make sure API reference links are correct.\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/llms/__package_name_short_snake__) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [__ModuleName__LLM](https://api.python.langchain.com/en/latest/llms/__module_name__.llms.__ModuleName__LLM.html) | [__package_name__](https://api.python.langchain.com/en/latest/__package_name_short_snake___api_reference.html) | ✅/❌ | beta/❌ | ✅/❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/__package_name__?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/__package_name__?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- [ ] TODO: Update with relevant info.\n",
+    "\n",
+    "To access __ModuleName__ models you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "- TODO: Update with relevant info.\n",
+    "\n",
+    "Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bc51e756",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
+    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"Enter your __ModuleName__ API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4b6e1ca6",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "196c2b41",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "809c6577",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain __ModuleName__ integration lives in the `__package_name__` package:"
    ]
   },
   {
@@ -29,8 +95,38 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# install package\n",
-    "!pip install -U __package_name__"
+    "%pip install -qU __package_name__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a760037",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a0562a13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __module_name__ import __ModuleName__LLM\n",
+    "\n",
+    "llm = __ModuleName__LLM(\n",
+    "    model=\"model-name\",\n",
+    "    temperature=0,\n",
+    "    max_tokens=None,\n",
+    "    timeout=None,\n",
+    "    max_retries=2,\n",
+    "    # other params...\n",
+    ")"
    ]
   },
   {
@@ -38,13 +134,9 @@
    "id": "0ee90032",
    "metadata": {},
    "source": [
-    "## Environment Setup\n",
+    "## Invocation\n",
     "\n",
-    "Make sure to set the following environment variables:\n",
-    "\n",
-    "- TODO: fill out relevant environment variables or secrets\n",
-    "\n",
-    "## Usage"
+    "- [ ] TODO: Run cells so output can be seen."
    ]
   },
   {
@@ -55,21 +147,65 @@
     "tags": []
    },
    "outputs": [],
+   "source": [
+    "input_text = \"__ModuleName__ is an AI company that \"\n",
+    "\n",
+    "completion = llm.invoke(input_text)\n",
+    "completion"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "add38532",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can [chain](/docs/how_to/sequence/) our completion model with a prompt template like so:\n",
+    "\n",
+    "- TODO: Run cells so output can be seen."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "078e9db2",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "from langchain_core.prompts import PromptTemplate\n",
-    "from __module_name__.llms import __ModuleName__LLM\n",
     "\n",
-    "template = \"\"\"Question: {question}\n",
+    "prompt = PromptTemplate(\n",
+    "    \"How to say {input} in {output_language}:\\n\"\n",
+    ")\n",
     "\n",
-    "Answer: Let's think step by step.\"\"\"\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e99eef30",
+   "metadata": {},
+   "source": [
+    "## TODO: Any functionality specific to this model provider\n",
     "\n",
-    "prompt = PromptTemplate.from_string(template)\n",
+    "E.g. creating/using finetuned models via this provider. Delete if not relevant"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9bdfcef",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
     "\n",
-    "model = __ModuleName__LLM()\n",
-    "\n",
-    "chain = prompt | model\n",
-    "\n",
-    "chain.invoke({\"question\": \"What is LangChain?\"})"
+    "For detailed documentation of all `__ModuleName__LLM` features and configurations head to the API reference: https://api.python.langchain.com/en/latest/llms/__module_name__.llms.__ModuleName__LLM.html"
    ]
   }
  ],

libs/cli/langchain_cli/integration_template/docs/retrievers.ipynb

@@ -0,0 +1,248 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: __ModuleName__\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# __ModuleName__Retriever\n",
+    "\n",
+    "## Overview\n",
+    "- TODO: Make sure API reference link is correct.\n",
+    "\n",
+    "This will help you getting started with the __ModuleName__ [retriever](/docs/concepts/#retrievers). For detailed documentation of all __ModuleName__Retriever features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/__module_name__.retrievers.__ModuleName__.__ModuleName__Retriever.html).\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "TODO: Select one of the tables below, as appropriate.\n",
+    "\n",
+    "1: Bring-your-own data (i.e., index and search a custom corpus of documents):\n",
+    "\n",
+    "| Retriever | Self-host | Cloud offering | Package |\n",
+    "| :--- | :--- | :---: | :---: |\n",
+    "[__ModuleName__Retriever](https://api.python.langchain.com/en/latest/retrievers/__package_name__.retrievers.__module_name__.__ModuleName__Retriever.html) | ❌ | ❌ | __package_name__ |\n",
+    "\n",
+    "2: External index (e.g., constructed from Internet data or similar)):\n",
+    "\n",
+    "| Retriever | Source | Package |\n",
+    "| :--- | :--- | :---: |\n",
+    "[__ModuleName__Retriever](https://api.python.langchain.com/en/latest/retrievers/__package_name__.retrievers.__module_name__.__ModuleName__Retriever.html) | Source description | __package_name__ |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- TODO: Update with relevant info."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from individual queries, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This retriever lives in the `__package_name__` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU __package_name__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our retriever:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "70cc8e65-2a02-408a-bbc6-8ef649057d82",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __module_name__ import __ModuleName__Retriever\n",
+    "\n",
+    "retriever = __ModuleName__Retriever(\n",
+    "    # ...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c5f2839-4020-424e-9fc9-07777eede442",
+   "metadata": {},
+   "source": [
+    "## Usage"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51a60dbe-9f2e-4e04-bb62-23968f17164a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"...\"\n",
+    "\n",
+    "retriever.invoke(query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfe8aad4-8626-4330-98a9-7ea1ca5d2e0e",
+   "metadata": {},
+   "source": [
+    "## Use within a chain\n",
+    "\n",
+    "Like other retrievers, __ModuleName__Retriever can be incorporated into LLM applications via [chains](/docs/how_to/sequence/).\n",
+    "\n",
+    "We will need a LLM or chat model:\n",
+    "\n",
+    "```{=mdx}\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"llm\" />\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "25b647a3-f8f2-4541-a289-7a241e43f9df",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "from langchain_openai import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\", temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23e11cc9-abd6-4855-a7eb-799f45ca01ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\n",
+    "    \"\"\"Answer the question based only on the context provided.\n",
+    "\n",
+    "Context: {context}\n",
+    "\n",
+    "Question: {question}\"\"\"\n",
+    ")\n",
+    "\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "\n",
+    "chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d47c37dd-5c11-416c-a3b6-bec413cd70e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"...\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": [
+    "## TODO: Any functionality or considerations specific to this retriever\n",
+    "\n",
+    "Fill in or delete if not relevant."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__Retriever features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/retrievers/__module_name__.retrievers.__ModuleName__.__ModuleName__Retriever.html)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

libs/cli/langchain_cli/integration_template/docs/text_embedding.ipynb

@@ -12,14 +12,217 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e49f1e0d",
+   "id": "9a3d6f34",
    "metadata": {},
    "source": [
     "# __ModuleName__Embeddings\n",
     "\n",
-    "This notebook covers how to get started with __ModuleName__ embedding models.\n",
+    "- [ ] TODO: Make sure API reference link is correct\n",
     "\n",
-    "## Installation"
+    "This will help you get started with __ModuleName__ embedding models using LangChain. For detailed documentation on `__ModuleName__Embeddings` features and configuration options, please refer to the [API reference](https://api.python.langchain.com/en/latest/embeddings/__module_name__.embeddings.__ModuleName__Embeddings.html).\n",
+    "\n",
+    "## Overview\n",
+    "### Integration details\n",
+    "\n",
+    "- TODO: Fill in table features.\n",
+    "- TODO: Remove JS support link if not relevant, otherwise ensure link is correct.\n",
+    "- TODO: Make sure API reference links are correct.\n",
+    "\n",
+    "| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/text_embedding/__package_name_short_snake__) | Package downloads | Package latest |\n",
+    "| :--- | :--- | :---: | :---: |  :---: | :---: | :---: |\n",
+    "| [__ModuleName__Embeddings](https://api.python.langchain.com/en/latest/embeddings/__module_name__.embeddings.__ModuleName__Embeddings.html) | [__package_name__](https://api.python.langchain.com/en/latest/__package_name_short_snake___api_reference.html) | ✅/❌ | beta/❌ | ✅/❌ | ![PyPI - Downloads](https://img.shields.io/pypi/dm/__package_name__?style=flat-square&label=%20) | ![PyPI - Version](https://img.shields.io/pypi/v/__package_name__?style=flat-square&label=%20) |\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- [ ] TODO: Update with relevant info.\n",
+    "\n",
+    "To access __ModuleName__ embedding models you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package.\n",
+    "\n",
+    "### Credentials\n",
+    "\n",
+    "- TODO: Update with relevant info.\n",
+    "\n",
+    "Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36521c2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
+    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"Enter your __ModuleName__ API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c84fb993",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "39a4953b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d9664366",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "The LangChain __ModuleName__ integration lives in the `__package_name__` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "64853226",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU __package_name__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45dd1724",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ea7a09b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __module_name__ import __ModuleName__Embeddings\n",
+    "\n",
+    "embeddings = __ModuleName__Embeddings(\n",
+    "    model=\"model-name\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "77d271b6",
+   "metadata": {},
+   "source": [
+    "## Indexing and Retrieval\n",
+    "\n",
+    "Embedding models are often used in retrieval-augmented generation (RAG) flows, both as part of indexing data as well as later retrieving it. For more detailed instructions, please see our RAG tutorials under the [working with external knowledge tutorials](/docs/tutorials/#working-with-external-knowledge).\n",
+    "\n",
+    "Below, see how to index and retrieve data using the `embeddings` object we initialized above. In this example, we will index and retrieve a sample document in the `InMemoryVectorStore`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d817716b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a vector store with a sample text\n",
+    "from langchain_core.vectorstores import InMemoryVectorStore\n",
+    "\n",
+    "text = \"LangChain is the framework for building context-aware reasoning applications\"\n",
+    "\n",
+    "vectorstore = InMemoryVectorStore.from_texts(\n",
+    "    [text],\n",
+    "    embedding=embeddings,\n",
+    ")\n",
+    "\n",
+    "# Use the vectorstore as a retriever\n",
+    "retriever = vectorstore.as_retriever()\n",
+    "\n",
+    "# Retrieve the most similar text\n",
+    "retrieved_document = retriever.invoke(\"What is LangChain?\")\n",
+    "\n",
+    "# show the retrieved document's content\n",
+    "retrieved_document.page_content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e02b9855",
+   "metadata": {},
+   "source": [
+    "## Direct Usage\n",
+    "\n",
+    "Under the hood, the vectorstore and retriever implementations are calling `embeddings.embed_documents(...)` and `embeddings.embed_query(...)` to create embeddings for the text(s) used in `from_texts` and retrieval `invoke` operations, respectively.\n",
+    "\n",
+    "You can directly call these methods to get embeddings for your own use cases.\n",
+    "\n",
+    "### Embed single texts\n",
+    "\n",
+    "You can embed single texts or documents with `embed_query`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d2befcd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "single_vector = embeddings.embed_query(text)\n",
+    "print(str(single_vector)[:100]) # Show the first 100 characters of the vector"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b5a7d03",
+   "metadata": {},
+   "source": [
+    "### Embed multiple texts\n",
+    "\n",
+    "You can embed multiple texts with `embed_documents`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2f4d6e97",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text2 = (\n",
+    "    \"LangGraph is a library for building stateful, multi-actor applications with LLMs\"\n",
+    ")\n",
+    "two_vectors = embeddings.embed_queries([text, text2])\n",
+    "for vector in two_vectors:\n",
+    "    print(str(vector)[:100]) # Show the first 100 characters of the vector"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "98785c12",
+   "metadata": {},
+   "source": [
+    "### Async Usage\n",
+    "\n",
+    "You can also use `aembed_query` and `aembed_documents` for producing embeddings asynchronously:\n"
    ]
   },
   {
@@ -29,83 +232,22 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# install package\n",
-    "!pip install -U __package_name__"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2b4f3e15",
-   "metadata": {},
-   "source": [
-    "## Environment Setup\n",
+    "import asyncio\n",
     "\n",
-    "Make sure to set the following environment variables:\n",
+    "async def async_example():\n",
+    "    single_vector = await embeddings.embed_query(text)\n",
+    "    print(str(single_vector)[:100]) # Show the first 100 characters of the vector\n",
     "\n",
-    "- TODO: fill out relevant environment variables or secrets\n",
-    "\n",
-    "## Usage"
+    "asyncio.run(async_example())"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "62e0dbc3",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from __module_name__.embeddings import __ModuleName__Embeddings\n",
-    "\n",
-    "embeddings = __ModuleName__Embeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "12fcfb4b",
+   "id": "f1bd4396",
    "metadata": {},
    "outputs": [],
-   "source": [
-    "embeddings.embed_query(\"My query to look up\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1f2e6104",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "embeddings.embed_documents(\n",
-    "    [\"This is a content of the document\", \"This is another document\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "46739f68",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# async embed query\n",
-    "await embeddings.aembed_query(\"My query to look up\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e48632ea",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# async embed documents\n",
-    "await embeddings.aembed_documents(\n",
-    "    [\"This is a content of the document\", \"This is another document\"]\n",
-    ")"
-   ]
+   "source": []
   }
  ],
  "metadata": {

libs/cli/langchain_cli/integration_template/docs/toolkits.ipynb

@@ -0,0 +1,201 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "afaf8039",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: __ModuleName__\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# __ModuleName__Toolkit\n",
+    "\n",
+    "- TODO: Make sure API reference link is correct.\n",
+    "\n",
+    "This will help you getting started with the __ModuleName__ [toolkit](/docs/concepts/#toolkits). For detailed documentation of all __ModuleName__Toolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/__module_name__.agent_toolkits.__ModuleName__.toolkit.__ModuleName__Toolkit.html).\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- TODO: Update with relevant info."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72ee0c4b-9764-423a-9dbf-95129e185210",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing from runs of individual tools, you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a15d341e-3e26-4ca3-830b-5aab30ed66de",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0730d6a1-c893-4840-9817-5e5251676d5d",
+   "metadata": {},
+   "source": [
+    "### Installation\n",
+    "\n",
+    "This toolkit lives in the `__package_name__` package:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "652d6238-1f87-422a-b135-f5abbb8652fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install -qU __package_name__"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a38cde65-254d-4219-a441-068766c0d4b5",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our toolkit:\n",
+    "\n",
+    "- TODO: Update model instantiation with relevant params."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb09c344-1836-4e0c-acf8-11d13ac1dbae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from __module_name__ import __ModuleName__Toolkit\n",
+    "\n",
+    "toolkit = __ModuleName__Toolkit(\n",
+    "    # ...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c5f2839-4020-424e-9fc9-07777eede442",
+   "metadata": {},
+   "source": [
+    "## Tools\n",
+    "\n",
+    "View available tools:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "51a60dbe-9f2e-4e04-bb62-23968f17164a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "toolkit.get_tools()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d11245ad-3661-4405-8558-1188896347ec",
+   "metadata": {},
+   "source": [
+    "TODO: list API reference pages for individual tools."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfe8aad4-8626-4330-98a9-7ea1ca5d2e0e",
+   "metadata": {},
+   "source": [
+    "## Use within an agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "310bf18e-6c9a-4072-b86e-47bc1fcca29d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langgraph.prebuilt import create_react_agent\n",
+    "\n",
+    "agent_executor = create_react_agent(llm, tools)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "23e11cc9-abd6-4855-a7eb-799f45ca01ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "example_query = \"...\"\n",
+    "\n",
+    "events = agent_executor.stream(\n",
+    "    {\"messages\": [(\"user\", example_query)]},\n",
+    "    stream_mode=\"values\",\n",
+    ")\n",
+    "for event in events:\n",
+    "    event[\"messages\"][-1].pretty_print()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1ee55bc-ffc8-4cfa-801c-993953a08cfd",
+   "metadata": {},
+   "source": [
+    "## TODO: Any functionality or considerations specific to this toolkit\n",
+    "\n",
+    "Fill in or delete if not relevant."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3a5bb5ca-c3ae-4a58-be67-2cd18574b9a3",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__Toolkit features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/agent_toolkits/__module_name__.agent_toolkits.__ModuleName__.toolkit.__ModuleName__Toolkit.html)."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

libs/cli/langchain_cli/integration_template/docs/tools.ipynb

@@ -0,0 +1,278 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "10238e62-3465-4973-9279-606cbb7ccf16",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_label: __ModuleName__\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a6f91f20",
+   "metadata": {},
+   "source": [
+    "# __ModuleName__\n",
+    "\n",
+    "- TODO: Make sure API reference link is correct.\n",
+    "\n",
+    "This notebook provides a quick overview for getting started with __ModuleName__ [tool](/docs/integrations/tools/). For detailed documentation of all __ModuleName__ features and configurations head to the [API reference](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.__module_name__.tool.__ModuleName__.html).\n",
+    "\n",
+    "- TODO: Add any other relevant links, like information about underlying API, etc.\n",
+    "\n",
+    "## Overview\n",
+    "\n",
+    "### Integration details\n",
+    "\n",
+    "- TODO: Make sure links and features are correct\n",
+    "\n",
+    "| Class | Package | Serializable | [JS support](https://js.langchain.com/v0.2/docs/integrations/tools/__module_name__) |  Package latest |\n",
+    "| :--- | :--- | :---: | :---: | :---: |\n",
+    "| [__ModuleName__](https://api.python.langchain.com/en/latest/tools/langchain_community.tools.__module_name__.tool.__ModuleName__.html) | [langchain-community](https://api.python.langchain.com/en/latest/community_api_reference.html) | beta/❌ | ✅/❌ |  ![PyPI - Version](https://img.shields.io/pypi/v/langchain-community?style=flat-square&label=%20) |\n",
+    "\n",
+    "### Tool features\n",
+    "\n",
+    "- TODO: Add feature table if it makes sense\n",
+    "\n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "- TODO: Add any additional deps\n",
+    "\n",
+    "The integration lives in the `langchain-community` package."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f85b4089",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install --quiet -U langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b15e9266",
+   "metadata": {},
+   "source": [
+    "### Credentials\n",
+    "\n",
+    "- TODO: Add any credentials that are needed"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e0b178a2-8816-40ca-b57c-ccdd86dde9c9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "# if not os.environ.get(\"__MODULE_NAME___API_KEY\"):\n",
+    "#     os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"__MODULE_NAME__ API key:\\n\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bc5ab717-fd27-4c59-b912-bdd099541478",
+   "metadata": {},
+   "source": [
+    "It's also helpful (but not needed) to set up [LangSmith](https://smith.langchain.com/) for best-in-class observability:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a6c2f136-6367-4f1f-825d-ae741e1bf281",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1c97218f-f366-479d-8bf7-fe9f2f6df73f",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "- TODO: Fill in instantiation params\n",
+    "\n",
+    "Here we show how to instatiate an instance of the __ModuleName__ tool, with "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "8b3ddfe9-ca79-494c-a7ab-1f56d9407a64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_community.tools import __ModuleName__\n",
+    "\n",
+    "\n",
+    "tool = __ModuleName__(\n",
+    "    ...\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "74147a1a",
+   "metadata": {},
+   "source": [
+    "## Invocation\n",
+    "\n",
+    "### [Invoke directly with args](/docs/concepts/#invoke-with-just-the-arguments)\n",
+    "\n",
+    "- TODO: Describe what the tool args are, fill them in, run cell"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "65310a8b-eb0c-4d9e-a618-4f4abe2414fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool.invoke({...})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d6e73897",
+   "metadata": {},
+   "source": [
+    "### [Invoke with ToolCall](/docs/concepts/#invoke-with-toolcall)\n",
+    "\n",
+    "We can also invoke the tool with a model-generated ToolCall, in which case a ToolMessage will be returned:\n",
+    "\n",
+    "- TODO: Fill in tool args and run cell"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f90e33a7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This is usually generated by a model, but we'll create a tool call directly for demo purposes.\n",
+    "model_generated_tool_call = {\n",
+    "    \"args\": {...},  # TODO: FILL IN\n",
+    "    \"id\": \"1\",\n",
+    "    \"name\": tool.name,\n",
+    "    \"type\": \"tool_call\",\n",
+    "}\n",
+    "tool.invoke(model_generated_tool_call)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "659f9fbd-6fcf-445f-aa8c-72d8e60154bd",
+   "metadata": {},
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "- TODO: Add user question and run cells\n",
+    "\n",
+    "We can use our tool in a chain by first binding it to a [tool-calling model](/docs/how_to/tool_calling/) and then calling it:\n",
+    "\n",
+    "import ChatModelTabs from \"@theme/ChatModelTabs\";\n",
+    "\n",
+    "<ChatModelTabs customVarName=\"llm\" />\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "af3123ad-7a02-40e5-b58e-7d56e23e5830",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# | output: false\n",
+    "# | echo: false\n",
+    "\n",
+    "# !pip install -qU langchain langchain-openai\n",
+    "from langchain.chat_models import init_chat_model\n",
+    "\n",
+    "llm = init_chat_model(model=\"gpt-4o\", model_provider=\"openai\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fdbf35b5-3aaf-4947-9ec6-48c21533fb95",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnableConfig, chain\n",
+    "\n",
+    "prompt = ChatPromptTemplate(\n",
+    "    [\n",
+    "        (\"system\", \"You are a helpful assistant.\"),\n",
+    "        (\"human\", \"{user_input}\"),\n",
+    "        (\"placeholder\", \"{messages}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# specifying tool_choice will force the model to call this tool.\n",
+    "llm_with_tools = llm.bind_tools([tool], tool_choice=tool.name)\n",
+    "\n",
+    "llm_chain = prompt | llm_with_tools\n",
+    "\n",
+    "\n",
+    "@chain\n",
+    "def tool_chain(user_input: str, config: RunnableConfig):\n",
+    "    input_ = {\"user_input\": user_input}\n",
+    "    ai_msg = llm_chain.invoke(input_, config=config)\n",
+    "    tool_msgs = tool.batch(ai_msg.tool_calls, config=config)\n",
+    "    return llm_chain.invoke({**input_, \"messages\": [ai_msg, *tool_msgs]}, config=config)\n",
+    "\n",
+    "\n",
+    "tool_chain.invoke(\"...\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ac8146c",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__ features and configurations head to the API reference: https://api.python.langchain.com/en/latest/tools/langchain_community.tools.__module_name__.tool.__ModuleName__.html"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv-311",
+   "language": "python",
+   "name": "poetry-venv-311"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

libs/cli/langchain_cli/integration_template/docs/vectorstores.ipynb

@@ -17,20 +17,7 @@
    "source": [
     "# __ModuleName__VectorStore\n",
     "\n",
-    "This notebook covers how to get started with the __ModuleName__ vector store.\n",
-    "\n",
-    "## Installation"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "d97b55c2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# install package\n",
-    "!pip install -U __package_name__"
+    "This notebook covers how to get started with the __ModuleName__ vector store."
    ]
   },
   {
@@ -38,14 +25,80 @@
    "id": "36fdc060",
    "metadata": {},
    "source": [
-    "## Environment Setup\n",
+    "## Setup\n",
     "\n",
-    "Make sure to set the following environment variables:\n",
+    "- TODO: Update with relevant info.\n",
+    "- TODO: Update minimum version to be correct.\n",
     "\n",
-    "- TODO: fill out relevant environment variables or secrets\n",
-    "- Op\n",
+    "To access __ModuleName__ vector stores you'll need to create a/an __ModuleName__ account, get an API key, and install the `__package_name__` integration package."
+   ]
+  },
+  {
+   "cell_type": "raw",
+   "id": "64e28aa6",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "%pip install -qU \"__package_name__>=MINIMUM_VERSION\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9695dee7",
+   "metadata": {},
+   "source": [
+    "### Credentials\n",
     "\n",
-    "## Usage"
+    "- TODO: Update with relevant info.\n",
+    "\n",
+    "Head to (TODO: link) to sign up to __ModuleName__ and generate an API key. Once you've done this set the __MODULE_NAME___API_KEY environment variable:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "894c30e4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "import os\n",
+    "\n",
+    "if not os.getenv(\"__MODULE_NAME___API_KEY\"):\n",
+    "    import getpass\n",
+    "    os.environ[\"__MODULE_NAME___API_KEY\"] = getpass.getpass(\"Enter your __ModuleName__ API key: \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93df377e",
+   "metadata": {},
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "- TODO: Fill out with relevant init params"
    ]
   },
   {
@@ -59,7 +112,224 @@
    "source": [
     "from __module_name__.vectorstores import __ModuleName__VectorStore\n",
     "\n",
-    "# TODO: switch for preferred way to init and use your vector store\n"
+    "vector_store = __ModuleName__VectorStore()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac6071d4",
+   "metadata": {},
+   "source": [
+    "## Manage vector store\n",
+    "\n",
+    "### Add items to vector store\n",
+    "\n",
+    "- TODO: Edit and then run code cell to generate output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17f5efc0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.documents import Document\n",
+    "\n",
+    "document_1 = Document(\n",
+    "    page_content=\"foo\",\n",
+    "    metadata={\"source\": \"https://example.com\"}\n",
+    ")\n",
+    "\n",
+    "document_2 = Document(\n",
+    "    page_content=\"bar\",\n",
+    "    metadata={\"source\": \"https://example.com\"}\n",
+    ")\n",
+    "\n",
+    "document_2 = Document(\n",
+    "    page_content=\"baz\",\n",
+    "    metadata={\"source\": \"https://example.com\"}\n",
+    ")\n",
+    "\n",
+    "documents = [document_1, document_2]\n",
+    "\n",
+    "vector_store.add_documents(documents=documents,ids=[\"1\",\"2\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c738c3e0",
+   "metadata": {},
+   "source": [
+    "### Update items in vector store\n",
+    "\n",
+    "- TODO: Edit and then run code cell to generate output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f0aa8b71",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "updated_document = Document(\n",
+    "    page_content=\"qux\",\n",
+    "    metadata={\"source\": \"https://another-example.com\"}\n",
+    ")\n",
+    "\n",
+    "vector_store.update_documents(document_id=\"1\",document=updated_document)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dcf1b905",
+   "metadata": {},
+   "source": [
+    "### Delete items from vector store\n",
+    "\n",
+    "- TODO: Edit and then run code cell to generate output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ef61e188",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "vector_store.delete(ids=[\"3\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3620501",
+   "metadata": {},
+   "source": [
+    "## Query vector store\n",
+    "\n",
+    "Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent. \n",
+    "\n",
+    "### Query directly\n",
+    "\n",
+    "Performing a simple similarity search can be done as follows:\n",
+    "\n",
+    "- TODO: Edit and then run code cell to generate output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aa0a16fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = vector_store.similarity_search(query=\"thud\",k=1,filter={\"source\":\"https://example.com\"})\n",
+    "for doc in results:\n",
+    "    print(f\"* {doc.page_content} [{doc.metadata}]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3ed9d733",
+   "metadata": {},
+   "source": [
+    "If you want to execute a similarity search and receive the corresponding scores you can run:\n",
+    "\n",
+    "- TODO: Edit and then run code cell to generate output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5efd2eaa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "results = vector_store.similarity_search_with_score(query=\"thud\",k=1,filter={\"source\":\"https://example.com\"})\n",
+    "for doc, score in results:\n",
+    "    print(f\"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c235cdc",
+   "metadata": {},
+   "source": [
+    "### Query by turning into retriever\n",
+    "\n",
+    "You can also transform the vector store into a retriever for easier usage in your chains. \n",
+    "\n",
+    "- TODO: Edit and then run code cell to generate output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f3460093",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = vector_store.as_retriever()\n",
+    "retriever.invoke(\"thud\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "901c75dc",
+   "metadata": {},
+   "source": [
+    "Using retriever in a simple RAG chain:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "619b5ef6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_openai import ChatOpenAI\n",
+    "from langchain import hub\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "\n",
+    "llm = ChatOpenAI(model=\"gpt-3.5-turbo-0125\")\n",
+    "\n",
+    "prompt = hub.pull(\"rlm/rag-prompt\")\n",
+    "\n",
+    "def format_docs(docs):\n",
+    "    return \"\\n\\n\".join(doc.page_content for doc in docs)\n",
+    "\n",
+    "rag_chain = (\n",
+    "    {\"context\": retriever | format_docs, \"question\": RunnablePassthrough()}\n",
+    "    | prompt\n",
+    "    | llm\n",
+    "    | StrOutputParser()\n",
+    ")\n",
+    "\n",
+    "rag_chain.invoke(\"thud\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "069f1b5f",
+   "metadata": {},
+   "source": [
+    "## TODO: Any functionality specific to this vector store\n",
+    "\n",
+    "E.g. creating a persisten database to save to your disk, etc."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a27244f",
+   "metadata": {},
+   "source": [
+    "## API reference\n",
+    "\n",
+    "For detailed documentation of all __ModuleName__VectorStore features and configurations head to the API reference: https://api.python.langchain.com/en/latest/vectorstores/__module_name__.vectorstores.__ModuleName__VectorStore.html"
    ]
   }
  ],

libs/cli/langchain_cli/integration_template/integration_template/embeddings.py

@@ -4,14 +4,70 @@ from langchain_core.embeddings import Embeddings
 
 
 class __ModuleName__Embeddings(Embeddings):
-    """__ModuleName__Embeddings embedding model.
+    """__ModuleName__ embedding model integration.
 
-    Example:
+    # TODO: Replace with relevant packages, env vars.
+    Setup:
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    # TODO: Populate with relevant params.
+    Key init args — completion params:
+        model: str
+            Name of __ModuleName__ model to use.
+
+    See full list of supported init args and their descriptions in the params section.
+
+    # TODO: Replace with relevant init params.
+    Instantiate:
         .. code-block:: python
 
             from __module_name__ import __ModuleName__Embeddings
 
-            model = __ModuleName__Embeddings()
+            embed = __ModuleName__Embeddings(
+                model="...",
+                # api_key="...",
+                # other params...
+            )
+
+    Embed single text:
+        .. code-block:: python
+
+            input_text = "The meaning of life is 42"
+            embed.embed_query(input_text)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    # TODO: Delete if token-level streaming isn't supported.
+    Embed multiple text:
+        .. code-block:: python
+
+             input_texts = ["Document 1...", "Document 2..."]
+            embed.embed_documents(input_texts)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    # TODO: Delete if native async isn't supported.
+    Async:
+        .. code-block:: python
+
+            await embed.aembed_query(input_text)
+
+            # multiple:
+            # await embed.aembed_documents(input_texts)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
     """
 
     def embed_documents(self, texts: List[str]) -> List[List[float]]:

libs/cli/langchain_cli/integration_template/integration_template/llms.py

@@ -2,36 +2,110 @@
 
 from typing import (
     Any,
-    AsyncIterator,
-    Iterator,
     List,
     Optional,
 )
 
 from langchain_core.callbacks import (
-    AsyncCallbackManagerForLLMRun,
     CallbackManagerForLLMRun,
 )
 from langchain_core.language_models import BaseLLM
-from langchain_core.outputs import GenerationChunk, LLMResult
+from langchain_core.outputs import LLMResult
 
 
 class __ModuleName__LLM(BaseLLM):
-    """__ModuleName__LLM large language models.
+    """__ModuleName__ completion model integration.
 
-    Example:
+    # TODO: Replace with relevant packages, env vars.
+    Setup:
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    # TODO: Populate with relevant params.
+    Key init args — completion params:
+        model: str
+            Name of __ModuleName__ model to use.
+        temperature: float
+            Sampling temperature.
+        max_tokens: Optional[int]
+            Max number of tokens to generate.
+
+    # TODO: Populate with relevant params.
+    Key init args — client params:
+        timeout: Optional[float]
+            Timeout for requests.
+        max_retries: int
+            Max number of retries.
+        api_key: Optional[str]
+            __ModuleName__ API key. If not passed in will be read from env var __MODULE_NAME___API_KEY.
+
+    See full list of supported init args and their descriptions in the params section.
+
+    # TODO: Replace with relevant init params.
+    Instantiate:
         .. code-block:: python
 
             from __module_name__ import __ModuleName__LLM
 
-            model = __ModuleName__LLM()
-            model.invoke("Come up with 10 names for a song about parrots")
-    """
+            llm = __ModuleName__LLM(
+                model="...",
+                temperature=0,
+                max_tokens=None,
+                timeout=None,
+                max_retries=2,
+                # api_key="...",
+                # other params...
+            )
 
-    @property
-    def _llm_type(self) -> str:
-        """Return type of LLM."""
-        return "__package_name_short__-llm"
+    Invoke:
+        .. code-block:: python
+
+            input_text = "The meaning of life is "
+            llm.invoke(input_text)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    # TODO: Delete if token-level streaming isn't supported.
+    Stream:
+        .. code-block:: python
+
+            for chunk in llm.stream(input_text):
+                print(chunk)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+        .. code-block:: python
+
+            ''.join(llm.stream(input_text))
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    # TODO: Delete if native async isn't supported.
+    Async:
+        .. code-block:: python
+
+            await llm.ainvoke(input_text)
+
+            # stream:
+            # async for chunk in (await llm.astream(input_text))
+
+            # batch:
+            # await llm.abatch([input_text])
+
+        .. code-block:: python
+
+            # TODO: Example output.
+    """
 
     # TODO: This method must be implemented to generate text completions.
     def _generate(
@@ -45,32 +119,37 @@ class __ModuleName__LLM(BaseLLM):
 
     # TODO: Implement if __ModuleName__LLM supports async generation. Otherwise
     # delete method.
-    async def _agenerate(
-        self,
-        prompts: List[str],
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> LLMResult:
-        raise NotImplementedError
+    # async def _agenerate(
+    #     self,
+    #     prompts: List[str],
+    #     stop: Optional[List[str]] = None,
+    #     run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+    #     **kwargs: Any,
+    # ) -> LLMResult:
+    #     raise NotImplementedError
 
     # TODO: Implement if __ModuleName__LLM supports streaming. Otherwise delete method.
-    def _stream(
-        self,
-        prompt: str,
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[CallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> Iterator[GenerationChunk]:
-        raise NotImplementedError
+    # def _stream(
+    #     self,
+    #     prompt: str,
+    #     stop: Optional[List[str]] = None,
+    #     run_manager: Optional[CallbackManagerForLLMRun] = None,
+    #     **kwargs: Any,
+    # ) -> Iterator[GenerationChunk]:
+    #     raise NotImplementedError
 
     # TODO: Implement if __ModuleName__LLM supports async streaming. Otherwise delete
     # method.
-    async def _astream(
-        self,
-        prompt: str,
-        stop: Optional[List[str]] = None,
-        run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
-        **kwargs: Any,
-    ) -> AsyncIterator[GenerationChunk]:
-        raise NotImplementedError
+    # async def _astream(
+    #     self,
+    #     prompt: str,
+    #     stop: Optional[List[str]] = None,
+    #     run_manager: Optional[AsyncCallbackManagerForLLMRun] = None,
+    #     **kwargs: Any,
+    # ) -> AsyncIterator[GenerationChunk]:
+    #     raise NotImplementedError
+
+    @property
+    def _llm_type(self) -> str:
+        """Return type of LLM."""
+        return "__package_name_short__-llm"

libs/cli/langchain_cli/integration_template/integration_template/retrievers.py

@@ -0,0 +1,89 @@
+"""__ModuleName__ retrievers."""
+
+from typing import List
+
+from langchain_core.documents import Document
+from langchain_core.retrievers import BaseRetriever
+
+
+class __ModuleName__Retriever(BaseRetriever):
+    # TODO: Replace all TODOs in docstring. See example docstring:
+    # https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/retrievers/tavily_search_api.py#L17
+    """__ModuleName__ retriever.
+
+    # TODO: Replace with relevant packages, env vars, etc.
+    Setup:
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    # TODO: Populate with relevant params.
+    Key init args:
+        arg 1: type
+            description
+        arg 2: type
+            description
+
+    # TODO: Replace with relevant init params.
+    Instantiate:
+        .. code-block:: python
+
+            from __package_name__ import __ModuleName__Retriever
+
+            retriever = __ModuleName__Retriever(
+                # ...
+            )
+
+    Usage:
+        .. code-block:: python
+
+            query = "..."
+
+            retriever.invoke(query)
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    Use within a chain:
+        .. code-block:: python
+
+            from langchain_core.output_parsers import StrOutputParser
+            from langchain_core.prompts import ChatPromptTemplate
+            from langchain_core.runnables import RunnablePassthrough
+            from langchain_openai import ChatOpenAI
+
+            prompt = ChatPromptTemplate.from_template(
+                \"\"\"Answer the question based only on the context provided.
+
+            Context: {context}
+
+            Question: {question}\"\"\"
+            )
+
+            llm = ChatOpenAI(model="gpt-3.5-turbo-0125")
+
+            def format_docs(docs):
+                return "\n\n".join(doc.page_content for doc in docs)
+
+            chain = (
+                {"context": retriever | format_docs, "question": RunnablePassthrough()}
+                | prompt
+                | llm
+                | StrOutputParser()
+            )
+
+            chain.invoke("...")
+
+        .. code-block:: python
+
+             # TODO: Example output.
+
+    """  # noqa: E501
+
+    # TODO: This method must be implemented to retrieve documents.
+    def _get_relevant_documents(self, query: str) -> List[Document]:
+        raise NotImplementedError()

libs/cli/langchain_cli/integration_template/integration_template/toolkits.py

@@ -0,0 +1,72 @@
+"""__ModuleName__ toolkits."""
+
+from typing import List
+
+from langchain_core.tools import BaseTool, BaseToolKit
+
+
+class __ModuleName__Toolkit(BaseToolKit):
+    # TODO: Replace all TODOs in docstring. See example docstring:
+    # https://github.com/langchain-ai/langchain/blob/c123cb2b304f52ab65db4714eeec46af69a861ec/libs/community/langchain_community/agent_toolkits/sql/toolkit.py#L19
+    """__ModuleName__ toolkit.
+
+    # TODO: Replace with relevant packages, env vars, etc.
+    Setup:
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    # TODO: Populate with relevant params.
+    Key init args:
+        arg 1: type
+            description
+        arg 2: type
+            description
+
+    # TODO: Replace with relevant init params.
+    Instantiate:
+        .. code-block:: python
+
+            from __package_name__ import __ModuleName__Toolkit
+
+            toolkit = __ModuleName__Toolkit(
+                # ...
+            )
+
+    Tools:
+        .. code-block:: python
+
+            toolkit.get_tools()
+
+        .. code-block:: python
+
+            # TODO: Example output.
+
+    Use within an agent:
+        .. code-block:: python
+
+            from langgraph.prebuilt import create_react_agent
+
+            agent_executor = create_react_agent(llm, tools)
+
+            example_query = "..."
+
+            events = agent_executor.stream(
+                {"messages": [("user", example_query)]},
+                stream_mode="values",
+            )
+            for event in events:
+                event["messages"][-1].pretty_print()
+
+        .. code-block:: python
+
+             # TODO: Example output.
+
+    """  # noqa: E501
+
+    # TODO: This method must be implemented to list tools.
+    def get_tools(self) -> List[BaseTool]:
+        raise NotImplementedError()

libs/cli/langchain_cli/integration_template/integration_template/tools.py

@@ -0,0 +1,92 @@
+"""__ModuleName__ tools."""
+
+from typing import Optional, Type
+
+from langchain_core.callbacks import (
+    CallbackManagerForToolRun,
+)
+from langchain_core.pydantic_v1 import BaseModel
+from langchain_core.tools import BaseTool
+
+
+class __ModuleName__Input(BaseModel):
+    """Input schema for __ModuleName__ tool.
+
+    This docstring is **not** part of what is sent to the model when performing tool
+    calling. The Field default values and descriptions **are** part of what is sent to
+    the model when performing tool calling.
+    """
+
+    # TODO: Add input args and descriptions.
+    # a: int = Field(..., description="first number")
+    # b: int = Field(0, description="second number")
+    ...
+
+
+class __ModuleName__Tool(BaseTool):
+    """__ModuleName__ tool.
+
+    Setup:
+        # TODO: Replace with relevant packages, env vars.
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    Instantiation:
+        .. code-block:: python
+
+            tool = __ModuleName__Tool(
+                # TODO: init params
+            )
+
+    Invocation with args:
+        .. code-block:: python
+
+            # TODO: invoke args
+            tool.invoke({...})
+
+        .. code-block:: python
+
+            # TODO: output of invocation
+
+    Invocation with ToolCall:
+
+        .. code-block:: python
+
+            # TODO: invoke args
+            tool.invoke({"args": {...}, "id": "1", "name": tool.name, "type": "tool_call})
+
+        .. code-block:: python
+
+            # TODO: output of invocation
+    """
+
+    # TODO: Set tool name and description
+    name: str = "TODO: Tool name"
+    """The name that is passed to the model when performing tool calling."""
+    description: str = "TODO: Tool description."
+    """The description that is passed to the model when performing tool calling."""
+    args_schema: Type[BaseModel] = __ModuleName__Input
+    """The schema that is passed to the model when performing tool calling."""
+
+    # TODO: Add any other init params for the tool.
+    # param1: Optional[str]
+    # """param1 determines foobar"""
+
+    # TODO: Replaced *args with real tool arguments.
+    def _run(
+        self, *args, run_manager: Optional[CallbackManagerForToolRun] = None
+    ) -> str:
+        raise NotImplementedError
+
+    # TODO: Implement if tool has native async functionality, otherwise delete.
+
+    # async def _arun(
+    #     self,
+    #     *args,
+    #     run_manager: Optional[AsyncCallbackManagerForToolRun] = None,
+    # ) -> str:
+    #     ...

libs/cli/langchain_cli/integration_template/integration_template/vectorstores.py

@@ -26,15 +26,109 @@ VST = TypeVar("VST", bound=VectorStore)
 
 
 class __ModuleName__VectorStore(VectorStore):
-    """__ModuleName__ vector store.
+    # TODO: Replace all TODOs in docstring.
+    """__ModuleName__ vector store integration.
 
-    Example:
+    # TODO: Replace with relevant packages, env vars.
+    Setup:
+        Install ``__package_name__`` and set environment variable ``__MODULE_NAME___API_KEY``.
+
+        .. code-block:: bash
+
+            pip install -U __package_name__
+            export __MODULE_NAME___API_KEY="your-api-key"
+
+    # TODO: Populate with relevant params.
+    Key init args — indexing params:
+        collection_name: str
+            Name of the collection.
+        embedding_function: Embeddings
+            Embedding function to use.
+
+    # TODO: Populate with relevant params.
+    Key init args — client params:
+        client: Optional[Client]
+            Client to use.
+        connection_args: Optional[dict]
+            Connection arguments.
+
+    # TODO: Replace with relevant init params.
+    Instantiate:
         .. code-block:: python
 
             from __module_name__.vectorstores import __ModuleName__VectorStore
 
-            vectorstore = __ModuleName__VectorStore()
-    """
+            vector_store = __ModuleName__VectorStore(
+                collection_name="foo",
+                embedding_function=OpenAIEmbeddings(),
+                connection_args={"uri": "./foo.db"},
+                # other params...
+            )
+
+    # TODO: Populate with relevant variables.
+    Add Documents:
+        .. code-block:: python
+
+            from langchain_core.documents import Document
+
+            document = Document(page_content="foo", metadata={"baz": "bar"})
+            vector_store.add_documents([document],ids=["1"])
+
+    # TODO: Populate with relevant variables.
+    Update Documents:
+        .. code-block:: python
+
+            updated_document = Document(
+                page_content="qux",
+                metadata={"bar": "baz"}
+            )
+
+            vector_store.update_documents(document_id="1",document=updated_document)
+
+    Delete Documents:
+        .. code-block:: python
+
+            vector_store.delete(ids=["1"])
+
+    # TODO: Fill out with relevant variables and example output.
+    Search:
+        .. code-block:: python
+
+            results = vector_store.similarity_search(query="thud",k=1)
+            for doc in results:
+                print(f"* {doc.page_content} [{doc.metadata}]")
+
+        .. code-block:: python
+
+            # TODO: Example output
+
+    # TODO: Fill out with relevant variables and example output.
+    Search with score:
+        .. code-block:: python
+
+            results = vector_store.similarity_search_with_score(query="thud",k=1)
+            for doc, score in results:
+                print(f"* [SIM={score:3f}] {doc.page_content} [{doc.metadata}]")
+
+        .. code-block:: python
+
+            # TODO: Example output
+
+    # TODO: Fill out with relevant variables and example output.
+    Use as Retriever:
+        .. code-block:: python
+
+            retriever = vector_store.as_retriever(
+                search_type="mmr",
+                search_kwargs={"k": 1, "fetch_k": 10, "lambda_mult": 0.5},
+            )
+            retriever.invoke("thud")
+
+        .. code-block:: python
+
+            # TODO: Example output
+
+    """  # noqa: E501
 
     def add_texts(
         self,

libs/cli/langchain_cli/integration_template/scripts/check_imports.py

@@ -9,7 +9,7 @@ if __name__ == "__main__":
         try:
             SourceFileLoader("x", file).load_module()
         except Exception:
-            has_faillure = True
+            has_failure = True
             print(file)  # noqa: T201
             traceback.print_exc()
             print()  # noqa: T201

libs/cli/langchain_cli/namespaces/integration.py

@@ -27,7 +27,7 @@ Replacements = TypedDict(
 )
 
 
-def _process_name(name: str):
+def _process_name(name: str, *, community: bool = False):
     preprocessed = name.replace("_", "-").lower()
 
     if preprocessed.startswith("langchain-"):
@@ -42,16 +42,17 @@ def _process_name(name: str):
         raise ValueError("Name should not end with `-`.")
     if preprocessed.find("--") != -1:
         raise ValueError("Name should not contain consecutive hyphens.")
-    return Replacements(
-        {
-            "__package_name__": f"langchain-{preprocessed}",
-            "__module_name__": "langchain_" + preprocessed.replace("-", "_"),
-            "__ModuleName__": preprocessed.title().replace("-", ""),
-            "__MODULE_NAME__": preprocessed.upper().replace("-", ""),
-            "__package_name_short__": preprocessed,
-            "__package_name_short_snake__": preprocessed.replace("-", "_"),
-        }
-    )
+    replacements = {
+        "__package_name__": f"langchain-{preprocessed}",
+        "__module_name__": "langchain_" + preprocessed.replace("-", "_"),
+        "__ModuleName__": preprocessed.title().replace("-", ""),
+        "__MODULE_NAME__": preprocessed.upper().replace("-", ""),
+        "__package_name_short__": preprocessed,
+        "__package_name_short_snake__": preprocessed.replace("-", "_"),
+    }
+    if community:
+        replacements["__module_name__"] = preprocessed.replace("-", "_")
+    return Replacements(replacements)
 
 
 @integration_cli.command()
@@ -126,6 +127,20 @@ def new(
     )
 
 
+TEMPLATE_MAP: dict[str, str] = {
+    "ChatModel": "chat.ipynb",
+    "DocumentLoader": "document_loaders.ipynb",
+    "Tool": "tools.ipynb",
+    "VectorStore": "vectorstores.ipynb",
+    "Embeddings": "text_embedding.ipynb",
+    "ByteStore": "kv_store.ipynb",
+    "LLM": "llms.ipynb",
+    "Provider": "provider.ipynb",
+    "Toolkit": "toolkits.ipynb",
+    "Retriever": "retrievers.ipynb",
+}
+
+
 @integration_cli.command()
 def create_doc(
     name: Annotated[
@@ -155,8 +170,8 @@ def create_doc(
         str,
         typer.Option(
             help=(
-                "The type of component. Currently only 'ChatModel', 'DocumentLoader' "
-                "supported."
+                "The type of component. Currently only 'ChatModel', "
+                "'DocumentLoader', 'VectorStore' supported."
             ),
         ),
     ] = "ChatModel",
@@ -172,7 +187,7 @@ def create_doc(
     Creates a new integration doc.
     """
     try:
-        replacements = _process_name(name)
+        replacements = _process_name(name, community=component_type == "Tool")
     except ValueError as e:
         typer.echo(e)
         raise typer.Exit(code=1)
@@ -200,14 +215,13 @@ def create_doc(
     )
 
     # copy over template from ../integration_template
-    if component_type == "ChatModel":
-        docs_template = (
-            Path(__file__).parents[1] / "integration_template/docs/chat.ipynb"
-        )
-    elif component_type == "DocumentLoader":
-        docs_template = (
-            Path(__file__).parents[1]
-            / "integration_template/docs/document_loaders.ipynb"
+    template_dir = Path(__file__).parents[1] / "integration_template" / "docs"
+    if component_type in TEMPLATE_MAP:
+        docs_template = template_dir / TEMPLATE_MAP[component_type]
+    else:
+        raise ValueError(
+            f"Unrecognized {component_type=}. Expected one of 'ChatModel', "
+            f"'DocumentLoader', 'Tool'."
         )
     shutil.copy(docs_template, destination_path)
 

libs/cli/poetry.lock

@@ -426,13 +426,13 @@ referencing = ">=0.31.0"
 
 [[package]]
 name = "langchain-core"
-version = "0.2.23"
+version = "0.2.25"
 description = "Building applications with LLMs through composability"
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langchain_core-0.2.23-py3-none-any.whl", hash = "sha256:ef0b4184b37e356a27182514aedcc8c41ffacbd6348a801bc775c1ce1f608637"},
-    {file = "langchain_core-0.2.23.tar.gz", hash = "sha256:ac8165f283d8f5214576ffc38387106ef0de7eb8d2c52576d06e8dd3285294b0"},
+    {file = "langchain_core-0.2.25-py3-none-any.whl", hash = "sha256:03d61b2a7f4b5f98df248c1b1f0ccd95c9d5ef2269e174133724365cd2a7ee1e"},
+    {file = "langchain_core-0.2.25.tar.gz", hash = "sha256:e64106a7d0e37e4d35b767f79e6c62b56e825f08f9e8cc4368bcea9955257a7e"},
 ]
 
 [package.dependencies]
@@ -473,13 +473,13 @@ server = ["fastapi (>=0.90.1,<1)", "sse-starlette (>=1.3.0,<2.0.0)"]
 
 [[package]]
 name = "langsmith"
-version = "0.1.93"
+version = "0.1.94"
 description = "Client library to connect to the LangSmith LLM Tracing and Evaluation Platform."
 optional = false
 python-versions = "<4.0,>=3.8.1"
 files = [
-    {file = "langsmith-0.1.93-py3-none-any.whl", hash = "sha256:811210b9d5f108f36431bd7b997eb9476a9ecf5a2abd7ddbb606c1cdcf0f43ce"},
-    {file = "langsmith-0.1.93.tar.gz", hash = "sha256:285b6ad3a54f50fa8eb97b5f600acc57d0e37e139dd8cf2111a117d0435ba9b4"},
+    {file = "langsmith-0.1.94-py3-none-any.whl", hash = "sha256:0d01212086d58699f75814117b026784218042f7859877ce08a248a98d84aa8d"},
+    {file = "langsmith-0.1.94.tar.gz", hash = "sha256:e44afcdc9eee6f238f6a87a02bba83111bd5fad376d881ae299834e06d39d712"},
 ]
 
 [package.dependencies]
@@ -1112,40 +1112,40 @@ files = [
 
 [[package]]
 name = "ruff"
-version = "0.5.4"
+version = "0.5.5"
 description = "An extremely fast Python linter and code formatter, written in Rust."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "ruff-0.5.4-py3-none-linux_armv6l.whl", hash = "sha256:82acef724fc639699b4d3177ed5cc14c2a5aacd92edd578a9e846d5b5ec18ddf"},
-    {file = "ruff-0.5.4-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:da62e87637c8838b325e65beee485f71eb36202ce8e3cdbc24b9fcb8b99a37be"},
-    {file = "ruff-0.5.4-py3-none-macosx_11_0_arm64.whl", hash = "sha256:e98ad088edfe2f3b85a925ee96da652028f093d6b9b56b76fc242d8abb8e2059"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4c55efbecc3152d614cfe6c2247a3054cfe358cefbf794f8c79c8575456efe19"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f9b85eaa1f653abd0a70603b8b7008d9e00c9fa1bbd0bf40dad3f0c0bdd06793"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0cf497a47751be8c883059c4613ba2f50dd06ec672692de2811f039432875278"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:09c14ed6a72af9ccc8d2e313d7acf7037f0faff43cde4b507e66f14e812e37f7"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:628f6b8f97b8bad2490240aa84f3e68f390e13fabc9af5c0d3b96b485921cd60"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3520a00c0563d7a7a7c324ad7e2cde2355733dafa9592c671fb2e9e3cd8194c1"},
-    {file = "ruff-0.5.4-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:93789f14ca2244fb91ed481456f6d0bb8af1f75a330e133b67d08f06ad85b516"},
-    {file = "ruff-0.5.4-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:029454e2824eafa25b9df46882f7f7844d36fd8ce51c1b7f6d97e2615a57bbcc"},
-    {file = "ruff-0.5.4-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:9492320eed573a13a0bc09a2957f17aa733fff9ce5bf00e66e6d4a88ec33813f"},
-    {file = "ruff-0.5.4-py3-none-musllinux_1_2_i686.whl", hash = "sha256:a6e1f62a92c645e2919b65c02e79d1f61e78a58eddaebca6c23659e7c7cb4ac7"},
-    {file = "ruff-0.5.4-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:768fa9208df2bec4b2ce61dbc7c2ddd6b1be9fb48f1f8d3b78b3332c7d71c1ff"},
-    {file = "ruff-0.5.4-py3-none-win32.whl", hash = "sha256:e1e7393e9c56128e870b233c82ceb42164966f25b30f68acbb24ed69ce9c3a4e"},
-    {file = "ruff-0.5.4-py3-none-win_amd64.whl", hash = "sha256:58b54459221fd3f661a7329f177f091eb35cf7a603f01d9eb3eb11cc348d38c4"},
-    {file = "ruff-0.5.4-py3-none-win_arm64.whl", hash = "sha256:bd53da65f1085fb5b307c38fd3c0829e76acf7b2a912d8d79cadcdb4875c1eb7"},
-    {file = "ruff-0.5.4.tar.gz", hash = "sha256:2795726d5f71c4f4e70653273d1c23a8182f07dd8e48c12de5d867bfb7557eed"},
+    {file = "ruff-0.5.5-py3-none-linux_armv6l.whl", hash = "sha256:605d589ec35d1da9213a9d4d7e7a9c761d90bba78fc8790d1c5e65026c1b9eaf"},
+    {file = "ruff-0.5.5-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:00817603822a3e42b80f7c3298c8269e09f889ee94640cd1fc7f9329788d7bf8"},
+    {file = "ruff-0.5.5-py3-none-macosx_11_0_arm64.whl", hash = "sha256:187a60f555e9f865a2ff2c6984b9afeffa7158ba6e1eab56cb830404c942b0f3"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fe26fc46fa8c6e0ae3f47ddccfbb136253c831c3289bba044befe68f467bfb16"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:4ad25dd9c5faac95c8e9efb13e15803cd8bbf7f4600645a60ffe17c73f60779b"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f70737c157d7edf749bcb952d13854e8f745cec695a01bdc6e29c29c288fc36e"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:cfd7de17cef6ab559e9f5ab859f0d3296393bc78f69030967ca4d87a541b97a0"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a09b43e02f76ac0145f86a08e045e2ea452066f7ba064fd6b0cdccb486f7c3e7"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d0b856cb19c60cd40198be5d8d4b556228e3dcd545b4f423d1ad812bfdca5884"},
+    {file = "ruff-0.5.5-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3687d002f911e8a5faf977e619a034d159a8373514a587249cc00f211c67a091"},
+    {file = "ruff-0.5.5-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:ac9dc814e510436e30d0ba535f435a7f3dc97f895f844f5b3f347ec8c228a523"},
+    {file = "ruff-0.5.5-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:af9bdf6c389b5add40d89b201425b531e0a5cceb3cfdcc69f04d3d531c6be74f"},
+    {file = "ruff-0.5.5-py3-none-musllinux_1_2_i686.whl", hash = "sha256:d40a8533ed545390ef8315b8e25c4bb85739b90bd0f3fe1280a29ae364cc55d8"},
+    {file = "ruff-0.5.5-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:cab904683bf9e2ecbbe9ff235bfe056f0eba754d0168ad5407832928d579e7ab"},
+    {file = "ruff-0.5.5-py3-none-win32.whl", hash = "sha256:696f18463b47a94575db635ebb4c178188645636f05e934fdf361b74edf1bb2d"},
+    {file = "ruff-0.5.5-py3-none-win_amd64.whl", hash = "sha256:50f36d77f52d4c9c2f1361ccbfbd09099a1b2ea5d2b2222c586ab08885cf3445"},
+    {file = "ruff-0.5.5-py3-none-win_arm64.whl", hash = "sha256:3191317d967af701f1b73a31ed5788795936e423b7acce82a2b63e26eb3e89d6"},
+    {file = "ruff-0.5.5.tar.gz", hash = "sha256:cc5516bdb4858d972fbc31d246bdb390eab8df1a26e2353be2dbc0c2d7f5421a"},
 ]
 
 [[package]]
 name = "setuptools"
-version = "71.1.0"
+version = "72.1.0"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "setuptools-71.1.0-py3-none-any.whl", hash = "sha256:33874fdc59b3188304b2e7c80d9029097ea31627180896fb549c578ceb8a0855"},
-    {file = "setuptools-71.1.0.tar.gz", hash = "sha256:032d42ee9fb536e33087fb66cac5f840eb9391ed05637b3f2a76a7c8fb477936"},
+    {file = "setuptools-72.1.0-py3-none-any.whl", hash = "sha256:5a03e1860cf56bb6ef48ce186b0e557fdba433237481a9a625176c2831be15d1"},
+    {file = "setuptools-72.1.0.tar.gz", hash = "sha256:8d243eff56d095e5817f796ede6ae32941278f542e0f941867cc05ae52b162ec"},
 ]
 
 [package.extras]

libs/cli/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "langchain-cli"
-version = "0.0.26"
+version = "0.0.28"
 description = "CLI for interacting with LangChain"
 authors = ["Erick Friis <erick@langchain.dev>"]
 readme = "README.md"

libs/community/extended_testing_deps.txt

@@ -40,6 +40,7 @@ jinja2>=3,<4
 jq>=1.4.1,<2
 jsonschema>1
 keybert>=0.8.5
+litellm>=1.30,<=1.39.5
 lxml>=4.9.3,<6.0
 markdownify>=0.11.6,<0.12
 motor>=3.3.1,<4
@@ -90,3 +91,4 @@ vdms>=0.0.20
 xata>=1.0.0a7,<2
 xmltodict>=0.13.0,<0.14
 nanopq==0.2.1
+mlflow[genai]>=2.14.0

libs/community/langchain_community/agent_toolkits/sql/toolkit.py

@@ -17,12 +17,63 @@ from langchain_community.utilities.sql_database import SQLDatabase
 
 
 class SQLDatabaseToolkit(BaseToolkit):
-    """Toolkit for interacting with SQL databases.
+    """SQLDatabaseToolkit for interacting with SQL databases.
 
-    Parameters:
-        db: SQLDatabase. The SQL database.
-        llm: BaseLanguageModel. The language model.
-    """
+    Setup:
+        Install ``langchain-community``.
+
+        .. code-block:: bash
+
+            pip install -U langchain-community
+
+    Key init args:
+        db: SQLDatabase
+            The SQL database.
+        llm: BaseLanguageModel
+            The language model (for use with QuerySQLCheckerTool)
+
+    Instantiate:
+        .. code-block:: python
+
+            from langchain_community.agent_toolkits.sql.toolkit import SQLDatabaseToolkit
+            from langchain_community.utilities.sql_database import SQLDatabase
+            from langchain_openai import ChatOpenAI
+
+            db = SQLDatabase.from_uri("sqlite:///Chinook.db")
+            llm = ChatOpenAI(temperature=0)
+
+            toolkit = SQLDatabaseToolkit(db=db, llm=llm)
+
+    Tools:
+        .. code-block:: python
+
+            toolkit.get_tools()
+
+    Use within an agent:
+        .. code-block:: python
+
+            from langchain import hub
+            from langgraph.prebuilt import create_react_agent
+
+            # Pull prompt (or define your own)
+            prompt_template = hub.pull("langchain-ai/sql-agent-system-prompt")
+            system_message = prompt_template.format(dialect="SQLite", top_k=5)
+
+            # Create agent
+            agent_executor = create_react_agent(
+                llm, toolkit.get_tools(), state_modifier=system_message
+            )
+
+            # Query agent
+            example_query = "Which country's customers spent the most?"
+
+            events = agent_executor.stream(
+                {"messages": [("user", example_query)]},
+                stream_mode="values",
+            )
+            for event in events:
+                event["messages"][-1].pretty_print()
+    """  # noqa: E501
 
     db: SQLDatabase = Field(exclude=True)
     llm: BaseLanguageModel = Field(exclude=True)

libs/community/langchain_community/callbacks/upstash_ratelimit_callback.py

@@ -58,7 +58,7 @@ class UpstashRatelimitHandler(BaseCallbackHandler):
     every time you invoke.
     """
 
-    raise_error = True
+    raise_error: bool = True
     _checked: bool = False
 
     def __init__(