bump version to 122 (#1970)

Ran into a broken build if bs4 wasn't installed in the project.

Minor tweak to follow the other doc loaders optional package-loading
conventions.

Also updated html docs to include reference to this new html loader.

side note: Should there be 2 different html-to-text document loaders?
This new one only handles local files, while the existing unstructured
html loader handles HTML from local and remote. So it seems like the
improvement was adding the title to the metadata, which is useful but
could also be added to `html.py`

.github/CONTRIBUTING.md

@@ -73,6 +73,8 @@ poetry install -E all
 
 This will install all requirements for running the package, examples, linting, formatting, tests, and coverage. Note the `-E all` flag will install all optional dependencies necessary for integration testing.
 
+❗Note: If you're running Poetry 1.4.1 and receive a `WheelFileValidationError` for `debugpy` during installation, you can try either downgrading to Poetry 1.4.0 or disabling "modern installation" (`poetry config installer.modern-installation false`) and re-install requirements. See [this `debugpy` issue](https://github.com/microsoft/debugpy/issues/1246) for more details.
+
 Now, you should be able to run the common tasks in the following section.
 
 ## ✅Common Tasks

.gitignore

@@ -135,3 +135,9 @@ dmypy.json
 
 # macOS display setting files
 .DS_Store
+
+# Wandb directory
+wandb/
+
+# asdf tool versions
+.tool-versions

README.md

@@ -79,4 +79,4 @@ For more information on these concepts, please see our [full documentation](http
 
 As an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.
 
-For detailed information on how to contribute, see [here](CONTRIBUTING.md).
+For detailed information on how to contribute, see [here](.github/CONTRIBUTING.md).

docs/conf.py

@@ -23,13 +23,14 @@ with open("../pyproject.toml") as f:
 # -- Project information -----------------------------------------------------
 
 project = "🦜🔗 LangChain"
-copyright = "2022, Harrison Chase"
+copyright = "2023, Harrison Chase"
 author = "Harrison Chase"
 
 version = data["tool"]["poetry"]["version"]
 release = version
 
 html_title = project + " " + version
+html_last_updated_fmt = "%b %d, %Y"
 
 
 # -- General configuration ---------------------------------------------------
@@ -45,6 +46,7 @@ extensions = [
     "sphinx.ext.viewcode",
     "sphinxcontrib.autodoc_pydantic",
     "myst_nb",
+    "sphinx_copybutton",
     "sphinx_panels",
     "IPython.sphinxext.ipython_console_highlighting",
 ]

docs/ecosystem/atlas.md

@@ -1,19 +1,21 @@
 # AtlasDB
 
-This page covers how to Nomic's Atlas ecosystem within LangChain.
+This page covers how to use Nomic's Atlas ecosystem within LangChain.
 It is broken into two parts: installation and setup, and then references to specific Atlas wrappers.
 
 ## Installation and Setup
 - Install the Python package with `pip install nomic`
 - Nomic is also included in langchains poetry extras `poetry install -E all`
-- 
+
 ## Wrappers
 
 ### VectorStore
 
 There exists a wrapper around the Atlas neural database, allowing you to use it as a vectorstore.
 This vectorstore also gives you full access to the underlying AtlasProject object, which will allow you to use the full range of Atlas map interactions, such as bulk tagging and automatic topic modeling.
-Please see [the Nomic docs](https://docs.nomic.ai/atlas_api.html) for more detailed information.
+Please see [the Atlas docs](https://docs.nomic.ai/atlas_api.html) for more detailed information.
+
+
 
 
 
@@ -22,4 +24,4 @@ To import this vectorstore:
 from langchain.vectorstores import AtlasDB
 ```
 
-For a more detailed walkthrough of the Chroma wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)
+For a more detailed walkthrough of the AtlasDB wrapper, see [this notebook](../modules/indexes/vectorstore_examples/atlas.ipynb)

docs/ecosystem/bananadev.md

@@ -5,7 +5,7 @@ It is broken into two parts: installation and setup, and then references to spec
 
 ## Installation and Setup
 
-- Install with `pip3 install banana-dev`
+- Install with `pip install banana-dev`
 - Get an Banana api key and set it as an environment variable (`BANANA_API_KEY`)
 
 ## Define your Banana Template

docs/ecosystem/google_serper.md

@@ -34,7 +34,8 @@ search = GoogleSerperAPIWrapper()
 tools = [
     Tool(
         name="Intermediate Answer",
-        func=search.run
+        func=search.run,
+        description="useful for when you need to ask with search"
     )
 ]
 

docs/ecosystem/graphsignal.md

@@ -1,6 +1,6 @@
 # Graphsignal
 
-This page covers how to use the Graphsignal to trace and monitor LangChain.
+This page covers how to use the Graphsignal ecosystem to trace and monitor LangChain.
 
 ## Installation and Setup
 

docs/ecosystem/helicone.md

@@ -1,6 +1,6 @@
 # Helicone
 
-This page covers how to use the [Helicone](https://helicone.ai) within LangChain.
+This page covers how to use the [Helicone](https://helicone.ai) ecosystem within LangChain.
 
 ## What is Helicone?
 

docs/ecosystem/milvus.md

@@ -0,0 +1,20 @@
+# Milvus
+
+This page covers how to use the Milvus ecosystem within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Milvus wrappers.
+
+## Installation and Setup
+- Install the Python SDK with `pip install pymilvus`
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Milvus indexes, allowing you to use it as a vectorstore,
+whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import Milvus
+```
+
+For a more detailed walkthrough of the Miluvs wrapper, see [this notebook](../modules/indexes/vectorstore_examples/milvus.ipynb)

docs/ecosystem/pgvector.md

@@ -0,0 +1,29 @@
+# PGVector
+
+This page covers how to use the Postgres [PGVector](https://github.com/pgvector/pgvector) ecosystem within LangChain
+It is broken into two parts: installation and setup, and then references to specific PGVector wrappers.
+
+## Installation
+- Install the Python package with `pip install pgvector`
+
+
+## Setup
+1. The first step is to create a database with the `pgvector` extension installed.
+
+    Follow the steps at [PGVector Installation Steps](https://github.com/pgvector/pgvector#installation) to install the database and the extension. The docker image is the easiest way to get started.
+
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Postgres vector databases, allowing you to use it as a vectorstore,
+whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores.pgvector import PGVector
+```
+
+### Usage
+
+For a more detailed walkthrough of the PGVector Wrapper, see [this notebook](../modules/indexes/vectorstore_examples/pgvector.ipynb)

docs/ecosystem/pinecone.md

@@ -17,4 +17,4 @@ To import this vectorstore:
 from langchain.vectorstores import Pinecone
 ```
 
-For a more detailed walkthrough of the Pinecone wrapper, see [this notebook](../modules/indexes/examples/vectorstores.ipynb)
+For a more detailed walkthrough of the Pinecone wrapper, see [this notebook](../modules/indexes/vectorstore_examples/pinecone.ipynb)

docs/ecosystem/promptlayer.md

@@ -25,7 +25,25 @@ from langchain.llms import PromptLayerOpenAI
 llm = PromptLayerOpenAI(pl_tags=["langchain-requests", "chatbot"])
 ```
 
+To get the PromptLayer request id, use the argument `return_pl_id` when instanializing the LLM
+```python
+from langchain.llms import PromptLayerOpenAI
+llm = PromptLayerOpenAI(return_pl_id=True)
+```
+This will add the PromptLayer request ID in the `generation_info` field of the `Generation` returned when using `.generate` or `.agenerate`
+
+For example:
+```python
+llm_results = llm.generate(["hello world"])
+for res in llm_results.generations:
+    print("pl request id: ", res[0].generation_info["pl_request_id"])
+```
+You can use the PromptLayer request ID to add a prompt, score, or other metadata to your request. [Read more about it here](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
+
 This LLM is identical to the [OpenAI LLM](./openai), except that
 - all your requests will be logged to your PromptLayer account
 - you can add `pl_tags` when instantializing to tag your requests on PromptLayer
+- you can add `return_pl_id` when instantializing to return a PromptLayer request id to use [while tracking requests](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9).
 
+
+PromptLayer also provides native wrappers for [`PromptLayerChatOpenAI`](../modules/chat/examples/promptlayer_chat_openai.ipynb) and `PromptLayerOpenAIChat`

docs/ecosystem/qdrant.md

@@ -0,0 +1,20 @@
+# Qdrant
+
+This page covers how to use the Qdrant ecosystem within LangChain.
+It is broken into two parts: installation and setup, and then references to specific Qdrant wrappers.
+
+## Installation and Setup
+- Install the Python SDK with `pip install qdrant-client`
+## Wrappers
+
+### VectorStore
+
+There exists a wrapper around Qdrant indexes, allowing you to use it as a vectorstore,
+whether for semantic search or example selection.
+
+To import this vectorstore:
+```python
+from langchain.vectorstores import Qdrant
+```
+
+For a more detailed walkthrough of the Qdrant wrapper, see [this notebook](../modules/indexes/vectorstore_examples/qdrant.ipynb)

docs/ecosystem/unstructured.md

@@ -17,9 +17,12 @@ This page is broken into two parts: installation and setup, and then references
     - `poppler-utils`
     - `tesseract-ocr`
     - `libreoffice`
-- If you are parsing PDFs, run the following to install the `detectron2` model, which
+- If you are parsing PDFs using the `"hi_res"` strategy, run the following to install the `detectron2` model, which
   `unstructured` uses for layout detection:
     - `pip install "detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2"`
+    - If `detectron2` is not installed, `unstructured` will fallback to processing PDFs
+      using the `"fast"` strategy, which uses `pdfminer` directly and doesn't require
+      `detectron2`.
 
 ## Wrappers
 

docs/ecosystem/wandb_tracking.ipynb

@@ -0,0 +1,625 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Weights & Biases\n",
+    "\n",
+    "This notebook goes over how to track your LangChain experiments into one centralized Weights and Biases dashboard. To learn more about prompt engineering and the callback please refer to this Report which explains both alongside the resultant dashboards you can expect to see.\n",
+    "\n",
+    "Run in Colab: https://colab.research.google.com/drive/1DXH4beT4HFaRKy_Vm4PoxhXVDRf7Ym8L?usp=sharing\n",
+    "\n",
+    "View Report: https://wandb.ai/a-sh0ts/langchain_callback_demo/reports/Prompt-Engineering-LLMs-with-LangChain-and-W-B--VmlldzozNjk1NTUw#👋-how-to-build-a-callback-in-langchain-for-better-prompt-engineering"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip install wandb\n",
+    "!pip install pandas\n",
+    "!pip install textstat\n",
+    "!pip install spacy\n",
+    "!python -m spacy download en_core_web_sm"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "T1bSmKd6V2If"
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "os.environ[\"WANDB_API_KEY\"] = \"\"\n",
+    "# os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
+    "# os.environ[\"SERPAPI_API_KEY\"] = \"\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "id": "8WAGnTWpUUnD"
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "from langchain.callbacks import WandbCallbackHandler, StdOutCallbackHandler\n",
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "```\n",
+    "Callback Handler that logs to Weights and Biases.\n",
+    "\n",
+    "Parameters:\n",
+    "    job_type (str): The type of job.\n",
+    "    project (str): The project to log to.\n",
+    "    entity (str): The entity to log to.\n",
+    "    tags (list): The tags to log.\n",
+    "    group (str): The group to log to.\n",
+    "    name (str): The name of the run.\n",
+    "    notes (str): The notes to log.\n",
+    "    visualize (bool): Whether to visualize the run.\n",
+    "    complexity_metrics (bool): Whether to log complexity metrics.\n",
+    "    stream_logs (bool): Whether to stream callback actions to W&B\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "cxBFfZR8d9FC"
+   },
+   "source": [
+    "```\n",
+    "Default values for WandbCallbackHandler(...)\n",
+    "\n",
+    "visualize: bool = False,\n",
+    "complexity_metrics: bool = False,\n",
+    "stream_logs: bool = False,\n",
+    "```\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "NOTE: For beta workflows we have made the default analysis based on textstat and the visualizations based on spacy"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "KAz8weWuUeXF"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mharrison-chase\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "Tracking run with wandb version 0.14.0"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150408-e47j1914</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">llm</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m The wandb callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/wandb/wandb/issues with the tag `langchain`.\n"
+     ]
+    }
+   ],
+   "source": [
+    "\"\"\"Main function.\n",
+    "\n",
+    "This function is used to try the callback handler.\n",
+    "Scenarios:\n",
+    "1. OpenAI LLM\n",
+    "2. Chain with multiple SubChains on multiple generations\n",
+    "3. Agent with Tools\n",
+    "\"\"\"\n",
+    "session_group = datetime.now().strftime(\"%m.%d.%Y_%H.%M.%S\")\n",
+    "wandb_callback = WandbCallbackHandler(\n",
+    "    job_type=\"inference\",\n",
+    "    project=\"langchain_callback_demo\",\n",
+    "    group=f\"minimal_{session_group}\",\n",
+    "    name=\"llm\",\n",
+    "    tags=[\"test\"],\n",
+    ")\n",
+    "manager = CallbackManager([StdOutCallbackHandler(), wandb_callback])\n",
+    "llm = OpenAI(temperature=0, callback_manager=manager, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "Q-65jwrDeK6w"
+   },
+   "source": [
+    "\n",
+    "\n",
+    "```\n",
+    "# Defaults for WandbCallbackHandler.flush_tracker(...)\n",
+    "\n",
+    "reset: bool = True,\n",
+    "finish: bool = False,\n",
+    "```\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "The `flush_tracker` function is used to log LangChain sessions to Weights & Biases. It takes in the LangChain module or agent, and logs at minimum the prompts and generations alongside the serialized form of the LangChain module to the specified Weights & Biases project. By default we reset the session as opposed to concluding the session outright."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "o_VmneyIUyx8"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run <strong style=\"color:#cdcd00\">llm</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/e47j1914</a><br/>Synced 5 W&B file(s), 2 media file(s), 5 artifact file(s) and 0 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find logs at: <code>./wandb/run-20230318_150408-e47j1914/logs</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0d7b4307ccdb450ea631497174fca2d1",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016745895149999985, max=1.0…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Tracking run with wandb version 0.14.0"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150534-jyxma7hu</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">simple_sequential</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# SCENARIO 1 - LLM\n",
+    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
+    "wandb_callback.flush_tracker(llm, name=\"simple_sequential\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "trxslyb1U28Y"
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.chains import LLMChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "uauQk10SUzF6"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run <strong style=\"color:#cdcd00\">simple_sequential</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/jyxma7hu</a><br/>Synced 4 W&B file(s), 2 media file(s), 6 artifact file(s) and 0 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find logs at: <code>./wandb/run-20230318_150534-jyxma7hu/logs</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "dbdbf28fb8ed40a3a60218d2e6d1a987",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "VBox(children=(Label(value='Waiting for wandb.init()...\\r'), FloatProgress(value=0.016736786816666675, max=1.0…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Tracking run with wandb version 0.14.0"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Run data is saved locally in <code>/Users/harrisonchase/workplace/langchain/docs/ecosystem/wandb/run-20230318_150550-wzy59zjq</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Syncing run <strong><a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">agent</a></strong> to <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/run' target=\"_blank\">docs</a>)<br/>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View project at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run at <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# SCENARIO 2 - Chain\n",
+    "template = \"\"\"You are a playwright. Given the title of play, it is your job to write a synopsis for that title.\n",
+    "Title: {title}\n",
+    "Playwright: This is a synopsis for the above play:\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"title\"], template=template)\n",
+    "synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)\n",
+    "\n",
+    "test_prompts = [\n",
+    "    {\n",
+    "        \"title\": \"documentary about good video games that push the boundary of game design\"\n",
+    "    },\n",
+    "    {\"title\": \"cocaine bear vs heroin wolf\"},\n",
+    "    {\"title\": \"the best in class mlops tooling\"},\n",
+    "]\n",
+    "synopsis_chain.apply(test_prompts)\n",
+    "wandb_callback.flush_tracker(synopsis_chain, name=\"agent\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "_jN73xcPVEpI"
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.agents import initialize_agent, load_tools"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "Gpq4rk6VT9cu"
+   },
+   "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 find out who Leo DiCaprio's girlfriend is and then calculate her age raised to the 0.43 power.\n",
+      "Action: Search\n",
+      "Action Input: \"Leo DiCaprio girlfriend\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mDiCaprio had a steady girlfriend in Camila Morrone. He had been with the model turned actress for nearly five years, as they were first said to be dating at the end of 2017. And the now 26-year-old Morrone is no stranger to Hollywood.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to calculate her age raised to the 0.43 power.\n",
+      "Action: Calculator\n",
+      "Action Input: 26^0.43\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.059182145592686\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: Leo DiCaprio's girlfriend is Camila Morrone and her current age raised to the 0.43 power is 4.059182145592686.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       " View run <strong style=\"color:#cdcd00\">agent</strong> at: <a href='https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq' target=\"_blank\">https://wandb.ai/harrison-chase/langchain_callback_demo/runs/wzy59zjq</a><br/>Synced 5 W&B file(s), 2 media file(s), 7 artifact file(s) and 0 other file(s)"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "Find logs at: <code>./wandb/run-20230318_150550-wzy59zjq/logs</code>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# SCENARIO 3 - Agent with Tools\n",
+    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callback_manager=manager)\n",
+    "agent = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=\"zero-shot-react-description\",\n",
+    "    callback_manager=manager,\n",
+    "    verbose=True,\n",
+    ")\n",
+    "agent.run(\n",
+    "    \"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\"\n",
+    ")\n",
+    "wandb_callback.flush_tracker(agent, reset=False, finish=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "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": 1
+}

docs/gallery.rst

@@ -158,14 +158,14 @@ Open Source
 
     ---
 
-    .. link-button:: https://github.com/jerryjliu/gpt_index
+    .. link-button:: https://github.com/jerryjliu/llama_index
         :type: url
-        :text: GPT Index
+        :text: LlamaIndex
         :classes: stretched-link btn-lg
     
     +++
 
-    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.
+    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.
 
     ---
 
@@ -322,5 +322,14 @@ Proprietary
 
     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.
+    

docs/index.rst

@@ -97,6 +97,8 @@ The above modules can be used in a variety of ways. LangChain also provides guid
 
 - `Summarization <./use_cases/summarization.html>`_: Summarizing longer documents into shorter, more condensed chunks of information. A type of Data Augmented Generation.
 
+- `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.
+
 - `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.
 
 - `Generate similar examples <./use_cases/generate_examples.html>`_: Generating similar examples to a given input. This is a common use case for many applications, and LangChain provides some prompts/chains for assisting in this.
@@ -117,6 +119,8 @@ The above modules can be used in a variety of ways. LangChain also provides guid
    ./use_cases/combine_docs.md
    ./use_cases/question_answering.md
    ./use_cases/summarization.md
+   ./use_cases/tabular.rst
+   ./use_cases/extraction.md
    ./use_cases/evaluation.rst
    ./use_cases/model_laboratory.ipynb
 

docs/modules/agents/agent_toolkits/vectorstore.ipynb

@@ -92,7 +92,7 @@
    "id": "f4814175-964d-42f1-aa9d-22801ce1e912",
    "metadata": {},
    "source": [
-    "## Initalize Toolkit and Agent\n",
+    "## Initialize Toolkit and Agent\n",
     "\n",
     "First, we'll create an agent with a single vectorstore."
    ]

docs/modules/agents/examples/agent_vectorstore.ipynb

@@ -22,7 +22,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 1,
    "id": "2e87c10a",
    "metadata": {},
    "outputs": [],
@@ -30,13 +30,14 @@
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain import OpenAI, VectorDBQA\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import RetrievalQA\n",
     "llm = OpenAI(temperature=0)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 2,
    "id": "f2675861",
    "metadata": {},
    "outputs": [
@@ -62,17 +63,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 4,
    "id": "bc5403d4",
    "metadata": {},
    "outputs": [],
    "source": [
-    "state_of_union = VectorDBQA.from_chain_type(llm=llm, chain_type=\"stuff\", vectorstore=docsearch)"
+    "state_of_union = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=docsearch.as_retriever())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 5,
    "id": "1431cded",
    "metadata": {},
    "outputs": [],
@@ -82,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 6,
    "id": "915d3ff3",
    "metadata": {},
    "outputs": [],
@@ -92,7 +93,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 7,
    "id": "96a2edf8",
    "metadata": {},
    "outputs": [
@@ -109,7 +110,7 @@
     "docs = loader.load()\n",
     "ruff_texts = text_splitter.split_documents(docs)\n",
     "ruff_db = Chroma.from_documents(ruff_texts, embeddings, collection_name=\"ruff\")\n",
-    "ruff = VectorDBQA.from_chain_type(llm=llm, chain_type=\"stuff\", vectorstore=ruff_db)"
+    "ruff = RetrievalQA.from_chain_type(llm=llm, chain_type=\"stuff\", retriever=ruff_db.as_retriever())"
    ]
   },
   {
@@ -264,9 +265,9 @@
    "id": "9161ba91",
    "metadata": {},
    "source": [
-    "You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the VectorDBQaChain.\n",
+    "You can also set `return_direct=True` if you intend to use the agent as a router and just want to directly return the result of the RetrievalQAChain.\n",
     "\n",
-    "Notice that in the above examples the agent did some extra work after querying the VectorDBQAChain. You can avoid that and just return the result directly."
+    "Notice that in the above examples the agent did some extra work after querying the RetrievalQAChain. You can avoid that and just return the result directly."
    ]
   },
   {

docs/modules/agents/examples/chat_conversation_agent.ipynb

@@ -0,0 +1,309 @@
+{
+ "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": [],
+   "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"
+   ]
+  },
+  {
+   "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=\"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",
+      "\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?'"
+      ]
+     },
+     "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",
+      "\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.'"
+      ]
+     },
+     "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 ...\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 make this week: Thai spicy chilli and basil fried rice, Thai curry noodle soup, and many more. You can find 59 easy Thai recipes for any night of the week on Marion Grasby's website.\"\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 many more. You can find 59 easy Thai recipes for any night of the week on Marion Grasby's website.\""
+      ]
+     },
+     "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;3mThe Argentina national football team represents Argentina in men's international football and is administered by the Argentine Football Association, the governing body for football in Argentina. Nicknamed La Albiceleste, they are the reigning world champions, having won the most recent World Cup in 2022.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m```json\n",
+      "{\n",
+      "    \"action\": \"Final Answer\",\n",
+      "    \"action_input\": \"The last letter in your name is 'b'. The Argentina national football team won the World Cup in 1978.\"\n",
+      "}\n",
+      "```\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"The last letter in your name is 'b'. The Argentina national football team won the World Cup in 1978.\""
+      ]
+     },
+     "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;3mMostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers possible. High near 40F. Winds NNW at 20 to 30 mph.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m{\n",
+      "    \"action\": \"Final Answer\",\n",
+      "    \"action_input\": \"The weather in Pomfret is mostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers are possible. High near 40F. Winds NNW at 20 to 30 mph.\"\n",
+      "}\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The weather in Pomfret is mostly cloudy with gusty winds developing during the afternoon. A few flurries or snow showers are possible. High near 40F. Winds NNW at 20 to 30 mph.'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"whats the weather like in pomfret?\")"
+   ]
+  },
+  {
+   "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
+}

docs/modules/agents/examples/human_tools.ipynb

@@ -0,0 +1,132 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Human as a tool\n",
+    "\n",
+    "Human are AGI so they can certainly be used as a tool to help out AI agent \n",
+    "when it is confused."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sys\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.agents import load_tools, initialize_agent\n",
+    "\n",
+    "llm = ChatOpenAI(temperature=0.0)\n",
+    "math_llm = OpenAI(temperature=0.0)\n",
+    "tools = load_tools(\n",
+    "    [\"human\", \"llm-math\"], \n",
+    "    llm=math_llm,\n",
+    ")\n",
+    "\n",
+    "agent_chain = initialize_agent(\n",
+    "    tools,\n",
+    "    llm,\n",
+    "    agent=\"zero-shot-react-description\",\n",
+    "    verbose=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In the above code you can see the tool takes input directly from command line.\n",
+    "You can customize `prompt_func` and `input_func` according to your need."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mI don't know Eric Zhu, so I should ask a human for guidance.\n",
+      "Action: Human\n",
+      "Action Input: \"Do you know when Eric Zhu's birthday is?\"\u001b[0m\n",
+      "\n",
+      "Do you know when Eric Zhu's birthday is?\n",
+      "last week\n",
+      "\n",
+      "Observation: \u001b[36;1m\u001b[1;3mlast week\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThat's not very helpful. I should ask for more information.\n",
+      "Action: Human\n",
+      "Action Input: \"Do you know the specific date of Eric Zhu's birthday?\"\u001b[0m\n",
+      "\n",
+      "Do you know the specific date of Eric Zhu's birthday?\n",
+      "august 1st\n",
+      "\n",
+      "Observation: \u001b[36;1m\u001b[1;3maugust 1st\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mNow that I have the date, I can check if it's a leap year or not.\n",
+      "Action: Calculator\n",
+      "Action Input: \"Is 2021 a leap year?\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: False\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI have all the information I need to answer the original question.\n",
+      "Final Answer: Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"Eric Zhu's birthday is on August 1st and it is not a leap year in 2021.\""
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "\n",
+    "agent_chain.run(\"What is Eric Zhu's birthday?\")\n",
+    "# Answer with \"last week\""
+   ]
+  },
+  {
+   "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": "3.9.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/agents/examples/load_from_hub.ipynb

@@ -61,7 +61,8 @@
     "tools = [\n",
     "    Tool(\n",
     "        name=\"Intermediate Answer\",\n",
-    "        func=search.run\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to ask with search\"\n",
     "    )\n",
     "]\n",
     "\n",

docs/modules/agents/examples/sharedmemory_for_tools.ipynb

@@ -0,0 +1,552 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "fa6802ac",
+   "metadata": {},
+   "source": [
+    "# Adding SharedMemory to an Agent and its Tools\n",
+    "\n",
+    "This notebook goes over adding memory to **both** of an Agent and its tools. Before going through this notebook, please walk through the following notebooks, as this will build on top of both of them:\n",
+    "\n",
+    "- [Adding memory to an LLM Chain](../../memory/examples/adding_memory.ipynb)\n",
+    "- [Custom Agents](custom_agent.ipynb)\n",
+    "\n",
+    "We are going to create a custom Agent. The agent has access to a conversation memory, search tool, and a summarization tool. And, the summarization tool also needs access to the conversation memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8db95912",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
+    "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
+    "from langchain import OpenAI, LLMChain, PromptTemplate\n",
+    "from langchain.utilities import GoogleSearchAPIWrapper"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "06b7187b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"This is a conversation between a human and a bot:\n",
+    "\n",
+    "{chat_history}\n",
+    "\n",
+    "Write a summary of the conversation for {input}:\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    input_variables=[\"input\", \"chat_history\"], \n",
+    "    template=template\n",
+    ")\n",
+    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
+    "readonlymemory = ReadOnlySharedMemory(memory=memory)\n",
+    "summry_chain = LLMChain(\n",
+    "    llm=OpenAI(), \n",
+    "    prompt=prompt, \n",
+    "    verbose=True, \n",
+    "    memory=readonlymemory, # use the read-only memory to prevent the tool from modifying the memory\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "97ad8467",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search = GoogleSearchAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name = \"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events\"\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name = \"Summary\",\n",
+    "        func=summry_chain.run,\n",
+    "        description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\"\n",
+    "    )\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e3439cd6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin!\"\n",
+    "\n",
+    "{chat_history}\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools, \n",
+    "    prefix=prefix, \n",
+    "    suffix=suffix, \n",
+    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0021675b",
+   "metadata": {},
+   "source": [
+    "We can now construct the LLMChain, with the Memory object, and then create the agent."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "c56a0e73",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
+    "agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "ca4bc1fb",
+   "metadata": {},
+   "outputs": [
+    {
+     "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 research ChatGPT to answer this question.\n",
+      "Action: Search\n",
+      "Action Input: \"ChatGPT\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\""
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"What is ChatGPT?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "45627664",
+   "metadata": {},
+   "source": [
+    "To test the memory of this agent, we can ask a followup question that relies on information in the previous exchange to be answered correctly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "eecc0462",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
+      "Action: Search\n",
+      "Action Input: Who developed ChatGPT\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'ChatGPT was developed by OpenAI.'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"Who developed it?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "c34424cf",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "Action: Summary\n",
+      "Action Input: My daughter 5 years old\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
+      "\n",
+      "Human: What is ChatGPT?\n",
+      "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
+      "Human: Who developed it?\n",
+      "AI: ChatGPT was developed by OpenAI.\n",
+      "\n",
+      "Write a summary of the conversation for My daughter 5 years old:\n",
+      "\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot. It was created by OpenAI and can send and receive images while chatting.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "4ebd8326",
+   "metadata": {},
+   "source": [
+    "Confirm that the memory was correctly updated."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b91f8c85",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Human: What is ChatGPT?\n",
+      "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
+      "Human: Who developed it?\n",
+      "AI: ChatGPT was developed by OpenAI.\n",
+      "Human: Thanks. Summarize the conversation, for my daughter 5 years old.\n",
+      "AI: ChatGPT is an artificial intelligence chatbot created by OpenAI that can send and receive images while chatting.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(agent_chain.memory.buffer)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "cc3d0aa4",
+   "metadata": {},
+   "source": [
+    "For comparison, below is a bad example that uses the same memory for both the Agent and the tool."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "3359d043",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## This is a bad practice for using the memory.\n",
+    "## Use the ReadOnlySharedMemory class, as shown above.\n",
+    "\n",
+    "template = \"\"\"This is a conversation between a human and a bot:\n",
+    "\n",
+    "{chat_history}\n",
+    "\n",
+    "Write a summary of the conversation for {input}:\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    input_variables=[\"input\", \"chat_history\"], \n",
+    "    template=template\n",
+    ")\n",
+    "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
+    "summry_chain = LLMChain(\n",
+    "    llm=OpenAI(), \n",
+    "    prompt=prompt, \n",
+    "    verbose=True, \n",
+    "    memory=memory,  # <--- this is the only change\n",
+    ")\n",
+    "\n",
+    "search = GoogleSearchAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name = \"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events\"\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name = \"Summary\",\n",
+    "        func=summry_chain.run,\n",
+    "        description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\"\n",
+    "    )\n",
+    "]\n",
+    "\n",
+    "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin!\"\n",
+    "\n",
+    "{chat_history}\n",
+    "Question: {input}\n",
+    "{agent_scratchpad}\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools, \n",
+    "    prefix=prefix, \n",
+    "    suffix=suffix, \n",
+    "    input_variables=[\"input\", \"chat_history\", \"agent_scratchpad\"]\n",
+    ")\n",
+    "\n",
+    "llm_chain = LLMChain(llm=OpenAI(temperature=0), prompt=prompt)\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, tools=tools, verbose=True)\n",
+    "agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True, memory=memory)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "970d23df",
+   "metadata": {},
+   "outputs": [
+    {
+     "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 research ChatGPT to answer this question.\n",
+      "Action: Search\n",
+      "Action Input: \"ChatGPT\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mNov 30, 2022 ... We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... ChatGPT. We've trained a model called ChatGPT which interacts in a conversational way. The dialogue format makes it possible for ChatGPT to answer ... Feb 2, 2023 ... ChatGPT, the popular chatbot from OpenAI, is estimated to have reached 100 million monthly active users in January, just two months after ... 2 days ago ... ChatGPT recently launched a new version of its own plagiarism detection tool, with hopes that it will squelch some of the criticism around how ... An API for accessing new AI models developed by OpenAI. Feb 19, 2023 ... ChatGPT is an AI chatbot system that OpenAI released in November to show off and test what a very large, powerful AI system can accomplish. You ... ChatGPT is fine-tuned from GPT-3.5, a language model trained to produce text. ChatGPT was optimized for dialogue by using Reinforcement Learning with Human ... 3 days ago ... Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting. Dec 1, 2022 ... ChatGPT is a natural language processing tool driven by AI technology that allows you to have human-like conversations and much more with a ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"What is ChatGPT?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "d9ea82f0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to find out who developed ChatGPT\n",
+      "Action: Search\n",
+      "Action Input: Who developed ChatGPT\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large ... Feb 15, 2023 ... Who owns Chat GPT? Chat GPT is owned and developed by AI research and deployment company, OpenAI. The organization is headquartered in San ... Feb 8, 2023 ... ChatGPT is an AI chatbot developed by San Francisco-based startup OpenAI. OpenAI was co-founded in 2015 by Elon Musk and Sam Altman and is ... Dec 7, 2022 ... ChatGPT is an AI chatbot designed and developed by OpenAI. The bot works by generating text responses based on human-user input, like questions ... Jan 12, 2023 ... In 2019, Microsoft invested $1 billion in OpenAI, the tiny San Francisco company that designed ChatGPT. And in the years since, it has quietly ... Jan 25, 2023 ... The inside story of ChatGPT: How OpenAI founder Sam Altman built the world's hottest technology with billions from Microsoft. Dec 3, 2022 ... ChatGPT went viral on social media for its ability to do anything from code to write essays. · The company that created the AI chatbot has a ... Jan 17, 2023 ... While many Americans were nursing hangovers on New Year's Day, 22-year-old Edward Tian was working feverishly on a new app to combat misuse ... ChatGPT is a language model created by OpenAI, an artificial intelligence research laboratory consisting of a team of researchers and engineers focused on ... 1 day ago ... Everyone is talking about ChatGPT, developed by OpenAI. This is such a great tool that has helped to make AI more accessible to a wider ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: ChatGPT was developed by OpenAI.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'ChatGPT was developed by OpenAI.'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"Who developed it?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "5b1f9223",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: I need to simplify the conversation for a 5 year old.\n",
+      "Action: Summary\n",
+      "Action Input: My daughter 5 years old\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThis is a conversation between a human and a bot:\n",
+      "\n",
+      "Human: What is ChatGPT?\n",
+      "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
+      "Human: Who developed it?\n",
+      "AI: ChatGPT was developed by OpenAI.\n",
+      "\n",
+      "Write a summary of the conversation for My daughter 5 years old:\n",
+      "\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_chain.run(input=\"Thanks. Summarize the conversation, for my daughter 5 years old.\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "d07415da",
+   "metadata": {},
+   "source": [
+    "The final answer is not wrong, but we see the 3rd Human input is actually from the agent in the memory because the memory was modified by the summary tool."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "32f97b21",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Human: What is ChatGPT?\n",
+      "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI and launched in November 2022. It is built on top of OpenAI's GPT-3 family of large language models and is optimized for dialogue by using Reinforcement Learning with Human-in-the-Loop. It is also capable of sending and receiving images during chatting.\n",
+      "Human: Who developed it?\n",
+      "AI: ChatGPT was developed by OpenAI.\n",
+      "Human: My daughter 5 years old\n",
+      "AI: \n",
+      "The conversation was about ChatGPT, an artificial intelligence chatbot developed by OpenAI. It is designed to have conversations with humans and can also send and receive images.\n",
+      "Human: Thanks. Summarize the conversation, for my daughter 5 years old.\n",
+      "AI: ChatGPT is an artificial intelligence chatbot developed by OpenAI that can have conversations with humans and send and receive images.\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(agent_chain.memory.buffer)"
+   ]
+  }
+ ],
+ "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
+}

docs/modules/agents/implementations/mrkl_chat.ipynb

@@ -0,0 +1,253 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "f1390152",
+   "metadata": {},
+   "source": [
+    "# MRKL Chat\n",
+    "\n",
+    "This notebook showcases using an agent to replicate the MRKL chain using an agent optimized for chat models."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "39ea3638",
+   "metadata": {},
+   "source": [
+    "This uses the example Chinook database.\n",
+    "To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ac561cc4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI, LLMMathChain, SerpAPIWrapper, SQLDatabase, SQLDatabaseChain\n",
+    "from langchain.agents import initialize_agent, Tool\n",
+    "from langchain.chat_models import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "07e96d99",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(temperature=0)\n",
+    "llm1 = OpenAI(temperature=0)\n",
+    "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",
+    "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",
+    "    Tool(\n",
+    "        name=\"Calculator\",\n",
+    "        func=llm_math_chain.run,\n",
+    "        description=\"useful for when you need to answer questions about math\"\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name=\"FooBar DB\",\n",
+    "        func=db_chain.run,\n",
+    "        description=\"useful for when you need to answer questions about FooBar. Input should be in the form of a question containing full context\"\n",
+    "    )\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "a069c4b6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "mrkl = initialize_agent(tools, llm, agent=\"chat-zero-shot-react-description\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e603cd7d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mThought: The first question requires a search, while the second question requires a calculator.\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;3mCamila Morrone\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mFor the second question, I need to use the calculator tool to raise her current age to the 0.43 power.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Calculator\",\n",
+      "  \"action_input\": \"22.0^(0.43)\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
+      "22.0^(0.43)\u001b[32;1m\u001b[1;3m\n",
+      "```python\n",
+      "import math\n",
+      "print(math.pow(22.0, 0.43))\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Answer: \u001b[33;1m\u001b[1;3m3.777824273683966\n",
+      "\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 3.777824273683966\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
+      "Final Answer: Camila Morrone, 3.777824273683966.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'Camila Morrone, 3.777824273683966.'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a5c07010",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mQuestion: What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\n",
+      "Thought: I should use the Search tool to find the answer to the first part of the question and then use the FooBar DB tool to find the answer to the second part of the question.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Search\",\n",
+      "  \"action_input\": \"Who recently released an album called 'The Storm Before the Calm'\"\n",
+      "}\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAlanis Morissette\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mNow that I have the name of the artist, I can use the FooBar DB tool to find their albums in the database.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"FooBar DB\",\n",
+      "  \"action_input\": \"What albums does Alanis Morissette have in the database?\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Entering new SQLDatabaseChain chain...\u001b[0m\n",
+      "What albums does Alanis Morissette have in the database? \n",
+      "SQLQuery:"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/harrisonchase/workplace/langchain/langchain/sql_database.py:141: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
+      "  sample_rows = connection.execute(command)\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[32;1m\u001b[1;3m SELECT Title FROM Album WHERE ArtistId IN (SELECT ArtistId FROM Artist WHERE Name = 'Alanis Morissette') LIMIT 5;\u001b[0m\n",
+      "SQLResult: \u001b[33;1m\u001b[1;3m[('Jagged Little Pill',)]\u001b[0m\n",
+      "Answer:\u001b[32;1m\u001b[1;3m Alanis Morissette has the album 'Jagged Little Pill' in the database.\u001b[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
+      "\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3m Alanis Morissette has the album 'Jagged Little Pill' in the database.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mI have found the answer to both parts of the question.\n",
+      "Final Answer: The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The album 'Jagged Little Pill' is in the FooBar database.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\"The artist who recently released an album called 'The Storm Before the Calm' is Alanis Morissette. The album 'Jagged Little Pill' is in the FooBar database.\""
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "mrkl.run(\"What is the full name of the artist who recently released an album called 'The Storm Before the Calm' and are they in the FooBar database? If so, what albums of theirs are in the FooBar database?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af016a70",
+   "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
+}

docs/modules/agents/implementations/react.ipynb

@@ -24,11 +24,13 @@
     "tools = [\n",
     "    Tool(\n",
     "        name=\"Search\",\n",
-    "        func=docstore.search\n",
+    "        func=docstore.search,\n",
+    "        description=\"useful for when you need to ask with search\"\n",
     "    ),\n",
     "    Tool(\n",
     "        name=\"Lookup\",\n",
-    "        func=docstore.lookup\n",
+    "        func=docstore.lookup,\n",
+    "        description=\"useful for when you need to ask with lookup\"\n",
     "    )\n",
     "]\n",
     "\n",

docs/modules/agents/implementations/self_ask_with_search.ipynb

@@ -52,7 +52,8 @@
     "tools = [\n",
     "    Tool(\n",
     "        name=\"Intermediate Answer\",\n",
-    "        func=search.run\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to ask with search\"\n",
     "    )\n",
     "]\n",
     "\n",

docs/modules/agents/key_concepts.md

@@ -13,3 +13,4 @@ For more detailed information on tools, and different types of tools in LangChai
 Toolkits are groups of tools that are best used together.
 They allow you to logically group and initialize a set of tools that share a particular resource (such as a database connection or json object). 
 They can be used to construct an agent for a specific use-case.
+For more detailed information on toolkits and their use cases, see [this documentation](how_to_guides.rst#agent-toolkits) (the "Agent Toolkits" section).

docs/modules/agents/tools.md

@@ -136,3 +136,19 @@ Below is a list of all supported tools and relevant information:
 - Requires LLM: No
 - Extra Parameters: `serper_api_key`
 - For more information on this, see [this page](../../ecosystem/google_serper.md)
+
+**wikipedia**
+
+- Tool Name: Wikipedia
+- Tool Description: A wrapper around Wikipedia. Useful for when you need to answer general questions about people, places, companies, historical events, or other subjects. Input should be a search query.
+- Notes: Uses the [wikipedia](https://pypi.org/project/wikipedia/) Python package to call the MediaWiki API and then parses results.
+- Requires LLM: No
+- Extra Parameters: `top_k_results`
+
+**podcast-api**
+
+- Tool Name: Podcast API
+- Tool Description: Use the Listen Notes Podcast API to search all podcasts or episodes. The input should be a question in natural language that this API can answer.
+- Notes: A natural language connection to the Listen Notes Podcast API (`https://www.PodcastAPI.com`), specifically the `/search/` endpoint.
+- Requires LLM: Yes
+- Extra Parameters: `listen_api_key` (your api key to access this endpoint)

docs/modules/chains/examples/api.ipynb

@@ -149,6 +149,33 @@
     "chain.run(\"Search for 'Avatar'\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Listen API Example"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains.api import podcast_docs\n",
+    "from langchain.chains import APIChain\n",
+    "\n",
+    "# Get api key here: https://www.listennotes.com/api/pricing/\n",
+    "listen_api_key = 'xxx'\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "headers = {\"X-ListenAPI-Key\": listen_api_key}\n",
+    "chain = APIChain.from_llm_and_api_docs(llm, podcast_docs.PODCAST_DOCS, headers=headers, verbose=True)\n",
+    "chain.run(\"Search for 'silicon valley bank' podcast episodes, audio length is more than 30 minutes, return only 1 results\")\n"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -173,7 +200,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/chains/examples/sqlite.ipynb

@@ -377,18 +377,19 @@
       "\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
       "\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
       ")\n",
-      "\n",
-      "SELECT * FROM 'Track' LIMIT 2;\n",
+      "/*\n",
+      "2 rows from Track table:\n",
       "TrackId\tName\tAlbumId\tMediaTypeId\tGenreId\tComposer\tMilliseconds\tBytes\tUnitPrice\n",
       "1\tFor Those About To Rock (We Salute You)\t1\t1\t1\tAngus Young, Malcolm Young, Brian Johnson\t343719\t11170334\t0.99\n",
-      "2\tBalls to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n"
+      "2\tBalls to the Wall\t2\t2\t1\tNone\t342562\t5510424\t0.99\n",
+      "*/\n"
      ]
     },
     {
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "/home/jon/projects/langchain/langchain/sql_database.py:121: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
+      "/home/jon/projects/langchain/langchain/sql_database.py:135: SAWarning: Dialect sqlite+pysqlite does *not* support Decimal objects natively, and SQLAlchemy must convert from floating point - rounding errors and other issues may occur. Please consider storing Decimal numbers as strings or integers on this platform for lossless storage.\n",
       "  sample_rows = connection.execute(command)\n"
      ]
     }
@@ -467,12 +468,13 @@
     "\t\"Composer\" NVARCHAR(220),\n",
     "\tPRIMARY KEY (\"TrackId\")\n",
     ")\n",
-    "\n",
-    "SELECT * FROM 'Track' LIMIT 3;\n",
+    "/*\n",
+    "3 rows from Track table:\n",
     "TrackId\tName\tComposer\n",
     "1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n",
     "2\tBalls to the Wall\tNone\n",
-    "3\tMy favorite song ever\tThe coolest composer of all time\"\"\"\n",
+    "3\tMy favorite song ever\tThe coolest composer of all time\n",
+    "*/\"\"\"\n",
     "}"
    ]
   },
@@ -492,11 +494,12 @@
       "\t\"Name\" NVARCHAR(120), \n",
       "\tPRIMARY KEY (\"PlaylistId\")\n",
       ")\n",
-      "\n",
-      "SELECT * FROM 'Playlist' LIMIT 2;\n",
+      "/*\n",
+      "2 rows from Playlist table:\n",
       "PlaylistId\tName\n",
       "1\tMusic\n",
       "2\tMovies\n",
+      "*/\n",
       "\n",
       "CREATE TABLE Track (\n",
       "\t\"TrackId\" INTEGER NOT NULL, \n",
@@ -504,12 +507,13 @@
       "\t\"Composer\" NVARCHAR(220),\n",
       "\tPRIMARY KEY (\"TrackId\")\n",
       ")\n",
-      "\n",
-      "SELECT * FROM 'Track' LIMIT 3;\n",
+      "/*\n",
+      "3 rows from Track table:\n",
       "TrackId\tName\tComposer\n",
       "1\tFor Those About To Rock (We Salute You)\tAngus Young, Malcolm Young, Brian Johnson\n",
       "2\tBalls to the Wall\tNone\n",
-      "3\tMy favorite song ever\tThe coolest composer of all time\n"
+      "3\tMy favorite song ever\tThe coolest composer of all time\n",
+      "*/\n"
      ]
     }
    ],
@@ -528,7 +532,7 @@
    "id": "5fc6f507",
    "metadata": {},
    "source": [
-    "Note how our custom table definition and sample rows for `Track` overrides the `sample_rows_in_table_info` parameter. Tables that are not overriden by `custom_table_info`, in this example `Playlist`, will have their table info gathered automatically as usual."
+    "Note how our custom table definition and sample rows for `Track` overrides the `sample_rows_in_table_info` parameter. Tables that are not overridden by `custom_table_info`, in this example `Playlist`, will have their table info gathered automatically as usual."
    ]
   },
   {
@@ -675,7 +679,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/chains/key_concepts.md

@@ -9,3 +9,12 @@ This is a specific type of chain where multiple other chains are run in sequence
 to the next. A subtype of this type of chain is the [`SimpleSequentialChain`](./generic/sequential_chains.html#simplesequentialchain), where all subchains have only one input and one output,
 and the output of one is therefore used as sole input to the next chain.
 
+## Prompt Selectors
+One thing that we've noticed is that the best prompt to use is really dependent on the model you use.
+Some prompts work really good with some models, but not great with others.
+One of our goals is provide good chains that "just work" out of the box. 
+A big part of chains like that is having prompts that "just work".
+So rather than having a default prompt for chains, we are moving towards a paradigm where if a prompt is not explicitly
+provided we select one with a PromptSelector. This class takes in the model passed in, and returns a default prompt.
+The inner workings of the PromptSelector can look at any aspect of the model - LLM vs ChatModel, OpenAI vs Cohere, GPT3 vs GPT4, etc.
+Due to this being a newer feature, this may not be implemented for all chains, but this is the direction we are moving.

docs/modules/chat/examples/chat_vector_db.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "This notebook goes over how to set up a chat model to chat with a vector database.\n",
     "\n",
-    "This notebook is very similar to the example of using an LLM in the ChatVectorDBChain. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
+    "This notebook is very similar to the example of using an LLM in the ConversationalRetrievalChain. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
    ]
   },
   {
@@ -24,7 +24,7 @@
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.chains import ChatVectorDBChain"
+    "from langchain.chains import ConversationalRetrievalChain"
    ]
   },
   {
@@ -157,7 +157,7 @@
    "id": "3c96b118",
    "metadata": {},
    "source": [
-    "We now initialize the ChatVectorDBChain"
+    "We now initialize the ConversationalRetrievalChain"
    ]
   },
   {
@@ -169,7 +169,7 @@
    },
    "outputs": [],
    "source": [
-    "qa = ChatVectorDBChain.from_llm(ChatOpenAI(temperature=0), vectorstore,qa_prompt=prompt)"
+    "qa = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0), vectorstore,qa_prompt=prompt)"
    ]
   },
   {
@@ -205,7 +205,7 @@
     {
      "data": {
       "text/plain": [
-       "\"The President nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court. He described her as one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and a consensus builder. He also mentioned that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+       "\"The President nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to serve on the United States Supreme Court. He described her as one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and a consensus builder. She has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
      "execution_count": 9,
@@ -227,7 +227,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "id": "00b4cf00",
    "metadata": {
     "tags": []
@@ -241,7 +241,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "id": "f01828d1",
    "metadata": {
     "tags": []
@@ -250,10 +250,10 @@
     {
      "data": {
       "text/plain": [
-       "'The context does not provide information about the predecessor of Ketanji Brown Jackson.'"
+       "\"The President mentioned Circuit Court of Appeals Judge Ketanji Brown Jackson as the nominee for the United States Supreme Court. He described her as one of the nation's top legal minds who will continue Justice Breyer's legacy of excellence. The President did not mention any specific sources of support for Judge Jackson, but he did note that advancing immigration reform is supported by everyone from labor unions to religious leaders to the U.S. Chamber of Commerce.\""
       ]
      },
-     "execution_count": 13,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -267,14 +267,14 @@
    "id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
    "metadata": {},
    "source": [
-    "## Chat Vector DB with streaming to `stdout`\n",
+    "## 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": 15,
+   "execution_count": 12,
    "id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
    "metadata": {
     "tags": []
@@ -285,7 +285,7 @@
     "from langchain.llms import OpenAI\n",
     "from langchain.callbacks.base import CallbackManager\n",
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT\n",
+    "from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT\n",
     "from langchain.chains.question_answering import load_qa_chain\n",
     "\n",
     "# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
@@ -296,12 +296,12 @@
     "question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
     "doc_chain = load_qa_chain(streaming_llm, chain_type=\"stuff\", prompt=prompt)\n",
     "\n",
-    "qa = ChatVectorDBChain(vectorstore=vectorstore, combine_docs_chain=doc_chain, question_generator=question_generator)"
+    "qa = ConversationalRetrievalChain(retriever=vectorstore.as_retriever(), combine_docs_chain=doc_chain, question_generator=question_generator)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 13,
    "id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
    "metadata": {
     "tags": []
@@ -323,7 +323,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 14,
    "id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
    "metadata": {
     "tags": []

docs/modules/chat/examples/promptlayer_chatopenai.ipynb

@@ -0,0 +1,188 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "959300d4",
+   "metadata": {},
+   "source": [
+    "# PromptLayer ChatOpenAI\n",
+    "\n",
+    "This example showcases how to connect to [PromptLayer](https://www.promptlayer.com) to start recording your ChatOpenAI requests."
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "6a45943e",
+   "metadata": {},
+   "source": [
+    "## Install PromptLayer\n",
+    "The `promptlayer` package is required to use PromptLayer with OpenAI. Install `promptlayer` using pip."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dbe09bd8",
+   "metadata": {
+    "vscode": {
+     "languageId": "powershell"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "pip install promptlayer"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "536c1dfa",
+   "metadata": {},
+   "source": [
+    "## Imports"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c16da3b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "from langchain.chat_models import PromptLayerChatOpenAI\n",
+    "from langchain.schema import HumanMessage"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "8564ce7d",
+   "metadata": {},
+   "source": [
+    "## Set the Environment API Key\n",
+    "You can create a PromptLayer API Key at [wwww.promptlayer.com](https://ww.promptlayer.com) by clicking the settings cog in the navbar.\n",
+    "\n",
+    "Set it as an environment variable called `PROMPTLAYER_API_KEY`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "46ba25dc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "os.environ[\"PROMPTLAYER_API_KEY\"] = \"**********\""
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "bf0294de",
+   "metadata": {},
+   "source": [
+    "## Use the PromptLayerOpenAI LLM like normal\n",
+    "*You can optionally pass in `pl_tags` to track your requests with PromptLayer's tagging feature.*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3acf0069",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content='to take a nap in a cozy spot. I search around for a suitable place and finally settle on a soft cushion on the window sill. I curl up into a ball and close my eyes, relishing the warmth of the sun on my fur. As I drift off to sleep, I can hear the birds chirping outside and feel the gentle breeze blowing through the window. This is the life of a contented cat.', additional_kwargs={})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat = PromptLayerChatOpenAI(pl_tags=[\"langchain\"])\n",
+    "chat([HumanMessage(content=\"I am a cat and I want\")])"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "a2d76826",
+   "metadata": {},
+   "source": [
+    "**The above request should now appear on your [PromptLayer dashboard](https://ww.promptlayer.com).**"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "05e9e2fe",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "c43803d1",
+   "metadata": {},
+   "source": [
+    "## Using PromptLayer Track\n",
+    "If you would like to use any of the [PromptLayer tracking features](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9), you need to pass the argument `return_pl_id` when instantializing the PromptLayer LLM to get the request id.  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b7d4db01",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = PromptLayerChatOpenAI(return_pl_id=True)\n",
+    "chat_results = chat.generate([[HumanMessage(content=\"I am a cat and I want\")]])\n",
+    "\n",
+    "for res in chat_results.generations:\n",
+    "    pl_request_id = res[0].generation_info[\"pl_request_id\"]\n",
+    "    promptlayer.track.score(request_id=pl_request_id, score=100)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "13e56507",
+   "metadata": {},
+   "source": [
+    "Using this allows you to track the performance of your model in the PromptLayer dashboard. If you are using a prompt template, you can attach a template to a request as well.\n",
+    "Overall, this gives you the opportunity to track the performance of different templates and models in the PromptLayer dashboard."
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "base",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.8 (default, Apr 13 2021, 12:59:45) \n[Clang 10.0.0 ]"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "8a5edab282632443219e051e4ade2d1d5bbc671c781051bf1437897cbdfea0f1"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/chat/examples/vector_db_qa.ipynb

@@ -5,16 +5,16 @@
    "id": "07c1e3b9",
    "metadata": {},
    "source": [
-    "# Vector DB Question/Answering\n",
+    "# Retrieval Question/Answering\n",
     "\n",
     "This example showcases using a chat model to do question answering over a vector database.\n",
     "\n",
-    "This notebook is very similar to the example of using an LLM in the ChatVectorDBChain. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
+    "This notebook is very similar to the example of using an LLM in the RetrievalQA. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 7,
    "id": "82525493",
    "metadata": {},
    "outputs": [],
@@ -22,7 +22,7 @@
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.chains import VectorDBQA"
+    "from langchain.chains import RetrievalQA"
    ]
   },
   {
@@ -100,28 +100,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "3018f865",
    "metadata": {},
    "outputs": [],
    "source": [
     "chain_type_kwargs = {\"prompt\": prompt}\n",
-    "qa = VectorDBQA.from_chain_type(llm=ChatOpenAI(), chain_type=\"stuff\", vectorstore=docsearch, chain_type_kwargs=chain_type_kwargs)"
+    "qa = RetrievalQA.from_chain_type(llm=ChatOpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "032a47f8",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\"The President nominated Ketanji Brown Jackson as a Judge for the United States Supreme Court. He described her as one of the nation's top legal minds and a former top litigator in private practice, a former federal public defender, and a consensus builder.\""
+       "\"The president nominated Ketanji Brown Jackson to serve on the United States Supreme Court. He referred to her as one of our nation's top legal minds, a former federal public defender, a consensus builder, and from a family of public school educators and police officers. Since she's been nominated, she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 7,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/modules/chat/examples/vector_db_qa_with_sources.ipynb

@@ -5,11 +5,11 @@
    "id": "efc5be67",
    "metadata": {},
    "source": [
-    "# VectorDB Question Answering with Sources\n",
+    "# Retrieval Question Answering with Sources\n",
     "\n",
-    "This notebook goes over how to do question-answering with sources with a chat model over a vector database. It does this by using the `VectorDBQAWithSourcesChain`, which does the lookup of the documents from a vector database. \n",
+    "This notebook goes over how to do question-answering with sources with a chat model over a vector database. It does this by using the `RetrievalQAWithSourcesChain`, which does the lookup of the documents from a vector database. \n",
     "\n",
-    "This notebook is very similar to the example of using an LLM in the ChatVectorDBChain. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
+    "This notebook is very similar to the example of using an LLM in the RetrievalQAWithSources. The only differences here are (1) using a ChatModel, and (2) passing in a ChatPromptTemplate (optimized for chat models)."
    ]
   },
   {
@@ -51,6 +51,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n",
       "Running Chroma using direct local API.\n",
       "Using DuckDB in-memory for database. Data will be transient.\n"
      ]
@@ -62,12 +64,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 9,
    "id": "8aa571ae",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains import VectorDBQAWithSourcesChain"
+    "from langchain.chains import RetrievalQAWithSourcesChain"
    ]
   },
   {
@@ -101,7 +103,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 6,
    "id": "ed00e906",
    "metadata": {},
    "outputs": [],
@@ -130,23 +132,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 10,
    "id": "aa859d4c",
    "metadata": {},
    "outputs": [],
    "source": [
     "chain_type_kwargs = {\"prompt\": prompt}\n",
-    "chain = VectorDBQAWithSourcesChain.from_chain_type(\n",
+    "chain = RetrievalQAWithSourcesChain.from_chain_type(\n",
     "    ChatOpenAI(temperature=0), \n",
     "    chain_type=\"stuff\", \n",
-    "    vectorstore=docsearch,\n",
+    "    retriever=docsearch.as_retriever(),\n",
     "    chain_type_kwargs=chain_type_kwargs\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 11,
    "id": "8ba36fa7",
    "metadata": {},
    "outputs": [
@@ -154,10 +156,10 @@
      "data": {
       "text/plain": [
        "{'answer': 'The President honored Justice Stephen Breyer, an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court, for his dedicated service to the country. \\n',\n",
-       " 'sources': '30-pl'}"
+       " 'sources': '31-pl'}"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -168,25 +170,11 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
-   "id": "c91fdc8a",
+   "execution_count": null,
+   "id": "8308fbf7",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
-       " 'sources': '30-pl'}"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "qa({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
-   ]
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/modules/chat/getting_started.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "522686de",
    "metadata": {
     "tags": []
@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "62e0dbc3",
    "metadata": {
     "tags": []
@@ -56,7 +56,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "76a6e7b0-e927-4bfb-a414-1332a4149106",
    "metadata": {
     "tags": []
@@ -68,7 +68,7 @@
        "AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -87,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "ce16ad78-8e6f-48cd-954e-98be75eb5836",
    "metadata": {
     "tags": []
@@ -99,7 +99,7 @@
        "AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -122,7 +122,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "2b21fc52-74b6-4950-ab78-45d12c68fb4d",
    "metadata": {
     "tags": []
@@ -131,10 +131,10 @@
     {
      "data": {
       "text/plain": [
-       "LLMResult(generations=[[ChatGeneration(text=\"J'aime programmer.\", generation_info=None, message=AIMessage(content=\"J'aime programmer.\", additional_kwargs={}))], [ChatGeneration(text=\"J'aime l'intelligence artificielle.\", generation_info=None, message=AIMessage(content=\"J'aime l'intelligence artificielle.\", additional_kwargs={}))]], llm_output=None)"
+       "LLMResult(generations=[[ChatGeneration(text=\"J'aime programmer.\", generation_info=None, message=AIMessage(content=\"J'aime programmer.\", additional_kwargs={}))], [ChatGeneration(text=\"J'aime l'intelligence artificielle.\", generation_info=None, message=AIMessage(content=\"J'aime l'intelligence artificielle.\", additional_kwargs={}))]], llm_output={'token_usage': {'prompt_tokens': 71, 'completion_tokens': 18, 'total_tokens': 89}})"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -150,7 +150,39 @@
     "        HumanMessage(content=\"Translate this sentence from English to French. I love artificial intelligence.\")\n",
     "    ],\n",
     "]\n",
-    "chat.generate(batch_messages)"
+    "result = chat.generate(batch_messages)\n",
+    "result"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2960f50f",
+   "metadata": {},
+   "source": [
+    "You can recover things like token usage from this LLMResult"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a6186bee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'token_usage': {'prompt_tokens': 71,\n",
+       "  'completion_tokens': 18,\n",
+       "  'total_tokens': 89}}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result.llm_output"
    ]
   },
   {

docs/modules/document_loaders/examples/blackboard.ipynb

@@ -0,0 +1,38 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Blackboard\n",
+    "\n",
+    "This covers how to load data from a Blackboard Learn instance."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import BlackboardLoader\n",
+    "\n",
+    "loader = BlackboardLoader(\n",
+    "    blackboard_course_url=\"https://blackboard.example.com/webapps/blackboard/execute/announcement?method=search&context=course_entry&course_id=_123456_1\",\n",
+    "    bbrouter=\"expires:12345...\",\n",
+    "    load_all_recursively=True,\n",
+    ")\n",
+    "documents = loader.load()"
+   ]
+  }
+ ],
+ "metadata": {
+  "language_info": {
+   "name": "python"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/document_loaders/examples/example_data/fake-content.html

@@ -1,5 +1,8 @@
 <!DOCTYPE html>
 <html>
+<head>
+    <title>Test Title</title>
+</head>
 <body>
 
 <h1>My First Heading</h1>

docs/modules/document_loaders/examples/example_data/mlb_teams_2012.csv

@@ -0,0 +1,32 @@
+"Team", "Payroll (millions)", "Wins"
+"Nationals",     81.34, 98
+"Reds",          82.20, 97
+"Yankees",      197.96, 95
+"Giants",       117.62, 94
+"Braves",        83.31, 94
+"Athletics",     55.37, 94
+"Rangers",      120.51, 93
+"Orioles",       81.43, 93
+"Rays",          64.17, 90
+"Angels",       154.49, 89
+"Tigers",       132.30, 88
+"Cardinals",    110.30, 88
+"Dodgers",       95.14, 86
+"White Sox",     96.92, 85
+"Brewers",       97.65, 83
+"Phillies",     174.54, 81
+"Diamondbacks",  74.28, 81
+"Pirates",       63.43, 79
+"Padres",        55.24, 76
+"Mariners",      81.97, 75
+"Mets",          93.35, 74
+"Blue Jays",     75.48, 73
+"Royals",        60.91, 72
+"Marlins",      118.07, 69
+"Red Sox",      173.18, 69
+"Indians",       78.43, 68
+"Twins",         94.08, 66
+"Rockies",       78.06, 64
+"Cubs",          88.19, 61
+"Astros",        60.65, 55
+

docs/modules/document_loaders/examples/figma.ipynb

@@ -0,0 +1,79 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "33205b12",
+   "metadata": {},
+   "source": [
+    "# Figma\n",
+    "\n",
+    "This notebook covers how to load data from the Figma REST API into a format that can be ingested into LangChain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "90b69c94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "from langchain.document_loaders import FigmaFileLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "13deb0f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = FigmaFileLoader(\n",
+    "    os.environ.get('ACCESS_TOKEN'),\n",
+    "    os.environ.get('NODE_IDS'),\n",
+    "    os.environ.get('FILE_KEY')\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9ccc1e2f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3e64cac2",
+   "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
+}

docs/modules/document_loaders/examples/html.ipynb

@@ -48,9 +48,7 @@
    "outputs": [
     {
      "data": {
-      "text/plain": [
-       "[Document(page_content='My First Heading\\n\\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]"
-      ]
+      "text/plain": "[Document(page_content='My First Heading\\n\\nMy first paragraph.', lookup_str='', metadata={'source': 'example_data/fake-content.html'}, lookup_index=0)]"
      },
      "execution_count": 4,
      "metadata": {},
@@ -61,13 +59,57 @@
     "data"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Loading HTML with BeautifulSoup4\n",
+    "\n",
+    "We can also use BeautifulSoup4 to load HTML documents using the `BSHTMLLoader`.  This will extract the text from the html into `page_content`, and the page title as `title` into `metadata`."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "79b1bce4",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "from langchain.document_loaders import BSHTMLLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "[Document(page_content='\\n\\nTest Title\\n\\n\\nMy First Heading\\nMy first paragraph.\\n\\n\\n', lookup_str='', metadata={'source': 'example_data/fake-content.html', 'title': 'Test Title'}, lookup_index=0)]"
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader = BSHTMLLoader(\"example_data/fake-content.html\")\n",
+    "data = loader.load()\n",
+    "data"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
   }
  ],
  "metadata": {

docs/modules/document_loaders/examples/markdown.ipynb

@@ -0,0 +1,145 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "39af9ecd",
+   "metadata": {},
+   "source": [
+    "# Markdown\n",
+    "\n",
+    "This covers how to load markdown documents into a document format that we can use downstream."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "721c48aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredMarkdownLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9d3d0e35",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredMarkdownLoader(\"../../../../README.md\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "06073f91",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "c9adc5cb",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content=\"ð\\x9f¦\\x9cï¸\\x8fð\\x9f”\\x97 LangChain\\n\\nâ\\x9a¡ Building applications with LLMs through composability â\\x9a¡\\n\\nProduction Support: As you move your LangChains into production, we'd love to offer more comprehensive support.\\nPlease fill out this form and we'll set up a dedicated support Slack channel.\\n\\nQuick Install\\n\\npip install langchain\\n\\nð\\x9f¤” What is this?\\n\\nLarge language models (LLMs) are emerging as a transformative technology, enabling\\ndevelopers to build applications that they previously could not.\\nBut using these LLMs in isolation is often not enough to\\ncreate a truly powerful app - the real power comes when you can combine them with other sources of computation or knowledge.\\n\\nThis library is aimed at assisting in the development of those types of applications. Common examples of these types of applications include:\\n\\nâ\\x9d“ Question Answering over specific documents\\n\\nDocumentation\\n\\nEnd-to-end Example: Question Answering over Notion Database\\n\\nð\\x9f’¬ Chatbots\\n\\nDocumentation\\n\\nEnd-to-end Example: Chat-LangChain\\n\\nð\\x9f¤\\x96 Agents\\n\\nDocumentation\\n\\nEnd-to-end Example: GPT+WolframAlpha\\n\\nð\\x9f“\\x96 Documentation\\n\\nPlease see here for full documentation on:\\n\\nGetting started (installation, setting up the environment, simple examples)\\n\\nHow-To examples (demos, integrations, helper functions)\\n\\nReference (full API docs)\\n  Resources (high-level explanation of core concepts)\\n\\nð\\x9f\\x9a\\x80 What can this help with?\\n\\nThere are six main areas that LangChain is designed to help with.\\nThese are, in increasing order of complexity:\\n\\nð\\x9f“\\x83 LLMs and Prompts:\\n\\nThis includes prompt management, prompt optimization, generic interface for all LLMs, and common utilities for working with LLMs.\\n\\nð\\x9f”\\x97 Chains:\\n\\nChains 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.\\n\\nð\\x9f“\\x9a Data Augmented Generation:\\n\\nData Augmented Generation involves specific types of chains that first interact with an external datasource to fetch data to use in the generation step. Examples of this include summarization of long pieces of text and question/answering over specific data sources.\\n\\nð\\x9f¤\\x96 Agents:\\n\\nAgents 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.\\n\\nð\\x9f§\\xa0 Memory:\\n\\nMemory 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.\\n\\nð\\x9f§\\x90 Evaluation:\\n\\n[BETA] 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.\\n\\nFor more information on these concepts, please see our full documentation.\\n\\nð\\x9f’\\x81 Contributing\\n\\nAs an open source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infra, or better documentation.\\n\\nFor detailed information on how to contribute, see here.\", lookup_str='', metadata={'source': '../../../../README.md'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "525d6b67",
+   "metadata": {},
+   "source": [
+    "## Retain Elements\n",
+    "\n",
+    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "064f9162",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredMarkdownLoader(\"../../../../README.md\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "abefbbdb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "a547c534",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Document(page_content='ð\\x9f¦\\x9cï¸\\x8fð\\x9f”\\x97 LangChain', lookup_str='', metadata={'source': '../../../../README.md', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0)"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "data[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "381d4139",
+   "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": "3.8.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/microsoft_word.ipynb

@@ -1,145 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "34c90eed",
-   "metadata": {},
-   "source": [
-    "# Microsoft Word\n",
-    "\n",
-    "This notebook shows how to load text from Microsoft word documents."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "28ded768",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.document_loaders import UnstructuredDocxLoader"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "f1f26035",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredDocxLoader('example_data/fake.docx')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "2c87dde9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "0e4a884c",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5d1472e9",
-   "metadata": {},
-   "source": [
-    "## Retain Elements\n",
-    "\n",
-    "Under the hood, Unstructured creates different \"elements\" for different chunks of text. By default we combine those together, but you can easily keep that separation by specifying `mode=\"elements\"`."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "93abf60b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "loader = UnstructuredDocxLoader('example_data/fake.docx', mode=\"elements\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "c35cdbcc",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data = loader.load()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "fae2d730",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='Lorem ipsum dolor sit amet.', lookup_str='', metadata={'source': 'example_data/fake.docx'}, lookup_index=0)]"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "data"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "961a7b1d",
-   "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
-}

docs/modules/document_loaders/examples/unstructured_file.ipynb

@@ -158,7 +158,72 @@
   },
   {
    "cell_type": "markdown",
-   "id": "7874d01d",
+   "id": "672733fd",
+   "metadata": {},
+   "source": [
+    "## Define a Partitioning Strategy\n",
+    "\n",
+    "Unstructured document loader allow users to pass in a `strategy` parameter that lets `unstructured` know how to partitioning the document. Currently supported strategies are `\"hi_res\"` (the default) and `\"fast\"`. Hi res partitioning strategies are more accurate, but take longer to process. Fast strategies partition the document more quickly, but trade-off accuracy. Not all document types have separate hi res and fast partitioning strategies. For those document types, the `strategy` kwarg is ignored. In some cases, the high res strategy will fallback to fast if there is a dependency missing (i.e. a model for document partitioning). You can see how to apply a strategy to an `UnstructuredFileLoader` below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "767238a4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredFileLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "9518b425",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = UnstructuredFileLoader(\"layout-parser-paper-fast.pdf\", strategy=\"fast\", mode=\"elements\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "645f29e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "60685353",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content='1', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
+       " Document(page_content='2', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
+       " Document(page_content='0', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
+       " Document(page_content='2', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'UncategorizedText'}, lookup_index=0),\n",
+       " Document(page_content='n', lookup_str='', metadata={'source': 'layout-parser-paper-fast.pdf', 'filename': 'layout-parser-paper-fast.pdf', 'page_number': 1, 'category': 'Title'}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[:5]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8de9ef16",
    "metadata": {},
    "source": [
     "## PDF Example\n",
@@ -166,7 +231,6 @@
     "Processing PDF documents works exactly the same way. Unstructured detects the file type and extracts the same types of `elements`. "
    ]
   },
-
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -225,7 +289,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "8ca8a648",
+   "id": "f52b04cb",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -247,7 +311,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.8.13"
   }
  },
  "nbformat": 4,

docs/modules/document_loaders/examples/word_document.ipynb

@@ -27,7 +27,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = UnstructuredWordDocumentLoader(\"fake.docx\")"
+    "loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\")"
    ]
   },
   {
@@ -78,7 +78,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "loader = UnstructuredWordDocumentLoader(\"fake.docx\", mode=\"elements\")"
+    "loader = UnstructuredWordDocumentLoader(\"example_data/fake.docx\", mode=\"elements\")"
    ]
   },
   {

docs/modules/document_loaders/examples/youtube.ipynb

@@ -7,22 +7,23 @@
    "source": [
     "# YouTube\n",
     "\n",
-    "How to load documents from YouTube transcripts."
+    "How to load documents from YouTube transcripts.\n",
+    "\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
-   "id": "da4a867f",
+   "execution_count": null,
+   "id": "427d5745",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.document_loaders import YoutubeLoader"
+    "from langchain.document_loaders import YoutubeLoader\n"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "id": "34a25b57",
    "metadata": {
     "scrolled": true
@@ -34,7 +35,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "id": "bc8b308a",
    "metadata": {},
    "outputs": [],
@@ -44,21 +45,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "d073dd36",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='LADIES AND GENTLEMEN, PEDRO PASCAL! [ CHEERS AND APPLAUSE ] >> THANK YOU, THANK YOU. THANK YOU VERY MUCH. I\\'M SO EXCITED TO BE HERE. THANK YOU. I SPENT THE LAST YEAR SHOOTING A SHOW CALLED \"THE LAST OF US\" ON HBO. FOR SOME HBO SHOES, YOU GET TO SHOOT IN A FIVE STAR ITALIAN RESORT SURROUNDED BY BEAUTIFUL PEOPLE, BUT I SAID, NO, THAT\\'S TOO EASY. I WANT TO SHOOT IN A FREEZING CANADIAN FOREST WHILE BEING CHASED AROUND BY A GUY WHOSE HEAD LOOKS LIKE A GENITAL WART. IT IS AN HONOR BEING A PART OF THESE HUGE FRANCHISEs LIKE \"GAME OF THRONES\" AND \"STAR WARS,\" BUT I\\'M STILL GETTING USED TO PEOPLE RECOGNIZING ME. THE OTHER DAY, A GUY STOPPED ME ON THE STREET AND SAYS, MY SON LOVES \"THE MANDALORIAN\" AND THE NEXT THING I KNOW, I\\'M FACE TIMING WITH A 6-YEAR-OLD WHO HAS NO IDEA WHO I AM BECAUSE MY CHARACTER WEARS A MASK THE ENTIRE SHOW. THE GUY IS LIKE, DO THE MANDO VOICE, BUT IT\\'S LIKE A BEDROOM VOICE. WITHOUT THE MASK, IT JUST SOUNDS PORNY. PEOPLE WALKING BY ON THE STREET SEE ME WHISPERING TO A 6-YEAR-OLD KID. I CAN BRING YOU IN WARM, OR I CAN BRING YOU IN COLD. EVEN THOUGH I CAME TO THE U.S. WHEN I WAS LITTLE, I WAS BORN IN CHILE, AND I HAVE 34 FIRST COUSINS WHO ARE STILL THERE. THEY\\'RE VERY PROUD OF ME. I KNOW THEY\\'RE PROUD BECAUSE THEY GIVE MY PHONE NUMBER TO EVERY PERSON THEY MEET, WHICH MEANS EVERY DAY, SOMEONE IN SANTIAGO WILL TEXT ME STUFF LIKE, CAN YOU COME TO MY WEDDING, OR CAN YOU SING MY PRIEST HAPPY BIRTHDAY, OR IS BABY YODA MEAN IN REAL LIFE. SO I HAVE TO BE LIKE NO, NO, AND HIS NAME IS GROGU. BUT MY COUSINS WEREN\\'T ALWAYS SO PROUD. EARLY IN MY CAREER, I PLAYED SMALL PARTS IN EVERY CRIME SHOW. I EVEN PLAYED TWO DIFFERENT CHARACTERS ON \"LAW AND ORDER.\" TITO CABASSA WHO LOOKED LIKE THIS. AND ONE YEAR LATER, I PLAYED REGGIE LUCKMAN WHO LOOKS LIKE THIS. AND THAT, MY FRIENDS, IS CALLED RANGE. BUT IT IS AMAZING TO BE HERE, LIKE I SAID. I WAS BORN IN CHILE, AND NINE MONTHS LATER, MY PARENTS FLED AND BROUGHT ME AND MY SISTER TO THE U.S. THEY WERE SO BRAVE, AND WITHOUT THEM, I WOULDN\\'T BE HERE IN THIS WONDERFUL COUNTRY, AND I CERTAINLY WOULDN\\'T BE STANDING HERE WITH YOU ALL TONIGHT. SO TO ALL MY FAMILY WATCHING IN CHILE, I WANT TO SAY [ SPEAKING NON-ENGLISH ] WHICH MEANS, I LOVE YOU, I MISS YOU, AND STOP GIVING OUT MY PHONE NUMBER. WE\\'VE GOT AN AMAZING SHOW FOR YOU TONIGHT. COLDPLAY IS HERE, SO STICK', lookup_str='', metadata={'source': 'QsYGlZkevEg', 'title': 'Pedro Pascal Monologue - SNL', 'description': 'First-time host Pedro Pascal talks about filming The Last of Us and being recognized by fans.\\n\\nSaturday Night Live. Stream now on Peacock: https://pck.tv/3uQxh4q\\n\\nSubscribe to SNL: https://goo.gl/tUsXwM\\nStream Current Full Episodes: http://www.nbc.com/saturday-night-live\\n\\nWATCH PAST SNL SEASONS\\nGoogle Play - http://bit.ly/SNLGooglePlay\\niTunes - http://bit.ly/SNLiTunes\\n\\nSNL ON SOCIAL\\nSNL Instagram: http://instagram.com/nbcsnl\\nSNL Facebook: https://www.facebook.com/snl\\nSNL Twitter: https://twitter.com/nbcsnl\\nSNL TikTok: https://www.tiktok.com/@nbcsnl\\n\\nGET MORE NBC\\nLike NBC: http://Facebook.com/NBC\\nFollow NBC: http://Twitter.com/NBC\\nNBC Tumblr: http://NBCtv.tumblr.com/\\nYouTube: http://www.youtube.com/nbc\\nNBC Instagram: http://instagram.com/nbc\\n\\n#SNL #PedroPascal #SNL48 #Coldplay', 'view_count': 1175057, 'thumbnail_url': 'https://i.ytimg.com/vi/QsYGlZkevEg/sddefault.jpg', 'publish_date': datetime.datetime(2023, 2, 4, 0, 0), 'length': 224, 'author': 'Saturday Night Live'}, lookup_index=0)]"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "loader.load()"
    ]
@@ -73,7 +63,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "id": "ba28af69",
    "metadata": {},
    "outputs": [],
@@ -83,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "id": "9b8ea390",
    "metadata": {},
    "outputs": [],
@@ -93,24 +83,61 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": null,
    "id": "97b98e92",
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "[Document(page_content='LADIES AND GENTLEMEN, PEDRO PASCAL! [ CHEERS AND APPLAUSE ] >> THANK YOU, THANK YOU. THANK YOU VERY MUCH. I\\'M SO EXCITED TO BE HERE. THANK YOU. I SPENT THE LAST YEAR SHOOTING A SHOW CALLED \"THE LAST OF US\" ON HBO. FOR SOME HBO SHOES, YOU GET TO SHOOT IN A FIVE STAR ITALIAN RESORT SURROUNDED BY BEAUTIFUL PEOPLE, BUT I SAID, NO, THAT\\'S TOO EASY. I WANT TO SHOOT IN A FREEZING CANADIAN FOREST WHILE BEING CHASED AROUND BY A GUY WHOSE HEAD LOOKS LIKE A GENITAL WART. IT IS AN HONOR BEING A PART OF THESE HUGE FRANCHISEs LIKE \"GAME OF THRONES\" AND \"STAR WARS,\" BUT I\\'M STILL GETTING USED TO PEOPLE RECOGNIZING ME. THE OTHER DAY, A GUY STOPPED ME ON THE STREET AND SAYS, MY SON LOVES \"THE MANDALORIAN\" AND THE NEXT THING I KNOW, I\\'M FACE TIMING WITH A 6-YEAR-OLD WHO HAS NO IDEA WHO I AM BECAUSE MY CHARACTER WEARS A MASK THE ENTIRE SHOW. THE GUY IS LIKE, DO THE MANDO VOICE, BUT IT\\'S LIKE A BEDROOM VOICE. WITHOUT THE MASK, IT JUST SOUNDS PORNY. PEOPLE WALKING BY ON THE STREET SEE ME WHISPERING TO A 6-YEAR-OLD KID. I CAN BRING YOU IN WARM, OR I CAN BRING YOU IN COLD. EVEN THOUGH I CAME TO THE U.S. WHEN I WAS LITTLE, I WAS BORN IN CHILE, AND I HAVE 34 FIRST COUSINS WHO ARE STILL THERE. THEY\\'RE VERY PROUD OF ME. I KNOW THEY\\'RE PROUD BECAUSE THEY GIVE MY PHONE NUMBER TO EVERY PERSON THEY MEET, WHICH MEANS EVERY DAY, SOMEONE IN SANTIAGO WILL TEXT ME STUFF LIKE, CAN YOU COME TO MY WEDDING, OR CAN YOU SING MY PRIEST HAPPY BIRTHDAY, OR IS BABY YODA MEAN IN REAL LIFE. SO I HAVE TO BE LIKE NO, NO, AND HIS NAME IS GROGU. BUT MY COUSINS WEREN\\'T ALWAYS SO PROUD. EARLY IN MY CAREER, I PLAYED SMALL PARTS IN EVERY CRIME SHOW. I EVEN PLAYED TWO DIFFERENT CHARACTERS ON \"LAW AND ORDER.\" TITO CABASSA WHO LOOKED LIKE THIS. AND ONE YEAR LATER, I PLAYED REGGIE LUCKMAN WHO LOOKS LIKE THIS. AND THAT, MY FRIENDS, IS CALLED RANGE. BUT IT IS AMAZING TO BE HERE, LIKE I SAID. I WAS BORN IN CHILE, AND NINE MONTHS LATER, MY PARENTS FLED AND BROUGHT ME AND MY SISTER TO THE U.S. THEY WERE SO BRAVE, AND WITHOUT THEM, I WOULDN\\'T BE HERE IN THIS WONDERFUL COUNTRY, AND I CERTAINLY WOULDN\\'T BE STANDING HERE WITH YOU ALL TONIGHT. SO TO ALL MY FAMILY WATCHING IN CHILE, I WANT TO SAY [ SPEAKING NON-ENGLISH ] WHICH MEANS, I LOVE YOU, I MISS YOU, AND STOP GIVING OUT MY PHONE NUMBER. WE\\'VE GOT AN AMAZING SHOW FOR YOU TONIGHT. COLDPLAY IS HERE, SO STICK', lookup_str='', metadata={'source': 'QsYGlZkevEg', 'title': 'Pedro Pascal Monologue - SNL', 'description': 'First-time host Pedro Pascal talks about filming The Last of Us and being recognized by fans.\\n\\nSaturday Night Live. Stream now on Peacock: https://pck.tv/3uQxh4q\\n\\nSubscribe to SNL: https://goo.gl/tUsXwM\\nStream Current Full Episodes: http://www.nbc.com/saturday-night-live\\n\\nWATCH PAST SNL SEASONS\\nGoogle Play - http://bit.ly/SNLGooglePlay\\niTunes - http://bit.ly/SNLiTunes\\n\\nSNL ON SOCIAL\\nSNL Instagram: http://instagram.com/nbcsnl\\nSNL Facebook: https://www.facebook.com/snl\\nSNL Twitter: https://twitter.com/nbcsnl\\nSNL TikTok: https://www.tiktok.com/@nbcsnl\\n\\nGET MORE NBC\\nLike NBC: http://Facebook.com/NBC\\nFollow NBC: http://Twitter.com/NBC\\nNBC Tumblr: http://NBCtv.tumblr.com/\\nYouTube: http://www.youtube.com/nbc\\nNBC Instagram: http://instagram.com/nbc\\n\\n#SNL #PedroPascal #SNL48 #Coldplay', 'view_count': 1175057, 'thumbnail_url': 'https://i.ytimg.com/vi/QsYGlZkevEg/sddefault.jpg', 'publish_date': datetime.datetime(2023, 2, 4, 0, 0), 'length': 224, 'author': 'Saturday Night Live'}, lookup_index=0)]"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "loader.load()"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "65796cc5",
+   "metadata": {},
+   "source": [
+    "## YouTube loader from Google Cloud\n",
+    "\n",
+    "### Prerequisites\n",
+    "\n",
+    "1. Create a Google Cloud project or use an existing project\n",
+    "1. Enable the [Youtube Api](https://console.cloud.google.com/apis/enableflow?apiid=youtube.googleapis.com&project=sixth-grammar-344520)\n",
+    "1. [Authorize credentials for desktop app](https://developers.google.com/drive/api/quickstart/python#authorize_credentials_for_a_desktop_application)\n",
+    "1. `pip install --upgrade google-api-python-client google-auth-httplib2 google-auth-oauthlib youtube-transcript-api`\n",
+    "\n",
+    "### 🧑 Instructions for ingesting your Google Docs data\n",
+    "By default, the `GoogleDriveLoader` expects the `credentials.json` file to be `~/.credentials/credentials.json`, but this is configurable using the `credentials_file` keyword argument. Same thing with `token.json`. Note that `token.json` will be created automatically the first time you use the loader.\n",
+    "\n",
+    "`GoogleApiYoutubeLoader` can load from a list of Google Docs document ids or a folder id. You can obtain your folder and document id from the URL:\n",
+    "Note depending on your set up, the `service_account_path` needs to be set up. See [here](https://developers.google.com/drive/api/v3/quickstart/python) for more details."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c345bc43",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import GoogleApiClient, GoogleApiYoutubeLoader\n",
+    "\n",
+    "# Init the GoogleApiClient \n",
+    "from pathlib import Path\n",
+    "\n",
+    "\n",
+    "google_api_client = GoogleApiClient(credentials_path=Path(\"your_path_creds.json\"))\n",
+    "\n",
+    "\n",
+    "# Use a Channel\n",
+    "youtube_loader_channel = GoogleApiYoutubeLoader(google_api_client=google_api_client, channel_name=\"Reducible\",captions_language=\"en\")\n",
+    "\n",
+    "# Use Youtube Ids\n",
+    "\n",
+    "youtube_loader_ids = GoogleApiYoutubeLoader(google_api_client=google_api_client, video_ids=[\"TrdevFK_am4\"], add_video_info=True)\n",
+    "\n",
+    "# returns a list of Documents\n",
+    "youtube_loader_channel.load()"
+   ]
   }
  ],
  "metadata": {
@@ -130,6 +157,11 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.9.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "604c1013f65d31a2eb1fca07aae054bedd5a5a0d272dbb31e502c81f0b254b99"
+   }
   }
  },
  "nbformat": 4,

docs/modules/document_loaders/how_to_guides.rst

@@ -21,8 +21,6 @@ There are a lot of different document loaders that LangChain supports. Below are
 
 `GoogleDrive <./examples/googledrive.html>`_: A walkthrough of how to load data from Google drive.
 
-`Microsoft Word <./examples/microsoft_word.html>`_: A walkthrough of how to load data from Microsoft Word files.
-
 `Obsidian <./examples/obsidian.html>`_: A walkthrough of how to load data from an Obsidian file dump.
 
 `Roam <./examples/roam.html>`_: A walkthrough of how to load data from a Roam file export.
@@ -55,12 +53,32 @@ There are a lot of different document loaders that LangChain supports. Below are
 
 `Airbyte Json <./examples/airbyte_json.html>`_: A walkthrough of how to load data from a local Airbyte JSON file.
 
-`Online PDF <./examples/online_pdf.html>`_: A walkthrough of how to load data from an online PDF.
-
 `CoNLL-U <./examples/CoNLL-U.html>`_: A walkthrough of how to load data from a ConLL-U file.
 
 `iFixit <./examples/ifixit.html>`_: A walkthrough of how to search and load data like guides, technical Q&A's, and device wikis from iFixit.com
 
+`Notebook <./examples/notebook.html>`_: A walkthrough of how to load data from .ipynb notebook.
+
+`Copypaste <./examples/copypaste.html>`_: A walkthrough of how to load a document object from something you just want to copy and paste.
+
+`CSV <./examples/csv.html>`_: A walkthrough of how to load data from a .csv file.
+
+`Facebook Chat <./examples/facebook_chat.html>`_: A walkthrough of how to load data from a Facebook Chat json file.
+
+`Image <./examples/image.html>`_: A walkthrough of how to load images such as JPGs PNGs into a document format that can be used downstream.
+
+`Markdown <./examples/markdown.html>`_: A walkthrough of how to load data from a markdown file.
+
+`SRT <./examples/srt.html>`_: A walkthrough of how to load data from a subtitle (`.srt`) file.
+
+`Telegram <./examples/telegram.html>`_: A walkthrough of how to load data from a Telegram Chat json file.
+
+`URL <./examples/url.html>`_: A walkthrough of how to load HTML documents from a list of URLs into a document format that we can use downstream.
+
+`Word Document <./examples/word_document.html>`_: A walkthrough of how to load data from Microsoft Word files.
+
+`Blackboard <./examples/blackboard.html>`_: A walkthrough of how to load data from a Blackboard course.
+
 .. toctree::
    :maxdepth: 1
    :glob:

docs/modules/indexes.rst

@@ -3,16 +3,24 @@ Indexes
 
 Indexes refer to ways to structure documents so that LLMs can best interact with them.
 This module contains utility functions for working with documents, different types of indexes, and then examples for using those indexes in chains.
-LangChain provides common indices for working with data (most prominently support for vector databases).
-For more complicated index structures, it is worth checking out `GPTIndex <https://gpt-index.readthedocs.io/en/latest/index.html>`_.
+
+The most common way that indexes are used in chains is in a "retrieval" step.
+This step refers to taking a user's query and returning the most relevant documents.
+We draw this distinction because (1) an index can be used for other things besides retrieval, and (2) retrieval can use other logic besides an index to find relevant documents.
+We therefor have a concept of a "Retriever" interface - this is the interface that most chains work with.
+
+Most of the time when we talk about indexes and retrieval we are talking about indexing and retrieving unstructured data (like text documents).
+For interacting with structured data (SQL tables, etc) or APIs, please see the corresponding use case sections for links to relevant functionality.
+The primary index and retrieval types supported by LangChain are currently centered around vector databases, and therefore
+a lot of the functionality we dive deep on those topics.
 
 The following sections of documentation are provided:
 
-- `Getting Started <./indexes/getting_started.html>`_: An overview of all the functionality LangChain provides for working with indexes.
+- `Getting Started <./indexes/getting_started.html>`_: An overview of the base "Retriever" interface, and then all the functionality LangChain provides for working with indexes.
 
 - `Key Concepts <./indexes/key_concepts.html>`_: A conceptual guide going over the various concepts related to indexes and the tools needed to create them.
 
-- `How-To Guides <./indexes/how_to_guides.html>`_: A collection of how-to guides. These highlight how to use all the relevant tools, the different types of vector databases, and how to use indexes in chains.
+- `How-To Guides <./indexes/how_to_guides.html>`_: A collection of how-to guides. These highlight how to use all the relevant tools, the different types of vector databases, different types of retrievers, and how to use retrievers and indexes in chains.
 
 
 .. toctree::

docs/modules/indexes/chain_examples/chat_vector_db.ipynb

@@ -5,9 +5,9 @@
    "id": "134a0785",
    "metadata": {},
    "source": [
-    "# Chat Vector DB\n",
+    "# Chat Index\n",
     "\n",
-    "This notebook goes over how to set up a chain to chat with a vector database. The only difference between this chain and the [VectorDBQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
+    "This notebook goes over how to set up a chain to chat with an index. The only difference between this chain and the [RetrievalQAChain](./vector_db_qa.ipynb) is that this allows for passing in of a chat history which can be used to allow for follow up questions."
    ]
   },
   {
@@ -23,7 +23,7 @@
     "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.llms import OpenAI\n",
-    "from langchain.chains import ChatVectorDBChain"
+    "from langchain.chains import ConversationalRetrievalChain"
    ]
   },
   {
@@ -109,7 +109,7 @@
    "id": "3c96b118",
    "metadata": {},
    "source": [
-    "We now initialize the ChatVectorDBChain"
+    "We now initialize the ConversationalRetrievalChain"
    ]
   },
   {
@@ -121,7 +121,7 @@
    },
    "outputs": [],
    "source": [
-    "qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore)"
+    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore)"
    ]
   },
   {
@@ -220,22 +220,22 @@
    "metadata": {},
    "source": [
     "## Return Source Documents\n",
-    "You can also easily return source documents from the ChatVectorDBChain. This is useful for when you want to inspect what documents were returned."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "562769c6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)"
+    "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": 11,
+   "id": "562769c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
    "id": "ea478300",
    "metadata": {},
    "outputs": [],
@@ -247,17 +247,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 13,
    "id": "4cb75b4e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
+       "Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -268,64 +268,60 @@
   },
   {
    "cell_type": "markdown",
+   "id": "4f49beab",
+   "metadata": {},
    "source": [
-    "## Chat Vector DB with `search_distance`\n",
+    "## 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."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 14,
+   "id": "5ed8d612",
+   "metadata": {},
    "outputs": [],
    "source": [
     "vectordbkwargs = {\"search_distance\": 0.9}"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 15,
+   "id": "6a7b3459",
+   "metadata": {},
    "outputs": [],
    "source": [
-    "qa = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, return_source_documents=True)\n",
+    "qa = ConversationalRetrievalChain.from_llm(OpenAI(temperature=0), vectorstore, 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})"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "id": "99b96dae",
+   "metadata": {},
    "source": [
-    "## Chat Vector DB with `map_reduce`\n",
-    "We can also use different types of combine document chains with the Chat Vector DB chain."
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+    "## ConversationalRetrievalChain with `map_reduce`\n",
+    "We can also use different types of combine document chains with the ConversationalRetrievalChain chain."
+   ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 16,
    "id": "e53a9d66",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.chains import LLMChain\n",
     "from langchain.chains.question_answering import load_qa_chain\n",
-    "from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT"
+    "from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 19,
    "id": "bf205e35",
    "metadata": {},
    "outputs": [],
@@ -334,8 +330,8 @@
     "question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)\n",
     "doc_chain = load_qa_chain(llm, chain_type=\"map_reduce\")\n",
     "\n",
-    "chain = ChatVectorDBChain(\n",
-    "    vectorstore=vectorstore,\n",
+    "chain = ConversationalRetrievalChain(\n",
+    "    retriever=vectorstore.as_retriever(),\n",
     "    question_generator=question_generator,\n",
     "    combine_docs_chain=doc_chain,\n",
     ")"
@@ -343,7 +339,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 20,
    "id": "78155887",
    "metadata": {},
    "outputs": [],
@@ -355,7 +351,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 21,
    "id": "e54b5fa2",
    "metadata": {},
    "outputs": [
@@ -365,7 +361,7 @@
        "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 11,
+     "execution_count": 21,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -379,14 +375,14 @@
    "id": "a2fe6b14",
    "metadata": {},
    "source": [
-    "## Chat Vector DB with Question Answering with sources\n",
+    "## 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": 12,
+   "execution_count": 22,
    "id": "d1058fd2",
    "metadata": {},
    "outputs": [],
@@ -396,7 +392,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 23,
    "id": "a6594482",
    "metadata": {},
    "outputs": [],
@@ -405,8 +401,8 @@
     "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 = ChatVectorDBChain(\n",
-    "    vectorstore=vectorstore,\n",
+    "chain = ConversationalRetrievalChain(\n",
+    "    retriever=vectorstore.as_retriever(),\n",
     "    question_generator=question_generator,\n",
     "    combine_docs_chain=doc_chain,\n",
     ")"
@@ -414,7 +410,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 24,
    "id": "e2badd21",
    "metadata": {},
    "outputs": [],
@@ -426,7 +422,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 25,
    "id": "edb31fe5",
    "metadata": {},
    "outputs": [
@@ -436,7 +432,7 @@
        "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\nSOURCES: ../../state_of_the_union.txt\""
       ]
      },
-     "execution_count": 16,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -450,14 +446,14 @@
    "id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
    "metadata": {},
    "source": [
-    "## Chat Vector DB with streaming to `stdout`\n",
+    "## 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": 10,
+   "execution_count": 26,
    "id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
    "metadata": {
     "tags": []
@@ -467,7 +463,7 @@
     "from langchain.chains.llm import LLMChain\n",
     "from langchain.callbacks.base import CallbackManager\n",
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "from langchain.chains.chat_vector_db.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
+    "from langchain.chains.chat_index.prompts import CONDENSE_QUESTION_PROMPT, QA_PROMPT\n",
     "from langchain.chains.question_answering import load_qa_chain\n",
     "\n",
     "# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
@@ -478,12 +474,13 @@
     "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 = ChatVectorDBChain(vectorstore=vectorstore, combine_docs_chain=doc_chain, question_generator=question_generator)"
+    "qa = ConversationalRetrievalChain(\n",
+    "    retriever=vectorstore.as_retriever(), combine_docs_chain=doc_chain, question_generator=question_generator)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 27,
    "id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
    "metadata": {
     "tags": []
@@ -505,7 +502,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 28,
    "id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
    "metadata": {
     "tags": []
@@ -524,6 +521,71 @@
     "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": 29,
+   "id": "a7ba9d8c",
+   "metadata": {},
+   "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(OpenAI(temperature=0), vectorstore, get_chat_history=get_chat_history)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "a3e33c0d",
+   "metadata": {},
+   "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": 31,
+   "id": "936dc62f",
+   "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, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b8c26901",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/modules/indexes/chain_examples/graph_qa.ipynb

@@ -178,16 +178,16 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new GraphQAChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new GraphQAChain chain...\u001b[0m\n",
       "Entities Extracted:\n",
-      "\u001B[32;1m\u001B[1;3m Intel\u001B[0m\n",
+      "\u001b[32;1m\u001b[1;3m Intel\u001b[0m\n",
       "Full Context:\n",
-      "\u001B[32;1m\u001B[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
+      "\u001b[32;1m\u001b[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
       "Intel is building state-of-the-art factories\n",
       "Intel is creating 10,000 new good-paying jobs\n",
-      "Intel is helping build Silicon Valley\u001B[0m\n",
+      "Intel is helping build Silicon Valley\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -205,10 +205,76 @@
     "chain.run(\"what is Intel going to build?\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "410aafa0",
+   "metadata": {},
+   "source": [
+    "## Save the graph\n",
+    "We can also save and load the graph."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "bc72cca0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "graph.write_to_gml(\"graph.gml\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "652760ad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.indexes.graph import NetworkxEntityGraph"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "eae591fe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loaded_graph = NetworkxEntityGraph.from_gml(\"graph.gml\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "9439d419",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[('Intel', '$20 billion semiconductor \"mega site\"', 'is going to build'),\n",
+       " ('Intel', 'state-of-the-art factories', 'is building'),\n",
+       " ('Intel', '10,000 new good-paying jobs', 'is creating'),\n",
+       " ('Intel', 'Silicon Valley', 'is helping build'),\n",
+       " ('Field of dreams',\n",
+       "  \"America's future will be built\",\n",
+       "  'is the ground on which')]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loaded_graph.get_triples()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f70b9ada",
+   "id": "045796cf",
    "metadata": {},
    "outputs": [],
    "source": []

docs/modules/indexes/chain_examples/qa_with_sources.ipynb

@@ -635,7 +635,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts.base import RegexParser\n",
+    "from langchain.output_parsers import RegexParser\n",
     "\n",
     "output_parser = RegexParser(\n",
     "    regex=r\"(.*?)\\nScore: (.*)\",\n",
@@ -732,4 +732,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

docs/modules/indexes/chain_examples/question_answering.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Question Answering\n",
     "\n",
-    "This notebook walks through how to use LangChain for question answering over a list of documents. It covers four different types of chains: `stuff`, `map_reduce`, `refine`, `map-rerank`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
+    "This notebook walks through how to use LangChain for question answering over a list of documents. It covers four different types of chains: `stuff`, `map_reduce`, `refine`, `map_rerank`. For a more in depth explanation of what these chain types are, see [here](../combine_docs.md)."
    ]
   },
   {
@@ -635,7 +635,7 @@
     }
    ],
    "source": [
-    "from langchain.prompts.base import RegexParser\n",
+    "from langchain.output_parsers import RegexParser\n",
     "\n",
     "output_parser = RegexParser(\n",
     "    regex=r\"(.*?)\\nScore: (.*)\",\n",

docs/modules/indexes/chain_examples/vector_db_qa.ipynb

@@ -5,9 +5,9 @@
    "id": "07c1e3b9",
    "metadata": {},
    "source": [
-    "# Vector DB Question/Answering\n",
+    "# Retrieval Question/Answering\n",
     "\n",
-    "This example showcases question answering over a vector database."
+    "This example showcases question answering over an index."
    ]
   },
   {
@@ -20,7 +20,8 @@
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain import OpenAI, VectorDBQA"
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import RetrievalQA"
    ]
   },
   {
@@ -56,7 +57,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch)"
+    "qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever())"
    ]
   },
   {
@@ -68,7 +69,7 @@
     {
      "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 federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+       "\" The president said that she is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support, from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
      "execution_count": 4,
@@ -87,7 +88,7 @@
    "metadata": {},
    "source": [
     "## Chain Type\n",
-    "You can easily specify different chain types to load and use in the VectorDBQA chain. For a more detailed walkthrough of these types, please see [this notebook](question_answering.ipynb).\n",
+    "You can easily specify different chain types to load and use in the RetrievalQA chain. For a more detailed walkthrough of these types, please see [this notebook](question_answering.ipynb).\n",
     "\n",
     "There are two ways to load different chain types. First, you can specify the chain type argument in the `from_chain_type` method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to `map_reduce`."
    ]
@@ -99,7 +100,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"map_reduce\", vectorstore=docsearch)"
+    "qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"map_reduce\", retriever=docsearch.as_retriever())"
    ]
   },
   {
@@ -111,7 +112,7 @@
     {
      "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, a former federal public defender, from a family of public school educators and police officers, a consensus builder, and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
+       "\" The president said that Judge Ketanji Brown Jackson is one of our nation's top legal minds, a former top litigator in private practice and a former federal public defender, from a family of public school educators and police officers, a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
      "execution_count": 6,
@@ -129,24 +130,24 @@
    "id": "60368f38",
    "metadata": {},
    "source": [
-    "The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](question_answering.ipynb)) and then pass that directly to the the VectorDBQA chain with the `combine_documents_chain` parameter. For example:"
+    "The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](question_answering.ipynb)) and then pass that directly to the the RetrievalQA chain with the `combine_documents_chain` parameter. For example:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 9,
    "id": "7b403f0d",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.chains.question_answering import load_qa_chain\n",
     "qa_chain = load_qa_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
-    "qa = VectorDBQA(combine_documents_chain=qa_chain, vectorstore=docsearch)"
+    "qa = RetrievalQA(combine_documents_chain=qa_chain, retriever=docsearch.as_retriever())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 10,
    "id": "9e04a9ac",
    "metadata": {},
    "outputs": [
@@ -156,7 +157,7 @@
        "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 19,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -177,7 +178,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 11,
    "id": "a45232a2",
    "metadata": {},
    "outputs": [],
@@ -196,28 +197,28 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 13,
    "id": "9b5c8d1d",
    "metadata": {},
    "outputs": [],
    "source": [
     "chain_type_kwargs = {\"prompt\": PROMPT}\n",
-    "qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch, chain_type_kwargs=chain_type_kwargs)"
+    "qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 14,
    "id": "26ee7671",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\" Il Presidente ha detto che Ketanji Brown Jackson è uno dei pensatori legali più importanti del nostro Paese, che continuerà l'eccellente eredità di giustizia Breyer. È un ex principale litigante in pratica privata, un ex difensore federale pubblico e appartiene a una famiglia di insegnanti e poliziotti delle scuole pubbliche. È un costruttore di consenso che ha ricevuto un ampio supporto da parte di Fraternal Order of Police e giudici designati da democratici e repubblicani.\""
+       "\" Il presidente ha detto che Ketanji Brown Jackson è una delle menti legali più importanti del paese, che continuerà l'eccellenza di Justice Breyer e che ha ricevuto un ampio sostegno, da Fraternal Order of Police a ex giudici nominati da democratici e repubblicani.\""
       ]
      },
-     "execution_count": 8,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -238,17 +239,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 15,
    "id": "af093aba",
    "metadata": {},
    "outputs": [],
    "source": [
-    "qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=docsearch, return_source_documents=True)"
+    "qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=docsearch.as_retriever(), return_source_documents=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 16,
    "id": "eac11321",
    "metadata": {},
    "outputs": [],
@@ -259,17 +260,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 17,
    "id": "7d75945a",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\" The president said that Ketanji Brown Jackson is one of our nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\""
+       "\" 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 from a family of public school educators and police officers, and that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 10,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -280,20 +281,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 18,
    "id": "35b4f31f",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "[Document(page_content='In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \\n\\nWe cannot let this happen. \\n\\nTonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={}, lookup_index=0),\n",
-       " Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', lookup_str='', metadata={}, lookup_index=0),\n",
-       " Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  \\n\\nFirst, beat the opioid epidemic.', lookup_str='', metadata={}, lookup_index=0),\n",
-       " Document(page_content='As I’ve told Xi Jinping, it is never a good bet to bet against the American people. \\n\\nWe’ll create good jobs for millions of Americans, modernizing roads, airports, ports, and waterways all across America. \\n\\nAnd we’ll do it all to withstand the devastating effects of the climate crisis and promote environmental justice. \\n\\nWe’ll build a national network of 500,000 electric vehicle charging stations, begin to replace poisonous lead pipes—so every child—and every American—has clean water to drink at home and at school, provide affordable high-speed internet for every American—urban, suburban, rural, and tribal communities. \\n\\n4,000 projects have already been announced. \\n\\nAnd tonight, I’m announcing that this year we will start fixing over 65,000 miles of highway and 1,500 bridges in disrepair. \\n\\nWhen we use taxpayer dollars to rebuild America – we are going to Buy American: buy American products to support American jobs.', lookup_str='', metadata={}, lookup_index=0)]"
+       "[Document(page_content='Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \\n\\nTonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \\n\\nOne of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \\n\\nAnd I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \\n\\nAnd if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \\n\\nWe can do both. At our border, we’ve installed new technology like cutting-edge scanners to better detect drug smuggling.  \\n\\nWe’ve set up joint patrols with Mexico and Guatemala to catch more human traffickers.  \\n\\nWe’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \\n\\nWe’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \\n\\nAs I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \\n\\nWhile it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \\n\\nAnd soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \\n\\nSo tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together.  \\n\\nFirst, beat the opioid epidemic.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0),\n",
+       " Document(page_content='Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. \\n\\nAnd as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up.  \\n\\nThat ends on my watch. \\n\\nMedicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. \\n\\nWe’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. \\n\\nLet’s pass the Paycheck Fairness Act and paid leave.  \\n\\nRaise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. \\n\\nLet’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.', lookup_str='', metadata={'source': '../../state_of_the_union.txt'}, lookup_index=0)]"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/modules/indexes/chain_examples/vector_db_qa_with_sources.ipynb

@@ -5,9 +5,9 @@
    "id": "efc5be67",
    "metadata": {},
    "source": [
-    "# VectorDB Question Answering with Sources\n",
+    "# Retrieval Question Answering with Sources\n",
     "\n",
-    "This notebook goes over how to do question-answering with sources over a vector database. It does this by using the `VectorDBQAWithSourcesChain`, which does the lookup of the documents from a vector database. "
+    "This notebook goes over how to do question-answering with sources over an Index. It does this by using the `RetrievalQAWithSourcesChain`, which does the lookup of the documents from an Index. "
    ]
   },
   {
@@ -41,7 +41,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "0e745d99",
    "metadata": {},
    "outputs": [
@@ -50,8 +50,7 @@
      "output_type": "stream",
      "text": [
       "Running Chroma using direct local API.\n",
-      "Using DuckDB in-memory for database. Data will be transient.\n",
-      "Exiting: Cleaning up .chroma directory\n"
+      "Using DuckDB in-memory for database. Data will be transient.\n"
      ]
     }
    ],
@@ -61,40 +60,40 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "8aa571ae",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains import VectorDBQAWithSourcesChain"
+    "from langchain.chains import RetrievalQAWithSourcesChain"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 5,
    "id": "aa859d4c",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain import OpenAI\n",
     "\n",
-    "chain = VectorDBQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"stuff\", vectorstore=docsearch)"
+    "chain = RetrievalQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"stuff\", retriever=docsearch.as_retriever())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 6,
    "id": "8ba36fa7",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'answer': ' The president thanked Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
-       " 'sources': '30-pl'}"
+       "{'answer': ' The president honored Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
+       " 'sources': '31-pl'}"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -109,35 +108,35 @@
    "metadata": {},
    "source": [
     "## Chain Type\n",
-    "You can easily specify different chain types to load and use in the VectorDBQAWithSourcesChain chain. For a more detailed walkthrough of these types, please see [this notebook](qa_with_sources.ipynb).\n",
+    "You can easily specify different chain types to load and use in the RetrievalQAWithSourcesChain chain. For a more detailed walkthrough of these types, please see [this notebook](qa_with_sources.ipynb).\n",
     "\n",
     "There are two ways to load different chain types. First, you can specify the chain type argument in the `from_chain_type` method. This allows you to pass in the name of the chain type you want to use. For example, in the below we change the chain type to `map_reduce`."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "8b35b30a",
    "metadata": {},
    "outputs": [],
    "source": [
-    "chain = VectorDBQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"map_reduce\", vectorstore=docsearch)"
+    "chain = RetrievalQAWithSourcesChain.from_chain_type(OpenAI(temperature=0), chain_type=\"map_reduce\", retriever=docsearch.as_retriever())"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "58bd424f",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
-       " 'sources': '30-pl'}"
+       "{'answer': ' The president said \"Justice Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service.\"\\n',\n",
+       " 'sources': '31-pl'}"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -151,19 +150,19 @@
    "id": "21e14eed",
    "metadata": {},
    "source": [
-    "The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](qa_with_sources.ipynb)) and then pass that directly to the the VectorDBQA chain with the `combine_documents_chain` parameter. For example:"
+    "The above way allows you to really simply change the chain_type, but it does provide a ton of flexibility over parameters to that chain type. If you want to control those parameters, you can load the chain directly (as you did in [this notebook](qa_with_sources.ipynb)) and then pass that directly to the the RetrievalQAWithSourcesChain chain with the `combine_documents_chain` parameter. For example:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "id": "af35f0c6",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.chains.qa_with_sources import load_qa_with_sources_chain\n",
     "qa_chain = load_qa_with_sources_chain(OpenAI(temperature=0), chain_type=\"stuff\")\n",
-    "qa = VectorDBQAWithSourcesChain(combine_documents_chain=qa_chain, vectorstore=docsearch)"
+    "qa = RetrievalQAWithSourcesChain(combine_documents_chain=qa_chain, retriever=docsearch.as_retriever())"
    ]
   },
   {
@@ -175,8 +174,8 @@
     {
      "data": {
       "text/plain": [
-       "{'answer': ' The president honored Justice Stephen Breyer for his service.\\n',\n",
-       " 'sources': '30-pl'}"
+       "{'answer': ' The president honored Justice Breyer for his service and mentioned his legacy of excellence.\\n',\n",
+       " 'sources': '31-pl'}"
       ]
      },
      "execution_count": 11,
@@ -187,6 +186,14 @@
    "source": [
     "qa({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c594296",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

docs/modules/indexes/chain_examples/vector_db_text_generation.ipynb

@@ -28,7 +28,7 @@
     "from langchain.docstore.document import Document\n",
     "import requests\n",
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.vectorstores import Chromama\n",
+    "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.prompts import PromptTemplate\n",
     "import pathlib\n",

docs/modules/indexes/combine_docs.md

@@ -19,20 +19,20 @@ to pass to the language model. This is implemented in LangChain as the `StuffDoc
 
 **Cons:** Most LLMs have a context length, and for large documents (or many documents) this will not work as it will result in a prompt larger than the context length.
 
-The main downside of this method is that it only works one smaller pieces of data. Once you are working
+The main downside of this method is that it only works on smaller pieces of data. Once you are working
 with many pieces of data, this approach is no longer feasible. The next two approaches are designed to help deal with that.
 
 ## Map Reduce
-This method involves an initial prompt on each chunk of data (for summarization tasks, this 
+This method involves running an initial prompt on each chunk of data (for summarization tasks, this 
 could be a summary of that chunk; for question-answering tasks, it could be an answer based solely on that chunk).
 Then a different prompt is run to combine all the initial outputs. This is implemented in the LangChain as the `MapReduceDocumentsChain`.
 
 **Pros:** Can scale to larger documents (and more documents) than `StuffDocumentsChain`. The calls to the LLM on individual documents are independent and can therefore be parallelized.
 
-**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. Loses some information during the final combining call.
+**Cons:** Requires many more calls to the LLM than `StuffDocumentsChain`. Loses some information during the final combined call.
 
 ## Refine
-This method involves an initial prompt on the first chunk of data, generating some output.
+This method involves running an initial prompt on the first chunk of data, generating some output.
 For the remaining documents, that output is passed in, along with the next document, 
 asking the LLM to refine the output based on the new document. 
 
@@ -46,6 +46,6 @@ This method involves running an initial prompt on each chunk of data, that not o
 task but also gives a score for how certain it is in its answer. The responses are then
 ranked according to this score, and the highest score is returned.
 
-**Pros:** Similar pros as `MapReduceDocumentsChain`. Compared to `MapReduceDocumentsChain`, it requires fewer calls.
+**Pros:** Similar pros as `MapReduceDocumentsChain`. Requires fewer calls, compared to `MapReduceDocumentsChain`.
 
 **Cons:** Cannot combine information between documents. This means it is most useful when you expect there to be a single simple answer in a single document.

docs/modules/indexes/examples/embeddings.ipynb

@@ -76,6 +76,129 @@
     "doc_result = embeddings.embed_documents([text])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "bb61bbeb",
+   "metadata": {},
+   "source": [
+    "Let's load the OpenAI Embedding class with first generation models (e.g. text-search-ada-doc-001/text-search-ada-query-001). Note: These are not recommended models - see [here](https://platform.openai.com/docs/guides/embeddings/what-are-embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c0b072cc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a56b70f5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = OpenAIEmbeddings(model_name=\"ada\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14aefb64",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c39ed33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e3221db6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_result = embeddings.embed_documents([text])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c3852491",
+   "metadata": {},
+   "source": [
+    "## AzureOpenAI\n",
+    "\n",
+    "Let's load the OpenAI Embedding class with environment variables set to indicate to use Azure endpoints."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1b40f827",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# set the environment variables needed for openai package to know to reach out to azure\n",
+    "import os\n",
+    "\n",
+    "os.environ[\"OPENAI_API_TYPE\"] = \"azure\"\n",
+    "os.environ[\"OPENAI_API_BASE\"] = \"https://<your-endpoint.openai.azure.com/\"\n",
+    "os.environ[\"OPENAI_API_KEY\"] = \"your AzureOpenAI key\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bb36d16c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = OpenAIEmbeddings(model=\"your-embeddings-deployment-name\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "228abcbb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = \"This is a test document.\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "60dd7fad",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "83bc1a72",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_result = embeddings.embed_documents([text])"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "42f76e43",
@@ -86,6 +209,12 @@
     "Let's load the Cohere Embedding class."
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "ca9e2b3a",
+   "metadata": {},
+   "source": []
+  },
   {
    "cell_type": "code",
    "execution_count": 1,
@@ -103,7 +232,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "embeddings = CohereEmbeddings(cohere_api_key= cohere_api_key)"
+    "embeddings = CohereEmbeddings(cohere_api_key=cohere_api_key)"
    ]
   },
   {
@@ -290,7 +419,9 @@
     }
    ],
    "source": [
-    "embeddings = HuggingFaceInstructEmbeddings(query_instruction=\"Represent the query for retrieval: \")"
+    "embeddings = HuggingFaceInstructEmbeddings(\n",
+    "    query_instruction=\"Represent the query for retrieval: \"\n",
+    ")"
    ]
   },
   {
@@ -332,9 +463,9 @@
    "outputs": [],
    "source": [
     "from langchain.embeddings import (\n",
-    "    SelfHostedEmbeddings, \n",
-    "    SelfHostedHuggingFaceEmbeddings, \n",
-    "    SelfHostedHuggingFaceInstructEmbeddings\n",
+    "    SelfHostedEmbeddings,\n",
+    "    SelfHostedHuggingFaceEmbeddings,\n",
+    "    SelfHostedHuggingFaceInstructEmbeddings,\n",
     ")\n",
     "import runhouse as rh"
    ]
@@ -353,7 +484,7 @@
     "# gpu = rh.cluster(name='rh-a10x', instance_type='g5.2xlarge', provider='aws')\n",
     "\n",
     "# For an existing cluster\n",
-    "# gpu = rh.cluster(ips=['<ip of the cluster>'], \n",
+    "# gpu = rh.cluster(ips=['<ip of the cluster>'],\n",
     "#                  ssh_creds={'ssh_user': '...', 'ssh_private_key':'<path_to_key>'},\n",
     "#                  name='my-cluster')"
    ]
@@ -424,16 +555,22 @@
    "outputs": [],
    "source": [
     "def get_pipeline():\n",
-    "    from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline  # Must be inside the function in notebooks\n",
+    "    from transformers import (\n",
+    "        AutoModelForCausalLM,\n",
+    "        AutoTokenizer,\n",
+    "        pipeline,\n",
+    "    )  # Must be inside the function in notebooks\n",
+    "\n",
     "    model_id = \"facebook/bart-base\"\n",
     "    tokenizer = AutoTokenizer.from_pretrained(model_id)\n",
     "    model = AutoModelForCausalLM.from_pretrained(model_id)\n",
     "    return pipeline(\"feature-extraction\", model=model, tokenizer=tokenizer)\n",
     "\n",
+    "\n",
     "def inference_fn(pipeline, prompt):\n",
     "    # Return last hidden state of the model\n",
     "    if isinstance(prompt, list):\n",
-    "        return [emb[0][-1] for emb in pipeline(prompt)] \n",
+    "        return [emb[0][-1] for emb in pipeline(prompt)]\n",
     "    return pipeline(prompt)[0][-1]"
    ]
   },
@@ -445,10 +582,10 @@
    "outputs": [],
    "source": [
     "embeddings = SelfHostedEmbeddings(\n",
-    "    model_load_fn=get_pipeline, \n",
+    "    model_load_fn=get_pipeline,\n",
     "    hardware=gpu,\n",
     "    model_reqs=[\"./\", \"torch\", \"transformers\"],\n",
-    "    inference_fn=inference_fn\n",
+    "    inference_fn=inference_fn,\n",
     ")"
    ]
   },
@@ -463,6 +600,153 @@
    "source": [
     "query_result = embeddings.embed_query(text)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f9c02c78",
+   "metadata": {},
+   "source": [
+    "## Fake Embeddings\n",
+    "\n",
+    "LangChain also provides a fake embedding class. You can use this to test your pipelines."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "2ffc2e4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings import FakeEmbeddings"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "80777571",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embeddings = FakeEmbeddings(size=1352)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3ec9d8f0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "3b9ae9e1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_results = embeddings.embed_documents([\"foo\"])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1f83f273",
+   "metadata": {},
+   "source": [
+    "## SageMaker Endpoint Embeddings\n",
+    "\n",
+    "Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
+    "\n",
+    "For instrucstions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "88d366bd",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install langchain boto3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1e9b926a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Dict\n",
+    "from langchain.embeddings import SagemakerEndpointEmbeddings\n",
+    "from langchain.llms.sagemaker_endpoint import ContentHandlerBase\n",
+    "import json\n",
+    "\n",
+    "\n",
+    "class ContentHandler(ContentHandlerBase):\n",
+    "    content_type = \"application/json\"\n",
+    "    accepts = \"application/json\"\n",
+    "\n",
+    "    def transform_input(self, prompt: str, model_kwargs: Dict) -> bytes:\n",
+    "        input_str = json.dumps({\"inputs\": prompt, **model_kwargs})\n",
+    "        return input_str.encode('utf-8')\n",
+    "    \n",
+    "    def transform_output(self, output: bytes) -> str:\n",
+    "        response_json = json.loads(output.read().decode(\"utf-8\"))\n",
+    "        return response_json[\"embeddings\"]\n",
+    "\n",
+    "content_handler = ContentHandler()\n",
+    "\n",
+    "\n",
+    "embeddings = SagemakerEndpointEmbeddings(\n",
+    "    # endpoint_name=\"endpoint-name\", \n",
+    "    # credentials_profile_name=\"credentials-profile-name\", \n",
+    "    endpoint_name=\"huggingface-pytorch-inference-2023-03-21-16-14-03-834\", \n",
+    "    region_name=\"us-east-1\", \n",
+    "    content_handler=content_handler\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fe9797b8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "query_result = embeddings.embed_query(\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "76f1b752",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_results = embeddings.embed_documents([\"foo\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fff99b21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc_results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "aaad49f8",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -481,11 +765,11 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {
-    "hash": "ce6f9b0d7cdac41515b0e0c38d0e6e153a2edce81d579281cb1ab99da6e8ea6d"
+    "hash": "7377c2ccc78bc62c2683122d48c8cd1fb85a53850a1b1fc29736ed39852c9885"
    }
   }
  },

docs/modules/indexes/examples/textsplitter.ipynb

@@ -176,6 +176,77 @@
     "docs"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "3a2f572e",
+   "metadata": {},
+   "source": [
+    "## Latex Text Splitter\n",
+    "\n",
+    "LatexTextSplitter splits text along Latex headings, headlines, enumerations and more. It's implemented as a simple subclass of RecursiveCharacterSplitter with Latex-specific separators. See the source code to see the Latex syntax expected by default.\n",
+    "\n",
+    "1. How the text is split: by list of latex specific tags\n",
+    "2. How the chunk size is measured: by length function passed in (defaults to number of characters)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c2503917",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.text_splitter import LatexTextSplitter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e46b753b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "latex_text = \"\"\"\n",
+    "\\documentclass{article}\n",
+    "\n",
+    "\\begin{document}\n",
+    "\n",
+    "\\maketitle\n",
+    "\n",
+    "\\section{Introduction}\n",
+    "Large language models (LLMs) are a type of machine learning model that can be trained on vast amounts of text data to generate human-like language. In recent years, LLMs have made significant advances in a variety of natural language processing tasks, including language translation, text generation, and sentiment analysis.\n",
+    "\n",
+    "\\subsection{History of LLMs}\n",
+    "The earliest LLMs were developed in the 1980s and 1990s, but they were limited by the amount of data that could be processed and the computational power available at the time. In the past decade, however, advances in hardware and software have made it possible to train LLMs on massive datasets, leading to significant improvements in performance.\n",
+    "\n",
+    "\\subsection{Applications of LLMs}\n",
+    "LLMs have many applications in industry, including chatbots, content creation, and virtual assistants. They can also be used in academia for research in linguistics, psychology, and computational linguistics.\n",
+    "\n",
+    "\\end{document}\n",
+    "\"\"\"\n",
+    "latex_splitter = LatexTextSplitter(chunk_size=400, chunk_overlap=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "73b5bd33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = latex_splitter.create_documents([latex_text])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e1c7fbd5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "c350765d",

docs/modules/indexes/getting_started.ipynb

@@ -1,20 +1,71 @@
 {
  "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "fcc8bb1c",
+   "metadata": {},
+   "source": [
+    "# Getting Started\n",
+    "\n",
+    "LangChain primary focuses on constructing indexes with the goal of using them as a Retriever. In order to best understand what this means, it's worth highlighting what the base Retriever interface is. The `BaseRetriever` class in LangChain is as follows:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b09ac324",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from abc import ABC, abstractmethod\n",
+    "from typing import List\n",
+    "from langchain.schema import Document\n",
+    "\n",
+    "class BaseRetriever(ABC):\n",
+    "    @abstractmethod\n",
+    "    def get_relevant_documents(self, query: str) -> List[Document]:\n",
+    "        \"\"\"Get texts relevant for a query.\n",
+    "\n",
+    "        Args:\n",
+    "            query: string to find relevant tests for\n",
+    "\n",
+    "        Returns:\n",
+    "            List of relevant documents\n",
+    "        \"\"\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e19d4adb",
+   "metadata": {},
+   "source": [
+    "It's that simple! The `get_relevant_documents` method can be implemented however you see fit.\n",
+    "\n",
+    "Of course, we also help construct what we think useful Retrievers are. The main type of Retriever that we focus on is a Vectorstore retriever. We will focus on that for the rest of this guide.\n",
+    "\n",
+    "In order to understand what a vectorstore retriever is, it's important to understand what a Vectorstore is. So let's look at that."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "2244801b",
    "metadata": {},
    "source": [
-    "# Getting Started\n",
+    "By default, LangChain uses [Chroma](../../ecosystem/chroma.md) as the vectorstore to index and search embeddings. To walk through this tutorial, we'll first need to install `chromadb`.\n",
+    "\n",
+    "```\n",
+    "pip install chromadb\n",
+    "```\n",
     "\n",
     "This example showcases question answering over documents.\n",
     "We have chosen this as the example for getting started because it nicely combines a lot of different elements (Text splitters, embeddings, vectorstores) and then also shows how to use them in a chain.\n",
     "\n",
-    "Question answering over documents consists of three steps:\n",
+    "Question answering over documents consists of four steps:\n",
     "\n",
     "1. Create an index\n",
-    "2. Create a question answering chain\n",
-    "3. Ask questions!\n",
+    "2. Create a Retriever from that index\n",
+    "3. Create a question answering chain\n",
+    "4. Ask questions!\n",
     "\n",
     "Each of the steps has multiple sub steps and potential configurations. In this notebook we will primarily focus on (1). We will start by showing the one-liner for doing so, but then break down what is actually going on.\n",
     "\n",
@@ -23,12 +74,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 3,
    "id": "8d369452",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains import VectorDBQA\n",
+    "from langchain.chains import RetrievalQA\n",
     "from langchain.llms import OpenAI"
    ]
   },
@@ -37,12 +88,12 @@
    "id": "07c1e3b9",
    "metadata": {},
    "source": [
-    "Next in the generic setup, let's specify the document loader we want to use."
+    "Next in the generic setup, let's specify the document loader we want to use. You can download the `state_of_the_union.txt` file [here](https://github.com/hwchase17/langchain/blob/master/docs/modules/state_of_the_union.txt)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "33958a86",
    "metadata": {},
    "outputs": [],
@@ -63,7 +114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "403fc231",
    "metadata": {},
    "outputs": [],
@@ -73,7 +124,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 6,
    "id": "57a8a199",
    "metadata": {},
    "outputs": [
@@ -100,7 +151,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 7,
    "id": "23d0d234",
    "metadata": {},
    "outputs": [
@@ -110,7 +161,7 @@
        "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and has received a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 5,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -122,7 +173,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "ae46b239",
    "metadata": {},
    "outputs": [
@@ -134,7 +185,7 @@
        " 'sources': '../state_of_the_union.txt'}"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -154,17 +205,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 9,
    "id": "b04f3c10",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<langchain.vectorstores.chroma.Chroma at 0x113a3a700>"
+       "<langchain.vectorstores.chroma.Chroma at 0x119aa5940>"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -173,6 +224,35 @@
     "index.vectorstore"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "297ccfa4",
+   "metadata": {},
+   "source": [
+    "If we then want to access the VectorstoreRetriever, we can do that with:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b8fef77d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "VectorStoreRetriever(vectorstore=<langchain.vectorstores.chroma.Chroma object at 0x119aa5940>, search_kwargs={})"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "index.vectorstore.as_retriever()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "2cb6d2eb",
@@ -195,7 +275,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 11,
    "id": "54270abc",
    "metadata": {},
    "outputs": [],
@@ -213,7 +293,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 12,
    "id": "afecb8cf",
    "metadata": {},
    "outputs": [],
@@ -233,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 13,
    "id": "9eaaa735",
    "metadata": {},
    "outputs": [],
@@ -252,7 +332,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 14,
    "id": "5c7049db",
    "metadata": {},
    "outputs": [
@@ -270,38 +350,55 @@
     "db = Chroma.from_documents(texts, embeddings)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f0ef85a6",
+   "metadata": {},
+   "source": [
+    "So that's creating the index. Then, we expose this index in a retriever interface."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "13495c77",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = db.as_retriever()"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "30c4e5c6",
    "metadata": {},
    "source": [
-    "So that's creating the index.\n",
     "Then, as before, we create a chain and use it to answer questions!"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 16,
    "id": "3018f865",
    "metadata": {},
    "outputs": [],
    "source": [
-    "qa = VectorDBQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", vectorstore=db)"
+    "qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=retriever)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 17,
    "id": "032a47f8",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\" The President said that Ketanji Brown Jackson is one of the nation's top legal minds and a consensus builder, with a broad range of support from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. She is a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers.\""
+       "\" The President said that Judge Ketanji Brown Jackson is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He said she is a consensus builder and has received a broad range of support from organizations such as the Fraternal Order of Police and former judges appointed by Democrats and Republicans.\""
       ]
      },
-     "execution_count": 13,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/modules/indexes/how_to_guides.rst

@@ -36,6 +36,8 @@ In the below guides, we cover different types of vectorstores and how to use the
 
 `Chroma <./vectorstore_examples/chroma.html>`_: A walkthrough of how to use the Chroma vectorstore wrapper.
 
+`AtlasDB <./vectorstore_examples/atlas.html>`_: A walkthrough of how to use the AtlasDB vectorstore and visualizer wrapper.
+
 `DeepLake <./vectorstore_examples/deeplake.html>`_: A walkthrough of how to use the Deep Lake, data lake, wrapper.
 
 `FAISS <./vectorstore_examples/faiss.html>`_: A walkthrough of how to use the FAISS vectorstore wrapper.
@@ -44,12 +46,16 @@ In the below guides, we cover different types of vectorstores and how to use the
 
 `Milvus <./vectorstore_examples/milvus.html>`_: A walkthrough of how to use the Milvus vectorstore wrapper.
 
+`Open Search <./vectorstore_examples/opensearch.html>`_: A walkthrough of how to use the OpenSearch wrapper.
+
 `Pinecone <./vectorstore_examples/pinecone.html>`_: A walkthrough of how to use the Pinecone vectorstore wrapper.
 
 `Qdrant <./vectorstore_examples/qdrant.html>`_: A walkthrough of how to use the Qdrant vectorstore wrapper.
 
 `Weaviate <./vectorstore_examples/weaviate.html>`_: A walkthrough of how to use the Weaviate vectorstore wrapper.
 
+`PGVector <./vectorstore_examples/pgvector.html>`_: A walkthrough of how to use the PGVector (Postgres Vector DB) vectorstore wrapper.
+
 
 .. toctree::
    :maxdepth: 1
@@ -61,6 +67,29 @@ In the below guides, we cover different types of vectorstores and how to use the
    vectorstore_examples/*
 
 
+Retrievers
+------------
+
+
+The retriever interface is a generic interface that makes it easy to combine documents with
+language models. This interface exposes a `get_relevant_documents` method which takes in a query
+(a string) and returns a list of documents.
+
+`Vectorstore Retriever <./retriever_examples/vectorstore-retriever.html>`_: A walkthrough of how to use a VectorStore as a Retriever.
+
+`ChatGPT Plugin Retriever <./retriever_examples/chatgpt-plugin-retriever.html>`_: A walkthrough of how to use the ChatGPT Plugin Retriever within the LangChain framework.
+
+
+.. toctree::
+   :maxdepth: 1
+   :glob:
+   :caption: Retrievers
+   :name: retrievers
+   :hidden:
+
+   retriever_examples/*
+
+
 Chains
 ------
 
@@ -92,4 +121,4 @@ The examples here are all end-to-end chains that use indexes or utils covered ab
    :name: chains
    :hidden:
 
-   ./chain_examples/*
+   ./chain_examples/*

docs/modules/indexes/retriever_examples/chatgpt-plugin-retriever.ipynb

@@ -0,0 +1,148 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1edb9e6b",
+   "metadata": {},
+   "source": [
+    "# ChatGPT Plugin Retriever\n",
+    "\n",
+    "This notebook shows how to use the ChatGPT Retriever Plugin within LangChain."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "074b0004",
+   "metadata": {},
+   "source": [
+    "## Create\n",
+    "\n",
+    "First, let's go over how to create the ChatGPT Retriever Plugin.\n",
+    "\n",
+    "To set up the ChatGPT Retriever Plugin, please follow instructions [here](https://github.com/openai/chatgpt-retrieval-plugin).\n",
+    "\n",
+    "You can also create the ChatGPT Retriever Plugin from LangChain document loaders. The below code walks through how to do that."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "bbe89ca0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# STEP 1: Load\n",
+    "\n",
+    "# Load documents using LangChain's DocumentLoaders\n",
+    "# This is from https://langchain.readthedocs.io/en/latest/modules/document_loaders/examples/csv.html\n",
+    "\n",
+    "from langchain.document_loaders.csv_loader import CSVLoader\n",
+    "loader = CSVLoader(file_path='../../document_loaders/examples/example_data/mlb_teams_2012.csv')\n",
+    "data = loader.load()\n",
+    "\n",
+    "\n",
+    "# STEP 2: Convert\n",
+    "\n",
+    "# Convert Document to format expected by https://github.com/openai/chatgpt-retrieval-plugin\n",
+    "from typing import List\n",
+    "from langchain.docstore.document import Document\n",
+    "import json\n",
+    "\n",
+    "def write_json(path: str, documents: List[Document])-> None:\n",
+    "    results = [{\"text\": doc.page_content} for doc in documents]\n",
+    "    with open(path, \"w\") as f:\n",
+    "        json.dump(results, f, indent=2)\n",
+    "\n",
+    "write_json(\"foo.json\", data)\n",
+    "\n",
+    "# STEP 3: Use\n",
+    "\n",
+    "# Ingest this as you would any other json file in https://github.com/openai/chatgpt-retrieval-plugin/tree/main/scripts/process_json\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0474661d",
+   "metadata": {},
+   "source": [
+    "## Using the ChatGPT Retriever Plugin\n",
+    "\n",
+    "Okay, so we've created the ChatGPT Retriever Plugin, but how do we actually use it?\n",
+    "\n",
+    "The below code walks through how to do that."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "39d6074e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.retrievers import ChatGPTPluginRetriever"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "33fd23d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = ChatGPTPluginRetriever(url=\"http://0.0.0.0:8000\", bearer_token=\"foo\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "16250bdf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[Document(page_content=\"This is Alice's phone number: 123-456-7890\", lookup_str='', metadata={'id': '456_0', 'metadata': {'source': 'email', 'source_id': '567', 'url': None, 'created_at': '1609592400.0', 'author': 'Alice', 'document_id': '456'}, 'embedding': None, 'score': 0.925571561}, lookup_index=0),\n",
+       " Document(page_content='This is a document about something', lookup_str='', metadata={'id': '123_0', 'metadata': {'source': 'file', 'source_id': 'https://example.com/doc1', 'url': 'https://example.com/doc1', 'created_at': '1609502400.0', 'author': 'Alice', 'document_id': '123'}, 'embedding': None, 'score': 0.6987589}, lookup_index=0),\n",
+       " Document(page_content='Team: Angels \"Payroll (millions)\": 154.49 \"Wins\": 89', lookup_str='', metadata={'id': '59c2c0c1-ae3f-4272-a1da-f44a723ea631_0', 'metadata': {'source': None, 'source_id': None, 'url': None, 'created_at': None, 'author': None, 'document_id': '59c2c0c1-ae3f-4272-a1da-f44a723ea631'}, 'embedding': None, 'score': 0.697888613}, lookup_index=0)]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retriever.get_relevant_documents(\"alice's phone number\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c8b5794b",
+   "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
+}

docs/modules/indexes/retriever_examples/vectorstore-retriever.ipynb

@@ -0,0 +1,93 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "fc0db1bc",
+   "metadata": {},
+   "source": [
+    "# VectorStore Retriever\n",
+    "\n",
+    "The index - and therefor the retriever - that LangChain has the most support for is a VectorStoreRetriever. As the name suggests, this retriever is backed heavily by a VectorStore.\n",
+    "\n",
+    "Once you construct a VectorStore, its very easy to construct a retriever. Let's walk through an example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5831703b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9fbcc58f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores import Chroma\n",
+    "from langchain.embeddings import OpenAIEmbeddings\n",
+    "\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "db = Chroma.from_documents(texts, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "0cbfb1af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retriever = db.as_retriever()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc12700b",
+   "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
+}

docs/modules/indexes/vectorstore_examples/atlas.ipynb

@@ -2,11 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "metadata": {
-    "pycharm": {
-     "name": "#%% md\n"
-    }
-   },
+   "metadata": {},
    "source": [
     "# AtlasDB\n",
     "\n",
@@ -15,10 +11,10 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "pycharm": {
-     "name": "#%%\n"
+     "is_executing": true
     }
    },
    "outputs": [],
@@ -32,56 +28,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Collecting en-core-web-sm==3.5.0\n",
-      "  Downloading https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.5.0/en_core_web_sm-3.5.0-py3-none-any.whl (12.8 MB)\n",
-      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m12.8/12.8 MB\u001B[0m \u001B[31m90.8 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m00:01\u001B[0m00:01\u001B[0m\n",
-      "\u001B[?25hRequirement already satisfied: spacy<3.6.0,>=3.5.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from en-core-web-sm==3.5.0) (3.5.0)\n",
-      "Requirement already satisfied: packaging>=20.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (23.0)\n",
-      "Requirement already satisfied: wasabi<1.2.0,>=0.9.1 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (1.1.1)\n",
-      "Requirement already satisfied: langcodes<4.0.0,>=3.2.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (3.3.0)\n",
-      "Requirement already satisfied: srsly<3.0.0,>=2.4.3 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (2.4.5)\n",
-      "Requirement already satisfied: pathy>=0.10.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (0.10.1)\n",
-      "Requirement already satisfied: setuptools in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (67.4.0)\n",
-      "Requirement already satisfied: tqdm<5.0.0,>=4.38.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (4.64.1)\n",
-      "Requirement already satisfied: spacy-loggers<2.0.0,>=1.0.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (1.0.4)\n",
-      "Requirement already satisfied: smart-open<7.0.0,>=5.2.1 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (6.3.0)\n",
-      "Requirement already satisfied: thinc<8.2.0,>=8.1.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (8.1.7)\n",
-      "Requirement already satisfied: cymem<2.1.0,>=2.0.2 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (2.0.7)\n",
-      "Requirement already satisfied: typer<0.8.0,>=0.3.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (0.7.0)\n",
-      "Requirement already satisfied: requests<3.0.0,>=2.13.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (2.28.2)\n",
-      "Requirement already satisfied: jinja2 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (3.1.2)\n",
-      "Requirement already satisfied: pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (1.10.5)\n",
-      "Requirement already satisfied: catalogue<2.1.0,>=2.0.6 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (2.0.8)\n",
-      "Requirement already satisfied: spacy-legacy<3.1.0,>=3.0.11 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (3.0.12)\n",
-      "Requirement already satisfied: numpy>=1.15.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (1.24.2)\n",
-      "Requirement already satisfied: murmurhash<1.1.0,>=0.28.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (1.0.9)\n",
-      "Requirement already satisfied: preshed<3.1.0,>=3.0.2 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (3.0.8)\n",
-      "Requirement already satisfied: typing-extensions>=4.2.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from pydantic!=1.8,!=1.8.1,<1.11.0,>=1.7.4->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (4.5.0)\n",
-      "Requirement already satisfied: charset-normalizer<4,>=2 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (3.0.1)\n",
-      "Requirement already satisfied: idna<4,>=2.5 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (3.4)\n",
-      "Requirement already satisfied: certifi>=2017.4.17 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (2022.12.7)\n",
-      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from requests<3.0.0,>=2.13.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (1.26.14)\n",
-      "Requirement already satisfied: blis<0.8.0,>=0.7.8 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from thinc<8.2.0,>=8.1.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (0.7.9)\n",
-      "Requirement already satisfied: confection<1.0.0,>=0.0.1 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from thinc<8.2.0,>=8.1.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (0.0.4)\n",
-      "Requirement already satisfied: click<9.0.0,>=7.1.1 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from typer<0.8.0,>=0.3.0->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (8.1.3)\n",
-      "Requirement already satisfied: MarkupSafe>=2.0 in /home/ubuntu/langchain/.venv/lib/python3.9/site-packages (from jinja2->spacy<3.6.0,>=3.5.0->en-core-web-sm==3.5.0) (2.1.2)\n",
-      "\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m A new release of pip is available: \u001B[0m\u001B[31;49m23.0\u001B[0m\u001B[39;49m -> \u001B[0m\u001B[32;49m23.0.1\u001B[0m\n",
-      "\u001B[1m[\u001B[0m\u001B[34;49mnotice\u001B[0m\u001B[1;39;49m]\u001B[0m\u001B[39;49m To update, run: \u001B[0m\u001B[32;49mpip install --upgrade pip\u001B[0m\n",
-      "\u001B[38;5;2m✔ Download and installation successful\u001B[0m\n",
-      "You can now load the package via spacy.load('en_core_web_sm')\n"
-     ]
+    "scrolled": true,
+    "pycharm": {
+     "is_executing": true
     }
-   ],
+   },
+   "outputs": [],
    "source": [
     "!python -m spacy download en_core_web_sm"
    ]
@@ -113,51 +67,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2023-02-24 16:13:49.696 | INFO     | nomic.project:_create_project:884 - Creating project `test_index_1677255228.136989` in organization `Atlas Demo`\n",
-      "2023-02-24 16:13:51.087 | INFO     | nomic.project:wait_for_project_lock:993 - test_index_1677255228.136989: Project lock is released.\n",
-      "2023-02-24 16:13:51.225 | INFO     | nomic.project:wait_for_project_lock:993 - test_index_1677255228.136989: Project lock is released.\n",
-      "2023-02-24 16:13:51.481 | INFO     | nomic.project:add_text:1351 - Uploading text to Atlas.\n",
-      "1it [00:00,  1.20it/s]\n",
-      "2023-02-24 16:13:52.318 | INFO     | nomic.project:add_text:1422 - Text upload succeeded.\n",
-      "2023-02-24 16:13:52.628 | INFO     | nomic.project:wait_for_project_lock:993 - test_index_1677255228.136989: Project lock is released.\n",
-      "2023-02-24 16:13:53.380 | INFO     | nomic.project:create_index:1192 - Created map `test_index_1677255228.136989_index` in project `test_index_1677255228.136989`: https://atlas.nomic.ai/map/ee2354a3-7f9a-4c6b-af43-b0cda09d7198/db996d77-8981-48a0-897a-ff2c22bbf541\n"
-     ]
+   "execution_count": null,
+   "metadata": {
+    "pycharm": {
+     "is_executing": true
     }
-   ],
+   },
+   "outputs": [],
    "source": [
     "db = AtlasDB.from_texts(texts=texts,\n",
-    "                        name='test_index_'+str(time.time()),\n",
-    "                        description='test_index',\n",
+    "                        name='test_index_'+str(time.time()), # unique name for your vector store\n",
+    "                        description='test_index', #a description for your vector store\n",
     "                        api_key=ATLAS_TEST_API_KEY,\n",
     "                        index_kwargs={'build_topic_model': True})"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "2023-02-24 16:14:09.106 | INFO     | nomic.project:wait_for_project_lock:993 - test_index_1677255228.136989: Project lock is released.\n"
-     ]
-    }
-   ],
+   "execution_count": null,
+   "outputs": [],
    "source": [
-    "with db.project.wait_for_project_lock():\n",
-    "    time.sleep(1)"
-   ]
+    "db.project.wait_for_project_lock()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
   },
   {
    "cell_type": "code",
@@ -263,4 +197,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 1
-}
+}

docs/modules/indexes/vectorstore_examples/faiss.ipynb

@@ -62,10 +62,6 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
-      "\n",
-      "We cannot let this happen. \n",
-      "\n",
       "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
       "\n",
       "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
@@ -200,10 +196,104 @@
     "docs[0]"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "57da60d4",
+   "metadata": {},
+   "source": [
+    "## Merging\n",
+    "You can also merge two FAISS vectorstores"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "6dfd2b78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db1 = FAISS.from_texts([\"foo\"], embeddings)\n",
+    "db2 = FAISS.from_texts([\"bar\"], embeddings)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "29960da7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'e0b74348-6c93-4893-8764-943139ec1d17': Document(page_content='foo', lookup_str='', metadata={}, lookup_index=0)}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db1.docstore._dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "83392605",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'bdc50ae3-a1bb-4678-9260-1b0979578f40': Document(page_content='bar', lookup_str='', metadata={}, lookup_index=0)}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db2.docstore._dict"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "a3fcc1c7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db1.merge_from(db2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "41c51f89",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'e0b74348-6c93-4893-8764-943139ec1d17': Document(page_content='foo', lookup_str='', metadata={}, lookup_index=0),\n",
+       " 'd5211050-c777-493d-8825-4800e74cfdb6': Document(page_content='bar', lookup_str='', metadata={}, lookup_index=0)}"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "db1.docstore._dict"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "bc8b71f7",
+   "id": "f80b60de",
    "metadata": {},
    "outputs": [],
    "source": []

docs/modules/indexes/vectorstore_examples/pgvector.ipynb

@@ -0,0 +1,194 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# PGVector\n",
+    "\n",
+    "This notebook shows how to use functionality related to the Postgres vector database (PGVector)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Loading Environment Variables\n",
+    "from typing import List, Tuple\n",
+    "from dotenv import load_dotenv\n",
+    "load_dotenv()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores.pgvector import PGVector\n",
+    "from langchain.document_loaders import TextLoader\n",
+    "from langchain.docstore.document import Document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## PGVector needs the connection string to the database.\n",
+    "## We will load it from the environment variables.\n",
+    "import os\n",
+    "CONNECTION_STRING = PGVector.connection_string_from_db_params(\n",
+    "    driver=os.environ.get(\"PGVECTOR_DRIVER\", \"psycopg2\"),\n",
+    "    host=os.environ.get(\"PGVECTOR_HOST\", \"localhost\"),\n",
+    "    port=int(os.environ.get(\"PGVECTOR_PORT\", \"5432\")),\n",
+    "    database=os.environ.get(\"PGVECTOR_DATABASE\", \"postgres\"),\n",
+    "    user=os.environ.get(\"PGVECTOR_USER\", \"postgres\"),\n",
+    "    password=os.environ.get(\"PGVECTOR_PASSWORD\", \"postgres\"),\n",
+    ")\n",
+    "\n",
+    "\n",
+    "## Example\n",
+    "# postgresql+psycopg2://username:password@localhost:5432/database_name"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Similarity search with score"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Similarity Search with Euclidean Distance (Default)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# The PGVector Module will try to create a table with the name of the collection. So, make sure that the collection name is unique and the user has the \n",
+    "# permission to create a table.\n",
+    "\n",
+    "db = PGVector.from_documents(\n",
+    "    embedding=embeddings,\n",
+    "    documents=docs,\n",
+    "    collection_name=\"state_of_the_union\",\n",
+    "    connection_string=CONNECTION_STRING,\n",
+    ")\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "docs_with_score: List[Tuple[Document, float]] = db.similarity_search_with_score(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6076628081132506\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "--------------------------------------------------------------------------------\n",
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6076628081132506\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "--------------------------------------------------------------------------------\n",
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6076804780049968\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "--------------------------------------------------------------------------------\n",
+      "--------------------------------------------------------------------------------\n",
+      "Score:  0.6076804780049968\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
+      "--------------------------------------------------------------------------------\n"
+     ]
+    }
+   ],
+   "source": [
+    "for doc, score in docs_with_score:\n",
+    "    print(\"-\" * 80)\n",
+    "    print(\"Score: \", score)\n",
+    "    print(doc.page_content)\n",
+    "    print(\"-\" * 80)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/indexes/vectorstore_examples/redis.ipynb

@@ -0,0 +1,191 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Redis\n",
+    "\n",
+    "This notebook shows how to use functionality related to the Redis database."
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores.redis import Redis"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "docs = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "outputs": [],
+   "source": [
+    "rds = Redis.from_documents(docs, embeddings, redis_url=\"redis://localhost:6379\",  index_name='link')"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "outputs": [
+    {
+     "data": {
+      "text/plain": "'b564189668a343648996bd5a1d353d4e'"
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "rds.index_name"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "markdown",
+   "source": [],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "In state after state, new laws have been passed, not only to suppress the vote, but to subvert entire elections. \n",
+      "\n",
+      "We cannot let this happen. \n",
+      "\n",
+      "Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
+      "\n",
+      "Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
+      "\n",
+      "One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
+      "\n",
+      "And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "results = rds.similarity_search(query)\n",
+    "print(results[0].page_content)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "['doc:333eadf75bd74be393acafa8bca48669']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(rds.add_texts([\"Ankush went to Princeton\"]))"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Ankush went to Princeton\n"
+     ]
+    }
+   ],
+   "source": [
+    "query = \"Princeton\"\n",
+    "results = rds.similarity_search(query)\n",
+    "print(results[0].page_content)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "#Query\n",
+    "rds = Redis.from_existing_index(embeddings, redis_url=\"redis://localhost:6379\", index_name='link')\n",
+    "\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "results = rds.similarity_search(query)\n",
+    "print(results[0].page_content)"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

docs/modules/llms/integrations/promptlayer_openai.ipynb

@@ -119,10 +119,39 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "05e9e2fe",
    "metadata": {},
-   "source": []
+   "source": [
+    "## Using PromptLayer Track\n",
+    "If you would like to use any of the [PromptLayer tracking features](https://magniv.notion.site/Track-4deee1b1f7a34c1680d085f82567dab9), you need to pass the argument `return_pl_id` when instantializing the PromptLayer LLM to get the request id.  "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1a7315b9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = PromptLayerOpenAI(return_pl_id=True)\n",
+    "llm_results = llm.generate([\"Tell me a joke\"])\n",
+    "\n",
+    "for res in llm_results.generations:\n",
+    "    pl_request_id = res[0].generation_info[\"pl_request_id\"]\n",
+    "    promptlayer.track.score(request_id=pl_request_id, score=100)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "7eb19139",
+   "metadata": {},
+   "source": [
+    "Using this allows you to track the performance of your model in the PromptLayer dashboard. If you are using a prompt template, you can attach a template to a request as well.\n",
+    "Overall, this gives you the opportunity to track the performance of different templates and models in the PromptLayer dashboard."
+   ]
   }
  ],
  "metadata": {
@@ -145,7 +174,7 @@
   },
   "vscode": {
    "interpreter": {
-    "hash": "c4fe2cd85a8d9e8baaec5340ce66faff1c77581a9f43e6c45e85e09b6fced008"
+    "hash": "8a5edab282632443219e051e4ade2d1d5bbc671c781051bf1437897cbdfea0f1"
    }
   }
  },

docs/modules/llms/integrations/sagemaker.ipynb

@@ -0,0 +1,131 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# SageMakerEndpoint\n",
+    "\n",
+    "This notebooks goes over how to use an LLM hosted on a SageMaker endpoint."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "!pip3 install langchain boto3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.docstore.document import Document"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "example_doc_1 = \"\"\"\n",
+    "Peter and Elizabeth took a taxi to attend the night party in the city. While in the party, Elizabeth collapsed and was rushed to the hospital.\n",
+    "Since she was diagnosed with a brain injury, the doctor told Peter to stay besides her until she gets well.\n",
+    "Therefore, Peter stayed with her at the hospital for 3 days without leaving.\n",
+    "\"\"\"\n",
+    "\n",
+    "docs = [\n",
+    "    Document(\n",
+    "        page_content=example_doc_1,\n",
+    "    )\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from typing import Dict\n",
+    "\n",
+    "from langchain import PromptTemplate, SagemakerEndpoint\n",
+    "from langchain.llms.sagemaker_endpoint import ContentHandlerBase\n",
+    "from langchain.chains.question_answering import load_qa_chain\n",
+    "import json\n",
+    "\n",
+    "query = \"\"\"How long was Elizabeth hospitalized?\n",
+    "\"\"\"\n",
+    "\n",
+    "prompt_template = \"\"\"Use the following pieces of context to answer the question at the end.\n",
+    "\n",
+    "{context}\n",
+    "\n",
+    "Question: {question}\n",
+    "Answer:\"\"\"\n",
+    "PROMPT = PromptTemplate(\n",
+    "    template=prompt_template, input_variables=[\"context\", \"question\"]\n",
+    ")\n",
+    "\n",
+    "class ContentHandler(ContentHandlerBase):\n",
+    "    content_type = \"application/json\"\n",
+    "    accepts = \"application/json\"\n",
+    "\n",
+    "    def transform_input(self, prompt: str, model_kwargs: Dict) -> bytes:\n",
+    "        input_str = json.dumps({prompt: prompt, **model_kwargs})\n",
+    "        return input_str.encode('utf-8')\n",
+    "    \n",
+    "    def transform_output(self, output: bytes) -> str:\n",
+    "        response_json = json.loads(output.read().decode(\"utf-8\"))\n",
+    "        return response_json[0][\"generated_text\"]\n",
+    "\n",
+    "content_handler = ContentHandler()\n",
+    "\n",
+    "chain = load_qa_chain(\n",
+    "    llm=SagemakerEndpoint(\n",
+    "        endpoint_name=\"endpoint-name\", \n",
+    "        credentials_profile_name=\"credentials-profile-name\", \n",
+    "        region_name=\"us-west-2\", \n",
+    "        model_kwargs={\"temperature\":1e-10},\n",
+    "        content_handler=content_handler\n",
+    "    ),\n",
+    "    prompt=PROMPT\n",
+    ")\n",
+    "\n",
+    "chain({\"input_documents\": docs, \"question\": query}, return_only_outputs=True)\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "31f2aee4e71d21fbe5cf8b01ff0e069b9275f58929596ceb00d14d90e3e16cd6"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

docs/modules/memory/getting_started.ipynb

@@ -30,36 +30,12 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.memory import ChatMessageHistory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "4404d509",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "history = ChatMessageHistory()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "78c1a67b",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "history.add_user_message(\"hi!\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "525ce606",
-   "metadata": {},
-   "outputs": [],
-   "source": [
+    "from langchain.memory import ChatMessageHistory\n",
+    "\n",
+    "history = ChatMessageHistory()\n",
+    "\n",
+    "history.add_user_message(\"hi!\")\n",
+    "\n",
     "history.add_ai_message(\"whats up?\")"
    ]
   },
@@ -331,6 +307,99 @@
     "conversation.predict(input=\"Tell me about yourself.\")"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "fb68bb9e",
+   "metadata": {},
+   "source": [
+    "## Saving Message History\n",
+    "\n",
+    "You may often to save messages, and then load them to use again. This can be done easily by first converting the messages to normal python dictionaries, saving those (as json or something) and then loading those. Here is an example of doing that."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "b5acbc4b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "from langchain.memory import ChatMessageHistory\n",
+    "from langchain.schema import messages_from_dict, messages_to_dict\n",
+    "\n",
+    "history = ChatMessageHistory()\n",
+    "\n",
+    "history.add_user_message(\"hi!\")\n",
+    "\n",
+    "history.add_ai_message(\"whats up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7812ee21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dicts = messages_to_dict(history.messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3ed6e6a0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[{'type': 'human', 'data': {'content': 'hi!', 'additional_kwargs': {}}},\n",
+       " {'type': 'ai', 'data': {'content': 'whats up?', 'additional_kwargs': {}}}]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dicts"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cdf4ebd2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "new_messages = messages_from_dict(dicts)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9724e24b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[HumanMessage(content='hi!', additional_kwargs={}),\n",
+       " AIMessage(content='whats up?', additional_kwargs={})]"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_messages"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "7826c210",

docs/modules/memory/how_to_guides.rst

@@ -1,10 +1,23 @@
 How-To Guides
 =============
 
+Types
+-----
+
 The first set of examples all highlight different types of memory.
 
+`Buffer <./types/buffer.html>`_: How to use a type of memory that just keeps previous messages in a buffer.
+
+`Buffer Window <./types/buffer_window.html>`_: How to use a type of memory that keeps previous messages in a buffer but only uses the previous `k` of them.
+
+`Summary <./types/summary.html>`_: How to use a type of memory that summarizes previous messages.
+
+`Summary Buffer <./types/summary_buffer.html>`_: How to use a type of memory that keeps a buffer of messages up to a point, and then summarizes them.
+
 `Entity Memory <./types/entity_summary_memory.html>`_: How to use a type of memory that organizes information by entity.
 
+`Knowledge Graph Memory <./types/kg.html>`_: How to use a type of memory that extracts and organizes information in a knowledge graph
+
 
 .. toctree::
    :maxdepth: 1
@@ -13,6 +26,10 @@ The first set of examples all highlight different types of memory.
 
    ./types/*
 
+
+Usage
+-----
+
 The examples here all highlight how to use memory in different ways.
 
 `Adding Memory <./examples/adding_memory.html>`_: How to add a memory component to any single input chain.

docs/modules/memory/key_concepts.md

@@ -9,8 +9,8 @@ both at a short term but also at a long term level. The concept of "Memory" exis
 One of the simpler forms of memory occurs in chatbots, where they remember previous conversations.
 There are a few different ways to accomplish this:
 - Buffer: This is just passing in the past `N` interactions in as context. `N` can be chosen based on a fixed number, the length of the interactions, or other!
-- Summary: This involves summarizing previous conversations and passing that summary in, instead of the raw dialouge itself. Compared to `Buffer`, this compresses information: meaning it is more lossy, but also less likely to run into context length limits.
-- Combination: A combination of the above two approaches, where you compute a summary but also pass in some previous interfactions directly!
+- Summary: This involves summarizing previous conversations and passing that summary in, instead of the raw dialogue itself. Compared to `Buffer`, this compresses information: meaning it is more lossy, but also less likely to run into context length limits.
+- Combination: A combination of the above two approaches, where you compute a summary but also pass in some previous interactions directly!
 
 ## Entity Memory
 A more complex form of memory is remembering information about specific entities in the conversation.

docs/modules/memory/types/token_buffer.ipynb

@@ -0,0 +1,288 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ff4be5f3",
+   "metadata": {},
+   "source": [
+    "## ConversationTokenBufferMemory\n",
+    "\n",
+    "`ConversationTokenBufferMemory` keeps a buffer of recent interactions in memory, and uses token length rather than number of interactions to determine when to flush interactions.\n",
+    "\n",
+    "Let's first walk through how to use the utilities"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "da3384db",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationTokenBufferMemory\n",
+    "from langchain.llms import OpenAI\n",
+    "llm = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e00d4938",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=10)\n",
+    "memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})\n",
+    "memory.save_context({\"input\": \"not much you\"}, {\"ouput\": \"not much\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2fe28a28",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': 'Human: not much you\\nAI: not much'}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cf57b97a",
+   "metadata": {},
+   "source": [
+    "We can also get the history as a list of messages (this is useful if you are using this with a chat model)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3422a3a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationTokenBufferMemory(llm=llm, max_token_limit=10, return_messages=True)\n",
+    "memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})\n",
+    "memory.save_context({\"input\": \"not much you\"}, {\"ouput\": \"not much\"})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a6d2569f",
+   "metadata": {},
+   "source": [
+    "## Using in a chain\n",
+    "Let's walk through an example, again setting `verbose=True` so we can see the prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ebd68c10",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+      "\n",
+      "Current conversation:\n",
+      "\n",
+      "Human: Hi, what's up?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Hi there! I'm doing great, just enjoying the day. How about you?\""
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import ConversationChain\n",
+    "conversation_with_summary = ConversationChain(\n",
+    "    llm=llm, \n",
+    "    # We set a very low max_token_limit for the purposes of testing.\n",
+    "    memory=ConversationTokenBufferMemory(llm=OpenAI(), max_token_limit=60),\n",
+    "    verbose=True\n",
+    ")\n",
+    "conversation_with_summary.predict(input=\"Hi, what's up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "86207a61",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: Hi, what's up?\n",
+      "AI:  Hi there! I'm doing great, just enjoying the day. How about you?\n",
+      "Human: Just working on writing some documentation!\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Sounds like a productive day! What kind of documentation are you writing?'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"Just working on writing some documentation!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "76a0ab39",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: Hi, what's up?\n",
+      "AI:  Hi there! I'm doing great, just enjoying the day. How about you?\n",
+      "Human: Just working on writing some documentation!\n",
+      "AI:  Sounds like a productive day! What kind of documentation are you writing?\n",
+      "Human: For LangChain! Have you heard of it?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Yes, I have heard of LangChain! It is a decentralized language-learning platform that connects native speakers and learners in real time. Is that the documentation you're writing about?\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"For LangChain! Have you heard of it?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "8c669db1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
+      "Prompt after formatting:\n",
+      "\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
+      "\n",
+      "Current conversation:\n",
+      "Human: For LangChain! Have you heard of it?\n",
+      "AI:  Yes, I have heard of LangChain! It is a decentralized language-learning platform that connects native speakers and learners in real time. Is that the documentation you're writing about?\n",
+      "Human: Haha nope, although a lot of people confuse it for that\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Oh, I see. Is there another language learning platform you're referring to?\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can see here that the buffer is updated\n",
+    "conversation_with_summary.predict(input=\"Haha nope, although a lot of people confuse it for that\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8c09a239",
+   "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
+}

docs/modules/prompts/examples/custom_prompt_template.ipynb

@@ -21,16 +21,17 @@
    "id": "5d56ce86",
    "metadata": {},
    "source": [
-    "## Create a custom prompt template\n",
+    "## Creating a Custom Prompt Template\n",
     "\n",
-    "The only two requirements for all prompt templates are:\n",
+    "There are essentially two distinct prompt templates available - string prompt templates and chat prompt templates. String prompt templates provides a simple prompt in string format, while chat prompt templates produces a more structured prompt to be used with a chat API.\n",
     "\n",
-    "1. They have a input_variables attribute that exposes what input variables this prompt template expects.\n",
-    "2. They expose a format method which takes in keyword arguments corresponding to the expected input_variables and returns the formatted prompt.\n",
+    "In this guide, we will create a custom prompt using a string prompt template. \n",
     "\n",
-    "Let's create a custom prompt template that takes in the function name as input, and formats the prompt template to provide the source code of the function.\n",
+    "To create a custom string prompt template, there are two requirements:\n",
+    "1. It has an input_variables attribute that exposes what input variables the prompt template expects.\n",
+    "2. It exposes a format method that takes in keyword arguments corresponding to the expected input_variables and returns the formatted prompt.\n",
     "\n",
-    "First, let's create a function that will return the source code of a function given its name."
+    "We will create a custom prompt template that takes in the function name as input and formats the prompt to provide the source code of the function. To achieve this, let's first create a function that will return the source code of a function given its name."
    ]
   },
   {
@@ -62,11 +63,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.prompts import BasePromptTemplate\n",
+    "from langchain.prompts import StringPromptTemplate\n",
     "from pydantic import BaseModel, validator\n",
     "\n",
     "\n",
-    "class FunctionExplainerPromptTemplate(BasePromptTemplate, BaseModel):\n",
+    "class FunctionExplainerPromptTemplate(StringPromptTemplate, BaseModel):\n",
     "    \"\"\" A custom prompt template that takes in the function name as input, and formats the prompt template to provide the source code of the function. \"\"\"\n",
     "\n",
     "    @validator(\"input_variables\")\n",

docs/modules/prompts/examples/output_parsers.ipynb

@@ -0,0 +1,764 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "084ee2f0",
+   "metadata": {},
+   "source": [
+    "# Output Parsers\n",
+    "\n",
+    "Language models output text. But many times you may want to get more structured information than just text back. This is where output parsers come in.\n",
+    "\n",
+    "Output parsers are classes that help structure language model responses. There are two main methods an output parser must implement:\n",
+    "\n",
+    "- `get_format_instructions() -> str`: A method which returns a string containing instructions for how the output of a language model should be formatted.\n",
+    "- `parse(str) -> Any`: A method which takes in a string (assumed to be the response from a language model) and parses it into some structure.\n",
+    "\n",
+    "And then one optional one:\n",
+    "\n",
+    "- `parse_with_prompt(str) -> Any`: A method which takes in a string (assumed to be the response from a language model) and a prompt (assumed to the prompt that generated such a response) and parses it into some structure. The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.\n",
+    "\n",
+    "\n",
+    "Below we go over some examples of output parsers."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5f0c8a33",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import PromptTemplate, ChatPromptTemplate, HumanMessagePromptTemplate\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chat_models import ChatOpenAI"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a1ae632a",
+   "metadata": {},
+   "source": [
+    "## PydanticOutputParser\n",
+    "This output parser allows users to specify an arbitrary JSON schema and query LLMs for JSON outputs that conform to that schema.\n",
+    "\n",
+    "Keep in mind that large language models are leaky abstractions! You'll have to use an LLM with sufficient capacity to generate well-formed JSON. In the OpenAI family, DaVinci can do reliably but Curie's ability already drops off dramatically. \n",
+    "\n",
+    "Use Pydantic to declare your data model. Pydantic's BaseModel like a Python dataclass, but with actual type checking + coercion."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "cba6d8e3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers import PydanticOutputParser\n",
+    "from pydantic import BaseModel, Field, validator\n",
+    "from typing import List"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0a203100",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model_name = 'text-davinci-003'\n",
+    "temperature = 0.0\n",
+    "model = OpenAI(model_name=model_name, temperature=temperature)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b3f16168",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Joke(setup='Why did the chicken cross the road?', punchline='To get to the other side!')"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Define your desired data structure.\n",
+    "class Joke(BaseModel):\n",
+    "    setup: str = Field(description=\"question to set up a joke\")\n",
+    "    punchline: str = Field(description=\"answer to resolve the joke\")\n",
+    "    \n",
+    "    # You can add custom validation logic easily with Pydantic.\n",
+    "    @validator('setup')\n",
+    "    def question_ends_with_question_mark(cls, field):\n",
+    "        if field[-1] != '?':\n",
+    "            raise ValueError(\"Badly formed question!\")\n",
+    "        return field\n",
+    "\n",
+    "# And a query intented to prompt a language model to populate the data structure.\n",
+    "joke_query = \"Tell me a joke.\"\n",
+    "\n",
+    "# Set up a parser + inject instructions into the prompt template.\n",
+    "parser = PydanticOutputParser(pydantic_object=Joke)\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    template=\"Answer the user query.\\n{format_instructions}\\n{query}\\n\",\n",
+    "    input_variables=[\"query\"],\n",
+    "    partial_variables={\"format_instructions\": parser.get_format_instructions()}\n",
+    ")\n",
+    "\n",
+    "_input = prompt.format_prompt(query=joke_query)\n",
+    "\n",
+    "output = model(_input.to_string())\n",
+    "\n",
+    "parser.parse(output)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "03049f88",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Actor(name='Tom Hanks', film_names=['Forrest Gump', 'Saving Private Ryan', 'The Green Mile', 'Cast Away', 'Toy Story'])"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Here's another example, but with a compound typed field.\n",
+    "class Actor(BaseModel):\n",
+    "    name: str = Field(description=\"name of an actor\")\n",
+    "    film_names: List[str] = Field(description=\"list of names of films they starred in\")\n",
+    "        \n",
+    "actor_query = \"Generate the filmography for a random actor.\"\n",
+    "\n",
+    "parser = PydanticOutputParser(pydantic_object=Actor)\n",
+    "\n",
+    "prompt = PromptTemplate(\n",
+    "    template=\"Answer the user query.\\n{format_instructions}\\n{query}\\n\",\n",
+    "    input_variables=[\"query\"],\n",
+    "    partial_variables={\"format_instructions\": parser.get_format_instructions()}\n",
+    ")\n",
+    "\n",
+    "_input = prompt.format_prompt(query=actor_query)\n",
+    "\n",
+    "output = model(_input.to_string())\n",
+    "\n",
+    "parser.parse(output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4d6c0c86",
+   "metadata": {},
+   "source": [
+    "## Fixing Output Parsing Mistakes\n",
+    "\n",
+    "The above guardrail simply tries to parse the LLM response. If it does not parse correctly, then it errors.\n",
+    "\n",
+    "But we can do other things besides throw errors. Specifically, we can pass the misformatted output, along with the formatted instructions, to the model and ask it to fix it.\n",
+    "\n",
+    "For this example, we'll use the above OutputParser. Here's what happens if we pass it a result that does not comply with the schema:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "73beb20d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "misformatted = \"{'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "f0e5ba80",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "OutputParserException",
+     "evalue": "Failed to parse Actor from completion {'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}. Got: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mJSONDecodeError\u001b[0m                           Traceback (most recent call last)",
+      "File \u001b[0;32m~/workplace/langchain/langchain/output_parsers/pydantic.py:23\u001b[0m, in \u001b[0;36mPydanticOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     22\u001b[0m     json_str \u001b[38;5;241m=\u001b[39m match\u001b[38;5;241m.\u001b[39mgroup()\n\u001b[0;32m---> 23\u001b[0m json_object \u001b[38;5;241m=\u001b[39m \u001b[43mjson\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloads\u001b[49m\u001b[43m(\u001b[49m\u001b[43mjson_str\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     24\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpydantic_object\u001b[38;5;241m.\u001b[39mparse_obj(json_object)\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.9.1/lib/python3.9/json/__init__.py:346\u001b[0m, in \u001b[0;36mloads\u001b[0;34m(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)\u001b[0m\n\u001b[1;32m    343\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (\u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m object_hook \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m    344\u001b[0m         parse_int \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m parse_float \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m\n\u001b[1;32m    345\u001b[0m         parse_constant \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m object_pairs_hook \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m kw):\n\u001b[0;32m--> 346\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_default_decoder\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    347\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mcls\u001b[39m \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.9.1/lib/python3.9/json/decoder.py:337\u001b[0m, in \u001b[0;36mJSONDecoder.decode\u001b[0;34m(self, s, _w)\u001b[0m\n\u001b[1;32m    333\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Return the Python representation of ``s`` (a ``str`` instance\u001b[39;00m\n\u001b[1;32m    334\u001b[0m \u001b[38;5;124;03mcontaining a JSON document).\u001b[39;00m\n\u001b[1;32m    335\u001b[0m \n\u001b[1;32m    336\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m--> 337\u001b[0m obj, end \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraw_decode\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m_w\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mend\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    338\u001b[0m end \u001b[38;5;241m=\u001b[39m _w(s, end)\u001b[38;5;241m.\u001b[39mend()\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.9.1/lib/python3.9/json/decoder.py:353\u001b[0m, in \u001b[0;36mJSONDecoder.raw_decode\u001b[0;34m(self, s, idx)\u001b[0m\n\u001b[1;32m    352\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 353\u001b[0m     obj, end \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mscan_once\u001b[49m\u001b[43m(\u001b[49m\u001b[43ms\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    354\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
+      "\u001b[0;31mJSONDecodeError\u001b[0m: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mOutputParserException\u001b[0m                     Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[7], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmisformatted\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/output_parsers/pydantic.py:29\u001b[0m, in \u001b[0;36mPydanticOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     27\u001b[0m name \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpydantic_object\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\n\u001b[1;32m     28\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFailed to parse \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m from completion \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. Got: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 29\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(msg)\n",
+      "\u001b[0;31mOutputParserException\u001b[0m: Failed to parse Actor from completion {'name': 'Tom Hanks', 'film_names': ['Forrest Gump']}. Got: Expecting property name enclosed in double quotes: line 1 column 2 (char 1)"
+     ]
+    }
+   ],
+   "source": [
+    "parser.parse(misformatted)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c7c82b6",
+   "metadata": {},
+   "source": [
+    "Now we can construct and use a `OutputFixingParser`. This output parser takes as an argument another output parser but also an LLM with which to try to correct any formatting mistakes."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "39b1a5ce",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers import OutputFixingParser\n",
+    "\n",
+    "new_parser = OutputFixingParser.from_llm(parser=parser, llm=ChatOpenAI())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "0fd96d68",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Actor(name='Tom Hanks', film_names=['Forrest Gump'])"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "new_parser.parse(misformatted)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ea34eeaa",
+   "metadata": {},
+   "source": [
+    "## Fixing Output Parsing Mistakes with the original prompt\n",
+    "\n",
+    "While in some cases it is possible to fix any parsing mistakes by only looking at the output, in other cases it can't. An example of this is when the output is not just in the incorrect format, but is partially complete. Consider the below example."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "67c5e1ac",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"Based on the user question, provide an Action and Action Input for what step should be taken.\n",
+    "{format_instructions}\n",
+    "Question: {query}\n",
+    "Response:\"\"\"\n",
+    "class Action(BaseModel):\n",
+    "    action: str = Field(description=\"action to take\")\n",
+    "    action_input: str = Field(description=\"input to the action\")\n",
+    "        \n",
+    "parser = PydanticOutputParser(pydantic_object=Action)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "007aa87f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = PromptTemplate(\n",
+    "    template=\"Answer the user query.\\n{format_instructions}\\n{query}\\n\",\n",
+    "    input_variables=[\"query\"],\n",
+    "    partial_variables={\"format_instructions\": parser.get_format_instructions()}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "10d207ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt_value = prompt.format_prompt(query=\"who is leo di caprios gf?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "68622837",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "bad_response = '{\"action\": \"search\"}'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "25631465",
+   "metadata": {},
+   "source": [
+    "If we try to parse this response as is, we will get an error"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "894967c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "OutputParserException",
+     "evalue": "Failed to parse Action from completion {\"action\": \"search\"}. Got: 1 validation error for Action\naction_input\n  field required (type=value_error.missing)",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValidationError\u001b[0m                           Traceback (most recent call last)",
+      "File \u001b[0;32m~/workplace/langchain/langchain/output_parsers/pydantic.py:24\u001b[0m, in \u001b[0;36mPydanticOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     23\u001b[0m     json_object \u001b[38;5;241m=\u001b[39m json\u001b[38;5;241m.\u001b[39mloads(json_str)\n\u001b[0;32m---> 24\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[43mpydantic_object\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse_obj\u001b[49m\u001b[43m(\u001b[49m\u001b[43mjson_object\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m     26\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (json\u001b[38;5;241m.\u001b[39mJSONDecodeError, ValidationError) \u001b[38;5;28;01mas\u001b[39;00m e:\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/pydantic/main.py:527\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.parse_obj\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.9.1/envs/langchain/lib/python3.9/site-packages/pydantic/main.py:342\u001b[0m, in \u001b[0;36mpydantic.main.BaseModel.__init__\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mValidationError\u001b[0m: 1 validation error for Action\naction_input\n  field required (type=value_error.missing)",
+      "\nDuring handling of the above exception, another exception occurred:\n",
+      "\u001b[0;31mOutputParserException\u001b[0m                     Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[15], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mparser\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparse\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbad_response\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/workplace/langchain/langchain/output_parsers/pydantic.py:29\u001b[0m, in \u001b[0;36mPydanticOutputParser.parse\u001b[0;34m(self, text)\u001b[0m\n\u001b[1;32m     27\u001b[0m name \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpydantic_object\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\n\u001b[1;32m     28\u001b[0m msg \u001b[38;5;241m=\u001b[39m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFailed to parse \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mname\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m from completion \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mtext\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m. Got: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m---> 29\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m OutputParserException(msg)\n",
+      "\u001b[0;31mOutputParserException\u001b[0m: Failed to parse Action from completion {\"action\": \"search\"}. Got: 1 validation error for Action\naction_input\n  field required (type=value_error.missing)"
+     ]
+    }
+   ],
+   "source": [
+    "parser.parse(bad_response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6b64696",
+   "metadata": {},
+   "source": [
+    "If we try to use the `OutputFixingParser` to fix this error, it will be confused - namely, it doesn't know what to actually put for action input."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "78b2b40d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fix_parser = OutputFixingParser.from_llm(parser=parser, llm=ChatOpenAI())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "4fe1301d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Action(action='search', action_input='keyword')"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "fix_parser.parse(bad_response)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9bd9ea7d",
+   "metadata": {},
+   "source": [
+    "Instead, we can use the RetryOutputParser, which passes in the prompt (as well as the original output) to try again to get a better response."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "7e8a8a28",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers import RetryWithErrorOutputParser"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "5c86e141",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "retry_parser = RetryWithErrorOutputParser.from_llm(parser=parser, llm=ChatOpenAI())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "9c04f731",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Action(action='search', action_input='leo di caprios girlfriend')"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "retry_parser.parse_with_prompt(bad_response, prompt_value)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "61f67890",
+   "metadata": {},
+   "source": [
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "64bf525a",
+   "metadata": {},
+   "source": [
+    "# Older, less powerful parsers"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "91871002",
+   "metadata": {},
+   "source": [
+    "## Structured Output Parser\n",
+    "\n",
+    "While the Pydantic/JSON parser is more powerful, we initially experimented data structures having text fields only."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "b492997a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers import StructuredOutputParser, ResponseSchema"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "09473dce",
+   "metadata": {},
+   "source": [
+    "Here we define the response schema we want to receive."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "432ac44a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "response_schemas = [\n",
+    "    ResponseSchema(name=\"answer\", description=\"answer to the user's question\"),\n",
+    "    ResponseSchema(name=\"source\", description=\"source used to answer the user's question, should be a website.\")\n",
+    "]\n",
+    "output_parser = StructuredOutputParser.from_response_schemas(response_schemas)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7b92ce96",
+   "metadata": {},
+   "source": [
+    "We now get a string that contains instructions for how the response should be formatted, and we then insert that into our prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "593cfc25",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "format_instructions = output_parser.get_format_instructions()\n",
+    "prompt = PromptTemplate(\n",
+    "    template=\"answer the users question as best as possible.\\n{format_instructions}\\n{question}\",\n",
+    "    input_variables=[\"question\"],\n",
+    "    partial_variables={\"format_instructions\": format_instructions}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0943e783",
+   "metadata": {},
+   "source": [
+    "We can now use this to format a prompt to send to the language model, and then parse the returned result."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "106f1ba6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "86d9d24f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_input = prompt.format_prompt(question=\"what's the capital of france\")\n",
+    "output = model(_input.to_string())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "956bdc99",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Paris'}"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output_parser.parse(output)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "da639285",
+   "metadata": {},
+   "source": [
+    "And here's an example of using this in a chat model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "8f483d7d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_model = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "f761cbf1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate(\n",
+    "    messages=[\n",
+    "        HumanMessagePromptTemplate.from_template(\"answer the users question as best as possible.\\n{format_instructions}\\n{question}\")  \n",
+    "    ],\n",
+    "    input_variables=[\"question\"],\n",
+    "    partial_variables={\"format_instructions\": format_instructions}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "edd73ae3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_input = prompt.format_prompt(question=\"what's the capital of france\")\n",
+    "output = chat_model(_input.to_messages())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "a3c8b91e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Paris'}"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output_parser.parse(output.content)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9936fa27",
+   "metadata": {},
+   "source": [
+    "## CommaSeparatedListOutputParser\n",
+    "\n",
+    "Here's another parser strictly less powerful than Pydantic/JSON parsing."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "872246d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers import CommaSeparatedListOutputParser"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "c3f9aee6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output_parser = CommaSeparatedListOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "e77871b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "format_instructions = output_parser.get_format_instructions()\n",
+    "prompt = PromptTemplate(\n",
+    "    template=\"List five {subject}.\\n{format_instructions}\",\n",
+    "    input_variables=[\"subject\"],\n",
+    "    partial_variables={\"format_instructions\": format_instructions}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "a71cb5d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "783d7d98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_input = prompt.format(subject=\"ice cream flavors\")\n",
+    "output = model(_input)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "fcb81344",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Vanilla',\n",
+       " 'Chocolate',\n",
+       " 'Strawberry',\n",
+       " 'Mint Chocolate Chip',\n",
+       " 'Cookies and Cream']"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "output_parser.parse(output)"
+   ]
+  }
+ ],
+ "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
+}

docs/modules/prompts/examples/prompt_serialization.ipynb

@@ -120,6 +120,25 @@
     "!cat simple_prompt.json"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "de75e959",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = load_prompt(\"simple_prompt.json\")\n",
+    "print(prompt.format(adjective=\"funny\", content=\"chickens\"))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d1d788f9",
+   "metadata": {},
+   "source": [
+    "Tell me a funny joke about chickens."
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "d788a83c",

docs/modules/prompts/how_to_guides.rst

@@ -32,3 +32,4 @@ The user guide here shows more advanced workflows and how to use the library in
    ./examples/prompt_serialization.ipynb
    ./examples/few_shot_examples_data.ipynb
    ./examples/example_selectors.ipynb
+   ./examples/output_parsers.ipynb

docs/modules/utils/examples/google_serper.ipynb

@@ -121,7 +121,8 @@
     "tools = [\n",
     "    Tool(\n",
     "        name=\"Intermediate Answer\",\n",
-    "        func=search.run\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to ask with search\"\n",
     "    )\n",
     "]\n",
     "\n",

docs/modules/utils/examples/zapier.ipynb

@@ -0,0 +1,326 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "16763ed3",
+   "metadata": {},
+   "source": [
+    "## Zapier Natural Language Actions API\n",
+    "\\\n",
+    "Full docs here: https://nla.zapier.com/api/v1/docs\n",
+    "\n",
+    "**Zapier Natural Language Actions** gives you access to the 5k+ apps, 20k+ actions on Zapier's platform through a natural language API interface.\n",
+    "\n",
+    "NLA supports apps like Gmail, Salesforce, Trello, Slack, Asana, HubSpot, Google Sheets, Microsoft Teams, and thousands more apps: https://zapier.com/apps\n",
+    "\n",
+    "Zapier NLA handles ALL the underlying API auth and translation from natural language --> underlying API call --> return simplified output for LLMs. The key idea is you, or your users, expose a set of actions via an oauth-like setup window, which you can then query and execute via a REST API.\n",
+    "\n",
+    "NLA offers both API Key and OAuth for signing NLA API requests.\n",
+    "\n",
+    "1. Server-side (API Key): for quickly getting started, testing, and production scenarios where LangChain will only use actions exposed in the developer's Zapier account (and will use the developer's connected accounts on Zapier.com)\n",
+    "\n",
+    "2. User-facing (Oauth): for production scenarios where you are deploying an end-user facing application and LangChain needs access to end-user's exposed actions and connected accounts on Zapier.com\n",
+    "\n",
+    "This quick start will focus on the server-side use case for brevity. Review [full docs](https://nla.zapier.com/api/v1/docs) or reach out to nla@zapier.com for user-facing oauth developer support.\n",
+    "\n",
+    "This example goes over how to use the Zapier integration with a `SimpleSequentialChain`, then an `Agent`.\n",
+    "In code, below:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a363309c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5cf33377",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "# get from https://platform.openai.com/\n",
+    "os.environ[\"OPENAI_API_KEY\"] = os.environ.get(\"OPENAI_API_KEY\", \"\")\n",
+    "\n",
+    "# get from https://nla.zapier.com/demo/provider/debug (under User Information, after logging in): \n",
+    "os.environ[\"ZAPIER_NLA_API_KEY\"] = os.environ.get(\"ZAPIER_NLA_API_KEY\", \"\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4881b484-1b97-478f-b206-aec407ceff66",
+   "metadata": {},
+   "source": [
+    "## Example with Agent\n",
+    "Zapier tools can be used with an agent. See the example below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "b2044b17-c941-4ffb-8a03-027a35e2df81",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.agents import initialize_agent\n",
+    "from langchain.agents.agent_toolkits import ZapierToolkit\n",
+    "from langchain.utilities.zapier import ZapierNLAWrapper"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7b505eeb",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## step 0. expose gmail 'find email' and slack 'send channel message' actions\n",
+    "\n",
+    "# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields \"Have AI guess\"\n",
+    "# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "cab18227-c232-4214-9256-bb8dd352266c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "zapier = ZapierNLAWrapper()\n",
+    "toolkit = ZapierToolkit.from_zapier_nla_wrapper(zapier)\n",
+    "agent = initialize_agent(toolkit.get_tools(), llm, agent=\"zero-shot-react-description\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f94713de-b64d-465f-a087-00288b5f80ec",
+   "metadata": {
+    "tags": []
+   },
+   "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 find the email and summarize it.\n",
+      "Action: Gmail: Find Email\n",
+      "Action Input: Find the latest email from Silicon Valley Bank\u001b[0m\n",
+      "Observation: \u001b[31;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I need to summarize the email and send it to the #test-zapier channel in Slack.\n",
+      "Action: Slack: Send Channel Message\n",
+      "Action Input: Send a slack message to the #test-zapier channel with the text \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m{\"message__text\": \"Silicon Valley Bank has announced that Tim Mayopoulos is the new CEO. FDIC is fully insuring all deposits and they have an ask for clients and partners as they rebuild.\", \"message__permalink\": \"https://langchain.slack.com/archives/C04TSGU0RA7/p1678859932375259\", \"channel\": \"C04TSGU0RA7\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:58:52Z\", \"message__bot_profile__icons__image_36\": \"https://avatars.slack-edge.com/2022-08-02/3888649620612_f864dc1bb794cf7d82b0_36.png\", \"message__blocks[]block_id\": \"kdZZ\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'I have sent a summary of the last email from Silicon Valley Bank to the #test-zapier channel in Slack.'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"Summarize the last email I received regarding Silicon Valley Bank. Send the summary to the #test-zapier channel in slack.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bcdea831",
+   "metadata": {},
+   "source": [
+    "# Example with SimpleSequentialChain\n",
+    "If you need more explicit control, use a chain, like below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "10a46e7e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import LLMChain, TransformChain, SimpleSequentialChain\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.tools.zapier.tool import ZapierNLARunAction\n",
+    "from langchain.utilities.zapier import ZapierNLAWrapper"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "b9358048",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "## step 0. expose gmail 'find email' and slack 'send direct message' actions\n",
+    "\n",
+    "# first go here, log in, expose (enable) the two actions: https://nla.zapier.com/demo/start -- for this example, can leave all fields \"Have AI guess\"\n",
+    "# in an oauth scenario, you'd get your own <provider> id (instead of 'demo') which you route your users through first\n",
+    "\n",
+    "actions = ZapierNLAWrapper().list()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "4e80f461",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## step 1. gmail find email\n",
+    "\n",
+    "GMAIL_SEARCH_INSTRUCTIONS = \"Grab the latest email from Silicon Valley Bank\"\n",
+    "\n",
+    "def nla_gmail(inputs):\n",
+    "    action = next((a for a in actions if a[\"description\"].startswith(\"Gmail: Find Email\")), None)\n",
+    "    return {\"email_data\": ZapierNLARunAction(action_id=action[\"id\"], zapier_description=action[\"description\"], params_schema=action[\"params\"]).run(inputs[\"instructions\"])}\n",
+    "gmail_chain = TransformChain(input_variables=[\"instructions\"], output_variables=[\"email_data\"], transform=nla_gmail)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "46893233",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## step 2. generate draft reply\n",
+    "\n",
+    "template = \"\"\"You are an assisstant who drafts replies to an incoming email. Output draft reply in plain text (not JSON).\n",
+    "\n",
+    "Incoming email:\n",
+    "{email_data}\n",
+    "\n",
+    "Draft email reply:\"\"\"\n",
+    "\n",
+    "prompt_template = PromptTemplate(input_variables=[\"email_data\"], template=template)\n",
+    "reply_chain = LLMChain(llm=OpenAI(temperature=.7), prompt=prompt_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "cd85c4f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## step 3. send draft reply via a slack direct message\n",
+    "\n",
+    "SLACK_HANDLE = \"@Ankush Gola\"\n",
+    "\n",
+    "def nla_slack(inputs):\n",
+    "    action = next((a for a in actions if a[\"description\"].startswith(\"Slack: Send Direct Message\")), None)\n",
+    "    instructions = f'Send this to {SLACK_HANDLE} in Slack: {inputs[\"draft_reply\"]}'\n",
+    "    return {\"slack_data\": ZapierNLARunAction(action_id=action[\"id\"], zapier_description=action[\"description\"], params_schema=action[\"params\"]).run(instructions)}\n",
+    "slack_chain = TransformChain(input_variables=[\"draft_reply\"], output_variables=[\"slack_data\"], transform=nla_slack)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "4829cab4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
+      "\u001b[36;1m\u001b[1;3m{\"from__name\": \"Silicon Valley Bridge Bank, N.A.\", \"from__email\": \"sreply@svb.com\", \"body_plain\": \"Dear Clients, After chaotic, tumultuous & stressful days, we have clarity on path for SVB, FDIC is fully insuring all deposits & have an ask for clients & partners as we rebuild. Tim Mayopoulos <https://eml.svb.com/NjEwLUtBSy0yNjYAAAGKgoxUeBCLAyF_NxON97X4rKEaNBLG\", \"reply_to__email\": \"sreply@svb.com\", \"subject\": \"Meet the new CEO Tim Mayopoulos\", \"date\": \"Tue, 14 Mar 2023 23:42:29 -0500 (CDT)\", \"message_url\": \"https://mail.google.com/mail/u/0/#inbox/186e393b13cfdf0a\", \"attachment_count\": \"0\", \"to__emails\": \"ankush@langchain.dev\", \"message_id\": \"186e393b13cfdf0a\", \"labels\": \"IMPORTANT, CATEGORY_UPDATES, INBOX\"}\u001b[0m\n",
+      "\u001b[33;1m\u001b[1;3m\n",
+      "Dear Silicon Valley Bridge Bank, \n",
+      "\n",
+      "Thank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \n",
+      "\n",
+      "Best regards, \n",
+      "[Your Name]\u001b[0m\n",
+      "\u001b[38;5;200m\u001b[1;3m{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\n\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\n\\nBest regards, \\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[['text']]\", \"message__blocks[]elements[]type\": \"['rich_text_section']\"}\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'{\"message__text\": \"Dear Silicon Valley Bridge Bank, \\\\n\\\\nThank you for your email and the update regarding your new CEO Tim Mayopoulos. We appreciate your dedication to keeping your clients and partners informed and we look forward to continuing our relationship with you. \\\\n\\\\nBest regards, \\\\n[Your Name]\", \"message__permalink\": \"https://langchain.slack.com/archives/D04TKF5BBHU/p1678859968241629\", \"channel\": \"D04TKF5BBHU\", \"message__bot_profile__name\": \"Zapier\", \"message__team\": \"T04F8K3FZB5\", \"message__bot_id\": \"B04TRV4R74K\", \"message__bot_profile__deleted\": \"false\", \"message__bot_profile__app_id\": \"A024R9PQM\", \"ts_time\": \"2023-03-15T05:59:28Z\", \"message__blocks[]block_id\": \"p7i\", \"message__blocks[]elements[]elements[]type\": \"[[\\'text\\']]\", \"message__blocks[]elements[]type\": \"[\\'rich_text_section\\']\"}'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## finally, execute\n",
+    "\n",
+    "overall_chain = SimpleSequentialChain(chains=[gmail_chain, reply_chain, slack_chain], verbose=True)\n",
+    "overall_chain.run(GMAIL_SEARCH_INSTRUCTIONS)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "09ff954e-45f2-4595-92ea-91627abde4a0",
+   "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
+}

docs/requirements.txt

@@ -9,3 +9,4 @@ sphinx-typlog-theme==0.8.0
 sphinx-panels
 toml
 myst_nb
+sphinx_copybutton

docs/tracing/agent_with_tracing.ipynb

@@ -35,12 +35,28 @@
     "\n",
     "import langchain\n",
     "from langchain.agents import Tool, initialize_agent, load_tools\n",
+    "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.llms import OpenAI"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
+   "id": "1b62cd48",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "tools = load_tools([\"llm-math\"], llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "id": "bfa16b79-aa4b-4d41-a067-70d1f593f667",
    "metadata": {
     "tags": []
@@ -70,16 +86,12 @@
        "'1.0891804557407723'"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Agent run with tracing. Ensure that OPENAI_API_KEY is set appropriately to run this example.\n",
-    "\n",
-    "llm = OpenAI(temperature=0)\n",
-    "tools = load_tools([\"llm-math\"], llm=llm)\n",
     "agent = initialize_agent(\n",
     "    tools, llm, agent=\"zero-shot-react-description\", verbose=True\n",
     ")\n",
@@ -87,10 +99,94 @@
     "agent.run(\"What is 2 raised to .123243 power?\")"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "4829eb1d",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mQuestion: What is 2 raised to .123243 power?\n",
+      "Thought: I need a calculator to solve this problem.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"calculator\",\n",
+      "  \"action_input\": \"2^0.123243\"\n",
+      "}\n",
+      "```\n",
+      "\u001b[0m\n",
+      "Observation: calculator is not a valid tool, try another one.\n",
+      "\u001b[32;1m\u001b[1;3mI made a mistake, I need to use the correct tool for this question.\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"calculator\",\n",
+      "  \"action_input\": \"2^0.123243\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "Observation: calculator is not a valid tool, try another one.\n",
+      "\u001b[32;1m\u001b[1;3mI made a mistake, the tool name is actually \"calc\" instead of \"calculator\".\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"calc\",\n",
+      "  \"action_input\": \"2^0.123243\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "Observation: calc is not a valid tool, try another one.\n",
+      "\u001b[32;1m\u001b[1;3mI made another mistake, the tool name is actually \"Calculator\" instead of \"calc\".\n",
+      "Action:\n",
+      "```\n",
+      "{\n",
+      "  \"action\": \"Calculator\",\n",
+      "  \"action_input\": \"2^0.123243\"\n",
+      "}\n",
+      "```\n",
+      "\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mAnswer: 1.0891804557407723\n",
+      "\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mThe final answer is 1.0891804557407723.\n",
+      "Final Answer: 1.0891804557407723\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'1.0891804557407723'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Agent run with tracing using a chat model\n",
+    "agent = initialize_agent(\n",
+    "    tools, ChatOpenAI(temperature=0), agent=\"chat-zero-shot-react-description\", verbose=True\n",
+    ")\n",
+    "\n",
+    "agent.run(\"What is 2 raised to .123243 power?\")"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "25addd7f",
+   "id": "76abfd82",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -112,7 +208,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/tracing/local_installation.md

@@ -7,8 +7,8 @@ This page contains instructions for installing and then setting up the environme
 1. Ensure you have Docker installed (see [Get Docker](https://docs.docker.com/get-docker/)) and that it’s running.
 2. Install the latest version of `langchain`: `pip install langchain` or `pip install langchain -U` to upgrade your
    existing version.
-3. Run `langchain-server`
-    1. This will spin up the server in the terminal.
+3. Run `langchain-server`. This command was installed automatically when you ran the above command (`pip install langchain`).
+    1. This will spin up the server in the terminal, hosted on port `4137` by default.
     2. Once you see the terminal
        output `langchain-langchain-frontend-1 | ➜ Local: [http://localhost:4173/](http://localhost:4173/)`, navigate
        to [http://localhost:4173/](http://localhost:4173/)

docs/use_cases/combine_docs.md

@@ -76,7 +76,7 @@ Examples of vector database companies include [Pinecone](https://www.pinecone.io
 
 Although this is perhaps the most common way of document retrieval, people are starting to think about alternative
 data structures and indexing techniques specifically for working with language models. For a leading example of this,
-check out [GPT Index](https://github.com/jerryjliu/gpt_index) - a collection of data structures created by and optimized
+check out [LlamaIndex](https://github.com/jerryjliu/llama_index) - a collection of data structures created by and optimized
 for language models.
 
 ## Augmenting

docs/use_cases/evaluation.rst

@@ -1,13 +1,89 @@
 Evaluation
 ==============
 
-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.
+This section of documentation covers how we approach and think about evaluation in LangChain.
+Both evaluation of internal chains/agents, but also how we would recommend people building on top of LangChain approach evaluation.
 
-The examples here all highlight how to use language models to assist in evaluation of themselves.
+The Problem
+-----------
+
+It can be really hard to evaluate LangChain chains and agents.
+There are two main reasons for this:
+
+**# 1: Lack of data**
+
+You generally don't have a ton of data to evaluate your chains/agents over before starting a project.
+This is usually because Large Language Models (the core of most chains/agents) are terrific few-shot and zero shot learners,
+meaning you are almost always able to get started on a particular task (text-to-SQL, question answering, etc) without
+a large dataset of examples.
+This is in stark contrast to traditional machine learning where you had to first collect a bunch of datapoints
+before even getting started using a model.
+
+**# 2: Lack of metrics**
+
+Most chains/agents are performing tasks for which there are not very good metrics to evaluate performance.
+For example, one of the most common use cases is generating text of some form.
+Evaluating generated text is much more complicated than evaluating a classification prediction, or a numeric prediction.
+
+The Solution
+------------
+
+LangChain attempts to tackle both of those issues.
+What we have so far are initial passes at solutions - we do not think we have a perfect solution.
+So we very much welcome feedback, contributions, integrations, and thoughts on this.
+
+Here is what we have for each problem so far:
+
+**# 1: Lack of data**
+
+We have started `LangChainDatasets <https://huggingface.co/LangChainDatasets>`_ a Community space on Hugging Face.
+We intend this to be a collection of open source datasets for evaluating common chains and agents.
+We have contributed five datasets of our own to start, but we highly intend this to be a community effort.
+In order to contribute a dataset, you simply need to join the community and then you will be able to upload datasets.
+
+We're also aiming to make it as easy as possible for people to create their own datasets.
+As a first pass at this, we've added a QAGenerationChain, which given a document comes up
+with question-answer pairs that can be used to evaluate question-answering tasks over that document down the line.
+See `this notebook <./evaluation/qa_generation.html>`_ for an example of how to use this chain.
+
+**# 2: Lack of metrics**
+
+We have two solutions to the lack of metrics.
+
+The first solution is to use no metrics, and rather just rely on looking at results by eye to get a sense for how the chain/agent is performing.
+To assist in this, we have developed (and will continue to develop) `tracing <../tracing.html>`_, a UI-based visualizer of your chain and agent runs.
+
+The second solution we recommend is to use Language Models themselves to evaluate outputs.
+For this we have a few different chains and prompts aimed at tackling this issue.
+
+The Examples
+------------
+
+We have created a bunch of examples combining the above two solutions to show how we internally evaluate chains and agents when we are developing.
+In addition to the examples we've curated, we also highly welcome contributions here.
+To facilitate that, we've included a `template notebook <./evaluation/benchmarking_template.html>`_ for community members to use to build their own examples.
+
+The existing examples we have are:
+
+`Question Answering (State of Union) <./evaluation/qa_benchmarking_sota.html>`_: An notebook showing evaluation of a question-answering task over a State-of-the-Union address.
+
+`Question Answering (Paul Graham Essay) <./evaluation/qa_benchmarking_pg.html>`_: An notebook showing evaluation of a question-answering task over a Paul Graham essay.
+
+`SQL Question Answering (Chinook) <./evaluation/sql_qa_benchmarking_chinook.html>`_: An notebook showing evaluation of a question-answering task over a SQL database (the Chinook database).
+
+`Agent Vectorstore <./evaluation/agent_vectordb_sota_pg.html>`_: An notebook showing evaluation of an agent doing question answering while routing between two different vector databases.
+
+`Agent Search + Calculator <./evaluation/agent_benchmarking.html>`_: An notebook showing evaluation of an agent doing question answering using a Search engine and a Calculator as tools.
+
+
+Other Examples
+------------
+
+In addition, we also have some more generic resources for evaluation.
 
 `Question Answering <./evaluation/question_answering.html>`_: An overview of LLMs aimed at evaluating question answering systems in general.
 
-`Data Augmented Question Answering <./evaluation/data_augmented_question_answering.html>`_: An end-to-end example of evaluating a question answering system focused on a specific document (a VectorDBQAChain to be precise). This example highlights how to use LLMs to come up with question/answer examples to evaluate over, and then highlights how to use LLMs to evaluate performance on those generated examples.
+`Data Augmented Question Answering <./evaluation/data_augmented_question_answering.html>`_: An end-to-end example of evaluating a question answering system focused on a specific document (a RetrievalQAChain to be precise). This example highlights how to use LLMs to come up with question/answer examples to evaluate over, and then highlights how to use LLMs to evaluate performance on those generated examples.
 
 `Hugging Face Datasets <./evaluation/huggingface_datasets.html>`_: Covers an example of loading and using a dataset from Hugging Face for evaluation.
 

docs/use_cases/evaluation/agent_benchmarking.ipynb

@@ -0,0 +1,343 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "984169ca",
+   "metadata": {},
+   "source": [
+    "# Agent Benchmarking: Search + Calculator\n",
+    "\n",
+    "Here we go over how to benchmark performance of an agent on tasks where it has access to a calculator and a search tool.\n",
+    "\n",
+    "It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "46bf9205",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a16b75d",
+   "metadata": {},
+   "source": [
+    "## Loading the data\n",
+    "First, let's load the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5b2d5e98",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--agent-search-calculator-8a025c0ce5fb99d2/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3a275586643f4ccfba1a8d54be28c351",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"agent-search-calculator\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ab6a716",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "Now we need to load an agent capable of answering these questions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "c18680b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import LLMMathChain\n",
+    "from langchain.agents import initialize_agent, Tool, load_tools\n",
+    "\n",
+    "tools = load_tools(['serpapi', 'llm-math'], llm=OpenAI(temperature=0))\n",
+    "agent = initialize_agent(tools, OpenAI(temperature=0), agent=\"zero-shot-react-description\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "68504a8f",
+   "metadata": {},
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "cbcafc92",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'38,630,316 people live in Canada as of 2023.'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(dataset[0]['question'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c16cd7",
+   "metadata": {},
+   "source": [
+    "## Make many predictions\n",
+    "Now we can make predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "24b4c66e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Retrying langchain.llms.openai.completion_with_retry.<locals>._completion_with_retry in 4.0 seconds as it raised APIConnectionError: Error communicating with OpenAI: ('Connection aborted.', ConnectionResetError(54, 'Connection reset by peer')).\n"
+     ]
+    }
+   ],
+   "source": [
+    "predictions = []\n",
+    "predicted_dataset = []\n",
+    "error_dataset = []\n",
+    "for data in dataset:\n",
+    "    new_data = {\"input\": data[\"question\"], \"answer\": data[\"answer\"]}\n",
+    "    try:\n",
+    "        predictions.append(agent(new_data))\n",
+    "        predicted_dataset.append(new_data)\n",
+    "    except Exception:\n",
+    "        error_dataset.append(new_data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49d969fb",
+   "metadata": {},
+   "source": [
+    "## Evaluate performance\n",
+    "Now we can evaluate the predictions. The first thing we can do is look at them by eye."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "1d583f03",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'How many people live in canada as of 2023?',\n",
+       " 'answer': 'approximately 38,625,801',\n",
+       " 'output': '38,630,316 people live in Canada as of 2023.',\n",
+       " 'intermediate_steps': [(AgentAction(tool='Search', tool_input='Population of Canada 2023', log=' I need to find population data\\nAction: Search\\nAction Input: Population of Canada 2023'),\n",
+       "   '38,630,316')]}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4783344b",
+   "metadata": {},
+   "source": [
+    "Next, we can use a language model to score them programatically"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "d0a9341d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation.qa import QAEvalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "1612dec1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "eval_chain = QAEvalChain.from_llm(llm)\n",
+    "graded_outputs = eval_chain.evaluate(dataset, predictions, question_key=\"question\", prediction_key=\"output\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79587806",
+   "metadata": {},
+   "source": [
+    "We can add in the graded output to the `predictions` dict and then get a count of the grades."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "2a689df5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, prediction in enumerate(predictions):\n",
+    "    prediction['grade'] = graded_outputs[i]['text']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "27b61215",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Counter({' CORRECT': 4, ' INCORRECT': 6})"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "Counter([pred['grade'] for pred in predictions])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12fe30f4",
+   "metadata": {},
+   "source": [
+    "We can also filter the datapoints to the incorrect examples and look at them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "47c692a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "incorrect = [pred for pred in predictions if pred['grade'] == \" INCORRECT\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "0ef976c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': \"who is dua lipa's boyfriend? what is his age raised to the .43 power?\",\n",
+       " 'answer': 'her boyfriend is Romain Gravas. his age raised to the .43 power is approximately 4.9373857399466665',\n",
+       " 'output': \"Isaac Carew, Dua Lipa's boyfriend, is 36 years old and his age raised to the .43 power is 4.6688516567750975.\",\n",
+       " 'intermediate_steps': [(AgentAction(tool='Search', tool_input=\"Dua Lipa's boyfriend\", log=' I need to find out who Dua Lipa\\'s boyfriend is and then calculate his age raised to the .43 power\\nAction: Search\\nAction Input: \"Dua Lipa\\'s boyfriend\"'),\n",
+       "   'Dua and Isaac, a model and a chef, dated on and off from 2013 to 2019. The two first split in early 2017, which is when Dua went on to date LANY ...'),\n",
+       "  (AgentAction(tool='Search', tool_input='Isaac Carew age', log=' I need to find out Isaac\\'s age\\nAction: Search\\nAction Input: \"Isaac Carew age\"'),\n",
+       "   '36 years'),\n",
+       "  (AgentAction(tool='Calculator', tool_input='36^.43', log=' I need to calculate 36 raised to the .43 power\\nAction: Calculator\\nAction Input: 36^.43'),\n",
+       "   'Answer: 4.6688516567750975\\n')],\n",
+       " 'grade': ' INCORRECT'}"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "incorrect[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7710401a",
+   "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
+}

docs/use_cases/evaluation/agent_vectordb_sota_pg.ipynb

@@ -0,0 +1,503 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "984169ca",
+   "metadata": {},
+   "source": [
+    "# Agent VectorDB Question Answering Benchmarking\n",
+    "\n",
+    "Here we go over how to benchmark performance on a question answering task using an agent to route between multiple vectordatabases.\n",
+    "\n",
+    "It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "7b57a50f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a16b75d",
+   "metadata": {},
+   "source": [
+    "## Loading the data\n",
+    "First, let's load the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5b2d5e98",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--agent-vectordb-qa-sota-pg-d3ae24016b514f92/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4c389519842e4b65afc33006a531dcbc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"agent-vectordb-qa-sota-pg\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "61375342",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What is the purpose of the NATO Alliance?',\n",
+       " 'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',\n",
+       " 'steps': [{'tool': 'State of Union QA System', 'tool_input': None},\n",
+       "  {'tool': None, 'tool_input': 'What is the purpose of the NATO Alliance?'}]}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "02500304",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What is the purpose of YC?',\n",
+       " 'answer': 'The purpose of YC is to cause startups to be founded that would not otherwise have existed.',\n",
+       " 'steps': [{'tool': 'Paul Graham QA System', 'tool_input': None},\n",
+       "  {'tool': None, 'tool_input': 'What is the purpose of YC?'}]}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset[-1]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ab6a716",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "Now we need to create some pipelines for doing question answering. Step one in that is creating indexes over the data in question."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "c18680b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader(\"../../modules/state_of_the_union.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "7f0de2b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.indexes import VectorstoreIndexCreator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ef84ff99",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "vectorstore_sota = VectorstoreIndexCreator(vectorstore_kwargs={\"collection_name\":\"sota\"}).from_loaders([loader]).vectorstore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0b5d8f6",
+   "metadata": {},
+   "source": [
+    "Now we can create a question answering chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "8843cb0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "573719a0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain_sota = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0), chain_type=\"stuff\", retriever=vectorstore_sota, input_key=\"question\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e48b03d8",
+   "metadata": {},
+   "source": [
+    "Now we do the same for the Paul Graham data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "c2dbb014",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = TextLoader(\"../../modules/paul_graham_essay.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "98d16f08",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "vectorstore_pg = VectorstoreIndexCreator(vectorstore_kwargs={\"collection_name\":\"paul_graham\"}).from_loaders([loader]).vectorstore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "ec0aab02",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain_pg = RetrievalQA.from_chain_type(llm=OpenAI(temperature=0), chain_type=\"stuff\", retriever=vectorstore_pg, input_key=\"question\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "76b5f8fb",
+   "metadata": {},
+   "source": [
+    "We can now set up an agent to route between them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "ade1aafa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import initialize_agent, Tool\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name = \"State of Union QA System\",\n",
+    "        func=chain_sota.run,\n",
+    "        description=\"useful for when you need to answer questions about the most recent state of the union address. Input should be a fully formed question.\"\n",
+    "    ),\n",
+    "    Tool(\n",
+    "        name = \"Paul Graham System\",\n",
+    "        func=chain_pg.run,\n",
+    "        description=\"useful for when you need to answer questions about Paul Graham. Input should be a fully formed question.\"\n",
+    "    ),\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "104853f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = initialize_agent(tools, OpenAI(temperature=0), agent=\"zero-shot-react-description\", max_iterations=3)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7f036641",
+   "metadata": {},
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "4664e79f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The purpose of the NATO Alliance is to promote peace and security in the North Atlantic region by providing a collective defense against potential threats.'"
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(dataset[0]['question'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c16cd7",
+   "metadata": {},
+   "source": [
+    "## Make many predictions\n",
+    "Now we can make predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "799f6c17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = []\n",
+    "predicted_dataset = []\n",
+    "error_dataset = []\n",
+    "for data in dataset:\n",
+    "    new_data = {\"input\": data[\"question\"], \"answer\": data[\"answer\"]}\n",
+    "    try:\n",
+    "        predictions.append(agent(new_data))\n",
+    "        predicted_dataset.append(new_data)\n",
+    "    except Exception:\n",
+    "        error_dataset.append(new_data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49d969fb",
+   "metadata": {},
+   "source": [
+    "## Evaluate performance\n",
+    "Now we can evaluate the predictions. The first thing we can do is look at them by eye."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d583f03",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4783344b",
+   "metadata": {},
+   "source": [
+    "Next, we can use a language model to score them programatically"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d0a9341d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation.qa import QAEvalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "1612dec1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "eval_chain = QAEvalChain.from_llm(llm)\n",
+    "graded_outputs = eval_chain.evaluate(predicted_dataset, predictions, question_key=\"input\", prediction_key=\"output\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79587806",
+   "metadata": {},
+   "source": [
+    "We can add in the graded output to the `predictions` dict and then get a count of the grades."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "2a689df5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, prediction in enumerate(predictions):\n",
+    "    prediction['grade'] = graded_outputs[i]['text']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "27b61215",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Counter({' CORRECT': 19, ' INCORRECT': 14})"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "Counter([pred['grade'] for pred in predictions])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12fe30f4",
+   "metadata": {},
+   "source": [
+    "We can also filter the datapoints to the incorrect examples and look at them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "47c692a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "incorrect = [pred for pred in predictions if pred['grade'] == \" INCORRECT\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "id": "0ef976c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input': 'What is the purpose of the Bipartisan Innovation Act mentioned in the text?',\n",
+       " 'answer': 'The Bipartisan Innovation Act will make record investments in emerging technologies and American manufacturing to level the playing field with China and other competitors.',\n",
+       " 'output': 'The purpose of the Bipartisan Innovation Act is to promote innovation and entrepreneurship in the United States by providing tax incentives and other support for startups and small businesses.',\n",
+       " 'grade': ' INCORRECT'}"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "incorrect[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7710401a",
+   "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
+}

docs/use_cases/evaluation/benchmarking_template.ipynb

@@ -0,0 +1,160 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a175c650",
+   "metadata": {},
+   "source": [
+    "# Benchmarking Template\n",
+    "\n",
+    "This is an example notebook that can be used to create a benchmarking notebook for a task of your choice. Evaluation is really hard, and so we greatly welcome any contributions that can make it easier for people to experiment"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "984169ca",
+   "metadata": {},
+   "source": [
+    "It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "9fe4d1b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f66405e",
+   "metadata": {},
+   "source": [
+    "## Loading the data\n",
+    "\n",
+    "First, let's load the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "79402a8f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This notebook should so how to load the dataset from LangChainDatasets on Hugging Face\n",
+    "\n",
+    "# Please upload your dataset to https://huggingface.co/LangChainDatasets\n",
+    "\n",
+    "# The value passed into `load_dataset` should NOT have the `LangChainDatasets/` prefix\n",
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"TODO\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a16b75d",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "\n",
+    "This next section should have an example of setting up a chain that can be run on this dataset."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a2661ce0",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c0062e7",
+   "metadata": {},
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d28c5e7d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Example of running the chain on a single datapoint (`dataset[0]`) goes here"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c16cd7",
+   "metadata": {},
+   "source": [
+    "## Make many predictions\n",
+    "Now we can make predictions."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "24b4c66e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Example of running the chain on many predictions goes here\n",
+    "\n",
+    "# Sometimes its as simple as `chain.apply(dataset)`\n",
+    "\n",
+    "# Othertimes you may want to write a for loop to catch errors"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4783344b",
+   "metadata": {},
+   "source": [
+    "## Evaluate performance\n",
+    "\n",
+    "Any guide to evaluating performance in a more systematic manner goes here."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7710401a",
+   "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
+}

docs/use_cases/evaluation/data_augmented_question_answering.ipynb

@@ -23,12 +23,13 @@
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
     "from langchain.vectorstores import Chroma\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain import OpenAI, VectorDBQA"
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import RetrievalQA"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "4fdc211d",
    "metadata": {},
    "outputs": [
@@ -50,7 +51,7 @@
     "\n",
     "embeddings = OpenAIEmbeddings()\n",
     "docsearch = Chroma.from_documents(texts, embeddings)\n",
-    "qa = VectorDBQA.from_llm(llm=OpenAI(), vectorstore=docsearch)"
+    "qa = RetrievalQA.from_llm(llm=OpenAI(), retriever=docsearch.as_retriever())"
    ]
   },
   {
@@ -67,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "3459b001",
    "metadata": {},
    "outputs": [],
@@ -87,7 +88,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "b9c3fa75",
    "metadata": {},
    "outputs": [],
@@ -99,7 +100,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "c24543a9",
    "metadata": {},
    "outputs": [],
@@ -116,16 +117,16 @@
     {
      "data": {
       "text/plain": [
-       "[{'query': 'What did Vladimir Putin miscalculate when he sought to shake the foundations of the free world? ',\n",
-       "  'answer': 'He miscalculated that the world would roll over and that he could roll into Ukraine without facing resistance.'},\n",
-       " {'query': 'What is the purpose of NATO?',\n",
-       "  'answer': 'The purpose of NATO is to secure peace and stability in Europe after World War 2.'},\n",
-       " {'query': \"What did the author do to prepare for Putin's attack on Ukraine?\",\n",
-       "  'answer': \"The author spent months building a coalition of freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin, shared with the world in advance what they knew Putin was planning, and countered Russia's lies with truth.\"},\n",
-       " {'query': 'What are the US and its allies doing to isolate Russia from the world?',\n",
-       "  'answer': \"Enforcing powerful economic sanctions, cutting off Russia's largest banks from the international financial system, preventing Russia's central bank from defending the Russian Ruble, choking off Russia's access to technology, and joining with European allies to find and seize assets of Russian oligarchs.\"},\n",
-       " {'query': 'How much direct assistance is the U.S. providing to Ukraine?',\n",
-       "  'answer': 'The U.S. is providing more than $1 Billion in direct assistance to Ukraine.'}]"
+       "[{'query': 'According to the document, what did Vladimir Putin miscalculate?',\n",
+       "  'answer': 'He miscalculated that he could roll into Ukraine and the world would roll over.'},\n",
+       " {'query': 'Who is the Ukrainian Ambassador to the United States?',\n",
+       "  'answer': 'The Ukrainian Ambassador to the United States is here tonight.'},\n",
+       " {'query': 'How many countries were part of the coalition formed to confront Putin?',\n",
+       "  'answer': '27 members of the European Union, France, Germany, Italy, the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland.'},\n",
+       " {'query': 'What action is the U.S. Department of Justice taking to target Russian oligarchs?',\n",
+       "  'answer': 'The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and joining with European allies to find and seize their yachts, luxury apartments, and private jets.'},\n",
+       " {'query': 'How much direct assistance is the United States providing to Ukraine?',\n",
+       "  'answer': 'The United States is providing more than $1 Billion in direct assistance to Ukraine.'}]"
       ]
      },
      "execution_count": 6,
@@ -211,44 +212,43 @@
       "Example 0:\n",
       "Question: What did the president say about Ketanji Brown Jackson\n",
       "Real Answer: He praised her legal ability and said he nominated her for the supreme court.\n",
-      "Predicted Answer:  The president said that Ketanji Brown Jackson is one of the nation's top legal minds and that she will continue Justice Breyer's legacy of excellence.\n",
+      "Predicted Answer:  The president said that she is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by both Democrats and Republicans.\n",
       "Predicted Grade:  CORRECT\n",
       "\n",
       "Example 1:\n",
       "Question: What did the president say about Michael Jackson\n",
       "Real Answer: Nothing\n",
-      "Predicted Answer: \n",
-      "The president did not mention Michael Jackson in this context.\n",
+      "Predicted Answer:  The president did not mention Michael Jackson in this speech.\n",
       "Predicted Grade:  CORRECT\n",
       "\n",
       "Example 2:\n",
-      "Question: What did Vladimir Putin miscalculate when he sought to shake the foundations of the free world? \n",
-      "Real Answer: He miscalculated that the world would roll over and that he could roll into Ukraine without facing resistance.\n",
-      "Predicted Answer:  Putin miscalculated that the West and NATO wouldn't respond to his attack on Ukraine and that he could divide the US and its allies.\n",
+      "Question: According to the document, what did Vladimir Putin miscalculate?\n",
+      "Real Answer: He miscalculated that he could roll into Ukraine and the world would roll over.\n",
+      "Predicted Answer:  Putin miscalculated that the world would roll over when he rolled into Ukraine.\n",
       "Predicted Grade:  CORRECT\n",
       "\n",
       "Example 3:\n",
-      "Question: What is the purpose of NATO?\n",
-      "Real Answer: The purpose of NATO is to secure peace and stability in Europe after World War 2.\n",
-      "Predicted Answer:  The purpose of NATO is to secure peace and stability in Europe after World War 2.\n",
-      "Predicted Grade:  CORRECT\n",
+      "Question: Who is the Ukrainian Ambassador to the United States?\n",
+      "Real Answer: The Ukrainian Ambassador to the United States is here tonight.\n",
+      "Predicted Answer:  I don't know.\n",
+      "Predicted Grade:  INCORRECT\n",
       "\n",
       "Example 4:\n",
-      "Question: What did the author do to prepare for Putin's attack on Ukraine?\n",
-      "Real Answer: The author spent months building a coalition of freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin, shared with the world in advance what they knew Putin was planning, and countered Russia's lies with truth.\n",
-      "Predicted Answer:  The author prepared extensively and carefully. They spent months building a coalition of other freedom-loving nations from Europe and the Americas to Asia and Africa to confront Putin, and they spent countless hours unifying their European allies. They also shared with the world in advance what they knew Putin was planning and precisely how he would try to falsely justify his aggression. They countered Russia’s lies with truth.\n",
-      "Predicted Grade:  CORRECT\n",
+      "Question: How many countries were part of the coalition formed to confront Putin?\n",
+      "Real Answer: 27 members of the European Union, France, Germany, Italy, the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland.\n",
+      "Predicted Answer:  The coalition included freedom-loving nations from Europe and the Americas to Asia and Africa, 27 members of the European Union including France, Germany, Italy, the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland.\n",
+      "Predicted Grade:  INCORRECT\n",
       "\n",
       "Example 5:\n",
-      "Question: What are the US and its allies doing to isolate Russia from the world?\n",
-      "Real Answer: Enforcing powerful economic sanctions, cutting off Russia's largest banks from the international financial system, preventing Russia's central bank from defending the Russian Ruble, choking off Russia's access to technology, and joining with European allies to find and seize assets of Russian oligarchs.\n",
-      "Predicted Answer:  The US and its allies are enforcing economic sanctions on Russia, cutting off its largest banks from the international financial system, preventing its central bank from defending the Russian Ruble, choking off Russia's access to technology, closing American airspace to all Russian flights, and providing support to Ukraine.\n",
-      "Predicted Grade:  CORRECT\n",
+      "Question: What action is the U.S. Department of Justice taking to target Russian oligarchs?\n",
+      "Real Answer: The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and joining with European allies to find and seize their yachts, luxury apartments, and private jets.\n",
+      "Predicted Answer:  The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and to find and seize their yachts, luxury apartments, and private jets.\n",
+      "Predicted Grade:  INCORRECT\n",
       "\n",
       "Example 6:\n",
-      "Question: How much direct assistance is the U.S. providing to Ukraine?\n",
-      "Real Answer: The U.S. is providing more than $1 Billion in direct assistance to Ukraine.\n",
-      "Predicted Answer:  The U.S. is providing more than $1 Billion in direct assistance to Ukraine.\n",
+      "Question: How much direct assistance is the United States providing to Ukraine?\n",
+      "Real Answer: The United States is providing more than $1 Billion in direct assistance to Ukraine.\n",
+      "Predicted Answer:  The United States is providing more than $1 billion in direct assistance to Ukraine.\n",
       "Predicted Grade:  CORRECT\n",
       "\n"
      ]
@@ -264,13 +264,159 @@
     "    print()"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "50a9e845",
+   "metadata": {},
+   "source": [
+    "## Evaluate with Other Metrics\n",
+    "\n",
+    "In addition to predicting whether the answer is correct or incorrect using a language model, we can also use other metrics to get a more nuanced view on the quality of the answers. To do so, we can use the [Critique](https://docs.inspiredco.ai/critique/) library, which allows for simple calculation of various metrics over generated text.\n",
+    "\n",
+    "First you can get an API key from the [Inspired Cognition Dashboard](https://dashboard.inspiredco.ai) and do some setup:\n",
+    "\n",
+    "```bash\n",
+    "export INSPIREDCO_API_KEY=\"...\"\n",
+    "pip install inspiredco\n",
+    "```"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 13,
    "id": "bd0b01dc",
    "metadata": {},
    "outputs": [],
-   "source": []
+   "source": [
+    "import inspiredco.critique\n",
+    "import os\n",
+    "critique = inspiredco.critique.Critique(api_key=os.environ['INSPIREDCO_API_KEY'])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4f52629e",
+   "metadata": {},
+   "source": [
+    "Then run the following code to set up the configuration and calculate the [ROUGE](https://docs.inspiredco.ai/critique/metric_rouge.html), [chrf](https://docs.inspiredco.ai/critique/metric_chrf.html), [BERTScore](https://docs.inspiredco.ai/critique/metric_bert_score.html), and [UniEval](https://docs.inspiredco.ai/critique/metric_uni_eval.html) (you can choose [other metrics](https://docs.inspiredco.ai/critique/metrics.html) too):"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "84a0ba21",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metrics = {\n",
+    "    \"rouge\": {\n",
+    "        \"metric\": \"rouge\",\n",
+    "        \"config\": {\"variety\": \"rouge_l\"},\n",
+    "    },\n",
+    "    \"chrf\": {\n",
+    "        \"metric\": \"chrf\",\n",
+    "        \"config\": {},\n",
+    "    },\n",
+    "    \"bert_score\": {\n",
+    "        \"metric\": \"bert_score\",\n",
+    "        \"config\": {\"model\": \"bert-base-uncased\"},\n",
+    "    },\n",
+    "    \"uni_eval\": {\n",
+    "        \"metric\": \"uni_eval\",\n",
+    "        \"config\": {\"task\": \"summarization\", \"evaluation_aspect\": \"relevance\"},\n",
+    "    },\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "3b9a4056",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "critique_data = [\n",
+    "    {\"target\": pred['result'], \"references\": [pred['answer']]} for pred in predictions\n",
+    "]\n",
+    "eval_results = {\n",
+    "    k: critique.evaluate(dataset=critique_data, metric=v[\"metric\"], config=v[\"config\"])\n",
+    "    for k, v in metrics.items()\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6f0ae799",
+   "metadata": {},
+   "source": [
+    "Finally, we can print out the results. We can see that overall the scores are higher when the output is semantically correct, and also when the output closely matches with the gold-standard answer."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "b51edcf4",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Example 0:\n",
+      "Question: What did the president say about Ketanji Brown Jackson\n",
+      "Real Answer: He praised her legal ability and said he nominated her for the supreme court.\n",
+      "Predicted Answer:  The president said that she is one of the nation's top legal minds, a former top litigator in private practice, a former federal public defender, and from a family of public school educators and police officers. He also said that she is a consensus builder and that she has received a broad range of support from the Fraternal Order of Police to former judges appointed by both Democrats and Republicans.\n",
+      "Predicted Scores: rouge=0.0941, chrf=0.2001, bert_score=0.5219, uni_eval=0.9043\n",
+      "\n",
+      "Example 1:\n",
+      "Question: What did the president say about Michael Jackson\n",
+      "Real Answer: Nothing\n",
+      "Predicted Answer:  The president did not mention Michael Jackson in this speech.\n",
+      "Predicted Scores: rouge=0.0000, chrf=0.1087, bert_score=0.3486, uni_eval=0.7802\n",
+      "\n",
+      "Example 2:\n",
+      "Question: According to the document, what did Vladimir Putin miscalculate?\n",
+      "Real Answer: He miscalculated that he could roll into Ukraine and the world would roll over.\n",
+      "Predicted Answer:  Putin miscalculated that the world would roll over when he rolled into Ukraine.\n",
+      "Predicted Scores: rouge=0.5185, chrf=0.6955, bert_score=0.8421, uni_eval=0.9578\n",
+      "\n",
+      "Example 3:\n",
+      "Question: Who is the Ukrainian Ambassador to the United States?\n",
+      "Real Answer: The Ukrainian Ambassador to the United States is here tonight.\n",
+      "Predicted Answer:  I don't know.\n",
+      "Predicted Scores: rouge=0.0000, chrf=0.0375, bert_score=0.3159, uni_eval=0.7493\n",
+      "\n",
+      "Example 4:\n",
+      "Question: How many countries were part of the coalition formed to confront Putin?\n",
+      "Real Answer: 27 members of the European Union, France, Germany, Italy, the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland.\n",
+      "Predicted Answer:  The coalition included freedom-loving nations from Europe and the Americas to Asia and Africa, 27 members of the European Union including France, Germany, Italy, the United Kingdom, Canada, Japan, Korea, Australia, New Zealand, and many others, even Switzerland.\n",
+      "Predicted Scores: rouge=0.7419, chrf=0.8602, bert_score=0.8388, uni_eval=0.0669\n",
+      "\n",
+      "Example 5:\n",
+      "Question: What action is the U.S. Department of Justice taking to target Russian oligarchs?\n",
+      "Real Answer: The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and joining with European allies to find and seize their yachts, luxury apartments, and private jets.\n",
+      "Predicted Answer:  The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and to find and seize their yachts, luxury apartments, and private jets.\n",
+      "Predicted Scores: rouge=0.9412, chrf=0.8687, bert_score=0.9607, uni_eval=0.9718\n",
+      "\n",
+      "Example 6:\n",
+      "Question: How much direct assistance is the United States providing to Ukraine?\n",
+      "Real Answer: The United States is providing more than $1 Billion in direct assistance to Ukraine.\n",
+      "Predicted Answer:  The United States is providing more than $1 billion in direct assistance to Ukraine.\n",
+      "Predicted Scores: rouge=1.0000, chrf=0.9483, bert_score=1.0000, uni_eval=0.9734\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i, eg in enumerate(examples):\n",
+    "    score_string = \", \".join([f\"{k}={v['examples'][i]['value']:.4f}\" for k, v in eval_results.items()])\n",
+    "    print(f\"Example {i}:\")\n",
+    "    print(\"Question: \" + predictions[i]['query'])\n",
+    "    print(\"Real Answer: \" + predictions[i]['answer'])\n",
+    "    print(\"Predicted Answer: \" + predictions[i]['result'])\n",
+    "    print(\"Predicted Scores: \" + score_string)\n",
+    "    print()"
+   ]
   }
  ],
  "metadata": {

docs/use_cases/evaluation/llm_math.ipynb

@@ -0,0 +1,306 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a4734146",
+   "metadata": {},
+   "source": [
+    "# LLM Math\n",
+    "\n",
+    "Evaluating chains that know how to do math."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "fdd7afae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "ce05ffea",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d028a511cede4de2b845b9a9954d6bea",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading readme:   0%|          | 0.00/21.0 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Downloading and preparing dataset json/LangChainDatasets--llm-math to /Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--llm-math-509b11d101165afa/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a71c8e5a21dd4da5a20a354b544f7a58",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading data files:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ae530ca624154a1a934075c47d1093a6",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading data:   0%|          | 0.00/631 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "7a4968df05d84bc483aa2c5039aecafe",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Extracting data files:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Generating train split: 0 examples [00:00, ? examples/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset json downloaded and prepared to /Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--llm-math-509b11d101165afa/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51. Subsequent calls will reuse this data.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9a2caed96225410fb1cc0f8f155eb766",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"llm-math\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a998d6f",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "Now we need to create some pipelines for doing math."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "7078f7f8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import LLMMathChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "2bd70c46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "954c3270",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = LLMMathChain(llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "f252027e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = chain.apply(dataset)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "c8af7041",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "numeric_output = [float(p['answer'].strip().strip(\"Answer: \")) for p in predictions]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "cc09ffe4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "correct = [example['answer'] == numeric_output[i] for i, example in enumerate(dataset)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "585244e4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "1.0"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sum(correct) / len(correct)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "0d14ac78",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "input:  5\n",
+      "expected output : 5.0\n",
+      "prediction:  5.0\n",
+      "input:  5 + 3\n",
+      "expected output : 8.0\n",
+      "prediction:  8.0\n",
+      "input:  2^3.171\n",
+      "expected output : 9.006708689094099\n",
+      "prediction:  9.006708689094099\n",
+      "input:    2 ^3.171 \n",
+      "expected output : 9.006708689094099\n",
+      "prediction:  9.006708689094099\n",
+      "input:  two to the power of three point one hundred seventy one\n",
+      "expected output : 9.006708689094099\n",
+      "prediction:  9.006708689094099\n",
+      "input:  five + three squared minus 1\n",
+      "expected output : 13.0\n",
+      "prediction:  13.0\n",
+      "input:  2097 times 27.31\n",
+      "expected output : 57269.07\n",
+      "prediction:  57269.07\n",
+      "input:  two thousand ninety seven times twenty seven point thirty one\n",
+      "expected output : 57269.07\n",
+      "prediction:  57269.07\n",
+      "input:  209758 / 2714\n",
+      "expected output : 77.28739867354459\n",
+      "prediction:  77.28739867354459\n",
+      "input:  209758.857 divided by 2714.31\n",
+      "expected output : 77.27888745205964\n",
+      "prediction:  77.27888745205964\n"
+     ]
+    }
+   ],
+   "source": [
+    "for i, example in enumerate(dataset):\n",
+    "    print(\"input: \", example[\"question\"])\n",
+    "    print(\"expected output :\", example[\"answer\"])\n",
+    "    print(\"prediction: \", numeric_output[i])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b9021ffd",
+   "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
+}

docs/use_cases/evaluation/qa_benchmarking_pg.ipynb

@@ -0,0 +1,374 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "984169ca",
+   "metadata": {},
+   "source": [
+    "# Question Answering Benchmarking: Paul Graham Essay\n",
+    "\n",
+    "Here we go over how to benchmark performance on a question answering task over a Paul Graham essay.\n",
+    "\n",
+    "It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3bd13ab7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a16b75d",
+   "metadata": {},
+   "source": [
+    "## Loading the data\n",
+    "First, let's load the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5b2d5e98",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--question-answering-paul-graham-76e8f711e038d742/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9264acfe710b4faabf060f0fcf4f7308",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"question-answering-paul-graham\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ab6a716",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "Now we need to create some pipelines for doing question answering. Step one in that is creating an index over the data in question."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "c18680b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader(\"../../modules/paul_graham_essay.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7f0de2b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.indexes import VectorstoreIndexCreator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ef84ff99",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "vectorstore = VectorstoreIndexCreator().from_loaders([loader]).vectorstore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0b5d8f6",
+   "metadata": {},
+   "source": [
+    "Now we can create a question answering chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "8843cb0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "573719a0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=vectorstore.as_retriever(), input_key=\"question\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "53b5aa23",
+   "metadata": {},
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "3f81d951",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What were the two main things the author worked on before college?',\n",
+       " 'answer': 'The two main things the author worked on before college were writing and programming.',\n",
+       " 'result': ' Writing and programming.'}"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain(dataset[0])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c16cd7",
+   "metadata": {},
+   "source": [
+    "## Make many predictions\n",
+    "Now we can make predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "24b4c66e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = chain.apply(dataset)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49d969fb",
+   "metadata": {},
+   "source": [
+    "## Evaluate performance\n",
+    "Now we can evaluate the predictions. The first thing we can do is look at them by eye."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1d583f03",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What were the two main things the author worked on before college?',\n",
+       " 'answer': 'The two main things the author worked on before college were writing and programming.',\n",
+       " 'result': ' Writing and programming.'}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4783344b",
+   "metadata": {},
+   "source": [
+    "Next, we can use a language model to score them programatically"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "d0a9341d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation.qa import QAEvalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "1612dec1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "eval_chain = QAEvalChain.from_llm(llm)\n",
+    "graded_outputs = eval_chain.evaluate(dataset, predictions, question_key=\"question\", prediction_key=\"result\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79587806",
+   "metadata": {},
+   "source": [
+    "We can add in the graded output to the `predictions` dict and then get a count of the grades."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "2a689df5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, prediction in enumerate(predictions):\n",
+    "    prediction['grade'] = graded_outputs[i]['text']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "27b61215",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Counter({' CORRECT': 12, ' INCORRECT': 10})"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "Counter([pred['grade'] for pred in predictions])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12fe30f4",
+   "metadata": {},
+   "source": [
+    "We can also filter the datapoints to the incorrect examples and look at them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "47c692a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "incorrect = [pred for pred in predictions if pred['grade'] == \" INCORRECT\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "0ef976c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What did the author write their dissertation on?',\n",
+       " 'answer': 'The author wrote their dissertation on applications of continuations.',\n",
+       " 'result': ' The author does not mention what their dissertation was on, so it is not known.',\n",
+       " 'grade': ' INCORRECT'}"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "incorrect[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7710401a",
+   "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
+}

docs/use_cases/evaluation/qa_benchmarking_sota.ipynb

@@ -0,0 +1,374 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "984169ca",
+   "metadata": {},
+   "source": [
+    "# Question Answering Benchmarking: State of the Union Address\n",
+    "\n",
+    "Here we go over how to benchmark performance on a question answering task over a state of the union address.\n",
+    "\n",
+    "It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f127fb04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a16b75d",
+   "metadata": {},
+   "source": [
+    "## Loading the data\n",
+    "First, let's load the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5b2d5e98",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Found cached dataset json (/Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--question-answering-state-of-the-union-a7e5a3b2db4f440d/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51)\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"question-answering-state-of-the-union\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4ab6a716",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "Now we need to create some pipelines for doing question answering. Step one in that is creating an index over the data in question."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "c18680b5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader(\"../../modules/state_of_the_union.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "7f0de2b3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.indexes import VectorstoreIndexCreator"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "ef84ff99",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Running Chroma using direct local API.\n",
+      "Using DuckDB in-memory for database. Data will be transient.\n"
+     ]
+    }
+   ],
+   "source": [
+    "vectorstore = VectorstoreIndexCreator().from_loaders([loader]).vectorstore"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0b5d8f6",
+   "metadata": {},
+   "source": [
+    "Now we can create a question answering chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8843cb0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import RetrievalQA\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "573719a0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type=\"stuff\", retriever=vectorstore.as_retriever(), input_key=\"question\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "37d669e9",
+   "metadata": {},
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "3089e409",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What is the purpose of the NATO Alliance?',\n",
+       " 'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',\n",
+       " 'result': ' The NATO Alliance was created to secure peace and stability in Europe after World War 2.'}"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain(dataset[0])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c16cd7",
+   "metadata": {},
+   "source": [
+    "## Make many predictions\n",
+    "Now we can make predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "24b4c66e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = chain.apply(dataset)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "49d969fb",
+   "metadata": {},
+   "source": [
+    "## Evaluate performance\n",
+    "Now we can evaluate the predictions. The first thing we can do is look at them by eye."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "1d583f03",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What is the purpose of the NATO Alliance?',\n",
+       " 'answer': 'The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.',\n",
+       " 'result': ' The purpose of the NATO Alliance is to secure peace and stability in Europe after World War 2.'}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4783344b",
+   "metadata": {},
+   "source": [
+    "Next, we can use a language model to score them programatically"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d0a9341d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation.qa import QAEvalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1612dec1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "eval_chain = QAEvalChain.from_llm(llm)\n",
+    "graded_outputs = eval_chain.evaluate(dataset, predictions, question_key=\"question\", prediction_key=\"result\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79587806",
+   "metadata": {},
+   "source": [
+    "We can add in the graded output to the `predictions` dict and then get a count of the grades."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "2a689df5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, prediction in enumerate(predictions):\n",
+    "    prediction['grade'] = graded_outputs[i]['text']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "27b61215",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Counter({' CORRECT': 7, ' INCORRECT': 4})"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "Counter([pred['grade'] for pred in predictions])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12fe30f4",
+   "metadata": {},
+   "source": [
+    "We can also filter the datapoints to the incorrect examples and look at them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "47c692a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "incorrect = [pred for pred in predictions if pred['grade'] == \" INCORRECT\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "0ef976c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What is the U.S. Department of Justice doing to combat the crimes of Russian oligarchs?',\n",
+       " 'answer': 'The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.',\n",
+       " 'result': ' The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs and is naming a chief prosecutor for pandemic fraud.',\n",
+       " 'grade': ' INCORRECT'}"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "incorrect[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7710401a",
+   "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
+}

docs/use_cases/evaluation/qa_generation.ipynb

@@ -0,0 +1,117 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ee2a3a21",
+   "metadata": {},
+   "source": [
+    "# QA Generation\n",
+    "This notebook shows how to use the `QAGenerationChain` to come up with question-answer pairs over a specific document.\n",
+    "This is important because often times you may not have data to evaluate your question-answer system over, so this is a cheap and lightweight way to generate it!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "33d3f0b4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import TextLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2029a29c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = TextLoader(\"../../modules/state_of_the_union.txt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "87edb84c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "doc = loader.load()[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "04125b6d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.chains import QAGenerationChain\n",
+    "chain = QAGenerationChain.from_llm(ChatOpenAI(temperature = 0))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "4f1593e4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "qa = chain.run(doc.page_content)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "ee831f92",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'What is the U.S. Department of Justice doing to combat the crimes of Russian oligarchs?',\n",
+       " 'answer': 'The U.S. Department of Justice is assembling a dedicated task force to go after the crimes of Russian oligarchs.'}"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "qa[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7028754e",
+   "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
+}

docs/use_cases/evaluation/question_answering.ipynb

@@ -191,7 +191,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "782ae8c8",
    "metadata": {},
@@ -316,7 +315,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": ".venv",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -330,7 +329,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.7 (default, Sep 16 2021, 08:50:36) \n[Clang 10.0.0 ]"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/use_cases/evaluation/sql_qa_benchmarking_chinook.ipynb

@@ -0,0 +1,423 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "984169ca",
+   "metadata": {},
+   "source": [
+    "# SQL Question Answering Benchmarking: Chinook\n",
+    "\n",
+    "Here we go over how to benchmark performance on a question answering task over a SQL database.\n",
+    "\n",
+    "It is highly reccomended that you do any evaluation/benchmarking with tracing enabled. See [here](https://langchain.readthedocs.io/en/latest/tracing.html) for an explanation of what tracing is and how to set it up."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "44874486",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Comment this out if you are NOT using tracing\n",
+    "import os\n",
+    "os.environ[\"LANGCHAIN_HANDLER\"] = \"langchain\""
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0f66405e",
+   "metadata": {},
+   "source": [
+    "## Loading the data\n",
+    "\n",
+    "First, let's load the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "0df1393f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "b220d07ee5d14909bc842b4545cdc0de",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading readme:   0%|          | 0.00/21.0 [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Downloading and preparing dataset json/LangChainDatasets--sql-qa-chinook to /Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--sql-qa-chinook-7528565d2d992b47/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e89e3c8ef76f49889c4b39c624828c71",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading data files:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a8421df6c26045e8978c7086cb418222",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Downloading data:   0%|          | 0.00/1.44k [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "d1fb6becc3324a85bf039a53caf30924",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Extracting data files:   0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Generating train split: 0 examples [00:00, ? examples/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset json downloaded and prepared to /Users/harrisonchase/.cache/huggingface/datasets/LangChainDatasets___json/LangChainDatasets--sql-qa-chinook-7528565d2d992b47/0.0.0/0f7e3662623656454fcd2b650f34e886a7db4b9104504885bd462096cc7a9f51. Subsequent calls will reuse this data.\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "9d68ad1b3e4a4bd79f92597aac4d3cc9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/1 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "from langchain.evaluation.loading import load_dataset\n",
+    "dataset = load_dataset(\"sql-qa-chinook\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ab44d504",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'How many employees are there?', 'answer': '8'}"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dataset[0]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8a16b75d",
+   "metadata": {},
+   "source": [
+    "## Setting up a chain\n",
+    "This uses the example Chinook database.\n",
+    "To set it up follow the instructions on https://database.guide/2-sample-databases-sqlite/, placing the `.db` file in a notebooks folder at the root of this repository.\n",
+    "\n",
+    "Note that here we load a simple chain. If you want to experiment with more complex chains, or an agent, just create the `chain` object in a different way."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "5b2d5e98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain import OpenAI, SQLDatabase, SQLDatabaseChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "33cdcbfc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "db = SQLDatabase.from_uri(\"sqlite:///../../../notebooks/Chinook.db\")\n",
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f0b5d8f6",
+   "metadata": {},
+   "source": [
+    "Now we can create a SQL database chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "8843cb0c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = SQLDatabaseChain(llm=llm, database=db, input_key=\"question\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6c0062e7",
+   "metadata": {},
+   "source": [
+    "## Make a prediction\n",
+    "\n",
+    "First, we can make predictions one datapoint at a time. Doing it at this level of granularity allows use to explore the outputs in detail, and also is a lot cheaper than running over multiple datapoints"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "d28c5e7d",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'How many employees are there?',\n",
+       " 'answer': '8',\n",
+       " 'result': ' There are 8 employees.'}"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain(dataset[0])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d0c16cd7",
+   "metadata": {},
+   "source": [
+    "## Make many predictions\n",
+    "Now we can make predictions. Note that we add a try-except because this chain can sometimes error (if SQL is written incorrectly, etc)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "24b4c66e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictions = []\n",
+    "predicted_dataset = []\n",
+    "error_dataset = []\n",
+    "for data in dataset:\n",
+    "    try:\n",
+    "        predictions.append(chain(data))\n",
+    "        predicted_dataset.append(data)\n",
+    "    except:\n",
+    "        error_dataset.append(data)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4783344b",
+   "metadata": {},
+   "source": [
+    "## Evaluate performance\n",
+    "Now we can evaluate the predictions. We can use a language model to score them programatically"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "d0a9341d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.evaluation.qa import QAEvalChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "1612dec1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "eval_chain = QAEvalChain.from_llm(llm)\n",
+    "graded_outputs = eval_chain.evaluate(predicted_dataset, predictions, question_key=\"question\", prediction_key=\"result\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "79587806",
+   "metadata": {},
+   "source": [
+    "We can add in the graded output to the `predictions` dict and then get a count of the grades."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "2a689df5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for i, prediction in enumerate(predictions):\n",
+    "    prediction['grade'] = graded_outputs[i]['text']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "27b61215",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Counter({' CORRECT': 3, ' INCORRECT': 4})"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from collections import Counter\n",
+    "Counter([pred['grade'] for pred in predictions])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "12fe30f4",
+   "metadata": {},
+   "source": [
+    "We can also filter the datapoints to the incorrect examples and look at them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "47c692a1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "incorrect = [pred for pred in predictions if pred['grade'] == \" INCORRECT\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "0ef976c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'question': 'How many employees are also customers?',\n",
+       " 'answer': 'None',\n",
+       " 'result': ' 59 employees are also customers.',\n",
+       " 'grade': ' INCORRECT'}"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "incorrect[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7710401a",
+   "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
+}

docs/use_cases/extraction.md

@@ -0,0 +1,20 @@
+# Extraction
+
+Most APIs and databases still deal with structured information.
+Therefore, in order to better work with those, it can be useful to extract structured information from text.
+Examples of this include:
+
+- Extracting a structured row to insert into a database from a sentence
+- Extracting multiple rows to insert into a database from a long document
+- Extracting the correct API parameters from a user query
+
+This work is extremely related to [output parsing](../modules/prompts/examples/output_parsers.ipynb).
+Output parsers are responsible for instructing the LLM to respond in a specific format.
+In this case, the output parsers specify the format of the data you would like to extract from the document.
+Then, in addition to the output format instructions, the prompt should also contain the data you would like to extract information from.
+
+While normal output parsers are good enough for basic structuring of response data,
+when doing extraction you often want to extract more complicated or nested structures.
+For a deep dive on extraction, we recommend checking out [`kor`](https://eyurtsev.github.io/kor/),
+a library that uses the existing LangChain chain and OutputParser abstractions
+but deep dives on allowing extraction of more complicated schemas.

docs/use_cases/tabular.md

@@ -0,0 +1,31 @@
+# Querying Tabular Data
+
+Lots of data and information is stored in tabular data, whether it be csvs, excel sheets, or SQL tables.
+This page covers all resources available in LangChain for working with data in this format.
+
+## Document Loading
+If you have text data stored in a tabular format, you may want to load the data into a Document and then index it as you would
+other text/unstructured data. For this, you should use a document loader like the [CSVLoader](../modules/document_loaders/examples/csv.ipynb)
+and then you should [create an index](../modules/indexes.rst) over that data, and [query it that way](../modules/indexes/chain_examples/vector_db_qa.ipynb).
+
+## Querying
+If you have more numeric tabular data, or have a large amount of data and don't want to index it, you should get started
+by looking at various chains and agents we have for dealing with this data.
+
+### Chains
+
+If you are just getting started, and you have relatively small/simple tabular data, you should get started with chains.
+Chains are a sequence of predetermined steps, so they are good to get started with as they give you more control and let you 
+understand what is happening better.
+
+- [SQL Database Chain](../modules/chains/examples/sqlite.ipynb)
+
+### Agents
+
+Agents are more complex, and involve multiple queries to the LLM to understand what to do.
+The downside of agents are that you have less control. The upside is that they are more powerful,
+which allows you to use them on larger databases and more complex schemas. 
+
+- [SQL Agent](../modules/agents/agent_toolkits/sql_database.ipynb)
+- [Pandas Agent](../modules/agents/agent_toolkits/pandas.ipynb)
+- [CSV Agent](../modules/agents/agent_toolkits/csv.ipynb)