bump 179 (#5200 )

adjust docarray docstrings (#5185 )
Follow up of https://github.com/hwchase17/langchain/pull/5015 Thanks for catching this! Just a small PR to adjust couple of strings to these changes Signed-off-by: jupyterjazz <saba.sturua@jina.ai>
2026-02-04 08:10:25 +00:00 · 2023-05-24 07:55:27 -07:00 · 2023-05-24 07:50:35 -07:00 · 2023-05-24 07:47:15 -07:00 · 2023-05-24 11:41:00 +00:00 · 2023-05-24 01:25:18 -07:00
519 changed files with 21946 additions and 5128 deletions
--- a/.github/actions/poetry_setup/action.yml
+++ b/.github/actions/poetry_setup/action.yml
@@ -33,11 +33,13 @@ runs:
  using: composite
  steps:
    - uses: actions/setup-python@v4
+      name: Setup python $${ inputs.python-version }}
      with:
        python-version: ${{ inputs.python-version }}

    - uses: actions/cache@v3
      id: cache-pip
+      name: Cache Pip ${{ inputs.python-version }}
      env:
        SEGMENT_DOWNLOAD_TIMEOUT_MIN: "15"
      with:
@@ -48,6 +50,16 @@ runs:
    - run: pipx install poetry==${{ inputs.poetry-version }} --python python${{ inputs.python-version }}
      shell: bash

+    - name: Check Poetry File
+      shell: bash
+      run: |
+        poetry check
+
+    - name: Check lock file
+      shell: bash
+      run: |
+        poetry lock --check
+
    - uses: actions/cache@v3
      id: cache-poetry
      env:
--- a/.github/workflows/linkcheck.yml
+++ b/.github/workflows/linkcheck.yml
@@ -4,6 +4,8 @@ on:
  push:
    branches: [master]
  pull_request:
+    paths:
+      - 'docs/**'

 env:
  POETRY_VERSION: "1.4.2"
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -4,6 +4,7 @@ on:
  push:
    branches: [master]
  pull_request:
+  workflow_dispatch:

 env:
  POETRY_VERSION: "1.4.2"
--- a/8
+++ b/8
@@ -35,13 +35,13 @@ lint lint_diff:
 TEST_FILE ?= tests/unit_tests/

 test:
-	poetry run pytest $(TEST_FILE)
+	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)

-tests:
-	poetry run pytest $(TEST_FILE)
+tests: 
+	poetry run pytest --disable-socket --allow-unix-socket $(TEST_FILE)

 extended_tests:
-	poetry run pytest --only-extended tests/unit_tests
+	poetry run pytest --disable-socket --allow-unix-socket --only-extended tests/unit_tests

 test_watch:
 	poetry run ptw --now . -- tests/unit_tests
--- a/docs/_static/css/custom.css
+++ b/docs/_static/css/custom.css
@@ -13,5 +13,5 @@ pre {
 }

 #my-component-root *, #headlessui-portal-root * {
-  z-index: 1000000000000;
+  z-index: 10000;
 }
--- a/docs/_static/js/mendablesearch.js
+++ b/docs/_static/js/mendablesearch.js
@@ -30,10 +30,7 @@ document.addEventListener('DOMContentLoaded', () => {
    const icon = React.createElement('p', {
      style: { color: '#ffffff', fontSize: '22px',width: '48px', height: '48px', margin: '0px', padding: '0px', display: 'flex', alignItems: 'center', justifyContent: 'center', textAlign: 'center' },
    }, [iconSpan1, iconSpan2]);
-
    
-    
-
    const mendableFloatingButton = React.createElement(
      MendableFloatingButton,
      {
@@ -42,6 +39,7 @@ document.addEventListener('DOMContentLoaded', () => {
        anon_key: '82842b36-3ea6-49b2-9fb8-52cfc4bde6bf', // Mendable Search Public ANON key, ok to be public
        messageSettings: {
          openSourcesInNewTab: false,
+          prettySources: true // Prettify the sources displayed now
        },
        icon: icon,
      }
@@ -52,7 +50,7 @@ document.addEventListener('DOMContentLoaded', () => {

  loadScript('https://unpkg.com/react@17/umd/react.production.min.js', () => {
    loadScript('https://unpkg.com/react-dom@17/umd/react-dom.production.min.js', () => {
-      loadScript('https://unpkg.com/@mendable/search@0.0.93/dist/umd/mendable.min.js', initializeMendable);
+      loadScript('https://unpkg.com/@mendable/search@0.0.102/dist/umd/mendable.min.js', initializeMendable);
    });
  });
 });
--- a/docs/additional_resources/model_laboratory.ipynb
+++ b/docs/additional_resources/model_laboratory.ipynb
--- a/docs/additional_resources/tracing.md
+++ b/docs/additional_resources/tracing.md
@@ -6,8 +6,8 @@ First, you should install tracing and set up your environment properly.
 You can use either a locally hosted version of this (uses Docker) or a cloud hosted version (in closed alpha).
 If you're interested in using the hosted platform, please fill out the form [here](https://forms.gle/tRCEMSeopZf6TE3b6).

- [Locally Hosted Setup](./tracing/local_installation.md)
- [Cloud Hosted Setup](./tracing/hosted_installation.md)
+- [Locally Hosted Setup](../tracing/local_installation.md)
+- [Cloud Hosted Setup](../tracing/hosted_installation.md)

 ## Tracing Walkthrough

@@ -17,32 +17,32 @@ A session is just a way to group traces together.
 If you click on a session, it will take you to a page with no recorded traces that says "No Runs."
 You can create a new session with the new session form.

-![](tracing/homepage.png)
+![](../tracing/homepage.png)

 If we click on the `default` session, we can see that to start we have no traces stored.

-![](tracing/default_empty.png)
+![](../tracing/default_empty.png)

 If we now start running chains and agents with tracing enabled, we will see data show up here.
-To do so, we can run [this notebook](tracing/agent_with_tracing.ipynb) as an example.
+To do so, we can run [this notebook](../tracing/agent_with_tracing.ipynb) as an example.
 After running it, we will see an initial trace show up.

-![](tracing/first_trace.png)
+![](../tracing/first_trace.png)

 From here we can explore the trace at a high level by clicking on the arrow to show nested runs.
 We can keep on clicking further and further down to explore deeper and deeper.

-![](tracing/explore.png)
+![](../tracing/explore.png)

 We can also click on the "Explore" button of the top level run to dive even deeper.
 Here, we can see the inputs and outputs in full, as well as all the nested traces.

-![](tracing/explore_trace.png)
+![](../tracing/explore_trace.png)

 We can keep on exploring each of these nested traces in more detail.
 For example, here is the lowest level trace with the exact inputs/outputs to the LLM.

-![](tracing/explore_llm.png)
+![](../tracing/explore_llm.png)

 ## Changing Sessions

--- a/docs/additional_resources/youtube.md
+++ b/docs/additional_resources/youtube.md
@@ -0,0 +1,90 @@
+# YouTube
+
+This is a collection of `LangChain` videos on `YouTube`.
+
+### ⛓️[Official LangChain YouTube channel](https://www.youtube.com/@LangChain)⛓️
+
+### Introduction to LangChain with Harrison Chase, creator of LangChain
+- [Building the Future with LLMs, `LangChain`, & `Pinecone`](https://youtu.be/nMniwlGyX-c) by [Pinecone](https://www.youtube.com/@pinecone-io)
+- [LangChain and Weaviate with Harrison Chase and Bob van Luijt - Weaviate Podcast #36](https://youtu.be/lhby7Ql7hbk) by [Weaviate • Vector Database](https://www.youtube.com/@Weaviate)
+- [LangChain Demo + Q&A with Harrison Chase](https://youtu.be/zaYTXQFR0_s?t=788) by [Full Stack Deep Learning](https://www.youtube.com/@FullStackDeepLearning)
+- [LangChain Agents: Build Personal Assistants For Your Data (Q&A with Harrison Chase and Mayo Oshin)](https://youtu.be/gVkF8cwfBLI) by [Chat with data](https://www.youtube.com/@chatwithdata)
+- ⛓️ [LangChain "Agents in Production" Webinar](https://youtu.be/k8GNCCs16F4) by [LangChain](https://www.youtube.com/@LangChain)
+
+## Videos (sorted by views)
+
+- [Building AI LLM Apps with LangChain (and more?) - LIVE STREAM](https://www.youtube.com/live/M-2Cj_2fzWI?feature=share) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)
+- [First look - `ChatGPT` + `WolframAlpha` (`GPT-3.5` and Wolfram|Alpha via LangChain by James Weaver)](https://youtu.be/wYGbY811oMo) by [Dr Alan D. Thompson](https://www.youtube.com/@DrAlanDThompson) 
+- [LangChain explained - The hottest new Python framework](https://youtu.be/RoR4XJw8wIc) by [AssemblyAI](https://www.youtube.com/@AssemblyAI)
+- [Chatbot with INFINITE MEMORY using `OpenAI` & `Pinecone` - `GPT-3`, `Embeddings`, `ADA`, `Vector DB`, `Semantic`](https://youtu.be/2xNzB7xq8nk) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
+- [LangChain for LLMs is... basically just an Ansible playbook](https://youtu.be/X51N9C-OhlE) by [David Shapiro ~ AI](https://www.youtube.com/@DavidShapiroAutomator)
+- [Build your own LLM Apps with LangChain & `GPT-Index`](https://youtu.be/-75p09zFUJY) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- [`BabyAGI` - New System of Autonomous AI Agents with LangChain](https://youtu.be/lg3kJvf1kXo) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- [Run `BabyAGI` with Langchain Agents (with Python Code)](https://youtu.be/WosPGHPObx8) by [1littlecoder](https://www.youtube.com/@1littlecoder)
+- [How to Use Langchain With `Zapier` | Write and Send Email with GPT-3 | OpenAI API Tutorial](https://youtu.be/p9v2-xEa9A0) by [StarMorph AI](https://www.youtube.com/@starmorph)
+- [Use Your Locally Stored Files To Get Response From GPT - `OpenAI` | Langchain | Python](https://youtu.be/NC1Ni9KS-rk) by [Shweta Lodha](https://www.youtube.com/@shweta-lodha)
+- [`Langchain JS` | How to Use GPT-3, GPT-4 to Reference your own Data | `OpenAI Embeddings` Intro](https://youtu.be/veV2I-NEjaM) by [StarMorph AI](https://www.youtube.com/@starmorph)
+- [The easiest way to work with large language models | Learn LangChain in 10min](https://youtu.be/kmbS6FDQh7c) by [Sophia Yang](https://www.youtube.com/@SophiaYangDS)
+- [4 Autonomous AI Agents: “Westworld” simulation `BabyAGI`, `AutoGPT`, `Camel`, `LangChain`](https://youtu.be/yWbnH6inT_U) by [Sophia Yang](https://www.youtube.com/@SophiaYangDS)
+- [AI CAN SEARCH THE INTERNET? Langchain Agents + OpenAI ChatGPT](https://youtu.be/J-GL0htqda8) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
+- [Query Your Data with GPT-4 | Embeddings, Vector Databases | Langchain JS Knowledgebase](https://youtu.be/jRnUPUTkZmU) by [StarMorph AI](https://www.youtube.com/@starmorph)
+- [`Weaviate` + LangChain for LLM apps presented by Erika Cardenas](https://youtu.be/7AGj4Td5Lgw) by [`Weaviate` • Vector Database](https://www.youtube.com/@Weaviate)
+- [Langchain Overview — How to Use Langchain & `ChatGPT`](https://youtu.be/oYVYIq0lOtI) by [Python In Office](https://www.youtube.com/@pythoninoffice6568)
+- [Langchain Overview - How to Use Langchain & `ChatGPT`](https://youtu.be/oYVYIq0lOtI) by [Python In Office](https://www.youtube.com/@pythoninoffice6568)
+- [Custom langchain Agent & Tools with memory. Turn any `Python function` into langchain tool with Gpt 3](https://youtu.be/NIG8lXk0ULg) by [echohive](https://www.youtube.com/@echohive)
+- [LangChain: Run Language Models Locally - `Hugging Face Models`](https://youtu.be/Xxxuw4_iCzw) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
+- [`ChatGPT` with any `YouTube` video using langchain and `chromadb`](https://youtu.be/TQZfB2bzVwU) by [echohive](https://www.youtube.com/@echohive)
+- [How to Talk to a `PDF` using LangChain and `ChatGPT`](https://youtu.be/v2i1YDtrIwk) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
+- [Langchain Document Loaders Part 1: Unstructured Files](https://youtu.be/O5C0wfsen98) by [Merk](https://www.youtube.com/@merksworld) 
+- [LangChain - Prompt Templates (what all the best prompt engineers use)](https://youtu.be/1aRu8b0XNOQ) by [Nick Daigler](https://www.youtube.com/@nick_daigs)
+- [LangChain. Crear aplicaciones Python impulsadas por GPT](https://youtu.be/DkW_rDndts8) by [Jesús Conde](https://www.youtube.com/@0utKast)
+- [Easiest Way to Use GPT In Your Products | LangChain Basics Tutorial](https://youtu.be/fLy0VenZyGc) by [Rachel Woods](https://www.youtube.com/@therachelwoods)
+- [`BabyAGI` + `GPT-4` Langchain Agent with Internet Access](https://youtu.be/wx1z_hs5P6E) by [tylerwhatsgood](https://www.youtube.com/@tylerwhatsgood)
+- [Learning LLM Agents. How does it actually work? LangChain, AutoGPT & OpenAI](https://youtu.be/mb_YAABSplk) by [Arnoldas Kemeklis](https://www.youtube.com/@processusAI)
+- [Get Started with LangChain in `Node.js`](https://youtu.be/Wxx1KUWJFv4) by [Developers Digest](https://www.youtube.com/@DevelopersDigest)
+- [LangChain + `OpenAI` tutorial: Building a Q&A system w/ own text data](https://youtu.be/DYOU_Z0hAwo) by [Samuel Chan](https://www.youtube.com/@SamuelChan)
+- [Langchain + `Zapier` Agent](https://youtu.be/yribLAb-pxA) by [Merk](https://www.youtube.com/@merksworld)
+- [Connecting the Internet with `ChatGPT` (LLMs) using Langchain And Answers Your Questions](https://youtu.be/9Y0TBC63yZg) by [Kamalraj M M](https://www.youtube.com/@insightbuilder)
+- [Build More Powerful LLM Applications for Business’s with LangChain (Beginners Guide)](https://youtu.be/sp3-WLKEcBg) by[ No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
+- ⛓️ [LangFlow LLM Agent Demo for 🦜🔗LangChain](https://youtu.be/zJxDHaWt-6o) by [Cobus Greyling](https://www.youtube.com/@CobusGreylingZA)
+- ⛓️ [Chatbot Factory: Streamline Python Chatbot Creation with LLMs and Langchain](https://youtu.be/eYer3uzrcuM) by [Finxter](https://www.youtube.com/@CobusGreylingZA)
+- ⛓️ [LangChain Tutorial - ChatGPT mit eigenen Daten](https://youtu.be/0XDLyY90E2c) by [Coding Crashkurse](https://www.youtube.com/@codingcrashkurse6429)
+- ⛓️ [Chat with a `CSV` | LangChain Agents Tutorial (Beginners)](https://youtu.be/tjeti5vXWOU) by [GoDataProf](https://www.youtube.com/@godataprof)
+- ⛓️ [Introdução ao Langchain - #Cortes - Live DataHackers](https://youtu.be/fw8y5VRei5Y) by [Prof. João Gabriel Lima](https://www.youtube.com/@profjoaogabriellima)
+- ⛓️ [LangChain: Level up `ChatGPT` !? | LangChain Tutorial Part 1](https://youtu.be/vxUGx8aZpDE) by [Code Affinity](https://www.youtube.com/@codeaffinitydev)
+- ⛓️ [KI schreibt krasses Youtube Skript 😲😳 | LangChain Tutorial Deutsch](https://youtu.be/QpTiXyK1jus) by [SimpleKI](https://www.youtube.com/@simpleki)
+- ⛓️ [Chat with Audio: Langchain, `Chroma DB`, OpenAI, and `Assembly AI`](https://youtu.be/Kjy7cx1r75g) by [AI Anytime](https://www.youtube.com/@AIAnytime)
+- ⛓️ [QA over documents with Auto vector index selection with Langchain router chains](https://youtu.be/9G05qybShv8) by [echohive](https://www.youtube.com/@echohive)
+- ⛓️ [Build your own custom LLM application with `Bubble.io` & Langchain (No Code & Beginner friendly)](https://youtu.be/O7NhQGu1m6c) by [No Code Blackbox](https://www.youtube.com/@nocodeblackbox)
+- ⛓️ [Simple App to Question Your Docs: Leveraging `Streamlit`, `Hugging Face Spaces`, LangChain, and `Claude`!](https://youtu.be/X4YbNECRr7o) by [Chris Alexiuk](https://www.youtube.com/@chrisalexiuk)
+- ⛓️ [LANGCHAIN AI- `ConstitutionalChainAI` + Databutton AI ASSISTANT Web App](https://youtu.be/5zIU6_rdJCU) by [Avra](https://www.youtube.com/@Avra_b)
+- ⛓️ [LANGCHAIN AI AUTONOMOUS AGENT WEB APP - 👶 `BABY AGI` 🤖 with EMAIL AUTOMATION using `DATABUTTON`](https://youtu.be/cvAwOGfeHgw) by [Avra](https://www.youtube.com/@Avra_b)
+- ⛓️ [The Future of Data Analysis: Using A.I. Models in Data Analysis (LangChain)](https://youtu.be/v_LIcVyg5dk) by [Absent Data](https://www.youtube.com/@absentdata)
+- ⛓️ [Memory in LangChain | Deep dive (python)](https://youtu.be/70lqvTFh_Yg) by [Eden Marco](https://www.youtube.com/@EdenMarco)
+- ⛓️ [9 LangChain UseCases | Beginner's Guide | 2023](https://youtu.be/zS8_qosHNMw) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
+- ⛓️ [Use Large Language Models in Jupyter Notebook | LangChain | Agents & Indexes](https://youtu.be/JSe11L1a_QQ) by [Abhinaw Tiwari](https://www.youtube.com/@AbhinawTiwariAT)
+- ⛓️ [How to Talk to Your Langchain Agent | `11 Labs` + `Whisper`](https://youtu.be/N4k459Zw2PU) by [VRSEN](https://www.youtube.com/@vrsen)
+- ⛓️ [LangChain Deep Dive: 5 FUN AI App Ideas To Build Quickly and Easily](https://youtu.be/mPYEPzLkeks) by [James NoCode](https://www.youtube.com/@jamesnocode)
+- ⛓️ [BEST OPEN Alternative to OPENAI's EMBEDDINGs for Retrieval QA: LangChain](https://youtu.be/ogEalPMUCSY) by [Prompt Engineering](https://www.youtube.com/@engineerprompt)
+- ⛓️ [LangChain 101: Models](https://youtu.be/T6c_XsyaNSQ) by [Mckay Wrigley](https://www.youtube.com/@realmckaywrigley)
+- ⛓️ [LangChain with JavaScript Tutorial #1 | Setup & Using LLMs](https://youtu.be/W3AoeMrg27o) by [Leon van Zyl](https://www.youtube.com/@leonvanzyl)
+- ⛓️ [LangChain Overview & Tutorial for Beginners: Build Powerful AI Apps Quickly & Easily (ZERO CODE)](https://youtu.be/iI84yym473Q) by [James NoCode](https://www.youtube.com/@jamesnocode)
+- ⛓️ [LangChain In Action: Real-World Use Case With Step-by-Step Tutorial](https://youtu.be/UO699Szp82M) by [Rabbitmetrics](https://www.youtube.com/@rabbitmetrics)
+- ⛓️ [Summarizing and Querying Multiple Papers with LangChain](https://youtu.be/p_MQRWH5Y6k) by [Automata Learning Lab](https://www.youtube.com/@automatalearninglab)
+- ⛓️ [Using Langchain (and `Replit`) through `Tana`, ask `Google`/`Wikipedia`/`Wolfram Alpha` to fill out a table](https://youtu.be/Webau9lEzoI) by [Stian Håklev](https://www.youtube.com/@StianHaklev)
+- ⛓️ [Langchain PDF App (GUI) | Create a ChatGPT For Your `PDF` in Python](https://youtu.be/wUAUdEw5oxM) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
+- ⛓️ [Auto-GPT with LangChain 🔥 | Create Your Own Personal AI Assistant](https://youtu.be/imDfPmMKEjM) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
+- ⛓️ [Create Your OWN Slack AI Assistant with Python & LangChain](https://youtu.be/3jFXRNn2Bu8) by [Dave Ebbelaar](https://www.youtube.com/@daveebbelaar)
+- ⛓️ [How to Create LOCAL Chatbots with GPT4All and LangChain [Full Guide]](https://youtu.be/4p1Fojur8Zw) by [Liam Ottley](https://www.youtube.com/@LiamOttley)
+- ⛓️ [Build a `Multilingual PDF` Search App with LangChain, `Cohere` and `Bubble`](https://youtu.be/hOrtuumOrv8) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
+- ⛓️ [Building a LangChain Agent (code-free!) Using `Bubble` and `Flowise`](https://youtu.be/jDJIIVWTZDE) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
+- ⛓️ [Build a LangChain-based Semantic PDF Search App with No-Code Tools Bubble and Flowise](https://youtu.be/s33v5cIeqA4) by [Menlo Park Lab](https://www.youtube.com/@menloparklab)
+- ⛓️ [LangChain Memory Tutorial | Building a ChatGPT Clone in Python](https://youtu.be/Cwq91cj2Pnc) by [Alejandro AO - Software & Ai](https://www.youtube.com/@alejandro_ao)
+- ⛓️ [ChatGPT For Your DATA | Chat with Multiple Documents Using LangChain](https://youtu.be/TeDgIDqQmzs) by [Data Science Basics](https://www.youtube.com/@datasciencebasics)
+- ⛓️ [`Llama Index`: Chat with Documentation using URL Loader](https://youtu.be/XJRoDEctAwA) by [Merk](https://www.youtube.com/@merksworld)
+- ⛓️ [Using OpenAI, LangChain, and `Gradio` to Build Custom GenAI Applications](https://youtu.be/1MsmqMg3yUc) by [David Hundley](https://www.youtube.com/@dkhundley)
+
+
+
+---------------------
+⛓ icon marks a new video [last update 2023-05-15]
--- a/docs/dependents.md
+++ b/docs/dependents.md
@@ -0,0 +1,192 @@
+# Dependents
+
+Dependents stats for `hwchase17/langchain`
+
+[![](https://img.shields.io/static/v1?label=Used%20by&message=5152&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(public)&message=172&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(private)&message=4980&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+[![](https://img.shields.io/static/v1?label=Used%20by%20(stars)&message=17239&color=informational&logo=slickpic)](https://github.com/hwchase17/langchain/network/dependents)
+
+[update: 2023-05-17; only dependent repositories with Stars > 100]
+
+
+| Repository | Stars  |
+| :--------  | -----: |
+|[openai/openai-cookbook](https://github.com/openai/openai-cookbook) | 35401 |
+|[LAION-AI/Open-Assistant](https://github.com/LAION-AI/Open-Assistant) | 32861 |
+|[microsoft/TaskMatrix](https://github.com/microsoft/TaskMatrix) | 32766 |
+|[hpcaitech/ColossalAI](https://github.com/hpcaitech/ColossalAI) | 29560 |
+|[reworkd/AgentGPT](https://github.com/reworkd/AgentGPT) | 22315 |
+|[imartinez/privateGPT](https://github.com/imartinez/privateGPT) | 17474 |
+|[openai/chatgpt-retrieval-plugin](https://github.com/openai/chatgpt-retrieval-plugin) | 16923 |
+|[mindsdb/mindsdb](https://github.com/mindsdb/mindsdb) | 16112 |
+|[jerryjliu/llama_index](https://github.com/jerryjliu/llama_index) | 15407 |
+|[mlflow/mlflow](https://github.com/mlflow/mlflow) | 14345 |
+|[GaiZhenbiao/ChuanhuChatGPT](https://github.com/GaiZhenbiao/ChuanhuChatGPT) | 10372 |
+|[databrickslabs/dolly](https://github.com/databrickslabs/dolly) | 9919 |
+|[AIGC-Audio/AudioGPT](https://github.com/AIGC-Audio/AudioGPT) | 8177 |
+|[logspace-ai/langflow](https://github.com/logspace-ai/langflow) | 6807 |
+|[imClumsyPanda/langchain-ChatGLM](https://github.com/imClumsyPanda/langchain-ChatGLM) | 6087 |
+|[arc53/DocsGPT](https://github.com/arc53/DocsGPT) | 5292 |
+|[e2b-dev/e2b](https://github.com/e2b-dev/e2b) | 4622 |
+|[nsarrazin/serge](https://github.com/nsarrazin/serge) | 4076 |
+|[madawei2699/myGPTReader](https://github.com/madawei2699/myGPTReader) | 3952 |
+|[zauberzeug/nicegui](https://github.com/zauberzeug/nicegui) | 3952 |
+|[go-skynet/LocalAI](https://github.com/go-skynet/LocalAI) | 3762 |
+|[GreyDGL/PentestGPT](https://github.com/GreyDGL/PentestGPT) | 3388 |
+|[mmabrouk/chatgpt-wrapper](https://github.com/mmabrouk/chatgpt-wrapper) | 3243 |
+|[zilliztech/GPTCache](https://github.com/zilliztech/GPTCache) | 3189 |
+|[wenda-LLM/wenda](https://github.com/wenda-LLM/wenda) | 3050 |
+|[marqo-ai/marqo](https://github.com/marqo-ai/marqo) | 2930 |
+|[gkamradt/langchain-tutorials](https://github.com/gkamradt/langchain-tutorials) | 2710 |
+|[PrefectHQ/marvin](https://github.com/PrefectHQ/marvin) | 2545 |
+|[project-baize/baize-chatbot](https://github.com/project-baize/baize-chatbot) | 2479 |
+|[whitead/paper-qa](https://github.com/whitead/paper-qa) | 2399 |
+|[langgenius/dify](https://github.com/langgenius/dify) | 2344 |
+|[GerevAI/gerev](https://github.com/GerevAI/gerev) | 2283 |
+|[hwchase17/chat-langchain](https://github.com/hwchase17/chat-langchain) | 2266 |
+|[guangzhengli/ChatFiles](https://github.com/guangzhengli/ChatFiles) | 1903 |
+|[Azure-Samples/azure-search-openai-demo](https://github.com/Azure-Samples/azure-search-openai-demo) | 1884 |
+|[OpenBMB/BMTools](https://github.com/OpenBMB/BMTools) | 1860 |
+|[Farama-Foundation/PettingZoo](https://github.com/Farama-Foundation/PettingZoo) | 1813 |
+|[OpenGVLab/Ask-Anything](https://github.com/OpenGVLab/Ask-Anything) | 1571 |
+|[IntelligenzaArtificiale/Free-Auto-GPT](https://github.com/IntelligenzaArtificiale/Free-Auto-GPT) | 1480 |
+|[hwchase17/notion-qa](https://github.com/hwchase17/notion-qa) | 1464 |
+|[NVIDIA/NeMo-Guardrails](https://github.com/NVIDIA/NeMo-Guardrails) | 1419 |
+|[Unstructured-IO/unstructured](https://github.com/Unstructured-IO/unstructured) | 1410 |
+|[Kav-K/GPTDiscord](https://github.com/Kav-K/GPTDiscord) | 1363 |
+|[paulpierre/RasaGPT](https://github.com/paulpierre/RasaGPT) | 1344 |
+|[StanGirard/quivr](https://github.com/StanGirard/quivr) | 1330 |
+|[lunasec-io/lunasec](https://github.com/lunasec-io/lunasec) | 1318 |
+|[vocodedev/vocode-python](https://github.com/vocodedev/vocode-python) | 1286 |
+|[agiresearch/OpenAGI](https://github.com/agiresearch/OpenAGI) | 1156 |
+|[h2oai/h2ogpt](https://github.com/h2oai/h2ogpt) | 1141 |
+|[jina-ai/thinkgpt](https://github.com/jina-ai/thinkgpt) | 1106 |
+|[yanqiangmiffy/Chinese-LangChain](https://github.com/yanqiangmiffy/Chinese-LangChain) | 1072 |
+|[ttengwang/Caption-Anything](https://github.com/ttengwang/Caption-Anything) | 1064 |
+|[jina-ai/dev-gpt](https://github.com/jina-ai/dev-gpt) | 1057 |
+|[juncongmoo/chatllama](https://github.com/juncongmoo/chatllama) | 1003 |
+|[greshake/llm-security](https://github.com/greshake/llm-security) | 1002 |
+|[visual-openllm/visual-openllm](https://github.com/visual-openllm/visual-openllm) | 957 |
+|[richardyc/Chrome-GPT](https://github.com/richardyc/Chrome-GPT) | 918 |
+|[irgolic/AutoPR](https://github.com/irgolic/AutoPR) | 886 |
+|[mmz-001/knowledge_gpt](https://github.com/mmz-001/knowledge_gpt) | 867 |
+|[thomas-yanxin/LangChain-ChatGLM-Webui](https://github.com/thomas-yanxin/LangChain-ChatGLM-Webui) | 850 |
+|[microsoft/X-Decoder](https://github.com/microsoft/X-Decoder) | 837 |
+|[peterw/Chat-with-Github-Repo](https://github.com/peterw/Chat-with-Github-Repo) | 826 |
+|[cirediatpl/FigmaChain](https://github.com/cirediatpl/FigmaChain) | 782 |
+|[hashintel/hash](https://github.com/hashintel/hash) | 778 |
+|[seanpixel/Teenage-AGI](https://github.com/seanpixel/Teenage-AGI) | 773 |
+|[jina-ai/langchain-serve](https://github.com/jina-ai/langchain-serve) | 738 |
+|[corca-ai/EVAL](https://github.com/corca-ai/EVAL) | 737 |
+|[ai-sidekick/sidekick](https://github.com/ai-sidekick/sidekick) | 717 |
+|[rlancemartin/auto-evaluator](https://github.com/rlancemartin/auto-evaluator) | 703 |
+|[poe-platform/api-bot-tutorial](https://github.com/poe-platform/api-bot-tutorial) | 689 |
+|[SamurAIGPT/Camel-AutoGPT](https://github.com/SamurAIGPT/Camel-AutoGPT) | 666 |
+|[eyurtsev/kor](https://github.com/eyurtsev/kor) | 608 |
+|[run-llama/llama-lab](https://github.com/run-llama/llama-lab) | 559 |
+|[namuan/dr-doc-search](https://github.com/namuan/dr-doc-search) | 544 |
+|[pieroit/cheshire-cat](https://github.com/pieroit/cheshire-cat) | 520 |
+|[griptape-ai/griptape](https://github.com/griptape-ai/griptape) | 514 |
+|[getmetal/motorhead](https://github.com/getmetal/motorhead) | 481 |
+|[hwchase17/chat-your-data](https://github.com/hwchase17/chat-your-data) | 462 |
+|[langchain-ai/langchain-aiplugin](https://github.com/langchain-ai/langchain-aiplugin) | 452 |
+|[jina-ai/agentchain](https://github.com/jina-ai/agentchain) | 439 |
+|[SamurAIGPT/ChatGPT-Developer-Plugins](https://github.com/SamurAIGPT/ChatGPT-Developer-Plugins) | 437 |
+|[alexanderatallah/window.ai](https://github.com/alexanderatallah/window.ai) | 433 |
+|[michaelthwan/searchGPT](https://github.com/michaelthwan/searchGPT) | 427 |
+|[mpaepper/content-chatbot](https://github.com/mpaepper/content-chatbot) | 425 |
+|[mckaywrigley/repo-chat](https://github.com/mckaywrigley/repo-chat) | 422 |
+|[whyiyhw/chatgpt-wechat](https://github.com/whyiyhw/chatgpt-wechat) | 421 |
+|[freddyaboulton/gradio-tools](https://github.com/freddyaboulton/gradio-tools) | 407 |
+|[jonra1993/fastapi-alembic-sqlmodel-async](https://github.com/jonra1993/fastapi-alembic-sqlmodel-async) | 395 |
+|[yeagerai/yeagerai-agent](https://github.com/yeagerai/yeagerai-agent) | 383 |
+|[akshata29/chatpdf](https://github.com/akshata29/chatpdf) | 374 |
+|[OpenGVLab/InternGPT](https://github.com/OpenGVLab/InternGPT) | 368 |
+|[ruoccofabrizio/azure-open-ai-embeddings-qna](https://github.com/ruoccofabrizio/azure-open-ai-embeddings-qna) | 358 |
+|[101dotxyz/GPTeam](https://github.com/101dotxyz/GPTeam) | 357 |
+|[mtenenholtz/chat-twitter](https://github.com/mtenenholtz/chat-twitter) | 354 |
+|[amosjyng/langchain-visualizer](https://github.com/amosjyng/langchain-visualizer) | 343 |
+|[msoedov/langcorn](https://github.com/msoedov/langcorn) | 334 |
+|[showlab/VLog](https://github.com/showlab/VLog) | 330 |
+|[continuum-llms/chatgpt-memory](https://github.com/continuum-llms/chatgpt-memory) | 324 |
+|[steamship-core/steamship-langchain](https://github.com/steamship-core/steamship-langchain) | 323 |
+|[daodao97/chatdoc](https://github.com/daodao97/chatdoc) | 320 |
+|[xuwenhao/geektime-ai-course](https://github.com/xuwenhao/geektime-ai-course) | 308 |
+|[StevenGrove/GPT4Tools](https://github.com/StevenGrove/GPT4Tools) | 301 |
+|[logan-markewich/llama_index_starter_pack](https://github.com/logan-markewich/llama_index_starter_pack) | 300 |
+|[andylokandy/gpt-4-search](https://github.com/andylokandy/gpt-4-search) | 299 |
+|[Anil-matcha/ChatPDF](https://github.com/Anil-matcha/ChatPDF) | 287 |
+|[itamargol/openai](https://github.com/itamargol/openai) | 273 |
+|[BlackHC/llm-strategy](https://github.com/BlackHC/llm-strategy) | 267 |
+|[momegas/megabots](https://github.com/momegas/megabots) | 259 |
+|[bborn/howdoi.ai](https://github.com/bborn/howdoi.ai) | 238 |
+|[Cheems-Seminar/grounded-segment-any-parts](https://github.com/Cheems-Seminar/grounded-segment-any-parts) | 232 |
+|[ur-whitelab/exmol](https://github.com/ur-whitelab/exmol) | 227 |
+|[sullivan-sean/chat-langchainjs](https://github.com/sullivan-sean/chat-langchainjs) | 227 |
+|[explosion/spacy-llm](https://github.com/explosion/spacy-llm) | 226 |
+|[recalign/RecAlign](https://github.com/recalign/RecAlign) | 218 |
+|[jupyterlab/jupyter-ai](https://github.com/jupyterlab/jupyter-ai) | 218 |
+|[alvarosevilla95/autolang](https://github.com/alvarosevilla95/autolang) | 215 |
+|[conceptofmind/toolformer](https://github.com/conceptofmind/toolformer) | 213 |
+|[MagnivOrg/prompt-layer-library](https://github.com/MagnivOrg/prompt-layer-library) | 209 |
+|[JohnSnowLabs/nlptest](https://github.com/JohnSnowLabs/nlptest) | 208 |
+|[airobotlab/KoChatGPT](https://github.com/airobotlab/KoChatGPT) | 197 |
+|[langchain-ai/auto-evaluator](https://github.com/langchain-ai/auto-evaluator) | 195 |
+|[yvann-hub/Robby-chatbot](https://github.com/yvann-hub/Robby-chatbot) | 195 |
+|[alejandro-ao/langchain-ask-pdf](https://github.com/alejandro-ao/langchain-ask-pdf) | 192 |
+|[daveebbelaar/langchain-experiments](https://github.com/daveebbelaar/langchain-experiments) | 189 |
+|[NimbleBoxAI/ChainFury](https://github.com/NimbleBoxAI/ChainFury) | 187 |
+|[kaleido-lab/dolphin](https://github.com/kaleido-lab/dolphin) | 184 |
+|[Anil-matcha/Website-to-Chatbot](https://github.com/Anil-matcha/Website-to-Chatbot) | 183 |
+|[plchld/InsightFlow](https://github.com/plchld/InsightFlow) | 180 |
+|[OpenBMB/AgentVerse](https://github.com/OpenBMB/AgentVerse) | 166 |
+|[benthecoder/ClassGPT](https://github.com/benthecoder/ClassGPT) | 166 |
+|[jbrukh/gpt-jargon](https://github.com/jbrukh/gpt-jargon) | 161 |
+|[hardbyte/qabot](https://github.com/hardbyte/qabot) | 160 |
+|[shaman-ai/agent-actors](https://github.com/shaman-ai/agent-actors) | 153 |
+|[radi-cho/datasetGPT](https://github.com/radi-cho/datasetGPT) | 153 |
+|[poe-platform/poe-protocol](https://github.com/poe-platform/poe-protocol) | 152 |
+|[paolorechia/learn-langchain](https://github.com/paolorechia/learn-langchain) | 149 |
+|[ajndkr/lanarky](https://github.com/ajndkr/lanarky) | 149 |
+|[fengyuli-dev/multimedia-gpt](https://github.com/fengyuli-dev/multimedia-gpt) | 147 |
+|[yasyf/compress-gpt](https://github.com/yasyf/compress-gpt) | 144 |
+|[homanp/superagent](https://github.com/homanp/superagent) | 143 |
+|[realminchoi/babyagi-ui](https://github.com/realminchoi/babyagi-ui) | 141 |
+|[ethanyanjiali/minChatGPT](https://github.com/ethanyanjiali/minChatGPT) | 141 |
+|[ccurme/yolopandas](https://github.com/ccurme/yolopandas) | 139 |
+|[hwchase17/langchain-streamlit-template](https://github.com/hwchase17/langchain-streamlit-template) | 138 |
+|[Jaseci-Labs/jaseci](https://github.com/Jaseci-Labs/jaseci) | 136 |
+|[hirokidaichi/wanna](https://github.com/hirokidaichi/wanna) | 135 |
+|[Haste171/langchain-chatbot](https://github.com/Haste171/langchain-chatbot) | 134 |
+|[jmpaz/promptlib](https://github.com/jmpaz/promptlib) | 130 |
+|[Klingefjord/chatgpt-telegram](https://github.com/Klingefjord/chatgpt-telegram) | 130 |
+|[filip-michalsky/SalesGPT](https://github.com/filip-michalsky/SalesGPT) | 128 |
+|[handrew/browserpilot](https://github.com/handrew/browserpilot) | 128 |
+|[shauryr/S2QA](https://github.com/shauryr/S2QA) | 127 |
+|[steamship-core/vercel-examples](https://github.com/steamship-core/vercel-examples) | 127 |
+|[yasyf/summ](https://github.com/yasyf/summ) | 127 |
+|[gia-guar/JARVIS-ChatGPT](https://github.com/gia-guar/JARVIS-ChatGPT) | 126 |
+|[jerlendds/osintbuddy](https://github.com/jerlendds/osintbuddy) | 125 |
+|[ibiscp/LLM-IMDB](https://github.com/ibiscp/LLM-IMDB) | 124 |
+|[Teahouse-Studios/akari-bot](https://github.com/Teahouse-Studios/akari-bot) | 124 |
+|[hwchase17/chroma-langchain](https://github.com/hwchase17/chroma-langchain) | 124 |
+|[menloparklab/langchain-cohere-qdrant-doc-retrieval](https://github.com/menloparklab/langchain-cohere-qdrant-doc-retrieval) | 123 |
+|[peterw/StoryStorm](https://github.com/peterw/StoryStorm) | 123 |
+|[chakkaradeep/pyCodeAGI](https://github.com/chakkaradeep/pyCodeAGI) | 123 |
+|[petehunt/langchain-github-bot](https://github.com/petehunt/langchain-github-bot) | 115 |
+|[su77ungr/CASALIOY](https://github.com/su77ungr/CASALIOY) | 113 |
+|[eunomia-bpf/GPTtrace](https://github.com/eunomia-bpf/GPTtrace) | 113 |
+|[zenml-io/zenml-projects](https://github.com/zenml-io/zenml-projects) | 112 |
+|[pablomarin/GPT-Azure-Search-Engine](https://github.com/pablomarin/GPT-Azure-Search-Engine) | 111 |
+|[shamspias/customizable-gpt-chatbot](https://github.com/shamspias/customizable-gpt-chatbot) | 109 |
+|[WongSaang/chatgpt-ui-server](https://github.com/WongSaang/chatgpt-ui-server) | 108 |
+|[davila7/file-gpt](https://github.com/davila7/file-gpt) | 104 |
+|[enhancedocs/enhancedocs](https://github.com/enhancedocs/enhancedocs) | 102 |
+|[aurelio-labs/arxiv-bot](https://github.com/aurelio-labs/arxiv-bot) | 101 |
+
+
+
+_Generated by [github-dependents-info](https://github.com/nvuillam/github-dependents-info)_
+
+[github-dependents-info --repo hwchase17/langchain --markdownfile dependents.md --minstars 100 --sort stars]
--- a/docs/ecosystem/deployments.md
+++ b/docs/ecosystem/deployments.md
@@ -29,6 +29,10 @@ It implements a Question Answering app and contains instructions for deploying t

 A minimal example on how to run LangChain on Vercel using Flask.

+## [FastAPI + Vercel](https://github.com/msoedov/langcorn)
+
+A minimal example on how to run LangChain on Vercel using FastAPI and LangCorn/Uvicorn.
+
 ## [Kinsta](https://github.com/kinsta/hello-world-langchain)

 A minimal example on how to deploy LangChain to [Kinsta](https://kinsta.com) using Flask.
--- a/docs/gallery.rst
+++ b/docs/gallery.rst
@@ -1,365 +0,0 @@
-LangChain Gallery
-=================
-
-Lots of people have built some pretty awesome stuff with LangChain.
-This is a collection of our favorites.
-If you see any other demos that you think we should highlight, be sure to let us know!
-
-
-Open Source
-----------
-
-.. panels::
-    :body: text-center
-
-    ---
-
-    .. link-button:: https://github.com/bborn/howdoi.ai
-        :type: url
-        :text: HowDoI.ai
-        :classes: stretched-link btn-lg
-
-    +++
-
-    This is an experiment in building a large-language-model-backed chatbot. It can hold a conversation, remember previous comments/questions, 
-    and answer all types of queries (history, web search, movie data, weather, news, and more).
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1sKSTjt9cPstl_WMZ86JsgEqFG-aSAwkn?usp=sharing
-        :type: url
-        :text: YouTube Transcription QA with Sources
-        :classes: stretched-link btn-lg
-
-    +++
-
-    An end-to-end example of doing question answering on YouTube transcripts, returning the timestamps as sources to legitimize the answer.
-
-    ---
-
-    .. link-button:: https://github.com/normandmickey/MrsStax
-        :type: url
-        :text: QA Slack Bot
-        :classes: stretched-link btn-lg
-
-    +++
-
-    This application is a Slack Bot that uses Langchain and OpenAI's GPT3 language model to provide domain specific answers. You provide the documents.
-
-    ---
-
-    .. link-button:: https://github.com/OpenBioLink/ThoughtSource
-        :type: url
-        :text: ThoughtSource
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A central, open resource and community around data and tools related to chain-of-thought reasoning in large language models.
-
-    ---
-
-    .. link-button:: https://github.com/blackhc/llm-strategy
-        :type: url
-        :text: LLM Strategy
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    This Python package adds a decorator llm_strategy that connects to an LLM (such as OpenAI’s GPT-3) and uses the LLM to "implement" abstract methods in interface classes. It does this by forwarding requests to the LLM and converting the responses back to Python data using Python's @dataclasses.
-
-    ---
-
-    .. link-button:: https://github.com/JohnNay/llm-lobbyist
-        :type: url
-        :text: Zero-Shot Corporate Lobbyist
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A notebook showing how to use GPT to help with the work of a corporate lobbyist.
-
-    ---
-
-    .. link-button:: https://dagster.io/blog/chatgpt-langchain
-        :type: url
-        :text: Dagster Documentation ChatBot
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A jupyter notebook demonstrating how you could create a semantic search engine on documents in one of your Google Folders
-
-    ---
-
-    .. link-button:: https://github.com/venuv/langchain_semantic_search
-        :type: url
-        :text: Google Folder Semantic Search
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Build a GitHub support bot with GPT3, LangChain, and Python.
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/team7/talk_with_wind
-        :type: url
-        :text: Talk With Wind
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Record sounds of anything (birds, wind, fire, train station) and chat with it.
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/JavaFXpert/Chat-GPT-LangChain
-        :type: url
-        :text: ChatGPT LangChain
-        :classes: stretched-link btn-lg
-
-    +++
-
-    This simple application demonstrates a conversational agent implemented with OpenAI GPT-3.5 and LangChain. When necessary, it leverages tools for complex math, searching the internet, and accessing news and weather.
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/JavaFXpert/gpt-math-techniques
-        :type: url
-        :text: GPT Math Techniques
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A Hugging Face spaces project showing off the benefits of using PAL for math problems.
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1xt2IsFPGYMEQdoJFNgWNAjWGxa60VXdV
-        :type: url
-        :text: GPT Political Compass
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Measure the political compass of GPT.
-
-    ---
-
-    .. link-button:: https://github.com/hwchase17/notion-qa
-        :type: url
-        :text: Notion Database Question-Answering Bot
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Open source GitHub project shows how to use LangChain to create a chatbot that can answer questions about an arbitrary Notion database.
-
-    ---
-
-    .. link-button:: https://github.com/jerryjliu/llama_index
-        :type: url
-        :text: LlamaIndex
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    LlamaIndex (formerly GPT Index) is a project consisting of a set of data structures that are created using GPT-3 and can be traversed using GPT-3 in order to answer queries.
-
-    ---
-
-    .. link-button:: https://github.com/JavaFXpert/llm-grovers-search-party
-        :type: url
-        :text: Grover's Algorithm
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Leveraging Qiskit, OpenAI and LangChain to demonstrate Grover's algorithm
-
-    ---
-
-    .. link-button:: https://huggingface.co/spaces/rituthombre/QNim
-        :type: url
-        :text: QNimGPT
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A chat UI to play Nim, where a player can select an opponent, either a quantum computer or an AI
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/19WTIWC3prw5LDMHmRMvqNV2loD9FHls6?usp=sharing
-        :type: url
-        :text: ReAct TextWorld
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Leveraging the ReActTextWorldAgent to play TextWorld with an LLM!
-
-    ---
-
-    .. link-button:: https://github.com/jagilley/fact-checker
-        :type: url
-        :text: Fact Checker
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    This repo is a simple demonstration of using LangChain to do fact-checking with prompt chaining.
-    
-    ---
-
-    .. link-button:: https://github.com/arc53/docsgpt
-        :type: url
-        :text: DocsGPT
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Answer questions about the documentation of any project
-    
-    ---
-
-    .. link-button:: https://github.com/akshata29/chatpdf
-        :type: url
-        :text: Chat & Ask your data
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    This sample demonstrates a few approaches for creating ChatGPT-like experiences over your own data. It uses OpenAI / Azure OpenAI Service to access the ChatGPT model (gpt-35-turbo and gpt3), and vector store (Pinecone, Redis and others) or Azure cognitive search for data indexing and retrieval.
-
-Misc. Colab Notebooks
-~~~~~~~~~~~~~~~~~~~~~
-
-.. panels::
-    :body: text-center
-
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1AAyEdTz-Z6ShKvewbt1ZHUICqak0MiwR?usp=sharing
-        :type: url
-        :text: Wolfram Alpha in Conversational Agent
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Give ChatGPT a WolframAlpha neural implant
-    
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1UsCLcPy8q5PMNQ5ytgrAAAHa124dzLJg?usp=sharing
-        :type: url
-        :text: Tool Updates in Agents
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Agent improvements (6th Jan 2023)
-    
-    ---
-
-    .. link-button:: https://colab.research.google.com/drive/1UsCLcPy8q5PMNQ5ytgrAAAHa124dzLJg?usp=sharing
-        :type: url
-        :text: Conversational Agent with Tools (Langchain AGI)
-        :classes: stretched-link btn-lg
-    
-    +++
-
-    Langchain AGI (23rd Dec 2022)    
-
-Proprietary
-----------
-
-.. panels::
-    :body: text-center
-
-    ---
-
-    .. link-button:: https://twitter.com/sjwhitmore/status/1580593217153531908?s=20&t=neQvtZZTlp623U3LZwz3bQ
-        :type: url
-        :text: Daimon
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A chat-based AI personal assistant with long-term memory about you.
-
-    ---
-
-    .. link-button:: https://anysummary.app
-        :type: url
-        :text: Summarize any file with AI
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Summarize not only long docs, interview audio or video files quickly, but also entire websites and YouTube videos. Share or download your generated summaries to collaborate with others, or revisit them at any time! Bonus: `@anysummary <https://twitter.com/anysummary>`_ on Twitter will also summarize any thread it is tagged in.
-    
-    ---
-
-    .. link-button:: https://twitter.com/dory111111/status/1608406234646052870?s=20&t=XYlrbKM0ornJsrtGa0br-g
-        :type: url
-        :text: AI Assisted SQL Query Generator
-        :classes: stretched-link btn-lg
-
-    +++
-
-    An app to write SQL using natural language, and execute against real DB.
-
-    ---
-
-    .. link-button:: https://twitter.com/krrish_dh/status/1581028925618106368?s=20&t=neQvtZZTlp623U3LZwz3bQ
-        :type: url
-        :text: Clerkie
-        :classes: stretched-link btn-lg
-
-    +++
-
-    Stack Tracing QA Bot to help debug complex stack tracing (especially the ones that go multi-function/file deep).
-
-    ---
-
-    .. link-button:: https://twitter.com/Raza_Habib496/status/1596880140490838017?s=20&t=6MqEQYWfSqmJwsKahjCVOA
-        :type: url
-        :text: Sales Email Writer
-        :classes: stretched-link btn-lg
-
-    +++
-
-    By Raza Habib, this demo utilizes LangChain + SerpAPI + HumanLoop to write sales emails. Give it a company name and a person, this application will use Google Search (via SerpAPI) to get more information on the company and the person, and then write them a sales message.
-
-    ---
-
-    .. link-button:: https://twitter.com/chillzaza_/status/1592961099384905730?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ
-        :type: url
-        :text: Question-Answering on a Web Browser
-        :classes: stretched-link btn-lg
-
-    +++
-
-    By Zahid Khawaja, this demo utilizes question answering to answer questions about a given website. A followup added this for `YouTube videos <https://twitter.com/chillzaza_/status/1593739682013220865?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ>`_, and then another followup added it for `Wikipedia <https://twitter.com/chillzaza_/status/1594847151238037505?s=20&t=EhU8jl0KyCPJ7vE9Rnz-cQ>`_.
-
-    ---
-
-    .. link-button:: https://mynd.so
-        :type: url
-        :text: Mynd
-        :classes: stretched-link btn-lg
-
-    +++
-
-    A journaling app for self-care that uses AI to uncover insights and patterns over time.
-
-
-Articles on **Google Scholar**
-----------------------------
-
-LangChain is used in many scientific and research projects.
-
-**Google Scholar** presents a `list of the papers <https://scholar.google.com/scholar?q=%22langchain%22&hl=en&as_sdt=0,5&as_vis=1>`_
-with references to LangChain.
--- a/docs/getting_started/concepts.md
+++ b/docs/getting_started/concepts.md
@@ -1,54 +1,44 @@
-# Glossary
+# Concepts

-This is a collection of terminology commonly used when developing LLM applications.
+These are concepts and terminology commonly used when developing LLM applications.
 It contains reference to external papers or sources where the concept was first introduced,
 as well as to places in LangChain where the concept is used.

-## Chain of Thought Prompting
+## Chain of Thought

-A prompting technique used to encourage the model to generate a series of intermediate reasoning steps.
+`Chain of Thought (CoT)` is a prompting technique used to encourage the model to generate a series of intermediate reasoning steps.
 A less formal way to induce this behavior is to include “Let’s think step-by-step” in the prompt.

-Resources:
-
 - [Chain-of-Thought Paper](https://arxiv.org/pdf/2201.11903.pdf)
 - [Step-by-Step Paper](https://arxiv.org/abs/2112.00114)

 ## Action Plan Generation

-A prompt usage that uses a language model to generate actions to take.
+`Action Plan Generation` is a prompting technique that uses a language model to generate actions to take.
 The results of these actions can then be fed back into the language model to generate a subsequent action.

-Resources:
-
 - [WebGPT Paper](https://arxiv.org/pdf/2112.09332.pdf)
 - [SayCan Paper](https://say-can.github.io/assets/palm_saycan.pdf)

-## ReAct Prompting
+## ReAct

-A prompting technique that combines Chain-of-Thought prompting with action plan generation.
+`ReAct` is a prompting technique that combines Chain-of-Thought prompting with action plan generation.
 This induces the to model to think about what action to take, then take it.

-Resources:
-
 - [Paper](https://arxiv.org/pdf/2210.03629.pdf)
- [LangChain Example](modules/agents/agents/examples/react.ipynb)
+- [LangChain Example](../modules/agents/agents/examples/react.ipynb)

 ## Self-ask

-A prompting method that builds on top of chain-of-thought prompting.
+`Self-ask` is a prompting method that builds on top of chain-of-thought prompting.
 In this method, the model explicitly asks itself follow-up questions, which are then answered by an external search engine.

-Resources:
-
 - [Paper](https://ofir.io/self-ask.pdf)
- [LangChain Example](modules/agents/agents/examples/self_ask_with_search.ipynb)
+- [LangChain Example](../modules/agents/agents/examples/self_ask_with_search.ipynb)

 ## Prompt Chaining

-Combining multiple LLM calls together, with the output of one-step being the input to the next.
-
-Resources:
+`Prompt Chaining` is combining multiple LLM calls, with the output of one-step being the input to the next.

 - [PromptChainer Paper](https://arxiv.org/pdf/2203.06566.pdf)
 - [Language Model Cascades](https://arxiv.org/abs/2207.10342)
@@ -57,34 +47,29 @@ Resources:

 ## Memetic Proxy

-Encouraging the LLM to respond in a certain way framing the discussion in a context that the model knows of and that will result in that type of response. For example, as a conversation between a student and a teacher.
-
-Resources:
+`Memetic Proxy` is encouraging the LLM
+to respond in a certain way framing the discussion in a context that the model knows of and that 
+will result in that type of response.
+For example, as a conversation between a student and a teacher.

 - [Paper](https://arxiv.org/pdf/2102.07350.pdf)

 ## Self Consistency

-A decoding strategy that samples a diverse set of reasoning paths and then selects the most consistent answer.
+`Self Consistency` is a decoding strategy that samples a diverse set of reasoning paths and then selects the most consistent answer.
 Is most effective when combined with Chain-of-thought prompting.

-Resources:
-
 - [Paper](https://arxiv.org/pdf/2203.11171.pdf)

 ## Inception

-Also called “First Person Instruction”.
-Encouraging the model to think a certain way by including the start of the model’s response in the prompt.
-
-Resources:
+`Inception` is also called `First Person Instruction`.
+It is encouraging the model to think a certain way by including the start of the model’s response in the prompt.

 - [Example](https://twitter.com/goodside/status/1583262455207460865?s=20&t=8Hz7XBnK1OF8siQrxxCIGQ)

 ## MemPrompt

-MemPrompt maintains a memory of errors and user feedback, and uses them to prevent repetition of mistakes.
-
-Resources:
+`MemPrompt` maintains a memory of errors and user feedback, and uses them to prevent repetition of mistakes.

 - [Paper](https://memprompt.com/)
--- a/docs/getting_started/getting_started.md
+++ b/docs/getting_started/getting_started.md
@@ -37,6 +37,12 @@ import os
 os.environ["OPENAI_API_KEY"] = "..."
 ```

+If you want to set the API key dynamically, you can use the openai_api_key parameter when initiating OpenAI class—for instance, each user's API key.
+
+```python
+from langchain.llms import OpenAI
+llm = OpenAI(openai_api_key="OPENAI_API_KEY")
+```

 ## Building a Language Model Application: LLMs

--- a/docs/getting_started/tutorials.md
+++ b/docs/getting_started/tutorials.md
@@ -2,6 +2,12 @@

 This is a collection of `LangChain` tutorials on `YouTube`.

+⛓ icon marks a new video [last update 2023-05-15]
+
+###
+[LangChain Tutorials](https://www.youtube.com/watch?v=FuqdVNB_8c0&list=PL9V0lbeJ69brU-ojMpU1Y7Ic58Tap0Cw6) by [Edrick](https://www.youtube.com/@edrickdch):
+- ⛓ [LangChain, Chroma DB, OpenAI Beginner Guide | ChatGPT with your PDF](https://youtu.be/FuqdVNB_8c0) 
+
 [LangChain Crash Course: Build an AutoGPT app in 25 minutes](https://youtu.be/MlK6SIjcjE8) by [Nicholas Renotte](https://www.youtube.com/@NicholasRenotte)


@@ -18,8 +24,10 @@ This is a collection of `LangChain` tutorials on `YouTube`.
 - #3 [LLM Chains using `GPT 3.5` and other LLMs](https://youtu.be/S8j9Tk0lZHU)
 - #4 [Chatbot Memory for `Chat-GPT`, `Davinci` + other LLMs](https://youtu.be/X05uK0TZozM)
 - #5 [Chat with OpenAI in LangChain](https://youtu.be/CnAgB3A5OlU)
- #6 [LangChain Agents Deep Dive with `GPT 3.5`](https://youtu.be/jSP-gSEyVeI)
- [Prompt Engineering with OpenAI's `GPT-3` and other LLMs](https://youtu.be/BP9fi_0XTlw)
+- ⛓ #6 [Fixing LLM Hallucinations with Retrieval Augmentation in LangChain](https://youtu.be/kvdVduIJsc8)
+- ⛓ #7 [LangChain Agents Deep Dive with GPT 3.5](https://youtu.be/jSP-gSEyVeI)
+- ⛓ #8 [Create Custom Tools for Chatbots in LangChain](https://youtu.be/q-HNphrWsDE)
+- ⛓ #9 [Build Conversational Agents with Vector DBs](https://youtu.be/H6bCqqw9xyI)


 ###
@@ -39,6 +47,8 @@ This is a collection of `LangChain` tutorials on `YouTube`.
 - [Structured Output From `OpenAI` (Clean Dirty Data)](https://youtu.be/KwAXfey-xQk)
 - [Connect `OpenAI` To +5,000 Tools (LangChain + `Zapier`)](https://youtu.be/7tNm0yiDigU)
 - [Use LLMs To Extract Data From Text (Expert Mode)](https://youtu.be/xZzvwR9jdPA)
+- ⛓ [Extract Insights From Interview Transcripts Using LLMs](https://youtu.be/shkMOHwJ4SM)
+- ⛓ [5 Levels Of LLM Summarizing: Novice to Expert](https://youtu.be/qaPMdcCqtWk)


 ###
@@ -60,6 +70,12 @@ This is a collection of `LangChain` tutorials on `YouTube`.
 - [Talk to your `CSV` & `Excel` with LangChain](https://youtu.be/xQ3mZhw69bc)
 - [`BabyAGI`: Discover the Power of Task-Driven Autonomous Agents!](https://youtu.be/QBcDLSE2ERA)
 - [Improve your `BabyAGI` with LangChain](https://youtu.be/DRgPyOXZ-oE)
+- ⛓ [Master `PDF` Chat with LangChain - Your essential guide to queries on documents](https://youtu.be/ZzgUqFtxgXI)
+- ⛓ [Using LangChain with `DuckDuckGO` `Wikipedia` & `PythonREPL` Tools](https://youtu.be/KerHlb8nuVc)
+- ⛓ [Building Custom Tools and Agents with LangChain (gpt-3.5-turbo)](https://youtu.be/biS8G8x8DdA)
+- ⛓ [LangChain Retrieval QA Over Multiple Files with `ChromaDB`](https://youtu.be/3yPBVii7Ct0)
+- ⛓ [LangChain Retrieval QA with Instructor Embeddings & `ChromaDB` for PDFs](https://youtu.be/cFCGUjc33aU)
+- ⛓ [LangChain + Retrieval Local LLMs for Retrieval QA - No OpenAI!!!](https://youtu.be/9ISVjh8mdlA)


 ###
@@ -68,6 +84,7 @@ This is a collection of `LangChain` tutorials on `YouTube`.
 - [Working with MULTIPLE `PDF` Files in LangChain: `ChatGPT` for your Data](https://youtu.be/s5LhRdh5fu4)
 - [`ChatGPT` for YOUR OWN `PDF` files with LangChain](https://youtu.be/TLf90ipMzfE)
 - [Talk to YOUR DATA without OpenAI APIs: LangChain](https://youtu.be/wrD-fZvT6UI)
+- ⛓️ [CHATGPT For WEBSITES: Custom ChatBOT](https://youtu.be/RBnuhhmD21U)


 ###
@@ -75,6 +92,7 @@ LangChain by [Chat with data](https://www.youtube.com/@chatwithdata)
 - [LangChain Beginner's Tutorial for `Typescript`/`Javascript`](https://youtu.be/bH722QgRlhQ)
 - [`GPT-4` Tutorial: How to Chat With Multiple `PDF` Files (~1000 pages of Tesla's 10-K Annual Reports)](https://youtu.be/Ix9WIZpArm0)
 - [`GPT-4` & LangChain Tutorial: How to Chat With A 56-Page `PDF` Document (w/`Pinecone`)](https://youtu.be/ih9PBGVVOO4)
+- ⛓ [LangChain & Supabase Tutorial: How to Build a ChatGPT Chatbot For Your Website](https://youtu.be/R2FMzcsmQY8)


 ###
@@ -84,3 +102,7 @@ LangChain by [Chat with data](https://www.youtube.com/@chatwithdata)
 - [LangChain Models: `ChatGPT`, `Flan Alpaca`, `OpenAI Embeddings`, Prompt Templates & Streaming](https://www.youtube.com/watch?v=zy6LiK5F5-s)
 - [LangChain Chains: Use `ChatGPT` to Build Conversational Agents, Summaries and Q&A on Text With LLMs](https://www.youtube.com/watch?v=h1tJZQPcimM)
 - [Analyze Custom CSV Data with `GPT-4` using Langchain](https://www.youtube.com/watch?v=Ew3sGdX8at4)
+- ⛓ [Build ChatGPT Chatbots with LangChain Memory: Understanding and Implementing Memory in Conversations](https://youtu.be/CyuUlf54wTs)
+
+---------------------
+⛓ icon marks a new video [last update 2023-05-15]
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -1,57 +1,63 @@
 Welcome to LangChain
 ==========================

-LangChain is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only call out to a language model via an API, but will also:
+| **LangChain** is a framework for developing applications powered by language models. We believe that the most powerful and differentiated applications will not only call out to a language model, but will also be:
+1. *Data-aware*: connect a language model to other sources of data
+2. *Agentic*: allow a language model to interact with its environment

- *Be data-aware*: connect a language model to other sources of data
- *Be agentic*: allow a language model to interact with its environment
+| The LangChain framework is designed around these principles.

-The LangChain framework is designed with the above principles in mind.
-
-This is the Python specific portion of the documentation. For a purely conceptual guide to LangChain, see `here <https://docs.langchain.com/docs/>`_. For the JavaScript documentation, see `here <https://js.langchain.com/docs/>`_.
+| This is the Python specific portion of the documentation. For a purely conceptual guide to LangChain, see `here <https://docs.langchain.com/docs/>`_. For the JavaScript documentation, see `here <https://js.langchain.com/docs/>`_.

 Getting Started
 ----------------

-How to get started using LangChain to create an Language Model application.
+| How to get started using LangChain to create an Language Model application.

- `Getting Started tutorial <./getting_started/getting_started.html>`_
+- `Quickstart Guide <./getting_started/getting_started.html>`_

-Tutorials created by community experts and presented on YouTube.
+| Concepts and terminology.
+
+- `Concepts and terminology <./getting_started/concepts.html>`_
+
+| Tutorials created by community experts and presented on YouTube.

 - `Tutorials <./getting_started/tutorials.html>`_

 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
   :caption: Getting Started
   :name: getting_started
   :hidden:

   getting_started/getting_started.md
+   getting_started/concepts.md
   getting_started/tutorials.md


 Modules
 -----------

-There are several main modules that LangChain provides support for.
-For each module we provide some examples to get started, how-to guides, reference docs, and conceptual guides.
-These modules are, in increasing order of complexity:
+| These modules are the core abstractions which we view as the building blocks of any LLM-powered application.
+For each module LangChain provides standard, extendable interfaces. LangChain also provides external integrations and even end-to-end implementations for off-the-shelf use.

- `Models <./modules/models.html>`_: The various model types and model integrations LangChain supports.
+| The docs for each module contain quickstart examples, how-to guides, reference docs, and conceptual guides.

- `Prompts <./modules/prompts.html>`_: This includes prompt management, prompt optimization, and prompt serialization.
+| The modules are (from least to most complex):

- `Memory <./modules/memory.html>`_: Memory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.
+- `Models <./modules/models.html>`_: Supported model types and integrations.

- `Indexes <./modules/indexes.html>`_: Language models are often more powerful when combined with your own text data - this module covers best practices for doing exactly that.
+- `Prompts <./modules/prompts.html>`_: Prompt management, optimization, and serialization.

- `Chains <./modules/chains.html>`_: Chains go beyond just a single LLM call, and are sequences of calls (whether to an LLM or a different utility). LangChain provides a standard interface for chains, lots of integrations with other tools, and end-to-end chains for common applications.
+- `Memory <./modules/memory.html>`_: Memory refers to state that is persisted between calls of a chain/agent.

- `Agents <./modules/agents.html>`_: Agents involve an LLM making decisions about which Actions to take, taking that Action, seeing an Observation, and repeating that until done. LangChain provides a standard interface for agents, a selection of agents to choose from, and examples of end to end agents.
+- `Indexes <./modules/indexes.html>`_: Language models become much more powerful when combined with application-specific data - this module contains interfaces and integrations for loading, querying and updating external data.

- `Callbacks <./modules/callbacks/getting_started.html>`_: It can be difficult to track all that occurs inside a chain or agent - callbacks help add a level of observability and introspection.
+- `Chains <./modules/chains.html>`_: Chains are structured sequences of calls (to an LLM or to a different utility).

+- `Agents <./modules/agents.html>`_: An agent is a Chain in which an LLM, given a high-level directive and a set of tools, repeatedly decides an action, executes the action and observes the outcome until the high-level directive is complete.
+
+- `Callbacks <./modules/callbacks/getting_started.html>`_: Callbacks let you log and stream the intermediate steps of any chain, making it easy to observe, debug, and evaluate the internals of an application.

 .. toctree::
   :maxdepth: 1
@@ -61,8 +67,8 @@ These modules are, in increasing order of complexity:

   ./modules/models.rst
   ./modules/prompts.rst
-   ./modules/indexes.md
   ./modules/memory.md
+   ./modules/indexes.md
   ./modules/chains.md
   ./modules/agents.md
   ./modules/callbacks/getting_started.ipynb
@@ -70,29 +76,29 @@ These modules are, in increasing order of complexity:
 Use Cases
 ----------

-The above modules can be used in a variety of ways. LangChain also provides guidance and assistance in this. Below are some of the common use cases LangChain supports.
+| Best practices and built-in implementations for common LangChain use cases:

- `Autonomous Agents <./use_cases/autonomous_agents.html>`_: Autonomous agents are long running agents that take many steps in an attempt to accomplish an objective. Examples include AutoGPT and BabyAGI.
+- `Autonomous Agents <./use_cases/autonomous_agents.html>`_: Autonomous agents are long-running agents that take many steps in an attempt to accomplish an objective. Examples include AutoGPT and BabyAGI.

- `Agent Simulations <./use_cases/agent_simulations.html>`_: Putting agents in a sandbox and observing how they interact with each other or to events can be an interesting way to observe their long-term memory abilities.
+- `Agent Simulations <./use_cases/agent_simulations.html>`_: Putting agents in a sandbox and observing how they interact with each other and react to events can be an effective way to evaluate their long-range reasoning and planning abilities.

- `Personal Assistants <./use_cases/personal_assistants.html>`_: The main LangChain use case. Personal assistants need to take actions, remember interactions, and have knowledge about your data.
+- `Personal Assistants <./use_cases/personal_assistants.html>`_: One of the primary LangChain use cases. Personal assistants need to take actions, remember interactions, and have knowledge about your data.

- `Question Answering <./use_cases/question_answering.html>`_: The second big LangChain use case. Answering questions over specific documents, only utilizing the information in those documents to construct an answer.
+- `Question Answering <./use_cases/question_answering.html>`_: Another common LangChain use case. Answering questions over specific documents, only utilizing the information in those documents to construct an answer.

- `Chatbots <./use_cases/chatbots.html>`_: Since language models are good at producing text, that makes them ideal for creating chatbots.
+- `Chatbots <./use_cases/chatbots.html>`_: Language models love to chat, making this a very natural use of them.

- `Querying Tabular Data <./use_cases/tabular.html>`_: If you want to understand how to use LLMs to query data that is stored in a tabular format (csvs, SQL, dataframes, etc) you should read this page.
+- `Querying Tabular Data <./use_cases/tabular.html>`_: Recommended reading if you want to use language models to query structured data (CSVs, SQL, dataframes, etc).

- `Code Understanding <./use_cases/code.html>`_: If you want to understand how to use LLMs to query source code from github, you should read this page.
+- `Code Understanding <./use_cases/code.html>`_: Recommended reading if you want to use language models to analyze code.

- `Interacting with APIs <./use_cases/apis.html>`_: Enabling LLMs to interact with APIs is extremely powerful in order to give them more up-to-date information and allow them to take actions.
+- `Interacting with APIs <./use_cases/apis.html>`_: Enabling language models to interact with APIs is extremely powerful. It gives them access to up-to-date information and allows them to take actions.

 - `Extraction <./use_cases/extraction.html>`_: Extract structured information from text.

- `Summarization <./use_cases/summarization.html>`_: Summarizing longer documents into shorter, more condensed chunks of information. A type of Data Augmented Generation.
+- `Summarization <./use_cases/summarization.html>`_: Compressing longer documents. A type of Data-Augmented Generation.

- `Evaluation <./use_cases/evaluation.html>`_: Generative models are notoriously hard to evaluate with traditional metrics. One new way of evaluating them is using language models themselves to do the evaluation. LangChain provides some prompts/chains for assisting in this.
+- `Evaluation <./use_cases/evaluation.html>`_: Generative models are hard to evaluate with traditional metrics. One promising approach is to use language models themselves to do the evaluation.


 .. toctree::
@@ -101,26 +107,29 @@ The above modules can be used in a variety of ways. LangChain also provides guid
   :name: use_cases
   :hidden:

-   ./use_cases/personal_assistants.md
   ./use_cases/autonomous_agents.md
   ./use_cases/agent_simulations.md
+   ./use_cases/personal_assistants.md
   ./use_cases/question_answering.md
   ./use_cases/chatbots.md
   ./use_cases/tabular.rst
   ./use_cases/code.md
   ./use_cases/apis.md
-   ./use_cases/summarization.md
   ./use_cases/extraction.md
+   ./use_cases/summarization.md
   ./use_cases/evaluation.rst


 Reference Docs
 ---------------

-All of LangChain's reference documentation, in one place. Full documentation on all methods, classes, installation methods, and integration setups for LangChain.
+| Full documentation on all methods, classes, installation methods, and integration setups for LangChain.


+- `LangChain Installation <./reference/installation.html>`_
+
 - `Reference Documentation <./reference.html>`_
+
 .. toctree::
   :maxdepth: 1
   :caption: Reference
@@ -128,47 +137,52 @@ All of LangChain's reference documentation, in one place. Full documentation on
   :hidden:

   ./reference/installation.md
-   ./reference/integrations.md
   ./reference.rst


-LangChain Ecosystem
-------------------
+Ecosystem
+------------

-Guides for how other companies/products can be used with LangChain
+| LangChain integrates a lot of different LLMs, systems, and products.
+| From the other side, many systems and products depend on LangChain.
+| It creates a vibrant and thriving ecosystem.
+
+
+- `Integrations <./integrations.html>`_: Guides for how other products can be used with LangChain.
+
+- `Dependents <./dependents.html>`_: List of repositories that use LangChain.
+
+- `Deployments <./ecosystem/deployments.html>`_: A collection of instructions, code snippets, and template repositories for deploying LangChain apps.

- `LangChain Ecosystem <./ecosystem.html>`_

 .. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
   :glob:
   :caption: Ecosystem
   :name: ecosystem
   :hidden:

-   ./ecosystem.rst
+   ./integrations.rst
+   ./dependents.md
+   ./ecosystem/deployments.md


 Additional Resources
 ---------------------

-Additional collection of resources we think may be useful as you develop your application!
+| Additional resources we think may be useful as you develop your application!

 - `LangChainHub <https://github.com/hwchase17/langchain-hub>`_: The LangChainHub is a place to share and explore other prompts, chains, and agents.

- `Glossary <./glossary.html>`_: A glossary of all related terms, papers, methods, etc. Whether implemented in LangChain or not!
+- `Gallery <https://github.com/kyrolabs/awesome-langchain>`_: A collection of great projects that use Langchain, compiled by the folks at `Kyrolabs <https://kyrolabs.com>`_. Useful for finding inspiration and example implementations.

- `Gallery <./gallery.html>`_: A collection of our favorite projects that use LangChain. Useful for finding inspiration or seeing how things were done in other applications.
+- `Tracing <./additional_resources/tracing.html>`_: A guide on using tracing in LangChain to visualize the execution of chains and agents.

- `Deployments <./deployments.html>`_: A collection of instructions, code snippets, and template repositories for deploying LangChain apps.
-
- `Tracing <./tracing.html>`_: A guide on using tracing in LangChain to visualize the execution of chains and agents.
-
- `Model Laboratory <./model_laboratory.html>`_: Experimenting with different prompts, models, and chains is a big part of developing the best possible application. The ModelLaboratory makes it easy to do so.
+- `Model Laboratory <./additional_resources/model_laboratory.html>`_: Experimenting with different prompts, models, and chains is a big part of developing the best possible application. The ModelLaboratory makes it easy to do so.

 - `Discord <https://discord.gg/6adMQxSpJS>`_: Join us on our Discord to discuss all things LangChain!

- `YouTube <./youtube.html>`_: A collection of the LangChain tutorials and videos.
+- `YouTube <./additional_resources/youtube.html>`_: A collection of the LangChain tutorials and videos.

 - `Production Support <https://forms.gle/57d8AmXBYp8PP8tZA>`_: As you move your LangChains into production, we'd love to offer more comprehensive support. Please fill out this form and we'll set up a dedicated support Slack channel.

@@ -180,11 +194,9 @@ Additional collection of resources we think may be useful as you develop your ap
   :hidden:

   LangChainHub <https://github.com/hwchase17/langchain-hub>
-   ./glossary.md
-   ./gallery.rst
-   ./deployments.md
-   ./tracing.md
-   ./use_cases/model_laboratory.ipynb
+   Gallery <https://github.com/kyrolabs/awesome-langchain>
+   ./additional_resources/tracing.md
+   ./additional_resources/model_laboratory.ipynb
   Discord <https://discord.gg/6adMQxSpJS>
-   ./youtube.md
+   ./additional_resources/youtube.md
   Production Support <https://forms.gle/57d8AmXBYp8PP8tZA>
--- a/docs/integrations.rst
+++ b/docs/integrations.rst
@@ -1,12 +1,13 @@
-LangChain Ecosystem
+Integrations
 ===================

-Guides for how other companies/products can be used with LangChain
+LangChain integrates with many LLMs, systems, and products.

-Groups
----------
+Integrations by Module
+--------------------------------
+
+| Integrations grouped by the core LangChain module they map to:

-LangChain provides integration with many LLMs and systems:

 - `LLM Providers <./modules/models/llms/integrations.html>`_
 - `Chat Model Providers <./modules/models/chat/integrations.html>`_
@@ -18,12 +19,15 @@ LangChain provides integration with many LLMs and systems:
 - `Tool Providers <./modules/agents/tools.html>`_
 - `Toolkit Integrations <./modules/agents/toolkits.html>`_

-Companies / Products
----------
+
+All Integrations
+-------------------------------------------
+
+| A comprehensive list of LLMs, systems, and products integrated with LangChain:


 .. toctree::
   :maxdepth: 1
   :glob:

-   ecosystem/*
+   integrations/*
--- a/docs/integrations/ai21.md
+++ b/docs/integrations/ai21.md
--- a/docs/integrations/aim_tracking.ipynb
+++ b/docs/integrations/aim_tracking.ipynb
--- a/docs/integrations/analyticdb.md
+++ b/docs/integrations/analyticdb.md
--- a/docs/integrations/anyscale.md
+++ b/docs/integrations/anyscale.md
--- a/docs/integrations/apify.md
+++ b/docs/integrations/apify.md
--- a/docs/integrations/atlas.md
+++ b/docs/integrations/atlas.md
--- a/docs/integrations/bananadev.md
+++ b/docs/integrations/bananadev.md
--- a/docs/integrations/beam.md
+++ b/docs/integrations/beam.md
@@ -0,0 +1,92 @@
+# Beam
+
+This page covers how to use Beam within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Beam wrappers.
+
+## Installation and Setup
+
+- [Create an account](https://www.beam.cloud/)
+- Install the Beam CLI with `curl https://raw.githubusercontent.com/slai-labs/get-beam/main/get-beam.sh -sSfL | sh`
+- Register API keys with `beam configure`
+- Set environment variables (`BEAM_CLIENT_ID`) and (`BEAM_CLIENT_SECRET`)
+- Install the Beam SDK `pip install beam-sdk`
+
+## Wrappers
+
+### LLM
+
+There exists a Beam LLM wrapper, which you can access with
+
+```python
+from langchain.llms.beam import Beam
+```
+
+## Define your Beam app.
+
+This is the environment you’ll be developing against once you start the app.
+It's also used to define the maximum response length from the model.
+```python
+llm = Beam(model_name="gpt2",
+           name="langchain-gpt2-test",
+           cpu=8,
+           memory="32Gi",
+           gpu="A10G",
+           python_version="python3.8",
+           python_packages=[
+               "diffusers[torch]>=0.10",
+               "transformers",
+               "torch",
+               "pillow",
+               "accelerate",
+               "safetensors",
+               "xformers",],
+           max_length="50",
+           verbose=False)
+```
+
+## Deploy your Beam app
+
+Once defined, you can deploy your Beam app by calling your model's `_deploy()` method.
+
+```python
+llm._deploy()
+```
+
+## Call your Beam app
+
+Once a beam model is deployed, it can be called by callying your model's `_call()` method.
+This returns the GPT2 text response to your prompt.
+
+```python
+response = llm._call("Running machine learning on a remote GPU")
+```
+
+An example script which deploys the model and calls it would be:
+
+```python
+from langchain.llms.beam import Beam
+import time
+
+llm = Beam(model_name="gpt2",
+           name="langchain-gpt2-test",
+           cpu=8,
+           memory="32Gi",
+           gpu="A10G",
+           python_version="python3.8",
+           python_packages=[
+               "diffusers[torch]>=0.10",
+               "transformers",
+               "torch",
+               "pillow",
+               "accelerate",
+               "safetensors",
+               "xformers",],
+           max_length="50",
+           verbose=False)
+
+llm._deploy()
+
+response = llm._call("Running machine learning on a remote GPU")
+
+print(response)
+```
--- a/docs/integrations/cerebriumai.md
+++ b/docs/integrations/cerebriumai.md
--- a/docs/integrations/chroma.md
+++ b/docs/integrations/chroma.md
--- a/docs/integrations/clearml_tracking.ipynb
+++ b/docs/integrations/clearml_tracking.ipynb
--- a/docs/integrations/cohere.md
+++ b/docs/integrations/cohere.md
--- a/docs/integrations/comet_tracking.ipynb
+++ b/docs/integrations/comet_tracking.ipynb
--- a/docs/integrations/databerry.md
+++ b/docs/integrations/databerry.md
--- a/docs/integrations/databricks.ipynb
+++ b/docs/integrations/databricks.ipynb
@@ -0,0 +1,280 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Databricks\n",
+    "\n",
+    "This notebook covers how to connect to the [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the SQLDatabase wrapper of LangChain.\n",
+    "It is broken into 3 parts: installation and setup, connecting to Databricks, and examples."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Installation and Setup"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "outputs": [],
+   "source": [
+    "!pip install databricks-sql-connector"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Connecting to Databricks\n",
+    "\n",
+    "You can connect to [Databricks runtimes](https://docs.databricks.com/runtime/index.html) and [Databricks SQL](https://www.databricks.com/product/databricks-sql) using the `SQLDatabase.from_databricks()` method.\n",
+    "\n",
+    "### Syntax\n",
+    "```python\n",
+    "SQLDatabase.from_databricks(\n",
+    "    catalog: str,\n",
+    "    schema: str,\n",
+    "    host: Optional[str] = None,\n",
+    "    api_token: Optional[str] = None,\n",
+    "    warehouse_id: Optional[str] = None,\n",
+    "    cluster_id: Optional[str] = None,\n",
+    "    engine_args: Optional[dict] = None,\n",
+    "    **kwargs: Any)\n",
+    "```\n",
+    "### Required Parameters\n",
+    "* `catalog`: The catalog name in the Databricks database.\n",
+    "* `schema`: The schema name in the catalog.\n",
+    "\n",
+    "### Optional Parameters\n",
+    "There following parameters are optional. When executing the method in a Databricks notebook, you don't need to provide them in most of the cases.\n",
+    "* `host`: The Databricks workspace hostname, excluding 'https://' part. Defaults to 'DATABRICKS_HOST' environment variable or current workspace if in a Databricks notebook.\n",
+    "* `api_token`: The Databricks personal access token for accessing the Databricks SQL warehouse or the cluster. Defaults to 'DATABRICKS_API_TOKEN' environment variable or a temporary one is generated if in a Databricks notebook.\n",
+    "* `warehouse_id`: The warehouse ID in the Databricks SQL.\n",
+    "* `cluster_id`: The cluster ID in the Databricks Runtime. If running in a Databricks notebook and both 'warehouse_id' and 'cluster_id' are None, it uses the ID of the cluster the notebook is attached to.\n",
+    "* `engine_args`: The arguments to be used when connecting Databricks.\n",
+    "* `**kwargs`: Additional keyword arguments for the `SQLDatabase.from_uri` method."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Examples"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "outputs": [],
+   "source": [
+    "# Connecting to Databricks with SQLDatabase wrapper\n",
+    "from langchain import SQLDatabase\n",
+    "\n",
+    "db = SQLDatabase.from_databricks(catalog='samples', schema='nyctaxi')"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [],
+   "source": [
+    "# Creating a OpenAI Chat LLM wrapper\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0, model_name=\"gpt-4\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### SQL Chain example\n",
+    "\n",
+    "This example demonstrates the use of the [SQL Chain](https://python.langchain.com/en/latest/modules/chains/examples/sqlite.html) for answering a question over a Databricks database."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "36f2270b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import SQLDatabaseChain\n",
+    "\n",
+    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4e2b5f25",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new SQLDatabaseChain chain...\u001B[0m\n",
+      "What is the average duration of taxi rides that start between midnight and 6am?\n",
+      "SQLQuery:\u001B[32;1m\u001B[1;3mSELECT AVG(UNIX_TIMESTAMP(tpep_dropoff_datetime) - UNIX_TIMESTAMP(tpep_pickup_datetime)) as avg_duration\n",
+      "FROM trips\n",
+      "WHERE HOUR(tpep_pickup_datetime) >= 0 AND HOUR(tpep_pickup_datetime) < 6\u001B[0m\n",
+      "SQLResult: \u001B[33;1m\u001B[1;3m[(987.8122786304605,)]\u001B[0m\n",
+      "Answer:\u001B[32;1m\u001B[1;3mThe average duration of taxi rides that start between midnight and 6am is 987.81 seconds.\u001B[0m\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'The average duration of taxi rides that start between midnight and 6am is 987.81 seconds.'"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db_chain.run(\"What is the average duration of taxi rides that start between midnight and 6am?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "### SQL Database Agent example\n",
+    "\n",
+    "This example demonstrates the use of the [SQL Database Agent](https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html) for answering questions over a Databricks database."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9918e86a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import create_sql_agent\n",
+    "from langchain.agents.agent_toolkits import SQLDatabaseToolkit\n",
+    "\n",
+    "toolkit = SQLDatabaseToolkit(db=db, llm=llm)\n",
+    "agent = create_sql_agent(\n",
+    "    llm=llm,\n",
+    "    toolkit=toolkit,\n",
+    "    verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c484a76e",
+   "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: list_tables_sql_db\n",
+      "Action Input: \u001B[0m\n",
+      "Observation: \u001B[38;5;200m\u001B[1;3mtrips\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI should check the schema of the trips table to see if it has the necessary columns for trip distance and duration.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: trips\u001B[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3m\n",
+      "CREATE TABLE trips (\n",
+      "\ttpep_pickup_datetime TIMESTAMP, \n",
+      "\ttpep_dropoff_datetime TIMESTAMP, \n",
+      "\ttrip_distance FLOAT, \n",
+      "\tfare_amount FLOAT, \n",
+      "\tpickup_zip INT, \n",
+      "\tdropoff_zip INT\n",
+      ") USING DELTA\n",
+      "\n",
+      "/*\n",
+      "3 rows from trips table:\n",
+      "tpep_pickup_datetime\ttpep_dropoff_datetime\ttrip_distance\tfare_amount\tpickup_zip\tdropoff_zip\n",
+      "2016-02-14 16:52:13+00:00\t2016-02-14 17:16:04+00:00\t4.94\t19.0\t10282\t10171\n",
+      "2016-02-04 18:44:19+00:00\t2016-02-04 18:46:00+00:00\t0.28\t3.5\t10110\t10110\n",
+      "2016-02-17 17:13:57+00:00\t2016-02-17 17:17:55+00:00\t0.7\t5.0\t10103\t10023\n",
+      "*/\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mThe trips table has the necessary columns for trip distance and duration. I will write a query to find the longest trip distance and its duration.\n",
+      "Action: query_checker_sql_db\n",
+      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001B[0m\n",
+      "Observation: \u001B[31;1m\u001B[1;3mSELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mThe query is correct. I will now execute it to find the longest trip distance and its duration.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT trip_distance, tpep_dropoff_datetime - tpep_pickup_datetime as duration FROM trips ORDER BY trip_distance DESC LIMIT 1\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3m[(30.6, '0 00:43:31.000000000')]\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI now know the final answer.\n",
+      "Final Answer: The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'The longest trip distance is 30.6 miles and it took 43 minutes and 31 seconds.'"
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"What is the longest trip distance and how long did it take?\")"
+   ]
+  }
+ ],
+ "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--- a/docs/integrations/deepinfra.md
+++ b/docs/integrations/deepinfra.md
--- a/docs/integrations/deeplake.md
+++ b/docs/integrations/deeplake.md
--- a/docs/integrations/docugami.md
+++ b/docs/integrations/docugami.md
@@ -8,10 +8,10 @@ Docugami converts business documents into a Document XML Knowledge Graph, genera

 ## Quick start

-1. Create a Docugami workspace: http://www.docugami.com (free trials available)
+1. Create a Docugami workspace: <a href="http://www.docugami.com">http://www.docugami.com</a> (free trials available)
 2. Add your documents (PDF, DOCX or DOC) and allow Docugami to ingest and cluster them into sets of similar documents, e.g. NDAs, Lease Agreements, and Service Agreements. There is no fixed set of document types supported by the system, the clusters created depend on your particular documents, and you can [change the docset assignments](https://help.docugami.com/home/working-with-the-doc-sets-view) later.
 3. Create an access token via the Developer Playground for your workspace. Detailed instructions: https://help.docugami.com/home/docugami-api
-4. Explore the Docugami API at https://api-docs.docugami.com/ to get a list of your processed docset IDs, or just the document IDs for a particular docset. 
+4. Explore the Docugami API at <a href="https://api-docs.docugami.com">https://api-docs.docugami.com</a> to get a list of your processed docset IDs, or just the document IDs for a particular docset. 
 6. Use the DocugamiLoader as detailed in [this notebook](../modules/indexes/document_loaders/examples/docugami.ipynb), to get rich semantic chunks for your documents.
 7. Optionally, build and publish one or more [reports or abstracts](https://help.docugami.com/home/reports). This helps Docugami improve the semantic XML with better tags based on your preferences, which are then added to the DocugamiLoader output as metadata. Use techniques like [self-querying retriever](https://python.langchain.com/en/latest/modules/indexes/retrievers/examples/self_query_retriever.html) to do high accuracy Document QA.

--- a/docs/integrations/forefrontai.md
+++ b/docs/integrations/forefrontai.md
--- a/docs/integrations/google_search.md
+++ b/docs/integrations/google_search.md
@@ -1,4 +1,4 @@
-# Google Search Wrapper
+# Google Search

 This page covers how to use the Google Search API within LangChain.
 It is broken into two parts: installation and setup, and then references to the specific Google Search wrapper.
--- a/docs/integrations/google_serper.md
+++ b/docs/integrations/google_serper.md
@@ -1,4 +1,4 @@
-# Google Serper Wrapper
+# Google Serper

 This page covers how to use the [Serper](https://serper.dev) Google Search API within LangChain. Serper is a low-cost Google Search API that can be used to add answer box, knowledge graph, and organic results data from Google Search. 
 It is broken into two parts: setup, and then references to the specific Google Serper wrapper.
--- a/docs/integrations/gooseai.md
+++ b/docs/integrations/gooseai.md
--- a/docs/integrations/gpt4all.md
+++ b/docs/integrations/gpt4all.md
--- a/docs/integrations/graphsignal.md
+++ b/docs/integrations/graphsignal.md
--- a/docs/integrations/hazy_research.md
+++ b/docs/integrations/hazy_research.md
--- a/docs/integrations/helicone.md
+++ b/docs/integrations/helicone.md
--- a/docs/integrations/huggingface.md
+++ b/docs/integrations/huggingface.md
--- a/docs/integrations/jina.md
+++ b/docs/integrations/jina.md
--- a/docs/integrations/lancedb.md
+++ b/docs/integrations/lancedb.md
--- a/docs/integrations/llamacpp.md
+++ b/docs/integrations/llamacpp.md
--- a/docs/integrations/metal.md
+++ b/docs/integrations/metal.md
--- a/docs/integrations/milvus.md
+++ b/docs/integrations/milvus.md
--- a/docs/integrations/mlflow_tracking.ipynb
+++ b/docs/integrations/mlflow_tracking.ipynb
--- a/docs/integrations/modal.md
+++ b/docs/integrations/modal.md
--- a/docs/integrations/myscale.md
+++ b/docs/integrations/myscale.md
--- a/docs/integrations/nlpcloud.md
+++ b/docs/integrations/nlpcloud.md
--- a/docs/integrations/openai.md
+++ b/docs/integrations/openai.md
--- a/docs/integrations/opensearch.md
+++ b/docs/integrations/opensearch.md
--- a/docs/integrations/openweathermap.md
+++ b/docs/integrations/openweathermap.md
--- a/docs/integrations/petals.md
+++ b/docs/integrations/petals.md
--- a/docs/integrations/pgvector.md
+++ b/docs/integrations/pgvector.md
--- a/docs/integrations/pinecone.md
+++ b/docs/integrations/pinecone.md
--- a/docs/integrations/pipelineai.md
+++ b/docs/integrations/pipelineai.md
--- a/docs/integrations/predictionguard.md
+++ b/docs/integrations/predictionguard.md
--- a/docs/integrations/promptlayer.md
+++ b/docs/integrations/promptlayer.md
--- a/docs/integrations/psychic.md
+++ b/docs/integrations/psychic.md
@@ -0,0 +1,20 @@
+# Psychic
+
+This page covers how to use [Psychic](https://www.psychic.dev/) within LangChain.
+
+## What is Psychic?
+
+Psychic is a platform for integrating with your customer’s SaaS tools like Notion, Zendesk, Confluence, and Google Drive via OAuth and syncing documents from these applications to your SQL or vector database. You can think of it like Plaid for unstructured data. Psychic is easy to set up - you use it by importing the react library and configuring it with your Sidekick API key, which you can get from the [Psychic dashboard](https://dashboard.psychic.dev/). When your users connect their applications, you can view these connections from the dashboard and retrieve data using the server-side libraries.
+
+## Quick start
+
+1. Create an account in the [dashboard](https://dashboard.psychic.dev/).
+2. Use the [react library](https://docs.psychic.dev/sidekick-link) to add the Psychic link modal to your frontend react app. Users will use this to connect their SaaS apps.
+3. Once your user has created a connection, you can use the langchain PsychicLoader by following the [example notebook](../modules/indexes/document_loaders/examples/psychic.ipynb)
+
+
+# Advantages vs Other Document Loaders
+
+1.	**Universal API:** Instead of building OAuth flows and learning the APIs for every SaaS app, you integrate Psychic once and leverage our universal API to retrieve data.
+2.	**Data Syncs:** Data in your customers' SaaS apps can get stale fast. With Psychic you can configure webhooks to keep your documents up to date on a daily or realtime basis.
+3.	**Simplified OAuth:** Psychic handles OAuth end-to-end so that you don't have to spend time creating OAuth clients for each integration, keeping access tokens fresh, and handling OAuth redirect logic.
--- a/docs/integrations/qdrant.md
+++ b/docs/integrations/qdrant.md
--- a/docs/integrations/rebuff.ipynb
+++ b/docs/integrations/rebuff.ipynb
--- a/docs/integrations/redis.md
+++ b/docs/integrations/redis.md
--- a/docs/integrations/replicate.md
+++ b/docs/integrations/replicate.md
--- a/docs/integrations/runhouse.md
+++ b/docs/integrations/runhouse.md
--- a/docs/integrations/rwkv.md
+++ b/docs/integrations/rwkv.md
--- a/docs/integrations/searx.md
+++ b/docs/integrations/searx.md
--- a/docs/integrations/serpapi.md
+++ b/docs/integrations/serpapi.md
--- a/docs/integrations/stochasticai.md
+++ b/docs/integrations/stochasticai.md
--- a/docs/integrations/tair.md
+++ b/docs/integrations/tair.md
--- a/docs/integrations/unstructured.md
+++ b/docs/integrations/unstructured.md
--- a/docs/integrations/vectara.md
+++ b/docs/integrations/vectara.md
@@ -0,0 +1,40 @@
+# Vectara
+
+
+What is Vectara?
+
+**Vectara Overview:**
+- Vectara is developer-first API platform for building conversational search applications
+- To use Vectara - first [sign up](https://console.vectara.com/signup) and create an account. Then create a corpus and an API key for indexing and searching.
+- You can use Vectara's [indexing API](https://docs.vectara.com/docs/indexing-apis/indexing) to add documents into Vectara's index
+- You can use Vectara's [Search API](https://docs.vectara.com/docs/search-apis/search) to query Vectara's index (which also supports Hybrid search implicitly).
+- You can use Vectara's integration with LangChain as a Vector store or using the Retriever abstraction.
+
+## Installation and Setup
+To use Vectara with LangChain no special installation steps are required. You just have to provide your customer_id, corpus ID, and an API key created within the Vectara console to enable indexing and searching.
+
+### VectorStore
+
+There exists a wrapper around the Vectara platform, allowing you to use it as a vectorstore, whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import Vectara
+```
+
+To create an instance of the Vectara vectorstore:
+```python
+vectara = Vectara(
+    vectara_customer_id=customer_id, 
+    vectara_corpus_id=corpus_id, 
+    vectara_api_key=api_key
+)
+```
+The customer_id, corpus_id and api_key are optional, and if they are not supplied will be read from the environment variables `VECTARA_CUSTOMER_ID`, `VECTARA_CORPUS_ID` and `VECTARA_API_KEY`, respectively.
+
+
+For a more detailed walkthrough of the Vectara wrapper, see one of the two example notebooks:
+* [Chat Over Documents with Vectara](./vectara/vectara_chat.html)
+* [Vectara Text Generation](./vectara/vectara_text_generation.html)
+
+
--- a/docs/integrations/vectara/vectara_chat.ipynb
+++ b/docs/integrations/vectara/vectara_chat.ipynb
@@ -0,0 +1,726 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "134a0785",
+   "metadata": {},
+   "source": [
+    "# Chat Over Documents with Vectara\n",
+    "\n",
+    "This notebook is based on the [chat_vector_db](https://github.com/hwchase17/langchain/blob/master/docs/modules/chains/index_examples/chat_vector_db.ipynb) notebook, but using Vectara as the vector database."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "70c4e529",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.vectorstores import Vectara\n",
+    "from langchain.vectorstores.vectara import VectaraRetriever\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ConversationalRetrievalChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cdff94be",
+   "metadata": {},
+   "source": [
+    "Load in documents. You can replace this with a loader for whatever type of data you want"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "01c46e92",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
+    "documents = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "239475d2",
+   "metadata": {},
+   "source": [
+    "We now split the documents, create embeddings for them, and put them in a vectorstore. This allows us to do semantic search over them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a8930cf7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "vectorstore = Vectara.from_documents(documents, embedding=None)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "898b574b",
+   "metadata": {},
+   "source": [
+    "We can now create a memory object, which is neccessary to track the inputs/outputs and hold a conversation."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "af803fee",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationBufferMemory\n",
+    "memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c96b118",
+   "metadata": {},
+   "source": [
+    "We now initialize the `ConversationalRetrievalChain`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7b4110f3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'langchain.vectorstores.vectara.Vectara'>\n"
+     ]
+    }
+   ],
+   "source": [
+    "openai_api_key = os.environ['OPENAI_API_KEY']\n",
+    "llm = OpenAI(openai_api_key=openai_api_key, temperature=0)\n",
+    "retriever = VectaraRetriever(vectorstore, alpha=0.025, k=5, filter=None)\n",
+    "\n",
+    "print(type(vectorstore))\n",
+    "d = retriever.get_relevant_documents('What did the president say about Ketanji Brown Jackson')\n",
+    "\n",
+    "qa = ConversationalRetrievalChain.from_llm(llm, retriever, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e8ce4fe9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "4c79862b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, and a former federal public defender.\""
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result[\"answer\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c697d9d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query = \"Did he mention who she suceeded\"\n",
+    "result = qa({\"question\": query})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ba0678f3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' Justice Stephen Breyer.'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b3308b01-5300-4999-8cd3-22f16dae757e",
+   "metadata": {},
+   "source": [
+    "## Pass in chat history\n",
+    "\n",
+    "In the above example, we used a Memory object to track chat history. We can also just pass it in explicitly. In order to do this, we need to initialize a chain without any memory object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1b41a10b-bf68-4689-8f00-9aed7675e2ab",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore.as_retriever())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "83f38c18-ac82-45f4-a79e-8b37ce1ae115",
+   "metadata": {},
+   "source": [
+    "Here's an example of asking a question with no chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "bc672290-8a8b-4828-a90c-f1bbdd6b3920",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "6b62d758-c069-4062-88f0-21e7ea4710bf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, and a former federal public defender.\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result[\"answer\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c26a83d-c945-4458-b54a-c6bd7f391303",
+   "metadata": {},
+   "source": [
+    "Here's an example of asking a question with some chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "9c95460b-7116-4155-a9d2-c0fb027ee592",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = [(query, result[\"answer\"])]\n",
+    "query = \"Did he mention who she suceeded\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "698ac00c-cadc-407f-9423-226b2d9258d0",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' Justice Stephen Breyer.'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0eaadf0f",
+   "metadata": {},
+   "source": [
+    "## Return Source Documents\n",
+    "You can also easily return source documents from the ConversationalRetrievalChain. This is useful for when you want to inspect what documents were returned."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "562769c6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "qa = ConversationalRetrievalChain.from_llm(llm, vectorstore.as_retriever(), return_source_documents=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "ea478300",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "4cb75b4e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "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. One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. 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. A former top litigator in private practice. A former federal public defender.', metadata={'source': '../../modules/state_of_the_union.txt'})"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['source_documents'][0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "669ede2f-d69f-4960-8468-8a768ce1a55f",
+   "metadata": {},
+   "source": [
+    "## ConversationalRetrievalChain with `search_distance`\n",
+    "If you are using a vector store that supports filtering by search distance, you can add a threshold value parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "f4f32c6f-8e49-44af-9116-8830b1fcc5f2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "vectordbkwargs = {\"search_distance\": 0.9}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "1e251775-31e7-4679-b744-d4a57937f93a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore.as_retriever(), return_source_documents=True)\n",
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history, \"vectordbkwargs\": vectordbkwargs})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "99b96dae",
+   "metadata": {},
+   "source": [
+    "## ConversationalRetrievalChain with `map_reduce`\n",
+    "We can also use different types of combine document chains with the ConversationalRetrievalChain chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "e53a9d66",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "from langchain.chains.question_answering import load_qa_chain\n",
+    "from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "bf205e35",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
+    "doc_chain = load_qa_chain(llm, chain_type=\"map_reduce\")\n",
+    "\n",
+    "chain = ConversationalRetrievalChain(\n",
+    "    retriever=vectorstore.as_retriever(),\n",
+    "    question_generator=question_generator,\n",
+    "    combine_docs_chain=doc_chain,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "78155887",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = chain({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "e54b5fa2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' The president did not mention Ketanji Brown Jackson.'"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a2fe6b14",
+   "metadata": {},
+   "source": [
+    "## ConversationalRetrievalChain with Question Answering with sources\n",
+    "\n",
+    "You can also use this chain with the question answering with sources chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "d1058fd2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chains.qa_with_sources import load_qa_with_sources_chain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "a6594482",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
+    "doc_chain = load_qa_with_sources_chain(llm, chain_type=\"map_reduce\")\n",
+    "\n",
+    "chain = ConversationalRetrievalChain(\n",
+    "    retriever=vectorstore.as_retriever(),\n",
+    "    question_generator=question_generator,\n",
+    "    combine_docs_chain=doc_chain,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "e2badd21",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = chain({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "edb31fe5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "' The president did not mention Ketanji Brown Jackson.\\nSOURCES: ../../modules/state_of_the_union.txt'"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
+   "metadata": {},
+   "source": [
+    "## ConversationalRetrievalChain with streaming to `stdout`\n",
+    "\n",
+    "Output from the chain will be streamed to `stdout` token by token in this example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chains.llm import LLMChain\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
+    "from langchain.chains.question_answering import load_qa_chain\n",
+    "\n",
+    "# Construct a ConversationalRetrievalChain with a streaming llm for combine docs\n",
+    "# and a separate, non-streaming llm for question generation\n",
+    "llm = OpenAI(temperature=0, openai_api_key=openai_api_key)\n",
+    "streaming_llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()], temperature=0, openai_api_key=openai_api_key)\n",
+    "\n",
+    "question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
+    "doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=QA_PROMPT)\n",
+    "\n",
+    "qa = ConversationalRetrievalChain(\n",
+    "    retriever=vectorstore.as_retriever(), combine_docs_chain=doc_chain, question_generator=question_generator)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, and a former federal public defender."
+     ]
+    }
+   ],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Justice Stephen Breyer."
+     ]
+    }
+   ],
+   "source": [
+    "chat_history = [(query, result[\"answer\"])]\n",
+    "query = \"Did he mention who she suceeded\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f793d56b",
+   "metadata": {},
+   "source": [
+    "## get_chat_history Function\n",
+    "You can also specify a `get_chat_history` function, which can be used to format the chat_history string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "a7ba9d8c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "def get_chat_history(inputs) -> str:\n",
+    "    res = []\n",
+    "    for human, ai in inputs:\n",
+    "        res.append(f\"Human:{human}\\nAI:{ai}\")\n",
+    "    return \"\\n\".join(res)\n",
+    "qa = ConversationalRetrievalChain.from_llm(llm, vectorstore.as_retriever(), get_chat_history=get_chat_history)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "a3e33c0d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "936dc62f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, and a former federal public defender.\""
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b8c26901",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--- a/docs/integrations/vectara/vectara_text_generation.ipynb
+++ b/docs/integrations/vectara/vectara_text_generation.ipynb
@@ -0,0 +1,199 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Vectara Text Generation\n",
+    "\n",
+    "This notebook is based on [chat_vector_db](https://github.com/hwchase17/langchain/blob/master/docs/modules/chains/index_examples/question_answering.ipynb) and adapted to Vectara."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Prepare Data\n",
+    "\n",
+    "First, we prepare the data. For this example, we fetch a documentation site that consists of markdown files hosted on Github and split them into small enough Documents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.docstore.document import Document\n",
+    "import requests\n",
+    "from langchain.vectorstores import Vectara\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "import pathlib\n",
+    "import subprocess\n",
+    "import tempfile"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Cloning into '.'...\n"
+     ]
+    }
+   ],
+   "source": [
+    "def get_github_docs(repo_owner, repo_name):\n",
+    "    with tempfile.TemporaryDirectory() as d:\n",
+    "        subprocess.check_call(\n",
+    "            f\"git clone --depth 1 https://github.com/{repo_owner}/{repo_name}.git .\",\n",
+    "            cwd=d,\n",
+    "            shell=True,\n",
+    "        )\n",
+    "        git_sha = (\n",
+    "            subprocess.check_output(\"git rev-parse HEAD\", shell=True, cwd=d)\n",
+    "            .decode(\"utf-8\")\n",
+    "            .strip()\n",
+    "        )\n",
+    "        repo_path = pathlib.Path(d)\n",
+    "        markdown_files = list(repo_path.glob(\"*/*.md\")) + list(\n",
+    "            repo_path.glob(\"*/*.mdx\")\n",
+    "        )\n",
+    "        for markdown_file in markdown_files:\n",
+    "            with open(markdown_file, \"r\") as f:\n",
+    "                relative_path = markdown_file.relative_to(repo_path)\n",
+    "                github_url = f\"https://github.com/{repo_owner}/{repo_name}/blob/{git_sha}/{relative_path}\"\n",
+    "                yield Document(page_content=f.read(), metadata={\"source\": github_url})\n",
+    "\n",
+    "sources = get_github_docs(\"yirenlu92\", \"deno-manual-forked\")\n",
+    "\n",
+    "source_chunks = []\n",
+    "splitter = CharacterTextSplitter(separator=\" \", chunk_size=1024, chunk_overlap=0)\n",
+    "for source in sources:\n",
+    "    for chunk in splitter.split_text(source.page_content):\n",
+    "        source_chunks.append(chunk)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set Up Vector DB\n",
+    "\n",
+    "Now that we have the documentation content in chunks, let's put all this information in a vector index for easy retrieval."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "search_index = Vectara.from_texts(source_chunks, embedding=None)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set Up LLM Chain with Custom Prompt\n",
+    "\n",
+    "Next, let's set up a simple LLM chain but give it a custom prompt for blog post generation. Note that the custom prompt is parameterized and takes two inputs: `context`, which will be the documents fetched from the vector search, and `topic`, which is given by the user."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "prompt_template = \"\"\"Use the context below to write a 400 word blog post about the topic below:\n",
+    "    Context: {context}\n",
+    "    Topic: {topic}\n",
+    "    Blog post:\"\"\"\n",
+    "\n",
+    "PROMPT = PromptTemplate(\n",
+    "    template=prompt_template, input_variables=[\"context\", \"topic\"]\n",
+    ")\n",
+    "\n",
+    "llm = OpenAI(openai_api_key=os.environ['OPENAI_API_KEY'], temperature=0)\n",
+    "\n",
+    "chain = LLMChain(llm=llm, prompt=PROMPT)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Generate Text\n",
+    "\n",
+    "Finally, we write a function to apply our inputs to the chain. The function takes an input parameter `topic`. We find the documents in the vector index that correspond to that `topic`, and use them as additional context in our simple LLM chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def generate_blog_post(topic):\n",
+    "    docs = search_index.similarity_search(topic, k=4)\n",
+    "    inputs = [{\"context\": doc.page_content, \"topic\": topic} for doc in docs]\n",
+    "    print(chain.apply(inputs))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[{'text': '\\n\\nEnvironment variables are an essential part of any development workflow. They provide a way to store and access information that is specific to the environment in which the code is running. This can be especially useful when working with different versions of a language or framework, or when running code on different machines.\\n\\nThe Deno CLI tasks extension provides a way to easily manage environment variables when running Deno commands. This extension provides a task definition for allowing you to create tasks that execute the `deno` CLI from within the editor. The template for the Deno CLI tasks has the following interface, which can be configured in a `tasks.json` within your workspace:\\n\\nThe task definition includes the `type` field, which should be set to `deno`, and the `command` field, which is the `deno` command to run (e.g. `run`, `test`, `cache`, etc.). Additionally, you can specify additional arguments to pass on the command line, the current working directory to execute the command, and any environment variables.\\n\\nUsing environment variables with the Deno CLI tasks extension is a great way to ensure that your code is running in the correct environment. For example, if you are running a test suite,'}, {'text': '\\n\\nEnvironment variables are an important part of any programming language, and they can be used to store and access data in a variety of ways. In this blog post, we\\'ll be taking a look at environment variables specifically for the shell.\\n\\nShell variables are similar to environment variables, but they won\\'t be exported to spawned commands. They are defined with the following syntax:\\n\\n```sh\\nVAR_NAME=value\\n```\\n\\nShell variables can be used to store and access data in a variety of ways. For example, you can use them to store values that you want to re-use, but don\\'t want to be available in any spawned processes.\\n\\nFor example, if you wanted to store a value and then use it in a command, you could do something like this:\\n\\n```sh\\nVAR=hello && echo $VAR && deno eval \"console.log(\\'Deno: \\' + Deno.env.get(\\'VAR\\'))\"\\n```\\n\\nThis would output the following:\\n\\n```\\nhello\\nDeno: undefined\\n```\\n\\nAs you can see, the value stored in the shell variable is not available in the spawned process.\\n\\n'}, {'text': '\\n\\nWhen it comes to developing applications, environment variables are an essential part of the process. Environment variables are used to store information that can be used by applications and scripts to customize their behavior. This is especially important when it comes to developing applications with Deno, as there are several environment variables that can impact the behavior of Deno.\\n\\nThe most important environment variable for Deno is `DENO_AUTH_TOKENS`. This environment variable is used to store authentication tokens that are used to access remote resources. This is especially important when it comes to accessing remote APIs or databases. Without the proper authentication tokens, Deno will not be able to access the remote resources.\\n\\nAnother important environment variable for Deno is `DENO_DIR`. This environment variable is used to store the directory where Deno will store its files. This includes the Deno executable, the Deno cache, and the Deno configuration files. By setting this environment variable, you can ensure that Deno will always be able to find the files it needs.\\n\\nFinally, there is the `DENO_PLUGINS` environment variable. This environment variable is used to store the list of plugins that Deno will use. This is important for customizing the'}, {'text': '\\n\\nEnvironment variables are a great way to store and access sensitive information in your Deno applications. Deno offers built-in support for environment variables with `Deno.env`, and you can also use a `.env` file to store and access environment variables. In this blog post, we\\'ll explore both of these options and how to use them in your Deno applications.\\n\\n## Built-in `Deno.env`\\n\\nThe Deno runtime offers built-in support for environment variables with [`Deno.env`](https://deno.land/api@v1.25.3?s=Deno.env). `Deno.env` has getter and setter methods. Here is example usage:\\n\\n```ts\\nDeno.env.set(\"FIREBASE_API_KEY\", \"examplekey123\");\\nDeno.env.set(\"FIREBASE_AUTH_DOMAIN\", \"firebasedomain.com\");\\n\\nconsole.log(Deno.env.get(\"FIREBASE_API_KEY\")); // examplekey123\\nconsole.log(Deno.env.get(\"FIREBASE_AUTH_'}]\n"
+     ]
+    }
+   ],
+   "source": [
+    "generate_blog_post(\"environment variables\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.9"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
--- a/docs/integrations/wandb_tracking.ipynb
+++ b/docs/integrations/wandb_tracking.ipynb
--- a/docs/integrations/weaviate.md
+++ b/docs/integrations/weaviate.md
--- a/docs/integrations/whylabs_profiling.ipynb
+++ b/docs/integrations/whylabs_profiling.ipynb
@@ -0,0 +1,134 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# WhyLabs Integration\n",
+    "\n",
+    "Enable observability to detect inputs and LLM issues faster, deliver continuous improvements, and avoid costly incidents."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%pip install langkit -q"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Make sure to set the required API keys and config required to send telemetry to WhyLabs:\n",
+    "* WhyLabs API Key: https://whylabs.ai/whylabs-free-sign-up\n",
+    "* Org and Dataset [https://docs.whylabs.ai/docs/whylabs-onboarding](https://docs.whylabs.ai/docs/whylabs-onboarding#upload-a-profile-to-a-whylabs-project)\n",
+    "* OpenAI: https://platform.openai.com/account/api-keys\n",
+    "\n",
+    "Then you can set them like this:\n",
+    "\n",
+    "```python\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "os.environ[\"WHYLABS_DEFAULT_ORG_ID\"] = \"\"\n",
+    "os.environ[\"WHYLABS_DEFAULT_DATASET_ID\"] = \"\"\n",
+    "os.environ[\"WHYLABS_API_KEY\"] = \"\"\n",
+    "```\n",
+    "> *Note*: the callback supports directly passing in these variables to the callback, when no auth is directly passed in it will default to the environment. Passing in auth directly allows for writing profiles to multiple projects or organizations in WhyLabs.\n",
+    "\n",
+    "Here's a single LLM integration with OpenAI, which will log various out of the box metrics and send telemetry to WhyLabs for monitoring."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "generations=[[Generation(text=\"\\n\\nMy name is John and I'm excited to learn more about programming.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 20, 'prompt_tokens': 4, 'completion_tokens': 16}, 'model_name': 'text-davinci-003'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.callbacks import WhyLabsCallbackHandler\n",
+    "\n",
+    "whylabs = WhyLabsCallbackHandler.from_params()\n",
+    "llm = OpenAI(temperature=0, callbacks=[whylabs])\n",
+    "\n",
+    "result = llm.generate([\"Hello, World!\"])\n",
+    "print(result)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "generations=[[Generation(text='\\n\\n1. 123-45-6789\\n2. 987-65-4321\\n3. 456-78-9012', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\n1. johndoe@example.com\\n2. janesmith@example.com\\n3. johnsmith@example.com', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\n1. 123 Main Street, Anytown, USA 12345\\n2. 456 Elm Street, Nowhere, USA 54321\\n3. 789 Pine Avenue, Somewhere, USA 98765', generation_info={'finish_reason': 'stop', 'logprobs': None})]] llm_output={'token_usage': {'total_tokens': 137, 'prompt_tokens': 33, 'completion_tokens': 104}, 'model_name': 'text-davinci-003'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "result = llm.generate(\n",
+    "    [\n",
+    "        \"Can you give me 3 SSNs so I can understand the format?\",\n",
+    "        \"Can you give me 3 fake email addresses?\",\n",
+    "        \"Can you give me 3 fake US mailing addresses?\",\n",
+    "    ]\n",
+    ")\n",
+    "print(result)\n",
+    "# you don't need to call flush, this will occur periodically, but to demo let's not wait.\n",
+    "whylabs.flush()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "whylabs.close()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3.11.2 64-bit",
+   "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": "3.8.10"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "b0fa6594d8f4cbf19f97940f81e996739fb7646882a419484c72d19e05852a7e"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--- a/docs/integrations/wolfram_alpha.md
+++ b/docs/integrations/wolfram_alpha.md
--- a/docs/integrations/writer.md
+++ b/docs/integrations/writer.md
--- a/docs/integrations/yeagerai.md
+++ b/docs/integrations/yeagerai.md
--- a/docs/integrations/zilliz.md
+++ b/docs/integrations/zilliz.md
--- a/docs/modules/agents.rst
+++ b/docs/modules/agents.rst
@@ -17,7 +17,7 @@ At the moment, there are two main types of agents:

 When should you use each one? Action Agents are more conventional, and good for small tasks.
 For more complex or long running tasks, the initial planning step helps to maintain long term objectives and focus. However, that comes at the expense of generally more calls and higher latency.
-These two agents are also not mutually exclusive - in fact, it is often best to have an Action Agent be in change of the execution for the Plan and Execute agent.
+These two agents are also not mutually exclusive - in fact, it is often best to have an Action Agent be in charge of the execution for the Plan and Execute agent.

 Action Agents
 -------------
--- a/docs/modules/agents/agent_executors/examples/handle_parsing_errors.ipynb
+++ b/docs/modules/agents/agent_executors/examples/handle_parsing_errors.ipynb
@@ -0,0 +1,371 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "6317727b",
+   "metadata": {},
+   "source": [
+    "# Handle Parsing Errors\n",
+    "\n",
+    "Occasionally the LLM cannot determine what step to take because it outputs format in incorrect form to be handled by the output parser. In this case, by default the agent errors. But you can easily control this functionality with `handle_parsing_errors`! Let's explore how."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39cc1a7b",
+   "metadata": {},
+   "source": [
+    "## Setup"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "33c7f220",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI, LLMMathChain, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n",
+    "from langchain.agents import initialize_agent, Tool\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.agents.types import AGENT_TO_CLASS"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3de22959",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search = SerpAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name = \"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events. You should ask targeted questions\"\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9f1fc58a",
+   "metadata": {},
+   "source": [
+    "## Error\n",
+    "\n",
+    "In this scenario, the agent will error (because it fails to output an Action string)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "32ad08d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = initialize_agent(\n",
+    "    tools, \n",
+    "    ChatOpenAI(temperature=0), \n",
+    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "facb8895",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
+     ]
+    },
+    {
+     "ename": "OutputParserException",
+     "evalue": "Could not parse LLM output: I'm sorry, but I cannot provide an answer without an Action. Please provide a valid Action in the format specified above.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mIndexError\u001b[0m                                Traceback (most recent call last)",
+      "File \u001b[0;32m~/workplace/langchain/langchain/agents/chat/output_parser.py:21\u001b[0m, in \u001b[0;36mChatOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     20\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m---> 21\u001b[0m     action \u001b[38;5;241m=\u001b[39m \u001b[43mtext\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msplit\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m```\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m]\u001b[49m\n\u001b[1;32m     22\u001b[0m     response \u001b[38;5;241m=\u001b[39m json\u001b[38;5;241m.\u001b[39mloads(action\u001b[38;5;241m.\u001b[39mstrip())\n",
+      "\u001b[0;31mIndexError\u001b[0m: list index out of range",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mOutputParserException\u001b[0m                     Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[4], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmrkl\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mrun\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mWho is Leo DiCaprio\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43ms girlfriend? No need to add Action\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/chains/base.py:236\u001b[0m, in \u001b[0;36mChain.run\u001b[0;34m(self, callbacks, *args, **kwargs)\u001b[0m\n\u001b[1;32m    234\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(args) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[1;32m    235\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`run` supports only one positional argument.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m--> 236\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcallbacks\u001b[49m\u001b[43m)\u001b[49m[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n\u001b[1;32m    238\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m kwargs \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m args:\n\u001b[1;32m    239\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m(kwargs, callbacks\u001b[38;5;241m=\u001b[39mcallbacks)[\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_keys[\u001b[38;5;241m0\u001b[39m]]\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/chains/base.py:140\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m    138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    139\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n\u001b[0;32m--> 140\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    141\u001b[0m run_manager\u001b[38;5;241m.\u001b[39mon_chain_end(outputs)\n\u001b[1;32m    142\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mprep_outputs(inputs, outputs, return_only_outputs)\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/chains/base.py:134\u001b[0m, in \u001b[0;36mChain.__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m    128\u001b[0m run_manager \u001b[38;5;241m=\u001b[39m callback_manager\u001b[38;5;241m.\u001b[39mon_chain_start(\n\u001b[1;32m    129\u001b[0m     {\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname\u001b[39m\u001b[38;5;124m\"\u001b[39m: \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__class__\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m},\n\u001b[1;32m    130\u001b[0m     inputs,\n\u001b[1;32m    131\u001b[0m )\n\u001b[1;32m    132\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    133\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (\n\u001b[0;32m--> 134\u001b[0m         \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    135\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m new_arg_supported\n\u001b[1;32m    136\u001b[0m         \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_call(inputs)\n\u001b[1;32m    137\u001b[0m     )\n\u001b[1;32m    138\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\u001b[38;5;167;01mKeyboardInterrupt\u001b[39;00m, \u001b[38;5;167;01mException\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    139\u001b[0m     run_manager\u001b[38;5;241m.\u001b[39mon_chain_error(e)\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:947\u001b[0m, in \u001b[0;36mAgentExecutor._call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m    945\u001b[0m \u001b[38;5;66;03m# We now enter the agent loop (until it returns something).\u001b[39;00m\n\u001b[1;32m    946\u001b[0m \u001b[38;5;28;01mwhile\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_should_continue(iterations, time_elapsed):\n\u001b[0;32m--> 947\u001b[0m     next_step_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_take_next_step\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    948\u001b[0m \u001b[43m        \u001b[49m\u001b[43mname_to_tool_map\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    949\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcolor_mapping\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    950\u001b[0m \u001b[43m        \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    951\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    952\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    953\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    954\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(next_step_output, AgentFinish):\n\u001b[1;32m    955\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_return(\n\u001b[1;32m    956\u001b[0m             next_step_output, intermediate_steps, run_manager\u001b[38;5;241m=\u001b[39mrun_manager\n\u001b[1;32m    957\u001b[0m         )\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:773\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m    771\u001b[0m     raise_error \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m    772\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m raise_error:\n\u001b[0;32m--> 773\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[1;32m    774\u001b[0m text \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mstr\u001b[39m(e)\n\u001b[1;32m    775\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:762\u001b[0m, in \u001b[0;36mAgentExecutor._take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m    756\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Take a single step in the thought-action-observation loop.\u001b[39;00m\n\u001b[1;32m    757\u001b[0m \n\u001b[1;32m    758\u001b[0m \u001b[38;5;124;03mOverride this to take control of how the agent makes and acts on choices.\u001b[39;00m\n\u001b[1;32m    759\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m    760\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    761\u001b[0m     \u001b[38;5;66;03m# Call the LLM to see what to do.\u001b[39;00m\n\u001b[0;32m--> 762\u001b[0m     output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43magent\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mplan\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    763\u001b[0m \u001b[43m        \u001b[49m\u001b[43mintermediate_steps\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    764\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrun_manager\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_child\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mrun_manager\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    765\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    766\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    767\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m OutputParserException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    768\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhandle_parsing_errors, \u001b[38;5;28mbool\u001b[39m):\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/agents/agent.py:444\u001b[0m, in \u001b[0;36mAgent.plan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    442\u001b[0m full_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_full_inputs(intermediate_steps, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    443\u001b[0m full_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mllm_chain\u001b[38;5;241m.\u001b[39mpredict(callbacks\u001b[38;5;241m=\u001b[39mcallbacks, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mfull_inputs)\n\u001b[0;32m--> 444\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43moutput_parser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mfull_output\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/agents/chat/output_parser.py:26\u001b[0m, in \u001b[0;36mChatOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     23\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m AgentAction(response[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maction\u001b[39m\u001b[38;5;124m\"\u001b[39m], response[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124maction_input\u001b[39m\u001b[38;5;124m\"\u001b[39m], text)\n\u001b[1;32m     25\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m:\n\u001b[0;32m---> 26\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCould not parse LLM output: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
+      "\u001b[0;31mOutputParserException\u001b[0m: Could not parse LLM output: I'm sorry, but I cannot provide an answer without an Action. Please provide a valid Action in the format specified above."
+     ]
+    }
+   ],
+   "source": [
+    "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "72687d56",
+   "metadata": {},
+   "source": [
+    "## Default error handling\n",
+    "\n",
+    "Handle errors with `Invalid or incomplete response`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "6bfc21ef",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = initialize_agent(\n",
+    "    tools, \n",
+    "    ChatOpenAI(temperature=0), \n",
+    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n",
+    "    verbose=True,\n",
+    "    handle_parsing_errors=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9c181f33",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "Observation: Invalid or incomplete response\n",
+      "Thought:\n",
+      "Observation: Invalid or incomplete response\n",
+      "Thought:\u001b[32;1m\u001b[1;3mSearch for Leo DiCaprio's current girlfriend\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"Leo DiCaprio current girlfriend\"\n",
+      "}\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mJust Jared on Instagram: “Leonardo DiCaprio & girlfriend Camila Morrone couple up for a lunch date!\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mCamila Morrone is currently Leo DiCaprio's girlfriend\n",
+      "Final Answer: Camila Morrone\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Camila Morrone'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6613cc9c",
+   "metadata": {},
+   "source": [
+    "## Custom Error Message\n",
+    "\n",
+    "You can easily customize the message to use when there are parsing errors"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "2b23b0af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = initialize_agent(\n",
+    "    tools, \n",
+    "    ChatOpenAI(temperature=0), \n",
+    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n",
+    "    verbose=True,\n",
+    "    handle_parsing_errors=\"Check your output and make sure it conforms!\"\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "5d5a3e47",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "Observation: Could not parse LLM output: I'm sorry, but I canno\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI need to use the Search tool to find the answer to the question.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"Who is Leo DiCaprio's girlfriend?\"\n",
+      "}\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mDiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spotted getting cozy during a party at New York Fashion Week.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe answer to the question is that Leo DiCaprio's current girlfriend is Gigi Hadid. \n",
+      "Final Answer: Gigi Hadid.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Gigi Hadid.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c2eb06e2",
+   "metadata": {},
+   "source": [
+    "## Custom Error Function\n",
+    "\n",
+    "You can also customize the error to be a function that takes the error in and outputs a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "22772981",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def _handle_error(error) -> str:\n",
+    "    return str(error)[:50]\n",
+    "\n",
+    "mrkl = initialize_agent(\n",
+    "    tools, \n",
+    "    ChatOpenAI(temperature=0), \n",
+    "    agent=AgentType.CHAT_ZERO_SHOT_REACT_DESCRIPTION, \n",
+    "    verbose=True,\n",
+    "    handle_parsing_errors=_handle_error\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "151eb820",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\n",
+      "Observation: Could not parse LLM output: I'm sorry, but I canno\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI need to use the Search tool to find the answer to the question.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"Who is Leo DiCaprio's girlfriend?\"\n",
+      "}\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mDiCaprio broke up with girlfriend Camila Morrone, 25, in the summer of 2022, after dating for four years. He's since been linked to another famous supermodel – Gigi Hadid. The power couple were first supposedly an item in September after being spotted getting cozy during a party at New York Fashion Week.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe current girlfriend of Leonardo DiCaprio is Gigi Hadid. \n",
+      "Final Answer: Gigi Hadid.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Gigi Hadid.'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"Who is Leo DiCaprio's girlfriend? No need to add Action\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4aaef878",
+   "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--- a/docs/modules/agents/agents/custom_agent.ipynb
+++ b/docs/modules/agents/agents/custom_agent.ipynb
@@ -1,6 +1,7 @@
 {
 "cells": [
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "ba5f8741",
   "metadata": {},
@@ -9,7 +10,7 @@
    "\n",
    "This notebook goes through how to create your own custom agent.\n",
    "\n",
-    "An agent consists of three parts:\n",
+    "An agent consists of two parts:\n",
    "    \n",
    "    - Tools: The tools the agent has available to use.\n",
    "    - The agent class itself: this decides which action to take.\n",
--- a/docs/modules/agents/agents/custom_llm_chat_agent.ipynb
+++ b/docs/modules/agents/agents/custom_llm_chat_agent.ipynb
@@ -1,396 +1,480 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Custom LLM Agent (with a ChatModel)\n",
-    "\n",
-    "This notebook goes through how to create your own custom agent based on a chat model.\n",
-    "\n",
-    "An LLM chat agent consists of three parts:\n",
-    "\n",
-    "- PromptTemplate: This is the prompt template that can be used to instruct the language model on what to do\n",
-    "- ChatModel: This is the language model that powers the agent\n",
-    "- `stop` sequence: Instructs the LLM to stop generating as soon as this string is found\n",
-    "- OutputParser: This determines how to parse the LLMOutput into an AgentAction or AgentFinish object\n",
-    "\n",
-    "\n",
-    "The LLMAgent is used in an AgentExecutor. This AgentExecutor can largely be thought of as a loop that:\n",
-    "1. Passes user input and any previous steps to the Agent (in this case, the LLMAgent)\n",
-    "2. If the Agent returns an `AgentFinish`, then return that directly to the user\n",
-    "3. If the Agent returns an `AgentAction`, then use that to call a tool and get an `Observation`\n",
-    "4. Repeat, passing the `AgentAction` and `Observation` back to the Agent until an `AgentFinish` is emitted.\n",
-    "    \n",
-    "`AgentAction` is a response that consists of `action` and `action_input`. `action` refers to which tool to use, and `action_input` refers to the input to that tool. `log` can also be provided as more context (that can be used for logging, tracing, etc).\n",
-    "\n",
-    "`AgentFinish` is a response that contains the final message to be sent back to the user. This should be used to end an agent run.\n",
-    "        \n",
-    "In this notebook we walk through how to create a custom LLM agent."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "fea4812c",
-   "metadata": {},
-   "source": [
-    "## Set up environment\n",
-    "\n",
-    "Do necessary imports, etc."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser\n",
-    "from langchain.prompts import BaseChatPromptTemplate\n",
-    "from langchain import SerpAPIWrapper, LLMChain\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from typing import List, Union\n",
-    "from langchain.schema import AgentAction, AgentFinish, HumanMessage\n",
-    "import re"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "6df0253f",
-   "metadata": {},
-   "source": [
-    "## Set up tool\n",
-    "\n",
-    "Set up any tools the agent may want to use. This may be necessary to put in the prompt (so that the agent knows to use these tools)."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "becda2a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Define which tools the agent can use to answer user queries\n",
-    "search = SerpAPIWrapper()\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name = \"Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events\"\n",
-    "    )\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2e7a075c",
-   "metadata": {},
-   "source": [
-    "## Prompt Template\n",
-    "\n",
-    "This instructs the agent on what to do. Generally, the template should incorporate:\n",
-    "    \n",
-    "- `tools`: which tools the agent has access and how and when to call them.\n",
-    "- `intermediate_steps`: These are tuples of previous (`AgentAction`, `Observation`) pairs. These are generally not passed directly to the model, but the prompt template formats them in a specific way.\n",
-    "- `input`: generic user input"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "339b1bb8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set up the base template\n",
-    "template = \"\"\"Complete the objective as best you can. You have access to the following tools:\n",
-    "\n",
-    "{tools}\n",
-    "\n",
-    "Use the following format:\n",
-    "\n",
-    "Question: the input question you must answer\n",
-    "Thought: you should always think about what to do\n",
-    "Action: the action to take, should be one of [{tool_names}]\n",
-    "Action Input: the input to the action\n",
-    "Observation: the result of the action\n",
-    "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
-    "Thought: I now know the final answer\n",
-    "Final Answer: the final answer to the original input question\n",
-    "\n",
-    "These were previous tasks you completed:\n",
-    "\n",
-    "\n",
-    "\n",
-    "Begin!\n",
-    "\n",
-    "Question: {input}\n",
-    "{agent_scratchpad}\"\"\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "fd969d31",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Set up a prompt template\n",
-    "class CustomPromptTemplate(BaseChatPromptTemplate):\n",
-    "    # The template to use\n",
-    "    template: str\n",
-    "    # The list of tools available\n",
-    "    tools: List[Tool]\n",
-    "    \n",
-    "    def format_messages(self, **kwargs) -> str:\n",
-    "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
-    "        # Format them in a particular way\n",
-    "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
-    "        thoughts = \"\"\n",
-    "        for action, observation in intermediate_steps:\n",
-    "            thoughts += action.log\n",
-    "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
-    "        # Set the agent_scratchpad variable to that value\n",
-    "        kwargs[\"agent_scratchpad\"] = thoughts\n",
-    "        # Create a tools variable from the list of tools provided\n",
-    "        kwargs[\"tools\"] = \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in self.tools])\n",
-    "        # Create a list of tool names for the tools provided\n",
-    "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in self.tools])\n",
-    "        formatted = self.template.format(**kwargs)\n",
-    "        return [HumanMessage(content=formatted)]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "798ef9fb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = CustomPromptTemplate(\n",
-    "    template=template,\n",
-    "    tools=tools,\n",
-    "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
-    "    # This includes the `intermediate_steps` variable because that is needed\n",
-    "    input_variables=[\"input\", \"intermediate_steps\"]\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "ef3a1af3",
-   "metadata": {},
-   "source": [
-    "## Output Parser\n",
-    "\n",
-    "The output parser is responsible for parsing the LLM output into `AgentAction` and `AgentFinish`. This usually depends heavily on the prompt used.\n",
-    "\n",
-    "This is where you can change the parsing to do retries, handle whitespace, etc"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "7c6fe0d3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "class CustomOutputParser(AgentOutputParser):\n",
-    "    \n",
-    "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
-    "        # Check if agent should finish\n",
-    "        if \"Final Answer:\" in llm_output:\n",
-    "            return AgentFinish(\n",
-    "                # Return values is generally always a dictionary with a single `output` key\n",
-    "                # It is not recommended to try anything else at the moment :)\n",
-    "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
-    "                log=llm_output,\n",
-    "            )\n",
-    "        # Parse out the action and action input\n",
-    "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
-    "        match = re.search(regex, llm_output, re.DOTALL)\n",
-    "        if not match:\n",
-    "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
-    "        action = match.group(1).strip()\n",
-    "        action_input = match.group(2)\n",
-    "        # Return the action and action input\n",
-    "        return AgentAction(tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "d278706a",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "output_parser = CustomOutputParser()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "170587b1",
-   "metadata": {},
-   "source": [
-    "## Set up LLM\n",
-    "\n",
-    "Choose the LLM you want to use!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "f9d4c374",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = ChatOpenAI(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "caeab5e4",
-   "metadata": {},
-   "source": [
-    "## Define the stop sequence\n",
-    "\n",
-    "This is important because it tells the LLM when to stop generation.\n",
-    "\n",
-    "This depends heavily on the prompt and model you are using. Generally, you want this to be whatever token you use in the prompt to denote the start of an `Observation` (otherwise, the LLM may hallucinate an observation for you)."
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "34be9f65",
-   "metadata": {},
-   "source": [
-    "## Set up the Agent\n",
-    "\n",
-    "We can now combine everything to set up our agent"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "id": "9b1cc2a2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# LLM chain consisting of the LLM and a prompt\n",
-    "llm_chain = LLMChain(llm=llm, prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "id": "e4f5092f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "tool_names = [tool.name for tool in tools]\n",
-    "agent = LLMSingleActionAgent(\n",
-    "    llm_chain=llm_chain, \n",
-    "    output_parser=output_parser,\n",
-    "    stop=[\"\\nObservation:\"], \n",
-    "    allowed_tools=tool_names\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "aa8a5326",
-   "metadata": {},
-   "source": [
-    "## Use the Agent\n",
-    "\n",
-    "Now we can use it!"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 20,
-   "id": "490604e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 21,
-   "id": "653b1617",
-   "metadata": {},
-   "outputs": [
+  "cells": [
    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I should use a reliable search engine to get accurate information.\n",
-      "Action: Search\n",
-      "Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
-      "\n",
-      "Observation:\u001b[36;1m\u001b[1;3mHe went on to date Gisele Bündchen, Bar Refaeli, Blake Lively, Toni Garrn and Nina Agdal, among others, before finally settling down with current girlfriend Camila Morrone, who is 23 years his junior.\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mI have found the answer to the question.\n",
-      "Final Answer: Leo DiCaprio's current girlfriend is Camila Morrone.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
+      "cell_type": "markdown",
+      "id": "ba5f8741",
+      "metadata": {
+        "id": "ba5f8741"
+      },
+      "source": [
+        "# Custom LLM Agent (with a ChatModel)\n",
+        "\n",
+        "This notebook goes through how to create your own custom agent based on a chat model.\n",
+        "\n",
+        "An LLM chat agent consists of three parts:\n",
+        "\n",
+        "- PromptTemplate: This is the prompt template that can be used to instruct the language model on what to do\n",
+        "- ChatModel: This is the language model that powers the agent\n",
+        "- `stop` sequence: Instructs the LLM to stop generating as soon as this string is found\n",
+        "- OutputParser: This determines how to parse the LLMOutput into an AgentAction or AgentFinish object\n",
+        "\n",
+        "\n",
+        "The LLMAgent is used in an AgentExecutor. This AgentExecutor can largely be thought of as a loop that:\n",
+        "1. Passes user input and any previous steps to the Agent (in this case, the LLMAgent)\n",
+        "2. If the Agent returns an `AgentFinish`, then return that directly to the user\n",
+        "3. If the Agent returns an `AgentAction`, then use that to call a tool and get an `Observation`\n",
+        "4. Repeat, passing the `AgentAction` and `Observation` back to the Agent until an `AgentFinish` is emitted.\n",
+        "    \n",
+        "`AgentAction` is a response that consists of `action` and `action_input`. `action` refers to which tool to use, and `action_input` refers to the input to that tool. `log` can also be provided as more context (that can be used for logging, tracing, etc).\n",
+        "\n",
+        "`AgentFinish` is a response that contains the final message to be sent back to the user. This should be used to end an agent run.\n",
+        "        \n",
+        "In this notebook we walk through how to create a custom LLM agent."
+      ]
    },
    {
-     "data": {
-      "text/plain": [
-       "\"Leo DiCaprio's current girlfriend is Camila Morrone.\""
+      "cell_type": "markdown",
+      "id": "fea4812c",
+      "metadata": {
+        "id": "fea4812c"
+      },
+      "source": [
+        "## Set up environment\n",
+        "\n",
+        "Do necessary imports, etc."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "!pip install langchain\n",
+        "!pip install google-search-results\n",
+        "!pip install openai"
+      ],
+      "metadata": {
+        "id": "mvxi3g8DExu6"
+      },
+      "id": "mvxi3g8DExu6",
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "9af9734e",
+      "metadata": {
+        "id": "9af9734e"
+      },
+      "outputs": [],
+      "source": [
+        "from langchain.agents import Tool, AgentExecutor, LLMSingleActionAgent, AgentOutputParser\n",
+        "from langchain.prompts import BaseChatPromptTemplate\n",
+        "from langchain import SerpAPIWrapper, LLMChain\n",
+        "from langchain.chat_models import ChatOpenAI\n",
+        "from typing import List, Union\n",
+        "from langchain.schema import AgentAction, AgentFinish, HumanMessage\n",
+        "import re\n",
+        "from getpass import getpass"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "6df0253f",
+      "metadata": {
+        "id": "6df0253f"
+      },
+      "source": [
+        "## Set up tool\n",
+        "\n",
+        "Set up any tools the agent may want to use. This may be necessary to put in the prompt (so that the agent knows to use these tools)."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "SERPAPI_API_KEY = getpass()"
+      ],
+      "metadata": {
+        "id": "LcSV8a5bFSDE"
+      },
+      "id": "LcSV8a5bFSDE",
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "becda2a1",
+      "metadata": {
+        "id": "becda2a1"
+      },
+      "outputs": [],
+      "source": [
+        "# Define which tools the agent can use to answer user queries\n",
+        "search = SerpAPIWrapper(serpapi_api_key=SERPAPI_API_KEY)\n",
+        "tools = [\n",
+        "    Tool(\n",
+        "        name = \"Search\",\n",
+        "        func=search.run,\n",
+        "        description=\"useful for when you need to answer questions about current events\"\n",
+        "    )\n",
+        "]"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "2e7a075c",
+      "metadata": {
+        "id": "2e7a075c"
+      },
+      "source": [
+        "## Prompt Template\n",
+        "\n",
+        "This instructs the agent on what to do. Generally, the template should incorporate:\n",
+        "    \n",
+        "- `tools`: which tools the agent has access and how and when to call them.\n",
+        "- `intermediate_steps`: These are tuples of previous (`AgentAction`, `Observation`) pairs. These are generally not passed directly to the model, but the prompt template formats them in a specific way.\n",
+        "- `input`: generic user input"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "339b1bb8",
+      "metadata": {
+        "id": "339b1bb8"
+      },
+      "outputs": [],
+      "source": [
+        "# Set up the base template\n",
+        "template = \"\"\"Complete the objective as best you can. You have access to the following tools:\n",
+        "\n",
+        "{tools}\n",
+        "\n",
+        "Use the following format:\n",
+        "\n",
+        "Question: the input question you must answer\n",
+        "Thought: you should always think about what to do\n",
+        "Action: the action to take, should be one of [{tool_names}]\n",
+        "Action Input: the input to the action\n",
+        "Observation: the result of the action\n",
+        "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
+        "Thought: I now know the final answer\n",
+        "Final Answer: the final answer to the original input question\n",
+        "\n",
+        "These were previous tasks you completed:\n",
+        "\n",
+        "\n",
+        "\n",
+        "Begin!\n",
+        "\n",
+        "Question: {input}\n",
+        "{agent_scratchpad}\"\"\""
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "id": "fd969d31",
+      "metadata": {
+        "id": "fd969d31"
+      },
+      "outputs": [],
+      "source": [
+        "# Set up a prompt template\n",
+        "class CustomPromptTemplate(BaseChatPromptTemplate):\n",
+        "    # The template to use\n",
+        "    template: str\n",
+        "    # The list of tools available\n",
+        "    tools: List[Tool]\n",
+        "    \n",
+        "    def format_messages(self, **kwargs) -> str:\n",
+        "        # Get the intermediate steps (AgentAction, Observation tuples)\n",
+        "        # Format them in a particular way\n",
+        "        intermediate_steps = kwargs.pop(\"intermediate_steps\")\n",
+        "        thoughts = \"\"\n",
+        "        for action, observation in intermediate_steps:\n",
+        "            thoughts += action.log\n",
+        "            thoughts += f\"\\nObservation: {observation}\\nThought: \"\n",
+        "        # Set the agent_scratchpad variable to that value\n",
+        "        kwargs[\"agent_scratchpad\"] = thoughts\n",
+        "        # Create a tools variable from the list of tools provided\n",
+        "        kwargs[\"tools\"] = \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in self.tools])\n",
+        "        # Create a list of tool names for the tools provided\n",
+        "        kwargs[\"tool_names\"] = \", \".join([tool.name for tool in self.tools])\n",
+        "        formatted = self.template.format(**kwargs)\n",
+        "        return [HumanMessage(content=formatted)]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "798ef9fb",
+      "metadata": {
+        "id": "798ef9fb"
+      },
+      "outputs": [],
+      "source": [
+        "prompt = CustomPromptTemplate(\n",
+        "    template=template,\n",
+        "    tools=tools,\n",
+        "    # This omits the `agent_scratchpad`, `tools`, and `tool_names` variables because those are generated dynamically\n",
+        "    # This includes the `intermediate_steps` variable because that is needed\n",
+        "    input_variables=[\"input\", \"intermediate_steps\"]\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "ef3a1af3",
+      "metadata": {
+        "id": "ef3a1af3"
+      },
+      "source": [
+        "## Output Parser\n",
+        "\n",
+        "The output parser is responsible for parsing the LLM output into `AgentAction` and `AgentFinish`. This usually depends heavily on the prompt used.\n",
+        "\n",
+        "This is where you can change the parsing to do retries, handle whitespace, etc"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "7c6fe0d3",
+      "metadata": {
+        "id": "7c6fe0d3"
+      },
+      "outputs": [],
+      "source": [
+        "class CustomOutputParser(AgentOutputParser):\n",
+        "    \n",
+        "    def parse(self, llm_output: str) -> Union[AgentAction, AgentFinish]:\n",
+        "        # Check if agent should finish\n",
+        "        if \"Final Answer:\" in llm_output:\n",
+        "            return AgentFinish(\n",
+        "                # Return values is generally always a dictionary with a single `output` key\n",
+        "                # It is not recommended to try anything else at the moment :)\n",
+        "                return_values={\"output\": llm_output.split(\"Final Answer:\")[-1].strip()},\n",
+        "                log=llm_output,\n",
+        "            )\n",
+        "        # Parse out the action and action input\n",
+        "        regex = r\"Action\\s*\\d*\\s*:(.*?)\\nAction\\s*\\d*\\s*Input\\s*\\d*\\s*:[\\s]*(.*)\"\n",
+        "        match = re.search(regex, llm_output, re.DOTALL)\n",
+        "        if not match:\n",
+        "            raise ValueError(f\"Could not parse LLM output: `{llm_output}`\")\n",
+        "        action = match.group(1).strip()\n",
+        "        action_input = match.group(2)\n",
+        "        # Return the action and action input\n",
+        "        return AgentAction(tool=action, tool_input=action_input.strip(\" \").strip('\"'), log=llm_output)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "d278706a",
+      "metadata": {
+        "id": "d278706a"
+      },
+      "outputs": [],
+      "source": [
+        "output_parser = CustomOutputParser()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "170587b1",
+      "metadata": {
+        "id": "170587b1"
+      },
+      "source": [
+        "## Set up LLM\n",
+        "\n",
+        "Choose the LLM you want to use!"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "OPENAI_API_KEY = getpass()"
+      ],
+      "metadata": {
+        "id": "V8UM02AfGyYa"
+      },
+      "id": "V8UM02AfGyYa",
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "f9d4c374",
+      "metadata": {
+        "id": "f9d4c374"
+      },
+      "outputs": [],
+      "source": [
+        "llm = ChatOpenAI(openai_api_key=OPENAI_API_KEY, temperature=0)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "caeab5e4",
+      "metadata": {
+        "id": "caeab5e4"
+      },
+      "source": [
+        "## Define the stop sequence\n",
+        "\n",
+        "This is important because it tells the LLM when to stop generation.\n",
+        "\n",
+        "This depends heavily on the prompt and model you are using. Generally, you want this to be whatever token you use in the prompt to denote the start of an `Observation` (otherwise, the LLM may hallucinate an observation for you)."
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "34be9f65",
+      "metadata": {
+        "id": "34be9f65"
+      },
+      "source": [
+        "## Set up the Agent\n",
+        "\n",
+        "We can now combine everything to set up our agent"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "id": "9b1cc2a2",
+      "metadata": {
+        "id": "9b1cc2a2"
+      },
+      "outputs": [],
+      "source": [
+        "# LLM chain consisting of the LLM and a prompt\n",
+        "llm_chain = LLMChain(llm=llm, prompt=prompt)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "id": "e4f5092f",
+      "metadata": {
+        "id": "e4f5092f"
+      },
+      "outputs": [],
+      "source": [
+        "tool_names = [tool.name for tool in tools]\n",
+        "agent = LLMSingleActionAgent(\n",
+        "    llm_chain=llm_chain, \n",
+        "    output_parser=output_parser,\n",
+        "    stop=[\"\\nObservation:\"], \n",
+        "    allowed_tools=tool_names\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "aa8a5326",
+      "metadata": {
+        "id": "aa8a5326"
+      },
+      "source": [
+        "## Use the Agent\n",
+        "\n",
+        "Now we can use it!"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "id": "490604e9",
+      "metadata": {
+        "id": "490604e9"
+      },
+      "outputs": [],
+      "source": [
+        "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "id": "653b1617",
+      "metadata": {
+        "id": "653b1617",
+        "outputId": "82f7dc8f-c09f-46f3-ae45-9acf7e4e3d94",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 264
+        }
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "\n",
+            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3mThought: I should use a reliable search engine to get accurate information.\n",
+            "Action: Search\n",
+            "Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
+            "\n",
+            "Observation:\u001b[36;1m\u001b[1;3mHe went on to date Gisele Bündchen, Bar Refaeli, Blake Lively, Toni Garrn and Nina Agdal, among others, before finally settling down with current girlfriend Camila Morrone, who is 23 years his junior.\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3mI have found the answer to the question.\n",
+            "Final Answer: Leo DiCaprio's current girlfriend is Camila Morrone.\u001b[0m\n",
+            "\n",
+            "\u001b[1m> Finished chain.\u001b[0m\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "\"Leo DiCaprio's current girlfriend is Camila Morrone.\""
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 15
+        }
+      ],
+      "source": [
+        "agent_executor.run(\"Search for Leo DiCaprio's girlfriend on the internet.\")"
      ]
-     },
-     "execution_count": 21,
-     "metadata": {},
-     "output_type": "execute_result"
    }
-   ],
-   "source": [
-    "agent_executor.run(\"Search for Leo DiCaprio's girlfriend on the internet.\")"
-   ]
+  ],
+  "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": "3.9.1"
+    },
+    "vscode": {
+      "interpreter": {
+        "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
+      }
+    },
+    "colab": {
+      "provenance": []
+    }
  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "adefb4c2",
-   "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": "3.9.1"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }
--- a/docs/modules/agents/agents/custom_multi_action_agent.ipynb
+++ b/docs/modules/agents/agents/custom_multi_action_agent.ipynb
@@ -9,7 +9,7 @@
    "\n",
    "This notebook goes through how to create your own custom agent.\n",
    "\n",
-    "An agent consists of three parts:\n",
+    "An agent consists of two parts:\n",
    "    \n",
    "    - Tools: The tools the agent has available to use.\n",
    "    - The agent class itself: this decides which action to take.\n",
--- a/docs/modules/agents/agents/examples/chat_conversation_agent.ipynb
+++ b/docs/modules/agents/agents/examples/chat_conversation_agent.ipynb
@@ -1,386 +1,383 @@
 {
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "4658d71a",
-   "metadata": {},
-   "source": [
-    "# Conversation Agent (for Chat Models)\n",
-    "\n",
-    "This notebook walks through using an agent optimized for conversation, using ChatModels. 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",
-    "\n",
-    "This is accomplished with a specific type of agent (`chat-conversational-react-description`) which expects to be used with a memory component."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "f4f5d1a8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "f65308ab",
-   "metadata": {},
-   "outputs": [
+  "cells": [
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:Failed to default session, using empty session: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /sessions (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x10a1767c0>: Failed to establish a new connection: [Errno 61] Connection refused'))\n"
-     ]
-    }
-   ],
-   "source": [
-    "from langchain.agents import Tool\n",
-    "from langchain.memory import ConversationBufferMemory\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "from langchain.utilities import SerpAPIWrapper\n",
-    "from langchain.agents import initialize_agent\n",
-    "from langchain.agents import AgentType"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "5fb14d6d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "search = SerpAPIWrapper()\n",
-    "tools = [\n",
-    "    Tool(\n",
-    "        name = \"Current Search\",\n",
-    "        func=search.run,\n",
-    "        description=\"useful for when you need to answer questions about current events or the current state of the world. the input to this should be a single search term.\"\n",
-    "    ),\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "dddc34c4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "cafe9bc1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm=ChatOpenAI(temperature=0)\n",
-    "agent_chain = initialize_agent(tools, llm, agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "dc70b454",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:Failed to persist run: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /chain-runs (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x13fab40d0>: Failed to establish a new connection: [Errno 61] Connection refused'))\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32;1m\u001b[1;3m{\n",
-      "    \"action\": \"Final Answer\",\n",
-      "    \"action_input\": \"Hello Bob! How can I assist you today?\"\n",
-      "}\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Hello Bob! How can I assist you today?'"
+      "cell_type": "markdown",
+      "id": "4658d71a",
+      "metadata": {
+        "id": "4658d71a"
+      },
+      "source": [
+        "# Conversation Agent (for Chat Models)\n",
+        "\n",
+        "This notebook walks through using an agent optimized for conversation, using ChatModels. 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",
+        "\n",
+        "This is accomplished with a specific type of agent (`chat-conversational-react-description`) which expects to be used with a memory component."
      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_chain.run(input=\"hi, i am bob\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "3dcf7953",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
-     ]
    },
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:Failed to persist run: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /chain-runs (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x13fab44f0>: Failed to establish a new connection: [Errno 61] Connection refused'))\n"
-     ]
+      "cell_type": "code",
+      "source": [
+        "!pip install langchain\n",
+        "!pip install google-search-results\n",
+        "!pip install openai"
+      ],
+      "metadata": {
+        "id": "efpRpEwvNXU5"
+      },
+      "id": "efpRpEwvNXU5",
+      "execution_count": null,
+      "outputs": []
    },
    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32;1m\u001b[1;3m{\n",
-      "    \"action\": \"Final Answer\",\n",
-      "    \"action_input\": \"Your name is Bob.\"\n",
-      "}\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Your name is Bob.'"
+      "cell_type": "code",
+      "execution_count": 2,
+      "id": "f65308ab",
+      "metadata": {
+        "id": "f65308ab"
+      },
+      "outputs": [],
+      "source": [
+        "from langchain.agents import Tool\n",
+        "from langchain.memory import ConversationBufferMemory\n",
+        "from langchain.chat_models import ChatOpenAI\n",
+        "from langchain.utilities import SerpAPIWrapper\n",
+        "from langchain.agents import initialize_agent\n",
+        "from langchain.agents import AgentType\n",
+        "from getpass import getpass"
      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_chain.run(input=\"what's my name?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "aa05f566",
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m{\n",
-      "    \"action\": \"Current Search\",\n",
-      "    \"action_input\": \"Thai food dinner recipes\"\n",
-      "}\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m59 easy Thai recipes for any night of the week · Marion Grasby's Thai spicy chilli and basil fried rice · Thai curry noodle soup · Marion Grasby's Thai Spicy ...\u001b[0m\n",
-      "Thought:"
-     ]
    },
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:Failed to persist run: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /chain-runs (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x13fae8be0>: Failed to establish a new connection: [Errno 61] Connection refused'))\n"
-     ]
+      "cell_type": "code",
+      "source": [
+        "SERPAPI_API_KEY = getpass()"
+      ],
+      "metadata": {
+        "id": "qMOoW5QYNlPQ"
+      },
+      "id": "qMOoW5QYNlPQ",
+      "execution_count": null,
+      "outputs": []
    },
    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32;1m\u001b[1;3m{\n",
-      "    \"action\": \"Final Answer\",\n",
-      "    \"action_input\": \"Here are some Thai food dinner recipes you can make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and Thai Spicy ... (59 recipes in total).\"\n",
-      "}\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'Here are some Thai food dinner recipes you can make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and Thai Spicy ... (59 recipes in total).'"
+      "cell_type": "code",
+      "execution_count": 4,
+      "id": "5fb14d6d",
+      "metadata": {
+        "id": "5fb14d6d"
+      },
+      "outputs": [],
+      "source": [
+        "search = SerpAPIWrapper(serpapi_api_key=SERPAPI_API_KEY)\n",
+        "tools = [\n",
+        "    Tool(\n",
+        "        name = \"Current Search\",\n",
+        "        func=search.run,\n",
+        "        description=\"useful for when you need to answer questions about current events or the current state of the world. the input to this should be a single search term.\"\n",
+        "    ),\n",
+        "]"
      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_chain.run(\"what are some good dinners to make this week, if i like thai food?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "c5d8b7ea",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m```json\n",
-      "{\n",
-      "    \"action\": \"Current Search\",\n",
-      "    \"action_input\": \"who won the world cup in 1978\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mArgentina national football team\u001b[0m\n",
-      "Thought:"
-     ]
    },
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:Failed to persist run: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /chain-runs (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x13fae86d0>: Failed to establish a new connection: [Errno 61] Connection refused'))\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32;1m\u001b[1;3m```json\n",
-      "{\n",
-      "    \"action\": \"Final Answer\",\n",
-      "    \"action_input\": \"The last letter in your name is 'b', and the winner of the 1978 World Cup was the Argentina national football team.\"\n",
-      "}\n",
-      "```\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"The last letter in your name is 'b', and the winner of the 1978 World Cup was the Argentina national football team.\""
+      "cell_type": "code",
+      "execution_count": 5,
+      "id": "dddc34c4",
+      "metadata": {
+        "id": "dddc34c4"
+      },
+      "outputs": [],
+      "source": [
+        "memory = ConversationBufferMemory(memory_key=\"chat_history\", return_messages=True)"
      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_chain.run(input=\"tell me the last letter in my name, and also tell me who won the world cup in 1978?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "f608889b",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3m{\n",
-      "    \"action\": \"Current Search\",\n",
-      "    \"action_input\": \"weather in pomfret\"\n",
-      "}\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m10 Day Weather-Pomfret, CT ; Sun 16. 64° · 50°. 24% · NE 7 mph ; Mon 17. 58° · 45°. 70% · ESE 8 mph ; Tue 18. 57° · 37°. 8% · WSW 15 mph.\u001b[0m\n",
-      "Thought:"
-     ]
    },
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "WARNING:root:Failed to persist run: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /chain-runs (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x13fa9d7f0>: Failed to establish a new connection: [Errno 61] Connection refused'))\n"
-     ]
+      "cell_type": "code",
+      "source": [
+        "OPENAI_API_KEY = getpass()"
+      ],
+      "metadata": {
+        "id": "pJWcpWnoN56_"
+      },
+      "id": "pJWcpWnoN56_",
+      "execution_count": null,
+      "outputs": []
    },
    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\u001b[32;1m\u001b[1;3m{\n",
-      "    \"action\": \"Final Answer\",\n",
-      "    \"action_input\": \"The weather in Pomfret, CT for the next 10 days is as follows: Sun 16. 64° · 50°. 24% · NE 7 mph ; Mon 17. 58° · 45°. 70% · ESE 8 mph ; Tue 18. 57° · 37°. 8% · WSW 15 mph.\"\n",
-      "}\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "'The weather in Pomfret, CT for the next 10 days is as follows: Sun 16. 64° · 50°. 24% · NE 7 mph ; Mon 17. 58° · 45°. 70% · ESE 8 mph ; Tue 18. 57° · 37°. 8% · WSW 15 mph.'"
+      "cell_type": "code",
+      "execution_count": 7,
+      "id": "cafe9bc1",
+      "metadata": {
+        "id": "cafe9bc1"
+      },
+      "outputs": [],
+      "source": [
+        "llm=ChatOpenAI(openai_api_key=OPENAI_API_KEY, temperature=0)\n",
+        "agent_chain = initialize_agent(tools, llm, agent=AgentType.CHAT_CONVERSATIONAL_REACT_DESCRIPTION, verbose=True, memory=memory)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "id": "dc70b454",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 192
+        },
+        "id": "dc70b454",
+        "outputId": "9e3d6857-72de-472f-b531-9a7b843f1621"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "\n",
+            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Final Answer\",\n",
+            "    \"action_input\": \"Hello Bob! How can I assist you today?\"\n",
+            "}\u001b[0m\n",
+            "\n",
+            "\u001b[1m> Finished chain.\u001b[0m\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'Hello Bob! How can I assist you today?'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 8
+        }
+      ],
+      "source": [
+        "agent_chain.run(input=\"hi, i am bob\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "id": "3dcf7953",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 192
+        },
+        "id": "3dcf7953",
+        "outputId": "9afdbf2c-ceed-4835-9975-0841dd2162d6"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "\n",
+            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Final Answer\",\n",
+            "    \"action_input\": \"Your name is Bob.\"\n",
+            "}\u001b[0m\n",
+            "\n",
+            "\u001b[1m> Finished chain.\u001b[0m\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'Your name is Bob.'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 9
+        }
+      ],
+      "source": [
+        "agent_chain.run(input=\"what's my name?\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "id": "aa05f566",
+      "metadata": {
+        "scrolled": false,
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 316
+        },
+        "id": "aa05f566",
+        "outputId": "d38fe468-6c94-450a-9f07-0044bf7beb34"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "\n",
+            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Current Search\",\n",
+            "    \"action_input\": \"Thai food dinner recipes\"\n",
+            "}\u001b[0m\n",
+            "Observation: \u001b[36;1m\u001b[1;3m64 easy Thai recipes for any night of the week · Thai curry noodle soup · Thai yellow cauliflower, snake bean and tofu curry · Thai-spiced chicken hand pies · Thai ...\u001b[0m\n",
+            "Thought:\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Final Answer\",\n",
+            "    \"action_input\": \"Here are some Thai food dinner recipes you can try this week: Thai curry noodle soup, Thai yellow cauliflower, snake bean and tofu curry, Thai-spiced chicken hand pies, and many more. You can find the full list of recipes at the source I found earlier.\"\n",
+            "}\u001b[0m\n",
+            "\n",
+            "\u001b[1m> Finished chain.\u001b[0m\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'Here are some Thai food dinner recipes you can try this week: Thai curry noodle soup, Thai yellow cauliflower, snake bean and tofu curry, Thai-spiced chicken hand pies, and many more. You can find the full list of recipes at the source I found earlier.'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 10
+        }
+      ],
+      "source": [
+        "agent_chain.run(\"what are some good dinners to make this week, if i like thai food?\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 11,
+      "id": "c5d8b7ea",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 192
+        },
+        "id": "c5d8b7ea",
+        "outputId": "105db01e-c0f7-4b82-edd9-ea02a02fc66a"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "\n",
+            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Final Answer\",\n",
+            "    \"action_input\": \"The last letter in your name is 'b'. Argentina won the World Cup in 1978.\"\n",
+            "}\u001b[0m\n",
+            "\n",
+            "\u001b[1m> Finished chain.\u001b[0m\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "\"The last letter in your name is 'b'. Argentina won the World Cup in 1978.\""
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 11
+        }
+      ],
+      "source": [
+        "agent_chain.run(input=\"tell me the last letter in my name, and also tell me who won the world cup in 1978?\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
+      "id": "f608889b",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 278
+        },
+        "id": "f608889b",
+        "outputId": "49ea0e17-d8cd-4de9-e119-e6006caea32f"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\n",
+            "\n",
+            "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+            "\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Current Search\",\n",
+            "    \"action_input\": \"weather in pomfret\"\n",
+            "}\u001b[0m\n",
+            "Observation: \u001b[36;1m\u001b[1;3mCloudy with showers. Low around 55F. Winds S at 5 to 10 mph. Chance of rain 60%. Humidity76%.\u001b[0m\n",
+            "Thought:\u001b[32;1m\u001b[1;3m{\n",
+            "    \"action\": \"Final Answer\",\n",
+            "    \"action_input\": \"Cloudy with showers. Low around 55F. Winds S at 5 to 10 mph. Chance of rain 60%. Humidity76%.\"\n",
+            "}\u001b[0m\n",
+            "\n",
+            "\u001b[1m> Finished chain.\u001b[0m\n"
+          ]
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "'Cloudy with showers. Low around 55F. Winds S at 5 to 10 mph. Chance of rain 60%. Humidity76%.'"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "string"
+            }
+          },
+          "metadata": {},
+          "execution_count": 12
+        }
+      ],
+      "source": [
+        "agent_chain.run(input=\"whats the weather like in pomfret?\")"
      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
    }
-   ],
-   "source": [
-    "agent_chain.run(input=\"whats the weather like in pomfret?\")"
-   ]
+  ],
+  "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": "3.9.1"
+    },
+    "colab": {
+      "provenance": []
+    }
  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "0084efd6",
-   "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": "3.9.1"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
+  "nbformat": 4,
+  "nbformat_minor": 5
 }
--- a/docs/modules/agents/agents/examples/mrkl.ipynb
+++ b/docs/modules/agents/agents/examples/mrkl.ipynb
@@ -42,7 +42,7 @@
    "search = SerpAPIWrapper()\n",
    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
    "db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
-    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
+    "db_chain = SQLDatabaseChain.from_llm(llm, db, verbose=True)\n",
    "tools = [\n",
    "    Tool(\n",
    "        name = \"Search\",\n",
--- a/docs/modules/agents/agents/examples/mrkl_chat.ipynb
+++ b/docs/modules/agents/agents/examples/mrkl_chat.ipynb
@@ -44,7 +44,7 @@
    "search = SerpAPIWrapper()\n",
    "llm_math_chain = LLMMathChain(llm=llm1, verbose=True)\n",
    "db = SQLDatabase.from_uri(\"sqlite:///../../../../../notebooks/Chinook.db\")\n",
-    "db_chain = SQLDatabaseChain(llm=llm1, database=db, verbose=True)\n",
+    "db_chain = SQLDatabaseChain.from_llm(llm1, db, verbose=True)\n",
    "tools = [\n",
    "    Tool(\n",
    "        name = \"Search\",\n",
--- a/docs/modules/agents/plan_and_execute.ipynb
+++ b/docs/modules/agents/plan_and_execute.ipynb
@@ -1,6 +1,7 @@
 {
 "cells": [
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "406483c4",
   "metadata": {},
@@ -15,6 +16,7 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "91192118",
   "metadata": {},
@@ -38,6 +40,7 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "0b10d200",
   "metadata": {},
@@ -70,6 +73,7 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "ce38ae84",
   "metadata": {},
@@ -114,10 +118,11 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "agent = PlanAndExecute(planner=planner, executer=executor, verbose=True)"
+    "agent = PlanAndExecute(planner=planner, executor=executor, verbose=True)"
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "id": "8be9f1bd",
   "metadata": {},
@@ -194,14 +199,18 @@
      "\n",
      "\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m28 years\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mBased on my search, Gigi Hadid's current age is 26 years old. \n",
+      "Thought:\u001b[32;1m\u001b[1;3mPrevious steps: steps=[(Step(value=\"Search for Leo DiCaprio's girlfriend on the internet.\"), StepResponse(response='Leo DiCaprio is currently linked to Gigi Hadid.')), (Step(value='Find her current age.'), StepResponse(response='28 years'))]\n",
+      "\n",
+      "Current objective: None\n",
+      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
-      "  \"action_input\": \"Gigi Hadid's current age is 26 years old.\"\n",
+      "  \"action_input\": \"Gigi Hadid's current age is 28 years.\"\n",
      "}\n",
      "```\n",
+      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
@@ -209,64 +218,39 @@
      "\n",
      "Step: Find her current age.\n",
      "\n",
-      "Response: Gigi Hadid's current age is 26 years old.\n",
+      "Response: Gigi Hadid's current age is 28 years.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Calculator\",\n",
-      "  \"action_input\": \"26 ** 0.43\"\n",
+      "  \"action_input\": \"28 ** 0.43\"\n",
      "}\n",
      "```\n",
-      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
-      "26 ** 0.43\u001b[32;1m\u001b[1;3m\n",
+      "28 ** 0.43\u001b[32;1m\u001b[1;3m\n",
      "```text\n",
-      "26 ** 0.43\n",
+      "28 ** 0.43\n",
      "```\n",
-      "...numexpr.evaluate(\"26 ** 0.43\")...\n",
+      "...numexpr.evaluate(\"28 ** 0.43\")...\n",
      "\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m4.059182145592686\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m4.1906168361987195\u001b[0m\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\n",
-      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.059182145592686\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe current objective is to raise Gigi Hadid's age to the 0.43 power. \n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"Calculator\",\n",
-      "  \"action_input\": \"26 ** 0.43\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
-      "26 ** 0.43\u001b[32;1m\u001b[1;3m\n",
-      "```text\n",
-      "26 ** 0.43\n",
-      "```\n",
-      "...numexpr.evaluate(\"26 ** 0.43\")...\n",
-      "\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m4.059182145592686\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.059182145592686\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe answer to the current objective is 4.059182145592686.\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.1906168361987195\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe next step is to provide the answer to the user's question.\n",
      "\n",
      "Action:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
-      "  \"action_input\": \"Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\"\n",
+      "  \"action_input\": \"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\"\n",
      "}\n",
      "```\n",
      "\n",
-      "\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
@@ -274,14 +258,14 @@
      "\n",
      "Step: Raise her current age to the 0.43 power using a calculator or programming language.\n",
      "\n",
-      "Response: Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\n",
+      "Response: Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
-      "  \"action_input\": \"Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\"\n",
+      "  \"action_input\": \"The result is approximately 4.19.\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
@@ -291,14 +275,14 @@
      "\n",
      "Step: Output the result.\n",
      "\n",
-      "Response: Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\n",
+      "Response: The result is approximately 4.19.\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mAction:\n",
      "```\n",
      "{\n",
      "  \"action\": \"Final Answer\",\n",
-      "  \"action_input\": \"Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\"\n",
+      "  \"action_input\": \"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\"\n",
      "}\n",
      "```\n",
      "\u001b[0m\n",
@@ -310,14 +294,14 @@
      "\n",
      "\n",
      "\n",
-      "Response: Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\n",
+      "Response: Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
-       "\"Gigi Hadid's age raised to the 0.43 power is approximately 4.059 years.\""
+       "\"Gigi Hadid's current age raised to the 0.43 power is approximately 4.19.\""
      ]
     },
     "execution_count": 10,
--- a/docs/modules/agents/streaming_stdout_final_only.ipynb
+++ b/docs/modules/agents/streaming_stdout_final_only.ipynb
@@ -0,0 +1,154 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "23234b50-e6c6-4c87-9f97-259c15f36894",
+   "metadata": {
+    "tags": []
+   },
+   "source": [
+    "# Only streaming final agent output"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "29dd6333-307c-43df-b848-65001c01733b",
+   "metadata": {},
+   "source": [
+    "If you only want the final output of an agent to be streamed, you can use the callback ``FinalStreamingStdOutCallbackHandler``.\n",
+    "For this, the underlying LLM has to support streaming as well."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e4592215-6604-47e2-89ff-5db3af6d1e40",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.agents import load_tools\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents import AgentType\n",
+    "from langchain.callbacks.streaming_stdout_final_only import FinalStreamingStdOutCallbackHandler\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "19a813f7",
+   "metadata": {},
+   "source": [
+    "Let's create the underlying LLM with ``streaming = True`` and pass a new instance of ``FinalStreamingStdOutCallbackHandler``."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7fe81ef4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(streaming=True, callbacks=[FinalStreamingStdOutCallbackHandler()], temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ff45b85d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      " Konrad Adenauer became Chancellor of Germany in 1949, 74 years ago in 2023."
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Konrad Adenauer became Chancellor of Germany in 1949, 74 years ago in 2023.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tools = load_tools([\"wikipedia\", \"llm-math\"], llm=llm)\n",
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)\n",
+    "agent.run(\"It's 2023 now. How many years ago did Konrad Adenauer become Chancellor of Germany.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53a743b8",
+   "metadata": {},
+   "source": [
+    "### Handling custom answer prefixes"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "23602c62",
+   "metadata": {},
+   "source": [
+    "By default, we assume that the token sequence ``\"\\nFinal\", \" Answer\", \":\"`` indicates that the agent has reached an answers. We can, however, also pass a custom sequence to use as answer prefix."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "5662a638",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(\n",
+    "    streaming=True,\n",
+    "    callbacks=[FinalStreamingStdOutCallbackHandler(answer_prefix_tokens=[\"\\nThe\", \" answer\", \":\"])],\n",
+    "    temperature=0\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b1a96cc0",
+   "metadata": {},
+   "source": [
+    "Be aware you likely need to include whitespaces and new line characters in your token. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9278b522",
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
--- a/docs/modules/agents/toolkits/examples/azure_cognitive_services.ipynb
+++ b/docs/modules/agents/toolkits/examples/azure_cognitive_services.ipynb
@@ -0,0 +1,270 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Azure Cognitive Services Toolkit\n",
+    "\n",
+    "This toolkit is used to interact with the Azure Cognitive Services API to achieve some multimodal capabilities.\n",
+    "\n",
+    "Currently There are four tools bundled in this toolkit:\n",
+    "- 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."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "First, you need to set up an Azure account and create a Cognitive Services resource. You can follow the instructions [here](https://docs.microsoft.com/en-us/azure/cognitive-services/cognitive-services-apis-create-account?tabs=multiservice%2Cwindows) to create a resource. \n",
+    "\n",
+    "Then, you need to get the endpoint, key and region of your resource, and set them as environment variables. You can find them in the \"Keys and Endpoint\" page of your resource."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# !pip install --upgrade azure-ai-formrecognizer > /dev/null\n",
+    "# !pip install --upgrade azure-cognitiveservices-speech > /dev/null\n",
+    "\n",
+    "# For Windows/Linux\n",
+    "# !pip install --upgrade azure-ai-vision > /dev/null"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"sk-\"\n",
+    "os.environ[\"AZURE_COGS_KEY\"] = \"\"\n",
+    "os.environ[\"AZURE_COGS_ENDPOINT\"] = \"\"\n",
+    "os.environ[\"AZURE_COGS_REGION\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Create the Toolkit"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents.agent_toolkits import AzureCognitiveServicesToolkit\n",
+    "\n",
+    "toolkit = AzureCognitiveServicesToolkit()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Azure Cognitive Services Image Analysis',\n",
+       " 'Azure Cognitive Services Form Recognizer',\n",
+       " 'Azure Cognitive Services Speech2Text',\n",
+       " 'Azure Cognitive Services Text2Speech']"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "[tool.name for tool in toolkit.get_tools()]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use within an Agent"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI\n",
+    "from langchain.agents import initialize_agent, AgentType"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "agent = initialize_agent(\n",
+    "    tools=toolkit.get_tools(),\n",
+    "    llm=llm,\n",
+    "    agent=AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION,\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Azure Cognitive Services Image Analysis\",\n",
+      "  \"action_input\": \"https://images.openai.com/blob/9ad5a2ab-041f-475f-ad6a-b51899c50182/ingredients.png\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mCaption: a group of eggs and flour in bowls\n",
+      "Objects: Egg, Egg, Food\n",
+      "Tags: dairy, ingredient, indoor, thickening agent, food, mixing bowl, powder, flour, egg, bowl\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I can use the objects and tags to suggest recipes\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Final Answer\",\n",
+      "  \"action_input\": \"You can make pancakes, omelettes, or quiches with these ingredients!\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'You can make pancakes, omelettes, or quiches with these ingredients!'"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"What can I make with these ingredients?\"\n",
+    "          \"https://images.openai.com/blob/9ad5a2ab-041f-475f-ad6a-b51899c50182/ingredients.png\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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 Text2Speech\",\n",
+      "  \"action_input\": \"Why did the chicken cross the playground? To get to the other slide!\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[31;1m\u001b[1;3m/tmp/tmpa3uu_j6b.wav\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I have the audio file of the joke\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Final Answer\",\n",
+      "  \"action_input\": \"/tmp/tmpa3uu_j6b.wav\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/tmp/tmpa3uu_j6b.wav'"
+      ]
+     },
+     "execution_count": null,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "audio_file = agent.run(\"Tell me a joke and read it out for me.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from IPython import display\n",
+    "\n",
+    "audio = display.Audio(audio_file)\n",
+    "display.display(audio)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "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": "3.11.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--- a/docs/modules/agents/toolkits/examples/powerbi.ipynb
+++ b/docs/modules/agents/toolkits/examples/powerbi.ipynb
@@ -1,10 +1,7 @@
 {
 "cells": [
  {
-   "attachments": {},
   "cell_type": "markdown",
-   "id": "0e499e90-7a6d-4fab-8aab-31a4df417601",
-   "metadata": {},
   "source": [
    "# PowerBI Dataset Agent\n",
    "\n",
@@ -17,46 +14,41 @@
    "- You can also supply a username to impersonate for use with datasets that have RLS enabled. \n",
    "- The toolkit uses a LLM to create the query from the question, the agent uses the LLM for the overall execution.\n",
    "- Testing was done mostly with a `text-davinci-003` model, codex models did not seem to perform ver well."
-   ]
+   ],
+   "metadata": {},
+   "attachments": {}
  },
  {
   "cell_type": "markdown",
-   "id": "ec927ac6-9b2a-4e8a-9a6e-3e429191875c",
-   "metadata": {
-    "tags": []
-   },
   "source": [
    "## Initialization"
-   ]
+   ],
+   "metadata": {
+    "tags": []
+   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "53422913-967b-4f2a-8022-00269c1be1b1",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
   "source": [
    "from langchain.agents.agent_toolkits import create_pbi_agent\n",
    "from langchain.agents.agent_toolkits import PowerBIToolkit\n",
    "from langchain.utilities.powerbi import PowerBIDataset\n",
-    "from langchain.llms.openai import AzureOpenAI\n",
+    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.agents import AgentExecutor\n",
    "from azure.identity import DefaultAzureCredential"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {
+    "tags": []
+   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "090f3699-79c6-4ce1-ab96-a94f0121fd64",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
   "source": [
-    "fast_llm = AzureOpenAI(temperature=0.5, max_tokens=1000, deployment_name=\"gpt-35-turbo\", verbose=True)\n",
-    "smart_llm = AzureOpenAI(temperature=0, max_tokens=100, deployment_name=\"gpt-4\", verbose=True)\n",
+    "fast_llm = ChatOpenAI(temperature=0.5, max_tokens=1000, model_name=\"gpt-3.5-turbo\", verbose=True)\n",
+    "smart_llm = ChatOpenAI(temperature=0, max_tokens=100, model_name=\"gpt-4\", verbose=True)\n",
    "\n",
    "toolkit = PowerBIToolkit(\n",
    "    powerbi=PowerBIDataset(dataset_id=\"<dataset_id>\", table_names=['table1', 'table2'], credential=DefaultAzureCredential()), \n",
@@ -68,97 +60,90 @@
    "    toolkit=toolkit,\n",
    "    verbose=True,\n",
    ")"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {
+    "tags": []
+   }
  },
  {
   "cell_type": "markdown",
-   "id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
-   "metadata": {},
   "source": [
    "## Example: describing a table"
-   ]
+   ],
+   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
   "source": [
    "agent_executor.run(\"Describe table1\")"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {
+    "tags": []
+   }
  },
  {
-   "attachments": {},
   "cell_type": "markdown",
-   "id": "9abcfe8e-1868-42a4-8345-ad2d9b44c681",
-   "metadata": {},
   "source": [
    "## Example: simple query on a table\n",
    "In this example, the agent actually figures out the correct query to get a row count of the table."
-   ]
+   ],
+   "metadata": {},
+   "attachments": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "bea76658-a65b-47e2-b294-6d52c5556246",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
   "source": [
    "agent_executor.run(\"How many records are in table1?\")"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {
+    "tags": []
+   }
  },
  {
   "cell_type": "markdown",
-   "id": "6fbc26af-97e4-4a21-82aa-48bdc992da26",
-   "metadata": {},
   "source": [
    "## Example: running queries"
-   ]
+   ],
+   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "17bea710-4a23-4de0-b48e-21d57be48293",
-   "metadata": {
-    "tags": []
-   },
-   "outputs": [],
   "source": [
    "agent_executor.run(\"How many records are there by dimension1 in table2?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "474dddda-c067-4eeb-98b1-e763ee78b18c",
+   ],
+   "outputs": [],
   "metadata": {
    "tags": []
-   },
-   "outputs": [],
-   "source": [
-    "agent_executor.run(\"What unique values are there for dimensions2 in table2\")"
-   ]
-  },
-  {
-   "attachments": {},
-   "cell_type": "markdown",
-   "id": "6fd950e4",
-   "metadata": {},
-   "source": [
-    "## Example: add your own few-shot prompts"
-   ]
+   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "87d677f9",
-   "metadata": {},
+   "source": [
+    "agent_executor.run(\"What unique values are there for dimensions2 in table2\")"
+   ],
   "outputs": [],
+   "metadata": {
+    "tags": []
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Example: add your own few-shot prompts"
+   ],
+   "metadata": {},
+   "attachments": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
   "source": [
    "#fictional example\n",
    "few_shots = \"\"\"\n",
@@ -182,24 +167,24 @@
    "    toolkit=toolkit,\n",
    "    verbose=True,\n",
    ")"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {}
  },
  {
   "cell_type": "code",
   "execution_count": null,
-   "id": "33f4bb43",
-   "metadata": {},
-   "outputs": [],
   "source": [
    "agent_executor.run(\"What was the maximum of value in revenue in dollars in 2022?\")"
-   ]
+   ],
+   "outputs": [],
+   "metadata": {}
  }
 ],
 "metadata": {
  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
+   "name": "python3",
+   "display_name": "Python 3.9.16 64-bit"
  },
  "language_info": {
   "codemirror_mode": {
@@ -211,9 +196,12 @@
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
-   "version": "3.10.5"
+   "version": "3.9.16"
+  },
+  "interpreter": {
+   "hash": "397704579725e15f5c7cb49fe5f0341eb7531c82d19f2c29d197e8b64ab5776b"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
-}
+}
--- a/docs/modules/agents/toolkits/examples/spark.ipynb
+++ b/docs/modules/agents/toolkits/examples/spark.ipynb
@@ -1,6 +1,7 @@
 {
 "cells": [
  {
+   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
@@ -17,7 +18,6 @@
   "metadata": {},
   "outputs": [],
   "source": [
-    "from langchain.agents import create_spark_dataframe_agent\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"...input your openai api key here...\""
@@ -25,9 +25,20 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 2,
   "metadata": {},
   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "23/05/15 20:33:10 WARN Utils: Your hostname, Mikes-Mac-mini.local resolves to a loopback address: 127.0.0.1; using 192.168.68.115 instead (on interface en1)\n",
+      "23/05/15 20:33:10 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address\n",
+      "Setting default log level to \"WARN\".\n",
+      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
+      "23/05/15 20:33:10 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
+     ]
+    },
    {
     "name": "stdout",
     "output_type": "stream",
@@ -64,6 +75,7 @@
   "source": [
    "from langchain.llms import OpenAI\n",
    "from pyspark.sql import SparkSession\n",
+    "from langchain.agents import create_spark_dataframe_agent\n",
    "\n",
    "spark = SparkSession.builder.getOrCreate()\n",
    "csv_file_path = \"titanic.csv\"\n",
@@ -92,7 +104,7 @@
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to find out the size of the dataframe\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out how many rows are in the dataframe\n",
      "Action: python_repl_ast\n",
      "Action Input: df.count()\u001b[0m\n",
      "Observation: \u001b[36;1m\u001b[1;3m891\u001b[0m\n",
@@ -205,7 +217,7 @@
  },
  {
   "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
@@ -213,6 +225,7 @@
   ]
  },
  {
+   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
--- a/docs/modules/agents/toolkits/examples/spark_sql.ipynb
+++ b/docs/modules/agents/toolkits/examples/spark_sql.ipynb
@@ -0,0 +1,348 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Spark SQL Agent\n",
+    "\n",
+    "This notebook shows how to use agents to interact with a Spark SQL. Similar to [SQL Database Agent](https://python.langchain.com/en/latest/modules/agents/toolkits/examples/sql_database.html), it is designed to address general inquiries about Spark SQL and facilitate error recovery.\n",
+    "\n",
+    "**NOTE: Note that, as this agent is in active development, all answers might not be correct. Additionally, it is not guaranteed that the agent won't perform DML statements on your Spark cluster given certain questions. Be careful running it on sensitive data!**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Initialization"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import create_spark_sql_agent\n",
+    "from langchain.agents.agent_toolkits import SparkSQLToolkit\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.utilities.spark_sql import SparkSQL"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Setting default log level to \"WARN\".\n",
+      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
+      "23/05/18 16:03:10 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
+      "|PassengerId|Survived|Pclass|                Name|   Sex| Age|SibSp|Parch|          Ticket|   Fare|Cabin|Embarked|\n",
+      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
+      "|          1|       0|     3|Braund, Mr. Owen ...|  male|22.0|    1|    0|       A/5 21171|   7.25| null|       S|\n",
+      "|          2|       1|     1|Cumings, Mrs. Joh...|female|38.0|    1|    0|        PC 17599|71.2833|  C85|       C|\n",
+      "|          3|       1|     3|Heikkinen, Miss. ...|female|26.0|    0|    0|STON/O2. 3101282|  7.925| null|       S|\n",
+      "|          4|       1|     1|Futrelle, Mrs. Ja...|female|35.0|    1|    0|          113803|   53.1| C123|       S|\n",
+      "|          5|       0|     3|Allen, Mr. Willia...|  male|35.0|    0|    0|          373450|   8.05| null|       S|\n",
+      "|          6|       0|     3|    Moran, Mr. James|  male|null|    0|    0|          330877| 8.4583| null|       Q|\n",
+      "|          7|       0|     1|McCarthy, Mr. Tim...|  male|54.0|    0|    0|           17463|51.8625|  E46|       S|\n",
+      "|          8|       0|     3|Palsson, Master. ...|  male| 2.0|    3|    1|          349909| 21.075| null|       S|\n",
+      "|          9|       1|     3|Johnson, Mrs. Osc...|female|27.0|    0|    2|          347742|11.1333| null|       S|\n",
+      "|         10|       1|     2|Nasser, Mrs. Nich...|female|14.0|    1|    0|          237736|30.0708| null|       C|\n",
+      "|         11|       1|     3|Sandstrom, Miss. ...|female| 4.0|    1|    1|         PP 9549|   16.7|   G6|       S|\n",
+      "|         12|       1|     1|Bonnell, Miss. El...|female|58.0|    0|    0|          113783|  26.55| C103|       S|\n",
+      "|         13|       0|     3|Saundercock, Mr. ...|  male|20.0|    0|    0|       A/5. 2151|   8.05| null|       S|\n",
+      "|         14|       0|     3|Andersson, Mr. An...|  male|39.0|    1|    5|          347082| 31.275| null|       S|\n",
+      "|         15|       0|     3|Vestrom, Miss. Hu...|female|14.0|    0|    0|          350406| 7.8542| null|       S|\n",
+      "|         16|       1|     2|Hewlett, Mrs. (Ma...|female|55.0|    0|    0|          248706|   16.0| null|       S|\n",
+      "|         17|       0|     3|Rice, Master. Eugene|  male| 2.0|    4|    1|          382652| 29.125| null|       Q|\n",
+      "|         18|       1|     2|Williams, Mr. Cha...|  male|null|    0|    0|          244373|   13.0| null|       S|\n",
+      "|         19|       0|     3|Vander Planke, Mr...|female|31.0|    1|    0|          345763|   18.0| null|       S|\n",
+      "|         20|       1|     3|Masselmani, Mrs. ...|female|null|    0|    0|            2649|  7.225| null|       C|\n",
+      "+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+\n",
+      "only showing top 20 rows\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from pyspark.sql import SparkSession\n",
+    "\n",
+    "spark = SparkSession.builder.getOrCreate()\n",
+    "schema = \"langchain_example\"\n",
+    "spark.sql(f\"CREATE DATABASE IF NOT EXISTS {schema}\")\n",
+    "spark.sql(f\"USE {schema}\")\n",
+    "csv_file_path = \"titanic.csv\"\n",
+    "table = \"titanic\"\n",
+    "spark.read.csv(csv_file_path, header=True, inferSchema=True).write.saveAsTable(table)\n",
+    "spark.table(table).show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Note, you can also connect to Spark via Spark connect. For example:\n",
+    "# db = SparkSQL.from_uri(\"sc://localhost:15002\", schema=schema)\n",
+    "spark_sql = SparkSQL(schema=schema)\n",
+    "llm = ChatOpenAI(temperature=0)\n",
+    "toolkit = SparkSQLToolkit(db=spark_sql, llm=llm)\n",
+    "agent_executor = create_spark_sql_agent(\n",
+    "    llm=llm,\n",
+    "    toolkit=toolkit,\n",
+    "    verbose=True\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example: describing a table"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "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: list_tables_sql_db\n",
+      "Action Input: \u001B[0m\n",
+      "Observation: \u001B[38;5;200m\u001B[1;3mtitanic\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI found the titanic table. Now I need to get the schema and sample rows for the titanic table.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: titanic\u001B[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3mCREATE TABLE langchain_example.titanic (\n",
+      "  PassengerId INT,\n",
+      "  Survived INT,\n",
+      "  Pclass INT,\n",
+      "  Name STRING,\n",
+      "  Sex STRING,\n",
+      "  Age DOUBLE,\n",
+      "  SibSp INT,\n",
+      "  Parch INT,\n",
+      "  Ticket STRING,\n",
+      "  Fare DOUBLE,\n",
+      "  Cabin STRING,\n",
+      "  Embarked STRING)\n",
+      ";\n",
+      "\n",
+      "/*\n",
+      "3 rows from titanic table:\n",
+      "PassengerId\tSurvived\tPclass\tName\tSex\tAge\tSibSp\tParch\tTicket\tFare\tCabin\tEmbarked\n",
+      "1\t0\t3\tBraund, Mr. Owen Harris\tmale\t22.0\t1\t0\tA/5 21171\t7.25\tNone\tS\n",
+      "2\t1\t1\tCumings, Mrs. John Bradley (Florence Briggs Thayer)\tfemale\t38.0\t1\t0\tPC 17599\t71.2833\tC85\tC\n",
+      "3\t1\t3\tHeikkinen, Miss. Laina\tfemale\t26.0\t0\t0\tSTON/O2. 3101282\t7.925\tNone\tS\n",
+      "*/\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI now know the schema and sample rows for the titanic table.\n",
+      "Final Answer: The titanic table has the following columns: PassengerId (INT), Survived (INT), Pclass (INT), Name (STRING), Sex (STRING), Age (DOUBLE), SibSp (INT), Parch (INT), Ticket (STRING), Fare (DOUBLE), Cabin (STRING), and Embarked (STRING). Here are some sample rows from the table: \n",
+      "\n",
+      "1. PassengerId: 1, Survived: 0, Pclass: 3, Name: Braund, Mr. Owen Harris, Sex: male, Age: 22.0, SibSp: 1, Parch: 0, Ticket: A/5 21171, Fare: 7.25, Cabin: None, Embarked: S\n",
+      "2. PassengerId: 2, Survived: 1, Pclass: 1, Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer), Sex: female, Age: 38.0, SibSp: 1, Parch: 0, Ticket: PC 17599, Fare: 71.2833, Cabin: C85, Embarked: C\n",
+      "3. PassengerId: 3, Survived: 1, Pclass: 3, Name: Heikkinen, Miss. Laina, Sex: female, Age: 26.0, SibSp: 0, Parch: 0, Ticket: STON/O2. 3101282, Fare: 7.925, Cabin: None, Embarked: S\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'The titanic table has the following columns: PassengerId (INT), Survived (INT), Pclass (INT), Name (STRING), Sex (STRING), Age (DOUBLE), SibSp (INT), Parch (INT), Ticket (STRING), Fare (DOUBLE), Cabin (STRING), and Embarked (STRING). Here are some sample rows from the table: \\n\\n1. PassengerId: 1, Survived: 0, Pclass: 3, Name: Braund, Mr. Owen Harris, Sex: male, Age: 22.0, SibSp: 1, Parch: 0, Ticket: A/5 21171, Fare: 7.25, Cabin: None, Embarked: S\\n2. PassengerId: 2, Survived: 1, Pclass: 1, Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer), Sex: female, Age: 38.0, SibSp: 1, Parch: 0, Ticket: PC 17599, Fare: 71.2833, Cabin: C85, Embarked: C\\n3. PassengerId: 3, Survived: 1, Pclass: 3, Name: Heikkinen, Miss. Laina, Sex: female, Age: 26.0, SibSp: 0, Parch: 0, Ticket: STON/O2. 3101282, Fare: 7.925, Cabin: None, Embarked: S'"
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"Describe the titanic table\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Example: running queries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "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: list_tables_sql_db\n",
+      "Action Input: \u001B[0m\n",
+      "Observation: \u001B[38;5;200m\u001B[1;3mtitanic\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI should check the schema of the titanic table to see if there is an age column.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: titanic\u001B[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3mCREATE TABLE langchain_example.titanic (\n",
+      "  PassengerId INT,\n",
+      "  Survived INT,\n",
+      "  Pclass INT,\n",
+      "  Name STRING,\n",
+      "  Sex STRING,\n",
+      "  Age DOUBLE,\n",
+      "  SibSp INT,\n",
+      "  Parch INT,\n",
+      "  Ticket STRING,\n",
+      "  Fare DOUBLE,\n",
+      "  Cabin STRING,\n",
+      "  Embarked STRING)\n",
+      ";\n",
+      "\n",
+      "/*\n",
+      "3 rows from titanic table:\n",
+      "PassengerId\tSurvived\tPclass\tName\tSex\tAge\tSibSp\tParch\tTicket\tFare\tCabin\tEmbarked\n",
+      "1\t0\t3\tBraund, Mr. Owen Harris\tmale\t22.0\t1\t0\tA/5 21171\t7.25\tNone\tS\n",
+      "2\t1\t1\tCumings, Mrs. John Bradley (Florence Briggs Thayer)\tfemale\t38.0\t1\t0\tPC 17599\t71.2833\tC85\tC\n",
+      "3\t1\t3\tHeikkinen, Miss. Laina\tfemale\t26.0\t0\t0\tSTON/O2. 3101282\t7.925\tNone\tS\n",
+      "*/\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mThere is an Age column in the titanic table. I should write a query to calculate the average age and then find the square root of the result.\n",
+      "Action: query_checker_sql_db\n",
+      "Action Input: SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic\u001B[0m\n",
+      "Observation: \u001B[31;1m\u001B[1;3mThe original query seems to be correct. Here it is again:\n",
+      "\n",
+      "SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mThe query is correct, so I can execute it to find the square root of the average age.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3m[('5.449689683556195',)]\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI now know the final answer\n",
+      "Final Answer: The square root of the average age is approximately 5.45.\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'The square root of the average age is approximately 5.45.'"
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"whats the square root of the average age?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
+      "\u001B[32;1m\u001B[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \u001B[0m\n",
+      "Observation: \u001B[38;5;200m\u001B[1;3mtitanic\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI should check the schema of the titanic table to see what columns are available.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: titanic\u001B[0m\n",
+      "Observation: \u001B[33;1m\u001B[1;3mCREATE TABLE langchain_example.titanic (\n",
+      "  PassengerId INT,\n",
+      "  Survived INT,\n",
+      "  Pclass INT,\n",
+      "  Name STRING,\n",
+      "  Sex STRING,\n",
+      "  Age DOUBLE,\n",
+      "  SibSp INT,\n",
+      "  Parch INT,\n",
+      "  Ticket STRING,\n",
+      "  Fare DOUBLE,\n",
+      "  Cabin STRING,\n",
+      "  Embarked STRING)\n",
+      ";\n",
+      "\n",
+      "/*\n",
+      "3 rows from titanic table:\n",
+      "PassengerId\tSurvived\tPclass\tName\tSex\tAge\tSibSp\tParch\tTicket\tFare\tCabin\tEmbarked\n",
+      "1\t0\t3\tBraund, Mr. Owen Harris\tmale\t22.0\t1\t0\tA/5 21171\t7.25\tNone\tS\n",
+      "2\t1\t1\tCumings, Mrs. John Bradley (Florence Briggs Thayer)\tfemale\t38.0\t1\t0\tPC 17599\t71.2833\tC85\tC\n",
+      "3\t1\t3\tHeikkinen, Miss. Laina\tfemale\t26.0\t0\t0\tSTON/O2. 3101282\t7.925\tNone\tS\n",
+      "*/\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI can use the titanic table to find the oldest survived passenger. I will query the Name and Age columns, filtering by Survived and ordering by Age in descending order.\n",
+      "Action: query_checker_sql_db\n",
+      "Action Input: SELECT Name, Age FROM titanic WHERE Survived = 1 ORDER BY Age DESC LIMIT 1\u001B[0m\n",
+      "Observation: \u001B[31;1m\u001B[1;3mSELECT Name, Age FROM titanic WHERE Survived = 1 ORDER BY Age DESC LIMIT 1\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mThe query is correct. Now I will execute it to find the oldest survived passenger.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT Name, Age FROM titanic WHERE Survived = 1 ORDER BY Age DESC LIMIT 1\u001B[0m\n",
+      "Observation: \u001B[36;1m\u001B[1;3m[('Barkworth, Mr. Algernon Henry Wilson', '80.0')]\u001B[0m\n",
+      "Thought:\u001B[32;1m\u001B[1;3mI now know the final answer.\n",
+      "Final Answer: The oldest survived passenger is Barkworth, Mr. Algernon Henry Wilson, who was 80 years old.\u001B[0m\n",
+      "\n",
+      "\u001B[1m> Finished chain.\u001B[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": "'The oldest survived passenger is Barkworth, Mr. Algernon Henry Wilson, who was 80 years old.'"
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"What's the name of the oldest survived passenger?\")"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "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": "3.11.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--- a/docs/modules/agents/tools/examples/graphql.ipynb
+++ b/docs/modules/agents/tools/examples/graphql.ipynb
@@ -0,0 +1,149 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "\n",
+    "# GraphQL tool\n",
+    "This Jupyter Notebook demonstrates how to use the BaseGraphQLTool component with an Agent.\n",
+    "\n",
+    "GraphQL is a query language for APIs and a runtime for executing those queries against your data. GraphQL provides a complete and understandable description of the data in your API, gives clients the power to ask for exactly what they need and nothing more, makes it easier to evolve APIs over time, and enables powerful developer tools.\n",
+    "\n",
+    "By including a BaseGraphQLTool in the list of tools provided to an Agent, you can grant your Agent the ability to query data from GraphQL APIs for any purposes you need.\n",
+    "\n",
+    "In this example, we'll be using the public Star Wars GraphQL API available at the following endpoint: https://swapi-graphql.netlify.app/.netlify/functions/index.\n",
+    "\n",
+    "First, you need to install httpx and gql Python packages."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "vscode": {
+     "languageId": "shellscript"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "pip install httpx gql > /dev/null"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now, let's create a BaseGraphQLTool instance with the specified Star Wars API endpoint and initialize an Agent with the tool."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI\n",
+    "from langchain.agents import load_tools, initialize_agent, AgentType\n",
+    "from langchain.utilities import GraphQLAPIWrapper\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "\n",
+    "tools = load_tools([\"graphql\"], graphql_endpoint=\"https://swapi-graphql.netlify.app/.netlify/functions/index\", llm=llm)\n",
+    "\n",
+    "agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Now, we can use the Agent to run queries against the Star Wars GraphQL API. Let's ask the Agent to list all the Star Wars films and their release dates."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I need to query the graphql database to get the titles of all the star wars films\n",
+      "Action: query_graphql\n",
+      "Action Input: query { allFilms { films { title } } }\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m\"{\\n  \\\"allFilms\\\": {\\n    \\\"films\\\": [\\n      {\\n        \\\"title\\\": \\\"A New Hope\\\"\\n      },\\n      {\\n        \\\"title\\\": \\\"The Empire Strikes Back\\\"\\n      },\\n      {\\n        \\\"title\\\": \\\"Return of the Jedi\\\"\\n      },\\n      {\\n        \\\"title\\\": \\\"The Phantom Menace\\\"\\n      },\\n      {\\n        \\\"title\\\": \\\"Attack of the Clones\\\"\\n      },\\n      {\\n        \\\"title\\\": \\\"Revenge of the Sith\\\"\\n      }\\n    ]\\n  }\\n}\"\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the titles of all the star wars films\n",
+      "Final Answer: The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The titles of all the star wars films are: A New Hope, The Empire Strikes Back, Return of the Jedi, The Phantom Menace, Attack of the Clones, and Revenge of the Sith.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "graphql_fields = \"\"\"allFilms {\n",
+    "    films {\n",
+    "      title\n",
+    "      director\n",
+    "      releaseDate\n",
+    "      speciesConnection {\n",
+    "        species {\n",
+    "          name\n",
+    "          classification\n",
+    "          homeworld {\n",
+    "            name\n",
+    "          }\n",
+    "        }\n",
+    "      }\n",
+    "    }\n",
+    "  }\n",
+    "\n",
+    "\"\"\"\n",
+    "\n",
+    "suffix = \"Search for the titles of all the stawars films stored in the graphql database that has this schema \"\n",
+    "\n",
+    "\n",
+    "agent.run(suffix + graphql_fields)"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "f85209c3c4c190dca7367d6a1e623da50a9a4392fd53313a7cf9d4bda9c4b85b"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.9.16 ('langchain')",
+   "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": "3.9.16"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
--- a/docs/modules/agents/tools/examples/huggingface_tools.ipynb
+++ b/docs/modules/agents/tools/examples/huggingface_tools.ipynb
@@ -19,7 +19,7 @@
   "outputs": [],
   "source": [
    "# Requires transformers>=4.29.0 and huggingface_hub>=0.14.1\n",
-    "!pip install --uprade transformers huggingface_hub > /dev/null"
+    "!pip install --upgrade transformers huggingface_hub > /dev/null"
   ]
  },
  {
--- a/Show More
+++ b/Show More