bump 317 (#11986)

Adds `langchain.runnables.hub.HubRunnable` for pulling configurable
objects from the hub

.github/CONTRIBUTING.md

@@ -289,6 +289,13 @@ make docs_linkcheck
 make api_docs_linkcheck
 ```
 
+### Verify Documentation changes
+
+After pushing documentation changes to the repository, you can preview and verify that the changes are 
+what you wanted by clicking the `View deployment` or `Visit Preview` buttons on the pull request `Conversation` page. 
+This will take you to a preview of the documentation changes.
+This preview is created by [Vercel](https://vercel.com/docs/getting-started-with-vercel).
+
 ## 🏭 Release Process
 
 As of now, LangChain has an ad hoc release process: releases are cut with high frequency by

.github/workflows/doc_lint.yml

@@ -19,4 +19,4 @@ jobs:
       run: |
         # We should not encourage imports directly from main init file
         # Expect for hub
-        git grep 'from langchain import' docs/{extras,docs_skeleton,snippets} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
+        git grep 'from langchain import' docs/{docs,snippets} | grep -vE 'from langchain import (hub)' && exit 1 || exit 0

.github/workflows/scheduled_test.yml

@@ -61,6 +61,10 @@ jobs:
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_DEPLOYMENT_NAME:  ${{ secrets.AZURE_OPENAI_DEPLOYMENT_NAME }}
         run: |
           make scheduled_tests
 

.gitignore

@@ -174,6 +174,7 @@ docs/api_reference/*/
 !docs/api_reference/_static/
 !docs/api_reference/templates/
 !docs/api_reference/themes/
-docs/docs_skeleton/build
-docs/docs_skeleton/node_modules
-docs/docs_skeleton/yarn.lock
+docs/docs/build
+docs/docs/node_modules
+docs/docs/yarn.lock
+_dist

.gitmodules

@@ -1,4 +0,0 @@
-[submodule "docs/_docs_skeleton"]
-	path = docs/_docs_skeleton
-	url = https://github.com/langchain-ai/langchain-shared-docs
-	branch = main

.readthedocs.yaml

@@ -9,9 +9,14 @@ build:
   os: ubuntu-22.04
   tools:
     python: "3.11"
-  jobs:
-    pre_build:
+  commands:
+      - python -mvirtualenv $READTHEDOCS_VIRTUALENV_PATH
+      - python -m pip install --upgrade --no-cache-dir pip setuptools
+      - python -m pip install --upgrade --no-cache-dir sphinx readthedocs-sphinx-ext
+      - python -m pip install --exists-action=w --no-cache-dir -r docs/api_reference/requirements.txt
       - python docs/api_reference/create_api_rst.py
+      - cat docs/api_reference/conf.py
+      - python -m sphinx -T -E -b html -d _build/doctrees -c docs/api_reference docs/api_reference $READTHEDOCS_OUTPUT/html -j auto
 
 # Build documentation in the docs/ directory with Sphinx
 sphinx:

Makefile

@@ -15,10 +15,10 @@ docs_build:
 	docs/.local_build.sh
 
 docs_clean:
-	rm -r docs/_dist
+	rm -r _dist
 
 docs_linkcheck:
-	poetry run linkchecker docs/_dist/docs_skeleton/ --ignore-url node_modules
+	poetry run linkchecker _dist/docs/ --ignore-url node_modules
 
 api_docs_build:
 	poetry run python docs/api_reference/create_api_rst.py
@@ -53,4 +53,4 @@ help:
 	@echo 'api_docs_linkcheck           - run linkchecker on the API Reference documentation'
 	@echo 'spell_check               	- run codespell on the project'
 	@echo 'spell_fix               		- run codespell on the project and fix the errors'
-	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'
+	@echo '-- TEST and LINT tasks are within libs/*/ per-package --'

README.md

@@ -18,8 +18,9 @@
 
 Looking for the JS/TS version? Check out [LangChain.js](https://github.com/langchain-ai/langchainjs).
 
-**Production Support:** As you move your LangChains into production, we'd love to offer more hands-on support.
-Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to share more about what you're building, and our team will get in touch.
+To help you ship LangChain apps to production faster, check out [LangSmith](https://smith.langchain.com). 
+[LangSmith](https://smith.langchain.com) is a unified developer platform for building, testing, and monitoring LLM applications. 
+Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) to get off the waitlist or speak with our sales team
 
 ## 🚨Breaking Changes for select chains (SQLDatabase) on 7/28/23
 

cookbook/elasticsearch_db_qa.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "# Elasticsearch\n",
     "\n",
-    "[![Open In Collab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs_skeleton/docs/use_cases/qa_structured/integrations/elasticsearch.ipynb)\n",
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/docs/use_cases/qa_structured/integrations/elasticsearch.ipynb)\n",
     "\n",
     "We can use LLMs to interact with Elasticsearch analytics databases in natural language.\n",
     "\n",

cookbook/forward_looking_retrieval_augmented_generation.ipynb

@@ -135,9 +135,9 @@
    "outputs": [],
    "source": [
     "# We set this so we can see what exactly is going on\n",
-    "import langchain\n",
+    "from langchain.globals import set_verbose\n",
     "\n",
-    "langchain.verbose = True"
+    "set_verbose(True)"
    ]
   },
   {
@@ -489,7 +489,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

cookbook/learned_prompt_optimization.ipynb

@@ -57,7 +57,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "##### Intialize the RL chain with provided defaults\n",
+    "##### Initialize the RL chain with provided defaults\n",
     "\n",
     "The prompt template which will be used to query the LLM needs to be defined.\n",
     "It can be anything, but here `{meal}` is being used and is going to be replaced by one of the meals above, the RL chain will try to pick and inject the best meal\n"
@@ -212,9 +212,9 @@
     "\n",
     "It's important to note that while the RL model can make sophisticated selections, it doesn't inherently recognize concepts like \"vegetarian\" or understand that \"beef enchiladas\" aren't vegetarian-friendly. Instead, it leverages the LLM to ground its choices in common sense.\n",
     "\n",
-    "The way the chain is learning that Tom prefers veggetarian meals is via an AutoSelectionScorer that is built into the chain. The scorer will call the LLM again and ask it to evaluate the selection (`ToSelectFrom`) using the information wrapped in (`BasedOn`).\n",
+    "The way the chain is learning that Tom prefers vegetarian meals is via an AutoSelectionScorer that is built into the chain. The scorer will call the LLM again and ask it to evaluate the selection (`ToSelectFrom`) using the information wrapped in (`BasedOn`).\n",
     "\n",
-    "You can set `langchain.debug=True` if you want to see the details of the auto-scorer, but you can also define the scoring prompt yourself."
+    "You can set `set_debug(True)` if you want to see the details of the auto-scorer, but you can also define the scoring prompt yourself."
    ]
   },
   {
@@ -286,7 +286,7 @@
     "        print(event.to_select_from)\n",
     "\n",
     "        # you can build a complex scoring function here\n",
-    "        # it is prefereable that the score ranges between 0 and 1 but it is not enforced\n",
+    "        # it is preferable that the score ranges between 0 and 1 but it is not enforced\n",
     "\n",
     "        selected_meal = event.to_select_from[\"meal\"][event.selected.index]\n",
     "        print(f\"selected meal: {selected_meal}\")\n",
@@ -617,7 +617,7 @@
     "\n",
     "### other advanced featurization options\n",
     "\n",
-    "Explictly numerical features can be provided with a colon separator:\n",
+    "Explicitly numerical features can be provided with a colon separator:\n",
     "`age = rl_chain.BasedOn(\"age:32\")`\n",
     "\n",
     "`ToSelectFrom` can be a bit more complex if the scenario demands it, instead of being a list of strings it can be:\n",
@@ -672,7 +672,7 @@
     "\n",
     "```\n",
     "\n",
-    "Internally the AutoSelectionScorer adjusted the scoring prompt to make sure that the llm scoring retured a single float.\n",
+    "Internally the AutoSelectionScorer adjusted the scoring prompt to make sure that the llm scoring returned a single float.\n",
     "\n",
     "However, if needed, a FULL scoring prompt can also be provided:\n"
    ]
@@ -730,7 +730,7 @@
       "\u001b[32;1m\u001b[1;3m[llm/start]\u001b[0m \u001b[1m[1:chain:LLMChain > 2:llm:OpenAI] Entering LLM run with input:\n",
       "\u001b[0m{\n",
       "  \"prompts\": [\n",
-      "    \"Given ['Vegetarian', 'regular dairy is ok'] rank how good or bad this selection is ['Beef Enchiladas with Feta cheese. Mexican-Greek fusion', 'Chicken Flatbreads with red sauce. Italian-Mexican fusion', 'Veggie sweet potato quesadillas with vegan cheese', 'One-Pan Tortelonni bake with peppers and onions']\\n\\nIMPORANT: you MUST return a single number between -1 and 1, -1 being bad, 1 being good\"\n",
+      "    \"Given ['Vegetarian', 'regular dairy is ok'] rank how good or bad this selection is ['Beef Enchiladas with Feta cheese. Mexican-Greek fusion', 'Chicken Flatbreads with red sauce. Italian-Mexican fusion', 'Veggie sweet potato quesadillas with vegan cheese', 'One-Pan Tortelonni bake with peppers and onions']\\n\\nIMPORTANT: you MUST return a single number between -1 and 1, -1 being bad, 1 being good\"\n",
       "  ]\n",
       "}\n",
       "\u001b[36;1m\u001b[1;3m[llm/end]\u001b[0m \u001b[1m[1:chain:LLMChain > 2:llm:OpenAI] [274ms] Exiting LLM run with output:\n",
@@ -778,14 +778,15 @@
    ],
    "source": [
     "from langchain.prompts.prompt import PromptTemplate\n",
-    "import langchain\n",
-    "langchain.debug = True\n",
+    "from langchain.globals import set_debug\n",
+    "\n",
+    "set_debug(True)\n",
     "\n",
     "REWARD_PROMPT_TEMPLATE = \"\"\"\n",
     "\n",
     "Given {preference} rank how good or bad this selection is {meal}\n",
     "\n",
-    "IMPORANT: you MUST return a single number between -1 and 1, -1 being bad, 1 being good\n",
+    "IMPORTANT: you MUST return a single number between -1 and 1, -1 being bad, 1 being good\n",
     "\n",
     "\"\"\"\n",
     "\n",
@@ -812,9 +813,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "poetry-venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "poetry-venv"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -826,7 +827,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.1"
   }
  },
  "nbformat": 4,

cookbook/llm_bash.ipynb

@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {
@@ -37,13 +37,13 @@
        "'Hello World\\n'"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain.chains import LLMBashChain\n",
+    "from langchain_experimental.llm_bash.base import LLMBashChain\n",
     "from langchain.llms import OpenAI\n",
     "\n",
     "llm = OpenAI(temperature=0)\n",
@@ -65,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -98,7 +98,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -125,7 +125,7 @@
        "'Hello World\\n'"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -149,7 +149,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -166,28 +166,24 @@
       "cd ..\n",
       "```\u001b[0m\n",
       "Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3mapi.html\t\t\tllm_summarization_checker.html\n",
-      "constitutional_chain.html\tmoderation.html\n",
-      "llm_bash.html\t\t\topenai_openapi.yaml\n",
-      "llm_checker.html\t\topenapi.html\n",
-      "llm_math.html\t\t\tpal.html\n",
-      "llm_requests.html\t\tsqlite.html\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3mcpal.ipynb  llm_bash.ipynb  llm_symbolic_math.ipynb\n",
+      "index.mdx   llm_math.ipynb  pal.ipynb\u001b[0m\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "'api.html\\t\\t\\tllm_summarization_checker.html\\r\\nconstitutional_chain.html\\tmoderation.html\\r\\nllm_bash.html\\t\\t\\topenai_openapi.yaml\\r\\nllm_checker.html\\t\\topenapi.html\\r\\nllm_math.html\\t\\t\\tpal.html\\r\\nllm_requests.html\\t\\tsqlite.html'"
+       "'cpal.ipynb  llm_bash.ipynb  llm_symbolic_math.ipynb\\r\\nindex.mdx   llm_math.ipynb  pal.ipynb'"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "from langchain.utilities.bash import BashProcess\n",
+    "from langchain_experimental.llm_bash.bash import BashProcess\n",
     "\n",
     "\n",
     "persistent_process = BashProcess(persistent=True)\n",
@@ -200,7 +196,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -217,18 +213,19 @@
       "cd ..\n",
       "```\u001b[0m\n",
       "Code: \u001b[33;1m\u001b[1;3m['ls', 'cd ..']\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3mexamples\t\tgetting_started.html\tindex_examples\n",
-      "generic\t\t\thow_to_guides.rst\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m_category_.yml\tdata_generation.ipynb\t\t   self_check\n",
+      "agents\t\tgraph\n",
+      "code_writing\tlearned_prompt_optimization.ipynb\u001b[0m\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
-       "'examples\\t\\tgetting_started.html\\tindex_examples\\r\\ngeneric\\t\\t\\thow_to_guides.rst'"
+       "'_category_.yml\\tdata_generation.ipynb\\t\\t   self_check\\r\\nagents\\t\\tgraph\\r\\ncode_writing\\tlearned_prompt_optimization.ipynb'"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -237,13 +234,6 @@
     "# Run the same command again and see that the state is maintained between calls\n",
     "bash_chain.run(text)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -262,7 +252,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,

cookbook/llm_symbolic_math.ipynb

@@ -10,12 +10,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.llms import OpenAI\n",
-    "from langchain.chains.llm_symbolic_math.base import LLMSymbolicMathChain\n",
+    "from langchain_experimental.llm_symbolic_math.base import LLMSymbolicMathChain\n",
     "\n",
     "llm = OpenAI(temperature=0)\n",
     "llm_symbolic_math = LLMSymbolicMathChain.from_llm(llm)"
@@ -30,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -39,7 +39,7 @@
        "'Answer: exp(x)*sin(x) + exp(x)*cos(x)'"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -50,7 +50,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -59,7 +59,7 @@
        "'Answer: exp(x)*sin(x)'"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -79,7 +79,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [
     {
@@ -88,7 +88,7 @@
        "'Answer: Eq(y(t), C2*exp(-t) + (C1 + t/2)*exp(t))'"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -99,7 +99,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -108,7 +108,7 @@
        "'Answer: {0, -sqrt(3)*I/3, sqrt(3)*I/3}'"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -119,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -128,7 +128,7 @@
        "'Answer: (3 - sqrt(7), -sqrt(7) - 2, 1 - sqrt(7)), (sqrt(7) + 3, -2 + sqrt(7), 1 + sqrt(7))'"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -140,9 +140,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
-   "name": "venv"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
@@ -154,9 +154,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.11.4"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

cookbook/plan_and_execute_agent.ipynb

@@ -0,0 +1,252 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "0ddfef23-3c74-444c-81dd-6753722997fa",
+   "metadata": {},
+   "source": [
+    "# Plan-and-execute\n",
+    "\n",
+    "Plan-and-execute agents accomplish an objective by first planning what to do, then executing the sub tasks. This idea is largely inspired by [BabyAGI](https://github.com/yoheinakajima/babyagi) and then the [\"Plan-and-Solve\" paper](https://arxiv.org/abs/2305.04091).\n",
+    "\n",
+    "The planning is almost always done by an LLM.\n",
+    "\n",
+    "The execution is usually done by a separate agent (equipped with tools)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a7ecb22a-7009-48ec-b14e-f0fa5aac1cd0",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5fbbd4ee-bfe8-4a25-afe4-8d1a552a3d2e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents.tools import Tool\n",
+    "from langchain.chains import LLMMathChain\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.utilities import DuckDuckGoSearchAPIWrapper\n",
+    "from langchain_experimental.plan_and_execute import PlanAndExecute, load_agent_executor, load_chat_planner"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e0e995e5-af9d-4988-bcd0-467a2a2e18cd",
+   "metadata": {},
+   "source": [
+    "## Tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "1d789f4e-54e3-4602-891a-f076e0ab9594",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search = DuckDuckGoSearchAPIWrapper()\n",
+    "llm = OpenAI(temperature=0)\n",
+    "llm_math_chain = LLMMathChain.from_llm(llm=llm, verbose=True)\n",
+    "tools = [\n",
+    " Tool(\n",
+    "     name=\"Search\",\n",
+    "     func=search.run,\n",
+    "     description=\"useful for when you need to answer questions about current events\"\n",
+    " ),\n",
+    " Tool(\n",
+    "     name=\"Calculator\",\n",
+    "     func=llm_math_chain.run,\n",
+    "     description=\"useful for when you need to answer questions about math\"\n",
+    " ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "04dc6452-a07f-49f9-be12-95be1e2afccc",
+   "metadata": {},
+   "source": [
+    "## Planner, Executor, and Agent\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "d8f49c03-c804-458b-8122-c92b26c7b7dd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = ChatOpenAI(temperature=0)\n",
+    "planner = load_chat_planner(model)\n",
+    "executor = load_agent_executor(model, tools, verbose=True)\n",
+    "agent = PlanAndExecute(planner=planner, executor=executor)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "78ba03dd-0322-4927-b58d-a7e2027fdbb3",
+   "metadata": {},
+   "source": [
+    "## Run example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a57f7efe-7866-47a7-bce5-9c7b1047964e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction:\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"current prime minister of the UK\"\n",
+      "}\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"current prime minister of the UK\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mBottom right: Rishi Sunak is the current prime minister and the first non-white prime minister. The prime minister of the United Kingdom is the principal minister of the crown of His Majesty's Government, and the head of the British Cabinet. 3 min. British Prime Minister Rishi Sunak asserted his stance on gender identity in a speech Wednesday, stating it was \"common sense\" that \"a man is a man and a woman is a woman\" — a ... The former chancellor Rishi Sunak is the UK's new prime minister. Here's what you need to know about him. He won after running for the second time this year He lost to Liz Truss in September,... Isaeli Prime Minister Benjamin Netanyahu spoke with US President Joe Biden on Wednesday, the prime minister's office said in a statement. Netanyahu \"thanked the President for the powerful words of ... By Yasmeen Serhan/London Updated: October 25, 2022 12:56 PM EDT | Originally published: October 24, 2022 9:17 AM EDT S top me if you've heard this one before: After a tumultuous period of political...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe search results indicate that Rishi Sunak is the current prime minister of the UK. However, it's important to note that this information may not be accurate or up to date.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"current age of the prime minister of the UK\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mHow old is Rishi Sunak? Mr Sunak was born on 12 May, 1980, making him 42 years old. He first became an MP in 2015, aged 34, and has served the constituency of Richmond in Yorkshire ever since. He... Prime Ministers' ages when they took office From oldest to youngest, the ages of the PMs were as follows: Winston Churchill - 65 years old James Callaghan - 64 years old Clement Attlee - 62 years... Anna Kaufman USA TODAY Just a few days after Liz Truss resigned as prime minister, the UK has a new prime minister. Truss, who lasted a mere 45 days in office, will be replaced by Rishi... Advertisement Rishi Sunak is the youngest British prime minister of modern times. Mr. Sunak is 42 and started out in Parliament in 2015. Rishi Sunak was appointed as chancellor of the Exchequer... The first prime minister of the current United Kingdom of Great Britain and Northern Ireland upon its effective creation in 1922 (when 26 Irish counties seceded and created the Irish Free State) was Bonar Law, [10] although the country was not renamed officially until 1927, when Stanley Baldwin was the serving prime minister. [11]\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mBased on the search results, it seems that Rishi Sunak is the current prime minister of the UK. However, I couldn't find any specific information about his age. Would you like me to search again for the current age of the prime minister?\n",
+      "\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"age of Rishi Sunak\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mRishi Sunak is 42 years old, making him the youngest person to hold the office of prime minister in modern times. How tall is Rishi Sunak? How Old Is Rishi Sunak? Rishi Sunak was born on May 12, 1980, in Southampton, England. Parents and Nationality Sunak's parents were born to Indian-origin families in East Africa before... Born on May 12, 1980, Rishi is currently 42 years old. He has been a member of parliament since 2015 where he was an MP for Richmond and has served in roles including Chief Secretary to the Treasury and the Chancellor of Exchequer while Boris Johnson was PM. Family Murty, 42, is the daughter of the Indian billionaire NR Narayana Murthy, often described as the Bill Gates of India, who founded the software company Infosys. According to reports, his... Sunak became the first non-White person to lead the country and, at age 42, the youngest to take on the role in more than a century. Like most politicians, Sunak is revered by some and...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mBased on the search results, Rishi Sunak is currently 42 years old. He was born on May 12, 1980.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: To calculate the age raised to the power of 0.43, I can use the calculator tool.\n",
+      "\n",
+      "Action:\n",
+      "```json\n",
+      "{\n",
+      "  \"action\": \"Calculator\",\n",
+      "  \"action_input\": \"42^0.43\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
+      "42^0.43\u001b[32;1m\u001b[1;3m```text\n",
+      "42**0.43\n",
+      "```\n",
+      "...numexpr.evaluate(\"42**0.43\")...\n",
+      "\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m4.9888126515157\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.9888126515157\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe age raised to the power of 0.43 is approximately 4.9888126515157.\n",
+      "\n",
+      "Final Answer:\n",
+      "```json\n",
+      "{\n",
+      "  \"action\": \"Final Answer\",\n",
+      "  \"action_input\": \"The age raised to the power of 0.43 is approximately 4.9888126515157.\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Final Answer\",\n",
+      "  \"action_input\": \"The current prime minister of the UK is Rishi Sunak. His age raised to the power of 0.43 is approximately 4.9888126515157.\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The current prime minister of the UK is Rishi Sunak. His age raised to the power of 0.43 is approximately 4.9888126515157.'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"Who is the current prime minister of the UK? What is their current age raised to the 0.43 power?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0ef78a07-1a2a-46f8-9bc9-ae45f9bd706c",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "poetry-venv",
+   "language": "python",
+   "name": "poetry-venv"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

cookbook/sales_agent_with_context.ipynb

@@ -12,7 +12,7 @@
     "\n",
     "SalesGPT is context-aware, which means it can understand what section of a sales conversation it is in and act accordingly.\n",
     " \n",
-    "As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activites, such as outbound sales calls. \n",
+    "As such, this agent can have a natural sales conversation with a prospect and behaves based on the conversation stage. Hence, this notebook demonstrates how we can use AI to automate sales development representatives activities, such as outbound sales calls. \n",
     "\n",
     "Additionally, the AI Sales agent has access to tools, which allow it to interact with other systems.\n",
     "\n",
@@ -66,7 +66,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# install aditional dependencies\n",
+    "# install additional dependencies\n",
     "# ! pip install chromadb openai tiktoken"
    ]
   },
@@ -150,7 +150,7 @@
     "            {conversation_history}\n",
     "            ===\n",
     "\n",
-    "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
+    "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
     "            1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
     "            2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
     "            3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",
@@ -277,7 +277,7 @@
       "            \n",
       "            ===\n",
       "\n",
-      "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting ony from the following options:\n",
+      "            Now determine what should be the next immediate conversation stage for the agent in the sales conversation by selecting only from the following options:\n",
       "            1. Introduction: Start the conversation by introducing yourself and your company. Be polite and respectful while keeping the tone of the conversation professional.\n",
       "            2. Qualification: Qualify the prospect by confirming if they are the right person to talk to regarding your product/service. Ensure that they have the authority to make purchasing decisions.\n",
       "            3. Value proposition: Briefly explain how your product/service can benefit the prospect. Focus on the unique selling points and value proposition of your product/service that sets it apart from competitors.\n",

cookbook/smart_llm.ipynb

@@ -17,7 +17,7 @@
     "\n",
     "Note that SmartLLMChains\n",
     "- use more LLM passes (ie n+2 instead of just 1)\n",
-    "- only work then the underlying LLM has the capability for reflection, whicher smaller models often don't\n",
+    "- only work then the underlying LLM has the capability for reflection, which smaller models often don't\n",
     "- only work with underlying models that return exactly 1 output, not multiple\n",
     "\n",
     "This notebook demonstrates how to use a SmartLLMChain."
@@ -241,7 +241,7 @@
     "    ideation_llm=ChatOpenAI(temperature=0.9, model_name=\"gpt-4\"),\n",
     "    llm=ChatOpenAI(\n",
     "        temperature=0, model_name=\"gpt-4\"\n",
-    "    ),  # will be used for critqiue and resolution as no specific llms are given\n",
+    "    ),  # will be used for critique and resolution as no specific llms are given\n",
     "    prompt=prompt,\n",
     "    n_ideas=3,\n",
     "    verbose=True,\n",

cookbook/sql_db_qa.mdx

@@ -1,3 +1,7 @@
+# SQL Database Chain
+
+This example demonstrates the use of the `SQLDatabaseChain` for answering questions over a SQL database.
+
 Under the hood, LangChain uses SQLAlchemy to connect to SQL databases. The `SQLDatabaseChain` can therefore be used with any SQL dialect supported by SQLAlchemy, such as MS SQL, MySQL, MariaDB, PostgreSQL, Oracle SQL, [Databricks](/docs/ecosystem/integrations/databricks.html) and SQLite. Please refer to the SQLAlchemy documentation for more information about requirements for connecting to your database. For example, a connection to MySQL requires an appropriate connector such as PyMySQL. A URI for a MySQL connection might look like: `mysql+pymysql://user:pass@some_mysql_db_address/db_name`.
 
 This demonstration uses SQLite and the example Chinook database.
@@ -31,8 +35,8 @@ db_chain.run("How many employees are there?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many employees are there?
     SQLQuery:
@@ -71,8 +75,8 @@ db_chain.run("How many albums by Aerosmith?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many albums by Aerosmith?
     SQLQuery:SELECT COUNT(*) FROM Album WHERE ArtistId = 3;
@@ -129,8 +133,8 @@ db_chain.run("How many employees are there in the foobar table?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many employees are there in the foobar table?
     SQLQuery:SELECT COUNT(*) FROM Employee;
@@ -165,8 +169,8 @@ result["intermediate_steps"]
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many employees are there in the foobar table?
     SQLQuery:SELECT COUNT(*) FROM Employee;
@@ -313,8 +317,8 @@ db_chain.run("What are some example tracks by composer Johann Sebastian Bach?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     What are some example tracks by composer Johann Sebastian Bach?
     SQLQuery:SELECT Name FROM Track WHERE Composer = 'Johann Sebastian Bach' LIMIT 3
@@ -352,23 +356,23 @@ print(db.table_info)
 <CodeOutputBlock lang="python">
 
 ```
-    
+
     CREATE TABLE "Track" (
-    	"TrackId" INTEGER NOT NULL, 
-    	"Name" NVARCHAR(200) NOT NULL, 
-    	"AlbumId" INTEGER, 
-    	"MediaTypeId" INTEGER NOT NULL, 
-    	"GenreId" INTEGER, 
-    	"Composer" NVARCHAR(220), 
-    	"Milliseconds" INTEGER NOT NULL, 
-    	"Bytes" INTEGER, 
-    	"UnitPrice" NUMERIC(10, 2) NOT NULL, 
-    	PRIMARY KEY ("TrackId"), 
-    	FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"), 
-    	FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"), 
+    	"TrackId" INTEGER NOT NULL,
+    	"Name" NVARCHAR(200) NOT NULL,
+    	"AlbumId" INTEGER,
+    	"MediaTypeId" INTEGER NOT NULL,
+    	"GenreId" INTEGER,
+    	"Composer" NVARCHAR(220),
+    	"Milliseconds" INTEGER NOT NULL,
+    	"Bytes" INTEGER,
+    	"UnitPrice" NUMERIC(10, 2) NOT NULL,
+    	PRIMARY KEY ("TrackId"),
+    	FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
+    	FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
     	FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
     )
-    
+
     /*
     2 rows from Track table:
     TrackId	Name	AlbumId	MediaTypeId	GenreId	Composer	Milliseconds	Bytes	UnitPrice
@@ -392,8 +396,8 @@ db_chain.run("What are some example tracks by Bach?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     What are some example tracks by Bach?
     SQLQuery:SELECT "Name", "Composer" FROM "Track" WHERE "Composer" LIKE '%Bach%' LIMIT 5
@@ -411,7 +415,7 @@ db_chain.run("What are some example tracks by Bach?")
 </CodeOutputBlock>
 
 ### Custom Table Info
-In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first `sample_rows_in_table_info` sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns. 
+In some cases, it can be useful to provide custom table information instead of using the automatically generated table definitions and the first `sample_rows_in_table_info` sample rows. For example, if you know that the first few rows of a table are uninformative, it could help to manually provide example rows that are more diverse or provide more information to the model. It is also possible to limit the columns that will be visible to the model if there are unnecessary columns.
 
 This information can be provided as a dictionary with table names as the keys and table information as the values. For example, let's provide a custom definition and sample rows for the Track table with only a few columns:
 
@@ -419,7 +423,7 @@ This information can be provided as a dictionary with table names as the keys an
 ```python
 custom_table_info = {
     "Track": """CREATE TABLE Track (
-	"TrackId" INTEGER NOT NULL, 
+	"TrackId" INTEGER NOT NULL,
 	"Name" NVARCHAR(200) NOT NULL,
 	"Composer" NVARCHAR(220),
 	PRIMARY KEY ("TrackId")
@@ -448,22 +452,22 @@ print(db.table_info)
 <CodeOutputBlock lang="python">
 
 ```
-    
+
     CREATE TABLE "Playlist" (
-    	"PlaylistId" INTEGER NOT NULL, 
-    	"Name" NVARCHAR(120), 
+    	"PlaylistId" INTEGER NOT NULL,
+    	"Name" NVARCHAR(120),
     	PRIMARY KEY ("PlaylistId")
     )
-    
+
     /*
     2 rows from Playlist table:
     PlaylistId	Name
     1	Music
     2	Movies
     */
-    
+
     CREATE TABLE Track (
-    	"TrackId" INTEGER NOT NULL, 
+    	"TrackId" INTEGER NOT NULL,
     	"Name" NVARCHAR(200) NOT NULL,
     	"Composer" NVARCHAR(220),
     	PRIMARY KEY ("TrackId")
@@ -490,8 +494,8 @@ db_chain.run("What are some example tracks by Bach?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     What are some example tracks by Bach?
     SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
@@ -501,31 +505,31 @@ db_chain.run("What are some example tracks by Bach?")
     Unless the user specifies in the question a specific number of examples to obtain, query for at most 5 results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.
     Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
     Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
-    
+
     Use the following format:
-    
+
     Question: "Question here"
     SQLQuery: "SQL Query to run"
     SQLResult: "Result of the SQLQuery"
     Answer: "Final answer here"
-    
+
     Only use the following tables:
-    
+
     CREATE TABLE "Playlist" (
-    	"PlaylistId" INTEGER NOT NULL, 
-    	"Name" NVARCHAR(120), 
+    	"PlaylistId" INTEGER NOT NULL,
+    	"Name" NVARCHAR(120),
     	PRIMARY KEY ("PlaylistId")
     )
-    
+
     /*
     2 rows from Playlist table:
     PlaylistId	Name
     1	Music
     2	Movies
     */
-    
+
     CREATE TABLE Track (
-    	"TrackId" INTEGER NOT NULL, 
+    	"TrackId" INTEGER NOT NULL,
     	"Name" NVARCHAR(200) NOT NULL,
     	"Composer" NVARCHAR(220),
     	PRIMARY KEY ("TrackId")
@@ -537,7 +541,7 @@ db_chain.run("What are some example tracks by Bach?")
     2	Balls to the Wall	None
     3	My favorite song ever	The coolest composer of all time
     */
-    
+
     Question: What are some example tracks by Bach?
     SQLQuery:SELECT "Name" FROM Track WHERE "Composer" LIKE '%Bach%' LIMIT 5;
     SQLResult: [('American Woman',), ('Concerto for 2 Violins in D Minor, BWV 1043: I. Vivace',), ('Aria Mit 30 Veränderungen, BWV 988 "Goldberg Variations": Aria',), ('Suite for Solo Cello No. 1 in G Major, BWV 1007: I. Prélude',), ('Toccata and Fugue in D Minor, BWV 565: I. Toccata',)]
@@ -557,7 +561,7 @@ db_chain.run("What are some example tracks by Bach?")
 
 ### SQL Views
 
-In some case, the table schema can be hidden behind a JSON or JSONB column. Adding row samples into the prompt might help won't always describe the data perfectly. 
+In some case, the table schema can be hidden behind a JSON or JSONB column. Adding row samples into the prompt might help won't always describe the data perfectly.
 
 For this reason, a custom SQL views can help.
 
@@ -609,19 +613,19 @@ chain.run("How many employees are also customers?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseSequentialChain chain...
     Table names to use:
     ['Employee', 'Customer']
-    
+
     > Entering new SQLDatabaseChain chain...
     How many employees are also customers?
     SQLQuery:SELECT COUNT(*) FROM Employee e INNER JOIN Customer c ON e.EmployeeId = c.SupportRepId;
     SQLResult: [(59,)]
     Answer:59 employees are also customers.
     > Finished chain.
-    
+
     > Finished chain.
 
 
@@ -692,8 +696,8 @@ local_chain("How many customers are there?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many customers are there?
     SQLQuery:
@@ -879,8 +883,8 @@ print("\n" + yaml_example)
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     List all the customer first names that start with 'a'
     SQLQuery:
@@ -900,7 +904,7 @@ print("\n" + yaml_example)
     [('François', 'Frantiek', 'Helena', 'Astrid', 'Daan', 'Kara', 'Eduardo', 'Alexandre', 'Fernanda', 'Mark', 'Frank', 'Jack', 'Dan', 'Kathy', 'Heather', 'Frank', 'Richard', 'Patrick', 'Julia', 'Edward', 'Martha', 'Aaron', 'Madalena', 'Hannah', 'Niklas', 'Camille', 'Marc', 'Wyatt', 'Isabelle', 'Ladislav', 'Lucas', 'Johannes', 'Stanisaw', 'Joakim', 'Emma', 'Mark', 'Manoj', 'Puja']
     > Finished chain.
     *** Query succeeded
-    
+
     answer: '[(''François'', ''Frantiek'', ''Helena'', ''Astrid'', ''Daan'', ''Kara'',
       ''Eduardo'', ''Alexandre'', ''Fernanda'', ''Mark'', ''Frank'', ''Jack'', ''Dan'',
       ''Kathy'', ''Heather'', ''Frank'', ''Richard'', ''Patrick'', ''Julia'', ''Edward'',
@@ -931,7 +935,7 @@ print("\n" + yaml_example)
       None\tGermany\t70174\t+49 0711 2842222\tNone\tleonekohler@surfeu.de\t5\n3\tFrançois\t\
       Tremblay\tNone\t1498 rue Bélanger\tMontréal\tQC\tCanada\tH2G 1A7\t+1 (514) 721-4711\t\
       None\tftremblay@gmail.com\t3\n*/"
-    
+
 ```
 
 </CodeOutputBlock>
@@ -944,20 +948,20 @@ YAML_EXAMPLES = """
 - input: How many customers are not from Brazil?
   table_info: |
     CREATE TABLE "Customer" (
-      "CustomerId" INTEGER NOT NULL, 
-      "FirstName" NVARCHAR(40) NOT NULL, 
-      "LastName" NVARCHAR(20) NOT NULL, 
-      "Company" NVARCHAR(80), 
-      "Address" NVARCHAR(70), 
-      "City" NVARCHAR(40), 
-      "State" NVARCHAR(40), 
-      "Country" NVARCHAR(40), 
-      "PostalCode" NVARCHAR(10), 
-      "Phone" NVARCHAR(24), 
-      "Fax" NVARCHAR(24), 
-      "Email" NVARCHAR(60) NOT NULL, 
-      "SupportRepId" INTEGER, 
-      PRIMARY KEY ("CustomerId"), 
+      "CustomerId" INTEGER NOT NULL,
+      "FirstName" NVARCHAR(40) NOT NULL,
+      "LastName" NVARCHAR(20) NOT NULL,
+      "Company" NVARCHAR(80),
+      "Address" NVARCHAR(70),
+      "City" NVARCHAR(40),
+      "State" NVARCHAR(40),
+      "Country" NVARCHAR(40),
+      "PostalCode" NVARCHAR(10),
+      "Phone" NVARCHAR(24),
+      "Fax" NVARCHAR(24),
+      "Email" NVARCHAR(60) NOT NULL,
+      "SupportRepId" INTEGER,
+      PRIMARY KEY ("CustomerId"),
       FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
     )
   sql_cmd: SELECT COUNT(*) FROM "Customer" WHERE NOT "Country" = "Brazil";
@@ -966,8 +970,8 @@ YAML_EXAMPLES = """
 - input: list all the genres that start with 'r'
   table_info: |
     CREATE TABLE "Genre" (
-      "GenreId" INTEGER NOT NULL, 
-      "Name" NVARCHAR(120), 
+      "GenreId" INTEGER NOT NULL,
+      "Name" NVARCHAR(120),
       PRIMARY KEY ("GenreId")
     )
 
@@ -980,7 +984,7 @@ YAML_EXAMPLES = """
     */
   sql_cmd: SELECT "Name" FROM "Genre" WHERE "Name" LIKE 'r%';
   sql_result: "[('Rock',), ('Rock and Roll',), ('Reggae',), ('R&B/Soul',)]"
-  answer: The genres that start with 'r' are Rock, Rock and Roll, Reggae and R&B/Soul. 
+  answer: The genres that start with 'r' are Rock, Rock and Roll, Reggae and R&B/Soul.
 """
 ```
 
@@ -1046,8 +1050,8 @@ result = local_chain("How many customers are from Brazil?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many customers are from Brazil?
     SQLQuery:SELECT count(*) FROM Customer WHERE Country = "Brazil";
@@ -1066,8 +1070,8 @@ result = local_chain("How many customers are not from Brazil?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many customers are not from Brazil?
     SQLQuery:SELECT count(*) FROM customer WHERE country NOT IN (SELECT country FROM customer WHERE country = 'Brazil')
@@ -1086,8 +1090,8 @@ result = local_chain("How many customers are there in total?")
 <CodeOutputBlock lang="python">
 
 ```
-    
-    
+
+
     > Entering new SQLDatabaseChain chain...
     How many customers are there in total?
     SQLQuery:SELECT count(*) FROM Customer;

docker/Dockerfile.base

@@ -1,3 +1,3 @@
-FROM python:latest
+FROM python:3.11
 
 RUN pip install langchain

docs/.local_build.sh

@@ -8,10 +8,11 @@ set -o xtrace
 SCRIPT_DIR="$(cd "$(dirname "$0")"; pwd)"
 cd "${SCRIPT_DIR}"
 
-mkdir -p _dist/docs_skeleton
-cp -r {docs_skeleton,snippets} _dist
-cd _dist/docs_skeleton
-poetry run nbdoc_build
-poetry run python generate_api_reference_links.py
+mkdir -p ../_dist
+cp -r . ../_dist
+cd ../_dist
+poetry run python scripts/model_feat_table.py
+poetry run nbdoc_build --srcdir docs
+poetry run python scripts/generate_api_reference_links.py
 yarn install
 yarn start

docs/README.md

@@ -42,7 +42,7 @@ If you are using GitHub pages for hosting, this command is a convenient way to b
 
 ### Continuous Integration
 
-Some common defaults for linting/formatting have been set for you. If you integrate your project with an open source Continuous Integration system (e.g. Travis CI, CircleCI), you may check for issues using the following command.
+Some common defaults for linting/formatting have been set for you. If you integrate your project with an open-source Continuous Integration system (e.g. Travis CI, CircleCI), you may check for issues using the following command.
 
 ```
 $ yarn ci

docs/api_reference/create_api_rst.py

@@ -122,8 +122,7 @@ def _merge_module_members(
 
 
 def _load_package_modules(
-    package_directory: Union[str, Path],
-    submodule: Optional[str] = None
+    package_directory: Union[str, Path], submodule: Optional[str] = None
 ) -> Dict[str, ModuleMembers]:
     """Recursively load modules of a package based on the file system.
 
@@ -171,7 +170,8 @@ def _load_package_modules(
             # different way
             if submodule is not None:
                 module_members = _load_module_members(
-                    f"{package_name}.{submodule}.{namespace}", f"{submodule}.{namespace}"
+                    f"{package_name}.{submodule}.{namespace}",
+                    f"{submodule}.{namespace}",
                 )
             else:
                 module_members = _load_module_members(
@@ -280,18 +280,9 @@ Functions
     return full_doc
 
 
-def main() -> None:
-    """Generate the reference.rst file for each package."""
-    lc_members = _load_package_modules(PKG_DIR)
-    # Put some packages at top level
-    tools = _load_package_modules(PKG_DIR, "tools")
-    lc_members['tools.render'] = tools['render']
-    agents = _load_package_modules(PKG_DIR, "agents")
-    lc_members['agents.output_parsers'] = agents['output_parsers']
-    lc_members['agents.format_scratchpad'] = agents['format_scratchpad']
-    lc_doc = ".. _api_reference:\n\n" + _construct_doc("langchain", lc_members)
-    with open(WRITE_FILE, "w") as f:
-        f.write(lc_doc)
+def _document_langchain_experimental() -> None:
+    """Document the langchain_experimental package."""
+    # Generate experimental_api_reference.rst
     exp_members = _load_package_modules(EXP_DIR)
     exp_doc = ".. _experimental_api_reference:\n\n" + _construct_doc(
         "langchain_experimental", exp_members
@@ -300,5 +291,36 @@ def main() -> None:
         f.write(exp_doc)
 
 
+def _document_langchain_core() -> None:
+    """Document the main langchain package."""
+    # load top level module members
+    lc_members = _load_package_modules(PKG_DIR)
+
+    # Add additional packages
+    tools = _load_package_modules(PKG_DIR, "tools")
+    agents = _load_package_modules(PKG_DIR, "agents")
+    schema = _load_package_modules(PKG_DIR, "schema")
+
+    lc_members.update(
+        {
+            "agents.output_parsers": agents["output_parsers"],
+            "agents.format_scratchpad": agents["format_scratchpad"],
+            "tools.render": tools["render"],
+            "schema.runnable": schema["runnable"],
+        }
+    )
+
+    lc_doc = ".. _api_reference:\n\n" + _construct_doc("langchain", lc_members)
+
+    with open(WRITE_FILE, "w") as f:
+        f.write(lc_doc)
+
+
+def main() -> None:
+    """Generate the reference.rst file for each package."""
+    _document_langchain_core()
+    _document_langchain_experimental()
+
+
 if __name__ == "__main__":
     main()

docs/docs/additional_resources/dependents.mdx

@@ -0,0 +1,465 @@
+# Dependents
+
+Dependents stats for `langchain-ai/langchain`
+
+[![](https://img.shields.io/static/v1?label=Used%20by&message=30534&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(public)&message=451&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(private)&message=30083&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(stars)&message=37822&color=informational&logo=slickpic)](https://github.com/langchain-ai/langchain/network/dependents)
+
+
+[update: `2023-10-06`; only dependent repositories with Stars > 100]
+
+
+| Repository | Stars  |
+| :--------  | -----: |
+|[openai/openai-cookbook](https://github.com/openai/openai-cookbook) | 49006 |
+|[AntonOsika/gpt-engineer](https://github.com/AntonOsika/gpt-engineer) | 44368 |
+|[imartinez/privateGPT](https://github.com/imartinez/privateGPT) | 38300 |
+|[LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) | 35327 |
+|[hpcaitech/ColossalAI](https://github.com/hpcaitech/ColossalAI) | 34799 |
+|[microsoft/TaskMatrix](https://github.com/microsoft/TaskMatrix) | 34161 |
+|[streamlit/streamlit](https://github.com/streamlit/streamlit) | 27697 |
+|[geekan/MetaGPT](https://github.com/geekan/MetaGPT) | 27302 |
+|[reworkd/AgentGPT](https://github.com/reworkd/AgentGPT) | 26805 |
+|[OpenBB-finance/OpenBBTerminal](https://github.com/OpenBB-finance/OpenBBTerminal) | 24473 |
+|[StanGirard/quivr](https://github.com/StanGirard/quivr) | 23323 |
+|[run-llama/llama_index](https://github.com/run-llama/llama_index) | 22151 |
+|[openai/chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) | 19741 |
+|[mindsdb/mindsdb](https://github.com/mindsdb/mindsdb) | 18062 |
+|[PromtEngineer/localGPT](https://github.com/PromtEngineer/localGPT) | 16413 |
+|[chatchat-space/Langchain-Chatchat](https://github.com/chatchat-space/Langchain-Chatchat) | 16300 |
+|[cube-js/cube](https://github.com/cube-js/cube) | 16261 |
+|[mlflow/mlflow](https://github.com/mlflow/mlflow) | 15487 |
+|[logspace-ai/langflow](https://github.com/logspace-ai/langflow) | 12599 |
+|[GaiZhenbiao/ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT) | 12501 |
+|[openai/evals](https://github.com/openai/evals) | 12056 |
+|[airbytehq/airbyte](https://github.com/airbytehq/airbyte) | 11919 |
+|[go-skynet/LocalAI](https://github.com/go-skynet/LocalAI) | 11767 |
+|[databrickslabs/dolly](https://github.com/databrickslabs/dolly) | 10609 |
+|[AIGC-Audio/AudioGPT](https://github.com/AIGC-Audio/AudioGPT) | 9240 |
+|[aws/amazon-sagemaker-examples](https://github.com/aws/amazon-sagemaker-examples) | 8892 |
+|[langgenius/dify](https://github.com/langgenius/dify) | 8764 |
+|[gventuri/pandas-ai](https://github.com/gventuri/pandas-ai) | 8687 |
+|[jmorganca/ollama](https://github.com/jmorganca/ollama) | 8628 |
+|[langchain-ai/langchainjs](https://github.com/langchain-ai/langchainjs) | 8392 |
+|[h2oai/h2ogpt](https://github.com/h2oai/h2ogpt) | 7953 |
+|[arc53/DocsGPT](https://github.com/arc53/DocsGPT) | 7730 |
+|[PipedreamHQ/pipedream](https://github.com/PipedreamHQ/pipedream) | 7261 |
+|[joshpxyne/gpt-migrate](https://github.com/joshpxyne/gpt-migrate) | 6349 |
+|[bentoml/OpenLLM](https://github.com/bentoml/OpenLLM) | 6213 |
+|[mage-ai/mage-ai](https://github.com/mage-ai/mage-ai) | 5600 |
+|[zauberzeug/nicegui](https://github.com/zauberzeug/nicegui) | 5499 |
+|[wenda-LLM/wenda](https://github.com/wenda-LLM/wenda) | 5497 |
+|[sweepai/sweep](https://github.com/sweepai/sweep) | 5489 |
+|[embedchain/embedchain](https://github.com/embedchain/embedchain) | 5428 |
+|[zilliztech/GPTCache](https://github.com/zilliztech/GPTCache) | 5311 |
+|[Shaunwei/RealChar](https://github.com/Shaunwei/RealChar) | 5264 |
+|[GreyDGL/PentestGPT](https://github.com/GreyDGL/PentestGPT) | 5146 |
+|[gkamradt/langchain-tutorials](https://github.com/gkamradt/langchain-tutorials) | 5134 |
+|[serge-chat/serge](https://github.com/serge-chat/serge) | 5009 |
+|[assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher) | 4836 |
+|[openchatai/OpenChat](https://github.com/openchatai/OpenChat) | 4697 |
+|[intel-analytics/BigDL](https://github.com/intel-analytics/BigDL) | 4412 |
+|[continuedev/continue](https://github.com/continuedev/continue) | 4324 |
+|[postgresml/postgresml](https://github.com/postgresml/postgresml) | 4267 |
+|[madawei2699/myGPTReader](https://github.com/madawei2699/myGPTReader) | 4214 |
+|[MineDojo/Voyager](https://github.com/MineDojo/Voyager) | 4204 |
+|[danswer-ai/danswer](https://github.com/danswer-ai/danswer) | 3973 |
+|[RayVentura/ShortGPT](https://github.com/RayVentura/ShortGPT) | 3922 |
+|[Azure/azure-sdk-for-python](https://github.com/Azure/azure-sdk-for-python) | 3849 |
+|[khoj-ai/khoj](https://github.com/khoj-ai/khoj) | 3817 |
+|[langchain-ai/chat-langchain](https://github.com/langchain-ai/chat-langchain) | 3742 |
+|[Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo) | 3731 |
+|[marqo-ai/marqo](https://github.com/marqo-ai/marqo) | 3627 |
+|[kyegomez/tree-of-thoughts](https://github.com/kyegomez/tree-of-thoughts) | 3553 |
+|[llm-workflow-engine/llm-workflow-engine](https://github.com/llm-workflow-engine/llm-workflow-engine) | 3483 |
+|[PrefectHQ/marvin](https://github.com/PrefectHQ/marvin) | 3460 |
+|[aiwaves-cn/agents](https://github.com/aiwaves-cn/agents) | 3413 |
+|[OpenBMB/ToolBench](https://github.com/OpenBMB/ToolBench) | 3388 |
+|[shroominic/codeinterpreter-api](https://github.com/shroominic/codeinterpreter-api) | 3218 |
+|[whitead/paper-qa](https://github.com/whitead/paper-qa) | 3085 |
+|[project-baize/baize-chatbot](https://github.com/project-baize/baize-chatbot) | 3039 |
+|[OpenGVLab/InternGPT](https://github.com/OpenGVLab/InternGPT) | 2911 |
+|[ParisNeo/lollms-webui](https://github.com/ParisNeo/lollms-webui) | 2907 |
+|[Unstructured-IO/unstructured](https://github.com/Unstructured-IO/unstructured) | 2874 |
+|[openchatai/OpenCopilot](https://github.com/openchatai/OpenCopilot) | 2759 |
+|[OpenBMB/BMTools](https://github.com/OpenBMB/BMTools) | 2657 |
+|[homanp/superagent](https://github.com/homanp/superagent) | 2624 |
+|[SamurAIGPT/EmbedAI](https://github.com/SamurAIGPT/EmbedAI) | 2575 |
+|[GerevAI/gerev](https://github.com/GerevAI/gerev) | 2488 |
+|[microsoft/promptflow](https://github.com/microsoft/promptflow) | 2475 |
+|[OpenBMB/AgentVerse](https://github.com/OpenBMB/AgentVerse) | 2445 |
+|[Mintplex-Labs/anything-llm](https://github.com/Mintplex-Labs/anything-llm) | 2434 |
+|[emptycrown/llama-hub](https://github.com/emptycrown/llama-hub) | 2432 |
+|[NVIDIA/NeMo-Guardrails](https://github.com/NVIDIA/NeMo-Guardrails) | 2327 |
+|[ShreyaR/guardrails](https://github.com/ShreyaR/guardrails) | 2307 |
+|[thomas-yanxin/LangChain-ChatGLM-Webui](https://github.com/thomas-yanxin/LangChain-ChatGLM-Webui) | 2305 |
+|[yanqiangmiffy/Chinese-LangChain](https://github.com/yanqiangmiffy/Chinese-LangChain) | 2291 |
+|[keephq/keep](https://github.com/keephq/keep) | 2252 |
+|[OpenGVLab/Ask-Anything](https://github.com/OpenGVLab/Ask-Anything) | 2194 |
+|[IntelligenzaArtificiale/Free-Auto-GPT](https://github.com/IntelligenzaArtificiale/Free-Auto-GPT) | 2169 |
+|[Farama-Foundation/PettingZoo](https://github.com/Farama-Foundation/PettingZoo) | 2031 |
+|[YiVal/YiVal](https://github.com/YiVal/YiVal) | 2014 |
+|[hwchase17/notion-qa](https://github.com/hwchase17/notion-qa) | 2014 |
+|[jupyterlab/jupyter-ai](https://github.com/jupyterlab/jupyter-ai) | 1977 |
+|[paulpierre/RasaGPT](https://github.com/paulpierre/RasaGPT) | 1887 |
+|[dot-agent/dotagent-WIP](https://github.com/dot-agent/dotagent-WIP) | 1812 |
+|[hegelai/prompttools](https://github.com/hegelai/prompttools) | 1775 |
+|[vocodedev/vocode-python](https://github.com/vocodedev/vocode-python) | 1734 |
+|[Vonng/pigsty](https://github.com/Vonng/pigsty) | 1693 |
+|[psychic-api/psychic](https://github.com/psychic-api/psychic) | 1597 |
+|[avinashkranjan/Amazing-Python-Scripts](https://github.com/avinashkranjan/Amazing-Python-Scripts) | 1546 |
+|[pinterest/querybook](https://github.com/pinterest/querybook) | 1539 |
+|[Forethought-Technologies/AutoChain](https://github.com/Forethought-Technologies/AutoChain) | 1531 |
+|[Kav-K/GPTDiscord](https://github.com/Kav-K/GPTDiscord) | 1503 |
+|[jina-ai/langchain-serve](https://github.com/jina-ai/langchain-serve) | 1487 |
+|[noahshinn024/reflexion](https://github.com/noahshinn024/reflexion) | 1481 |
+|[jina-ai/dev-gpt](https://github.com/jina-ai/dev-gpt) | 1436 |
+|[ttengwang/Caption-Anything](https://github.com/ttengwang/Caption-Anything) | 1425 |
+|[milvus-io/bootcamp](https://github.com/milvus-io/bootcamp) | 1420 |
+|[agiresearch/OpenAGI](https://github.com/agiresearch/OpenAGI) | 1401 |
+|[greshake/llm-security](https://github.com/greshake/llm-security) | 1381 |
+|[jina-ai/thinkgpt](https://github.com/jina-ai/thinkgpt) | 1366 |
+|[lunasec-io/lunasec](https://github.com/lunasec-io/lunasec) | 1352 |
+|[101dotxyz/GPTeam](https://github.com/101dotxyz/GPTeam) | 1339 |
+|[refuel-ai/autolabel](https://github.com/refuel-ai/autolabel) | 1320 |
+|[melih-unsal/DemoGPT](https://github.com/melih-unsal/DemoGPT) | 1320 |
+|[mmz-001/knowledge_gpt](https://github.com/mmz-001/knowledge_gpt) | 1320 |
+|[richardyc/Chrome-GPT](https://github.com/richardyc/Chrome-GPT) | 1315 |
+|[run-llama/sec-insights](https://github.com/run-llama/sec-insights) | 1312 |
+|[Azure/azureml-examples](https://github.com/Azure/azureml-examples) | 1305 |
+|[cofactoryai/textbase](https://github.com/cofactoryai/textbase) | 1286 |
+|[dataelement/bisheng](https://github.com/dataelement/bisheng) | 1273 |
+|[eyurtsev/kor](https://github.com/eyurtsev/kor) | 1263 |
+|[pluralsh/plural](https://github.com/pluralsh/plural) | 1188 |
+|[FlagOpen/FlagEmbedding](https://github.com/FlagOpen/FlagEmbedding) | 1184 |
+|[juncongmoo/chatllama](https://github.com/juncongmoo/chatllama) | 1144 |
+|[poe-platform/server-bot-quick-start](https://github.com/poe-platform/server-bot-quick-start) | 1139 |
+|[visual-openllm/visual-openllm](https://github.com/visual-openllm/visual-openllm) | 1137 |
+|[griptape-ai/griptape](https://github.com/griptape-ai/griptape) | 1124 |
+|[microsoft/X-Decoder](https://github.com/microsoft/X-Decoder) | 1119 |
+|[ThousandBirdsInc/chidori](https://github.com/ThousandBirdsInc/chidori) | 1116 |
+|[filip-michalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) | 1112 |
+|[psychic-api/rag-stack](https://github.com/psychic-api/rag-stack) | 1110 |
+|[irgolic/AutoPR](https://github.com/irgolic/AutoPR) | 1100 |
+|[promptfoo/promptfoo](https://github.com/promptfoo/promptfoo) | 1099 |
+|[nod-ai/SHARK](https://github.com/nod-ai/SHARK) | 1062 |
+|[SamurAIGPT/Camel-AutoGPT](https://github.com/SamurAIGPT/Camel-AutoGPT) | 1036 |
+|[Farama-Foundation/chatarena](https://github.com/Farama-Foundation/chatarena) | 1020 |
+|[peterw/Chat-with-Github-Repo](https://github.com/peterw/Chat-with-Github-Repo) | 993 |
+|[jiran214/GPT-vup](https://github.com/jiran214/GPT-vup) | 967 |
+|[alejandro-ao/ask-multiple-pdfs](https://github.com/alejandro-ao/ask-multiple-pdfs) | 958 |
+|[run-llama/llama-lab](https://github.com/run-llama/llama-lab) | 953 |
+|[LC1332/Chat-Haruhi-Suzumiya](https://github.com/LC1332/Chat-Haruhi-Suzumiya) | 950 |
+|[rlancemartin/auto-evaluator](https://github.com/rlancemartin/auto-evaluator) | 927 |
+|[cheshire-cat-ai/core](https://github.com/cheshire-cat-ai/core) | 902 |
+|[Anil-matcha/ChatPDF](https://github.com/Anil-matcha/ChatPDF) | 894 |
+|[cirediatpl/FigmaChain](https://github.com/cirediatpl/FigmaChain) | 881 |
+|[seanpixel/Teenage-AGI](https://github.com/seanpixel/Teenage-AGI) | 876 |
+|[xusenlinzy/api-for-open-llm](https://github.com/xusenlinzy/api-for-open-llm) | 865 |
+|[ricklamers/shell-ai](https://github.com/ricklamers/shell-ai) | 864 |
+|[codeacme17/examor](https://github.com/codeacme17/examor) | 856 |
+|[corca-ai/EVAL](https://github.com/corca-ai/EVAL) | 836 |
+|[microsoft/Llama-2-Onnx](https://github.com/microsoft/Llama-2-Onnx) | 835 |
+|[explodinggradients/ragas](https://github.com/explodinggradients/ragas) | 833 |
+|[ajndkr/lanarky](https://github.com/ajndkr/lanarky) | 817 |
+|[kennethleungty/Llama-2-Open-Source-LLM-CPU-Inference](https://github.com/kennethleungty/Llama-2-Open-Source-LLM-CPU-Inference) | 814 |
+|[ray-project/llm-applications](https://github.com/ray-project/llm-applications) | 804 |
+|[hwchase17/chat-your-data](https://github.com/hwchase17/chat-your-data) | 801 |
+|[LambdaLabsML/examples](https://github.com/LambdaLabsML/examples) | 759 |
+|[kreneskyp/ix](https://github.com/kreneskyp/ix) | 758 |
+|[pyspark-ai/pyspark-ai](https://github.com/pyspark-ai/pyspark-ai) | 750 |
+|[billxbf/ReWOO](https://github.com/billxbf/ReWOO) | 746 |
+|[e-johnstonn/BriefGPT](https://github.com/e-johnstonn/BriefGPT) | 738 |
+|[akshata29/entaoai](https://github.com/akshata29/entaoai) | 733 |
+|[getmetal/motorhead](https://github.com/getmetal/motorhead) | 717 |
+|[ruoccofabrizio/azure-open-ai-embeddings-qna](https://github.com/ruoccofabrizio/azure-open-ai-embeddings-qna) | 712 |
+|[msoedov/langcorn](https://github.com/msoedov/langcorn) | 698 |
+|[Dataherald/dataherald](https://github.com/Dataherald/dataherald) | 684 |
+|[jondurbin/airoboros](https://github.com/jondurbin/airoboros) | 657 |
+|[Ikaros-521/AI-Vtuber](https://github.com/Ikaros-521/AI-Vtuber) | 651 |
+|[whyiyhw/chatgpt-wechat](https://github.com/whyiyhw/chatgpt-wechat) | 644 |
+|[langchain-ai/streamlit-agent](https://github.com/langchain-ai/streamlit-agent) | 637 |
+|[SamurAIGPT/ChatGPT-Developer-Plugins](https://github.com/SamurAIGPT/ChatGPT-Developer-Plugins) | 637 |
+|[OpenGenerativeAI/GenossGPT](https://github.com/OpenGenerativeAI/GenossGPT) | 632 |
+|[AILab-CVC/GPT4Tools](https://github.com/AILab-CVC/GPT4Tools) | 629 |
+|[langchain-ai/auto-evaluator](https://github.com/langchain-ai/auto-evaluator) | 614 |
+|[explosion/spacy-llm](https://github.com/explosion/spacy-llm) | 613 |
+|[alexanderatallah/window.ai](https://github.com/alexanderatallah/window.ai) | 607 |
+|[MiuLab/Taiwan-LLaMa](https://github.com/MiuLab/Taiwan-LLaMa) | 601 |
+|[microsoft/PodcastCopilot](https://github.com/microsoft/PodcastCopilot) | 600 |
+|[Dicklesworthstone/swiss_army_llama](https://github.com/Dicklesworthstone/swiss_army_llama) | 596 |
+|[NoDataFound/hackGPT](https://github.com/NoDataFound/hackGPT) | 596 |
+|[namuan/dr-doc-search](https://github.com/namuan/dr-doc-search) | 593 |
+|[amosjyng/langchain-visualizer](https://github.com/amosjyng/langchain-visualizer) | 582 |
+|[microsoft/sample-app-aoai-chatGPT](https://github.com/microsoft/sample-app-aoai-chatGPT) | 581 |
+|[yvann-hub/Robby-chatbot](https://github.com/yvann-hub/Robby-chatbot) | 581 |
+|[yeagerai/yeagerai-agent](https://github.com/yeagerai/yeagerai-agent) | 547 |
+|[tgscan-dev/tgscan](https://github.com/tgscan-dev/tgscan) | 533 |
+|[Azure-Samples/openai](https://github.com/Azure-Samples/openai) | 531 |
+|[plastic-labs/tutor-gpt](https://github.com/plastic-labs/tutor-gpt) | 531 |
+|[xuwenhao/geektime-ai-course](https://github.com/xuwenhao/geektime-ai-course) | 526 |
+|[michaelthwan/searchGPT](https://github.com/michaelthwan/searchGPT) | 526 |
+|[jonra1993/fastapi-alembic-sqlmodel-async](https://github.com/jonra1993/fastapi-alembic-sqlmodel-async) | 522 |
+|[jina-ai/agentchain](https://github.com/jina-ai/agentchain) | 519 |
+|[mckaywrigley/repo-chat](https://github.com/mckaywrigley/repo-chat) | 518 |
+|[modelscope/modelscope-agent](https://github.com/modelscope/modelscope-agent) | 512 |
+|[daveebbelaar/langchain-experiments](https://github.com/daveebbelaar/langchain-experiments) | 504 |
+|[freddyaboulton/gradio-tools](https://github.com/freddyaboulton/gradio-tools) | 497 |
+|[sidhq/Multi-GPT](https://github.com/sidhq/Multi-GPT) | 494 |
+|[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 489 |
+|[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 487 |
+|[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 483 |
+|[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 481 |
+|[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 474 |
+|[truera/trulens](https://github.com/truera/trulens) | 464 |
+|[marella/chatdocs](https://github.com/marella/chatdocs) | 459 |
+|[opencopilotdev/opencopilot](https://github.com/opencopilotdev/opencopilot) | 453 |
+|[poe-platform/poe-protocol](https://github.com/poe-platform/poe-protocol) | 444 |
+|[DataDog/dd-trace-py](https://github.com/DataDog/dd-trace-py) | 441 |
+|[logan-markewich/llama_index_starter_pack](https://github.com/logan-markewich/llama_index_starter_pack) | 441 |
+|[opentensor/bittensor](https://github.com/opentensor/bittensor) | 433 |
+|[DjangoPeng/openai-quickstart](https://github.com/DjangoPeng/openai-quickstart) | 425 |
+|[CarperAI/OpenELM](https://github.com/CarperAI/OpenELM) | 424 |
+|[daodao97/chatdoc](https://github.com/daodao97/chatdoc) | 423 |
+|[showlab/VLog](https://github.com/showlab/VLog) | 411 |
+|[Anil-matcha/Chatbase](https://github.com/Anil-matcha/Chatbase) | 402 |
+|[yakami129/VirtualWife](https://github.com/yakami129/VirtualWife) | 399 |
+|[wandb/weave](https://github.com/wandb/weave) | 399 |
+|[mtenenholtz/chat-twitter](https://github.com/mtenenholtz/chat-twitter) | 398 |
+|[LinkSoul-AI/AutoAgents](https://github.com/LinkSoul-AI/AutoAgents) | 397 |
+|[Agenta-AI/agenta](https://github.com/Agenta-AI/agenta) | 389 |
+|[huchenxucs/ChatDB](https://github.com/huchenxucs/ChatDB) | 386 |
+|[mallorbc/Finetune_LLMs](https://github.com/mallorbc/Finetune_LLMs) | 379 |
+|[junruxiong/IncarnaMind](https://github.com/junruxiong/IncarnaMind) | 372 |
+|[MagnivOrg/prompt-layer-library](https://github.com/MagnivOrg/prompt-layer-library) | 368 |
+|[mosaicml/examples](https://github.com/mosaicml/examples) | 366 |
+|[rsaryev/talk-codebase](https://github.com/rsaryev/talk-codebase) | 364 |
+|[morpheuslord/GPT_Vuln-analyzer](https://github.com/morpheuslord/GPT_Vuln-analyzer) | 362 |
+|[monarch-initiative/ontogpt](https://github.com/monarch-initiative/ontogpt) | 362 |
+|[JayZeeDesign/researcher-gpt](https://github.com/JayZeeDesign/researcher-gpt) | 361 |
+|[personoids/personoids-lite](https://github.com/personoids/personoids-lite) | 361 |
+|[intel/intel-extension-for-transformers](https://github.com/intel/intel-extension-for-transformers) | 357 |
+|[jerlendds/osintbuddy](https://github.com/jerlendds/osintbuddy) | 357 |
+|[steamship-packages/langchain-production-starter](https://github.com/steamship-packages/langchain-production-starter) | 356 |
+|[onlyphantom/llm-python](https://github.com/onlyphantom/llm-python) | 354 |
+|[Azure-Samples/miyagi](https://github.com/Azure-Samples/miyagi) | 340 |
+|[mrwadams/attackgen](https://github.com/mrwadams/attackgen) | 338 |
+|[rgomezcasas/dotfiles](https://github.com/rgomezcasas/dotfiles) | 337 |
+|[eosphoros-ai/DB-GPT-Hub](https://github.com/eosphoros-ai/DB-GPT-Hub) | 336 |
+|[andylokandy/gpt-4-search](https://github.com/andylokandy/gpt-4-search) | 335 |
+|[NimbleBoxAI/ChainFury](https://github.com/NimbleBoxAI/ChainFury) | 330 |
+|[momegas/megabots](https://github.com/momegas/megabots) | 329 |
+|[Nuggt-dev/Nuggt](https://github.com/Nuggt-dev/Nuggt) | 315 |
+|[itamargol/openai](https://github.com/itamargol/openai) | 315 |
+|[BlackHC/llm-strategy](https://github.com/BlackHC/llm-strategy) | 315 |
+|[aws-samples/aws-genai-llm-chatbot](https://github.com/aws-samples/aws-genai-llm-chatbot) | 312 |
+|[Cheems-Seminar/grounded-segment-any-parts](https://github.com/Cheems-Seminar/grounded-segment-any-parts) | 312 |
+|[preset-io/promptimize](https://github.com/preset-io/promptimize) | 311 |
+|[dgarnitz/vectorflow](https://github.com/dgarnitz/vectorflow) | 309 |
+|[langchain-ai/langsmith-cookbook](https://github.com/langchain-ai/langsmith-cookbook) | 309 |
+|[CambioML/pykoi](https://github.com/CambioML/pykoi) | 309 |
+|[wandb/edu](https://github.com/wandb/edu) | 301 |
+|[XzaiCloud/luna-ai](https://github.com/XzaiCloud/luna-ai) | 300 |
+|[liangwq/Chatglm_lora_multi-gpu](https://github.com/liangwq/Chatglm_lora_multi-gpu) | 294 |
+|[Haste171/langchain-chatbot](https://github.com/Haste171/langchain-chatbot) | 291 |
+|[sullivan-sean/chat-langchainjs](https://github.com/sullivan-sean/chat-langchainjs) | 286 |
+|[sugarforever/LangChain-Tutorials](https://github.com/sugarforever/LangChain-Tutorials) | 285 |
+|[facebookresearch/personal-timeline](https://github.com/facebookresearch/personal-timeline) | 283 |
+|[hnawaz007/pythondataanalysis](https://github.com/hnawaz007/pythondataanalysis) | 282 |
+|[yuanjie-ai/ChatLLM](https://github.com/yuanjie-ai/ChatLLM) | 280 |
+|[MetaGLM/FinGLM](https://github.com/MetaGLM/FinGLM) | 279 |
+|[JohnSnowLabs/langtest](https://github.com/JohnSnowLabs/langtest) | 277 |
+|[Em1tSan/NeuroGPT](https://github.com/Em1tSan/NeuroGPT) | 274 |
+|[Safiullah-Rahu/CSV-AI](https://github.com/Safiullah-Rahu/CSV-AI) | 274 |
+|[conceptofmind/toolformer](https://github.com/conceptofmind/toolformer) | 274 |
+|[airobotlab/KoChatGPT](https://github.com/airobotlab/KoChatGPT) | 266 |
+|[gia-guar/JARVIS-ChatGPT](https://github.com/gia-guar/JARVIS-ChatGPT) | 263 |
+|[Mintplex-Labs/vector-admin](https://github.com/Mintplex-Labs/vector-admin) | 262 |
+|[artitw/text2text](https://github.com/artitw/text2text) | 262 |
+|[kaarthik108/snowChat](https://github.com/kaarthik108/snowChat) | 261 |
+|[paolorechia/learn-langchain](https://github.com/paolorechia/learn-langchain) | 260 |
+|[shamspias/customizable-gpt-chatbot](https://github.com/shamspias/customizable-gpt-chatbot) | 260 |
+|[ur-whitelab/exmol](https://github.com/ur-whitelab/exmol) | 258 |
+|[hwchase17/chroma-langchain](https://github.com/hwchase17/chroma-langchain) | 257 |
+|[bborn/howdoi.ai](https://github.com/bborn/howdoi.ai) | 255 |
+|[ur-whitelab/chemcrow-public](https://github.com/ur-whitelab/chemcrow-public) | 253 |
+|[pablomarin/GPT-Azure-Search-Engine](https://github.com/pablomarin/GPT-Azure-Search-Engine) | 251 |
+|[gustavz/DataChad](https://github.com/gustavz/DataChad) | 249 |
+|[radi-cho/datasetGPT](https://github.com/radi-cho/datasetGPT) | 249 |
+|[ennucore/clippinator](https://github.com/ennucore/clippinator) | 247 |
+|[recalign/RecAlign](https://github.com/recalign/RecAlign) | 244 |
+|[lilacai/lilac](https://github.com/lilacai/lilac) | 243 |
+|[kaleido-lab/dolphin](https://github.com/kaleido-lab/dolphin) | 236 |
+|[iusztinpaul/hands-on-llms](https://github.com/iusztinpaul/hands-on-llms) | 233 |
+|[PradipNichite/Youtube-Tutorials](https://github.com/PradipNichite/Youtube-Tutorials) | 231 |
+|[shaman-ai/agent-actors](https://github.com/shaman-ai/agent-actors) | 231 |
+|[hwchase17/langchain-streamlit-template](https://github.com/hwchase17/langchain-streamlit-template) | 231 |
+|[yym68686/ChatGPT-Telegram-Bot](https://github.com/yym68686/ChatGPT-Telegram-Bot) | 226 |
+|[grumpyp/aixplora](https://github.com/grumpyp/aixplora) | 222 |
+|[su77ungr/CASALIOY](https://github.com/su77ungr/CASALIOY) | 222 |
+|[alvarosevilla95/autolang](https://github.com/alvarosevilla95/autolang) | 222 |
+|[arthur-ai/bench](https://github.com/arthur-ai/bench) | 220 |
+|[miaoshouai/miaoshouai-assistant](https://github.com/miaoshouai/miaoshouai-assistant) | 219 |
+|[AutoPackAI/beebot](https://github.com/AutoPackAI/beebot) | 217 |
+|[edreisMD/plugnplai](https://github.com/edreisMD/plugnplai) | 216 |
+|[nicknochnack/LangchainDocuments](https://github.com/nicknochnack/LangchainDocuments) | 214 |
+|[AkshitIreddy/Interactive-LLM-Powered-NPCs](https://github.com/AkshitIreddy/Interactive-LLM-Powered-NPCs) | 213 |
+|[SpecterOps/Nemesis](https://github.com/SpecterOps/Nemesis) | 210 |
+|[kyegomez/swarms](https://github.com/kyegomez/swarms) | 210 |
+|[wpydcr/LLM-Kit](https://github.com/wpydcr/LLM-Kit) | 208 |
+|[orgexyz/BlockAGI](https://github.com/orgexyz/BlockAGI) | 204 |
+|[Chainlit/cookbook](https://github.com/Chainlit/cookbook) | 202 |
+|[WongSaang/chatgpt-ui-server](https://github.com/WongSaang/chatgpt-ui-server) | 202 |
+|[jbrukh/gpt-jargon](https://github.com/jbrukh/gpt-jargon) | 202 |
+|[handrew/browserpilot](https://github.com/handrew/browserpilot) | 202 |
+|[langchain-ai/web-explorer](https://github.com/langchain-ai/web-explorer) | 200 |
+|[plchld/InsightFlow](https://github.com/plchld/InsightFlow) | 200 |
+|[alphasecio/langchain-examples](https://github.com/alphasecio/langchain-examples) | 199 |
+|[Gentopia-AI/Gentopia](https://github.com/Gentopia-AI/Gentopia) | 198 |
+|[SamPink/dev-gpt](https://github.com/SamPink/dev-gpt) | 196 |
+|[yasyf/compress-gpt](https://github.com/yasyf/compress-gpt) | 196 |
+|[benthecoder/ClassGPT](https://github.com/benthecoder/ClassGPT) | 195 |
+|[voxel51/voxelgpt](https://github.com/voxel51/voxelgpt) | 193 |
+|[CL-lau/SQL-GPT](https://github.com/CL-lau/SQL-GPT) | 192 |
+|[blob42/Instrukt](https://github.com/blob42/Instrukt) | 191 |
+|[streamlit/llm-examples](https://github.com/streamlit/llm-examples) | 191 |
+|[stepanogil/autonomous-hr-chatbot](https://github.com/stepanogil/autonomous-hr-chatbot) | 190 |
+|[TsinghuaDatabaseGroup/DB-GPT](https://github.com/TsinghuaDatabaseGroup/DB-GPT) | 189 |
+|[PJLab-ADG/DriveLikeAHuman](https://github.com/PJLab-ADG/DriveLikeAHuman) | 187 |
+|[Azure-Samples/azure-search-power-skills](https://github.com/Azure-Samples/azure-search-power-skills) | 187 |
+|[microsoft/azure-openai-in-a-day-workshop](https://github.com/microsoft/azure-openai-in-a-day-workshop) | 187 |
+|[ju-bezdek/langchain-decorators](https://github.com/ju-bezdek/langchain-decorators) | 182 |
+|[hardbyte/qabot](https://github.com/hardbyte/qabot) | 181 |
+|[hongbo-miao/hongbomiao.com](https://github.com/hongbo-miao/hongbomiao.com) | 180 |
+|[QwenLM/Qwen-Agent](https://github.com/QwenLM/Qwen-Agent) | 179 |
+|[showlab/UniVTG](https://github.com/showlab/UniVTG) | 179 |
+|[Azure-Samples/jp-azureopenai-samples](https://github.com/Azure-Samples/jp-azureopenai-samples) | 176 |
+|[afaqueumer/DocQA](https://github.com/afaqueumer/DocQA) | 174 |
+|[ethanyanjiali/minChatGPT](https://github.com/ethanyanjiali/minChatGPT) | 174 |
+|[shauryr/S2QA](https://github.com/shauryr/S2QA) | 174 |
+|[RoboCoachTechnologies/GPT-Synthesizer](https://github.com/RoboCoachTechnologies/GPT-Synthesizer) | 173 |
+|[chakkaradeep/pyCodeAGI](https://github.com/chakkaradeep/pyCodeAGI) | 172 |
+|[vaibkumr/prompt-optimizer](https://github.com/vaibkumr/prompt-optimizer) | 171 |
+|[ccurme/yolopandas](https://github.com/ccurme/yolopandas) | 170 |
+|[anarchy-ai/LLM-VM](https://github.com/anarchy-ai/LLM-VM) | 169 |
+|[ray-project/langchain-ray](https://github.com/ray-project/langchain-ray) | 169 |
+|[fengyuli-dev/multimedia-gpt](https://github.com/fengyuli-dev/multimedia-gpt) | 169 |
+|[ibiscp/LLM-IMDB](https://github.com/ibiscp/LLM-IMDB) | 168 |
+|[mayooear/private-chatbot-mpt30b-langchain](https://github.com/mayooear/private-chatbot-mpt30b-langchain) | 167 |
+|[OpenPluginACI/openplugin](https://github.com/OpenPluginACI/openplugin) | 165 |
+|[jmpaz/promptlib](https://github.com/jmpaz/promptlib) | 165 |
+|[kjappelbaum/gptchem](https://github.com/kjappelbaum/gptchem) | 162 |
+|[JorisdeJong123/7-Days-of-LangChain](https://github.com/JorisdeJong123/7-Days-of-LangChain) | 161 |
+|[retr0reg/Ret2GPT](https://github.com/retr0reg/Ret2GPT) | 161 |
+|[menloparklab/falcon-langchain](https://github.com/menloparklab/falcon-langchain) | 159 |
+|[summarizepaper/summarizepaper](https://github.com/summarizepaper/summarizepaper) | 158 |
+|[emarco177/ice_breaker](https://github.com/emarco177/ice_breaker) | 157 |
+|[AmineDiro/cria](https://github.com/AmineDiro/cria) | 156 |
+|[morpheuslord/HackBot](https://github.com/morpheuslord/HackBot) | 156 |
+|[homanp/vercel-langchain](https://github.com/homanp/vercel-langchain) | 156 |
+|[mlops-for-all/mlops-for-all.github.io](https://github.com/mlops-for-all/mlops-for-all.github.io) | 155 |
+|[positive666/Prompt-Can-Anything](https://github.com/positive666/Prompt-Can-Anything) | 154 |
+|[deeppavlov/dream](https://github.com/deeppavlov/dream) | 153 |
+|[flurb18/AgentOoba](https://github.com/flurb18/AgentOoba) | 151 |
+|[Open-Swarm-Net/GPT-Swarm](https://github.com/Open-Swarm-Net/GPT-Swarm) | 151 |
+|[v7labs/benchllm](https://github.com/v7labs/benchllm) | 150 |
+|[Klingefjord/chatgpt-telegram](https://github.com/Klingefjord/chatgpt-telegram) | 150 |
+|[Aggregate-Intellect/sherpa](https://github.com/Aggregate-Intellect/sherpa) | 148 |
+|[Coding-Crashkurse/Langchain-Full-Course](https://github.com/Coding-Crashkurse/Langchain-Full-Course) | 148 |
+|[SuperDuperDB/superduperdb](https://github.com/SuperDuperDB/superduperdb) | 147 |
+|[defenseunicorns/leapfrogai](https://github.com/defenseunicorns/leapfrogai) | 147 |
+|[menloparklab/langchain-cohere-qdrant-doc-retrieval](https://github.com/menloparklab/langchain-cohere-qdrant-doc-retrieval) | 147 |
+|[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 146 |
+|[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 146 |
+|[iMagist486/ElasticSearch-Langchain-Chatglm2](https://github.com/iMagist486/ElasticSearch-Langchain-Chatglm2) | 144 |
+|[peterw/StoryStorm](https://github.com/peterw/StoryStorm) | 143 |
+|[kulltc/chatgpt-sql](https://github.com/kulltc/chatgpt-sql) | 142 |
+|[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 142 |
+|[hirokidaichi/wanna](https://github.com/hirokidaichi/wanna) | 141 |
+|[yasyf/summ](https://github.com/yasyf/summ) | 141 |
+|[solana-labs/chatgpt-plugin](https://github.com/solana-labs/chatgpt-plugin) | 140 |
+|[ssheng/BentoChain](https://github.com/ssheng/BentoChain) | 139 |
+|[mallahyari/drqa](https://github.com/mallahyari/drqa) | 139 |
+|[petehunt/langchain-github-bot](https://github.com/petehunt/langchain-github-bot) | 139 |
+|[dbpunk-labs/octogen](https://github.com/dbpunk-labs/octogen) | 138 |
+|[RedisVentures/redis-openai-qna](https://github.com/RedisVentures/redis-openai-qna) | 138 |
+|[eunomia-bpf/GPTtrace](https://github.com/eunomia-bpf/GPTtrace) | 138 |
+|[langchain-ai/langsmith-sdk](https://github.com/langchain-ai/langsmith-sdk) | 137 |
+|[jina-ai/fastapi-serve](https://github.com/jina-ai/fastapi-serve) | 137 |
+|[yeagerai/genworlds](https://github.com/yeagerai/genworlds) | 137 |
+|[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 137 |
+|[luisroque/large_laguage_models](https://github.com/luisroque/large_laguage_models) | 136 |
+|[ChuloAI/BrainChulo](https://github.com/ChuloAI/BrainChulo) | 136 |
+|[3Alan/DocsMind](https://github.com/3Alan/DocsMind) | 136 |
+|[KylinC/ChatFinance](https://github.com/KylinC/ChatFinance) | 133 |
+|[langchain-ai/text-split-explorer](https://github.com/langchain-ai/text-split-explorer) | 133 |
+|[davila7/file-gpt](https://github.com/davila7/file-gpt) | 133 |
+|[tencentmusic/supersonic](https://github.com/tencentmusic/supersonic) | 132 |
+|[kimtth/azure-openai-llm-vector-langchain](https://github.com/kimtth/azure-openai-llm-vector-langchain) | 131 |
+|[ciare-robotics/world-creator](https://github.com/ciare-robotics/world-creator) | 129 |
+|[zenml-io/zenml-projects](https://github.com/zenml-io/zenml-projects) | 129 |
+|[log1stics/voice-generator-webui](https://github.com/log1stics/voice-generator-webui) | 129 |
+|[snexus/llm-search](https://github.com/snexus/llm-search) | 129 |
+|[fixie-ai/fixie-examples](https://github.com/fixie-ai/fixie-examples) | 128 |
+|[MedalCollector/Orator](https://github.com/MedalCollector/Orator) | 127 |
+|[grumpyp/chroma-langchain-tutorial](https://github.com/grumpyp/chroma-langchain-tutorial) | 127 |
+|[langchain-ai/langchain-aws-template](https://github.com/langchain-ai/langchain-aws-template) | 127 |
+|[prof-frink-lab/slangchain](https://github.com/prof-frink-lab/slangchain) | 126 |
+|[KMnO4-zx/huanhuan-chat](https://github.com/KMnO4-zx/huanhuan-chat) | 124 |
+|[RCGAI/SimplyRetrieve](https://github.com/RCGAI/SimplyRetrieve) | 124 |
+|[Dicklesworthstone/llama2_aided_tesseract](https://github.com/Dicklesworthstone/llama2_aided_tesseract) | 123 |
+|[sdaaron/QueryGPT](https://github.com/sdaaron/QueryGPT) | 122 |
+|[athina-ai/athina-sdk](https://github.com/athina-ai/athina-sdk) | 121 |
+|[AIAnytime/Llama2-Medical-Chatbot](https://github.com/AIAnytime/Llama2-Medical-Chatbot) | 121 |
+|[MuhammadMoinFaisal/LargeLanguageModelsProjects](https://github.com/MuhammadMoinFaisal/LargeLanguageModelsProjects) | 121 |
+|[Azure/business-process-automation](https://github.com/Azure/business-process-automation) | 121 |
+|[definitive-io/code-indexer-loop](https://github.com/definitive-io/code-indexer-loop) | 119 |
+|[nrl-ai/pautobot](https://github.com/nrl-ai/pautobot) | 119 |
+|[Azure/app-service-linux-docs](https://github.com/Azure/app-service-linux-docs) | 118 |
+|[zilliztech/akcio](https://github.com/zilliztech/akcio) | 118 |
+|[CodeAlchemyAI/ViLT-GPT](https://github.com/CodeAlchemyAI/ViLT-GPT) | 117 |
+|[georgesung/llm_qlora](https://github.com/georgesung/llm_qlora) | 117 |
+|[nicknochnack/Nopenai](https://github.com/nicknochnack/Nopenai) | 115 |
+|[nftblackmagic/flask-langchain](https://github.com/nftblackmagic/flask-langchain) | 115 |
+|[mortium91/langchain-assistant](https://github.com/mortium91/langchain-assistant) | 115 |
+|[Ngonie-x/langchain_csv](https://github.com/Ngonie-x/langchain_csv) | 114 |
+|[wombyz/HormoziGPT](https://github.com/wombyz/HormoziGPT) | 114 |
+|[langchain-ai/langchain-teacher](https://github.com/langchain-ai/langchain-teacher) | 113 |
+|[mluogh/eastworld](https://github.com/mluogh/eastworld) | 112 |
+|[mudler/LocalAGI](https://github.com/mudler/LocalAGI) | 112 |
+|[marimo-team/marimo](https://github.com/marimo-team/marimo) | 111 |
+|[trancethehuman/entities-extraction-web-scraper](https://github.com/trancethehuman/entities-extraction-web-scraper) | 111 |
+|[xuwenhao/mactalk-ai-course](https://github.com/xuwenhao/mactalk-ai-course) | 111 |
+|[dcaribou/transfermarkt-datasets](https://github.com/dcaribou/transfermarkt-datasets) | 111 |
+|[rabbitmetrics/langchain-13-min](https://github.com/rabbitmetrics/langchain-13-min) | 111 |
+|[dotvignesh/PDFChat](https://github.com/dotvignesh/PDFChat) | 111 |
+|[aws-samples/cdk-eks-blueprints-patterns](https://github.com/aws-samples/cdk-eks-blueprints-patterns) | 110 |
+|[topoteretes/PromethAI-Backend](https://github.com/topoteretes/PromethAI-Backend) | 110 |
+|[jlonge4/local_llama](https://github.com/jlonge4/local_llama) | 110 |
+|[RUC-GSAI/YuLan-Rec](https://github.com/RUC-GSAI/YuLan-Rec) | 108 |
+|[gh18l/CrawlGPT](https://github.com/gh18l/CrawlGPT) | 107 |
+|[c0sogi/LLMChat](https://github.com/c0sogi/LLMChat) | 107 |
+|[hwchase17/langchain-gradio-template](https://github.com/hwchase17/langchain-gradio-template) | 107 |
+|[ArjanCodes/examples](https://github.com/ArjanCodes/examples) | 106 |
+|[genia-dev/GeniA](https://github.com/genia-dev/GeniA) | 105 |
+|[nexus-stc/stc](https://github.com/nexus-stc/stc) | 105 |
+|[mbchang/data-driven-characters](https://github.com/mbchang/data-driven-characters) | 105 |
+|[ademakdogan/ChatSQL](https://github.com/ademakdogan/ChatSQL) | 104 |
+|[crosleythomas/MirrorGPT](https://github.com/crosleythomas/MirrorGPT) | 104 |
+|[IvanIsCoding/ResuLLMe](https://github.com/IvanIsCoding/ResuLLMe) | 104 |
+|[avrabyt/MemoryBot](https://github.com/avrabyt/MemoryBot) | 104 |
+|[Azure/azure-sdk-tools](https://github.com/Azure/azure-sdk-tools) | 103 |
+|[aniketmaurya/llm-inference](https://github.com/aniketmaurya/llm-inference) | 103 |
+|[Anil-matcha/Youtube-to-chatbot](https://github.com/Anil-matcha/Youtube-to-chatbot) | 103 |
+|[nyanp/chat2plot](https://github.com/nyanp/chat2plot) | 102 |
+|[aws-samples/amazon-kendra-langchain-extensions](https://github.com/aws-samples/amazon-kendra-langchain-extensions) | 101 |
+|[atisharma/llama_farm](https://github.com/atisharma/llama_farm) | 100 |
+|[Xueheng-Li/SynologyChatbotGPT](https://github.com/Xueheng-Li/SynologyChatbotGPT) | 100 |
+
+
+
+_Generated by [github-dependents-info](https://github.com/nvuillam/github-dependents-info)_
+
+`github-dependents-info --repo langchain-ai/langchain --markdownfile dependents.md --minstars 100 --sort stars`

docs/docs/additional_resources/youtube.mdx

@@ -91,7 +91,7 @@
 - [Chat with a `CSV` | `LangChain Agents` Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
 - [Create Your Own ChatGPT with `PDF` Data in 5 Minutes (LangChain Tutorial)](https://youtu.be/au2WVVGUvc8) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
 - [Build a Custom Chatbot with OpenAI: `GPT-Index` & LangChain | Step-by-Step Tutorial](https://youtu.be/FIDv6nc4CgU) by [Fabrikod](https://www.youtube.com/@fabrikod)
-- [`Flowise` is an open source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
+- [`Flowise` is an open-source no-code UI visual tool to build 🦜🔗LangChain applications](https://youtu.be/CovAPtQPU0k) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
 - [LangChain & GPT 4 For Data Analysis: The `Pandas` Dataframe Agent](https://youtu.be/rFQ5Kmkd4jc) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
 - [`GirlfriendGPT` - AI girlfriend with LangChain](https://youtu.be/LiN3D1QZGQw) by [Toolfinder AI](https://www.youtube.com/@toolfinderai)
 - [How to build with Langchain 10x easier | ⛓️ LangFlow & `Flowise`](https://youtu.be/Ya1oGL7ZTvU) by [AI Jason](https://www.youtube.com/@AIJasonZ)

docs/docs/community.md

@@ -48,7 +48,6 @@ If you’re working on something you’re proud of, and think the LangChain comm
 Here’s where our team hangs out, talks shop, spotlights cool work, and shares what we’re up to. We’d love to see you there too.
 
 - **[Twitter](https://twitter.com/LangChainAI):** We post about what we’re working on and what cool things we’re seeing in the space. If you tag @langchainai in your post, we’ll almost certainly see it, and can show you some love!
-- **[Discord](https://discord.gg/6adMQxSpJS):** connect with >30k developers who are building with LangChain
+- **[Discord](https://discord.gg/6adMQxSpJS):** connect with over 30,000 developers who are building with LangChain.
 - **[GitHub](https://github.com/langchain-ai/langchain):** Open pull requests, contribute to a discussion, and/or contribute
 - **[Subscribe to our bi-weekly Release Notes](https://6w1pwbss0py.typeform.com/to/KjZB1auB):** a twice/month email roundup of the coolest things going on in our orbit
-- **Slack:** If you’re building an application in production at your company, we’d love to get into a Slack channel together. Fill out [this form](https://airtable.com/appwQzlErAS2qiP0L/shrGtGaVBVAz7NcV2) and we’ll get in touch about setting one up.

docs/docs/expression_language/cookbook/memory.ipynb

@@ -20,7 +20,7 @@
     "from operator import itemgetter\n",
     "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain.schema.runnable import RunnablePassthrough\n",
+    "from langchain.schema.runnable import RunnablePassthrough, RunnableLambda\n",
     "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
     "\n",
     "model = ChatOpenAI()\n",
@@ -70,7 +70,7 @@
    "outputs": [],
    "source": [
     "chain = RunnablePassthrough.assign(\n",
-    "    memory=memory.load_memory_variables | itemgetter(\"history\")\n",
+    "    memory=RunnableLambda(memory.load_memory_variables) | itemgetter(\"history\")\n",
     ") | prompt | model\n"
    ]
   },

docs/docs/expression_language/cookbook/prompt_llm_parser.ipynb

@@ -184,7 +184,7 @@
    "source": [
     "## PromptTemplate + LLM + OutputParser\n",
     "\n",
-    "We can also add in an output parser to easily trasform the raw LLM/ChatModel output into a more workable format"
+    "We can also add in an output parser to easily transform the raw LLM/ChatModel output into a more workable format"
    ]
   },
   {

docs/docs/expression_language/cookbook/retrieval.ipynb

@@ -42,7 +42,7 @@
     "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.embeddings import OpenAIEmbeddings\n",
     "from langchain.schema.output_parser import StrOutputParser\n",
-    "from langchain.schema.runnable import RunnablePassthrough\n",
+    "from langchain.schema.runnable import RunnablePassthrough, RunnableLambda\n",
     "from langchain.vectorstores import FAISS\n"
    ]
   },
@@ -338,7 +338,7 @@
     "# First we add a step to load memory\n",
     "# This adds a \"memory\" key to the input object\n",
     "loaded_memory = RunnablePassthrough.assign(\n",
-    "    chat_history=memory.load_memory_variables | itemgetter(\"history\"),\n",
+    "    chat_history=RunnableLambda(memory.load_memory_variables) | itemgetter(\"history\"),\n",
     ")\n",
     "# Now we calculate the standalone question\n",
     "standalone_question = {\n",
@@ -363,7 +363,7 @@
     "    \"docs\": itemgetter(\"docs\"),\n",
     "}\n",
     "# And now we put it all together!\n",
-    "final_chain = loaded_memory | expanded_memory | standalone_question | retrieved_documents | answer\n"
+    "final_chain = loaded_memory | standalone_question | retrieved_documents | answer\n"
    ]
   },
   {

docs/docs/expression_language/how_to/configure.ipynb

@@ -0,0 +1,363 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "79d51519",
+   "metadata": {},
+   "source": [
+    "# Configurable Alternatives\n",
+    "\n",
+    "Oftentimes you may want to experiment with, or even expose to the end user, multiple different ways of doing things.\n",
+    "In order to make this experience as easy as possible, we have defined a `configurable_alternatives` method.\n",
+    "With this method, you can list out alternatives for any particular runnable that can be set during runtime."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ac733d35",
+   "metadata": {},
+   "source": [
+    "## With LLMs\n",
+    "\n",
+    "Let's take a look at doing this with LLMs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "430ab8cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI, ChatAnthropic\n",
+    "from langchain.schema.runnable import ConfigurableField\n",
+    "from langchain.prompts import PromptTemplate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "71248a9f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
+    "    # This gives this field an id\n",
+    "    # When configuring the end runnable, we can then use this id to configure this field\n",
+    "    ConfigurableField(id=\"llm\"),\n",
+    "    # This sets a default_key.\n",
+    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    default_key=\"anthropic\",\n",
+    "    # This adds a new option, with name `openai` that is equal to `ChatOpenAI()`\n",
+    "    openai=ChatOpenAI(),\n",
+    "    # This adds a new option, with name `gpt4` that is equal to `ChatOpenAI(model=\"gpt-4\")`\n",
+    "    gpt4=ChatOpenAI(model=\"gpt-4\"),\n",
+    "    # You can add more configuration options here\n",
+    ")\n",
+    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\")\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "e598b1f1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# By default it will call Anthropic\n",
+    "chain.invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "48b45337",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they already have bear feet!\")"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can use `.with_config(configurable={\"llm\": \"openai\"})` to specify an llm to use\n",
+    "chain.with_config(configurable={\"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "42647fb7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# If we use the `default_key` then it uses the default\n",
+    "chain.with_config(configurable={\"llm\": \"anthropic\"}).invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a9134559",
+   "metadata": {},
+   "source": [
+    "## With Prompts\n",
+    "\n",
+    "We can do a similar thing, but alternate between prompts\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "9f6a7c6c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatAnthropic(temperature=0)\n",
+    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\").configurable_alternatives(\n",
+    "    # This gives this field an id\n",
+    "    # When configuring the end runnable, we can then use this id to configure this field\n",
+    "    ConfigurableField(id=\"prompt\"),\n",
+    "    # This sets a default_key.\n",
+    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    default_key=\"joke\",\n",
+    "    # This adds a new option, with name `poem`\n",
+    "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
+    "    # You can add more configuration options here\n",
+    ")\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "97eda915",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\" Here's a silly joke about bears:\\n\\nWhat do you call a bear with no teeth?\\nA gummy bear!\")"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# By default it will write a joke\n",
+    "chain.invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "927297a1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Here is a short poem about bears:\\n\\nThe bears awaken from their sleep\\nAnd lumber out into the deep\\nForests filled with trees so tall\\nForaging for food before nightfall \\nTheir furry coats and claws so sharp\\nSniffing for berries and fish to nab\\nLumbering about without a care\\nThe mighty grizzly and black bear\\nProud creatures, wild and free\\nRuling their domain majestically\\nWandering the woods they call their own\\nBefore returning to their dens alone')"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can configure it write a poem\n",
+    "chain.with_config(configurable={\"prompt\": \"poem\"}).invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c77124e",
+   "metadata": {},
+   "source": [
+    "## With Prompts and LLMs\n",
+    "\n",
+    "We can also have multiple things configurable!\n",
+    "Here's an example doing that with both prompts and LLMs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "97538c23",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatAnthropic(temperature=0).configurable_alternatives(\n",
+    "    # This gives this field an id\n",
+    "    # When configuring the end runnable, we can then use this id to configure this field\n",
+    "    ConfigurableField(id=\"llm\"),\n",
+    "    # This sets a default_key.\n",
+    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    default_key=\"anthropic\",\n",
+    "    # This adds a new option, with name `openai` that is equal to `ChatOpenAI()`\n",
+    "    openai=ChatOpenAI(),\n",
+    "    # This adds a new option, with name `gpt4` that is equal to `ChatOpenAI(model=\"gpt-4\")`\n",
+    "    gpt4=ChatOpenAI(model=\"gpt-4\"),\n",
+    "    # You can add more configuration options here\n",
+    ")\n",
+    "prompt = PromptTemplate.from_template(\"Tell me a joke about {topic}\").configurable_alternatives(\n",
+    "    # This gives this field an id\n",
+    "    # When configuring the end runnable, we can then use this id to configure this field\n",
+    "    ConfigurableField(id=\"prompt\"),\n",
+    "    # This sets a default_key.\n",
+    "    # If we specify this key, the default LLM (ChatAnthropic initialized above) will be used\n",
+    "    default_key=\"joke\",\n",
+    "    # This adds a new option, with name `poem`\n",
+    "    poem=PromptTemplate.from_template(\"Write a short poem about {topic}\"),\n",
+    "    # You can add more configuration options here\n",
+    ")\n",
+    "chain = prompt | llm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "1dcc7ccc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"In the forest, where tall trees sway,\\nA creature roams, both fierce and gray.\\nWith mighty paws and piercing eyes,\\nThe bear, a symbol of strength, defies.\\n\\nThrough snow-kissed mountains, it does roam,\\nA guardian of its woodland home.\\nWith fur so thick, a shield of might,\\nIt braves the coldest winter night.\\n\\nA gentle giant, yet wild and free,\\nThe bear commands respect, you see.\\nWith every step, it leaves a trace,\\nOf untamed power and ancient grace.\\n\\nFrom honeyed feast to salmon's leap,\\nIt takes its place, in nature's keep.\\nA symbol of untamed delight,\\nThe bear, a wonder, day and night.\\n\\nSo let us honor this noble beast,\\nIn forests where its soul finds peace.\\nFor in its presence, we come to know,\\nThe untamed spirit that in us also flows.\")"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can configure it write a poem with OpenAI\n",
+    "chain.with_config(configurable={\"prompt\": \"poem\", \"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "e4ee9fbc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Sure, here's a bear joke for you:\\n\\nWhy don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can always just configure only one if we want\n",
+    "chain.with_config(configurable={\"llm\": \"openai\"}).invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "02fc4841",
+   "metadata": {},
+   "source": [
+    "## Saving configurations\n",
+    "\n",
+    "We can also easily save configured chains as their own objects"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "5cf53202",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "openai_poem = chain.with_config(configurable={\"llm\": \"openai\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "9486d701",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\")"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "openai_poem.invoke({\"topic\": \"bears\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a43e3b70",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.10.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/expression_language/how_to/map.ipynb

@@ -101,7 +101,7 @@
    "source": [
     "Here the input to prompt is expected to be a map with keys \"context\" and \"question\". The user input is just the question. So we need to get the context using our retriever and passthrough the user input under the \"question\" key.\n",
     "\n",
-    "Note that when composing a RunnableMap when another Runnable we don't even need to wrap our dictuionary in the RunnableMap class — the type conversion is handled for us."
+    "Note that when composing a RunnableMap when another Runnable we don't even need to wrap our dictionary in the RunnableMap class — the type conversion is handled for us."
    ]
   },
   {

docs/docs/expression_language/index.mdx

@@ -31,3 +31,6 @@ How to use core features of LCEL
 
 #### [Cookbook](/docs/expression_language/cookbook)
 Examples of common LCEL usage patterns
+
+#### [Why use LCEL](/docs/expression_language/why)
+A deeper dive into the benefits of LCEL