fmt

Instead of using JSON-like syntax to describe node and relationship
properties we changed to a shorter and more concise schema description

Old:

```
        Node properties are the following:
        [{'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Movie'}, {'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Actor'}]
        Relationship properties are the following:
        []
        The relationships are the following:
        ['(:Actor)-[:ACTED_IN]->(:Movie)']
```

New:

```
Node properties are the following:
Movie {name: STRING},Actor {name: STRING}
Relationship properties are the following:

The relationships are the following:
(:Actor)-[:ACTED_IN]->(:Movie)
```

.github/CONTRIBUTING.md

@@ -23,7 +23,7 @@ It's essential that we maintain great documentation and testing. If you:
   - Update any affected example notebooks and documentation. These live in `docs`.
   - Update unit and integration tests when relevant.
 - Add a feature
-  - Add a demo notebook in `docs/modules`.
+  - Add a demo notebook in `docs/docs/`.
   - Add unit and integration tests.
 
 We are a small, progress-oriented team. If there's something you'd like to add or change, opening a pull request is the
@@ -214,6 +214,10 @@ ignore-words-list = 'momento,collison,ned,foor,reworkd,parth,whats,aapply,mysogy
 
 Langchain relies heavily on optional dependencies to keep the Langchain package lightweight.
 
+You only need to add a new dependency if a **unit test** relies on the package.
+If your package is only required for **integration tests**, then you can skip these
+steps and leave all pyproject.toml and poetry.lock files alone.
+
 If you're adding a new dependency to Langchain, assume that it will be an optional dependency, and
 that most users won't have it installed.
 

.github/workflows/_lint.yml

@@ -68,7 +68,7 @@ jobs:
         # It doesn't matter how you change it, any change will cause a cache-bust.
         working-directory: ${{ inputs.working-directory }}
         run: |
-          poetry install --with dev,lint,test,typing
+          poetry install --with lint,typing
 
       - name: Install langchain editable
         working-directory: ${{ inputs.working-directory }}
@@ -76,7 +76,7 @@ jobs:
         env:
           LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
         run: |
-          pip install -e "$LANGCHAIN_LOCATION"
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
 
       - name: Get .mypy_cache to speed up mypy
         uses: actions/cache@v3

.github/workflows/_pydantic_compatibility.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      langchain-location:
+        required: false
+        type: string
+        description: "Relative path to the langchain library folder"
 
 env:
   POETRY_VERSION: "1.6.1"
@@ -40,6 +44,14 @@ jobs:
         shell: bash
         run: poetry install
 
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
+
       - name: Install the opposite major version of pydantic
         # If normal tests use pydantic v1, here we'll use v2, and vice versa.
         shell: bash

.github/workflows/_test.yml

@@ -7,6 +7,10 @@ on:
         required: true
         type: string
         description: "From which folder this pipeline executes"
+      langchain-location:
+        required: false
+        type: string
+        description: "Relative path to the langchain library folder"
 
 env:
   POETRY_VERSION: "1.6.1"
@@ -38,11 +42,20 @@ jobs:
 
       - name: Install dependencies
         shell: bash
-        run: poetry install
+        run: poetry install --with test
+
+      - name: Install langchain editable
+        working-directory: ${{ inputs.working-directory }}
+        if: ${{ inputs.langchain-location }}
+        env:
+          LANGCHAIN_LOCATION: ${{ inputs.langchain-location }}
+        run: |
+          poetry run pip install -e "$LANGCHAIN_LOCATION"
 
       - name: Run core tests
         shell: bash
-        run: make test
+        run: |
+          make test
 
       - name: Ensure the tests did not create any additional files
         shell: bash

.github/workflows/langchain_ci.yml

@@ -3,18 +3,19 @@ name: libs/langchain CI
 
 on:
   push:
-    branches: [ master ]
+    branches: [master]
   pull_request:
     paths:
-      - '.github/actions/poetry_setup/action.yml'
-      - '.github/tools/**'
-      - '.github/workflows/_lint.yml'
-      - '.github/workflows/_test.yml'
-      - '.github/workflows/_pydantic_compatibility.yml'
-      - '.github/workflows/langchain_ci.yml'
-      - 'libs/*'
-      - 'libs/langchain/**'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+      - ".github/actions/poetry_setup/action.yml"
+      - ".github/tools/**"
+      - ".github/workflows/_lint.yml"
+      - ".github/workflows/_test.yml"
+      - ".github/workflows/_pydantic_compatibility.yml"
+      - ".github/workflows/langchain_ci.yml"
+      - "libs/*"
+      - "libs/langchain/**"
+      - "libs/core/**"
+  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
 
 # If another push to the same PR or branch happens while this workflow is still running,
 # cancel the earlier run in favor of the next run.
@@ -32,29 +33,25 @@ env:
 
 jobs:
   lint:
-    uses:
-      ./.github/workflows/_lint.yml
+    uses: ./.github/workflows/_lint.yml
     with:
       working-directory: libs/langchain
     secrets: inherit
 
   test:
-    uses:
-      ./.github/workflows/_test.yml
+    uses: ./.github/workflows/_test.yml
     with:
       working-directory: libs/langchain
     secrets: inherit
 
   compile-integration-tests:
-    uses:
-      ./.github/workflows/_compile_integration_test.yml
+    uses: ./.github/workflows/_compile_integration_test.yml
     with:
       working-directory: libs/langchain
     secrets: inherit
 
   pydantic-compatibility:
-    uses:
-      ./.github/workflows/_pydantic_compatibility.yml
+    uses: ./.github/workflows/_pydantic_compatibility.yml
     with:
       working-directory: libs/langchain
     secrets: inherit
@@ -89,6 +86,11 @@ jobs:
           echo "Running extended tests, installing dependencies with poetry..."
           poetry install -E extended_testing
 
+      - name: Install langchain core editable
+        shell: bash
+        run: |
+          poetry run pip install -e ../core
+
       - name: Run extended tests
         run: make extended_tests
 

.github/workflows/langchain_core_ci.yml

@@ -0,0 +1,52 @@
+---
+name: libs/langchain core CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    paths:
+      - '.github/actions/poetry_setup/action.yml'
+      - '.github/tools/**'
+      - '.github/workflows/_lint.yml'
+      - '.github/workflows/_test.yml'
+      - '.github/workflows/_pydantic_compatibility.yml'
+      - '.github/workflows/langchain_core_ci.yml'
+      - 'libs/core/**'
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  POETRY_VERSION: "1.6.1"
+  WORKDIR: "libs/core"
+
+jobs:
+  lint:
+    uses:
+      ./.github/workflows/_lint.yml
+    with:
+      working-directory: libs/core
+    secrets: inherit
+
+  test:
+    uses:
+      ./.github/workflows/_test.yml
+    with:
+      working-directory: libs/core
+    secrets: inherit
+
+  pydantic-compatibility:
+    uses:
+      ./.github/workflows/_pydantic_compatibility.yml
+    with:
+      working-directory: libs/core
+    secrets: inherit

.github/workflows/langchain_core_release.yml

@@ -0,0 +1,13 @@
+---
+name: libs/core Release
+
+on:
+  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+
+jobs:
+  release:
+    uses:
+      ./.github/workflows/_release.yml
+    with:
+      working-directory: libs/core
+    secrets: inherit

.github/workflows/langchain_experimental_ci.yml

@@ -3,17 +3,19 @@ name: libs/experimental CI
 
 on:
   push:
-    branches: [ master ]
+    branches: [master]
   pull_request:
     paths:
-      - '.github/actions/poetry_setup/action.yml'
-      - '.github/tools/**'
-      - '.github/workflows/_lint.yml'
-      - '.github/workflows/_test.yml'
-      - '.github/workflows/langchain_experimental_ci.yml'
-      - 'libs/*'
-      - 'libs/experimental/**'
-  workflow_dispatch:  # Allows to trigger the workflow manually in GitHub UI
+      - ".github/actions/poetry_setup/action.yml"
+      - ".github/tools/**"
+      - ".github/workflows/_lint.yml"
+      - ".github/workflows/_test.yml"
+      - ".github/workflows/langchain_experimental_ci.yml"
+      - "libs/*"
+      - "libs/experimental/**"
+      - "libs/langchain/**"
+      - "libs/core/**"
+  workflow_dispatch: # Allows to trigger the workflow manually in GitHub UI
 
 # If another push to the same PR or branch happens while this workflow is still running,
 # cancel the earlier run in favor of the next run.
@@ -31,23 +33,19 @@ env:
 
 jobs:
   lint:
-    uses:
-      ./.github/workflows/_lint.yml
+    uses: ./.github/workflows/_lint.yml
     with:
       working-directory: libs/experimental
-      langchain-location: ../langchain
     secrets: inherit
 
   test:
-    uses:
-      ./.github/workflows/_test.yml
+    uses: ./.github/workflows/_test.yml
     with:
       working-directory: libs/experimental
     secrets: inherit
 
   compile-integration-tests:
-    uses:
-      ./.github/workflows/_compile_integration_test.yml
+    uses: ./.github/workflows/_compile_integration_test.yml
     with:
       working-directory: libs/experimental
     secrets: inherit
@@ -88,6 +86,7 @@ jobs:
 
           echo "Editably installing langchain outside of poetry, to avoid messing up lockfile..."
           poetry run pip install -e ../langchain
+          poetry run pip install -e ../core
 
       - name: Run tests
         run: make test

LICENSE

@@ -1,6 +1,6 @@
-The MIT License
+MIT License
 
-Copyright (c) Harrison Chase
+Copyright (c) LangChain, Inc.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -9,13 +9,13 @@ to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 copies of the Software, and to permit persons to whom the Software is
 furnished to do so, subject to the following conditions:
 
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
 
 THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Makefile

@@ -44,6 +44,7 @@ spell_fix:
 lint:
 	poetry run ruff docs templates cookbook
 	poetry run ruff format docs templates cookbook --diff
+	poetry run ruff --select I docs templates cookbook
 
 format format_diff:
 	poetry run ruff format docs templates cookbook

README.md

@@ -30,7 +30,7 @@ pip install langchain
 
 With conda:
 ```bash
-pip install langsmith && conda install langchain -c conda-forge
+conda install langchain -c conda-forge
 ```
 
 ## 🤔 What is LangChain?

cookbook/code-analysis-deeplake.ipynb

@@ -648,7 +648,7 @@
     {
      "data": {
       "text/plain": [
-       "OpenAIEmbeddings(client=<class 'openai.api_resources.embedding.Embedding'>, model='text-embedding-ada-002', deployment='text-embedding-ada-002', openai_api_version='', openai_api_base='', openai_api_type='', openai_proxy='', embedding_ctx_length=8191, openai_api_key='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', openai_organization='', allowed_special=set(), disallowed_special='all', chunk_size=1000, max_retries=6, request_timeout=None, headers=None, tiktoken_model_name=None, show_progress_bar=False, model_kwargs={})"
+       "OpenAIEmbeddings(client=<class 'openai.api_resources.embedding.Embedding'>, model='text-embedding-ada-002', deployment='text-embedding-ada-002', openai_api_version='', openai_api_base='', openai_api_type='', openai_proxy='', embedding_ctx_length=8191, openai_api_key='', openai_organization='', allowed_special=set(), disallowed_special='all', chunk_size=1000, max_retries=6, request_timeout=None, headers=None, tiktoken_model_name=None, show_progress_bar=False, model_kwargs={})"
       ]
      },
      "execution_count": 13,

cookbook/llm_bash.ipynb

@@ -69,8 +69,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.llm_bash.prompt import BashOutputParser\n",
     "from langchain.prompts.prompt import PromptTemplate\n",
+    "from langchain_experimental.llm_bash.prompt import BashOutputParser\n",
     "\n",
     "_PROMPT_TEMPLATE = \"\"\"If someone asks you to perform a task, your job is to come up with a series of bash commands that will perform the task. There is no need to put \"#!/bin/bash\" in your answer. Make sure to reason step by step, using this format:\n",
     "Question: \"copy the files in the directory named 'target' into a new directory at the same level as target called 'myNewDirectory'\"\n",

docs/api_reference/create_api_rst.py

@@ -13,8 +13,10 @@ HERE = Path(__file__).parent
 
 PKG_DIR = ROOT_DIR / "libs" / "langchain" / "langchain"
 EXP_DIR = ROOT_DIR / "libs" / "experimental" / "langchain_experimental"
+CORE_DIR = ROOT_DIR / "libs" / "core" / "langchain_core"
 WRITE_FILE = HERE / "api_reference.rst"
 EXP_WRITE_FILE = HERE / "experimental_api_reference.rst"
+CORE_WRITE_FILE = HERE / "core_api_reference.rst"
 
 
 ClassKind = Literal["TypedDict", "Regular", "Pydantic", "enum"]
@@ -292,6 +294,17 @@ def _document_langchain_experimental() -> None:
 
 
 def _document_langchain_core() -> None:
+    """Document the langchain_core package."""
+    # Generate core_api_reference.rst
+    core_members = _load_package_modules(CORE_DIR)
+    core_doc = ".. _core_api_reference:\n\n" + _construct_doc(
+        "langchain_core", core_members
+    )
+    with open(CORE_WRITE_FILE, "w") as f:
+        f.write(core_doc)
+
+
+def _document_langchain() -> None:
     """Document the main langchain package."""
     # load top level module members
     lc_members = _load_package_modules(PKG_DIR)
@@ -306,7 +319,6 @@ def _document_langchain_core() -> None:
             "agents.output_parsers": agents["output_parsers"],
             "agents.format_scratchpad": agents["format_scratchpad"],
             "tools.render": tools["render"],
-            "schema.runnable": schema["runnable"],
         }
     )
 
@@ -318,8 +330,9 @@ def _document_langchain_core() -> None:
 
 def main() -> None:
     """Generate the reference.rst file for each package."""
-    _document_langchain_core()
+    _document_langchain()
     _document_langchain_experimental()
+    _document_langchain_core()
 
 
 if __name__ == "__main__":

docs/api_reference/requirements.txt

@@ -1,5 +1,6 @@
 -e libs/langchain
 -e libs/experimental
+-e libs/core
 pydantic<2
 autodoc_pydantic==1.8.0
 myst_parser

docs/api_reference/themes/scikit-learn-modern/nav.html

@@ -34,6 +34,9 @@
         <li class="nav-item">
           <a class="sk-nav-link nav-link" href="{{ pathto('api_reference') }}">API</a>
         </li>
+        <li class="nav-item">
+          <a class="sk-nav-link nav-link" href="{{ pathto('core_api_reference') }}">Core</a>
+        </li>
         <li class="nav-item">
           <a class="sk-nav-link nav-link" href="{{ pathto('experimental_api_reference') }}">Experimental</a>
         </li>

docs/docs/expression_language/cookbook/retrieval.ipynb

@@ -234,7 +234,13 @@
     "from typing import List, Tuple\n",
     "\n",
     "\n",
-    "def _format_chat_history(chat_history: List[Tuple]) -> str:\n",
+    "def _format_chat_history(chat_history: List[Tuple[str, str]]) -> str:\n",
+    "    # chat history is of format:\n",
+    "    # [\n",
+    "    #   (human_message_str, ai_message_str),\n",
+    "    #   ...\n",
+    "    # ]\n",
+    "    # see below for an example of how it's invoked\n",
     "    buffer = \"\"\n",
     "    for dialogue_turn in chat_history:\n",
     "        human = \"Human: \" + dialogue_turn[0]\n",

docs/docs/expression_language/get_started.ipynb

@@ -0,0 +1,888 @@
+{
+ "cells": [
+  {
+   "cell_type": "raw",
+   "id": "366a0e68-fd67-4fe5-a292-5c33733339ea",
+   "metadata": {},
+   "source": [
+    "---\n",
+    "sidebar_position: 0\n",
+    "title: Get started\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f331037f-be3f-4782-856f-d55dab952488",
+   "metadata": {},
+   "source": [
+    "LCEL makes it easy to build complex chains from basic components, and supports out of the box functionality such as streaming, parallelism, and logging."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9a9acd2e",
+   "metadata": {},
+   "source": [
+    "## Basic example: prompt + model + output parser\n",
+    "\n",
+    "The most basic and common use case is chaining a prompt template and a model together. To see how this works, let's create a chain that takes a topic and generates a joke:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b6c5518-85eb-43af-afd8-d3ff4643c389",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts import ChatPromptTemplate\n",
+    "from langchain.schema.output_parser import StrOutputParser\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a short joke about {topic}\")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "chain = prompt | model | output_parser\n",
+    "\n",
+    "chain.invoke({\"topic\": \"ice cream\"})"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "ae8ca065-8479-4083-b593-5b5823ffc91a",
+   "metadata": {},
+   "source": [
+    "Notice this line, where we piece together the different components into a single chain\n",
+    "\n",
+    "```python\n",
+    "chain = prompt | model | output_parser\n",
+    "```\n",
+    "\n",
+    "The `|` symbol is similar to a unix pipe operator, creating a chain in which the output of each component is fed as input into the next component.\n",
+    "\n",
+    "In this chain the user input is passed to the prompt template, then the prompt template output is passed to the model, then the model output is passed to the output parser. Let's take a look at each component individually to really understand what's going on. \n",
+    "\n",
+    "### 1. Prompt\n",
+    "\n",
+    "`prompt` is a `BasePromptTemplate`, which means it takes in a dictionary of template variables and produces a `PromptValue`. A `PromptValue` is a wrapper around a completed prompt that can be passed to either an `LLM` (which takes a string as input) or `ChatModel` (which takes a sequence of messages as input). It can work with either language model type because it defines logic both for producing `BaseMessage`s and for producing a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "15b85a8f-0d79-49da-9132-b4554d7283e5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "ChatPromptValue(messages=[HumanMessage(content='Tell me a short joke about ice cream')])"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value = prompt.invoke({\"topic\": \"ice cream\"})\n",
+    "prompt_value"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d0ca55ee-1b96-4e1f-bddb-bb3b12d5e54b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='Tell me a short joke about ice cream')]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value.to_messages()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "d5b345ba-48e4-4fda-873b-c92685237c52",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Human: Tell me a short joke about ice cream'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prompt_value.to_string()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1619c4b7-38f8-4ba4-bf46-ef6ffa92a6d6",
+   "metadata": {},
+   "source": [
+    "### 2. Model\n",
+    "\n",
+    "The `PromptValue` is then passed to `model`. In this case our `model` is a `ChatModel`, meaning it will output a `BaseMessage`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "5f99f50c-8091-4bd6-9602-6b7504575ef0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='Why did the ice cream go to therapy? \\n\\nBecause it was feeling a little rocky road!')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message = model.invoke(prompt_value)\n",
+    "message"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b774231e-29d4-4f22-8c7e-8fd20b756d0d",
+   "metadata": {},
+   "source": [
+    "If our `model` was an `LLM`, it would output a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7d851773-25f9-4173-bb91-c1e94b61967e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\n\\nWhy did the ice cream go to therapy?\\n\\nBecause it was feeling a little soft serve.'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\")\n",
+    "llm.invoke(prompt_value)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "71d18c82-e9aa-4e5a-acda-d211aac20f1d",
+   "metadata": {},
+   "source": [
+    "### 3. Output parser\n",
+    "\n",
+    "And lastly we pass our `model` output to the `output_parser`, which is a `BaseOutputParser` meaning it takes either a string or a \n",
+    "`BaseMessage` as input. The `StrOutputParser` specifically simple converts any input into a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "a3a0f4f3-6fa6-42de-bfaf-0bd8f3fdbd19",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Why did the ice cream go to therapy? \\n\\nBecause it was feeling a little rocky road!'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output_parser.invoke(message)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5b258fd5-22ab-4069-862f-e64c4be6c9a8",
+   "metadata": {},
+   "source": [
+    "## Why use LCEL\n",
+    "\n",
+    "To understand the value of LCEL, let's see what we'd have to do to achieve similar functionality without it in this simple use case.\n",
+    "\n",
+    "### Without LCEL\n",
+    "\n",
+    "We could recreate our above functionality without LCEL or LangChain at all by doing something like this:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e628905c-430e-4e4a-9d7c-c91d2f42052e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import openai\n",
+    "\n",
+    "\n",
+    "def manual_chain(topic: str) -> str:\n",
+    "    prompt_value = f\"Tell me a short joke about {topic}\"\n",
+    "    client = openai.OpenAI()\n",
+    "    response = client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo\", messages=[{\"role\": \"user\", \"content\": prompt_value}]\n",
+    "    )\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c0b0513-77b8-4371-a20e-3e487cec7e7f",
+   "metadata": {},
+   "source": [
+    "#### Stream\n",
+    "\n",
+    "If we want to stream results instead, we'll need to change our function:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4f2cc6dc-d70a-4c13-9258-452f14290da6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Iterator\n",
+    "\n",
+    "\n",
+    "def manual_chain_stream(topic: str) -> Iterator[str]:\n",
+    "    prompt_value = f\"Tell me a short joke about {topic}\"\n",
+    "    client = openai.OpenAI()\n",
+    "    stream = client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo\",\n",
+    "        messages=[{\"role\": \"user\", \"content\": prompt_value}],\n",
+    "        stream=True,\n",
+    "    )\n",
+    "    for response in stream:\n",
+    "        content = response.choices[0].delta.content\n",
+    "        if content is not None:\n",
+    "            yield content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b9b41e78-ddeb-44d0-a58b-a0ea0c99a761",
+   "metadata": {},
+   "source": [
+    "#### Batch\n",
+    "\n",
+    "If we want to run on a batch of inputs in parallel, we'll again need a new function:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6b492f13-73a6-48ed-8d4f-9ad634da9988",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from concurrent.futures import ThreadPoolExecutor\n",
+    "\n",
+    "\n",
+    "def manual_chain_batch(topics: list) -> list:\n",
+    "    with ThreadPoolExecutor(max_workers=5) as executor:\n",
+    "        return list(executor.map(manual_chain, topics))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cc5ba36f-eec1-4fc1-8cfe-fa242a7f7809",
+   "metadata": {},
+   "source": [
+    "#### Async\n",
+    "\n",
+    "If you needed an asynchronous version:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "eabe6621-e815-41e3-9c9d-5aa561a69835",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "async def manual_chain_async(topic: str) -> str:\n",
+    "    prompt_value = f\"Tell me a short joke about {topic}\"\n",
+    "    client = openai.AsyncOpenAI()\n",
+    "    response = await client.chat.completions.create(\n",
+    "        model=\"gpt-3.5-turbo\", messages=[{\"role\": \"user\", \"content\": prompt_value}]\n",
+    "    )\n",
+    "    return response.choices[0].message.content"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6888245-1ebe-4768-a53b-e1fef6a8b379",
+   "metadata": {},
+   "source": [
+    "#### LLM instead of chat model\n",
+    "\n",
+    "If we want to use a completion endpoint instead of a chat endpoint: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9aca946b-acaa-4f7e-a3d0-ad8e3225e7f2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def manual_chain_completion(topic: str) -> str:\n",
+    "    prompt_value = f\"Tell me a short joke about {topic}\"\n",
+    "    client = openai.OpenAI()\n",
+    "    response = client.completions.create(\n",
+    "        model=\"gpt-3.5-turbo-instruct\",\n",
+    "        prompt=prompt_value,\n",
+    "    )\n",
+    "    return response.choices[0].text"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ca115eaf-59ef-45c1-aac1-e8b0ce7db250",
+   "metadata": {},
+   "source": [
+    "#### Different model provider\n",
+    "\n",
+    "If we want to use Anthropic instead of OpenAI: "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cde2ceb0-f65e-487b-9a32-137b0e9d79d5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import anthropic\n",
+    "\n",
+    "\n",
+    "def manual_chain_anthropic(topic: str) -> str:\n",
+    "    prompt_value = f\"Human:\\n\\nTell me a short joke about {topic}\\n\\nAssistant:\"\n",
+    "    client = anthropic.Anthropic()\n",
+    "    response = client.completions.create(\n",
+    "        model=\"claude-2\",\n",
+    "        prompt=prompt_value,\n",
+    "        max_tokens_to_sample=256,\n",
+    "    )\n",
+    "    return response.completion"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "370dd4d7-b825-40c4-ae3c-2693cba2f22a",
+   "metadata": {},
+   "source": [
+    "#### Logging\n",
+    "\n",
+    "If we want to log our intermediate results (we'll `print` here for illustrative purposes):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "383a3c51-926d-48c6-b9ae-42bf8f14ecc8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def manual_chain_anthropic_logging(topic: str) -> str:\n",
+    "    print(f\"Input: {topic}\")\n",
+    "    prompt_value = f\"Human:\\n\\nTell me a short joke about {topic}\\n\\nAssistant:\"\n",
+    "    print(f\"Formatted prompt: {prompt_value}\")\n",
+    "    client = anthropic.Anthropic()\n",
+    "    response = client.completions.create(\n",
+    "        model=\"claude-2\",\n",
+    "        prompt=prompt_value,\n",
+    "        max_tokens_to_sample=256,\n",
+    "    )\n",
+    "    print(f\"Output: {response.completion}\")\n",
+    "    return response.completion"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e25ce3c5-27a7-4954-9f0e-b94313597135",
+   "metadata": {},
+   "source": [
+    "#### Fallbacks\n",
+    "\n",
+    "If you wanted to add retry or fallback logic:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2e49d512-bc83-4c5f-b56e-934b8343b0fe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def manual_chain_with_fallback(topic: str) -> str:\n",
+    "    try:\n",
+    "        return manual_chain(topic)\n",
+    "    except Exception:\n",
+    "        return manual_chain_anthropic(topic)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f7ef59b5-2ce3-479e-a7ac-79e1e2f30e9c",
+   "metadata": {},
+   "source": [
+    "### With LCEL\n",
+    "\n",
+    "Now let's take a look at how all of this work with LCEL. We'll use our chain from before (and for ease of use take in a string instead of a dict):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "dc0de76a-daf5-4ec0-ba7f-c63225821591",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a short joke about {topic}\")\n",
+    "model = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
+    "output_parser = StrOutputParser()\n",
+    "\n",
+    "chain = {\"topic\": RunnablePassthrough()} | prompt | model | output_parser"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b0d85dda-d63c-459f-99ec-5d6d669b5b0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.invoke(\"ice cream\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c9eb899-e7c8-4ab5-aecd-d305cd716082",
+   "metadata": {},
+   "source": [
+    "#### Streaming"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "71f15ae5-8353-4fe6-b506-73c67ec9c27d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for chunk in chain.stream(\"ice cream\"):\n",
+    "    print(chunk, end=\"\", flush=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2eff0ae2-f2ca-4463-bacb-634fc788b5bb",
+   "metadata": {},
+   "source": [
+    "#### Batch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dcf9f4a7-5ded-47fb-9057-adb04ed3382e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain.batch([\"ice cream\", \"spaghetti\", \"dumplings\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "82c49198-3ac3-4805-b898-063c45ce89fb",
+   "metadata": {},
+   "source": [
+    "#### Async\n",
+    "```python\n",
+    "chain.ainvoke(\"ice cream)\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c184ca63-e74d-478c-980c-2c19b459cccd",
+   "metadata": {},
+   "source": [
+    "#### LLM instead of chat model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9f18118e-e901-42ec-a4a0-75d011bec10e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "\n",
+    "llm = OpenAI(model=\"gpt-3.5-turbo-instruct\")\n",
+    "llm_chain = {\"topic\": RunnablePassthrough()} | prompt | llm | output_parser\n",
+    "llm_chain.invoke(\"ice cream\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a5de0201-3980-4f78-b89e-c8c59f1c4e7d",
+   "metadata": {},
+   "source": [
+    "If we wanted, we could even make the choice of chat model or llm runtime configurable"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "937fa94a-b019-450b-bec5-b6e3443fa903",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.runnables import ConfigurableField\n",
+    "\n",
+    "configurable_model = model.configurable_alternatives(\n",
+    "    ConfigurableField(id=\"model\"), default_key=\"chat_openai\", openai=llm\n",
+    ")\n",
+    "configurable_chain = {\"topic\": RunnablePassthrough()} | prompt | llm | output_parser\n",
+    "configurable_chain.invoke(\"ice cream\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2187eb0b-e86b-4845-a2b3-2355781e1b8a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "configurable_chain.invoke(\"ice cream\", config={\"configurable\": {\"model\": \"openai\"}})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e900a52e-f858-4604-9413-7fa7cb04a8a5",
+   "metadata": {},
+   "source": [
+    "#### Different model provider\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "983b323c-f573-452a-8f81-98eb8d6906f9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatAnthropic\n",
+    "\n",
+    "anthropic = ChatAnthropic(model=\"claude-2\")\n",
+    "anthropic_chain = {\"topic\": RunnablePassthrough()} | prompt | anthropic | output_parser\n",
+    "anthropic_chain.invoke(\"ice cream\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9c5e16de-a8db-4689-aeef-b2e76d9071cd",
+   "metadata": {},
+   "source": [
+    "#### Logging\n",
+    "\n",
+    "By turning on LangSmith, every step of every chain is automatically logged. We set these environment variables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d6204f21-d2e7-4ac6-871f-b60b34e5bd36",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"LANGCHAIN_API_KEY\"] = \"...\"\n",
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4842ec53-b58a-4689-97da-32ed17003981",
+   "metadata": {},
+   "source": [
+    "And then get a trace of every chain run: {trace}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4274f4bd-3a78-4a28-a531-28ea7ac1efae",
+   "metadata": {},
+   "source": [
+    "#### Fallbacks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3d0d8a0f-66eb-4c35-9529-74bec44ce4b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fallback_chain = chain.with_fallbacks([anthropic_chain])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f58af836-26bd-4eab-97a0-76dd56d53430",
+   "metadata": {},
+   "source": [
+    "### With vs without LCEL"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9fb3d71d-8c69-4dc4-81b7-95cd46b271c2",
+   "metadata": {},
+   "source": [
+    "Our full code **with LCEL** looks like:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "715c469a-545e-434e-bd6e-99745dd880a7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain.chat_models import ChatAnthropic, ChatOpenAI\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain_core.output_parsers import StrOutputParser\n",
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "from langchain_core.runnables import RunnablePassthrough\n",
+    "\n",
+    "os.environ[\"LANGCHAIN_API_KEY\"] = \"...\"\n",
+    "os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_template(\"Tell me a short joke about {topic}\")\n",
+    "\n",
+    "chat_openai = ChatOpenAI(model=\"gpt-3.5-turbo\")\n",
+    "openai = OpenAI(model=\"gpt-3.5-turbo-instruct\")\n",
+    "anthropic = ChatAnthropic(model=\"claude-2\")\n",
+    "model = chat_openai.with_fallbacks([anthropic]).configurable_alternatives(\n",
+    "    ConfigurableField(id=\"model\"),\n",
+    "    default_key=\"chat_openai\",\n",
+    "    openai=openai,\n",
+    "    anthropic=anthropic,\n",
+    ")\n",
+    "\n",
+    "chain = {\"topic\": RunnablePassthrough()} | prompt | model | StrOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a925003-4a1f-406f-87f2-1fd8965b9f87",
+   "metadata": {},
+   "source": [
+    "Our code **without LCEL** might look something like:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a25837c5-829b-42a3-92b4-7e25831350c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from concurrent.futures import ThreadPoolExecutor\n",
+    "from typing import Iterator, List, Tuple\n",
+    "\n",
+    "import openai\n",
+    "\n",
+    "prompt_template = \"Tell me a short joke about {topic}\"\n",
+    "\n",
+    "\n",
+    "def manual_chain(topic: str, *, model: str = \"chat_openai\") -> str:\n",
+    "    print(f\"Input: {topic}\")\n",
+    "    prompt_value = prompt_template.format(topic=topic)\n",
+    "\n",
+    "    if model == \"chat_openai\":\n",
+    "        print(f\"Full prompt: {prompt_value}\")\n",
+    "        response = openai.OpenAI().chat.completions.create(\n",
+    "            model=\"gpt-3.5-turbo\", messages=[{\"role\": \"user\", \"content\": prompt_value}]\n",
+    "        )\n",
+    "        output = response.choices[0].message.content\n",
+    "    elif model == \"openai\":\n",
+    "        print(f\"Full prompt: {prompt_value}\")\n",
+    "        response = openai.OpenAI().completions.create(\n",
+    "            model=\"gpt-3.5-turbo-instruct\",\n",
+    "            prompt=prompt_value,\n",
+    "        )\n",
+    "        output = response.choices[0].text\n",
+    "    elif model == \"anthropic\":\n",
+    "        prompt_value = f\"Human:\\n\\n{prompt_value}\\n\\nAssistant:\"\n",
+    "        print(f\"Full prompt: {prompt_value}\")\n",
+    "        response = anthropic.Anthropic().completions.create(\n",
+    "            model=\"claude-2\",\n",
+    "            prompt=prompt_value,\n",
+    "            max_tokens_to_sample=256,\n",
+    "        )\n",
+    "        output = response.completion\n",
+    "    else:\n",
+    "        raise ValueError(\n",
+    "            f\"Invalid model {model}. Should be one of chat_openai, openai, anthropic.\"\n",
+    "        )\n",
+    "    print(f\"Output: {output}\")\n",
+    "    return output\n",
+    "\n",
+    "\n",
+    "def manual_chain_with_fallbacks(\n",
+    "    topic: str, *, model: str = \"chat_openai\", fallbacks: Tuple[str] = (\"anthropic\",)\n",
+    ") -> str:\n",
+    "    for fallback in fallbacks:\n",
+    "        try:\n",
+    "            return manual_chain(topic, model=model)\n",
+    "        except Exception as e:\n",
+    "            print(f\"Error {e}\")\n",
+    "            model = fallback\n",
+    "    raise e\n",
+    "\n",
+    "\n",
+    "def manual_chain_batch(\n",
+    "    topics: List[str],\n",
+    "    *,\n",
+    "    model: str = \"chat_openai\",\n",
+    "    fallbacks: Tuple[str] = (\"anthropic\",),\n",
+    ") -> List[str]:\n",
+    "    models = [model] * len(topics)\n",
+    "    fallbacks_list = [fallbacks] * len(topics)\n",
+    "    with ThreadPoolExecutor(max_workers=5) as executor:\n",
+    "        return list(\n",
+    "            executor.map(manual_chain_with_fallbacks, topics, models, fallbacks_list)\n",
+    "        )\n",
+    "\n",
+    "\n",
+    "def manual_chain_stream(topic: str, *, model: str = \"chat_openai\") -> Iterator[str]:\n",
+    "    print(f\"Input: {topic}\")\n",
+    "    prompt_value = prompt_template.format(topic=topic)\n",
+    "\n",
+    "    if model == \"chat_openai\":\n",
+    "        print(f\"Full prompt: {prompt_value}\")\n",
+    "        stream = openai.OpenAI().chat.completions.create(\n",
+    "            model=\"gpt-3.5-turbo\",\n",
+    "            messages=[{\"role\": \"user\", \"content\": prompt_value}],\n",
+    "            stream=True,\n",
+    "        )\n",
+    "        for response in stream:\n",
+    "            content = response.choices[0].delta.content\n",
+    "            if content is not None:\n",
+    "                yield content\n",
+    "    elif model == \"openai\":\n",
+    "        print(f\"Full prompt: {prompt_value}\")\n",
+    "        stream = openai.OpenAI().completions.create(\n",
+    "            model=\"gpt-3.5-turbo-instruct\", prompt=prompt_value, stream=True\n",
+    "        )\n",
+    "        for response in stream:\n",
+    "            yield response.choices[0].text\n",
+    "    elif model == \"anthropic\":\n",
+    "        prompt_value = f\"Human:\\n\\n{prompt_value}\\n\\nAssistant:\"\n",
+    "        print(f\"Full prompt: {prompt_value}\")\n",
+    "        stream = anthropic.Anthropic().completions.create(\n",
+    "            model=\"claude-2\", prompt=prompt_value, max_tokens_to_sample=256, stream=True\n",
+    "        )\n",
+    "        for response in stream:\n",
+    "            yield response.completion\n",
+    "    else:\n",
+    "        raise ValueError(\n",
+    "            f\"Invalid model {model}. Should be one of chat_openai, openai, anthropic.\"\n",
+    "        )\n",
+    "\n",
+    "\n",
+    "async def manual_chain_async(topic: str, *, model: str = \"chat_openai\") -> str:\n",
+    "    # You get the idea :)\n",
+    "    ...\n",
+    "\n",
+    "\n",
+    "async def manual_chain_async_batch(\n",
+    "    topics: List[str], *, model: str = \"chat_openai\"\n",
+    ") -> List[str]:\n",
+    "    ...\n",
+    "\n",
+    "\n",
+    "async def manual_chain_async_stream(\n",
+    "    topic: str, *, model: str = \"chat_openai\"\n",
+    ") -> Iterator[str]:\n",
+    "    ...\n",
+    "\n",
+    "\n",
+    "def manual_chain_stream_with_fallbacks(\n",
+    "    topic: str, *, model: str = \"chat_openai\", fallbacks: Tuple[str] = (\"anthropic\",)\n",
+    ") -> Iterator[str]:\n",
+    "    ..."
+   ]
+  }
+ ],
+ "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
+}

docs/docs/expression_language/how_to/map.ipynb

@@ -104,7 +104,7 @@
    "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 dictionary in the RunnableMap class — the type conversion is handled for us."
+    "Note that when composing a RunnableMap with 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/how_to/message_history.ipynb

@@ -0,0 +1,396 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6a4becbd-238e-4c1d-a02d-08e61fbc3763",
+   "metadata": {},
+   "source": [
+    "# Add message history (memory)\n",
+    "\n",
+    "The `RunnableWithMessageHistory` let's us add message history to certain types of chains.\n",
+    "\n",
+    "Specifically, it can be used for any Runnable that takes as input one of\n",
+    "* a sequence of `BaseMessage`\n",
+    "* a dict with a key that takes a sequence of `BaseMessage`\n",
+    "* a dict with a key that takes the latest message(s) as a string or sequence of `BaseMessage`, and a separate key that takes historical messages\n",
+    "\n",
+    "And returns as output one of\n",
+    "* a string that can be treated as the contents of an `AIMessage`\n",
+    "* a sequence of `BaseMessage`\n",
+    "* a dict with a key that contains a sequence of `BaseMessage`\n",
+    "\n",
+    "Let's take a look at some examples to see how it works."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6bca45e5-35d9-4603-9ca9-6ac0ce0e35cd",
+   "metadata": {},
+   "source": [
+    "## Setup\n",
+    "\n",
+    "We'll use Redis to store our chat message histories and Anthropic's claude-2 model so we'll need to install the following dependencies:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "477d04b3-c2b6-4ba5-962f-492c0d625cd5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install -U langchain redis anthropic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "93776323-d6b8-4912-bb6a-867c5e655f46",
+   "metadata": {},
+   "source": [
+    "Set your [Anthropic API  key](https://console.anthropic.com/):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c7f56f69-d2f1-4a21-990c-b5551eb012fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import getpass\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"ANTHROPIC_API_KEY\"] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6a0ec9e0-7b1c-4c6f-b570-e61d520b47c6",
+   "metadata": {},
+   "source": [
+    "Start a local Redis Stack server if we don't have an existing Redis deployment to connect to:\n",
+    "```bash\n",
+    "docker run -d -p 6379:6379 -p 8001:8001 redis/redis-stack:latest\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "cd6a250e-17fe-4368-a39d-1fe6b2cbde68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "REDIS_URL = \"redis://localhost:6379/0\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36f43b87-655c-4f64-aa7b-bd8c1955d8e5",
+   "metadata": {},
+   "source": [
+    "### [LangSmith](/docs/langsmith)\n",
+    "\n",
+    "LangSmith is especially useful for something like message history injection, where it can be hard to otherwise understand what the inputs are to various parts of the chain.\n",
+    "\n",
+    "Note that LangSmith is not needed, but it is helpful.\n",
+    "If you do want to use LangSmith, after you sign up at the link above, make sure to uncoment the below and set your environment variables to start logging traces:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2afc1556-8da1-4499-ba11-983b66c58b18",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# os.environ[\"LANGCHAIN_TRACING_V2\"] = \"true\"\n",
+    "# os.environ[\"LANGCHAIN_API_KEY\"] = getpass.getpass()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1a5a632e-ba9e-4488-b586-640ad5494f62",
+   "metadata": {},
+   "source": [
+    "## Example: Dict input, message output\n",
+    "\n",
+    "Let's create a simple chain that takes a dict as input and returns a BaseMessage.\n",
+    "\n",
+    "In this case the `\"question\"` key in the input represents our input message, and the `\"history\"` key is where our historical messages will be injected."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2a150d6f-8878-4950-8634-a608c5faad56",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Optional\n",
+    "\n",
+    "from langchain.chat_models import ChatAnthropic\n",
+    "from langchain.memory.chat_message_histories import RedisChatMessageHistory\n",
+    "from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
+    "from langchain.schema.chat_history import BaseChatMessageHistory\n",
+    "from langchain.schema.runnable.history import RunnableWithMessageHistory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3185edba-4eb6-4b32-80c6-577c0d19af97",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\"system\", \"You're an assistant who's good at {ability}\"),\n",
+    "        MessagesPlaceholder(variable_name=\"history\"),\n",
+    "        (\"human\", \"{question}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | ChatAnthropic(model=\"claude-2\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f9d81796-ce61-484c-89e2-6c567d5e54ef",
+   "metadata": {},
+   "source": [
+    "### Adding message history\n",
+    "\n",
+    "To add message history to our original chain we wrap it in the `RunnableWithMessageHistory` class.\n",
+    "\n",
+    "Crucially, we also need to  define a method that takes a session_id string and based on it returns a `BaseChatMessageHistory`. Given the same input, this method should return an equivalent output.\n",
+    "\n",
+    "In this case we'll also want to specify `input_messages_key` (the key to be treated as the latest input message) and `history_messages_key` (the key to add historical messages to)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ca7c64d8-e138-4ef8-9734-f82076c47d80",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain_with_history = RunnableWithMessageHistory(\n",
+    "    chain,\n",
+    "    lambda session_id: RedisChatMessageHistory(session_id, url=REDIS_URL),\n",
+    "    input_messages_key=\"question\",\n",
+    "    history_messages_key=\"history\",\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "37eefdec-9901-4650-b64c-d3c097ed5f4d",
+   "metadata": {},
+   "source": [
+    "## Invoking with config\n",
+    "\n",
+    "Whenever we call our chain with message history, we need to include a config that contains the `session_id`\n",
+    "```python\n",
+    "config={\"configurable\": {\"session_id\": \"<SESSION_ID>\"}}\n",
+    "```\n",
+    "\n",
+    "Given the same configuration, our chain should be pulling from the same chat message history."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a85bcc22-ca4c-4ad5-9440-f94be7318f3e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' Cosine is one of the basic trigonometric functions in mathematics. It is defined as the ratio of the adjacent side to the hypotenuse in a right triangle.\\n\\nSome key properties and facts about cosine:\\n\\n- It is denoted by cos(θ), where θ is the angle in a right triangle. \\n\\n- The cosine of an acute angle is always positive. For angles greater than 90 degrees, cosine can be negative.\\n\\n- Cosine is one of the three main trig functions along with sine and tangent.\\n\\n- The cosine of 0 degrees is 1. As the angle increases towards 90 degrees, the cosine value decreases towards 0.\\n\\n- The range of values for cosine is -1 to 1.\\n\\n- The cosine function maps angles in a circle to the x-coordinate on the unit circle.\\n\\n- Cosine is used to find adjacent side lengths in right triangles, and has many other applications in mathematics, physics, engineering and more.\\n\\n- Key cosine identities include: cos(A+B) = cosAcosB − sinAsinB and cos(2A) = cos^2(A) − sin^2(A)\\n\\nSo in summary, cosine is a fundamental trig')"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain_with_history.invoke(\n",
+    "    {\"ability\": \"math\", \"question\": \"What does cosine mean?\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"foobar\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ab29abd3-751f-41ce-a1b0-53f6b565e79d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=' The inverse of the cosine function is called the arccosine or inverse cosine, often denoted as cos-1(x) or arccos(x).\\n\\nThe key properties and facts about arccosine:\\n\\n- It is defined as the angle θ between 0 and π radians whose cosine is x. So arccos(x) = θ such that cos(θ) = x.\\n\\n- The range of arccosine is 0 to π radians (0 to 180 degrees).\\n\\n- The domain of arccosine is -1 to 1. \\n\\n- arccos(cos(θ)) = θ for values of θ from 0 to π radians.\\n\\n- arccos(x) is the angle in a right triangle whose adjacent side is x and hypotenuse is 1.\\n\\n- arccos(0) = 90 degrees. As x increases from 0 to 1, arccos(x) decreases from 90 to 0 degrees.\\n\\n- arccos(1) = 0 degrees. arccos(-1) = 180 degrees.\\n\\n- The graph of y = arccos(x) is part of the unit circle, restricted to x')"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain_with_history.invoke(\n",
+    "    {\"ability\": \"math\", \"question\": \"What's its inverse\"},\n",
+    "    config={\"configurable\": {\"session_id\": \"foobar\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "da3d1feb-b4bb-4624-961c-7db2e1180df7",
+   "metadata": {},
+   "source": [
+    ":::tip [Langsmith trace](https://smith.langchain.com/public/863a003b-7ca8-4b24-be9e-d63ec13c106e/r)\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61d5115e-64a1-4ad5-b676-8afd4ef6093e",
+   "metadata": {},
+   "source": [
+    "Looking at the Langsmith trace for the second call, we can see that when constructing the prompt, a \"history\" variable has been injected which is a list of two messages (our first input and first output)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "028cf151-6cd5-4533-b3cf-c8d735554647",
+   "metadata": {},
+   "source": [
+    "## Example: messages input, dict output"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "0bb446b5-6251-45fe-a92a-4c6171473c53",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output_message': AIMessage(content=' Here is a summary of Simone de Beauvoir\\'s views on free will:\\n\\n- De Beauvoir was an existentialist philosopher and believed strongly in the concept of free will. She rejected the idea that human nature or instincts determine behavior.\\n\\n- Instead, de Beauvoir argued that human beings define their own essence or nature through their actions and choices. As she famously wrote, \"One is not born, but rather becomes, a woman.\"\\n\\n- De Beauvoir believed that while individuals are situated in certain cultural contexts and social conditions, they still have agency and the ability to transcend these situations. Freedom comes from choosing one\\'s attitude toward these constraints.\\n\\n- She emphasized the radical freedom and responsibility of the individual. We are \"condemned to be free\" because we cannot escape making choices and taking responsibility for our choices. \\n\\n- De Beauvoir felt that many people evade their freedom and responsibility by adopting rigid mindsets, ideologies, or conforming uncritically to social roles.\\n\\n- She advocated for the recognition of ambiguity in the human condition and warned against the quest for absolute rules that deny freedom and responsibility. Authentic living involves embracing ambiguity.\\n\\nIn summary, de Beauvoir promoted an existential ethics')}"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.schema.messages import HumanMessage\n",
+    "from langchain.schema.runnable import RunnableMap\n",
+    "\n",
+    "chain = RunnableMap({\"output_message\": ChatAnthropic(model=\"claude-2\")})\n",
+    "chain_with_history = RunnableWithMessageHistory(\n",
+    "    chain,\n",
+    "    lambda session_id: RedisChatMessageHistory(session_id, url=REDIS_URL),\n",
+    "    output_messages_key=\"output_message\",\n",
+    ")\n",
+    "\n",
+    "chain_with_history.invoke(\n",
+    "    [HumanMessage(content=\"What did Simone de Beauvoir believe about free will\")],\n",
+    "    config={\"configurable\": {\"session_id\": \"baz\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "601ce3ff-aea8-424d-8e54-fd614256af4f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'output_message': AIMessage(content=\" There are many similarities between Simone de Beauvoir's views on free will and those of Jean-Paul Sartre, though some key differences emerge as well:\\n\\nSimilarities with Sartre:\\n\\n- Both were existentialist thinkers who rejected determinism and emphasized human freedom and responsibility.\\n\\n- They agreed that existence precedes essence - there is no predefined human nature that determines who we are.\\n\\n- Individuals must define themselves through their choices and actions. This leads to anxiety but also freedom.\\n\\n- The human condition is characterized by ambiguity and uncertainty, rather than fixed meanings/values.\\n\\n- Both felt that most people evade their freedom through self-deception, conformity, or adopting collective identities/values uncritically.\\n\\nDifferences from Sartre: \\n\\n- Sartre placed more emphasis on the burden and anguish of radical freedom. De Beauvoir focused more on its positive potential.\\n\\n- De Beauvoir critiqued Sartre's premise that human relations are necessarily conflictual. She saw more potential for mutual recognition.\\n\\n- Sartre saw the Other's gaze as a threat to freedom. De Beauvoir put more stress on how the Other's gaze can confirm\")}"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain_with_history.invoke(\n",
+    "    [HumanMessage(content=\"How did this compare to Sartre\")],\n",
+    "    config={\"configurable\": {\"session_id\": \"baz\"}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b898d1b1-11e6-4d30-a8dd-cc5e45533611",
+   "metadata": {},
+   "source": [
+    ":::tip [LangSmith trace](https://smith.langchain.com/public/f6c3e1d1-a49d-4955-a9fa-c6519df74fa7/r)\n",
+    ":::"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1724292c-01c6-44bb-83e8-9cdb6bf01483",
+   "metadata": {},
+   "source": [
+    "## More examples\n",
+    "\n",
+    "We could also do any of the below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fd89240b-5a25-48f8-9568-5c1127f9ffad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from operator import itemgetter\n",
+    "\n",
+    "# messages in, messages out\n",
+    "RunnableWithMessageHistory(\n",
+    "    ChatAnthropic(model=\"claude-2\"),\n",
+    "    lambda session_id: RedisChatMessageHistory(session_id, url=REDIS_URL),\n",
+    ")\n",
+    "\n",
+    "# dict with single key for all messages in, messages out\n",
+    "RunnableWithMessageHistory(\n",
+    "    itemgetter(\"input_messages\") | ChatAnthropic(model=\"claude-2\"),\n",
+    "    lambda session_id: RedisChatMessageHistory(session_id, url=REDIS_URL),\n",
+    "    input_messages_key=\"input_messages\",\n",
+    ")"
+   ]
+  }
+ ],
+ "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
+}

docs/docs/expression_language/interface.ipynb

@@ -6,7 +6,7 @@
    "metadata": {},
    "source": [
     "---\n",
-    "sidebar_position: 0\n",
+    "sidebar_position: 1\n",
     "title: Interface\n",
     "---"
    ]

docs/docs/get_started/introduction.mdx

@@ -14,7 +14,7 @@ This framework consists of several parts.
 - **[LangServe](/docs/langserve)**: A library for deploying LangChain chains as a REST API.
 - **[LangSmith](/docs/langsmith)**: A developer platform that lets you debug, test, evaluate, and monitor chains built on any LLM framework and seamlessly integrates with LangChain.
 
-![LangChain Diagram](/img/langchain_stack.png)
+![LangChain Diagram](/svg/langchain_stack.svg)
 
 Together, these products simplify the entire application lifecycle:
 - **Develop**: Write your applications in LangChain/LangChain.js. Hit the ground running using Templates for reference.
@@ -49,7 +49,7 @@ LCEL is a declarative way to compose chains. LCEL was designed from day 1 to sup
 
 - **[Overview](/docs/expression_language/)**: LCEL and its benefits
 - **[Interface](/docs/expression_language/interface)**: The standard interface for LCEL objects
-- **[How-to](/docs/expression_language/interface)**: Key features of LCEL
+- **[How-to](/docs/expression_language/how_to)**: Key features of LCEL
 - **[Cookbook](/docs/expression_language/cookbook)**: Example code for accomplishing common tasks
 
 

docs/docs/guides/safety/hugging_face_prompt_injection.ipynb

@@ -8,7 +8,7 @@
     "# Hugging Face prompt injection identification\n",
     "\n",
     "This notebook shows how to prevent prompt injection attacks using the text classification model from `HuggingFace`.\n",
-    "It exploits the *deberta* model trained to identify prompt injections: https://huggingface.co/deepset/deberta-v3-base-injection"
+    "By default it uses a *deberta* model trained to identify prompt injections. In this walkthrough we'll use https://huggingface.co/laiyer/deberta-v3-base-prompt-injection."
    ]
   },
   {
@@ -21,19 +21,37 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "aea25588-3c3f-4506-9094-221b3a0d519b",
    "metadata": {},
    "outputs": [
     {
      "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "58ab3557623a495d8cc3c3e32a61938f",
+       "version_major": 2,
+       "version_minor": 0
+      },
       "text/plain": [
-       "'hugging_face_injection_identifier'"
+       "Downloading config.json:   0%|          | 0.00/994 [00:00<?, ?B/s]"
       ]
      },
-     "execution_count": 1,
      "metadata": {},
-     "output_type": "execute_result"
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3bf062f02d304ab5a485a2a228b4cf41",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading model.safetensors:   0%|          | 0.00/738M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
     }
    ],
    "source": [
@@ -41,7 +59,10 @@
     "    HuggingFaceInjectionIdentifier,\n",
     ")\n",
     "\n",
-    "injection_identifier = HuggingFaceInjectionIdentifier()\n",
+    "# Using https://huggingface.co/laiyer/deberta-v3-base-prompt-injection\n",
+    "injection_identifier = HuggingFaceInjectionIdentifier(\n",
+    "    model=\"laiyer/deberta-v3-base-prompt-injection\"\n",
+    ")\n",
     "injection_identifier.name"
    ]
   },
@@ -299,9 +320,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv"
   },
   "language_info": {
    "codemirror_mode": {
@@ -313,7 +334,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/docs/integrations/adapters/openai.ipynb

@@ -49,18 +49,6 @@
     "Original OpenAI call"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "e1d27dfa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "result = openai.ChatCompletion.create(\n",
-    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 15,
@@ -79,6 +67,9 @@
     }
    ],
    "source": [
+    "result = openai.ChatCompletion.create(\n",
+    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0\n",
+    ")\n",
     "result[\"choices\"][0][\"message\"].to_dict_recursive()"
    ]
   },
@@ -90,18 +81,6 @@
     "LangChain OpenAI wrapper call"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "87c2d515",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "lc_result = lc_openai.ChatCompletion.create(\n",
-    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 17,
@@ -120,6 +99,9 @@
     }
    ],
    "source": [
+    "lc_result = lc_openai.ChatCompletion.create(\n",
+    "    messages=messages, model=\"gpt-3.5-turbo\", temperature=0\n",
+    ")\n",
     "lc_result[\"choices\"][0][\"message\"]"
    ]
   },
@@ -131,18 +113,6 @@
     "Swapping out model providers"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "7a2c011c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "lc_result = lc_openai.ChatCompletion.create(\n",
-    "    messages=messages, model=\"claude-2\", temperature=0, provider=\"ChatAnthropic\"\n",
-    ")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": 19,
@@ -161,6 +131,9 @@
     }
    ],
    "source": [
+    "lc_result = lc_openai.ChatCompletion.create(\n",
+    "    messages=messages, model=\"claude-2\", temperature=0, provider=\"ChatAnthropic\"\n",
+    ")\n",
     "lc_result[\"choices\"][0][\"message\"]"
    ]
   },
@@ -302,7 +275,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/azure_chat_openai.ipynb

@@ -7,7 +7,9 @@
    "source": [
     "# Azure OpenAI\n",
     "\n",
-    "This notebook goes over how to connect to an Azure hosted OpenAI endpoint. We recommend having version `openai>=1` installed."
+    ">[Azure OpenAI Service](https://learn.microsoft.com/en-us/azure/ai-services/openai/overview) provides REST API access to OpenAI's powerful language models including the GPT-4, GPT-3.5-Turbo, and Embeddings model series. These models can be easily adapted to your specific task including but not limited to content generation, summarization, semantic search, and natural language to code translation. Users can access the service through REST APIs, Python SDK, or a web-based interface in the Azure OpenAI Studio.\n",
+    "\n",
+    "This notebook goes over how to connect to an Azure-hosted OpenAI endpoint. We recommend having version `openai>=1` installed."
    ]
   },
   {
@@ -162,7 +164,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/azureml_chat_endpoint.ipynb

@@ -4,11 +4,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# AzureML Chat Online Endpoint\n",
+    "# Azure ML Endpoint\n",
     "\n",
-    "[AzureML](https://azure.microsoft.com/en-us/products/machine-learning/) is a platform used to build, train, and deploy machine learning models. Users can explore the types of models to deploy in the Model Catalog, which provides Azure Foundation Models and OpenAI Models. Azure Foundation Models include various open-source models and popular Hugging Face models. Users can also import models of their liking into AzureML.\n",
+    ">[Azure Machine Learning](https://azure.microsoft.com/en-us/products/machine-learning/) is a platform used to build, train, and deploy machine learning models. Users can explore the types of models to deploy in the Model Catalog, which provides Azure Foundation Models and OpenAI Models. `Azure Foundation Models` include various open-source models and popular Hugging Face models. Users can also import models of their liking into AzureML.\n",
+    ">\n",
+    ">[Azure Machine Learning Online Endpoints](https://learn.microsoft.com/en-us/azure/machine-learning/concept-endpoints). After you train machine learning models or pipelines, you need to deploy them to production so that others can use them for inference. Inference is the process of applying new input data to the machine learning model or pipeline to generate outputs. While these outputs are typically referred to as \"predictions,\" inferencing can be used to generate outputs for other machine learning tasks, such as classification and clustering. In `Azure Machine Learning`, you perform inferencing by using endpoints and deployments. `Endpoints` and `Deployments` allow you to decouple the interface of your production workload from the implementation that serves it.\n",
     "\n",
-    "This notebook goes over how to use a chat model hosted on an `AzureML online endpoint`"
+    "This notebook goes over how to use a chat model hosted on an `Azure Machine Learning Endpoint`."
    ]
   },
   {
@@ -91,7 +93,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/chat/hunyuan.ipynb

@@ -36,7 +36,7 @@
    "outputs": [],
    "source": [
     "chat = ChatHunyuan(\n",
-    "    hunyuan_app_id=\"YOUR_APP_ID\",\n",
+    "    hunyuan_app_id=111111111,\n",
     "    hunyuan_secret_id=\"YOUR_SECRET_ID\",\n",
     "    hunyuan_secret_key=\"YOUR_SECRET_KEY\",\n",
     ")"

docs/docs/integrations/chat/llama2_chat.ipynb

@@ -0,0 +1,729 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "90a1faf2",
+   "metadata": {},
+   "source": [
+    "# Llama-2 Chat\n",
+    "\n",
+    "This notebook shows how to augment Llama-2 `LLM`s with the `Llama2Chat` wrapper to support the [Llama-2 chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2). Several `LLM` implementations in LangChain can be used as interface to Llama-2 chat models. These include [HuggingFaceTextGenInference](https://python.langchain.com/docs/integrations/llms/huggingface_textgen_inference), [LlamaCpp](https://python.langchain.com/docs/use_cases/question_answering/how_to/local_retrieval_qa), [GPT4All](https://python.langchain.com/docs/integrations/llms/gpt4all), ..., to mention a few examples. \n",
+    "\n",
+    "`Llama2Chat` is a generic wrapper that implements `BaseChatModel` and can therefore be used in applications as [chat model](https://python.langchain.com/docs/modules/model_io/models/chat/). `Llama2Chat` converts a list of [chat messages](https://python.langchain.com/docs/modules/model_io/models/chat/#messages) into the [required chat prompt format](https://huggingface.co/blog/llama2#how-to-prompt-llama-2) and forwards the formatted prompt as `str` to the wrapped `LLM`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "36c03540",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "from langchain.memory import ConversationBufferMemory\n",
+    "from langchain_experimental.chat_models import Llama2Chat"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c76910f",
+   "metadata": {},
+   "source": [
+    "For the chat application examples below, we'll use the following chat `prompt_template`:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9bbfaf3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    "    MessagesPlaceholder,\n",
+    ")\n",
+    "from langchain.schema import SystemMessage\n",
+    "\n",
+    "template_messages = [\n",
+    "    SystemMessage(content=\"You are a helpful assistant.\"),\n",
+    "    MessagesPlaceholder(variable_name=\"chat_history\"),\n",
+    "    HumanMessagePromptTemplate.from_template(\"{text}\"),\n",
+    "]\n",
+    "prompt_template = ChatPromptTemplate.from_messages(template_messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2f3343b7",
+   "metadata": {},
+   "source": [
+    "## Chat with Llama-2 via `HuggingFaceTextGenInference` LLM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2ff99380",
+   "metadata": {},
+   "source": [
+    "A [HuggingFaceTextGenInference](https://python.langchain.com/docs/integrations/llms/huggingface_textgen_inference) LLM encapsulates access to a [text-generation-inference](https://github.com/huggingface/text-generation-inference) server. In the following example, the inference server serves a [meta-llama/Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) model. It can be started locally with:\n",
+    "\n",
+    "```bash\n",
+    "docker run \\\n",
+    "  --rm \\\n",
+    "  --gpus all \\\n",
+    "  --ipc=host \\\n",
+    "  -p 8080:80 \\\n",
+    "  -v ~/.cache/huggingface/hub:/data \\\n",
+    "  -e HF_API_TOKEN=${HF_API_TOKEN} \\\n",
+    "  ghcr.io/huggingface/text-generation-inference:0.9 \\\n",
+    "  --hostname 0.0.0.0 \\\n",
+    "  --model-id meta-llama/Llama-2-13b-chat-hf \\\n",
+    "  --quantize bitsandbytes \\\n",
+    "  --num-shard 4\n",
+    "```\n",
+    "\n",
+    "This works on a machine with 4 x RTX 3080ti cards, for example. Adjust the `--num_shard` value to the number of GPUs available. The `HF_API_TOKEN` environment variable holds the Hugging Face API token."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "238095fd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip3 install text-generation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79c4ace9",
+   "metadata": {},
+   "source": [
+    "Create a `HuggingFaceTextGenInference` instance that connects to the local inference server and wrap it into `Llama2Chat`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7a9f6de2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import HuggingFaceTextGenInference\n",
+    "\n",
+    "llm = HuggingFaceTextGenInference(\n",
+    "    inference_server_url=\"http://127.0.0.1:8080/\",\n",
+    "    max_new_tokens=512,\n",
+    "    top_k=50,\n",
+    "    temperature=0.1,\n",
+    "    repetition_penalty=1.03,\n",
+    ")\n",
+    "\n",
+    "model = Llama2Chat(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f646a2b",
+   "metadata": {},
+   "source": [
+    "Then you are ready to use the chat `model` together with `prompt_template` and conversation `memory` in an `LLMChain`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "54b5d1d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)\n",
+    "chain = LLMChain(llm=model, prompt=prompt_template, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e6717947",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Sure, I'd be happy to help! Here are a few popular locations to consider visiting in Vienna:\n",
+      "\n",
+      "1. Schönbrunn Palace\n",
+      "2. St. Stephen's Cathedral\n",
+      "3. Hofburg Palace\n",
+      "4. Belvedere Palace\n",
+      "5. Prater Park\n",
+      "6. Vienna State Opera\n",
+      "7. Albertina Museum\n",
+      "8. Museum of Natural History\n",
+      "9. Kunsthistorisches Museum\n",
+      "10. Ringstrasse\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\n",
+    "    chain.run(\n",
+    "        text=\"What can I see in Vienna? Propose a few locations. Names only, no details.\"\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "17bf10d5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Certainly! St. Stephen's Cathedral (Stephansdom) is one of the most recognizable landmarks in Vienna and a must-see attraction for visitors. This stunning Gothic cathedral is located in the heart of the city and is known for its intricate stone carvings, colorful stained glass windows, and impressive dome.\n",
+      "\n",
+      "The cathedral was built in the 12th century and has been the site of many important events throughout history, including the coronation of Holy Roman emperors and the funeral of Mozart. Today, it is still an active place of worship and offers guided tours, concerts, and special events. Visitors can climb up the south tower for panoramic views of the city or attend a service to experience the beautiful music and chanting.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(text=\"Tell me more about #2.\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2a297e09",
+   "metadata": {},
+   "source": [
+    "## Chat with Llama-2 via `LlamaCPP` LLM"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52c1a0b9",
+   "metadata": {},
+   "source": [
+    "For using a Llama-2 chat model with a [LlamaCPP](https://python.langchain.com/docs/integrations/llms/llamacpp) `LMM`, install the `llama-cpp-python` library using [these installation instructions](https://python.langchain.com/docs/integrations/llms/llamacpp#installation). The following example uses a quantized [llama-2-7b-chat.Q4_0.gguf](https://huggingface.co/TheBloke/Llama-2-7b-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_0.gguf) model stored locally at `~/Models/llama-2-7b-chat.Q4_0.gguf`. \n",
+    "\n",
+    "After creating a `LlamaCpp` instance, the `llm` is again wrapped into `Llama2Chat`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "07c0d04e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "llama_model_loader: loaded meta data with 19 key-value pairs and 291 tensors from /home/martin/Models/llama-2-7b-chat.Q4_0.gguf (version GGUF V2)\n",
+      "llama_model_loader: - tensor    0:                token_embd.weight q4_0     [  4096, 32000,     1,     1 ]\n",
+      "llama_model_loader: - tensor    1:           blk.0.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor    2:            blk.0.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    3:            blk.0.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor    4:              blk.0.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor    5:            blk.0.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor    6:              blk.0.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    7:         blk.0.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    8:              blk.0.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor    9:              blk.0.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   10:           blk.1.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   11:            blk.1.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   12:            blk.1.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   13:              blk.1.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   14:            blk.1.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   15:              blk.1.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   16:         blk.1.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   17:              blk.1.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   18:              blk.1.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   19:          blk.10.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   20:           blk.10.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   21:           blk.10.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   22:             blk.10.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   23:           blk.10.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   24:             blk.10.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   25:        blk.10.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   26:             blk.10.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   27:             blk.10.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   28:          blk.11.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   29:           blk.11.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   30:           blk.11.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   31:             blk.11.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   32:           blk.11.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   33:             blk.11.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   34:        blk.11.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   35:             blk.11.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   36:             blk.11.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   37:          blk.12.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   38:           blk.12.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   39:           blk.12.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   40:             blk.12.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   41:           blk.12.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   42:             blk.12.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   43:        blk.12.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   44:             blk.12.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   45:             blk.12.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   46:          blk.13.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   47:           blk.13.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   48:           blk.13.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   49:             blk.13.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   50:           blk.13.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   51:             blk.13.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   52:        blk.13.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   53:             blk.13.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   54:             blk.13.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   55:          blk.14.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   56:           blk.14.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   57:           blk.14.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   58:             blk.14.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   59:           blk.14.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   60:             blk.14.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   61:        blk.14.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   62:             blk.14.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   63:             blk.14.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   64:          blk.15.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   65:           blk.15.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   66:           blk.15.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   67:             blk.15.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   68:           blk.15.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   69:             blk.15.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   70:        blk.15.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   71:             blk.15.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   72:             blk.15.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   73:          blk.16.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   74:           blk.16.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   75:           blk.16.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   76:             blk.16.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   77:           blk.16.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   78:             blk.16.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   79:        blk.16.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   80:             blk.16.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   81:             blk.16.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   82:          blk.17.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   83:           blk.17.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   84:           blk.17.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   85:             blk.17.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   86:           blk.17.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   87:             blk.17.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   88:        blk.17.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   89:             blk.17.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   90:             blk.17.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   91:          blk.18.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   92:           blk.18.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   93:           blk.18.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   94:             blk.18.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor   95:           blk.18.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor   96:             blk.18.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   97:        blk.18.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   98:             blk.18.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor   99:             blk.18.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  100:          blk.19.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  101:           blk.19.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  102:           blk.19.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  103:             blk.19.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  104:           blk.19.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  105:             blk.19.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  106:        blk.19.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  107:             blk.19.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  108:             blk.19.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  109:           blk.2.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  110:            blk.2.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  111:            blk.2.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  112:              blk.2.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  113:            blk.2.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  114:              blk.2.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  115:         blk.2.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  116:              blk.2.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  117:              blk.2.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  118:          blk.20.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  119:           blk.20.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  120:           blk.20.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  121:             blk.20.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  122:           blk.20.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  123:             blk.20.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  124:        blk.20.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  125:             blk.20.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  126:             blk.20.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  127:          blk.21.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  128:           blk.21.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  129:           blk.21.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  130:             blk.21.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  131:           blk.21.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  132:             blk.21.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  133:        blk.21.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  134:             blk.21.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  135:             blk.21.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  136:          blk.22.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  137:           blk.22.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  138:           blk.22.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  139:             blk.22.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  140:           blk.22.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  141:             blk.22.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  142:        blk.22.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  143:             blk.22.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  144:             blk.22.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  145:          blk.23.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  146:           blk.23.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  147:           blk.23.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  148:             blk.23.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  149:           blk.23.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  150:             blk.23.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  151:        blk.23.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  152:             blk.23.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  153:             blk.23.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  154:           blk.3.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  155:            blk.3.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  156:            blk.3.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  157:              blk.3.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  158:            blk.3.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  159:              blk.3.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  160:         blk.3.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  161:              blk.3.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  162:              blk.3.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  163:           blk.4.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  164:            blk.4.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  165:            blk.4.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  166:              blk.4.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  167:            blk.4.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  168:              blk.4.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  169:         blk.4.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  170:              blk.4.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  171:              blk.4.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  172:           blk.5.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  173:            blk.5.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  174:            blk.5.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  175:              blk.5.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  176:            blk.5.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  177:              blk.5.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  178:         blk.5.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  179:              blk.5.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  180:              blk.5.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  181:           blk.6.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  182:            blk.6.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  183:            blk.6.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  184:              blk.6.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  185:            blk.6.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  186:              blk.6.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  187:         blk.6.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  188:              blk.6.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  189:              blk.6.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  190:           blk.7.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  191:            blk.7.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  192:            blk.7.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  193:              blk.7.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  194:            blk.7.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  195:              blk.7.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  196:         blk.7.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  197:              blk.7.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  198:              blk.7.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  199:           blk.8.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  200:            blk.8.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  201:            blk.8.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  202:              blk.8.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  203:            blk.8.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  204:              blk.8.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  205:         blk.8.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  206:              blk.8.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  207:              blk.8.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  208:           blk.9.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  209:            blk.9.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  210:            blk.9.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  211:              blk.9.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  212:            blk.9.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  213:              blk.9.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  214:         blk.9.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  215:              blk.9.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  216:              blk.9.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  217:                    output.weight q6_K     [  4096, 32000,     1,     1 ]\n",
+      "llama_model_loader: - tensor  218:          blk.24.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  219:           blk.24.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  220:           blk.24.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  221:             blk.24.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  222:           blk.24.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  223:             blk.24.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  224:        blk.24.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  225:             blk.24.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  226:             blk.24.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  227:          blk.25.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  228:           blk.25.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  229:           blk.25.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  230:             blk.25.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  231:           blk.25.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  232:             blk.25.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  233:        blk.25.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  234:             blk.25.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  235:             blk.25.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  236:          blk.26.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  237:           blk.26.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  238:           blk.26.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  239:             blk.26.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  240:           blk.26.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  241:             blk.26.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  242:        blk.26.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  243:             blk.26.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  244:             blk.26.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  245:          blk.27.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  246:           blk.27.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  247:           blk.27.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  248:             blk.27.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  249:           blk.27.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  250:             blk.27.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  251:        blk.27.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  252:             blk.27.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  253:             blk.27.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  254:          blk.28.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  255:           blk.28.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  256:           blk.28.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  257:             blk.28.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  258:           blk.28.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  259:             blk.28.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  260:        blk.28.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  261:             blk.28.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  262:             blk.28.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  263:          blk.29.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  264:           blk.29.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  265:           blk.29.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  266:             blk.29.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  267:           blk.29.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  268:             blk.29.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  269:        blk.29.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  270:             blk.29.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  271:             blk.29.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  272:          blk.30.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  273:           blk.30.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  274:           blk.30.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  275:             blk.30.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  276:           blk.30.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  277:             blk.30.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  278:        blk.30.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  279:             blk.30.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  280:             blk.30.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  281:          blk.31.attn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  282:           blk.31.ffn_down.weight q4_0     [ 11008,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  283:           blk.31.ffn_gate.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  284:             blk.31.ffn_up.weight q4_0     [  4096, 11008,     1,     1 ]\n",
+      "llama_model_loader: - tensor  285:           blk.31.ffn_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - tensor  286:             blk.31.attn_k.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  287:        blk.31.attn_output.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  288:             blk.31.attn_q.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  289:             blk.31.attn_v.weight q4_0     [  4096,  4096,     1,     1 ]\n",
+      "llama_model_loader: - tensor  290:               output_norm.weight f32      [  4096,     1,     1,     1 ]\n",
+      "llama_model_loader: - kv   0:                       general.architecture str     \n",
+      "llama_model_loader: - kv   1:                               general.name str     \n",
+      "llama_model_loader: - kv   2:                       llama.context_length u32     \n",
+      "llama_model_loader: - kv   3:                     llama.embedding_length u32     \n",
+      "llama_model_loader: - kv   4:                          llama.block_count u32     \n",
+      "llama_model_loader: - kv   5:                  llama.feed_forward_length u32     \n",
+      "llama_model_loader: - kv   6:                 llama.rope.dimension_count u32     \n",
+      "llama_model_loader: - kv   7:                 llama.attention.head_count u32     \n",
+      "llama_model_loader: - kv   8:              llama.attention.head_count_kv u32     \n",
+      "llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32     \n",
+      "llama_model_loader: - kv  10:                          general.file_type u32     \n",
+      "llama_model_loader: - kv  11:                       tokenizer.ggml.model str     \n",
+      "llama_model_loader: - kv  12:                      tokenizer.ggml.tokens arr     \n",
+      "llama_model_loader: - kv  13:                      tokenizer.ggml.scores arr     \n",
+      "llama_model_loader: - kv  14:                  tokenizer.ggml.token_type arr     \n",
+      "llama_model_loader: - kv  15:                tokenizer.ggml.bos_token_id u32     \n",
+      "llama_model_loader: - kv  16:                tokenizer.ggml.eos_token_id u32     \n",
+      "llama_model_loader: - kv  17:            tokenizer.ggml.unknown_token_id u32     \n",
+      "llama_model_loader: - kv  18:               general.quantization_version u32     \n",
+      "llama_model_loader: - type  f32:   65 tensors\n",
+      "llama_model_loader: - type q4_0:  225 tensors\n",
+      "llama_model_loader: - type q6_K:    1 tensors\n",
+      "llm_load_vocab: special tokens definition check successful ( 259/32000 ).\n",
+      "llm_load_print_meta: format           = GGUF V2\n",
+      "llm_load_print_meta: arch             = llama\n",
+      "llm_load_print_meta: vocab type       = SPM\n",
+      "llm_load_print_meta: n_vocab          = 32000\n",
+      "llm_load_print_meta: n_merges         = 0\n",
+      "llm_load_print_meta: n_ctx_train      = 4096\n",
+      "llm_load_print_meta: n_embd           = 4096\n",
+      "llm_load_print_meta: n_head           = 32\n",
+      "llm_load_print_meta: n_head_kv        = 32\n",
+      "llm_load_print_meta: n_layer          = 32\n",
+      "llm_load_print_meta: n_rot            = 128\n",
+      "llm_load_print_meta: n_gqa            = 1\n",
+      "llm_load_print_meta: f_norm_eps       = 0.0e+00\n",
+      "llm_load_print_meta: f_norm_rms_eps   = 1.0e-06\n",
+      "llm_load_print_meta: f_clamp_kqv      = 0.0e+00\n",
+      "llm_load_print_meta: f_max_alibi_bias = 0.0e+00\n",
+      "llm_load_print_meta: n_ff             = 11008\n",
+      "llm_load_print_meta: rope scaling     = linear\n",
+      "llm_load_print_meta: freq_base_train  = 10000.0\n",
+      "llm_load_print_meta: freq_scale_train = 1\n",
+      "llm_load_print_meta: n_yarn_orig_ctx  = 4096\n",
+      "llm_load_print_meta: rope_finetuned   = unknown\n",
+      "llm_load_print_meta: model type       = 7B\n",
+      "llm_load_print_meta: model ftype      = mostly Q4_0\n",
+      "llm_load_print_meta: model params     = 6.74 B\n",
+      "llm_load_print_meta: model size       = 3.56 GiB (4.54 BPW) \n",
+      "llm_load_print_meta: general.name   = LLaMA v2\n",
+      "llm_load_print_meta: BOS token = 1 '<s>'\n",
+      "llm_load_print_meta: EOS token = 2 '</s>'\n",
+      "llm_load_print_meta: UNK token = 0 '<unk>'\n",
+      "llm_load_print_meta: LF token  = 13 '<0x0A>'\n",
+      "llm_load_tensors: ggml ctx size =    0.11 MB\n",
+      "llm_load_tensors: mem required  = 3647.97 MB\n",
+      "..................................................................................................\n",
+      "llama_new_context_with_model: n_ctx      = 512\n",
+      "llama_new_context_with_model: freq_base  = 10000.0\n",
+      "llama_new_context_with_model: freq_scale = 1\n",
+      "llama_new_context_with_model: kv self size  =  256.00 MB\n",
+      "llama_build_graph: non-view tensors processed: 740/740\n",
+      "llama_new_context_with_model: compute buffer total size = 2.66 MB\n",
+      "AVX = 1 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 0 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | \n"
+     ]
+    }
+   ],
+   "source": [
+    "from os.path import expanduser\n",
+    "\n",
+    "from langchain.llms import LlamaCpp\n",
+    "\n",
+    "model_path = expanduser(\"~/Models/llama-2-7b-chat.Q4_0.gguf\")\n",
+    "\n",
+    "llm = LlamaCpp(\n",
+    "    model_path=model_path,\n",
+    "    streaming=False,\n",
+    ")\n",
+    "model = Llama2Chat(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "50498d96",
+   "metadata": {},
+   "source": [
+    "and used in the same way as in the previous example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "90782b96",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)\n",
+    "chain = LLMChain(llm=model, prompt=prompt_template, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "2160b26d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  Of course! Vienna is a beautiful city with a rich history and culture. Here are some of the top tourist attractions you might want to consider visiting:\n",
+      "1. Schönbrunn Palace\n",
+      "2. St. Stephen's Cathedral\n",
+      "3. Hofburg Palace\n",
+      "4. Belvedere Palace\n",
+      "5. Prater Park\n",
+      "6. MuseumsQuartier\n",
+      "7. Ringstrasse\n",
+      "8. Vienna State Opera\n",
+      "9. Kunsthistorisches Museum\n",
+      "10. Imperial Palace\n",
+      "\n",
+      "These are just a few of the many amazing places to see in Vienna. Each one has its own unique history and charm, so I hope you enjoy exploring this beautiful city!\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     250.46 ms\n",
+      "llama_print_timings:      sample time =      56.40 ms /   144 runs   (    0.39 ms per token,  2553.37 tokens per second)\n",
+      "llama_print_timings: prompt eval time =    1444.25 ms /    47 tokens (   30.73 ms per token,    32.54 tokens per second)\n",
+      "llama_print_timings:        eval time =    8832.02 ms /   143 runs   (   61.76 ms per token,    16.19 tokens per second)\n",
+      "llama_print_timings:       total time =   10645.94 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(\n",
+    "    chain.run(\n",
+    "        text=\"What can I see in Vienna? Propose a few locations. Names only, no details.\"\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d9ce06e3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Llama.generate: prefix-match hit\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  Of course! St. Stephen's Cathedral (also known as Stephansdom) is a stunning Gothic-style cathedral located in the heart of Vienna, Austria. It is one of the most recognizable landmarks in the city and is considered a symbol of Vienna.\n",
+      "Here are some interesting facts about St. Stephen's Cathedral:\n",
+      "1. History: The construction of St. Stephen's Cathedral began in the 12th century on the site of a former Romanesque church, and it took over 600 years to complete. The cathedral has been renovated and expanded several times throughout its history, with the most significant renovation taking place in the 19th century.\n",
+      "2. Architecture: St. Stephen's Cathedral is built in the Gothic style, characterized by its tall spires, pointed arches, and intricate stone carvings. The cathedral features a mix of Romanesque, Gothic, and Baroque elements, making it a unique blend of styles.\n",
+      "3. Design: The cathedral's design is based on the plan of a cross with a long nave and two shorter arms extending from it. The main altar is\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "llama_print_timings:        load time =     250.46 ms\n",
+      "llama_print_timings:      sample time =     100.60 ms /   256 runs   (    0.39 ms per token,  2544.73 tokens per second)\n",
+      "llama_print_timings: prompt eval time =    5128.71 ms /   160 tokens (   32.05 ms per token,    31.20 tokens per second)\n",
+      "llama_print_timings:        eval time =   16193.02 ms /   255 runs   (   63.50 ms per token,    15.75 tokens per second)\n",
+      "llama_print_timings:       total time =   21988.57 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(chain.run(text=\"Tell me more about #2.\"))"
+   ]
+  }
+ ],
+ "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": "3.9.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/document_loaders/docugami.ipynb

@@ -21,8 +21,8 @@
    },
    "outputs": [],
    "source": [
-    "# You need the lxml package to use the DocugamiLoader (run pip install directly without \"poetry run\" if you are not using poetry)\n",
-    "!poetry run pip install lxml --quiet"
+    "# You need the dgml-utils package to use the DocugamiLoader (run pip install directly without \"poetry run\" if you are not using poetry)\n",
+    "!poetry run pip install dgml-utils==0.3.0 --upgrade --quiet"
    ]
   },
   {
@@ -43,8 +43,8 @@
     "Appropriate chunking of your documents is critical for retrieval from documents. Many chunking techniques exist, including simple ones that rely on whitespace and recursive chunk splitting based on character length. Docugami offers a different approach:\n",
     "\n",
     "1. **Intelligent Chunking:** Docugami breaks down every document into a hierarchical semantic XML tree of chunks of varying sizes, from single words or numerical values to entire sections. These chunks follow the semantic contours of the document, providing a more meaningful representation than arbitrary length or simple whitespace-based chunking.\n",
-    "2. **Structured Representation:** In addition, the XML tree indicates the structural contours of every document, using attributes denoting headings, paragraphs, lists, tables, and other common elements, and does that consistently across all supported document formats, such as scanned PDFs or DOCX files. It appropriately handles long-form document characteristics like page headers/footers or multi-column flows for clean text extraction.\n",
-    "3. **Semantic Annotations:** Chunks are annotated with semantic tags that are coherent across the document set, facilitating consistent hierarchical queries across multiple documents, even if they are written and formatted differently. For example, in set of lease agreements, you can easily identify key provisions like the Landlord, Tenant, or Renewal Date, as well as more complex information such as the wording of any sub-lease provision or whether a specific jurisdiction has an exception section within a Termination Clause.\n",
+    "2. **Semantic Annotations:** Chunks are annotated with semantic tags that are coherent across the document set, facilitating consistent hierarchical queries across multiple documents, even if they are written and formatted differently. For example, in set of lease agreements, you can easily identify key provisions like the Landlord, Tenant, or Renewal Date, as well as more complex information such as the wording of any sub-lease provision or whether a specific jurisdiction has an exception section within a Termination Clause.\n",
+    "3. **Structured Representation:** In addition, the XML tree indicates the structural contours of every document, using attributes denoting headings, paragraphs, lists, tables, and other common elements, and does that consistently across all supported document formats, such as scanned PDFs or DOCX files. It appropriately handles long-form document characteristics like page headers/footers or multi-column flows for clean text extraction.\n",
     "4. **Additional Metadata:** Chunks are also annotated with additional metadata, if a user has been using Docugami. This additional metadata can be used for high-accuracy Document QA without context window restrictions. See detailed code walk-through below.\n"
    ]
   },
@@ -65,52 +65,42 @@
    "source": [
     "## Load Documents\n",
     "\n",
-    "If the DOCUGAMI_API_KEY environment variable is set, there is no need to pass it in to the loader explicitly otherwise you can pass it in as the `access_token` parameter.\n",
-    "\n",
-    "The DocugamiLoader has a default minimum chunk size of 32. Chunks smaller than that are appended to subsequent chunks. Set min_chunk_size to 0 to get all structural chunks regardless of size."
+    "If the DOCUGAMI_API_KEY environment variable is set, there is no need to pass it in to the loader explicitly otherwise you can pass it in as the `access_token` parameter."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "DOCUGAMI_API_KEY = os.environ.get(\"DOCUGAMI_API_KEY\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='MUTUAL NON-DISCLOSURE AGREEMENT This  Mutual Non-Disclosure Agreement  (this “ Agreement ”) is entered into and made effective as of  April  4 ,  2018  between  Docugami Inc. , a  Delaware  corporation , whose address is  150  Lake Street South ,  Suite  221 ,  Kirkland ,  Washington  98033 , and  Caleb Divine , an individual, whose address is  1201  Rt  300 ,  Newburgh  NY  12550 .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:ThisMutualNon-disclosureAgreement', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'ThisMutualNon-disclosureAgreement'}),\n",
-       " Document(page_content='The above named parties desire to engage in discussions regarding a potential agreement or other transaction between the parties (the “Purpose”). In connection with such discussions, it may be necessary for the parties to disclose to each other certain confidential information or materials to enable them to evaluate whether to enter into such agreement or transaction.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Discussions', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'Discussions'}),\n",
-       " Document(page_content='In consideration of the foregoing, the parties agree as follows:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Consideration', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'Consideration'}),\n",
-       " Document(page_content='1. Confidential Information . For purposes of this  Agreement , “ Confidential Information ” means any information or materials disclosed by  one  party  to the other party that: (i) if disclosed in writing or in the form of tangible materials, is marked “confidential” or “proprietary” at the time of such disclosure; (ii) if disclosed orally or by visual presentation, is identified as “confidential” or “proprietary” at the time of such disclosure, and is summarized in a writing sent by the disclosing party to the receiving party within  thirty  ( 30 ) days  after any such disclosure; or (iii) due to its nature or the circumstances of its disclosure, a person exercising reasonable business judgment would understand to be confidential or proprietary.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Purposes/docset:ConfidentialInformation-section/docset:ConfidentialInformation[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ConfidentialInformation'}),\n",
-       " Document(page_content=\"2. Obligations and  Restrictions . Each party agrees: (i) to maintain the  other party's Confidential Information  in strict confidence; (ii) not to disclose  such Confidential Information  to any third party; and (iii) not to use  such Confidential Information  for any purpose except for the Purpose. Each party may disclose the  other party’s Confidential Information  to its employees and consultants who have a bona fide need to know  such Confidential Information  for the Purpose, but solely to the extent necessary to pursue the  Purpose  and for no other purpose; provided, that each such employee and consultant first executes a written agreement (or is otherwise already bound by a written agreement) that contains use and nondisclosure restrictions at least as protective of the  other party’s Confidential Information  as those set forth in this  Agreement .\", metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Obligations/docset:ObligationsAndRestrictions-section/docset:ObligationsAndRestrictions', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ObligationsAndRestrictions'}),\n",
-       " Document(page_content='3. Exceptions. The obligations and restrictions in Section  2  will not apply to any information or materials that:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Exceptions/docset:Exceptions-section/docset:Exceptions[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Exceptions'}),\n",
-       " Document(page_content='(i) were, at the date of disclosure, or have subsequently become, generally known or available to the public through no act or failure to act by the receiving party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:TheDate/docset:TheDate', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheDate'}),\n",
-       " Document(page_content='(ii) were rightfully known by the receiving party prior to receiving such information or materials from the disclosing party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:SuchInformation/docset:TheReceivingParty', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheReceivingParty'}),\n",
-       " Document(page_content='(iii) are rightfully acquired by the receiving party from a third party who has the right to disclose such information or materials without breach of any confidentiality obligation to the disclosing party;', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheDate/docset:TheReceivingParty/docset:TheReceivingParty', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheReceivingParty'}),\n",
-       " Document(page_content='4. Compelled Disclosure . Nothing in this  Agreement  will be deemed to restrict a party from disclosing the  other party’s Confidential Information  to the extent required by any order, subpoena, law, statute or regulation; provided, that the party required to make such a disclosure uses reasonable efforts to give the other party reasonable advance notice of such required disclosure in order to enable the other party to prevent or limit such disclosure.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Disclosure/docset:CompelledDisclosure-section/docset:CompelledDisclosure', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'CompelledDisclosure'}),\n",
-       " Document(page_content='5. Return of  Confidential Information . Upon the completion or abandonment of the Purpose, and in any event upon the disclosing party’s request, the receiving party will promptly return to the disclosing party all tangible items and embodiments containing or consisting of the  disclosing party’s Confidential Information  and all copies thereof (including electronic copies), and any notes, analyses, compilations, studies, interpretations, memoranda or other documents (regardless of the form thereof) prepared by or on behalf of the receiving party that contain or are based upon the  disclosing party’s Confidential Information .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheCompletion/docset:ReturnofConfidentialInformation-section/docset:ReturnofConfidentialInformation', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'ReturnofConfidentialInformation'}),\n",
-       " Document(page_content='6. No  Obligations . Each party retains the right to determine whether to disclose any  Confidential Information  to the other party.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:NoObligations/docset:NoObligations-section/docset:NoObligations[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'NoObligations'}),\n",
-       " Document(page_content='7. No Warranty. ALL  CONFIDENTIAL INFORMATION  IS PROVIDED BY THE  DISCLOSING PARTY  “AS  IS ”.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:NoWarranty/docset:NoWarranty-section/docset:NoWarranty[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'NoWarranty'}),\n",
-       " Document(page_content='8. Term. This  Agreement  will remain in effect for a period of  seven  ( 7 ) years  from the date of last disclosure of  Confidential Information  by either party, at which time it will terminate.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:ThisAgreement/docset:Term-section/docset:Term', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Term'}),\n",
-       " Document(page_content='9. Equitable Relief . Each party acknowledges that the unauthorized use or disclosure of the  disclosing party’s Confidential Information  may cause the disclosing party to incur irreparable harm and significant damages, the degree of which may be difficult to ascertain. Accordingly, each party agrees that the disclosing party will have the right to seek immediate equitable relief to enjoin any unauthorized use or disclosure of  its Confidential Information , in addition to any other rights and remedies that it may have at law or otherwise.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:EquitableRelief/docset:EquitableRelief-section/docset:EquitableRelief[2]', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'EquitableRelief'}),\n",
-       " Document(page_content='10. Non-compete. To the maximum extent permitted by applicable law, during the  Term  of this  Agreement  and for a period of  one  ( 1 ) year  thereafter,  Caleb  Divine  may not market software products or do business that directly or indirectly competes with  Docugami  software products .', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:TheMaximumExtent/docset:Non-compete-section/docset:Non-compete', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Non-compete'}),\n",
-       " Document(page_content='11. Miscellaneous. This  Agreement  will be governed and construed in accordance with the laws of the  State  of  Washington , excluding its body of law controlling conflict of laws. This  Agreement  is the complete and exclusive understanding and agreement between the parties regarding the subject matter of this  Agreement  and supersedes all prior agreements, understandings and communications, oral or written, between the parties regarding the subject matter of this  Agreement . If any provision of this  Agreement  is held invalid or unenforceable by a court of competent jurisdiction, that provision of this  Agreement  will be enforced to the maximum extent permissible and the other provisions of this  Agreement  will remain in full force and effect. Neither party may assign this  Agreement , in whole or in part, by operation of law or otherwise, without the other party’s prior written consent, and any attempted assignment without such consent will be void. This  Agreement  may be executed in counterparts, each of which will be deemed an original, but all of which together will constitute one and the same instrument.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:MutualNon-disclosure/docset:MUTUALNON-DISCLOSUREAGREEMENT-section/docset:MUTUALNON-DISCLOSUREAGREEMENT/docset:Consideration/docset:Purposes/docset:Accordance/docset:Miscellaneous-section/docset:Miscellaneous', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'div', 'tag': 'Miscellaneous'}),\n",
-       " Document(page_content='[SIGNATURE PAGE FOLLOWS] IN  WITNESS  WHEREOF, the parties hereto have executed this  Mutual Non-Disclosure Agreement  by their duly authorized officers or representatives as of the date first set forth above.', metadata={'xpath': '/docset:MutualNon-disclosure/docset:Witness/docset:TheParties/docset:TheParties', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': 'p', 'tag': 'TheParties'}),\n",
-       " Document(page_content='DOCUGAMI INC . : \\n\\n Caleb Divine : \\n\\n Signature:  Signature:  Name: \\n\\n Jean Paoli  Name:  Title: \\n\\n CEO  Title:', metadata={'xpath': '/docset:MutualNon-disclosure/docset:Witness/docset:TheParties/docset:DocugamiInc/docset:DocugamiInc/xhtml:table', 'id': '43rj0ds7s0ur', 'source': 'NDA simple layout.docx', 'structure': '', 'tag': 'table'})]"
+       "120"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "DOCUGAMI_API_KEY = os.environ.get(\"DOCUGAMI_API_KEY\")\n",
+    "docset_id = \"26xpy3aes7xp\"\n",
+    "document_ids = [\"d7jqdzcj50sj\", \"cgd1eacfkchw\"]\n",
     "\n",
     "# To load all docs in the given docset ID, just don't provide document_ids\n",
-    "loader = DocugamiLoader(docset_id=\"ecxqpipcoe2p\", document_ids=[\"43rj0ds7s0ur\"])\n",
-    "docs = loader.load()\n",
-    "docs"
+    "loader = DocugamiLoader(docset_id=docset_id, document_ids=document_ids)\n",
+    "chunks = loader.load()\n",
+    "len(chunks)"
    ]
   },
   {
@@ -122,7 +112,39 @@
     "1. **id and source:** ID and Name of the file (PDF, DOC or DOCX) the chunk is sourced from within Docugami.\n",
     "2. **xpath:** XPath inside the XML representation of the document, for the chunk. Useful for source citations directly to the actual chunk inside the document XML.\n",
     "3. **structure:** Structural attributes of the chunk, e.g. h1, h2, div, table, td, etc. Useful to filter out certain kinds of chunks if needed by the caller.\n",
-    "4. **tag:** Semantic tag for the chunk, using various generative and extractive techniques. More details here: https://github.com/docugami/DFM-benchmarks"
+    "4. **tag:** Semantic tag for the chunk, using various generative and extractive techniques. More details here: https://github.com/docugami/DFM-benchmarks\n",
+    "\n",
+    "You can control chunking behavior by setting the following properties on the `DocugamiLoader` instance:\n",
+    "\n",
+    "1. You can set min and max chunk size, which the system tries to adhere to with minimal truncation. You can set `loader.min_text_length` and `loader.max_text_length` to control these.\n",
+    "2. By default, only the text for chunks is returned. However, Docugami's XML knowledge graph has additional rich information including semantic tags for entities inside the chunk. Set `loader.include_xml_tags = True` if you want the additional xml metadata on the returned chunks.\n",
+    "3. In addition, you can set `loader.parent_hierarchy_levels` if you want Docugami to return parent chunks in the chunks it returns. The child chunks point to the parent chunks via the `loader.parent_id_key` value. This is useful e.g. with the [MultiVector Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval. See detailed example later in this notebook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "page_content='MASTER SERVICES AGREEMENT\\n <ThisServicesAgreement> This Services Agreement (the “Agreement”) sets forth terms under which <Company>MagicSoft, Inc. </Company>a <Org><USState>Washington </USState>Corporation </Org>(“Company”) located at <CompanyAddress><CompanyStreetAddress><Company>600 </Company><Company>4th Ave</Company></CompanyStreetAddress>, <Company>Seattle</Company>, <Client>WA </Client><ProvideServices>98104 </ProvideServices></CompanyAddress>shall provide services to <Client>Daltech, Inc.</Client>, a <Company><USState>Washington </USState>Corporation </Company>(the “Client”) located at <ClientAddress><ClientStreetAddress><Client>701 </Client><Client>1st St</Client></ClientStreetAddress>, <Client>Kirkland</Client>, <State>WA </State><Client>98033</Client></ClientAddress>. This Agreement is effective as of <EffectiveDate>February 15, 2021 </EffectiveDate>(“Effective Date”). </ThisServicesAgreement>' metadata={'xpath': '/dg:chunk/docset:MASTERSERVICESAGREEMENT-section/dg:chunk', 'id': 'c28554d0af5114e2b102e6fc4dcbbde5', 'name': 'Master Services Agreement - Daltech.docx', 'source': 'Master Services Agreement - Daltech.docx', 'structure': 'h1 p', 'tag': 'chunk ThisServicesAgreement', 'Liability': '', 'Workers Compensation Insurance': '$1,000,000', 'Limit': '$1,000,000', 'Commercial General Liability Insurance': '$2,000,000', 'Technology Professional Liability Errors Omissions Policy': '$5,000,000', 'Excess Liability Umbrella Coverage': '$9,000,000', 'Client': 'Daltech, Inc.', 'Services Agreement Date': 'INITIAL STATEMENT  OF WORK (SOW)  The purpose of this SOW is to describe the Software and Services that Company will initially provide to  Daltech, Inc.  the “Client”) under the terms and conditions of the  Services Agreement  entered into between the parties on  June 15, 2021', 'Completion of the Services by Company Date': 'February 15, 2022', 'Charge': 'one hundred percent (100%)', 'Company': 'MagicSoft, Inc.', 'Effective Date': 'February 15, 2021', 'Start Date': '03/15/2021', 'Scheduled Onsite Visits Are Cancelled': 'ten (10) working days', 'Limit on Liability': '', 'Liability Cap': '', 'Business Automobile Liability': 'Business Automobile Liability  covering all vehicles that Company owns, hires or leases with a limit of no less than  $1,000,000  (combined single limit for bodily injury and property damage) for each accident.', 'Contractual Liability Coverage': 'Commercial General Liability insurance including  Contractual Liability Coverage , with coverage for products liability, completed operations, property damage and bodily injury, including  death , with an aggregate limit of no less than  $2,000,000 . This policy shall name Client as an additional insured with respect to the provision of services provided under this Agreement. This policy shall include a waiver of subrogation against Client.', 'Technology Professional Liability Errors Omissions': 'Technology Professional Liability Errors & Omissions policy (which includes Cyber Risk coverage and Computer Security and Privacy Liability coverage) with a limit of no less than  $5,000,000  per occurrence and in the aggregate.'}\n",
+      "page_content='A. STANDARD SOFTWARE AND SERVICES AGREEMENT\\n 1. Deliverables.\\n Company shall provide Client with software, technical support, product management, development, and <_testRef>testing </_testRef>services (“Services”) to the Client as described on one or more Statements of Work signed by Company and Client that reference this Agreement (“SOW” or “Statement of Work”). Company shall perform Services in a prompt manner and have the final product or service (“Deliverable”) ready for Client no later than the due date specified in the applicable SOW (“Completion Date”). This due date is subject to change in accordance with the Change Order process defined in the applicable SOW. Client shall assist Company by promptly providing all information requests known or available and relevant to the Services in a timely manner.' metadata={'xpath': '/dg:chunk/docset:MASTERSERVICESAGREEMENT-section/docset:MASTERSERVICESAGREEMENT/dg:chunk[1]/docset:Standard/dg:chunk[1]/dg:chunk[1]', 'id': 'de60160d328df10fa2637637c803d2d4', 'name': 'Master Services Agreement - Daltech.docx', 'source': 'Master Services Agreement - Daltech.docx', 'structure': 'lim h1 lim h1 div', 'tag': 'chunk', 'Liability': '', 'Workers Compensation Insurance': '$1,000,000', 'Limit': '$1,000,000', 'Commercial General Liability Insurance': '$2,000,000', 'Technology Professional Liability Errors Omissions Policy': '$5,000,000', 'Excess Liability Umbrella Coverage': '$9,000,000', 'Client': 'Daltech, Inc.', 'Services Agreement Date': 'INITIAL STATEMENT  OF WORK (SOW)  The purpose of this SOW is to describe the Software and Services that Company will initially provide to  Daltech, Inc.  the “Client”) under the terms and conditions of the  Services Agreement  entered into between the parties on  June 15, 2021', 'Completion of the Services by Company Date': 'February 15, 2022', 'Charge': 'one hundred percent (100%)', 'Company': 'MagicSoft, Inc.', 'Effective Date': 'February 15, 2021', 'Start Date': '03/15/2021', 'Scheduled Onsite Visits Are Cancelled': 'ten (10) working days', 'Limit on Liability': '', 'Liability Cap': '', 'Business Automobile Liability': 'Business Automobile Liability  covering all vehicles that Company owns, hires or leases with a limit of no less than  $1,000,000  (combined single limit for bodily injury and property damage) for each accident.', 'Contractual Liability Coverage': 'Commercial General Liability insurance including  Contractual Liability Coverage , with coverage for products liability, completed operations, property damage and bodily injury, including  death , with an aggregate limit of no less than  $2,000,000 . This policy shall name Client as an additional insured with respect to the provision of services provided under this Agreement. This policy shall include a waiver of subrogation against Client.', 'Technology Professional Liability Errors Omissions': 'Technology Professional Liability Errors & Omissions policy (which includes Cyber Risk coverage and Computer Security and Privacy Liability coverage) with a limit of no less than  $5,000,000  per occurrence and in the aggregate.'}\n",
+      "page_content='2. Onsite Services.\\n 2.1 Onsite visits will be charged on a <Frequency>daily </Frequency>basis (minimum <OnsiteVisits>8 hours</OnsiteVisits>).' metadata={'xpath': '/dg:chunk/docset:MASTERSERVICESAGREEMENT-section/docset:MASTERSERVICESAGREEMENT/dg:chunk[1]/docset:Standard/dg:chunk[3]/dg:chunk[1]', 'id': 'db18315b437ac2de6b555d2d8ef8f893', 'name': 'Master Services Agreement - Daltech.docx', 'source': 'Master Services Agreement - Daltech.docx', 'structure': 'lim h1 lim p', 'tag': 'chunk', 'Liability': '', 'Workers Compensation Insurance': '$1,000,000', 'Limit': '$1,000,000', 'Commercial General Liability Insurance': '$2,000,000', 'Technology Professional Liability Errors Omissions Policy': '$5,000,000', 'Excess Liability Umbrella Coverage': '$9,000,000', 'Client': 'Daltech, Inc.', 'Services Agreement Date': 'INITIAL STATEMENT  OF WORK (SOW)  The purpose of this SOW is to describe the Software and Services that Company will initially provide to  Daltech, Inc.  the “Client”) under the terms and conditions of the  Services Agreement  entered into between the parties on  June 15, 2021', 'Completion of the Services by Company Date': 'February 15, 2022', 'Charge': 'one hundred percent (100%)', 'Company': 'MagicSoft, Inc.', 'Effective Date': 'February 15, 2021', 'Start Date': '03/15/2021', 'Scheduled Onsite Visits Are Cancelled': 'ten (10) working days', 'Limit on Liability': '', 'Liability Cap': '', 'Business Automobile Liability': 'Business Automobile Liability  covering all vehicles that Company owns, hires or leases with a limit of no less than  $1,000,000  (combined single limit for bodily injury and property damage) for each accident.', 'Contractual Liability Coverage': 'Commercial General Liability insurance including  Contractual Liability Coverage , with coverage for products liability, completed operations, property damage and bodily injury, including  death , with an aggregate limit of no less than  $2,000,000 . This policy shall name Client as an additional insured with respect to the provision of services provided under this Agreement. This policy shall include a waiver of subrogation against Client.', 'Technology Professional Liability Errors Omissions': 'Technology Professional Liability Errors & Omissions policy (which includes Cyber Risk coverage and Computer Security and Privacy Liability coverage) with a limit of no less than  $5,000,000  per occurrence and in the aggregate.'}\n",
+      "page_content='2.2 <Expenses>Time and expenses will be charged based on actuals unless otherwise described in an Order Form or accompanying SOW. </Expenses>' metadata={'xpath': '/dg:chunk/docset:MASTERSERVICESAGREEMENT-section/docset:MASTERSERVICESAGREEMENT/dg:chunk[1]/docset:Standard/dg:chunk[3]/dg:chunk[2]/docset:ADailyBasis/dg:chunk[2]/dg:chunk', 'id': '506220fa472d5c48c8ee3db78c1122c1', 'name': 'Master Services Agreement - Daltech.docx', 'source': 'Master Services Agreement - Daltech.docx', 'structure': 'lim p', 'tag': 'chunk Expenses', 'Liability': '', 'Workers Compensation Insurance': '$1,000,000', 'Limit': '$1,000,000', 'Commercial General Liability Insurance': '$2,000,000', 'Technology Professional Liability Errors Omissions Policy': '$5,000,000', 'Excess Liability Umbrella Coverage': '$9,000,000', 'Client': 'Daltech, Inc.', 'Services Agreement Date': 'INITIAL STATEMENT  OF WORK (SOW)  The purpose of this SOW is to describe the Software and Services that Company will initially provide to  Daltech, Inc.  the “Client”) under the terms and conditions of the  Services Agreement  entered into between the parties on  June 15, 2021', 'Completion of the Services by Company Date': 'February 15, 2022', 'Charge': 'one hundred percent (100%)', 'Company': 'MagicSoft, Inc.', 'Effective Date': 'February 15, 2021', 'Start Date': '03/15/2021', 'Scheduled Onsite Visits Are Cancelled': 'ten (10) working days', 'Limit on Liability': '', 'Liability Cap': '', 'Business Automobile Liability': 'Business Automobile Liability  covering all vehicles that Company owns, hires or leases with a limit of no less than  $1,000,000  (combined single limit for bodily injury and property damage) for each accident.', 'Contractual Liability Coverage': 'Commercial General Liability insurance including  Contractual Liability Coverage , with coverage for products liability, completed operations, property damage and bodily injury, including  death , with an aggregate limit of no less than  $2,000,000 . This policy shall name Client as an additional insured with respect to the provision of services provided under this Agreement. This policy shall include a waiver of subrogation against Client.', 'Technology Professional Liability Errors Omissions': 'Technology Professional Liability Errors & Omissions policy (which includes Cyber Risk coverage and Computer Security and Privacy Liability coverage) with a limit of no less than  $5,000,000  per occurrence and in the aggregate.'}\n",
+      "page_content='2.3 <RegularWorkingHours>All work will be executed during regular working hours <RegularWorkingHours>Monday</RegularWorkingHours>-<Weekday>Friday </Weekday><RegularWorkingHours><RegularWorkingHours>0800</RegularWorkingHours>-<Number>1900</Number></RegularWorkingHours>. For work outside of these hours on weekdays, Company will charge <Charge>one hundred percent (100%) </Charge>of the regular hourly rate and <Charge>two hundred percent (200%) </Charge>for Saturdays, Sundays and public holidays applicable to Company. </RegularWorkingHours>' metadata={'xpath': '/dg:chunk/docset:MASTERSERVICESAGREEMENT-section/docset:MASTERSERVICESAGREEMENT/dg:chunk[1]/docset:Standard/dg:chunk[3]/dg:chunk[2]/docset:ADailyBasis/dg:chunk[3]/dg:chunk', 'id': 'dac7a3ded61b5c4f3e59771243ea46c1', 'name': 'Master Services Agreement - Daltech.docx', 'source': 'Master Services Agreement - Daltech.docx', 'structure': 'lim p', 'tag': 'chunk RegularWorkingHours', 'Liability': '', 'Workers Compensation Insurance': '$1,000,000', 'Limit': '$1,000,000', 'Commercial General Liability Insurance': '$2,000,000', 'Technology Professional Liability Errors Omissions Policy': '$5,000,000', 'Excess Liability Umbrella Coverage': '$9,000,000', 'Client': 'Daltech, Inc.', 'Services Agreement Date': 'INITIAL STATEMENT  OF WORK (SOW)  The purpose of this SOW is to describe the Software and Services that Company will initially provide to  Daltech, Inc.  the “Client”) under the terms and conditions of the  Services Agreement  entered into between the parties on  June 15, 2021', 'Completion of the Services by Company Date': 'February 15, 2022', 'Charge': 'one hundred percent (100%)', 'Company': 'MagicSoft, Inc.', 'Effective Date': 'February 15, 2021', 'Start Date': '03/15/2021', 'Scheduled Onsite Visits Are Cancelled': 'ten (10) working days', 'Limit on Liability': '', 'Liability Cap': '', 'Business Automobile Liability': 'Business Automobile Liability  covering all vehicles that Company owns, hires or leases with a limit of no less than  $1,000,000  (combined single limit for bodily injury and property damage) for each accident.', 'Contractual Liability Coverage': 'Commercial General Liability insurance including  Contractual Liability Coverage , with coverage for products liability, completed operations, property damage and bodily injury, including  death , with an aggregate limit of no less than  $2,000,000 . This policy shall name Client as an additional insured with respect to the provision of services provided under this Agreement. This policy shall include a waiver of subrogation against Client.', 'Technology Professional Liability Errors Omissions': 'Technology Professional Liability Errors & Omissions policy (which includes Cyber Risk coverage and Computer Security and Privacy Liability coverage) with a limit of no less than  $5,000,000  per occurrence and in the aggregate.'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "loader.min_text_length = 64\n",
+    "loader.include_xml_tags = True\n",
+    "chunks = loader.load()\n",
+    "\n",
+    "for chunk in chunks[:5]:\n",
+    "    print(chunk)"
    ]
   },
   {
@@ -136,27 +158,41 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
-    "!poetry run pip -q install openai tiktoken chromadb"
+    "!poetry run pip install --upgrade openai tiktoken chromadb hnswlib --quiet"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4674\n"
+     ]
+    }
+   ],
    "source": [
-    "from langchain.chains import RetrievalQA\n",
-    "from langchain.embeddings import OpenAIEmbeddings\n",
-    "from langchain.llms import OpenAI\n",
-    "from langchain.vectorstores import Chroma\n",
-    "\n",
     "# For this example, we already have a processed docset for a set of lease documents\n",
-    "loader = DocugamiLoader(docset_id=\"wh2kned25uqm\")\n",
-    "documents = loader.load()"
+    "loader = DocugamiLoader(docset_id=\"zo954yqy53wp\")\n",
+    "chunks = loader.load()\n",
+    "\n",
+    "# strip semantic metadata intentionally, to test how things work without semantic metadata\n",
+    "for chunk in chunks:\n",
+    "    stripped_metadata = chunk.metadata.copy()\n",
+    "    for key in chunk.metadata:\n",
+    "        if key not in [\"name\", \"xpath\", \"id\", \"structure\"]:\n",
+    "            # remove semantic metadata\n",
+    "            del stripped_metadata[key]\n",
+    "    chunk.metadata = stripped_metadata\n",
+    "\n",
+    "print(len(chunks))"
    ]
   },
   {
@@ -170,12 +206,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.llms.openai import OpenAI\n",
+    "from langchain.vectorstores.chroma import Chroma\n",
+    "\n",
     "embedding = OpenAIEmbeddings()\n",
-    "vectordb = Chroma.from_documents(documents=documents, embedding=embedding)\n",
+    "vectordb = Chroma.from_documents(documents=chunks, embedding=embedding)\n",
     "retriever = vectordb.as_retriever()\n",
     "qa_chain = RetrievalQA.from_chain_type(\n",
     "    llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=True\n",
@@ -184,21 +225,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
        "{'query': 'What can tenants do with signage on their properties?',\n",
-       " 'result': \" Tenants can place or attach signs (digital or otherwise) to their premises with written permission from the landlord. The signs must conform to all applicable laws, ordinances, etc. governing the same. Tenants can also have their name listed in the building's directory at the landlord's cost.\",\n",
-       " 'source_documents': [Document(page_content='ARTICLE VI  SIGNAGE 6.01  Signage . Tenant  may place or attach to the  Premises signs  (digital or otherwise) or other such identification as needed after receiving written permission from the  Landlord , which permission shall not be unreasonably withheld. Any damage caused to the Premises by the  Tenant ’s erecting or removing such signs shall be repaired promptly by the  Tenant  at the  Tenant ’s expense . Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same.  Tenant  also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises.', metadata={'Landlord': 'BUBBA CENTER PARTNERSHIP', 'Lease Date': 'April  24  \\n\\n ,', 'Lease Parties': 'This  OFFICE LEASE AGREEMENT  (this \"Lease\") is made and entered into by and between  BUBBA CENTER PARTNERSHIP  (\" Landlord \"), and  Truetone Lane LLC , a  Delaware  limited liability company  (\" Tenant \").', 'Tenant': 'Truetone Lane LLC', 'id': 'v1bvgaozfkak', 'source': 'TruTone Lane 2.docx', 'structure': 'div', 'tag': '_601Signage', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:Article/docset:ARTICLEVISIGNAGE-section/docset:_601Signage-section/docset:_601Signage'}),\n",
-       "  Document(page_content='Signage.  Tenant  may place or attach to the  Premises signs  (digital or otherwise) or other such identification as needed after receiving written permission from the  Landlord , which permission shall not be unreasonably withheld. Any damage caused to the Premises by the  Tenant ’s erecting or removing such signs shall be repaired promptly by the  Tenant  at the  Tenant ’s expense . Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same.  Tenant  also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises. \\n\\n                                                          ARTICLE VII  UTILITIES 7.01', metadata={'Landlord': 'GLORY ROAD LLC', 'Lease Date': 'April  30  ,  2020', 'Lease Parties': 'This  OFFICE LEASE AGREEMENT  (this  \"Lease\") is made and entered into by and between  GLORY ROAD LLC  (\" Landlord \"), and  Truetone Lane LLC , a  Delaware  limited liability company  (\" Tenant \").', 'Tenant': 'Truetone Lane LLC', 'id': 'g2fvhekmltza', 'source': 'TruTone Lane 6.pdf', 'structure': 'lim', 'tag': 'chunk', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:Article/docset:ArticleIiiUse/docset:ARTICLEIIIUSEANDCAREOFPREMISES-section/docset:ARTICLEIIIUSEANDCAREOFPREMISES/docset:AnyTime/docset:Addition/dg:chunk'}),\n",
-       "  Document(page_content='Landlord , its agents, servants, employees, licensees, invitees, and contractors during the last year of the term of this  Lease  at any and all times during regular business hours, after  24  hour  notice  to tenant, to pass and repass on and through the Premises, or such portion thereof as may be necessary, in order that they or any of them may gain access to the Premises for the purpose of showing the  Premises  to potential new tenants or real estate brokers. In addition,  Landlord  shall be entitled to place a \"FOR  RENT \" or \"FOR LEASE\" sign (not exceeding  8.5 ” x  11 ”) in the front window of the Premises during the  last  six  months  of the term of this  Lease .', metadata={'Landlord': 'BIRCH STREET ,  LLC', 'Lease Date': 'October  15 ,  2021', 'Lease Parties': 'The provisions of this rider are hereby incorporated into and made a part of the  Lease  dated as of  October  15 ,  2021  between  BIRCH STREET ,  LLC , having an address at  c/o Birch Palace ,  6  Grace Avenue Suite  200 ,  Great Neck ,  New York  11021  (\" Landlord \"), and  Trutone Lane LLC , having an address at  4  Pearl Street ,  New York ,  New York  10012  (\" Tenant \") of Premises known as the ground floor space and lower level space, as per floor plan annexed hereto and made a part hereof as  Exhibit A  (“Premises”) at  4  Pearl Street ,  New York ,  New York  10012  in the  City  of  New York ,  Borough  of  Manhattan , to which this rider is annexed. If there is any conflict between the provisions of this rider and the remainder of this  Lease , the provisions of this rider shall govern.', 'Tenant': 'Trutone Lane LLC', 'id': 'omvs4mysdk6b', 'source': 'TruTone Lane 1.docx', 'structure': 'p', 'tag': 'Landlord', 'xpath': '/docset:Rider/docset:RIDERTOLEASE-section/docset:RIDERTOLEASE/docset:FixedRent/docset:TermYearPeriod/docset:Lease/docset:_42FLandlordSAccess-section/docset:_42FLandlordSAccess/docset:LandlordsRights/docset:Landlord'}),\n",
-       "  Document(page_content=\"24. SIGNS . No signage shall be placed by  Tenant  on any portion of the  Project . However,  Tenant  shall be permitted to place a sign bearing its name in a location approved by  Landlord  near the entrance to the  Premises  (at  Tenant's cost ) and will be furnished a single listing of its name in the  Building's directory  (at  Landlord 's cost ), all in accordance with the criteria adopted  from time to time  by  Landlord  for the  Project . Any changes or additional listings in the directory shall be furnished (subject to availability of space) for the  then Building Standard charge .\", metadata={'Landlord': 'Perry  &  Blair LLC', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'dsyfhh4vpeyf', 'source': 'Shorebucks LLC_CO.pdf', 'structure': 'div', 'tag': 'SIGNS', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:ThisLease-section/docset:ThisLease/docset:Guaranty-section/docset:Guaranty[2]/docset:TheTransfer/docset:TheTerms/docset:Indemnification/docset:INDEMNIFICATION-section/docset:INDEMNIFICATION/docset:Waiver/docset:Waiver/docset:Signs/docset:SIGNS-section/docset:SIGNS'})]}"
+       " 'result': ' Tenants can place or attach signage (digital or otherwise) to their property after receiving written permission from the landlord, which permission shall not be unreasonably withheld. The signage must conform to all applicable laws, ordinances, etc. governing the same, and tenants must remove all such signs by the termination of the lease.',\n",
+       " 'source_documents': [Document(page_content='6.01 Signage. Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord, which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant’s expense. Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises. ARTICLE VII UTILITIES', metadata={'id': '1c290eea05915ba0f24c4a1ffc05d6f3', 'name': 'Sample Commercial Leases/TruTone Lane 6.pdf', 'structure': 'lim h1', 'xpath': '/dg:chunk/dg:chunk/dg:chunk[2]/dg:chunk[1]/docset:TheApprovedUse/dg:chunk[12]/dg:chunk[1]'}),\n",
+       "  Document(page_content='6.01 Signage. Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord, which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant’s expense. Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises. ARTICLE VII UTILITIES', metadata={'id': '1c290eea05915ba0f24c4a1ffc05d6f3', 'name': 'Sample Commercial Leases/TruTone Lane 2.pdf', 'structure': 'lim h1', 'xpath': '/dg:chunk/dg:chunk/dg:chunk[2]/dg:chunk[1]/docset:TheApprovedUse/dg:chunk[12]/dg:chunk[1]'}),\n",
+       "  Document(page_content='Tenant may place or attach to the Premises signs (digital or otherwise) or other such identification as needed after receiving written permission from the Landlord, which permission shall not be unreasonably withheld. Any damage caused to the Premises by the Tenant’s erecting or removing such signs shall be repaired promptly by the Tenant at the Tenant’s expense. Any signs or other form of identification allowed must conform to all applicable laws, ordinances, etc. governing the same. Tenant also agrees to have any window or glass identification completely removed and cleaned at its expense promptly upon vacating the Premises.', metadata={'id': '58d268162ecc36d8633b7bc364afcb8c', 'name': 'Sample Commercial Leases/TruTone Lane 2.docx', 'structure': 'div', 'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/dg:chunk/docset:ARTICLEVISIGNAGE-section/docset:ARTICLEVISIGNAGE/docset:_601Signage'}),\n",
+       "  Document(page_content='8. SIGNS:\\n Tenant shall not install signs upon the Premises without Landlord’s prior written approval, which approval shall not be unreasonably withheld or delayed, and any such signage shall be subject to any applicable governmental laws, ordinances, regulations, and other requirements. Tenant shall remove all such signs by the terminations of this Lease. Such installations and removals shall be made in such a manner as to avoid injury or defacement of the Building and other improvements, and Tenant shall repair any injury or defacement, including without limitation discoloration caused by such installations and/or removal.', metadata={'id': '6b7d88f0c979c65d5db088fc177fa81f', 'name': 'Lease Agreements/Bioplex, Inc.pdf', 'structure': 'lim h1 div', 'xpath': '/dg:chunk/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/docset:TheObligation/dg:chunk[8]/dg:chunk'})]}"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -212,7 +253,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Using Docugami to Add Metadata to Chunks for High Accuracy Document QA\n",
+    "## Using Docugami Knowledge Graph for High Accuracy Document QA\n",
     "\n",
     "One issue with large documents is that the correct answer to your question may depend on chunks that are far apart in the document. Typical chunking techniques, even with overlap, will struggle with providing the LLM sufficent context to answer such questions. With upcoming very large context LLMs, it may be possible to stuff a lot of tokens, perhaps even entire documents, inside the context but this will still hit limits at some point with very long documents, or a lot of documents.\n",
     "\n",
@@ -221,16 +262,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "' 9,753 square feet.'"
+       "\" I don't know.\""
       ]
      },
-     "execution_count": 8,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -240,28 +281,21 @@
     "chain_response[\"result\"]  # correct answer should be 13,500 sq ft"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "At first glance the answer may seem reasonable, but if you review the source chunks carefully for this answer, you will see that the chunking of the document did not end up putting the Landlord name and the rentable area in the same context, since they are far apart in the document. The retriever therefore ends up finding unrelated chunks from other documents not even related to the **DHA Group** landlord. That landlord happens to be mentioned on the first page of the file **Shorebucks LLC_NJ.pdf** file, and while one of the source chunks used by the chain is indeed from that doc that contains the correct answer (**13,500**), other source chunks from different docs are included, and the answer is therefore incorrect."
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='1.1 Landlord . DHA Group , a  Delaware  limited liability company  authorized to transact business in  New Jersey .', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'DhaGroup', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:DhaGroup/docset:Landlord-section/docset:DhaGroup'}),\n",
-       " Document(page_content='WITNESSES: LANDLORD: DHA Group , a  Delaware  limited liability company', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'DhaGroup', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Guaranty-section/docset:Guaranty[2]/docset:SIGNATURESONNEXTPAGE-section/docset:INWITNESSWHEREOF-section/docset:INWITNESSWHEREOF/docset:Behalf/docset:Witnesses/xhtml:table/xhtml:tbody/xhtml:tr[3]/xhtml:td[2]/docset:DhaGroup'}),\n",
-       " Document(page_content=\"1.16 Landlord 's Notice Address . DHA  Group , Suite  1010 ,  111  Bauer Dr ,  Oakland ,  New Jersey ,  07436 , with a copy to the  Building  Management  Office  at the  Project , Attention:  On - Site  Property Manager .\", metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'LandlordsNoticeAddress', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:NoticeAddress[2]/docset:LandlordsNoticeAddress-section/docset:LandlordsNoticeAddress[2]'}),\n",
-       " Document(page_content='1.6 Rentable Area  of the Premises. 9,753  square feet . This square footage figure includes an add-on factor for  Common Areas  in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'Landlord': 'Perry  &  Blair LLC', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'dsyfhh4vpeyf', 'source': 'Shorebucks LLC_CO.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:PerryBlair/docset:PerryBlair/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'})]"
+       "[Document(page_content='1.6 Rentable Area of the Premises.', metadata={'id': '5b39a1ae84d51682328dca1467be211f', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'lim h1', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:CatalystGroup/dg:chunk[6]/dg:chunk'}),\n",
+       " Document(page_content='1.6 Rentable Area of the Premises.', metadata={'id': '5b39a1ae84d51682328dca1467be211f', 'name': 'Sample Commercial Leases/Shorebucks LLC_AZ.pdf', 'structure': 'lim h1', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:MenloGroup/dg:chunk[6]/dg:chunk'}),\n",
+       " Document(page_content='1.6 Rentable Area of the Premises.', metadata={'id': '5b39a1ae84d51682328dca1467be211f', 'name': 'Sample Commercial Leases/Shorebucks LLC_FL.pdf', 'structure': 'lim h1', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:Florida-section/docset:Florida/docset:Shorebucks/dg:chunk[5]/dg:chunk'}),\n",
+       " Document(page_content='1.6 Rentable Area of the Premises.', metadata={'id': '5b39a1ae84d51682328dca1467be211f', 'name': 'Sample Commercial Leases/Shorebucks LLC_TX.pdf', 'structure': 'lim h1', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:LandmarkLlc/dg:chunk[6]/dg:chunk'})]"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -270,43 +304,42 @@
     "chain_response[\"source_documents\"]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "At first glance the answer may seem reasonable, but it is incorrect. If you review the source chunks carefully for this answer, you will see that the chunking of the document did not end up putting the Landlord name and the rentable area in the same context, and produced irrelevant chunks therefore the answer is incorrect (should be **13,500 sq ft**)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "Docugami can help here. Chunks are annotated with additional metadata created using different techniques if a user has been [using Docugami](https://help.docugami.com/home/reports). More technical approaches will be added later.\n",
     "\n",
-    "Specifically, let's look at the additional metadata that is returned on the documents returned by docugami, in the form of some simple key/value pairs on all the text chunks:"
+    "Specifically, let's ask Docugami to return XML tags on its output, as well as additional metadata:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
-     "data": {
-      "text/plain": [
-       "{'xpath': '/docset:OFFICELEASEAGREEMENT-section/docset:OFFICELEASEAGREEMENT/docset:LeaseParties',\n",
-       " 'id': 'v1bvgaozfkak',\n",
-       " 'source': 'TruTone Lane 2.docx',\n",
-       " 'structure': 'p',\n",
-       " 'tag': 'LeaseParties',\n",
-       " 'Lease Date': 'April  24  \\n\\n ,',\n",
-       " 'Landlord': 'BUBBA CENTER PARTNERSHIP',\n",
-       " 'Tenant': 'Truetone Lane LLC',\n",
-       " 'Lease Parties': 'This  OFFICE LEASE AGREEMENT  (this \"Lease\") is made and entered into by and between  BUBBA CENTER PARTNERSHIP  (\" Landlord \"), and  Truetone Lane LLC , a  Delaware  limited liability company  (\" Tenant \").'}"
-      ]
-     },
-     "execution_count": 14,
-     "metadata": {},
-     "output_type": "execute_result"
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'xpath': '/docset:OFFICELEASE-section/dg:chunk', 'id': '47297e277e556f3ce8b570047304560b', 'name': 'Sample Commercial Leases/Shorebucks LLC_AZ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_AZ.pdf', 'structure': 'h1 h1 p', 'tag': 'chunk Lease', 'Lease Date': 'March  29th , 2019', 'Landlord': 'Menlo Group', 'Tenant': 'Shorebucks LLC', 'Premises Address': '1564  E Broadway Rd ,  Tempe ,  Arizona  85282', 'Term of Lease': '96  full calendar months', 'Square Feet': '16,159'}\n"
+     ]
     }
    ],
    "source": [
-    "loader = DocugamiLoader(docset_id=\"wh2kned25uqm\")\n",
-    "documents = loader.load()\n",
-    "documents[0].metadata"
+    "loader = DocugamiLoader(docset_id=\"zo954yqy53wp\")\n",
+    "loader.include_xml_tags = (\n",
+    "    True  # for additional semantics from the Docugami knowledge graph\n",
+    ")\n",
+    "chunks = loader.load()\n",
+    "print(chunks[0].metadata)"
    ]
   },
   {
@@ -318,12 +351,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!poetry run pip install --upgrade lark --quiet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.chains.query_constructor.schema import AttributeInfo\n",
     "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain.vectorstores.chroma import Chroma\n",
     "\n",
     "EXCLUDE_KEYS = [\"id\", \"xpath\", \"structure\"]\n",
     "metadata_field_info = [\n",
@@ -332,19 +375,23 @@
     "        description=f\"The {key} for this chunk\",\n",
     "        type=\"string\",\n",
     "    )\n",
-    "    for key in documents[0].metadata\n",
+    "    for key in chunks[0].metadata\n",
     "    if key.lower() not in EXCLUDE_KEYS\n",
     "]\n",
     "\n",
-    "\n",
     "document_content_description = \"Contents of this chunk\"\n",
     "llm = OpenAI(temperature=0)\n",
-    "vectordb = Chroma.from_documents(documents=documents, embedding=embedding)\n",
+    "\n",
+    "vectordb = Chroma.from_documents(documents=chunks, embedding=embedding)\n",
     "retriever = SelfQueryRetriever.from_llm(\n",
     "    llm, vectordb, document_content_description, metadata_field_info, verbose=True\n",
     ")\n",
     "qa_chain = RetrievalQA.from_chain_type(\n",
-    "    llm=OpenAI(), chain_type=\"stuff\", retriever=retriever, return_source_documents=True\n",
+    "    llm=OpenAI(),\n",
+    "    chain_type=\"stuff\",\n",
+    "    retriever=retriever,\n",
+    "    return_source_documents=True,\n",
+    "    verbose=True,\n",
     ")"
    ]
   },
@@ -357,36 +404,32 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/root/Source/github/docugami.langchain/libs/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
-      "  warnings.warn(\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "query='rentable area' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='Landlord', value='DHA Group') limit=None\n"
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new RetrievalQA chain...\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
      "data": {
       "text/plain": [
        "{'query': 'What is rentable area for the property owned by DHA Group?',\n",
-       " 'result': ' The rentable area for the property owned by DHA Group is 13,500 square feet.',\n",
-       " 'source_documents': [Document(page_content='1.6 Rentable Area  of the Premises. 13,500  square feet . This square footage figure includes an add-on factor for  Common Areas  in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'}),\n",
-       "  Document(page_content='1.6 Rentable Area  of the Premises. 13,500  square feet . This square footage figure includes an add-on factor for  Common Areas  in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party.', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:TheTerms/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/docset:DhaGroup/docset:Premises[2]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'}),\n",
-       "  Document(page_content='1.11 Percentage Rent . (a) 55 %  of  Gross Revenue  to  Landlord  until  Landlord  receives  Percentage Rent  in an amount equal to the  Annual Market Rent Hurdle  (as escalated); and', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'GrossRevenue', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent-section/docset:PercentageRent[2]/docset:PercentageRent/docset:GrossRevenue[1]/docset:GrossRevenue'}),\n",
-       "  Document(page_content='1.11 Percentage Rent . (a) 55 %  of  Gross Revenue  to  Landlord  until  Landlord  receives  Percentage Rent  in an amount equal to the  Annual Market Rent Hurdle  (as escalated); and', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th ,  2019', 'Lease Parties': 'THIS OFFICE LEASE  (the \"Lease\") is made and entered into as of  March  29th ,  2019 , by and between  Landlord  and  Tenant . \"Date of this Lease\" shall mean the date on which the last one of the  Landlord  and  Tenant  has signed this  Lease .', 'Tenant': 'Shorebucks LLC', 'id': 'md8rieecquyv', 'source': 'Shorebucks LLC_NJ.pdf', 'structure': 'p', 'tag': 'GrossRevenue', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:THISOFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCreditTheRentCredit-section/docset:GrossRentCreditTheRentCredit/docset:Period/docset:ApplicableSalesTax/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent/docset:PercentageRent-section/docset:PercentageRent[2]/docset:PercentageRent/docset:GrossRevenue[1]/docset:GrossRevenue'})]}"
+       " 'result': ' The rentable area of the property owned by DHA Group is 13,500 square feet.',\n",
+       " 'source_documents': [Document(page_content='1.6 Rentable Area of the Premises.', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th , 2019', 'Premises Address': '111  Bauer Dr ,  Oakland ,  New Jersey ,  07436', 'Square Feet': '13,500', 'Tenant': 'Shorebucks LLC', 'Term of Lease': '84  full calendar  months', 'id': '5b39a1ae84d51682328dca1467be211f', 'name': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'structure': 'lim h1', 'tag': 'chunk', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/dg:chunk[6]/dg:chunk'}),\n",
+       "  Document(page_content='<RentableAreaofthePremises><SquareFeet>13,500 </SquareFeet>square feet. This square footage figure includes an add-on factor for Common Areas in the Building and has been agreed upon by the parties as final and correct and is not subject to challenge or dispute by either party. </RentableAreaofthePremises>', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th , 2019', 'Premises Address': '111  Bauer Dr ,  Oakland ,  New Jersey ,  07436', 'Square Feet': '13,500', 'Tenant': 'Shorebucks LLC', 'Term of Lease': '84  full calendar  months', 'id': '4c06903d087f5a83e486ee42cd702d31', 'name': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'RentableAreaofthePremises', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/docset:DhaGroup/dg:chunk[6]/docset:RentableAreaofthePremises-section/docset:RentableAreaofthePremises'}),\n",
+       "  Document(page_content='<TheTermAnnualMarketRent>shall mean (i) for the initial Lease Year (“Year 1”) <Money>$2,239,748.00 </Money>per year (i.e., the product of the Rentable Area of the Premises multiplied by <Money>$82.00</Money>) (the “Year 1 Market Rent Hurdle”); (ii) for the Lease Year thereafter, <Percent>one hundred three percent (103%) </Percent>of the Year 1 Market Rent Hurdle, and (iii) for each Lease Year thereafter until the termination or expiration of this Lease, the Annual Market Rent Threshold shall be <AnnualMarketRentThreshold>one hundred three percent (103%) </AnnualMarketRentThreshold>of the Annual Market Rent Threshold for the immediately prior Lease Year. </TheTermAnnualMarketRent>', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th , 2019', 'Premises Address': '111  Bauer Dr ,  Oakland ,  New Jersey ,  07436', 'Square Feet': '13,500', 'Tenant': 'Shorebucks LLC', 'Term of Lease': '84  full calendar  months', 'id': '6b90beeadace5d4d12b25706fb48e631', 'name': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'structure': 'div', 'tag': 'TheTermAnnualMarketRent', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCredit-section/docset:GrossRentCredit/dg:chunk/dg:chunk/dg:chunk/dg:chunk[2]/docset:PercentageRent/dg:chunk[2]/dg:chunk[2]/docset:TenantSRevenue/dg:chunk[2]/docset:TenantSRevenue/dg:chunk[3]/docset:TheTermAnnualMarketRent-section/docset:TheTermAnnualMarketRent'}),\n",
+       "  Document(page_content='1.11 Percentage Rent.\\n (a) <GrossRevenue><Percent>55% </Percent>of Gross Revenue to Landlord until Landlord receives Percentage Rent in an amount equal to the Annual Market Rent Hurdle (as escalated); and </GrossRevenue>', metadata={'Landlord': 'DHA Group', 'Lease Date': 'March  29th , 2019', 'Premises Address': '111  Bauer Dr ,  Oakland ,  New Jersey ,  07436', 'Square Feet': '13,500', 'Tenant': 'Shorebucks LLC', 'Term of Lease': '84  full calendar  months', 'id': 'c8bb9cbedf65a578d9db3f25f519dd3d', 'name': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'structure': 'lim h1 lim p', 'tag': 'chunk GrossRevenue', 'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/docset:GrossRentCredit-section/docset:GrossRentCredit/dg:chunk/dg:chunk/dg:chunk/docset:PercentageRent/dg:chunk[1]/dg:chunk[1]'})]}"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -403,6 +446,198 @@
    "source": [
     "This time the answer is correct, since the self-querying retriever created a filter on the landlord attribute of the metadata, correctly filtering to document that specifically is about the DHA Group landlord. The resulting source chunks are all relevant to this landlord, and this improves answer accuracy even though the landlord is not directly mentioned in the specific chunk that contains the correct answer."
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Advanced Topic: Small-to-Big Retrieval with Document Knowledge Graph Hierarchy"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Documents are inherently semi-structured and the DocugamiLoader is able to navigate the semantic and structural contours of the document to provide parent chunk references on the chunks it returns. This is useful e.g. with the [MultiVector Retriever](https://python.langchain.com/docs/modules/data_connection/retrievers/multi_vector) for [small-to-big](https://www.youtube.com/watch?v=ihSiRrOUwmg) retrieval.\n",
+    "\n",
+    "To get parent chunk references, you can set `loader.parent_hierarchy_levels` to a non-zero value."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Dict, List\n",
+    "\n",
+    "from langchain.document_loaders import DocugamiLoader\n",
+    "from langchain.schema.document import Document\n",
+    "\n",
+    "loader = DocugamiLoader(docset_id=\"zo954yqy53wp\")\n",
+    "loader.include_xml_tags = (\n",
+    "    True  # for additional semantics from the Docugami knowledge graph\n",
+    ")\n",
+    "loader.parent_hierarchy_levels = 3  # for expanded context\n",
+    "loader.max_text_length = (\n",
+    "    1024 * 8\n",
+    ")  # 8K chars are roughly 2K tokens (ref: https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them)\n",
+    "loader.include_project_metadata_in_doc_metadata = (\n",
+    "    False  # Not filtering on vector metadata, so remove to lighten the vectors\n",
+    ")\n",
+    "chunks: List[Document] = loader.load()\n",
+    "\n",
+    "# build separate maps of parent and child chunks\n",
+    "parents_by_id: Dict[str, Document] = {}\n",
+    "children_by_id: Dict[str, Document] = {}\n",
+    "for chunk in chunks:\n",
+    "    chunk_id = chunk.metadata.get(\"id\")\n",
+    "    parent_chunk_id = chunk.metadata.get(loader.parent_id_key)\n",
+    "    if not parent_chunk_id:\n",
+    "        # parent chunk\n",
+    "        parents_by_id[chunk_id] = chunk\n",
+    "    else:\n",
+    "        # child chunk\n",
+    "        children_by_id[chunk_id] = chunk"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "PARENT CHUNK 7df09fbfc65bb8377054808aac2d16fd: page_content='OFFICE LEASE\\n THIS OFFICE LEASE\\n <Lease>(the \"Lease\") is made and entered into as of <LeaseDate>March 29th, 2019</LeaseDate>, by and between Landlord and Tenant. \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease. </Lease>\\nW I T N E S S E T H\\n <TheTerms> Subject to and on the terms and conditions of this Lease, Landlord leases to Tenant and Tenant hires from Landlord the Premises. </TheTerms>\\n1. BASIC LEASE INFORMATION AND DEFINED TERMS.\\nThe key business terms of this Lease and the defined terms used in this Lease are as follows:' metadata={'xpath': '/docset:OFFICELEASE-section/dg:chunk', 'id': '7df09fbfc65bb8377054808aac2d16fd', 'name': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'structure': 'h1 h1 p h1 p lim h1 p', 'tag': 'chunk Lease chunk TheTerms'}\n",
+      "CHUNK 47297e277e556f3ce8b570047304560b: page_content='OFFICE LEASE\\n THIS OFFICE LEASE\\n <Lease>(the \"Lease\") is made and entered into as of <LeaseDate>March 29th, 2019</LeaseDate>, by and between Landlord and Tenant. \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease. </Lease>' metadata={'xpath': '/docset:OFFICELEASE-section/dg:chunk', 'id': '47297e277e556f3ce8b570047304560b', 'name': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_NJ.pdf', 'structure': 'h1 h1 p', 'tag': 'chunk Lease', 'doc_id': '7df09fbfc65bb8377054808aac2d16fd'}\n",
+      "PARENT CHUNK bb84925da3bed22c30ea1bdc173ff54f: page_content='OFFICE LEASE\\n THIS OFFICE LEASE\\n <Lease>(the \"Lease\") is made and entered into as of <LeaseDate>January 8th, 2018</LeaseDate>, by and between Landlord and Tenant. \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease. </Lease>\\nW I T N E S S E T H\\n <TheTerms> Subject to and on the terms and conditions of this Lease, Landlord leases to Tenant and Tenant hires from Landlord the Premises. </TheTerms>\\n1. BASIC LEASE INFORMATION AND DEFINED TERMS.\\nThe key business terms of this Lease and the defined terms used in this Lease are as follows:\\n1.1 Landlord.\\n <Landlord>Catalyst Group LLC </Landlord>' metadata={'xpath': '/docset:OFFICELEASE-section/dg:chunk', 'id': 'bb84925da3bed22c30ea1bdc173ff54f', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'h1 h1 p h1 p lim h1 p lim h1 div', 'tag': 'chunk Lease chunk TheTerms chunk Landlord'}\n",
+      "CHUNK 2f1746cbd546d1d61a9250c50de7a7fa: page_content='W I T N E S S E T H\\n <TheTerms> Subject to and on the terms and conditions of this Lease, Landlord leases to Tenant and Tenant hires from Landlord the Premises. </TheTerms>' metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/dg:chunk', 'id': '2f1746cbd546d1d61a9250c50de7a7fa', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'h1 p', 'tag': 'chunk TheTerms', 'doc_id': 'bb84925da3bed22c30ea1bdc173ff54f'}\n",
+      "PARENT CHUNK 0b0d765b6e504a6ba54fa76b203e62ec: page_content='OFFICE LEASE\\n THIS OFFICE LEASE\\n <Lease>(the \"Lease\") is made and entered into as of <LeaseDate>January 8th, 2018</LeaseDate>, by and between Landlord and Tenant. \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease. </Lease>\\nW I T N E S S E T H\\n <TheTerms> Subject to and on the terms and conditions of this Lease, Landlord leases to Tenant and Tenant hires from Landlord the Premises. </TheTerms>\\n1. BASIC LEASE INFORMATION AND DEFINED TERMS.\\nThe key business terms of this Lease and the defined terms used in this Lease are as follows:\\n1.1 Landlord.\\n <Landlord>Catalyst Group LLC </Landlord>\\n1.2 Tenant.\\n <Tenant>Shorebucks LLC </Tenant>' metadata={'xpath': '/docset:OFFICELEASE-section/dg:chunk', 'id': '0b0d765b6e504a6ba54fa76b203e62ec', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'h1 h1 p h1 p lim h1 p lim h1 div lim h1 div', 'tag': 'chunk Lease chunk TheTerms chunk Landlord chunk Tenant'}\n",
+      "CHUNK b362dfe776ec5a7a66451a8c7c220b59: page_content='1. BASIC LEASE INFORMATION AND DEFINED TERMS.' metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/dg:chunk', 'id': 'b362dfe776ec5a7a66451a8c7c220b59', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'lim h1', 'tag': 'chunk', 'doc_id': '0b0d765b6e504a6ba54fa76b203e62ec'}\n",
+      "PARENT CHUNK c942010baaf76aa4d4657769492f6edb: page_content='OFFICE LEASE\\n THIS OFFICE LEASE\\n <Lease>(the \"Lease\") is made and entered into as of <LeaseDate>January 8th, 2018</LeaseDate>, by and between Landlord and Tenant. \"Date of this Lease\" shall mean the date on which the last one of the Landlord and Tenant has signed this Lease. </Lease>\\nW I T N E S S E T H\\n <TheTerms> Subject to and on the terms and conditions of this Lease, Landlord leases to Tenant and Tenant hires from Landlord the Premises. </TheTerms>\\n1. BASIC LEASE INFORMATION AND DEFINED TERMS.\\nThe key business terms of this Lease and the defined terms used in this Lease are as follows:\\n1.1 Landlord.\\n <Landlord>Catalyst Group LLC </Landlord>\\n1.2 Tenant.\\n <Tenant>Shorebucks LLC </Tenant>\\n1.3 Building.\\n <Building>The building containing the Premises located at <PremisesAddress><PremisesStreetAddress><MainStreet>600 </MainStreet><StreetName>Main Street</StreetName></PremisesStreetAddress>, <City>Bellevue</City>, <State>WA</State>, <Premises>98004</Premises></PremisesAddress>. The Building is located within the Project. </Building>' metadata={'xpath': '/docset:OFFICELEASE-section/dg:chunk', 'id': 'c942010baaf76aa4d4657769492f6edb', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'h1 h1 p h1 p lim h1 p lim h1 div lim h1 div lim h1 div', 'tag': 'chunk Lease chunk TheTerms chunk Landlord chunk Tenant chunk Building'}\n",
+      "CHUNK a95971d693b7aa0f6640df1fbd18c2ba: page_content='The key business terms of this Lease and the defined terms used in this Lease are as follows:' metadata={'xpath': '/docset:OFFICELEASE-section/docset:OFFICELEASE-section/docset:OFFICELEASE/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk/dg:chunk/docset:BasicLeaseInformation/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS-section/docset:BASICLEASEINFORMATIONANDDEFINEDTERMS/dg:chunk', 'id': 'a95971d693b7aa0f6640df1fbd18c2ba', 'name': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'source': 'Sample Commercial Leases/Shorebucks LLC_WA.pdf', 'structure': 'p', 'tag': 'chunk', 'doc_id': 'c942010baaf76aa4d4657769492f6edb'}\n",
+      "PARENT CHUNK f34b649cde7fc4ae156849a56d690495: page_content='W I T N E S S E T H\\n <TheTerms> Subject to and on the terms and conditions of this Lease, Landlord leases to Tenant and Tenant hires from Landlord the Premises. </TheTerms>\\n1. BASIC LEASE INFORMATION AND DEFINED TERMS.\\n<BASICLEASEINFORMATIONANDDEFINEDTERMS>The key business terms of this Lease and the defined terms used in this Lease are as follows: </BASICLEASEINFORMATIONANDDEFINEDTERMS>\\n1.1 Landlord.\\n <Landlord><Landlord>Menlo Group</Landlord>, a <USState>Delaware </USState>limited liability company authorized to transact business in <USState>Arizona</USState>. </Landlord>\\n1.2 Tenant.\\n <Tenant>Shorebucks LLC </Tenant>\\n1.3 Building.\\n <Building>The building containing the Premises located at <PremisesAddress><PremisesStreetAddress><Premises>1564 </Premises><Premises>E Broadway Rd</Premises></PremisesStreetAddress>, <City>Tempe</City>, <USState>Arizona </USState><Premises>85282</Premises></PremisesAddress>. The Building is located within the Project. </Building>\\n1.4 Project.\\n <Project>The parcel of land and the buildings and improvements located on such land known as Shorebucks Office <ShorebucksOfficeAddress><ShorebucksOfficeStreetAddress><ShorebucksOffice>6 </ShorebucksOffice><ShorebucksOffice6>located at <Number>1564 </Number>E Broadway Rd</ShorebucksOffice6></ShorebucksOfficeStreetAddress>, <City>Tempe</City>, <USState>Arizona </USState><Number>85282</Number></ShorebucksOfficeAddress>. The Project is legally described in EXHIBIT \"A\" to this Lease. </Project>' metadata={'xpath': '/dg:chunk/docset:WITNESSETH-section/dg:chunk', 'id': 'f34b649cde7fc4ae156849a56d690495', 'name': 'Sample Commercial Leases/Shorebucks LLC_AZ.docx', 'source': 'Sample Commercial Leases/Shorebucks LLC_AZ.docx', 'structure': 'h1 p lim h1 div lim h1 div lim h1 div lim h1 div lim h1 div', 'tag': 'chunk TheTerms BASICLEASEINFORMATIONANDDEFINEDTERMS chunk Landlord chunk Tenant chunk Building chunk Project'}\n",
+      "CHUNK 21b4d9517f7ccdc0e3a028ce5043a2a0: page_content='1.1 Landlord.\\n <Landlord><Landlord>Menlo Group</Landlord>, a <USState>Delaware </USState>limited liability company authorized to transact business in <USState>Arizona</USState>. </Landlord>' metadata={'xpath': '/dg:chunk/docset:WITNESSETH-section/docset:WITNESSETH/dg:chunk[1]/dg:chunk[1]/dg:chunk/dg:chunk[2]/dg:chunk', 'id': '21b4d9517f7ccdc0e3a028ce5043a2a0', 'name': 'Sample Commercial Leases/Shorebucks LLC_AZ.docx', 'source': 'Sample Commercial Leases/Shorebucks LLC_AZ.docx', 'structure': 'lim h1 div', 'tag': 'chunk Landlord', 'doc_id': 'f34b649cde7fc4ae156849a56d690495'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Explore some of the parent chunk relationships\n",
+    "for id, chunk in list(children_by_id.items())[:5]:\n",
+    "    parent_chunk_id = chunk.metadata.get(loader.parent_id_key)\n",
+    "    if parent_chunk_id:\n",
+    "        # child chunks have the parent chunk id set\n",
+    "        print(f\"PARENT CHUNK {parent_chunk_id}: {parents_by_id[parent_chunk_id]}\")\n",
+    "        print(f\"CHUNK {id}: {chunk}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "from langchain.retrievers.multi_vector import MultiVectorRetriever, SearchType\n",
+    "from langchain.storage import InMemoryStore\n",
+    "from langchain.vectorstores.chroma import Chroma\n",
+    "\n",
+    "# The vectorstore to use to index the child chunks\n",
+    "vectorstore = Chroma(collection_name=\"big2small\", embedding_function=OpenAIEmbeddings())\n",
+    "\n",
+    "# The storage layer for the parent documents\n",
+    "store = InMemoryStore()\n",
+    "\n",
+    "# The retriever (empty to start)\n",
+    "retriever = MultiVectorRetriever(\n",
+    "    vectorstore=vectorstore,\n",
+    "    docstore=store,\n",
+    "    search_type=SearchType.mmr,  # use max marginal relevance search\n",
+    "    search_kwargs={\"k\": 2},\n",
+    ")\n",
+    "\n",
+    "# Add child chunks to vector store\n",
+    "retriever.vectorstore.add_documents(list(children_by_id.values()))\n",
+    "\n",
+    "# Add parent chunks to docstore\n",
+    "retriever.docstore.mset(parents_by_id.items())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "24. SIGNS.\n",
+      " <SIGNS>No signage shall be placed by Tenant on any portion of the Project. However, Tenant shall be permitted to place a sign bearing its name in a location approved by Landlord near the entrance to the Premises (at Tenant's cost) and will be furnished a single listing of its name in the Building's directory (at Landlord's cost), all in accordance with the criteria adopted <Frequency>from time to time </Frequency>by Landlord for the Project. Any changes or additional listings in the directory shall be furnished (subject to availability of space) for the then Building Standard charge. </SIGNS>\n",
+      "43090337ed2409e0da24ee07e2adbe94\n",
+      "<TheExterior> Tenant agrees that all signs, awnings, protective gates, security devices and other installations visible from the exterior of the Premises shall be subject to Landlord's prior written approval, shall be subject to the prior approval of the <Org>Landmarks </Org><Landmarks>Preservation Commission </Landmarks>of the City of <USState>New <Org>York</Org></USState>, if required, and shall not interfere with or block either of the adjacent stores, provided, however, that Landlord shall not unreasonably withhold consent for signs that Tenant desires to install. Tenant agrees that any permitted signs, awnings, protective gates, security devices, and other installations shall be installed at Tenant’s sole cost and expense professionally prepared and dignified and subject to Landlord's prior written approval, which shall not be unreasonably withheld, delayed or conditioned, and subject to such reasonable rules and restrictions as Landlord <Frequency>from time to time </Frequency>may impose. Tenant shall submit to Landlord drawings of the proposed signs and other installations, showing the size, color, illumination and general appearance thereof, together with a statement of the manner in which the same are to be affixed to the Premises. Tenant shall not commence the installation of the proposed signs and other installations unless and until Landlord shall have approved the same in writing. . Tenant shall not install any neon sign. The aforesaid signs shall be used solely for the purpose of identifying Tenant's business. No changes shall be made in the signs and other installations without first obtaining Landlord's prior written consent thereto, which consent shall not be unreasonably withheld, delayed or conditioned. Tenant shall, at its own cost and expense, obtain and exhibit to Landlord such permits or certificates of approval as Tenant may be required to obtain from any and all City, State and other authorities having jurisdiction covering the erection, installation, maintenance or use of said signs or other installations, and Tenant shall maintain the said signs and other installations together with any appurtenances thereto in good order and condition and to the satisfaction of the Landlord and in accordance with any and all orders, regulations, requirements and rules of any public authorities having jurisdiction thereover. Landlord consents to Tenant’s Initial Signage described in annexed Exhibit D. </TheExterior>\n",
+      "54ddfc3e47f41af7e747b2bc439ea96b\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Query vector store directly, should return chunks\n",
+    "found_chunks = vectorstore.similarity_search(\n",
+    "    \"what signs does Birch Street allow on their property?\", k=2\n",
+    ")\n",
+    "\n",
+    "for chunk in found_chunks:\n",
+    "    print(chunk.page_content)\n",
+    "    print(chunk.metadata[loader.parent_id_key])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "21. SERVICES AND UTILITIES.\n",
+      " <SERVICESANDUTILITIES>Landlord shall have no obligation to provide any utilities or services to the Premises other than passenger elevator service to the Premises. Tenant shall be solely responsible for and shall promptly pay all charges for water, electricity, or any other utility used or consumed in the Premises, including all costs associated with separately metering for the Premises. Tenant shall be responsible for repairs and maintenance to exit lighting, emergency lighting, and fire extinguishers for the Premises. Tenant is responsible for interior janitorial, pest control, and waste removal services. Landlord may at any time change the electrical utility provider for the Building. Tenant’s use of electrical, HVAC, or other services furnished by Landlord shall not exceed, either in voltage, rated capacity, use, or overall load, that which Landlord deems to be standard for the Building. In no event shall Landlord be liable for damages resulting from the failure to furnish any service, and any interruption or failure shall in no manner entitle Tenant to any remedies including abatement of Rent. If at any time during the Lease Term the Project has any type of card access system for the Parking Areas or the Building, Tenant shall purchase access cards for all occupants of the Premises from Landlord at a Building Standard charge and shall comply with Building Standard terms relating to access to the Parking Areas and the Building. </SERVICESANDUTILITIES>\n",
+      "22. SECURITY DEPOSIT.\n",
+      " <SECURITYDEPOSIT>The Security Deposit shall be held by Landlord as security for Tenant's full and faithful performance of this Lease including the payment of Rent. Tenant grants Landlord a security interest in the Security Deposit. The Security Deposit may be commingled with other funds of Landlord and Landlord shall have no liability for payment of any interest on the Security Deposit. Landlord may apply the Security Deposit to the extent required to cure any default by Tenant. If Landlord so applies the Security Deposit, Tenant shall deliver to Landlord the amount necessary to replenish the Security Deposit to its original sum within <Deliver>five days </Deliver>after notice from Landlord. The Security Deposit shall not be deemed an advance payment of Rent or a measure of damages for any default by Tenant, nor shall it be a defense to any action that Landlord may bring against Tenant. </SECURITYDEPOSIT>\n",
+      "23. GOVERNMENTAL REGULATIONS.\n",
+      " <GOVERNMENTALREGULATIONS>Tenant, at Tenant's sole cost and expense, shall promptly comply (and shall cause all subtenants and licensees to comply) with all laws, codes, and ordinances of governmental authorities, including the Americans with Disabilities Act of <AmericanswithDisabilitiesActDate>1990 </AmericanswithDisabilitiesActDate>as amended (the \"ADA\"), and all recorded covenants and restrictions affecting the Project, pertaining to Tenant, its conduct of business, and its use and occupancy of the Premises, including the performance of any work to the Common Areas required because of Tenant's specific use (as opposed to general office use) of the Premises or Alterations to the Premises made by Tenant. </GOVERNMENTALREGULATIONS>\n",
+      "24. SIGNS.\n",
+      " <SIGNS>No signage shall be placed by Tenant on any portion of the Project. However, Tenant shall be permitted to place a sign bearing its name in a location approved by Landlord near the entrance to the Premises (at Tenant's cost) and will be furnished a single listing of its name in the Building's directory (at Landlord's cost), all in accordance with the criteria adopted <Frequency>from time to time </Frequency>by Landlord for the Project. Any changes or additional listings in the directory shall be furnished (subject to availability of space) for the then Building Standard charge. </SIGNS>\n",
+      "25. BROKER.\n",
+      " <BROKER>Landlord and Tenant each represent and warrant that they have neither consulted nor negotiated with any broker or finder regarding the Premises, except the Landlord's Broker and Tenant's Broker. Tenant shall indemnify, defend, and hold Landlord harmless from and against any claims for commissions from any real estate broker other than Landlord's Broker and Tenant's Broker with whom Tenant has dealt in connection with this Lease. Landlord shall indemnify, defend, and hold Tenant harmless from and against payment of any leasing commission due Landlord's Broker and Tenant's Broker in connection with this Lease and any claims for commissions from any real estate broker other than Landlord's Broker and Tenant's Broker with whom Landlord has dealt in connection with this Lease. The terms of this article shall survive the expiration or earlier termination of this Lease. </BROKER>\n",
+      "26. END OF TERM.\n",
+      " <ENDOFTERM>Tenant shall surrender the Premises to Landlord at the expiration or sooner termination of this Lease or Tenant's right of possession in good order and condition, broom-clean, except for reasonable wear and tear. All Alterations made by Landlord or Tenant to the Premises shall become Landlord's property on the expiration or sooner termination of the Lease Term. On the expiration or sooner termination of the Lease Term, Tenant, at its expense, shall remove from the Premises all of Tenant's personal property, all computer and telecommunications wiring, and all Alterations that Landlord designates by notice to Tenant. Tenant shall also repair any damage to the Premises caused by the removal. Any items of Tenant's property that shall remain in the Premises after the expiration or sooner termination of the Lease Term, may, at the option of Landlord and without notice, be deemed to have been abandoned, and in that case, those items may be retained by Landlord as its property to be disposed of by Landlord, without accountability or notice to Tenant or any other party, in the manner Landlord shall determine, at Tenant's expense. </ENDOFTERM>\n",
+      "27. ATTORNEYS' FEES.\n",
+      " <ATTORNEYSFEES>Except as otherwise provided in this Lease, the prevailing party in any litigation or other dispute resolution proceeding, including arbitration, arising out of or in any manner based on or relating to this Lease, including tort actions and actions for injunctive, declaratory, and provisional relief, shall be entitled to recover from the losing party actual attorneys' fees and costs, including fees for litigating the entitlement to or amount of fees or costs owed under this provision, and fees in connection with bankruptcy, appellate, or collection proceedings. No person or entity other than Landlord or Tenant has any right to recover fees under this paragraph. In addition, if Landlord becomes a party to any suit or proceeding affecting the Premises or involving this Lease or Tenant's interest under this Lease, other than a suit between Landlord and Tenant, or if Landlord engages counsel to collect any of the amounts owed under this Lease, or to enforce performance of any of the agreements, conditions, covenants, provisions, or stipulations of this Lease, without commencing litigation, then the costs, expenses, and reasonable attorneys' fees and disbursements incurred by Landlord shall be paid to Landlord by Tenant. </ATTORNEYSFEES>\n",
+      "43090337ed2409e0da24ee07e2adbe94\n",
+      "<TenantsSoleCost> Tenant, at Tenant's sole cost and expense, shall be responsible for the removal and disposal of all of garbage, waste, and refuse from the Premises on a <Frequency>daily </Frequency>basis. Tenant shall cause all garbage, waste and refuse to be stored within the Premises until <Stored>thirty (30) minutes </Stored>before closing, except that Tenant shall be permitted, to the extent permitted by law, to place garbage outside the Premises after the time specified in the immediately preceding sentence for pick up prior to <PickUp>6:00 A.M. </PickUp>next following. Garbage shall be placed at the edge of the sidewalk in front of the Premises at the location furthest from he main entrance to the Building or such other location in front of the Building as may be specified by Landlord. </TenantsSoleCost>\n",
+      "<ItsSoleCost> Tenant, at its sole cost and expense, agrees to use all reasonable diligence in accordance with the best prevailing methods for the prevention and extermination of vermin, rats, and mice, mold, fungus, allergens, <Bacterium>bacteria </Bacterium>and all other similar conditions in the Premises. Tenant, at Tenant's expense, shall cause the Premises to be exterminated <Exterminated>from time to time </Exterminated>to the reasonable satisfaction of Landlord and shall employ licensed exterminating companies. Landlord shall not be responsible for any cleaning, waste removal, janitorial, or similar services for the Premises, and Tenant sha ll not be entitled to seek any abatement, setoff or credit from the Landlord in the event any conditions described in this Article are found to exist in the Premises. </ItsSoleCost>\n",
+      "42B. Sidewalk Use and Maintenance\n",
+      "<TheSidewalk> Tenant shall, at its sole cost and expense, keep the sidewalk in front of the Premises 18 inches into the street from the curb clean free of garbage, waste, refuse, excess water, snow, and ice and Tenant shall pay, as additional rent, any fine, cost, or expense caused by Tenant's failure to do so. In the event Tenant operates a sidewalk café, Tenant shall, at its sole cost and expense, maintain, repair, and replace as necessary, the sidewalk in front of the Premises and the metal trapdoor leading to the basement of the Premises, if any. Tenant shall post warning signs and cones on all sides of any side door when in use and attach a safety bar across any such door at all times when open. </TheSidewalk>\n",
+      "<Display> In no event shall Tenant use, or permit to be used, the space adjacent to or any other space outside of the Premises, for display, sale or any other similar undertaking; except [1] in the event of a legal and licensed “street fair” type program or [<Number>2</Number>] if the local zoning, Community Board [if applicable] and other municipal laws, rules and regulations, allow for sidewalk café use and, if such I s the case, said operation shall be in strict accordance with all of the aforesaid requirements and conditions. . In no event shall Tenant use, or permit to be used, any advertising medium and/or loud speaker and/or sound amplifier and/or radio or television broadcast which may be heard outside of the Premises or which does not comply with the reasonable rules and regulations of Landlord which then will be in effect. </Display>\n",
+      "42C. Store Front Maintenance\n",
+      " <TheBulkheadAndSecurityGate> Tenant agrees to wash the storefront, including the bulkhead and security gate, from the top to the ground, monthly or more often as Landlord reasonably requests and make all repairs and replacements as and when deemed necessary by Landlord, to all windows and plate and ot her glass in or about the Premises and the security gate, if any. In case of any default by Tenant in maintaining the storefront as herein provided, Landlord may do so at its own expense and bill the cost thereof to Tenant as additional rent. </TheBulkheadAndSecurityGate>\n",
+      "42D. Music, Noise, and Vibration\n",
+      "4474c92ae7ccec9184ed2fef9f072734\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Query retriever, should return parents (using MMR since that was set as search_type above)\n",
+    "retrieved_parent_docs = retriever.get_relevant_documents(\n",
+    "    \"what signs does Birch Street allow on their property?\"\n",
+    ")\n",
+    "for chunk in retrieved_parent_docs:\n",
+    "    print(chunk.page_content)\n",
+    "    print(chunk.metadata[\"id\"])"
+   ]
   }
  ],
  "metadata": {

docs/docs/integrations/document_loaders/example_data/notebook.md

@@ -1,29 +0,0 @@
-# Notebook
-
-This notebook covers how to load data from an .ipynb notebook into a format suitable by LangChain.
-
-
-
-
-```python
-from langchain.document_loaders import NotebookLoader
-```
-
-
-```python
-loader = NotebookLoader("example_data/notebook.ipynb")
-```
-
-`NotebookLoader.load()` loads the `.ipynb` notebook file into a `Document` object.
-
-**Parameters**:
-
-* `include_outputs` (bool): whether to include cell outputs in the resulting document (default is False).
-* `max_output_length` (int): the maximum number of characters to include from each cell output (default is 10).
-* `remove_newline` (bool): whether to remove newline characters from the cell sources and outputs (default is False).
-* `traceback` (bool): whether to include full traceback (default is False).
-
-
-```python
-loader.load(include_outputs=True, max_output_length=20, remove_newline=True)
-```

docs/docs/integrations/document_loaders/onenote.ipynb

@@ -0,0 +1,118 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6125a85e",
+   "metadata": {},
+   "source": [
+    "# Microsoft OneNote\n",
+    "\n",
+    "This notebook covers how to load documents from `OneNote`.\n",
+    "\n",
+    "## Prerequisites\n",
+    "1. Register an application with the [Microsoft identity platform](https://learn.microsoft.com/en-us/azure/active-directory/develop/quickstart-register-app) instructions.\n",
+    "2. When registration finishes, the Azure portal displays the app registration's Overview pane. You see the Application (client) ID. Also called the `client ID`, this value uniquely identifies your application in the Microsoft identity platform.\n",
+    "3. During the steps you will be following at **item 1**, you can set the redirect URI as `http://localhost:8000/callback`\n",
+    "4. During the steps you will be following at **item 1**, generate a new password (`client_secret`) under Application Secrets section.\n",
+    "5. Follow the instructions at this [document](https://learn.microsoft.com/en-us/azure/active-directory/develop/quickstart-configure-app-expose-web-apis#add-a-scope) to add the following `SCOPES` (`Notes.Read`) to your application.\n",
+    "6. You need to install the msal and bs4 packages using the commands `pip install msal` and `pip install beautifulsoup4`.\n",
+    "7. At the end of the steps you must have the following values: \n",
+    "- `CLIENT_ID`\n",
+    "- `CLIENT_SECRET`\n",
+    "\n",
+    "## 🧑 Instructions for ingesting your documents from OneNote\n",
+    "\n",
+    "### 🔑 Authentication\n",
+    "\n",
+    "By default, the `OneNoteLoader` expects that the values of `CLIENT_ID` and `CLIENT_SECRET` must be stored as environment variables named `MS_GRAPH_CLIENT_ID` and `MS_GRAPH_CLIENT_SECRET` respectively. You could pass those environment variables through a `.env` file at the root of your application or using the following command in your script.\n",
+    "\n",
+    "```python\n",
+    "os.environ['MS_GRAPH_CLIENT_ID'] = \"YOUR CLIENT ID\"\n",
+    "os.environ['MS_GRAPH_CLIENT_SECRET'] = \"YOUR CLIENT SECRET\"\n",
+    "```\n",
+    "\n",
+    "This loader uses an authentication called [*on behalf of a user*](https://learn.microsoft.com/en-us/graph/auth-v2-user?context=graph%2Fapi%2F1.0&view=graph-rest-1.0). It is a 2 step authentication with user consent. When you instantiate the loader, it will call will print a url that the user must visit to give consent to the app on the required permissions. The user must then visit this url and give consent to the application. Then the user must copy the resulting page url and paste it back on the console. The method will then return True if the login attempt was successful.\n",
+    "\n",
+    "\n",
+    "```python\n",
+    "from langchain.document_loaders.onenote import OneNoteLoader\n",
+    "\n",
+    "loader = OneNoteLoader(notebook_name=\"NOTEBOOK NAME\", section_name=\"SECTION NAME\", page_title=\"PAGE TITLE\")\n",
+    "```\n",
+    "\n",
+    "Once the authentication has been done, the loader will store a token (`onenote_graph_token.txt`) at `~/.credentials/` folder. This token could be used later to authenticate without the copy/paste steps explained earlier. To use this token for authentication, you need to change the `auth_with_token` parameter to True in the instantiation of the loader.\n",
+    "\n",
+    "```python\n",
+    "from langchain.document_loaders.onenote import OneNoteLoader\n",
+    "\n",
+    "loader = OneNoteLoader(notebook_name=\"NOTEBOOK NAME\", section_name=\"SECTION NAME\", page_title=\"PAGE TITLE\", auth_with_token=True)\n",
+    "```\n",
+    "\n",
+    "Alternatively, you can also pass the token directly to the loader. This is useful when you want to authenticate with a token that was generated by another application. For instance, you can use the [Microsoft Graph Explorer](https://developer.microsoft.com/en-us/graph/graph-explorer) to generate a token and then pass it to the loader.\n",
+    "\n",
+    "```python\n",
+    "from langchain.document_loaders.onenote import OneNoteLoader\n",
+    "\n",
+    "loader = OneNoteLoader(notebook_name=\"NOTEBOOK NAME\", section_name=\"SECTION NAME\", page_title=\"PAGE TITLE\", access_token=\"TOKEN\")\n",
+    "```\n",
+    "\n",
+    "### 🗂️ Documents loader\n",
+    "\n",
+    "#### 📑 Loading pages from a OneNote Notebook\n",
+    "\n",
+    "`OneNoteLoader` can load pages from OneNote notebooks stored in OneDrive. You can specify any combination of `notebook_name`, `section_name`, `page_title` to filter for pages under a specific notebook, under a specific section, or with a specific title respectively. For instance, you want to load all pages that are stored under a section called `Recipes` within any of your notebooks OneDrive.\n",
+    "\n",
+    "\n",
+    "```python\n",
+    "from langchain.document_loaders.onenote import OneNoteLoader\n",
+    "\n",
+    "loader = OneNoteLoader(section_name=\"Recipes\", auth_with_token=True)\n",
+    "documents = loader.load()\n",
+    "```\n",
+    "\n",
+    "#### 📑 Loading pages from a list of Page IDs\n",
+    "\n",
+    "Another possibility is to provide a list of `object_ids` for each page you want to load. For that, you will need to query the [Microsoft Graph API](https://developer.microsoft.com/en-us/graph/graph-explorer) to find all the documents ID that you are interested in. This [link](https://learn.microsoft.com/en-us/graph/onenote-get-content#page-collection) provides a list of endpoints that will be helpful to retrieve the documents ID.\n",
+    "\n",
+    "For instance, to retrieve information about all pages that are stored in your notebooks, you need make a request to: `https://graph.microsoft.com/v1.0/me/onenote/pages`. Once you have the list of IDs that you are interested in, then you can instantiate the loader with the following parameters.\n",
+    "\n",
+    "\n",
+    "```python\n",
+    "from langchain.document_loaders.onenote import OneNoteLoader\n",
+    "\n",
+    "loader = OneNoteLoader(object_ids=[\"ID_1\", \"ID_2\"], auth_with_token=True)\n",
+    "documents = loader.load()\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bb36fe41",
+   "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": "3.11.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/document_loaders/youtube_transcript.ipynb

@@ -99,7 +99,7 @@
     "\n",
     "Language param : It's a list of language codes in a descending priority, `en` by default.\n",
     "\n",
-    "translation param : It's a translate preference when the youtube does'nt have your select language, `en` by default."
+    "translation param : It's a translate preference, you can translate available transcript to your preferred language."
    ]
   },
   {

docs/docs/integrations/llms/huggingface_hub.ipynb

@@ -101,8 +101,8 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain"
+    "from langchain.chains import LLMChain\n",
+    "from langchain.prompts import PromptTemplate"
    ]
   },
   {

docs/docs/integrations/llms/llamacpp.ipynb

@@ -550,7 +550,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "In the first example, supply the path to the specifed `json.gbnf` file in order to produce JSON:"
+    "In the first example, supply the path to the specified `json.gbnf` file in order to produce JSON:"
    ]
   },
   {

docs/docs/integrations/llms/llm_caching.ipynb

@@ -912,7 +912,7 @@
    "source": [
     "## `Cassandra` caches\n",
     "\n",
-    "You can use Cassandra / Astra DB for caching LLM responses, choosing from the exact-match `CassandraCache` or the (vector-similarity-based) `CassandraSemanticCache`.\n",
+    "You can use Cassandra / Astra DB through CQL for caching LLM responses, choosing from the exact-match `CassandraCache` or the (vector-similarity-based) `CassandraSemanticCache`.\n",
     "\n",
     "Let's see both in action in the following cells."
    ]
@@ -924,7 +924,7 @@
    "source": [
     "#### Connect to the DB\n",
     "\n",
-    "First you need to establish a `Session` to the DB and to specify a _keyspace_ for the cache table(s). The following gets you started with an Astra DB instance (see e.g. [here](https://cassio.org/start_here/#vector-database) for more backends and connection options)."
+    "First you need to establish a `Session` to the DB and to specify a _keyspace_ for the cache table(s). The following gets you connected to Astra DB through CQL (see e.g. [here](https://cassio.org/start_here/#vector-database) for more backends and connection options)."
    ]
   },
   {
@@ -1132,6 +1132,214 @@
     "print(llm(\"How come we always see one face of the moon?\"))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "8712f8fc-bb89-4164-beb9-c672778bbd91",
+   "metadata": {},
+   "source": [
+    "## `Astra DB` Caches"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "173041d9-e4af-4f68-8461-d302bfc7e1bd",
+   "metadata": {},
+   "source": [
+    "You can easily use [Astra DB](https://docs.datastax.com/en/astra/home/astra.html) as an LLM cache, with either the \"exact\" or the \"semantic-based\" cache.\n",
+    "\n",
+    "Make sure you have a running database (it must be a Vector-enabled database to use the Semantic cache) and get the required credentials on your Astra dashboard:\n",
+    "\n",
+    "- the API Endpoint looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n",
+    "- the Token looks like `AstraCS:6gBhNmsk135....`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "feb510b6-99a3-4228-8e11-563051f8178e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "ASTRA_DB_API_ENDPOINT =  https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com\n",
+      "ASTRA_DB_APPLICATION_TOKEN =  ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import getpass\n",
+    "\n",
+    "ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
+    "ASTRA_DB_APPLICATION_TOKEN = getpass.getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ee6d587f-4b7c-43f4-9e90-5129c842a143",
+   "metadata": {},
+   "source": [
+    "### Astra DB exact LLM cache\n",
+    "\n",
+    "This will avoid invoking the LLM when the supplied prompt is _exactly_ the same as one encountered already:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ad63c146-ee41-4896-90ee-29fcc39f0ed5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.cache import AstraDBCache\n",
+    "from langchain.globals import set_llm_cache\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    AstraDBCache(\n",
+    "        api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
+    "        token=ASTRA_DB_APPLICATION_TOKEN,\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "83e0fb02-e8eb-4483-9eb1-55b5e14c4487",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "There is no definitive answer to this question as it depends on the interpretation of the terms \"true fakery\" and \"fake truth\". However, one possible interpretation is that a true fakery is a counterfeit or imitation that is intended to deceive, whereas a fake truth is a false statement that is presented as if it were true.\n",
+      "CPU times: user 70.8 ms, sys: 4.13 ms, total: 74.9 ms\n",
+      "Wall time: 2.06 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "print(llm(\"Is a true fakery the same as a fake truth?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "4d20d498-fe28-4e26-8531-2b31c52ee687",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "There is no definitive answer to this question as it depends on the interpretation of the terms \"true fakery\" and \"fake truth\". However, one possible interpretation is that a true fakery is a counterfeit or imitation that is intended to deceive, whereas a fake truth is a false statement that is presented as if it were true.\n",
+      "CPU times: user 15.1 ms, sys: 3.7 ms, total: 18.8 ms\n",
+      "Wall time: 531 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "print(llm(\"Is a true fakery the same as a fake truth?\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "524b94fa-6162-4880-884d-d008749d14e2",
+   "metadata": {},
+   "source": [
+    "### Astra DB Semantic cache\n",
+    "\n",
+    "This cache will do a semantic similarity search and return a hit if it finds a cached entry that is similar enough, For this, you need to provide an `Embeddings` instance of your choice."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "dc329c55-1cc4-4b74-94f9-61f8990fb214",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "\n",
+    "embedding = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "83952a90-ab14-4e59-87c0-d2bdc1d43e43",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.cache import AstraDBSemanticCache\n",
+    "\n",
+    "set_llm_cache(\n",
+    "    AstraDBSemanticCache(\n",
+    "        api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
+    "        token=ASTRA_DB_APPLICATION_TOKEN,\n",
+    "        embedding=embedding,\n",
+    "        collection_name=\"demo_semantic_cache\",\n",
+    "    )\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "d74b249a-94d5-42d0-af74-f7565a994dea",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "There is no definitive answer to this question since it presupposes a great deal about the nature of truth itself, which is a matter of considerable philosophical debate. It is possible, however, to construct scenarios in which something could be considered true despite being false, such as if someone sincerely believes something to be true even though it is not.\n",
+      "CPU times: user 65.6 ms, sys: 15.3 ms, total: 80.9 ms\n",
+      "Wall time: 2.72 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "print(llm(\"Are there truths that are false?\"))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "11973d73-d2f4-46bd-b229-1c589df9b788",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "There is no definitive answer to this question since it presupposes a great deal about the nature of truth itself, which is a matter of considerable philosophical debate. It is possible, however, to construct scenarios in which something could be considered true despite being false, such as if someone sincerely believes something to be true even though it is not.\n",
+      "CPU times: user 29.3 ms, sys: 6.21 ms, total: 35.5 ms\n",
+      "Wall time: 1.03 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "\n",
+    "print(llm(\"Is is possible that something false can be also true?\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "0c69d84d",

docs/docs/integrations/memory/astradb_chat_message_history.ipynb

@@ -0,0 +1,147 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "90cd3ded",
+   "metadata": {},
+   "source": [
+    "# Astra DB \n",
+    "\n",
+    "> DataStax [Astra DB](https://docs.datastax.com/en/astra/home/astra.html) is a serverless vector-capable database built on Cassandra and made conveniently available through an easy-to-use JSON API.\n",
+    "\n",
+    "This notebook goes over how to use Astra DB to store chat message history."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f507f58b-bf22-4a48-8daf-68d869bcd1ba",
+   "metadata": {},
+   "source": [
+    "## Setting up\n",
+    "\n",
+    "To run this notebook you need a running Astra DB. Get the connection secrets on your Astra dashboard:\n",
+    "\n",
+    "- the API Endpoint looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`;\n",
+    "- the Token looks like `AstraCS:6gBhNmsk135...`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d7092199",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install --quiet \"astrapy>=0.6.2\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3d97b65",
+   "metadata": {},
+   "source": [
+    "### Set up the database connection parameters and secrets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "163d97f0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      "ASTRA_DB_API_ENDPOINT =  https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com\n",
+      "ASTRA_DB_APPLICATION_TOKEN =  ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "import getpass\n",
+    "\n",
+    "ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
+    "ASTRA_DB_APPLICATION_TOKEN = getpass.getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "55860b2d",
+   "metadata": {},
+   "source": [
+    "Depending on whether local or cloud-based Astra DB, create the corresponding database connection \"Session\" object."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36c163e8",
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "d15e3302",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import AstraDBChatMessageHistory\n",
+    "\n",
+    "message_history = AstraDBChatMessageHistory(\n",
+    "    session_id=\"test-session\",\n",
+    "    api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
+    "    token=ASTRA_DB_APPLICATION_TOKEN,\n",
+    ")\n",
+    "\n",
+    "message_history.add_user_message(\"hi!\")\n",
+    "\n",
+    "message_history.add_ai_message(\"whats up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "64fc465e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='hi!'), AIMessage(content='whats up?')]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "message_history.messages"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/memory/elasticsearch_chat_message_history.ipynb

@@ -7,11 +7,11 @@
     "id": "683953b3"
    },
    "source": [
-    "# Elasticsearch Chat Message History\n",
+    "# Elasticsearch\n",
     "\n",
     ">[Elasticsearch](https://www.elastic.co/elasticsearch/) is a distributed, RESTful search and analytics engine, capable of performing both vector and lexical search. It is built on top of the Apache Lucene library.\n",
     "\n",
-    "This notebook shows how to use chat message history functionality with Elasticsearch."
+    "This notebook shows how to use chat message history functionality with `Elasticsearch`."
    ]
   },
   {
@@ -46,6 +46,59 @@
     "%pip install elasticsearch langchain"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "c46c216c",
+   "metadata": {},
+   "source": [
+    "## Authentication\n",
+    "\n",
+    "### How to obtain a password for the default \"elastic\" user\n",
+    "\n",
+    "To obtain your Elastic Cloud password for the default \"elastic\" user:\n",
+    "1. Log in to the [Elastic Cloud console](https://cloud.elastic.co)\n",
+    "2. Go to \"Security\" > \"Users\"\n",
+    "3. Locate the \"elastic\" user and click \"Edit\"\n",
+    "4. Click \"Reset password\"\n",
+    "5. Follow the prompts to reset the password\n",
+    "\n",
+    "\n",
+    "### Use the Username/password\n",
+    "\n",
+    "```python\n",
+    "es_username = os.environ.get(\"ES_USERNAME\", \"elastic\")\n",
+    "es_password = os.environ.get(\"ES_PASSWORD\", \"change me...\")\n",
+    "\n",
+    "history = ElasticsearchChatMessageHistory(\n",
+    "    es_url=es_url,\n",
+    "    es_user=es_username,\n",
+    "    es_password=es_password,\n",
+    "    index=\"test-history\",\n",
+    "    session_id=\"test-session\"\n",
+    ")\n",
+    "```\n",
+    "\n",
+    "### How to obtain an API key\n",
+    "\n",
+    "To obtain an API key:\n",
+    "1. Log in to the [Elastic Cloud console](https://cloud.elastic.co)\n",
+    "2. Open `Kibana` and go to Stack Management > API Keys\n",
+    "3. Click \"Create API key\"\n",
+    "4. Enter a name for the API key and click \"Create\"\n",
+    "\n",
+    "### Use the API key\n",
+    "\n",
+    "```python\n",
+    "es_api_key = os.environ.get(\"ES_API_KEY\")\n",
+    "\n",
+    "history = ElasticsearchChatMessageHistory(\n",
+    "    es_api_key=es_api_key,\n",
+    "    index=\"test-history\",\n",
+    "    session_id=\"test-session\"\n",
+    ")\n",
+    "```\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "8be8fcc3",
@@ -104,58 +157,6 @@
     "history.add_user_message(\"hi!\")\n",
     "history.add_ai_message(\"whats up?\")"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "c46c216c",
-   "metadata": {},
-   "source": [
-    "# Authentication\n",
-    "\n",
-    "## Username/password\n",
-    "\n",
-    "```python\n",
-    "es_username = os.environ.get(\"ES_USERNAME\", \"elastic\")\n",
-    "es_password = os.environ.get(\"ES_PASSWORD\", \"changeme\")\n",
-    "\n",
-    "history = ElasticsearchChatMessageHistory(\n",
-    "    es_url=es_url,\n",
-    "    es_user=es_username,\n",
-    "    es_password=es_password,\n",
-    "    index=\"test-history\",\n",
-    "    session_id=\"test-session\"\n",
-    ")\n",
-    "```\n",
-    "\n",
-    "### How to obtain a password for the default \"elastic\" user\n",
-    "\n",
-    "To obtain your Elastic Cloud password for the default \"elastic\" user:\n",
-    "1. Log in to the Elastic Cloud console at https://cloud.elastic.co\n",
-    "2. Go to \"Security\" > \"Users\"\n",
-    "3. Locate the \"elastic\" user and click \"Edit\"\n",
-    "4. Click \"Reset password\"\n",
-    "5. Follow the prompts to reset the password\n",
-    "\n",
-    "## API key\n",
-    "\n",
-    "```python\n",
-    "es_api_key = os.environ.get(\"ES_API_KEY\")\n",
-    "\n",
-    "history = ElasticsearchChatMessageHistory(\n",
-    "    es_api_key=es_api_key,\n",
-    "    index=\"test-history\",\n",
-    "    session_id=\"test-session\"\n",
-    ")\n",
-    "```\n",
-    "\n",
-    "### How to obtain an API key\n",
-    "\n",
-    "To obtain an API key:\n",
-    "1. Log in to the Elastic Cloud console at https://cloud.elastic.co\n",
-    "2. Open Kibana and go to Stack Management > API Keys\n",
-    "3. Click \"Create API key\"\n",
-    "4. Enter a name for the API key and click \"Create\""
-   ]
   }
  ],
  "metadata": {
@@ -177,7 +178,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/memory/mongodb_chat_message_history.ipynb

@@ -5,7 +5,7 @@
    "id": "91c6a7ef",
    "metadata": {},
    "source": [
-    "# MongodDB\n",
+    "# MongoDB\n",
     "\n",
     ">`MongoDB` is a source-available cross-platform document-oriented database program. Classified as a NoSQL database program, `MongoDB` uses `JSON`-like documents with optional schemas.\n",
     ">\n",

docs/docs/integrations/memory/upstash_redis_chat_message_history.ipynb

@@ -4,9 +4,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Upstash Redis Chat Message History\n",
+    "# Upstash Redis\n",
     "\n",
-    "This notebook goes over how to use Upstash Redis to store chat message history."
+    ">[Upstash](https://upstash.com/docs/introduction) is a provider of the serverless `Redis`, `Kafka`, and `QStash` APIs.\n",
+    "\n",
+    "This notebook goes over how to use `Upstash Redis` to store chat message history."
    ]
   },
   {
@@ -42,7 +44,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -56,10 +58,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
-  },
-  "orig_nbformat": 4
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/platforms/microsoft.mdx

@@ -81,6 +81,7 @@ See a [usage example for the Azure Files](/docs/integrations/document_loaders/az
 from langchain.document_loaders import AzureBlobStorageFileLoader
 ```
 
+
 ### Microsoft OneDrive
 
 >[Microsoft OneDrive](https://en.wikipedia.org/wiki/OneDrive) (formerly `SkyDrive`) is a file-hosting service operated by Microsoft.
@@ -97,6 +98,7 @@ See a [usage example](/docs/integrations/document_loaders/microsoft_onedrive).
 from langchain.document_loaders import OneDriveLoader
 ```
 
+
 ### Microsoft Word
 
 >[Microsoft Word](https://www.microsoft.com/en-us/microsoft-365/word) is a word processor developed by Microsoft.
@@ -108,6 +110,48 @@ from langchain.document_loaders import UnstructuredWordDocumentLoader
 ```
 
 
+### Microsoft Excel
+
+>[Microsoft Excel](https://en.wikipedia.org/wiki/Microsoft_Excel) is a spreadsheet editor developed by 
+> Microsoft for Windows, macOS, Android, iOS and iPadOS. 
+> It features calculation or computation capabilities, graphing tools, pivot tables, and a macro programming 
+> language called Visual Basic for Applications (VBA). Excel forms part of the Microsoft 365 suite of software.
+
+The `UnstructuredExcelLoader` is used to load `Microsoft Excel` files. The loader works with both `.xlsx` and `.xls` files. 
+The page content will be the raw text of the Excel file. If you use the loader in `"elements"` mode, an HTML 
+representation of the Excel file will be available in the document metadata under the `text_as_html` key.
+
+See a [usage example](/docs/integrations/document_loaders/excel).
+
+```python
+from langchain.document_loaders import UnstructuredExcelLoader
+```
+
+
+### Microsoft SharePoint
+
+>[Microsoft SharePoint](https://en.wikipedia.org/wiki/SharePoint) is a website-based collaboration system 
+> that uses workflow applications, “list” databases, and other web parts and security features to 
+> empower business teams to work together developed by Microsoft.
+
+See a [usage example](/docs/integrations/document_loaders/microsoft_sharepoint).
+
+```python
+from langchain.document_loaders.sharepoint import SharePointLoader
+```
+
+
+### Microsoft PowerPoint
+
+>[Microsoft PowerPoint](https://en.wikipedia.org/wiki/Microsoft_PowerPoint) is a presentation program by Microsoft.
+
+See a [usage example](/docs/integrations/document_loaders/microsoft_powerpoint).
+
+```python
+from langchain.document_loaders import UnstructuredPowerPointLoader
+```
+
+
 ## Vector stores
 
 ### Azure Cosmos DB

docs/docs/integrations/platforms/openai.mdx

@@ -99,3 +99,10 @@ See a [usage example](/docs/guides/safety/moderation).
 from langchain.chains import OpenAIModerationChain
 ```
 
+## Adapter
+
+See a [usage example](/docs/integrations/adapters/openai).
+
+```python
+from langchain.adapters import openai as lc_openai
+```

docs/docs/integrations/providers/astradb.mdx

@@ -29,6 +29,47 @@ vector_store = AstraDB(
 
 Learn more in the [example notebook](/docs/integrations/vectorstores/astradb).
 
+### LLM Cache
+
+```python
+from langchain.globals import set_llm_cache
+from langchain.cache import AstraDBCache
+set_llm_cache(AstraDBCache(
+    api_endpoint="...",
+    token="...",
+))
+```
+
+Learn more in the [example notebook](/docs/integrations/llms/llm_caching) (scroll to the Astra DB section).
+
+
+### Semantic LLM Cache
+
+```python
+from langchain.globals import set_llm_cache
+from langchain.cache import AstraDBSemanticCache
+set_llm_cache(AstraDBSemanticCache(
+    embedding=my_embedding,
+    api_endpoint="...",
+    token="...",
+))
+```
+
+Learn more in the [example notebook](/docs/integrations/llms/llm_caching) (scroll to the appropriate section).
+
+### Chat message history
+
+```python
+from langchain.memory import AstraDBChatMessageHistory
+message_history = AstraDBChatMessageHistory(
+    session_id="test-session"
+    api_endpoint="...",
+    token="...",
+)
+```
+
+Learn more in the [example notebook](/docs/integrations/memory/astradb_chat_message_history).
+
 
 ## Apache Cassandra and Astra DB through CQL
 

docs/docs/integrations/providers/docugami.mdx

@@ -8,7 +8,7 @@
 
 
 ```bash
-pip install lxml
+pip install dgml-utils
 ```
 
 ## Document Loader

docs/docs/integrations/providers/infinity.mdx

@@ -0,0 +1,11 @@
+# Infinity
+
+>[Infinity](https://github.com/michaelfeil/infinity) allows the creation of text embeddings.
+
+## Text Embedding Model
+
+There exists an infinity Embedding model, which you can access with 
+```python
+from langchain.embeddings import InfinityEmbeddings
+```
+For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/infinity)

docs/docs/integrations/providers/langchain_decorators.mdx

@@ -1,10 +1,13 @@
 # LangChain Decorators ✨
 
-lanchchain decorators is a layer on the top of LangChain that provides syntactic sugar 🍭 for writing custom langchain prompts and chains
-
-For Feedback, Issues, Contributions - please raise an issue here: 
-[ju-bezdek/langchain-decorators](https://github.com/ju-bezdek/langchain-decorators)
+~~~
+Disclaimer: `LangChain decorators` is not created by the LangChain team and is not supported by it.
+~~~
 
+>`LangChain decorators` is a layer on the top of LangChain that provides syntactic sugar 🍭 for writing custom langchain prompts and chains
+>
+>For Feedback, Issues, Contributions - please raise an issue here: 
+>[ju-bezdek/langchain-decorators](https://github.com/ju-bezdek/langchain-decorators)
 
 
 Main principles and benefits:
@@ -17,7 +20,6 @@ Main principles and benefits:
 - easily share parameters between the prompts by binding them to one class
 
 
-
 Here is a simple example of a code written with **LangChain Decorators ✨**
 
 ``` python

docs/docs/integrations/providers/outline.mdx

@@ -0,0 +1,22 @@
+# Outline
+
+> [Outline](https://www.getoutline.com/) is an open-source collaborative knowledge base platform designed for team information sharing.
+
+## Setup
+
+You first need to [create an api key](https://www.getoutline.com/developers#section/Authentication) for your Outline instance. Then you need to set the following environment variables:
+
+```python
+import os
+
+os.environ["OUTLINE_API_KEY"] = "xxx"
+os.environ["OUTLINE_INSTANCE_URL"] = "https://app.getoutline.com"
+```
+
+## Retriever
+
+See a [usage example](/docs/integrations/retrievers/outline).
+
+```python
+from langchain.retrievers import OutlineRetriever
+```

docs/docs/integrations/providers/stackexchange.mdx

@@ -0,0 +1,36 @@
+# Stack Exchange
+
+>[Stack Exchange](https://en.wikipedia.org/wiki/Stack_Exchange) is a network of 
+question-and-answer (Q&A) websites on topics in diverse fields, each site covering 
+a specific topic, where questions, answers, and users are subject to a reputation award process.
+
+This page covers how to use the `Stack Exchange API` within LangChain.
+
+## Installation and Setup
+- Install requirements with 
+```bash
+pip install stackapi
+```
+
+## Wrappers
+
+### Utility
+
+There exists a StackExchangeAPIWrapper utility which wraps this API. To import this utility:
+
+```python
+from langchain.utilities import StackExchangeAPIWrapper
+```
+
+For a more detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/stackexchange).
+
+### Tool
+
+You can also easily load this wrapper as a Tool (to use with an Agent).
+You can do this with:
+```python
+from langchain.agents import load_tools
+tools = load_tools(["stackexchange"])
+```
+
+For more information on tools, see [this page](/docs/modules/agents/tools/).

docs/docs/integrations/retrievers/Activeloop DeepMemory+LangChain.ipynb

@@ -4,14 +4,16 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Activeloop DeepLake's DeepMemory + LangChain + ragas or how to get +27% on RAG recall."
+    "# Activeloop Deep Memory"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Retrieval-Augmented Generators (RAGs) have recently gained significant attention. As advanced RAG techniques and agents emerge, they expand the potential of what RAGs can accomplish. However, several challenges may limit the integration of RAGs into production. The primary factors to consider when implementing RAGs in production settings are accuracy (recall), cost, and latency. For basic use cases, OpenAI's Ada model paired with a naive similarity search can produce satisfactory results. Yet, for higher accuracy or recall during searches, one might need to employ advanced retrieval techniques. These methods might involve varying data chunk sizes, rewriting queries multiple times, and more, potentially increasing latency and costs.  [Activeloop's](https://activeloop.ai/) [Deep Memory](https://www.activeloop.ai/resources/use-deep-memory-to-boost-rag-apps-accuracy-by-up-to-22/) a feature available to Activeloop Deep Lake users, addresses these issuea by introducing a tiny neural network layer trained to match user queries with relevant data from a corpus. While this addition incurs minimal latency during search, it can boost retrieval accuracy by up to 27\n",
+    ">[Activeloop Deep Memory](https://docs.activeloop.ai/performance-features/deep-memory) is a suite of tools that enables you to optimize your Vector Store for your use-case and achieve higher accuracy in your LLM apps.\n",
+    "\n",
+    "`Retrieval-Augmented Generatation` (`RAG`) has recently gained significant attention. As advanced RAG techniques and agents emerge, they expand the potential of what RAGs can accomplish. However, several challenges may limit the integration of RAGs into production. The primary factors to consider when implementing RAGs in production settings are accuracy (recall), cost, and latency. For basic use cases, OpenAI's Ada model paired with a naive similarity search can produce satisfactory results. Yet, for higher accuracy or recall during searches, one might need to employ advanced retrieval techniques. These methods might involve varying data chunk sizes, rewriting queries multiple times, and more, potentially increasing latency and costs.  [Activeloop's](https://activeloop.ai/) [Deep Memory](https://www.activeloop.ai/resources/use-deep-memory-to-boost-rag-apps-accuracy-by-up-to-22/) a feature available to `Activeloop Deep Lake` users, addresses these issuea by introducing a tiny neural network layer trained to match user queries with relevant data from a corpus. While this addition incurs minimal latency during search, it can boost retrieval accuracy by up to 27\n",
     "% and remains cost-effective and simple to use, without requiring any additional advanced rag techniques.\n"
    ]
   },
@@ -19,23 +21,13 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "For this tutorial we will parse deeplake documentation, and create a RAG system that could answer the question from the docs. \n",
-    "\n",
-    "The tutorial can be divided into several parts:\n",
-    "1. [Dataset creation and uploading](#1-dataset-creation)\n",
-    "2. [Generating synthetic queries and training deep_memory](#2-generating-synthetic-queries-and-training-deep_memory)\n",
-    "3. [Evaluating deep memory performance](#3-evaluating-deep-memory-performance)\n",
-    "    - 3.1 [using deepmemory recall@10 metric](#31-using-deepmemory-recall10-metric)\n",
-    "    - 3.2 [using ragas](#32-deepmemory--ragas)\n",
-    "    - 3.3 [deep_memory inference](#33-deepmemory-inference)\n",
-    "    - 3.4 [deep_memory cost savings](#34-cost-savings)"
+    "For this tutorial we will parse `DeepLake` documentation, and create a RAG system that could answer the question from the docs. \n"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<a name=\"dataset-creation\"></a>\n",
     "## 1. Dataset Creation"
    ]
   },
@@ -227,10 +219,11 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
    "source": [
-    "<a name=\"training\"></a>\n",
-    "## 2. Generating synthetic queries and training deep_memory "
+    "## 2. Generating synthetic queries and training Deep Memory "
    ]
   },
   {
@@ -422,8 +415,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<a name=\"evaluation\"></a>\n",
-    "## 3. Evaluating deep memory performance"
+    "## 3. Evaluating Deep Memory performance"
    ]
   },
   {
@@ -437,15 +429,16 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<a name=\"recall@10\"></a>\n",
-    "### 3.1 using deepmemory recall@10 metric"
+    "### 3.1 Deep Memory evaluation"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "For the beginning we can use deep_memory's builtin evaluation method. it can be done easily in a few lines of code:"
+    "For the beginning we can use deep_memory's builtin evaluation method. \n",
+    "It calculates several `recall` metrics.\n",
+    "It can be done easily in a few lines of code."
    ]
   },
   {
@@ -495,8 +488,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<a name=\"ragas\"></a>\n",
-    "### 3.2 DeepMemory + ragas"
+    "### 3.2 Deep Memory + RAGas"
    ]
   },
   {
@@ -596,10 +588,11 @@
   },
   {
    "cell_type": "markdown",
-   "metadata": {},
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
    "source": [
-    "<a name=\"inference\"></a>\n",
-    "### 3.3 DeepMemory Inference"
+    "### 3.3 Deep Memory Inference"
    ]
   },
   {
@@ -677,8 +670,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "<a name=\"cost\"></a>\n",
-    "### 3.4 Cost savings"
+    "### 3.4 Deep Memory cost savings"
    ]
   },
   {
@@ -691,7 +683,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -705,10 +697,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.4"
-  },
-  "orig_nbformat": 4
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/retrievers/bedrock.ipynb

@@ -0,0 +1,116 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "b6636c27-35da-4ba7-8313-eca21660cab3",
+   "metadata": {},
+   "source": [
+    "# Amazon Bedrock (Knowledge Bases)\n",
+    "\n",
+    "> [Knowledge bases for Amazon Bedrock](https://aws.amazon.com/bedrock/knowledge-bases/) is an Amazon Web Services (AWS) offering which lets you quickly build RAG applications by using your private data to customize FM response.\n",
+    "\n",
+    "> Implementing RAG requires organizations to perform several cumbersome steps to convert data into embeddings (vectors), store the embeddings in a specialized vector database, and build custom integrations into the database to search and retrieve text relevant to the user’s query. This can be time-consuming and inefficient.\n",
+    "\n",
+    "> With Knowledge Bases for Amazon Bedrock, simply point to the location of your data in Amazon S3, and Knowledge Bases for Amazon Bedrock takes care of the entire ingestion workflow into your vector database. If you do not have an existing vector database, Amazon Bedrock creates an Amazon OpenSearch Serverless vector store for you. For retrievals, use the Langchain - Amazon Bedrock integration via the Retrieve API to retrieve relevant results for a user query from knowledge bases.\n",
+    "\n",
+    "> Knowledge base can be configured through [AWS Console](https://aws.amazon.com/console/) or by using [AWS SDKs](https://aws.amazon.com/developer/tools/)."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b34c8cbe-c6e5-4398-adf1-4925204bcaed",
+   "metadata": {},
+   "source": [
+    "## Using the Knowledge Bases Retriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "26c97d36-911c-4fe0-a478-546192728f30",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install boto3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "30337664-8844-4dfe-97db-077abb51af68",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import AmazonKnowledgeBasesRetriever\n",
+    "\n",
+    "retriever = AmazonKnowledgeBasesRetriever(\n",
+    "    knowledge_base_id=\"PUIJP4EQUA\",\n",
+    "    retrieval_config={\"vectorSearchConfiguration\": {\"numberOfResults\": 4}},\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f9fefa50-f0fb-40e3-b4e4-67c5b232a090",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown?\"\n",
+    "\n",
+    "retriever.get_relevant_documents(query=query)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7de9b61b-597b-4aba-95fb-49d11e84510e",
+   "metadata": {},
+   "source": [
+    "### Using in a QA Chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0fd71709-aaed-42b5-a990-e3067bfa7143",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from botocore.client import Config\n",
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.llms import Bedrock\n",
+    "\n",
+    "model_kwargs_claude = {\"temperature\": 0, \"top_k\": 10, \"max_tokens_to_sample\": 3000}\n",
+    "\n",
+    "llm = Bedrock(model_id=\"anthropic.claude-v2\", model_kwargs=model_kwargs_claude)\n",
+    "\n",
+    "qa = RetrievalQA.from_chain_type(\n",
+    "    llm=llm, retriever=retriever, return_source_documents=True\n",
+    ")\n",
+    "\n",
+    "qa(query)"
+   ]
+  }
+ ],
+ "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": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/retrievers/embedchain.ipynb

@@ -0,0 +1,255 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "2f0f85ac-9c49-4111-a320-e53bccc99b13",
+   "metadata": {},
+   "source": [
+    "# Embedchain\n",
+    "\n",
+    "Embedchain is a RAG framework to create data pipelines. It loads, indexes, retrieves and syncs all the data.\n",
+    "\n",
+    "It is available as an [open source package](https://github.com/embedchain/embedchain) and as a [hosted platform solution](https://app.embedchain.ai/).\n",
+    "\n",
+    "This notebook shows how to use a retriever that uses Embedchain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e48de822-307b-4284-96e7-c91f11ce005b",
+   "metadata": {},
+   "source": [
+    "# Installation\n",
+    "\n",
+    "First you will need to install the [`embedchain` package](https://pypi.org/project/embedchain/). \n",
+    "\n",
+    "You can install the package by running "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c690a78c-5999-4072-b4e1-2712ff73f950",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#!pip install --upgrade embedchain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bc89ba12-6ebd-4cd6-8c85-7410531579ff",
+   "metadata": {},
+   "source": [
+    "# Create New Retriever\n",
+    "\n",
+    "`EmbedchainRetriever` has a static `.create()` factory method that takes the following arguments:\n",
+    "\n",
+    "* `yaml_path: string` optional -- Path to the YAML configuration file. If not provided, a default configuration is used. You can browse the [docs](https://docs.embedchain.ai/) to explore various customization options."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "8e639bd4-2e60-487b-b7aa-f7e6b921b069",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdin",
+     "output_type": "stream",
+     "text": [
+      " ········\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Setup API Key\n",
+    "\n",
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "223fbc76-91ad-4504-87e9-980fb0e027fc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import EmbedchainRetriever\n",
+    "\n",
+    "# create retriever with default options\n",
+    "retriever = EmbedchainRetriever.create()\n",
+    "\n",
+    "# or if you want to customize, pass the yaml config path\n",
+    "# retriever = EmbedchainRetiever.create(yaml_path=\"config.yaml\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "536f3a1d-3491-45b5-9f25-869bd6fb6d6a",
+   "metadata": {},
+   "source": [
+    "# Add Data\n",
+    "\n",
+    "In embedchain, you can as many supported data types as possible. You can browse our [docs](https://docs.embedchain.ai/) to see the data types supported.\n",
+    "\n",
+    "Embedchain automatically deduces the types of the data. So you can add a string, URL or local file path."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "31262be3-7d0d-42e8-9253-052160576dc7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Inserting batches in chromadb: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4/4 [00:08<00:00,  2.22s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully saved https://en.wikipedia.org/wiki/Elon_Musk (DataType.WEB_PAGE). New chunks count: 378\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Inserting batches in chromadb: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:01<00:00,  1.17s/it]\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully saved https://www.forbes.com/profile/elon-musk (DataType.WEB_PAGE). New chunks count: 13\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Inserting batches in chromadb: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00,  2.25s/it]"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully saved https://www.youtube.com/watch?v=RcYjXbSJBN8 (DataType.YOUTUBE_VIDEO). New chunks count: 53\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "['1eab8dd1ffa92906f7fc839862871ca5',\n",
+       " '8cf46026cabf9b05394a2658bd1fe890',\n",
+       " 'da3227cdbcedb018e05c47b774d625f6']"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.add_texts(\n",
+    "    [\n",
+    "        \"https://en.wikipedia.org/wiki/Elon_Musk\",\n",
+    "        \"https://www.forbes.com/profile/elon-musk\",\n",
+    "        \"https://www.youtube.com/watch?v=RcYjXbSJBN8\",\n",
+    "    ]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e1f34a62-7f8e-4c03-8e10-c317ed3296aa",
+   "metadata": {},
+   "source": [
+    "# Use Retriever\n",
+    "\n",
+    "You can now use the retrieve to find relevant documents given a query"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6106baf9-652a-4a94-b2d7-d6a5d2917975",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "result = retriever.get_relevant_documents(\n",
+    "    \"How many companies does Elon Musk run and name those?\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "1deae5d0-e0fa-431d-b164-e9680ef3e69b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='Views Filmography Companies Zip2 X.com PayPal SpaceX Starlink Tesla, Inc. Energycriticismlitigation OpenAI Neuralink The Boring Company Thud X Corp. Twitteracquisitiontenure as CEO xAI In popular culture Elon Musk (Isaacson) Elon Musk (Vance) Ludicrous Power Play \"Members Only\" \"The Platonic Permutation\" \"The Musk Who Fell to Earth\" \"One Crew over the Crewcoo\\'s Morty\" Elon Musk\\'s Crash Course Related Boring Test Tunnel Hyperloop Musk family Musk vs. Zuckerberg SolarCity Tesla Roadster in space', metadata={'source': 'https://en.wikipedia.org/wiki/Elon_Musk', 'document_id': 'c33c05d0-5028-498b-b5e3-c43a4f9e8bf8--3342161a0fbc19e91f6bf387204aa30fbb2cea05abc81882502476bde37b9392'}),\n",
+       " Document(page_content='Elon Musk PROFILEElon MuskCEO, Tesla$241.2B$508M (0.21%)Real Time Net Worthas of 11/18/23Reflects change since 5 pm ET of prior trading day. 1 in the world todayPhoto by Martin Schoeller for ForbesAbout Elon MuskElon Musk cofounded six companies, including electric car maker Tesla, rocket producer SpaceX and tunneling startup Boring Company.He owns about 21% of Tesla between stock and options, but has pledged more than half his shares as collateral for personal loans of up to $3.5', metadata={'source': 'https://www.forbes.com/profile/elon-musk', 'document_id': 'c33c05d0-5028-498b-b5e3-c43a4f9e8bf8--3c8573134c575fafc025e9211413723e1f7a725b5936e8ee297fb7fb63bdd01a'}),\n",
+       " Document(page_content='to form PayPal. In October 2002, eBay acquired PayPal for $1.5 billion, and that same year, with $100 million of the money he made, Musk founded SpaceX, a spaceflight services company. In 2004, he became an early investor in electric vehicle manufacturer Tesla Motors, Inc. (now Tesla, Inc.). He became its chairman and product architect, assuming the position of CEO in 2008. In 2006, Musk helped create SolarCity, a solar-energy company that was acquired by Tesla in 2016 and became Tesla Energy.', metadata={'source': 'https://en.wikipedia.org/wiki/Elon_Musk', 'document_id': 'c33c05d0-5028-498b-b5e3-c43a4f9e8bf8--3342161a0fbc19e91f6bf387204aa30fbb2cea05abc81882502476bde37b9392'})]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3f26c2b-048d-4588-90a0-50f5c9c35837",
+   "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": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/docs/integrations/retrievers/outline.ipynb

@@ -0,0 +1,182 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Outline\n",
+    "\n",
+    ">[Outline](https://www.getoutline.com/) is an open-source collaborative knowledge base platform designed for team information sharing.\n",
+    "\n",
+    "This notebook shows how to retrieve documents from your Outline instance into the Document format that is used downstream."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You first need to [create an api key](https://www.getoutline.com/developers#section/Authentication) for your Outline instance. Then you need to set the following environment variables:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OUTLINE_API_KEY\"] = \"xxx\"\n",
+    "os.environ[\"OUTLINE_INSTANCE_URL\"] = \"https://app.getoutline.com\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "`OutlineRetriever` has these arguments:\n",
+    "- optional `top_k_results`: default=3. Use it to limit number of documents retrieved.\n",
+    "- optional `load_all_available_meta`: default=False. By default only the most important fields retrieved: `title`, `source` (the url of the document). If True, other fields also retrieved.\n",
+    "- optional `doc_content_chars_max` default=4000. Use it to limit the number of characters for each document retrieved.\n",
+    "\n",
+    "`get_relevant_documents()` has one argument, `query`: free text which used to find documents in your Outline instance."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Examples"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Running retriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import OutlineRetriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = OutlineRetriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='This walkthrough demonstrates how to use an agent optimized for conversation. Other agents are often optimized for using tools to figure out the best response, which is not ideal in a conversational setting where you may want the agent to be able to chat with the user as well.\\n\\nIf we compare it to the standard ReAct agent, the main difference is the prompt. We want it to be much more conversational.\\n\\nfrom langchain.agents import AgentType, Tool, initialize_agent\\n\\nfrom langchain.llms import OpenAI\\n\\nfrom langchain.memory import ConversationBufferMemory\\n\\nfrom langchain.utilities import SerpAPIWrapper\\n\\nsearch = SerpAPIWrapper() tools = \\\\[ Tool( name=\"Current Search\", func=search.run, description=\"useful for when you need to answer questions about current events or the current state of the world\", ), \\\\]\\n\\n\\\\\\nllm = OpenAI(temperature=0)\\n\\nUsing LCEL\\n\\nWe will first show how to create this agent using LCEL\\n\\nfrom langchain import hub\\n\\nfrom langchain.agents.format_scratchpad import format_log_to_str\\n\\nfrom langchain.agents.output_parsers import ReActSingleInputOutputParser\\n\\nfrom langchain.tools.render import render_text_description\\n\\nprompt = hub.pull(\"hwchase17/react-chat\")\\n\\nprompt = prompt.partial( tools=render_text_description(tools), tool_names=\", \".join(\\\\[[t.name](http://t.name) for t in tools\\\\]), )\\n\\nllm_with_stop = llm.bind(stop=\\\\[\"\\\\nObservation\"\\\\])\\n\\nagent = ( { \"input\": lambda x: x\\\\[\"input\"\\\\], \"agent_scratchpad\": lambda x: format_log_to_str(x\\\\[\"intermediate_steps\"\\\\]), \"chat_history\": lambda x: x\\\\[\"chat_history\"\\\\], } | prompt | llm_with_stop | ReActSingleInputOutputParser() )\\n\\nfrom langchain.agents import AgentExecutor\\n\\nmemory = ConversationBufferMemory(memory_key=\"chat_history\") agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True, memory=memory)\\n\\nagent_executor.invoke({\"input\": \"hi, i am bob\"})\\\\[\"output\"\\\\]\\n\\n```\\n> Entering new AgentExecutor chain...\\n\\nThought: Do I need to use a tool? No\\nFinal Answer: Hi Bob, nice to meet you! How can I help you today?\\n\\n> Finished chain.\\n```\\n\\n\\\\\\n\\'Hi Bob, nice to meet you! How can I help you today?\\'\\n\\nagent_executor.invoke({\"input\": \"whats my name?\"})\\\\[\"output\"\\\\]\\n\\n```\\n> Entering new AgentExecutor chain...\\n\\nThought: Do I need to use a tool? No\\nFinal Answer: Your name is Bob.\\n\\n> Finished chain.\\n```\\n\\n\\\\\\n\\'Your name is Bob.\\'\\n\\nagent_executor.invoke({\"input\": \"what are some movies showing 9/21/2023?\"})\\\\[\"output\"\\\\]\\n\\n```\\n> Entering new AgentExecutor chain...\\n\\nThought: Do I need to use a tool? Yes\\nAction: Current Search\\nAction Input: Movies showing 9/21/2023[\\'September 2023 Movies: The Creator • Dumb Money • Expend4bles • The Kill Room • The Inventor • The Equalizer 3 • PAW Patrol: The Mighty Movie, ...\\'] Do I need to use a tool? No\\nFinal Answer: According to current search, some movies showing on 9/21/2023 are The Creator, Dumb Money, Expend4bles, The Kill Room, The Inventor, The Equalizer 3, and PAW Patrol: The Mighty Movie.\\n\\n> Finished chain.\\n```\\n\\n\\\\\\n\\'According to current search, some movies showing on 9/21/2023 are The Creator, Dumb Money, Expend4bles, The Kill Room, The Inventor, The Equalizer 3, and PAW Patrol: The Mighty Movie.\\'\\n\\n\\\\\\nUse the off-the-shelf agent\\n\\nWe can also create this agent using the off-the-shelf agent class\\n\\nagent_executor = initialize_agent( tools, llm, agent=AgentType.CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory, )\\n\\nUse a chat model\\n\\nWe can also use a chat model here. The main difference here is in the prompts used.\\n\\nfrom langchain import hub\\n\\nfrom langchain.chat_models import ChatOpenAI\\n\\nprompt = hub.pull(\"hwchase17/react-chat-json\") chat_model = ChatOpenAI(temperature=0, model=\"gpt-4\")\\n\\nprompt = prompt.partial( tools=render_text_description(tools), tool_names=\", \".join(\\\\[[t.name](http://t.name) for t in tools\\\\]), )\\n\\nchat_model_with_stop = chat_model.bind(stop=\\\\[\"\\\\nObservation\"\\\\])\\n\\nfrom langchain.agents.format_scratchpad import format_log_to_messages\\n\\nfrom langchain.agents.output_parsers import JSONAgentOutputParser\\n\\n# We need some extra steering, or the c', metadata={'title': 'Conversational', 'source': 'https://d01.getoutline.com/doc/conversational-B5dBkUgQ4b'}),\n",
+       " Document(page_content='Quickstart\\n\\nIn this quickstart we\\'ll show you how to:\\n\\nGet setup with LangChain, LangSmith and LangServe\\n\\nUse the most basic and common components of LangChain: prompt templates, models, and output parsers\\n\\nUse LangChain Expression Language, the protocol that LangChain is built on and which facilitates component chaining\\n\\nBuild a simple application with LangChain\\n\\nTrace your application with LangSmith\\n\\nServe your application with LangServe\\n\\nThat\\'s a fair amount to cover! Let\\'s dive in.\\n\\nSetup\\n\\nInstallation\\n\\nTo install LangChain run:\\n\\nPip\\n\\nConda\\n\\npip install langchain\\n\\nFor more details, see our Installation guide.\\n\\nEnvironment\\n\\nUsing LangChain will usually require integrations with one or more model providers, data stores, APIs, etc. For this example, we\\'ll use OpenAI\\'s model APIs.\\n\\nFirst we\\'ll need to install their Python package:\\n\\npip install openai\\n\\nAccessing the API requires an API key, which you can get by creating an account and heading here. Once we have a key we\\'ll want to set it as an environment variable by running:\\n\\nexport OPENAI_API_KEY=\"...\"\\n\\nIf you\\'d prefer not to set an environment variable you can pass the key in directly via the openai_api_key named parameter when initiating the OpenAI LLM class:\\n\\nfrom langchain.chat_models import ChatOpenAI\\n\\nllm = ChatOpenAI(openai_api_key=\"...\")\\n\\nLangSmith\\n\\nMany of the applications you build with LangChain will contain multiple steps with multiple invocations of LLM calls. As these applications get more and more complex, it becomes crucial to be able to inspect what exactly is going on inside your chain or agent. The best way to do this is with LangSmith.\\n\\nNote that LangSmith is not needed, but it is helpful. If you do want to use LangSmith, after you sign up at the link above, make sure to set your environment variables to start logging traces:\\n\\nexport LANGCHAIN_TRACING_V2=\"true\" export LANGCHAIN_API_KEY=...\\n\\nLangServe\\n\\nLangServe helps developers deploy LangChain chains as a REST API. You do not need to use LangServe to use LangChain, but in this guide we\\'ll show how you can deploy your app with LangServe.\\n\\nInstall with:\\n\\npip install \"langserve\\\\[all\\\\]\"\\n\\nBuilding with LangChain\\n\\nLangChain provides many modules that can be used to build language model applications. Modules can be used as standalones in simple applications and they can be composed for more complex use cases. Composition is powered by LangChain Expression Language (LCEL), which defines a unified Runnable interface that many modules implement, making it possible to seamlessly chain components.\\n\\nThe simplest and most common chain contains three things:\\n\\nLLM/Chat Model: The language model is the core reasoning engine here. In order to work with LangChain, you need to understand the different types of language models and how to work with them. Prompt Template: This provides instructions to the language model. This controls what the language model outputs, so understanding how to construct prompts and different prompting strategies is crucial. Output Parser: These translate the raw response from the language model to a more workable format, making it easy to use the output downstream. In this guide we\\'ll cover those three components individually, and then go over how to combine them. Understanding these concepts will set you up well for being able to use and customize LangChain applications. Most LangChain applications allow you to configure the model and/or the prompt, so knowing how to take advantage of this will be a big enabler.\\n\\nLLM / Chat Model\\n\\nThere are two types of language models:\\n\\nLLM: underlying model takes a string as input and returns a string\\n\\nChatModel: underlying model takes a list of messages as input and returns a message\\n\\nStrings are simple, but what exactly are messages? The base message interface is defined by BaseMessage, which has two required attributes:\\n\\ncontent: The content of the message. Usually a string. role: The entity from which the BaseMessage is coming. LangChain provides several ob', metadata={'title': 'Quick Start', 'source': 'https://d01.getoutline.com/doc/quick-start-jGuGGGOTuL'}),\n",
+       " Document(page_content='This walkthrough showcases using an agent to implement the [ReAct](https://react-lm.github.io/) logic.\\n\\n```javascript\\nfrom langchain.agents import AgentType, initialize_agent, load_tools\\nfrom langchain.llms import OpenAI\\n```\\n\\nFirst, let\\'s load the language model we\\'re going to use to control the agent.\\n\\n```javascript\\nllm = OpenAI(temperature=0)\\n```\\n\\nNext, let\\'s load some tools to use. Note that the llm-math tool uses an LLM, so we need to pass that in.\\n\\n```javascript\\ntools = load_tools([\"serpapi\", \"llm-math\"], llm=llm)\\n```\\n\\n## Using LCEL[\\u200b](https://python.langchain.com/docs/modules/agents/agent_types/react#using-lcel \"Direct link to Using LCEL\")\\n\\nWe will first show how to create the agent using LCEL\\n\\n```javascript\\nfrom langchain import hub\\nfrom langchain.agents.format_scratchpad import format_log_to_str\\nfrom langchain.agents.output_parsers import ReActSingleInputOutputParser\\nfrom langchain.tools.render import render_text_description\\n```\\n\\n```javascript\\nprompt = hub.pull(\"hwchase17/react\")\\nprompt = prompt.partial(\\n    tools=render_text_description(tools),\\n    tool_names=\", \".join([t.name for t in tools]),\\n)\\n```\\n\\n```javascript\\nllm_with_stop = llm.bind(stop=[\"\\\\nObservation\"])\\n```\\n\\n```javascript\\nagent = (\\n    {\\n        \"input\": lambda x: x[\"input\"],\\n        \"agent_scratchpad\": lambda x: format_log_to_str(x[\"intermediate_steps\"]),\\n    }\\n    | prompt\\n    | llm_with_stop\\n    | ReActSingleInputOutputParser()\\n)\\n```\\n\\n```javascript\\nfrom langchain.agents import AgentExecutor\\n```\\n\\n```javascript\\nagent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)\\n```\\n\\n```javascript\\nagent_executor.invoke(\\n    {\\n        \"input\": \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\"\\n    }\\n)\\n```\\n\\n```javascript\\n    \\n    \\n    > Entering new AgentExecutor chain...\\n     I need to find out who Leo DiCaprio\\'s girlfriend is and then calculate her age raised to the 0.43 power.\\n    Action: Search\\n    Action Input: \"Leo DiCaprio girlfriend\"model Vittoria Ceretti I need to find out Vittoria Ceretti\\'s age\\n    Action: Search\\n    Action Input: \"Vittoria Ceretti age\"25 years I need to calculate 25 raised to the 0.43 power\\n    Action: Calculator\\n    Action Input: 25^0.43Answer: 3.991298452658078 I now know the final answer\\n    Final Answer: Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\\n    \\n    > Finished chain.\\n\\n\\n\\n\\n\\n    {\\'input\\': \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\",\\n     \\'output\\': \"Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\"}\\n```\\n\\n## Using ZeroShotReactAgent[\\u200b](https://python.langchain.com/docs/modules/agents/agent_types/react#using-zeroshotreactagent \"Direct link to Using ZeroShotReactAgent\")\\n\\nWe will now show how to use the agent with an off-the-shelf agent implementation\\n\\n```javascript\\nagent_executor = initialize_agent(\\n    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True\\n)\\n```\\n\\n```javascript\\nagent_executor.invoke(\\n    {\\n        \"input\": \"Who is Leo DiCaprio\\'s girlfriend? What is her current age raised to the 0.43 power?\"\\n    }\\n)\\n```\\n\\n```javascript\\n    \\n    \\n    > Entering new AgentExecutor chain...\\n     I need to find out who Leo DiCaprio\\'s girlfriend is and then calculate her age raised to the 0.43 power.\\n    Action: Search\\n    Action Input: \"Leo DiCaprio girlfriend\"\\n    Observation: model Vittoria Ceretti\\n    Thought: I need to find out Vittoria Ceretti\\'s age\\n    Action: Search\\n    Action Input: \"Vittoria Ceretti age\"\\n    Observation: 25 years\\n    Thought: I need to calculate 25 raised to the 0.43 power\\n    Action: Calculator\\n    Action Input: 25^0.43\\n    Observation: Answer: 3.991298452658078\\n    Thought: I now know the final answer\\n    Final Answer: Leo DiCaprio\\'s girlfriend is Vittoria Ceretti and her current age raised to the 0.43 power is 3.991298452658078.\\n    \\n    > Finished chain.\\n\\n\\n\\n\\n\\n    {\\'input\\': \"Who is L', metadata={'title': 'ReAct', 'source': 'https://d01.getoutline.com/doc/react-d6rxRS1MHk'})]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(query=\"LangChain\", doc_content_chars_max=100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Answering Questions on Outline Documents"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from getpass import getpass\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = getpass(\"OpenAI API Key:\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import ConversationalRetrievalChain\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "model = ChatOpenAI(model_name=\"gpt-3.5-turbo\")\n",
+    "qa = ConversationalRetrievalChain.from_llm(model, retriever=retriever)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'what is langchain?',\n",
+       " 'chat_history': {},\n",
+       " 'answer': \"LangChain is a framework for developing applications powered by language models. It provides a set of libraries and tools that enable developers to build context-aware and reasoning-based applications. LangChain allows you to connect language models to various sources of context, such as prompt instructions, few-shot examples, and content, to enhance the model's responses. It also supports the composition of multiple language model components using LangChain Expression Language (LCEL). Additionally, LangChain offers off-the-shelf chains, templates, and integrations for easy application development. LangChain can be used in conjunction with LangSmith for debugging and monitoring chains, and with LangServe for deploying applications as a REST API.\"}"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "qa({\"question\": \"what is langchain?\", \"chat_history\": {}})"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "venv",
+   "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": "3.9.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/text_embedding/ernie.ipynb

@@ -4,9 +4,9 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# ERNIE Embedding-V1\n",
+    "# ERNIE\n",
     "\n",
-    "[ERNIE Embedding-V1](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/alj562vvu) is a text representation model based on Baidu Wenxin's large-scale model technology, \n",
+    "[ERNIE Embedding-V1](https://cloud.baidu.com/doc/WENXINWORKSHOP/s/alj562vvu) is a text representation model based on `Baidu Wenxin` large-scale model technology, \n",
     "which converts text into a vector form represented by numerical values, and is used in text retrieval, information recommendation, knowledge mining and other scenarios."
    ]
   },
@@ -53,8 +53,19 @@
    "language": "python",
    "name": "python3"
   },
-  "orig_nbformat": 4
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/text_embedding/fastembed.ipynb

@@ -5,14 +5,14 @@
    "id": "900fbd04-f6aa-4813-868f-1c54e3265385",
    "metadata": {},
    "source": [
-    "# Qdrant FastEmbed\n",
+    "# FastEmbed by Qdrant\n",
     "\n",
-    "[FastEmbed](https://qdrant.github.io/fastembed/) is a lightweight, fast, Python library built for embedding generation. \n",
-    "\n",
-    "- Quantized model weights\n",
-    "- ONNX Runtime, no PyTorch dependency\n",
-    "- CPU-first design\n",
-    "- Data-parallelism for encoding of large datasets."
+    ">[FastEmbed](https://qdrant.github.io/fastembed/) from [Qdrant](https://qdrant.tech) is a lightweight, fast, Python library built for embedding generation. \n",
+    ">\n",
+    ">- Quantized model weights\n",
+    ">- ONNX Runtime, no PyTorch dependency\n",
+    ">- CPU-first design\n",
+    ">- Data-parallelism for encoding of large datasets."
    ]
   },
   {
@@ -154,7 +154,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/text_embedding/infinity.ipynb

@@ -0,0 +1,191 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Infinity\n",
+    "\n",
+    "`Infinity` allows to create `Embeddings` using a MIT-licensed Embedding Server. \n",
+    "\n",
+    "This notebook goes over how to use Langchain with Embeddings with the [Infinity Github Project](https://github.com/michaelfeil/infinity).\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import InfinityEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Optional: Make sure to start the Infinity instance\n",
+    "\n",
+    "To install infinity use the following command. For further details check out the [Docs on Github](https://github.com/michaelfeil/infinity).\n",
+    "```bash\n",
+    "pip install infinity_emb[all]\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: infinity_emb[cli] in /home/michi/langchain/.venv/lib/python3.10/site-packages (0.0.8)\n",
+      "\u001b[33mWARNING: infinity-emb 0.0.8 does not provide the extra 'cli'\u001b[0m\u001b[33m\n",
+      "\u001b[0mRequirement already satisfied: numpy>=1.20.0 in /home/michi/langchain/.venv/lib/python3.10/site-packages (from infinity_emb[cli]) (1.24.4)\n",
+      "\u001b[33mWARNING: There was an error checking the latest version of pip.\u001b[0m\u001b[33m\n",
+      "\u001b[0m"
+     ]
+    }
+   ],
+   "source": [
+    "# Install the infinity package\n",
+    "!pip install infinity_emb[cli,torch]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Start up the server - best to be done from a separate terminal, not inside Jupyter Notebook\n",
+    "\n",
+    "```bash\n",
+    "model=sentence-transformers/all-MiniLM-L6-v2\n",
+    "port=7797\n",
+    "infinity_emb --port $port --model-name-or-path $model\n",
+    "```\n",
+    "\n",
+    "or alternativley just use docker:\n",
+    "```bash\n",
+    "model=sentence-transformers/all-MiniLM-L6-v2\n",
+    "port=7797\n",
+    "docker run -it --gpus all -p $port:$port michaelf34/infinity:latest --model-name-or-path $model --port $port\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Embed your documents using your Infinity instance "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "documents = [\n",
+    "    \"Baguette is a dish.\",\n",
+    "    \"Paris is the capital of France.\",\n",
+    "    \"numpy is a lib for linear algebra\",\n",
+    "    \"You escaped what I've escaped - You'd be in Paris getting fucked up too\",\n",
+    "]\n",
+    "query = \"Where is Paris?\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "embeddings created successful\n"
+     ]
+    }
+   ],
+   "source": [
+    "#\n",
+    "infinity_api_url = \"http://localhost:7797/v1\"\n",
+    "# model is currently not validated.\n",
+    "embeddings = InfinityEmbeddings(\n",
+    "    model=\"sentence-transformers/all-MiniLM-L6-v2\", infinity_api_url=infinity_api_url\n",
+    ")\n",
+    "try:\n",
+    "    documents_embedded = embeddings.embed_documents(documents)\n",
+    "    query_result = embeddings.embed_query(query)\n",
+    "    print(\"embeddings created successful\")\n",
+    "except Exception as ex:\n",
+    "    print(\n",
+    "        \"Make sure the infinity instance is running. Verify by clicking on \"\n",
+    "        f\"{infinity_api_url.replace('v1','docs')} Exception: {ex}. \"\n",
+    "    )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'Baguette is a dish.': 0.31344215908661155,\n",
+       " 'Paris is the capital of France.': 0.8148670296896388,\n",
+       " 'numpy is a lib for linear algebra': 0.004429399861302009,\n",
+       " \"You escaped what I've escaped - You'd be in Paris getting fucked up too\": 0.5088476180154582}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# (demo) compute similarity\n",
+    "import numpy as np\n",
+    "\n",
+    "scores = np.array(documents_embedded) @ np.array(query_result).T\n",
+    "dict(zip(documents, scores))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

docs/docs/integrations/text_embedding/instruct_embeddings.ipynb

@@ -5,8 +5,10 @@
    "id": "59428e05",
    "metadata": {},
    "source": [
-    "# InstructEmbeddings\n",
-    "Let's load the HuggingFace instruct Embeddings class."
+    "# Instruct Embeddings on Hugging Face\n",
+    "\n",
+    ">[Hugging Face sentence-transformers](https://huggingface.co/sentence-transformers) is a Python framework for state-of-the-art sentence, text and image embeddings.\n",
+    ">One of the instruct embedding models is used in the `HuggingFaceInstructEmbeddings` class.\n"
    ]
   },
   {
@@ -85,7 +87,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/docs/integrations/text_embedding/johnsnowlabs_embedding.ipynb

@@ -2,183 +2,207 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "source": [
-    "# Johnsnowlabs Embedding\n",
-    "\n",
-    "### Loading the Johnsnowlabs embedding class to generate and query embeddings\n",
-    "\n",
-    "Models are loaded with [nlp.load](https://nlp.johnsnowlabs.com/docs/en/jsl/load_api) and spark session is started with [nlp.start()](https://nlp.johnsnowlabs.com/docs/en/jsl/start-a-sparksession) under the hood.\n",
-    "For all 24.000+ models, see the [John Snow Labs Model Models Hub](https://nlp.johnsnowlabs.com/models)\n"
-   ],
    "metadata": {
-    "collapsed": false
-   }
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "# John Snow Labs\n",
+    "\n",
+    ">[John Snow Labs](https://nlp.johnsnowlabs.com/) NLP & LLM ecosystem includes software libraries for state-of-the-art AI at scale, Responsible AI, No-Code AI, and access to over 20,000 models for Healthcare, Legal, Finance, etc.\n",
+    ">\n",
+    ">Models are loaded with [nlp.load](https://nlp.johnsnowlabs.com/docs/en/jsl/load_api) and spark session is started >with [nlp.start()](https://nlp.johnsnowlabs.com/docs/en/jsl/start-a-sparksession) under the hood.\n",
+    ">For all 24.000+ models, see the [John Snow Labs Model Models Hub](https://nlp.johnsnowlabs.com/models)\n"
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {},
    "source": [
-    "! pip install johnsnowlabs\n"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "## Setting up"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "! pip install johnsnowlabs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "# If you have a enterprise license, you can run this to install enterprise features\n",
     "# from johnsnowlabs import nlp\n",
     "# nlp.install()"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
-  },
-  {
-   "cell_type": "code",
-   "source": [
-    "#### Import the necessary classes"
-   ],
-   "metadata": {
-    "collapsed": false
-   },
-   "execution_count": 1,
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Found existing installation: langchain 0.0.189\n",
-      "Uninstalling langchain-0.0.189:\n",
-      "  Successfully uninstalled langchain-0.0.189\n"
-     ]
-    }
    ]
   },
   {
    "cell_type": "markdown",
-   "source": [],
-   "metadata": {
-    "collapsed": false
-   }
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "from langchain.embeddings.johnsnowlabs import JohnSnowLabsEmbeddings"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "#### Initialize Johnsnowlabs Embeddings and Spark Session"
-   ],
    "metadata": {
-    "collapsed": false
-   }
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "Initialize Johnsnowlabs Embeddings and Spark Session"
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "embedder = JohnSnowLabsEmbeddings(\"en.embed_sentence.biobert.clinical_base_cased\")"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "#### Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
-   ],
    "metadata": {
-    "collapsed": false
-   }
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "texts = [\"Cancer is caused by smoking\", \"Antibiotics aren't painkiller\"]"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "#### Generate and print embeddings for the texts . The JohnSnowLabsEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
-   ],
    "metadata": {
-    "collapsed": false
-   }
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "Generate and print embeddings for the texts . The JohnSnowLabsEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "embeddings = embedder.embed_documents(texts)\n",
     "for i, embedding in enumerate(embeddings):\n",
     "    print(f\"Embedding for document {i+1}: {embedding}\")"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
-   "source": [
-    "#### Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
-   ],
    "metadata": {
-    "collapsed": false
-   }
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "source": [
+    "Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
    "outputs": [],
    "source": [
     "query = \"Cancer is caused by smoking\"\n",
     "query_embedding = embedder.embed_query(query)\n",
     "print(f\"Embedding for query: {query_embedding}\")"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }

docs/docs/integrations/text_embedding/sentence_transformers.ipynb

@@ -5,11 +5,13 @@
    "id": "ed47bb62",
    "metadata": {},
    "source": [
-    "# Sentence Transformers\n",
+    "# Sentence Transformers on Hugging Face\n",
     "\n",
-    ">[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
+    ">[Hugging Face sentence-transformers](https://huggingface.co/sentence-transformers) is a Python framework for state-of-the-art sentence, text and image embeddings.\n",
+    ">One of the embedding models is used in the `HuggingFaceEmbeddings` class.\n",
+    ">We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
     "\n",
-    "`SentenceTransformers` is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
+    "`sentence_transformers` package models are originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
    ]
   },
   {

docs/docs/integrations/text_embedding/tensorflowhub.ipynb

@@ -5,7 +5,11 @@
    "id": "fff4734f",
    "metadata": {},
    "source": [
-    "# TensorflowHub\n",
+    "# TensorFlow Hub\n",
+    "\n",
+    ">[TensorFlow Hub](https://www.tensorflow.org/hub) is a repository of trained machine learning models ready for fine-tuning and deployable anywhere. Reuse trained models like `BERT` and `Faster R-CNN` with just a few lines of code.\n",
+    ">\n",
+    ">\n",
     "Let's load the TensorflowHub Embedding class."
    ]
   },
@@ -105,7 +109,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/docs/integrations/text_embedding/voyageai.ipynb

@@ -7,6 +7,8 @@
    "source": [
     "# Voyage AI\n",
     "\n",
+    ">[Voyage AI](https://www.voyageai.com/) provides cutting-edge embedding/vectorizations models.\n",
+    "\n",
     "Let's load the Voyage Embedding class."
    ]
   },
@@ -215,7 +217,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.10.12"
   },
   "vscode": {
    "interpreter": {

docs/docs/integrations/toolkits/azure_cognitive_services.ipynb

@@ -12,7 +12,8 @@
     "- AzureCogsImageAnalysisTool: used to extract caption, objects, tags, and text from images. (Note: this tool is not available on Mac OS yet, due to the dependency on `azure-ai-vision` package, which is only supported on Windows and Linux currently.)\n",
     "- AzureCogsFormRecognizerTool: used to extract text, tables, and key-value pairs from documents.\n",
     "- AzureCogsSpeech2TextTool: used to transcribe speech to text.\n",
-    "- AzureCogsText2SpeechTool: used to synthesize text to speech."
+    "- AzureCogsText2SpeechTool: used to synthesize text to speech.\n",
+    "- AzureCogsTextAnalyticsHealthTool: used to extract healthcare entities."
    ]
   },
   {
@@ -32,6 +33,7 @@
    "source": [
     "# !pip install --upgrade azure-ai-formrecognizer > /dev/null\n",
     "# !pip install --upgrade azure-cognitiveservices-speech > /dev/null\n",
+    "# !pip install --upgrade azure-ai-textanalytics > /dev/null\n",
     "\n",
     "# For Windows/Linux\n",
     "# !pip install --upgrade azure-ai-vision > /dev/null"
@@ -60,7 +62,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -101,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -111,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -240,6 +242,65 @@
     "display.display(audio)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "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",
+      "{\n",
+      "  \"action\": \"azure_cognitive_services_text_analyics_health\",\n",
+      "  \"action_input\": \"The patient is a 54-year-old gentleman with a history of progressive angina over the past several months. The patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and 50% left main disease, with a strong family history of coronary artery disease with a brother dying at the age of 52 from a myocardial infarction and another brother who is status post coronary artery bypass grafting. The patient had a stress echocardiogram done on July, 2001, which showed no wall motion abnormalities, but this was a difficult study due to body habitus. The patient went for six minutes with minimal ST depressions in the anterior lateral leads, thought due to fatigue and wrist pain, his anginal equivalent. Due to the patient's increased symptoms and family history and history left main disease with total occasional of his RCA was referred for revascularization with open heart surgery.\"\n",
+      "}\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mThe text conatins the following healthcare entities: 54-year-old is a healthcare entity of type Age, gentleman is a healthcare entity of type Gender, progressive angina is a healthcare entity of type Diagnosis, past several months is a healthcare entity of type Time, cardiac catheterization is a healthcare entity of type ExaminationName, July of this year is a healthcare entity of type Time, total is a healthcare entity of type ConditionQualifier, occlusion is a healthcare entity of type SymptomOrSign, RCA is a healthcare entity of type BodyStructure, 50 is a healthcare entity of type MeasurementValue, % is a healthcare entity of type MeasurementUnit, left main is a healthcare entity of type BodyStructure, disease is a healthcare entity of type Diagnosis, family is a healthcare entity of type FamilyRelation, coronary artery disease is a healthcare entity of type Diagnosis, brother is a healthcare entity of type FamilyRelation, dying is a healthcare entity of type Diagnosis, 52 is a healthcare entity of type Age, myocardial infarction is a healthcare entity of type Diagnosis, brother is a healthcare entity of type FamilyRelation, coronary artery bypass grafting is a healthcare entity of type TreatmentName, stress echocardiogram is a healthcare entity of type ExaminationName, July, 2001 is a healthcare entity of type Time, wall motion abnormalities is a healthcare entity of type SymptomOrSign, body habitus is a healthcare entity of type SymptomOrSign, six minutes is a healthcare entity of type Time, minimal is a healthcare entity of type ConditionQualifier, ST depressions in the anterior lateral leads is a healthcare entity of type SymptomOrSign, fatigue is a healthcare entity of type SymptomOrSign, wrist pain is a healthcare entity of type SymptomOrSign, anginal equivalent is a healthcare entity of type SymptomOrSign, increased is a healthcare entity of type Course, symptoms is a healthcare entity of type SymptomOrSign, family is a healthcare entity of type FamilyRelation, left is a healthcare entity of type Direction, main is a healthcare entity of type BodyStructure, disease is a healthcare entity of type Diagnosis, occasional is a healthcare entity of type Course, RCA is a healthcare entity of type BodyStructure, revascularization is a healthcare entity of type TreatmentName, open heart surgery is a healthcare entity of type TreatmentName\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I know what to respond\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Final Answer\",\n",
+      "  \"action_input\": \"The text contains the following diagnoses: progressive angina, coronary artery disease, myocardial infarction, and coronary artery bypass grafting.\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The text contains the following diagnoses: progressive angina, coronary artery disease, myocardial infarction, and coronary artery bypass grafting.'"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\n",
+    "    \"\"\"The patient is a 54-year-old gentleman with a history of progressive angina over the past several months.\n",
+    "The patient had a cardiac catheterization in July of this year revealing total occlusion of the RCA and 50% left main disease ,\n",
+    "with a strong family history of coronary artery disease with a brother dying at the age of 52 from a myocardial infarction and\n",
+    "another brother who is status post coronary artery bypass grafting. The patient had a stress echocardiogram done on July , 2001 ,\n",
+    "which showed no wall motion abnormalities , but this was a difficult study due to body habitus. The patient went for six minutes with\n",
+    "minimal ST depressions in the anterior lateral leads , thought due to fatigue and wrist pain , his anginal equivalent. Due to the patient's\n",
+    "increased symptoms and family history and history left main disease with total occasional of his RCA was referred for revascularization with open heart surgery.\n",
+    "\n",
+    "List all the diagnoses.\n",
+    "\"\"\"\n",
+    ")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -264,7 +325,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.8.10"
   }
  },
  "nbformat": 4,

docs/docs/integrations/toolkits/clickup.ipynb

@@ -4,7 +4,11 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# ClickUp Langchain Toolkit"
+    "# ClickUp\n",
+    "\n",
+    ">[ClickUp](https://clickup.com/) is an all-in-one productivity platform that provides small and large teams across industries with flexible and customizable work management solutions, tools, and functions. \n",
+    "\n",
+    ">It is a cloud-based project management solution for businesses of all sizes featuring communication and collaboration tools to help achieve organizational goals."
    ]
   },
   {
@@ -27,14 +31,14 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Init"
+    "## Initializing"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Get Authenticated\n",
+    "### Get Authenticated\n",
     "1. Create a [ClickUp App](https://help.clickup.com/hc/en-us/articles/6303422883095-Create-your-own-app-with-the-ClickUp-API)\n",
     "2. Follow [these steps](https://clickup.com/api/developer-portal/authentication/) to get your `client_id` and `client_secret`.\n",
     "    - *Suggestion: use `https://google.com` as the redirect_uri. This is what we assume in the defaults for this toolkit.*\n",
@@ -112,18 +116,7 @@
    "source": [
     "access_token = ClickupAPIWrapper.get_access_token(\n",
     "    oauth_client_id, oauth_client_secret, code\n",
-    ")\n",
-    "\n",
-    "if access_token is not None:\n",
-    "    print(\"Copy/paste this code, into the next cell so you can reuse it!\")\n",
-    "    print(access_token)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "## Create Toolkit"
+    ")"
    ]
   },
   {
@@ -142,12 +135,6 @@
     }
    ],
    "source": [
-    "# Set your access token here\n",
-    "access_token = \"12345678_myaccesstokengoeshere123\"\n",
-    "access_token = (\n",
-    "    \"81928627_c009bf122ccf36ec3ba3e0ef748b07042c5e4217260042004a5934540cb61527\"\n",
-    ")\n",
-    "\n",
     "# Init toolkit\n",
     "clickup_api_wrapper = ClickupAPIWrapper(access_token=access_token)\n",
     "toolkit = ClickupToolkit.from_clickup_api_wrapper(clickup_api_wrapper)\n",
@@ -160,7 +147,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Create Agent"
+    "### Create Agent"
    ]
   },
   {
@@ -180,7 +167,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Run"
+    "## Use an Agent"
    ]
   },
   {
@@ -203,7 +190,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Navigation\n",
+    "### Navigation\n",
     "You can get the teams, folder and spaces your user has access to"
    ]
   },
@@ -287,7 +274,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Task Operations\n",
+    "### Task Operations\n",
     "You can get, ask question about tasks and update them"
    ]
   },
@@ -594,7 +581,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Creation\n",
+    "### Creation\n",
     "You can create tasks, lists and folders"
    ]
   },
@@ -778,7 +765,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Multi-Step Tasks"
+    "## Multi-Step Tasks"
    ]
   },
   {
@@ -848,7 +835,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "clickup-copilot",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -862,10 +849,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
-  },
-  "orig_nbformat": 4
+   "version": "3.10.12"
+  }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/tools/stackexchange.ipynb

@@ -0,0 +1,74 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# StackExchange\n",
+    "\n",
+    "This notebook goes over how to use the stack exchange component.\n",
+    "\n",
+    "All you need to do is install stackapi:\n",
+    "1. pip install stackapi\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pip install stackapi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.utilities import StackExchangeAPIWrapper"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stackexchange = StackExchangeAPIWrapper()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stackexchange.run(\"zsh: command not found: python\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/docs/integrations/vectorstores/astradb.ipynb

@@ -44,7 +44,7 @@
    "metadata": {},
    "source": [
     "_Note: depending on your LangChain setup, you may need to install/upgrade other dependencies needed for this demo_\n",
-    "_(specifically, recent versions of `datasets` `openai` `pypdf` and `tiktoken` are required)._"
+    "_(specifically, recent versions of `datasets`, `openai`, `pypdf` and `tiktoken` are required)._"
    ]
   },
   {
@@ -64,8 +64,6 @@
     "from langchain.document_loaders import PyPDFLoader\n",
     "from langchain.embeddings import OpenAIEmbeddings\n",
     "from langchain.prompts import ChatPromptTemplate\n",
-    "\n",
-    "# if not present yet, run: pip install \"datasets==2.14.6\"\n",
     "from langchain.schema import Document\n",
     "from langchain.schema.output_parser import StrOutputParser\n",
     "from langchain.schema.runnable import RunnablePassthrough\n",
@@ -145,7 +143,7 @@
    "outputs": [],
    "source": [
     "ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n",
-    "ASTRA_DB_TOKEN = getpass(\"ASTRA_DB_TOKEN = \")"
+    "ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")"
    ]
   },
   {
@@ -159,7 +157,7 @@
     "    embedding=embe,\n",
     "    collection_name=\"astra_vector_demo\",\n",
     "    api_endpoint=ASTRA_DB_API_ENDPOINT,\n",
-    "    token=ASTRA_DB_TOKEN,\n",
+    "    token=ASTRA_DB_APPLICATION_TOKEN,\n",
     ")"
    ]
   },
@@ -171,6 +169,14 @@
     "### Load a dataset"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "552e56b0-301a-4b06-99c7-57ba6faa966f",
+   "metadata": {},
+   "source": [
+    "Convert each entry in the source dataset into a `Document`, then write them into the vector store:"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -190,6 +196,16 @@
     "print(f\"\\nInserted {len(inserted_ids)} documents.\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "79d4f436-ef04-4288-8f79-97c9abb983ed",
+   "metadata": {},
+   "source": [
+    "In the above, `metadata` dictionaries are created from the source data and are part of the `Document`.\n",
+    "\n",
+    "_Note: check the [Astra DB API Docs](https://docs.datastax.com/en/astra-serverless/docs/develop/dev-with-json.html#_json_api_limits) for the valid metadata field names: some characters are reserved and cannot be used._"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "084d8802-ab39-4262-9a87-42eafb746f92",
@@ -213,6 +229,16 @@
     "print(f\"\\nInserted {len(inserted_ids_2)} documents.\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "63840eb3-8b29-4017-bc2f-301bf5001f28",
+   "metadata": {},
+   "source": [
+    "_Note: you may want to speed up the execution of `add_texts` and `add_documents` by increasing the concurrency level for_\n",
+    "_these bulk operations - check out the `*_concurrency` parameters in the class constructor and the `add_texts` docstrings_\n",
+    "_for more details. Depending on the network and the client machine specifications, your best-performing choice of parameters may vary._"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c031760a-1fc5-4855-adf2-02ed52fe2181",
@@ -625,7 +651,7 @@
    "outputs": [],
    "source": [
     "ASTRA_DB_ID = input(\"ASTRA_DB_ID = \")\n",
-    "ASTRA_DB_TOKEN = getpass(\"ASTRA_DB_TOKEN = \")\n",
+    "ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")\n",
     "\n",
     "desired_keyspace = input(\"ASTRA_DB_KEYSPACE (optional, can be left empty) = \")\n",
     "if desired_keyspace:\n",
@@ -645,7 +671,7 @@
     "\n",
     "cassio.init(\n",
     "    database_id=ASTRA_DB_ID,\n",
-    "    token=ASTRA_DB_TOKEN,\n",
+    "    token=ASTRA_DB_APPLICATION_TOKEN,\n",
     "    keyspace=ASTRA_DB_KEYSPACE,\n",
     ")"
    ]

docs/docs/integrations/vectorstores/faiss.ipynb

@@ -38,8 +38,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
-   "id": "47f9b495-88f1-4286-8d5d-1416103931a7",
+   "execution_count": null,
+   "id": "dc37144c-208d-4ab3-9f3a-0407a69fe052",
    "metadata": {
     "tags": []
    },
@@ -51,34 +51,12 @@
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
     "\n",
     "# Uncomment the following line if you need to initialize FAISS with no AVX2 optimization\n",
-    "# os.environ['FAISS_NO_AVX2'] = '1'"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "aac9563e",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
+    "# os.environ['FAISS_NO_AVX2'] = '1'\n",
+    "\n",
     "from langchain.document_loaders import TextLoader\n",
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "a3c3999a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders import TextLoader\n",
+    "from langchain.vectorstores import FAISS\n",
     "\n",
     "loader = TextLoader(\"../../../extras/modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",
@@ -200,31 +178,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
-   "id": "428a6816",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "db.save_local(\"faiss_index\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "56d1841c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "new_db = FAISS.load_local(\"faiss_index\", embeddings)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "39055525",
+   "execution_count": null,
+   "id": "1b31fe27-e0b3-42c6-b17c-8270b517ee1f",
    "metadata": {},
    "outputs": [],
    "source": [
+    "db.save_local(\"faiss_index\")\n",
+    "\n",
+    "new_db = FAISS.load_local(\"faiss_index\", embeddings)\n",
+    "\n",
     "docs = new_db.similarity_search(query)"
    ]
   },
@@ -266,30 +228,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "pkl = db.serialize_to_bytes()  # serializes the faiss index"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "eb083247",
-   "metadata": {
-    "vscode": {
-     "languageId": "r"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e36e220b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "from langchain.embeddings.huggingface import HuggingFaceEmbeddings\n",
+    "\n",
+    "pkl = db.serialize_to_bytes()  # serializes the faiss\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
+    "\n",
     "db = FAISS.deserialize_from_bytes(\n",
     "    embeddings=embeddings, serialized=pkl\n",
     ")  # Load the index"
@@ -306,33 +249,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
-   "id": "6dfd2b78",
+   "execution_count": null,
+   "id": "9b8f5e31-3f40-4e94-8d97-5883125efba7",
    "metadata": {},
    "outputs": [],
    "source": [
     "db1 = FAISS.from_texts([\"foo\"], embeddings)\n",
-    "db2 = FAISS.from_texts([\"bar\"], embeddings)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "29960da7",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'068c473b-d420-487a-806b-fb0ccea7f711': Document(page_content='foo', metadata={})}"
-      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
+    "db2 = FAISS.from_texts([\"bar\"], embeddings)\n",
+    "\n",
     "db1.docstore._dict"
    ]
   },

docs/docs/integrations/vectorstores/faiss_async.ipynb

@@ -5,15 +5,16 @@
    "id": "683953b3",
    "metadata": {},
    "source": [
-    "# Faiss\n",
+    "# Faiss (Async)\n",
     "\n",
     ">[Facebook AI Similarity Search (Faiss)](https://engineering.fb.com/2017/03/29/data-infrastructure/faiss-a-library-for-efficient-similarity-search/) is a library for efficient similarity search and clustering of dense vectors. It contains algorithms that search in sets of vectors of any size, up to ones that possibly do not fit in RAM. It also contains supporting code for evaluation and parameter tuning.\n",
     "\n",
     "[Faiss documentation](https://faiss.ai/).\n",
     "\n",
-    "This notebook shows how to use functionality related to the `FAISS` vector database using asyncio.\n",
+    "This notebook shows how to use functionality related to the `FAISS` vector database using `asyncio`.\n",
+    "LangChain implemented the synchronous and asynchronous vector store functions.\n",
     "\n",
-    "See synchronous version [here](https://python.langchain.com/docs/integrations/vectorstores/faiss)."
+    "See `synchronous` version [here](https://python.langchain.com/docs/integrations/vectorstores/faiss)."
    ]
   },
   {
@@ -40,8 +41,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "47f9b495-88f1-4286-8d5d-1416103931a7",
+   "execution_count": null,
+   "id": "971a172a-2d87-4eec-be92-87aa174fec30",
    "metadata": {
     "tags": []
    },
@@ -53,81 +54,25 @@
     "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
     "\n",
     "# Uncomment the following line if you need to initialize FAISS with no AVX2 optimization\n",
-    "# os.environ['FAISS_NO_AVX2'] = '1'"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "aac9563e",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
+    "# os.environ['FAISS_NO_AVX2'] = '1'\n",
+    "\n",
     "from langchain.document_loaders import TextLoader\n",
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import FAISS"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "a3c3999a",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders import TextLoader\n",
+    "from langchain.vectorstores import FAISS\n",
     "\n",
     "loader = TextLoader(\"../../../extras/modules/state_of_the_union.txt\")\n",
     "documents = loader.load()\n",
     "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
     "docs = text_splitter.split_documents(documents)\n",
     "\n",
-    "embeddings = OpenAIEmbeddings()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "5eabdb75",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
-   "source": [
+    "embeddings = OpenAIEmbeddings()\n",
+    "\n",
     "db = await FAISS.afrom_documents(docs, embeddings)\n",
     "\n",
     "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "docs = await db.asimilarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "4b172de8",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
-      "\n",
-      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
-      "\n",
-      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
-      "\n",
-      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
-     ]
-    }
-   ],
-   "source": [
+    "docs = await db.asimilarity_search(query)\n",
+    "\n",
     "print(docs[0].page_content)"
    ]
   },
@@ -142,33 +87,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "186ee1d8",
+   "execution_count": null,
+   "id": "30bf7c85-a273-45dc-ae9e-f138e330b42e",
    "metadata": {},
    "outputs": [],
    "source": [
-    "docs_and_scores = await db.asimilarity_search_with_score(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "284e04b5",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "(Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': './state_of_the_union.txt'}),\n",
-       " 0.36871302)"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
+    "docs_and_scores = await db.asimilarity_search_with_score(query)\n",
+    "\n",
     "docs_and_scores[0]"
    ]
   },
@@ -202,52 +127,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "428a6816",
+   "execution_count": null,
+   "id": "88e11f08-1ac8-45aa-8bc0-56439ef87256",
    "metadata": {},
    "outputs": [],
    "source": [
-    "db.save_local(\"faiss_index\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "56d1841c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "new_db = FAISS.load_local(\"faiss_index\", embeddings, asynchronous=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "39055525",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "docs = await new_db.asimilarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "98378c4e",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', metadata={'source': './state_of_the_union.txt'})"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
+    "db.save_local(\"faiss_index\")\n",
+    "\n",
+    "new_db = FAISS.load_local(\"faiss_index\", embeddings, asynchronous=True)\n",
+    "\n",
+    "docs = await new_db.asimilarity_search(query)\n",
+    "\n",
     "docs[0]"
    ]
   },
@@ -261,26 +151,6 @@
     "you can pickle the FAISS Index by these functions. If you use embeddings model which is of 90 mb (sentence-transformers/all-MiniLM-L6-v2 or any other model), the resultant pickle size would be more than 90 mb. the size of the model is also included in the overall size. To overcome this, use the below functions. These functions only serializes FAISS index and size would be much lesser. this can be helpful if you wish to store the index in database like sql."
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "d8faead5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "pkl = db.serialize_to_bytes()  # serializes the faiss index"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "eb083247",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -288,6 +158,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain.embeddings.huggingface import HuggingFaceEmbeddings\n",
+    "\n",
+    "pkl = db.serialize_to_bytes()  # serializes the faiss index\n",
+    "embeddings = HuggingFaceEmbeddings(model_name=\"all-MiniLM-L6-v2\")\n",
     "db = FAISS.deserialize_from_bytes(\n",
     "    embeddings=embeddings, serialized=pkl, asynchronous=True\n",
     ")  # Load the index"
@@ -596,7 +470,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.3"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/hippo.ipynb

@@ -4,13 +4,15 @@
    "cell_type": "markdown",
    "id": "357f24224a8e818f",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
-    "## Hippo\n",
+    "# Hippo\n",
     "\n",
-    ">[Hippo](https://www.transwarp.cn/starwarp) Please visit our official website for how to run a Hippo instance and\n",
-    "how to use functionality related to the Hippo vector database\n",
+    ">[Transwarp Hippo](https://www.transwarp.cn/en/subproduct/hippo) is an enterprise-level cloud-native distributed vector database that supports storage, retrieval, and management of massive vector-based datasets. It efficiently solves problems such as vector similarity search and high-density vector clustering. `Hippo` features high availability, high performance, and easy scalability. It has many functions, such as multiple vector search indexes, data partitioning and sharding, data persistence, incremental data ingestion, vector scalar field filtering, and mixed queries. It can effectively meet the high real-time search demands of enterprises for massive vector data\n",
     "\n",
     "## Getting Started\n",
     "\n",
@@ -21,12 +23,15 @@
    "cell_type": "markdown",
    "id": "a92d2ce26df7ac4c",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Installing Dependencies\n",
     "\n",
-    "Initially, we require the installation of certain dependencies, such as OpenAI, Langchain, and Hippo-API. Please note, you should install the appropriate versions tailored to your environment."
+    "Initially, we require the installation of certain dependencies, such as OpenAI, Langchain, and Hippo-API. Please note, that you should install the appropriate versions tailored to your environment."
    ]
   },
   {
@@ -38,7 +43,10 @@
      "end_time": "2023-10-30T06:47:54.718488Z",
      "start_time": "2023-10-30T06:47:53.563129Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -59,12 +67,15 @@
    "cell_type": "markdown",
    "id": "554081137df2c252",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "Note: Python version needs to be >=3.8.\n",
     "\n",
-    "## Best Practice\n",
+    "## Best Practices\n",
     "### Importing Dependency Packages"
    ]
   },
@@ -77,7 +88,10 @@
      "end_time": "2023-10-30T06:47:56.003409Z",
      "start_time": "2023-10-30T06:47:55.998839Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -94,7 +108,10 @@
    "cell_type": "markdown",
    "id": "dad255dae8aea755",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Loading Knowledge Documents"
@@ -109,7 +126,10 @@
      "end_time": "2023-10-30T06:47:59.027869Z",
      "start_time": "2023-10-30T06:47:59.023934Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -122,7 +142,10 @@
    "cell_type": "markdown",
    "id": "e9b93c330f1c6160",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Segmenting the Knowledge Document\n",
@@ -139,7 +162,10 @@
      "end_time": "2023-10-30T06:48:00.279351Z",
      "start_time": "2023-10-30T06:48:00.275763Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -151,7 +177,10 @@
    "cell_type": "markdown",
    "id": "eefe28c7c993ffdf",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Declaring the Embedding Model\n",
@@ -167,7 +196,10 @@
      "end_time": "2023-10-30T06:48:11.686166Z",
      "start_time": "2023-10-30T06:48:11.664355Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -188,7 +220,10 @@
    "cell_type": "markdown",
    "id": "e60235602ed91d3c",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Declaring Hippo Client"
@@ -203,7 +238,10 @@
      "end_time": "2023-10-30T06:48:48.594298Z",
      "start_time": "2023-10-30T06:48:48.585267Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -214,7 +252,10 @@
    "cell_type": "markdown",
    "id": "43ee6dbd765c3172",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Storing the Document"
@@ -229,7 +270,10 @@
      "end_time": "2023-10-30T06:51:12.661741Z",
      "start_time": "2023-10-30T06:51:06.257156Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -257,7 +301,10 @@
    "cell_type": "markdown",
    "id": "89077cc9763d5dd0",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Conducting Knowledge-based Question and Answer\n",
@@ -274,7 +321,10 @@
      "end_time": "2023-10-30T06:51:28.329351Z",
      "start_time": "2023-10-30T06:51:28.318713Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -293,7 +343,10 @@
    "cell_type": "markdown",
    "id": "a4c5d73016a9db0c",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Acquiring Related Knowledge Based on the Question："
@@ -308,7 +361,10 @@
      "end_time": "2023-10-30T06:51:33.195634Z",
      "start_time": "2023-10-30T06:51:32.196493Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -328,7 +384,10 @@
    "cell_type": "markdown",
    "id": "e5adbaaa7086d1ae",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Constructing a Prompt Template"
@@ -343,7 +402,10 @@
      "end_time": "2023-10-30T06:51:35.649376Z",
      "start_time": "2023-10-30T06:51:35.645763Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -358,7 +420,10 @@
    "cell_type": "markdown",
    "id": "b36b6a9adbec8a82",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "### Waiting for the Large Language Model to Generate an Answer"
@@ -373,7 +438,10 @@
      "end_time": "2023-10-30T06:52:17.967885Z",
      "start_time": "2023-10-30T06:51:37.692819Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -402,7 +470,10 @@
     "ExecuteTime": {
      "start_time": "2023-10-30T06:42:42.172639Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": []
@@ -410,21 +481,21 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/meilisearch.ipynb

@@ -23,7 +23,7 @@
     "\n",
     "You will need a running Meilisearch instance to use as your vector store. You can run [Meilisearch in local](https://www.meilisearch.com/docs/learn/getting_started/installation#local-installation) or create a [Meilisearch Cloud](https://cloud.meilisearch.com/) account.\n",
     "\n",
-    "As of Meilisearch v1.3, vector storage is an experimental feature. After launching your Meilisearch instance, you need to **enable vector storage**. For self-hosted Meilisearch, read the docs on [enabling experimental features](https://www.meilisearch.com/docs/learn/experimental/vector-search). On **Meilisearch Cloud**, enable _Vector Store_ via your project _Settings_ page.\n",
+    "As of Meilisearch v1.3, vector storage is an experimental feature. After launching your Meilisearch instance, you need to **enable vector storage**. For self-hosted Meilisearch, read the docs on [enabling experimental features](https://www.meilisearch.com/docs/learn/experimental/overview). On **Meilisearch Cloud**, enable _Vector Store_ via your project _Settings_ page.\n",
     "\n",
     "You should now have a running Meilisearch instance with vector storage enabled. 🎉\n",
     "\n",

docs/docs/integrations/vectorstores/mongodb_atlas.ipynb

@@ -24,7 +24,7 @@
    "source": [
     "> Note: \n",
     ">* This feature is in Public Preview and available for evaluation purposes, to validate functionality, and to gather feedback from public preview users. It is not recommended for production deployments as we may introduce breaking changes.\n",
-    ">* The langchain version 0.0.35 ([release notes](https://github.com/langchain-ai/langchain/releases/tag/v0.0.305)) introduces the support for $vectorSearch MQL stage, which is available with MongoDB Atlas 6.0.11 and 7.0.2. Users utilizing earlier versions of MongoDB Atlas need to pin their LangChain version to <=0.0.304\n",
+    ">* The langchain version 0.0.305 ([release notes](https://github.com/langchain-ai/langchain/releases/tag/v0.0.305)) introduces the support for $vectorSearch MQL stage, which is available with MongoDB Atlas 6.0.11 and 7.0.2. Users utilizing earlier versions of MongoDB Atlas need to pin their LangChain version to <=0.0.304\n",
     "> \n",
     "> "
    ]

docs/docs/integrations/vectorstores/semadb.ipynb

@@ -7,11 +7,11 @@
    "source": [
     "# SemaDB\n",
     "\n",
-    "> SemaDB is a no fuss vector similarity database for building AI applications. The hosted SemaDB Cloud offers a no fuss developer experience to get started.\n",
+    "> [SemaDB](https://www.semafind.com/products/semadb) from [SemaFind](https://www.semafind.com) is a no fuss vector similarity database for building AI applications. The hosted `SemaDB Cloud` offers a no fuss developer experience to get started.\n",
     "\n",
     "The full documentation of the API along with examples and an interactive playground is available on [RapidAPI](https://rapidapi.com/semafind-semadb/api/semadb).\n",
     "\n",
-    "This notebook demonstrates how the `langchain` wrapper can be used with SemaDB Cloud."
+    "This notebook demonstrates usage of the `SemaDB Cloud` vector store."
    ]
   },
   {

docs/docs/integrations/vectorstores/sklearn.ipynb

@@ -217,7 +217,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.6"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/sqlitevss.ipynb

@@ -3,12 +3,15 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
-    "# sqlite-vss\n",
+    "# SQLite-VSS\n",
     "\n",
-    ">[sqlite-vss](https://alexgarcia.xyz/sqlite-vss/) is an SQLite extension designed for vector search, emphasizing local-first operations and easy integration into applications without external servers. Leveraging the Faiss library, it offers efficient similarity search and clustering capabilities.\n",
+    ">[SQLite-VSS](https://alexgarcia.xyz/sqlite-vss/) is an `SQLite` extension designed for vector search, emphasizing local-first operations and easy integration into applications without external servers. Leveraging the `Faiss` library, it offers efficient similarity search and clustering capabilities.\n",
     "\n",
     "This notebook shows how to use the `SQLiteVSS` vector database."
    ]
@@ -17,7 +20,10 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -28,10 +34,13 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
-    "### Quickstart"
+    "## Quickstart"
    ]
   },
   {
@@ -42,7 +51,10 @@
      "end_time": "2023-09-06T14:55:55.370351Z",
      "start_time": "2023-09-06T14:55:53.547755Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -97,10 +109,13 @@
   {
    "cell_type": "markdown",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
-    "### Using existing sqlite connection"
+    "## Using existing SQLite connection"
    ]
   },
   {
@@ -111,7 +126,10 @@
      "end_time": "2023-09-06T14:59:22.086252Z",
      "start_time": "2023-09-06T14:59:21.693237Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -166,7 +184,10 @@
      "end_time": "2023-09-06T15:01:15.550318Z",
      "start_time": "2023-09-06T15:01:15.546428Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -180,7 +201,10 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": []
@@ -188,23 +212,23 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }

docs/docs/integrations/vectorstores/timescalevector.ipynb

@@ -7,28 +7,30 @@
    "source": [
     "# Timescale Vector (Postgres)\n",
     "\n",
+    ">[Timescale Vector](https://www.timescale.com/ai?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral) is `PostgreSQL++` vector database for AI applications.\n",
+    "\n",
     "This notebook shows how to use the Postgres vector database `Timescale Vector`. You'll learn how to use TimescaleVector for (1) semantic search, (2) time-based vector search, (3) self-querying, and (4) how to create indexes to speed up queries.\n",
     "\n",
     "## What is Timescale Vector?\n",
-    "**[Timescale Vector](https://www.timescale.com/ai?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral) is PostgreSQL++ for AI applications.**\n",
     "\n",
-    "Timescale Vector enables you to efficiently store and query millions of vector embeddings in `PostgreSQL`.\n",
+    "`Timescale Vector` enables you to efficiently store and query millions of vector embeddings in `PostgreSQL`.\n",
     "- Enhances `pgvector` with faster and more accurate similarity search on 100M+ vectors via `DiskANN` inspired indexing algorithm.\n",
     "- Enables fast time-based vector search via automatic time-based partitioning and indexing.\n",
     "- Provides a familiar SQL interface for querying vector embeddings and relational data.\n",
     "\n",
-    "Timescale Vector is cloud PostgreSQL for AI that scales with you from POC to production:\n",
+    "`Timescale Vector` is cloud `PostgreSQL` for AI that scales with you from POC to production:\n",
     "- Simplifies operations by enabling you to store relational metadata, vector embeddings, and time-series data in a single database.\n",
-    "- Benefits from rock-solid PostgreSQL foundation with enterprise-grade feature liked streaming backups and replication, high-availability and row-level security.\n",
+    "- Benefits from rock-solid PostgreSQL foundation with enterprise-grade features like streaming backups and replication, high availability and row-level security.\n",
     "- Enables a worry-free experience with enterprise-grade security and compliance.\n",
     "\n",
     "## How to access Timescale Vector\n",
-    "Timescale Vector is available on [Timescale](https://www.timescale.com/ai?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral), the cloud PostgreSQL platform. (There is no self-hosted version at this time.)\n",
+    "\n",
+    "`Timescale Vector` is available on [Timescale](https://www.timescale.com/ai?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral), the cloud PostgreSQL platform. (There is no self-hosted version at this time.)\n",
     "\n",
     "LangChain users get a 90-day free trial for Timescale Vector.\n",
     "- To get started, [signup](https://console.cloud.timescale.com/signup?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral) to Timescale, create a new database and follow this notebook!\n",
     "- See the [Timescale Vector explainer blog](https://www.timescale.com/blog/how-we-made-postgresql-the-best-vector-database/?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral) for more details and performance benchmarks.\n",
-    "- See the [installation instructions](https://github.com/timescale/python-vector) for more details on using Timescale Vector in python."
+    "- See the [installation instructions](https://github.com/timescale/python-vector) for more details on using Timescale Vector in Python."
    ]
   },
   {
@@ -1726,7 +1728,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.16"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/integrations/vectorstores/vearch.ipynb

@@ -1,5 +1,43 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Vearch\n",
+    "\n",
+    ">[Vearch](https://vearch.readthedocs.io) is the vector search infrastructure for deeping learning and AI applications.\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Setting up\n",
+    "\n",
+    "Follow [instructions](https://vearch.readthedocs.io/en/latest/quick-start-guide.html#)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install vearch\n",
+    "\n",
+    "# OR\n",
+    "\n",
+    "!pip install vearch_cluster"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 2,
@@ -464,7 +502,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.10.13 ('vearch_cluster_langchain')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -478,9 +516,8 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.13"
+   "version": "3.10.12"
   },
-  "orig_nbformat": 4,
   "vscode": {
    "interpreter": {
     "hash": "f1da10a89896267ed34b497c9568817f36cc7ea79826b5cfca4d96376f5b4835"
@@ -488,5 +525,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }

docs/docs/integrations/vectorstores/zep.ipynb

@@ -4,27 +4,21 @@
    "cell_type": "markdown",
    "id": "9eb8dfa6fdb71ef5",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "# Zep\n",
-    "## VectorStore Example for [Zep](https://docs.getzep.com/) - Fast, scalable building blocks for LLM Apps\n",
     "\n",
-    "### More on Zep:\n",
+    ">[Zep](https://docs.getzep.com/) is an open-source platform for LLM apps. Go from a prototype\n",
+    ">built in LangChain or LlamaIndex, or a custom app, to production in minutes without rewriting code.\n",
     "\n",
-    "Zep is an open source platform for productionizing LLM apps. Go from a prototype\n",
-    "built in LangChain or LlamaIndex, or a custom app, to production in minutes without\n",
-    "rewriting code.\n",
+    "## Key Features:\n",
     "\n",
-    "## Fast, Scalable Building Blocks for LLM Apps\n",
-    "Zep is an open source platform for productionizing LLM apps. Go from a prototype\n",
-    "built in LangChain or LlamaIndex, or a custom app, to production in minutes without\n",
-    "rewriting code.\n",
-    "\n",
-    "Key Features:\n",
-    "\n",
-    "- **Fast!** Zep operates independently of the your chat loop, ensuring a snappy user experience.\n",
-    "- **Chat History Memory, Archival, and Enrichment**, populate your prompts with relevant chat history, sumamries, named entities, intent data, and more.\n",
+    "- **Fast!** `Zep` operates independently of your chat loop, ensuring a snappy user experience.\n",
+    "- **Chat History Memory, Archival, and Enrichment**, populate your prompts with relevant chat history, summaries, named entities, intent data, and more.\n",
     "- **Vector Search over Chat History and Documents** Automatic embedding of documents, chat histories, and summaries. Use Zep's similarity or native MMR Re-ranked search to find the most relevant.\n",
     "- **Manage Users and their Chat Sessions** Users and their Chat Sessions are first-class citizens in Zep, allowing you to manage user interactions with your bots or agents easily.\n",
     "- **Records Retention and Privacy Compliance** Comply with corporate and regulatory mandates for records retention while ensuring compliance with privacy regulations such as CCPA and GDPR. Fulfill *Right To Be Forgotten* requests with a single API call\n",
@@ -34,14 +28,15 @@
     "and searching your user's chat history.\n",
     "\n",
     "## Installation\n",
-    "Follow the [Zep Quickstart Guide](https://docs.getzep.com/deployment/quickstart/) to install and get started with Zep.\n",
     "\n",
-    "## Usage\n",
+    "Follow the [Zep Quickstart Guide](https://docs.getzep.com/deployment/quickstart/) to install and get started with Zep.\n",
     "\n",
     "You'll need your Zep API URL and optionally an API key to use the Zep VectorStore. \n",
     "See the [Zep docs](https://docs.getzep.com) for more information.\n",
     "\n",
-    "In the examples below, we're using Zep's auto-embedding feature which automatically embed documents on the Zep server \n",
+    "## Usage\n",
+    "\n",
+    "In the examples below, we're using Zep's auto-embedding feature which automatically embeds documents on the Zep server \n",
     "using low-latency embedding models.\n",
     "\n",
     "## Note\n",
@@ -55,7 +50,10 @@
    "cell_type": "markdown",
    "id": "9a3a11aab1412d98",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Load or create a Collection from documents"
@@ -70,7 +68,10 @@
      "end_time": "2023-08-13T01:07:50.672390Z",
      "start_time": "2023-08-13T01:07:48.777799Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -124,7 +125,10 @@
      "end_time": "2023-08-13T01:07:53.807663Z",
      "start_time": "2023-08-13T01:07:50.671241Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -170,7 +174,10 @@
    "cell_type": "markdown",
    "id": "94ca9dfa7d0ecaa5",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Simarility Search Query over the Collection"
@@ -185,7 +192,10 @@
      "end_time": "2023-08-13T01:07:54.195988Z",
      "start_time": "2023-08-13T01:07:53.808550Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -237,7 +247,10 @@
    "cell_type": "markdown",
    "id": "e02b61a9af0b2c80",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "## Search over Collection Re-ranked by MMR\n",
@@ -254,7 +267,10 @@
      "end_time": "2023-08-13T01:07:54.394873Z",
      "start_time": "2023-08-13T01:07:54.180901Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -304,7 +320,10 @@
    "cell_type": "markdown",
    "id": "42455e31d4ab0d68",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
     "# Filter by Metadata\n",
@@ -321,7 +340,10 @@
      "end_time": "2023-08-13T01:08:06.323569Z",
      "start_time": "2023-08-13T01:07:54.381822Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -367,10 +389,13 @@
    "cell_type": "markdown",
    "id": "5b225f3ae1e61de8",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
-    "### We see results from both books. Note the `source` metadata"
+    "We see results from both books. Note the `source` metadata"
    ]
   },
   {
@@ -382,7 +407,10 @@
      "end_time": "2023-08-13T01:08:06.504769Z",
      "start_time": "2023-08-13T01:08:06.325435Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -431,10 +459,13 @@
    "cell_type": "markdown",
    "id": "7b81d7cae351a1ec",
    "metadata": {
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "source": [
-    "### Let's try again using a filter for only the Sherlock Holmes document."
+    "Now, we set up a filter"
    ]
   },
   {
@@ -446,7 +477,10 @@
      "end_time": "2023-08-13T01:08:06.672836Z",
      "start_time": "2023-08-13T01:08:06.505944Z"
     },
-    "collapsed": false
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -515,7 +549,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -529,7 +563,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.6"
+   "version": "3.10.12"
   }
  },
  "nbformat": 4,

docs/docs/modules/agents/agent_types/openai_assistants.ipynb

@@ -25,7 +25,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "aa761a93-caa1-4e56-b901-5ff50a89bc82",
    "metadata": {},
    "outputs": [],
@@ -35,10 +35,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 12,
    "id": "5944a18a-95eb-44ce-a66f-5f50db1d3e1f",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[ThreadMessage(id='msg_qgxkD5kvkZyl0qOaL4czPFkZ', assistant_id='asst_0T8S7CJuUa4Y4hm1PF6n62v7', content=[MessageContentText(text=Text(annotations=[], value='The result of the calculation \\\\(10 - 4^{2.7}\\\\) is approximately \\\\(-32.224\\\\).'), type='text')], created_at=1700169519, file_ids=[], metadata={}, object='thread.message', role='assistant', run_id='run_aH3ZgSWNk3vYIBQm3vpE8tr4', thread_id='thread_9K6cYfx1RBh0pOWD8SxwVWW9')]"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "interpreter_assistant = OpenAIAssistantRunnable.create_assistant(\n",
     "    name=\"langchain assistant\",\n",
@@ -72,19 +83,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "cc0cba70-8507-498d-92ac-fe47133db200",
    "metadata": {},
    "outputs": [],
    "source": [
+    "import getpass\n",
+    "\n",
     "from langchain.tools import DuckDuckGoSearchRun, E2BDataAnalysisTool\n",
     "\n",
-    "tools = [E2BDataAnalysisTool(api_key=\"...\"), DuckDuckGoSearchRun()]"
+    "tools = [E2BDataAnalysisTool(api_key=getpass.getpass()), DuckDuckGoSearchRun()]"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "91e6973d-3d9a-477f-99e2-4aaad16004ec",
    "metadata": {},
    "outputs": [],
@@ -103,15 +116,31 @@
    "id": "78fa9320-06fc-4cbc-a3cf-39aaf2427080",
    "metadata": {},
    "source": [
-    "#### Using AgentExecutor"
+    "#### Using AgentExecutor\n",
+    "\n",
+    "The OpenAIAssistantRunnable is compatible with the AgentExecutor, so we can pass it in as an agent directly to the executor. The AgentExecutor handles calling the invoked tools and uploading the tool outputs back to the Assistants API. Plus it comes with built-in LangSmith tracing."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "e38007a4-fcc1-419b-9ae4-70d36c3fc1cd",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'content': \"What's the weather in SF today divided by 2.7\",\n",
+       " 'output': \"The search results indicate that the weather in San Francisco is 67 °F. Now I will divide this temperature by 2.7 and provide you with the result. Please note that this is a mathematical operation and does not represent a meaningful physical quantity.\\n\\nLet's calculate 67 °F divided by 2.7.\\nThe result of dividing the current temperature in San Francisco, which is 67 °F, by 2.7 is approximately 24.815.\",\n",
+       " 'thread_id': 'thread_hcpYI0tfpB9mHa9d95W7nK2B',\n",
+       " 'run_id': 'run_qOuVmPXS9xlV3XNPcfP8P9W2'}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "from langchain.agents import AgentExecutor\n",
     "\n",
@@ -119,17 +148,28 @@
     "agent_executor.invoke({\"content\": \"What's the weather in SF today divided by 2.7\"})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "db6b9cbf-dd54-4346-be6c-842e08756ccc",
+   "metadata": {},
+   "source": [
+    ":::tip [LangSmith trace](https://smith.langchain.com/public/6750972b-0849-4beb-a8bb-353d424ffade/r)\n",
+    ":::"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "6bf4199a-eed1-485a-8da3-aed948c0e1e2",
    "metadata": {},
    "source": [
-    "#### Custom execution"
+    "#### Custom execution\n",
+    "\n",
+    "Or with LCEL we can easily write our own execution loop for running the assistant. This gives us full control over execution."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "357361ff-f54d-4fd0-b69b-77689f56f40e",
    "metadata": {},
    "outputs": [],
@@ -145,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "id": "864e7f9b-0501-4bb7-8aad-a7aa19b601af",
    "metadata": {},
    "outputs": [],
@@ -177,34 +217,86 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 8,
    "id": "5ad6bb07-aac4-4b71-9e67-cc177fcbc537",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "e2b_data_analysis {'python_code': 'result = 10 - 4 ** 2.7\\nprint(result)'} {\"stdout\": \"-32.22425314473263\", \"stderr\": \"\", \"artifacts\": []}\n",
+      "\n",
+      "\\( 10 - 4^{2.7} \\) equals approximately -32.224.\n"
+     ]
+    }
+   ],
    "source": [
     "response = execute_agent(agent, tools, {\"content\": \"What's 10 - 4 raised to the 2.7\"})\n",
     "print(response.return_values[\"output\"])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "6fd9f9c0-4b07-4f71-a784-88ee7bd4b089",
+   "metadata": {},
+   "source": [
+    "## Using existing Thread\n",
+    "\n",
+    "To use an existing thread we just need to pass the \"thread_id\" in when invoking the agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "f55a3a3a-8169-491e-aa15-cf30a2b230df",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "e2b_data_analysis {'python_code': 'result = 10 - 4 ** 2.7 + 17.241\\nprint(result)'} {\"stdout\": \"-14.983253144732629\", \"stderr\": \"\", \"artifacts\": []}\n",
+      "\n",
+      "\\( 10 - 4^{2.7} + 17.241 \\) equals approximately -14.983.\n"
+     ]
+    }
+   ],
+   "source": [
+    "next_response = execute_agent(\n",
+    "    agent,\n",
+    "    tools,\n",
+    "    {\"content\": \"now add 17.241\", \"thread_id\": response.return_values[\"thread_id\"]},\n",
+    ")\n",
+    "print(next_response.return_values[\"output\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1b97ee01-a657-452c-ba7f-95227ec7056e",
+   "metadata": {},
+   "source": [
+    "## Using existing Assistant\n",
+    "\n",
+    "To use an existing Assistant we can initialize the `OpenAIAssistantRunnable` directly with an `assistant_id`."
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f55a3a3a-8169-491e-aa15-cf30a2b230df",
+   "id": "08ef6ef5-e8bc-4c69-882d-65273655f6a7",
    "metadata": {},
    "outputs": [],
    "source": [
-    "next_response = execute_agent(\n",
-    "    agent, tools, {\"content\": \"now add 17.241\", \"thread_id\": response.thread_id}\n",
-    ")\n",
-    "print(next_response.return_values[\"output\"])"
+    "agent = OpenAIAssistantRunnable(assistant_id=\"<ASSISTANT_ID>\", as_agent=True)"
    ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "poetry-venv",
    "language": "python",
-   "name": "python3"
+   "name": "poetry-venv"
   },
   "language_info": {
    "codemirror_mode": {

docs/docs/modules/agents/how_to/agent_iter.ipynb

@@ -22,11 +22,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import pydantic\n",
     "from langchain.agents import AgentType, initialize_agent\n",
     "from langchain.agents.tools import Tool\n",
     "from langchain.chains import LLMMathChain\n",
-    "from langchain.chat_models import ChatOpenAI"
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from pydantic.v1 import BaseModel, Field"
    ]
   },
   {
@@ -65,12 +65,12 @@
     "primes = {998: 7901, 999: 7907, 1000: 7919}\n",
     "\n",
     "\n",
-    "class CalculatorInput(pydantic.BaseModel):\n",
-    "    question: str = pydantic.Field()\n",
+    "class CalculatorInput(BaseModel):\n",
+    "    question: str = Field()\n",
     "\n",
     "\n",
-    "class PrimeInput(pydantic.BaseModel):\n",
-    "    n: int = pydantic.Field()\n",
+    "class PrimeInput(BaseModel):\n",
+    "    n: int = Field()\n",
     "\n",
     "\n",
     "def is_prime(n: int) -> bool:\n",

docs/docs/modules/data_connection/index.mdx

@@ -18,23 +18,23 @@ This encompasses several key modules.
 
 **[Document loaders](/docs/modules/data_connection/document_loaders/)**
 
-Load documents from many different sources.
+**Document loaders** load documents from many different sources.
 LangChain provides over 100 different document loaders as well as integrations with other major providers in the space,
 like AirByte and Unstructured.
-We provide integrations to load all types of documents (HTML, PDF, code) from all types of locations (private s3 buckets, public websites).
+LangChain provides integrations to load all types of documents (HTML, PDF, code) from all types of locations (private S3 buckets, public websites).
 
 **[Document transformers](/docs/modules/data_connection/document_transformers/)**
 
 A key part of retrieval is fetching only the relevant parts of documents.
-This involves several transformation steps in order to best prepare the documents for retrieval.
+This involves several transformation steps to prepare the documents for retrieval.
 One of the primary ones here is splitting (or chunking) a large document into smaller chunks.
-LangChain provides several different algorithms for doing this, as well as logic optimized for specific document types (code, markdown, etc).
+LangChain provides several transformation algorithms for doing this, as well as logic optimized for specific document types (code, markdown, etc).
 
 **[Text embedding models](/docs/modules/data_connection/text_embedding/)**
 
-Another key part of retrieval has become creating embeddings for documents.
+Another key part of retrieval is creating embeddings for documents.
 Embeddings capture the semantic meaning of the text, allowing you to quickly and
-efficiently find other pieces of text that are similar.
+efficiently find other pieces of a text that are similar.
 LangChain provides integrations with over 25 different embedding providers and methods,
 from open-source to proprietary API,
 allowing you to choose the one best suited for your needs.
@@ -51,7 +51,7 @@ LangChain exposes a standard interface, allowing you to easily swap between vect
 
 Once the data is in the database, you still need to retrieve it.
 LangChain supports many different retrieval algorithms and is one of the places where we add the most value.
-We support basic methods that are easy to get started - namely simple semantic search.
+LangChain supports basic methods that are easy to get started - namely simple semantic search.
 However, we have also added a collection of algorithms on top of this to increase performance.
 These include:
 
@@ -60,3 +60,13 @@ These include:
 - [Ensemble Retriever](/docs/modules/data_connection/retrievers/ensemble): Sometimes you may want to retrieve documents from multiple different sources, or using multiple different algorithms. The ensemble retriever allows you to easily do this.
 - And more!
 
+**[Indexing](/docs/modules/data_connection/indexing)**
+
+The LangChain **Indexing API** syncs your data from any source into a vector store,
+helping you:
+
+- Avoid writing duplicated content into the vector store
+- Avoid re-writing unchanged content
+- Avoid re-computing embeddings over unchanged content
+
+All of which should save you time and money, as well as improve your vector search results.

docs/docs/modules/data_connection/indexing.ipynb

@@ -60,7 +60,7 @@
     "   * document addition by id (`add_documents` method with `ids` argument)\n",
     "   * delete by id (`delete` method with `ids` argument)\n",
     "\n",
-    "Compatible Vectorstores: `AnalyticDB`, `AstraDB`, `AwaDB`, `Bagel`, `Cassandra`, `Chroma`, `DashVector`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `MyScale`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `ScaNN`, `SupabaseVectorStore`, `TimescaleVector`, `Vald`, `Vearch`, `VespaStore`, `Weaviate`, `ZepVectorStore`.\n",
+    "Compatible Vectorstores: `AnalyticDB`, `AstraDB`, `AwaDB`, `Bagel`, `Cassandra`, `Chroma`, `DashVector`, `DatabricksVectorSearch`, `DeepLake`, `Dingo`, `ElasticVectorSearch`, `ElasticsearchStore`, `FAISS`, `MyScale`, `PGVector`, `Pinecone`, `Qdrant`, `Redis`, `ScaNN`, `SupabaseVectorStore`, `TimescaleVector`, `Vald`, `Vearch`, `VespaStore`, `Weaviate`, `ZepVectorStore`.\n",
     "  \n",
     "## Caution\n",
     "\n",

docs/docs/modules/data_connection/retrievers/multi_vector.ipynb

@@ -143,7 +143,7 @@
     {
      "data": {
       "text/plain": [
-       "Document(page_content='Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '10e9cbc0-4ba5-4d79-a09b-c033d1ba7b01', 'source': '../../state_of_the_union.txt'})"
+       "Document(page_content='Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court.', metadata={'doc_id': '455205f7-bb7d-4c36-b442-d1d6f9f701ed', 'source': '../../state_of_the_union.txt'})"
       ]
      },
      "execution_count": 8,
@@ -165,7 +165,7 @@
     {
      "data": {
       "text/plain": [
-       "9874"
+       "9875"
       ]
      },
      "execution_count": 9,
@@ -178,6 +178,39 @@
     "len(retriever.get_relevant_documents(\"justice breyer\")[0].page_content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "cdef8339-f9fa-4b3b-955f-ad9dbdf2734f",
+   "metadata": {},
+   "source": [
+    "The default search type the retriever performs on the vector database is a similarity search. LangChain Vector Stores also support searching via [Max Marginal Relevance](https://api.python.langchain.com/en/latest/schema/langchain.schema.vectorstore.VectorStore.html#langchain.schema.vectorstore.VectorStore.max_marginal_relevance_search) so if you want this instead you can just set the `search_type` property as follows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "36739460-a737-4a8e-b70f-50bf8c8eaae7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "9875"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.retrievers.multi_vector import SearchType\n",
+    "\n",
+    "retriever.search_type = SearchType.mmr\n",
+    "\n",
+    "len(retriever.get_relevant_documents(\"justice breyer\")[0].page_content)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "d6a7ae0d",
@@ -576,7 +609,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.1"
+   "version": "3.9.16"
   }
  },
  "nbformat": 4,

docs/docs/modules/model_io/prompts/prompt_templates/msg_prompt_templates.mdx

@@ -27,6 +27,8 @@ LangChain also provides `MessagesPlaceholder`, which gives you full control of w
 
 ```python
 from langchain.prompts import MessagesPlaceholder
+from langchain.prompts import HumanMessagePromptTemplate
+from langchain.prompts import ChatPromptTemplate
 
 human_prompt = "Summarize our conversation so far in {word_count} words."
 human_message_template = HumanMessagePromptTemplate.from_template(human_prompt)
@@ -36,6 +38,8 @@ chat_prompt = ChatPromptTemplate.from_messages([MessagesPlaceholder(variable_nam
 
 
 ```python
+from langchain.schema.messages import HumanMessage, AIMessage
+
 human_message = HumanMessage(content="What is the best way to learn programming?")
 ai_message = AIMessage(content="""\
 1. Choose a programming language: Decide on a programming language that you want to learn.

docs/docs/use_cases/graph/graph_cypher_qa.ipynb

@@ -48,16 +48,7 @@
    "execution_count": 2,
    "id": "0928915d",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/home/tomaz/neo4j/langchain/libs/langchain/langchain/graphs/neo4j_graph.py:52: ExperimentalWarning: The configuration may change in the future.\n",
-      "  self._driver.verify_connectivity()\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "graph = Neo4jGraph(\n",
     "    url=\"bolt://localhost:7687\", username=\"neo4j\", password=\"pleaseletmein\"\n",
@@ -132,14 +123,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "Node properties are the following:\n",
+      "Movie {name: STRING},Actor {name: STRING}\n",
+      "Relationship properties are the following:\n",
       "\n",
-      "        Node properties are the following:\n",
-      "        [{'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Movie'}, {'properties': [{'property': 'name', 'type': 'STRING'}], 'labels': 'Actor'}]\n",
-      "        Relationship properties are the following:\n",
-      "        []\n",
-      "        The relationships are the following:\n",
-      "        ['(:Actor)-[:ACTED_IN]->(:Movie)']\n",
-      "        \n"
+      "The relationships are the following:\n",
+      "(:Actor)-[:ACTED_IN]->(:Movie)\n"
      ]
     }
    ],
@@ -556,12 +545,12 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Node properties are the following: \n",
-      " {'Actor': [{'property': 'name', 'type': 'STRING'}]}\n",
-      "Relationships properties are the following: \n",
-      " {}\n",
-      "Relationships are: \n",
-      "[]\n"
+      "Node properties are the following:\n",
+      "Actor {name: STRING}\n",
+      "Relationship properties are the following:\n",
+      "\n",
+      "The relationships are the following:\n",
+      "\n"
      ]
     }
    ],
@@ -656,7 +645,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.8"
+   "version": "3.10.13"
   }
  },
  "nbformat": 4,

docs/docs/use_cases/question_answering/code_understanding.ipynb

@@ -28,7 +28,7 @@
     "\n",
     "## Overview\n",
     "\n",
-    "The pipeline for QA over code follows [the steps we do for document question answering](/docs/docs/use_cases/question_answering), with some differences:\n",
+    "The pipeline for QA over code follows [the steps we do for document question answering](/docs/use_cases/question_answering), with some differences:\n",
     "\n",
     "In particular, we can employ a [splitting strategy](https://python.langchain.com/docs/integrations/document_loaders/source_code) that does a few things:\n",
     "\n",

docs/docs/use_cases/question_answering/index.ipynb

@@ -57,11 +57,14 @@
     "1. **Load**: First we need to load our data. We'll use [DocumentLoaders](/docs/modules/data_connection/document_loaders/) for this.\n",
     "2. **Split**: [Text splitters](/docs/modules/data_connection/document_transformers/) break large `Documents` into smaller chunks. This is useful both for indexing data and for passing it in to a model, since large chunks are harder to search over and won't in a model's finite context window.\n",
     "3. **Store**: We need somewhere to store and index our splits, so that they can later be searched over. This is often done using a [VectorStore](/docs/modules/data_connection/vectorstores/) and [Embeddings](/docs/modules/data_connection/text_embedding/) model.\n",
+    "\n",
+    "![index_diagram](/img/rag_indexing.png)\n",
+    "\n",
     "#### Retrieval and generation\n",
     "4. **Retrieve**: Given a user input, relevant splits are retrieved from storage using a [Retriever](/docs/modules/data_connection/retrievers/).\n",
     "5. **Generate**: A [ChatModel](/docs/modules/model_io/chat_models) / [LLM](/docs/modules/model_io/llms/) produces an answer using a prompt that includes the question and the retrieved data\n",
     "\n",
-    "![flow.jpeg](/img/qa_flow.jpeg)"
+    "![retrieval_diagram](/img/rag_retrieval_generation.png)"
    ]
   },
   {
@@ -740,7 +743,7 @@
     "- [Docs](/docs/modules/model_io/llms)\n",
     "- [Integrations](/docs/integrations/llms): Explore over 75 `LLM` integrations.\n",
     "\n",
-    "See a guide on RAG with locally-running models [here](/docs/modules/use_cases/question_answering/local_retrieval_qa)."
+    "See a guide on RAG with locally-running models [here](/docs/use_cases/question_answering/local_retrieval_qa)."
    ]
   },
   {
@@ -1053,10 +1056,10 @@
   },
   {
    "cell_type": "markdown",
-   "id": "e6e5191f-43e6-4fa0-9ba5-db002fcaacf3",
+   "id": "fdf6c7e0-84f8-4747-b2ae-e84315152bd9",
    "metadata": {},
    "source": [
-    "Of course, we've written here the logic for using chat history when it's provided, but we haven't actually added functionality for storing chat history for each user session. This is something that's fairly application specific and is usually best handled outside of LangChain."
+    "Here we've gone over how to add chain logic for incorporating historical outputs. But how do we actually store and retrieve historical outputs for different sessions? For that check out the LCEL [How to add message history (memory)](/docs/expression_language/how_to/message_history) page."
    ]
   },
   {

docs/docs/use_cases/summarization.ipynb

@@ -356,7 +356,7 @@
    "source": [
     "# Reduce\n",
     "reduce_template = \"\"\"The following is set of summaries:\n",
-    "{doc_summaries}\n",
+    "{docs}\n",
     "Take these and distill it into a final, consolidated summary of the main themes. \n",
     "Helpful Answer:\"\"\"\n",
     "reduce_prompt = PromptTemplate.from_template(reduce_template)"

docs/docusaurus.config.js

@@ -166,7 +166,7 @@ const config = {
             label: "Guides",
           },
           {
-            href: "https://api.python.langchain.com",
+            href: "https://api.python.langchain.com/en/stable/api_reference.html",
             label: "API",
             position: "left",
           },
@@ -211,20 +211,19 @@ const config = {
               { label: "Gallery", href: "https://github.com/kyrolabs/awesome-langchain" }
             ]
           },
-          {
-            href: "https://chat.langchain.com",
-            label: "Chat our docs",
-            position: "right",
-          },
           {
             type: "dropdown",
-            label: "Also by LangChain",
+            label: "🦜️🔗",
             position: "right",
             items: [
               {
                 href: "https://smith.langchain.com",
                 label: "LangSmith",
               },
+              {
+                href: "https://docs.smith.langchain.com/",
+                label: "LangSmith Docs",
+              },
               {
                 href: "https://github.com/langchain-ai/langserve",
                 label: "LangServe GitHub",
@@ -243,6 +242,11 @@ const config = {
               },
             ]
           },
+          {
+            href: "https://chat.langchain.com",
+            label: "Chat",
+            position: "right",
+          },
           // Please keep GitHub link to the right for consistency.
           {
             href: "https://github.com/langchain-ai/langchain",

docs/sidebars.js

@@ -110,6 +110,7 @@ module.exports = {
         { type: "category", label: "Memory", collapsed: true, items: [{type: "autogenerated", dirName: "integrations/memory" }], link: {type: "generated-index", slug: "integrations/memory" }},
         { type: "category", label: "Callbacks", collapsed: true, items: [{type: "autogenerated", dirName: "integrations/callbacks" }], link: {type: "generated-index", slug: "integrations/callbacks" }},
         { type: "category", label: "Chat loaders", collapsed: true, items: [{type: "autogenerated", dirName: "integrations/chat_loaders" }], link: {type: "generated-index", slug: "integrations/chat_loaders" }},
+        { type: "category", label: "Adapters", collapsed: true, items: [{type: "autogenerated", dirName: "integrations/adapters" }], link: {type: "generated-index", slug: "integrations/adapters" }},
       ],
       link: {
         type: 'generated-index',