.

Co-authored-by: Aidan Holland <thehappydinoa@gmail.com>
Co-authored-by: Jan de Boer <44832123+Janldeboer@users.noreply.github.com>

.gitignore

@@ -135,3 +135,6 @@ dmypy.json
 
 # macOS display setting files
 .DS_Store
+
+# 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

@@ -30,6 +30,7 @@ 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/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/searx.md

@@ -5,21 +5,44 @@ It is broken into two parts: installation and setup, and then references to the
 
 ## Installation and Setup
 
-- You can find a list of public SearxNG instances [here](https://searx.space/). 
-- It recommended to use a self-hosted instance to avoid abuse on the public instances. Also note that public instances often have a limit on the number of requests.
-- To run a self-hosted instance see [this page](https://searxng.github.io/searxng/admin/installation.html) for more information.
-- To use the tool you need to provide the searx host url by:
-    1. passing the named parameter `searx_host` when creating the instance.
-    2. exporting the environment variable `SEARXNG_HOST`. 
+While it is possible to utilize the wrapper in conjunction with  [public searx
+instances](https://searx.space/) these instances frequently do not permit API
+access (see note on output format below) and have limitations on the frequency
+of requests. It is recommended to opt for a self-hosted instance instead.
+
+### Self Hosted Instance:
+
+See [this page](https://searxng.github.io/searxng/admin/installation.html) for installation instructions.
+
+When you install SearxNG, the only active output format by default is the HTML format.
+You need to activate the `json` format to use the API. This can be done by adding the following line to the `settings.yml` file:
+```yaml
+search:
+    formats:
+        - html
+        - json
+```
+You can make sure that the API is working by issuing a curl request to the API endpoint:
+
+`curl -kLX GET --data-urlencode q='langchain' -d format=json http://localhost:8888`
+
+This should return a JSON object with the results.
+
 
 ## Wrappers
 
 ### Utility
 
+To use the wrapper we need to pass the host of the SearxNG instance to the wrapper with:
+    1. the named parameter `searx_host` when creating the instance.
+    2. exporting the environment variable `SEARXNG_HOST`.
+
 You can use the wrapper to get results from a SearxNG instance. 
 
 ```python
 from langchain.utilities import SearxSearchWrapper
+s = SearxSearchWrapper(searx_host="http://localhost:8888")
+s.run("what is a large language model?")
 ```
 
 ### Tool
@@ -29,7 +52,7 @@ You can do this with:
 
 ```python
 from langchain.agents import load_tools
-tools = load_tools(["searx-search"], searx_host="https://searx.example.com")
+tools = load_tools(["searx-search"], searx_host="http://localhost:8888")
 ```
 
-For more information on this, see [this page](../modules/agents/tools.md)
+For more information on tools, see [this page](../modules/agents/tools.md)

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/gallery.rst

@@ -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/getting_started/getting_started.md

@@ -66,7 +66,7 @@ llm = OpenAI(temperature=0.9)
 We can now call it on some input!
 
 ```python
-text = "What would be a good company name a company that makes colorful socks?"
+text = "What would be a good company name for a company that makes colorful socks?"
 print(llm(text))
 ```
 

docs/index.rst

@@ -63,7 +63,7 @@ These modules are, in increasing order of complexity:
 
 - `Memory <./modules/memory.html>`_: Memory is the concept of persisting state between calls of a chain/agent. LangChain provides a standard interface for memory, a collection of memory implementations, and examples of chains/agents that use memory.
 
-- `Chat <./modules/chat.html>`_: WIP: how to work with chat models.
+- `Chat <./modules/chat.html>`_: Chat models are a variation on Language Models that expose a different API - rather than working with raw text, they work with messages. LangChain provides a standard interface for working with them and doing all the same things as above.
 
 
 .. toctree::
@@ -78,9 +78,9 @@ These modules are, in increasing order of complexity:
    ./modules/utils.md
    ./modules/indexes.md
    ./modules/chains.md
-   ./modules/chat.md
    ./modules/agents.md
    ./modules/memory.md
+   ./modules/chat.md
 
 Use Cases
 ----------

docs/modules/agents/agent_toolkits/sql_database.ipynb

@@ -59,20 +59,6 @@
     ")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "a88b8e4f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models.openai import ChatOpenAI\n",
-    "from langchain.agents.chat.base import ChatAgent\n",
-    "\n",
-    "agent = ChatAgent.from_chat_model_and_tools(ChatOpenAI(temperature=0), toolkit.get_tools())\n",
-    "agent_executor.agent = agent"
-   ]
-  },
   {
    "cell_type": "markdown",
    "id": "36ae48c7-cb08-4fef-977e-c7d4b96a464b",
@@ -83,7 +69,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "ff70e83d-5ad0-4fc7-bb96-27d82ac166d7",
    "metadata": {
     "tags": []
@@ -96,26 +82,12 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to check the schema of the database to see if there is a table called \"play list track\"\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"list_tables_sql_db\",\n",
-      "  \"action_input\": \"\"\n",
-      "}\n",
-      "```\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3mCustomer, Invoice, Track, Artist, Genre, Employee, MediaType, InvoiceLine, Playlist, PlaylistTrack, Album, sales_table\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThere is a table called \"PlaylistTrack\" in the database. I need to use the schema_sql_db tool to get the schema and sample rows for this table.\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"schema_sql_db\",\n",
-      "  \"action_input\": \"PlaylistTrack\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \"\"\u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mArtist, Invoice, Playlist, Genre, Album, PlaylistTrack, Track, InvoiceLine, MediaType, Employee, Customer\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the playlisttrack table\n",
+      "Action: schema_sql_db\n",
+      "Action Input: \"PlaylistTrack\"\u001b[0m\n",
       "Observation: \u001b[33;1m\u001b[1;3m\n",
       "CREATE TABLE \"PlaylistTrack\" (\n",
       "\t\"PlaylistId\" INTEGER NOT NULL, \n",
@@ -126,12 +98,12 @@
       ")\n",
       "\n",
       "SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
-      "PlaylistId\tTrackId\n",
-      "1\t3402\n",
-      "1\t3389\n",
-      "1\t3390\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe PlaylistTrack table has two columns: PlaylistId and TrackId. It has a composite primary key consisting of both columns. There are foreign key constraints on both columns referencing the Playlist and Track tables respectively. The sample rows show the first three entries in the table.\n",
-      "Final Answer: The PlaylistTrack table has two columns: PlaylistId and TrackId. It has a composite primary key consisting of both columns. There are foreign key constraints on both columns referencing the Playlist and Track tables respectively. The sample rows show the first three entries in the table.\u001b[0m\n",
+      "PlaylistId TrackId\n",
+      "1 3402\n",
+      "1 3389\n",
+      "1 3390\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -139,16 +111,16 @@
     {
      "data": {
       "text/plain": [
-       "'The PlaylistTrack table has two columns: PlaylistId and TrackId. It has a composite primary key consisting of both columns. There are foreign key constraints on both columns referencing the Playlist and Track tables respectively. The sample rows show the first three entries in the table.'"
+       "'The PlaylistTrack table has two columns, PlaylistId and TrackId, and is linked to the Playlist and Track tables.'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent_executor.run(\"Describe the play list track table\")"
+    "agent_executor.run(\"Describe the playlisttrack table\")"
    ]
   },
   {
@@ -163,7 +135,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 15,
    "id": "bea76658-a65b-47e2-b294-6d52c5556246",
    "metadata": {
     "tags": []
@@ -176,69 +148,36 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to use the `schema_sql_db` tool to get the schema and sample rows for the table that has song information. But first, I need to know the name of the table.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"list_tables_sql_db\",\n",
-      "  \"action_input\": \"\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3mCustomer, Invoice, Track, Artist, Genre, Employee, MediaType, InvoiceLine, Playlist, PlaylistTrack, Album, sales_table\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe table that has song information is likely to be named \"Track\". I will use the `schema_sql_db` tool to get the schema and sample rows for this table.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"schema_sql_db\",\n",
-      "  \"action_input\": \"Track\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \"\"\u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the PlaylistSong table\n",
+      "Action: schema_sql_db\n",
+      "Action Input: \"PlaylistSong\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3mError: table_names {'PlaylistSong'} not found in database\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should check the spelling of the table\n",
+      "Action: list_tables_sql_db\n",
+      "Action Input: \"\"\u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mGenre, PlaylistTrack, MediaType, Invoice, InvoiceLine, Track, Playlist, Customer, Album, Employee, Artist\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m The table is called PlaylistTrack\n",
+      "Action: schema_sql_db\n",
+      "Action Input: \"PlaylistTrack\"\u001b[0m\n",
       "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "CREATE TABLE \"Track\" (\n",
+      "CREATE TABLE \"PlaylistTrack\" (\n",
+      "\t\"PlaylistId\" INTEGER NOT NULL, \n",
       "\t\"TrackId\" INTEGER NOT NULL, \n",
-      "\t\"Name\" NVARCHAR(200) NOT NULL, \n",
-      "\t\"AlbumId\" INTEGER, \n",
-      "\t\"MediaTypeId\" INTEGER NOT NULL, \n",
-      "\t\"GenreId\" INTEGER, \n",
-      "\t\"Composer\" NVARCHAR(220), \n",
-      "\t\"Milliseconds\" INTEGER NOT NULL, \n",
-      "\t\"Bytes\" INTEGER, \n",
-      "\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
-      "\tPRIMARY KEY (\"TrackId\"), \n",
-      "\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
-      "\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
-      "\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
+      "\tPRIMARY KEY (\"PlaylistId\", \"TrackId\"), \n",
+      "\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
+      "\tFOREIGN KEY(\"PlaylistId\") REFERENCES \"Playlist\" (\"PlaylistId\")\n",
       ")\n",
       "\n",
-      "SELECT * FROM 'Track' LIMIT 3;\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",
-      "3\tFast As a Shark\t3\t2\t1\tF. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman\t230619\t3990994\t0.99\u001b[0m\n",
-      "Thought:"
-     ]
-    },
-    {
-     "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;3mThe table \"Track\" has columns for TrackId, Name, AlbumId, MediaTypeId, GenreId, Composer, Milliseconds, Bytes, and UnitPrice. The sample rows show the first three tracks in the table. \n",
-      "\n",
-      "Final Answer: The table that has song information is named \"Track\" and has columns for TrackId, Name, AlbumId, MediaTypeId, GenreId, Composer, Milliseconds, Bytes, and UnitPrice.\u001b[0m\n",
+      "SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
+      "PlaylistId TrackId\n",
+      "1 3402\n",
+      "1 3389\n",
+      "1 3390\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -246,16 +185,16 @@
     {
      "data": {
       "text/plain": [
-       "'The table that has song information is named \"Track\" and has columns for TrackId, Name, AlbumId, MediaTypeId, GenreId, Composer, Milliseconds, Bytes, and UnitPrice.'"
+       "'The PlaylistTrack table contains two columns, PlaylistId and TrackId, which are both integers and are used to link Playlist and Track tables.'"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "agent_executor.run(\"Describe the table for that has song information\")"
+    "agent_executor.run(\"Describe the playlistsong table\")"
    ]
   },
   {
@@ -268,7 +207,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 8,
    "id": "17bea710-4a23-4de0-b48e-21d57be48293",
    "metadata": {
     "tags": []
@@ -281,57 +220,63 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mQuestion: List the total sales per country. Which country's customers spent the most?\n",
-      "Thought: I need to retrieve the total sales per country and then find the country with the highest total sales.\n",
-      "Action:\n",
-      "```\n",
-      "{\"action\": \"query_sql_db\", \"action_input\": \"SELECT SUM(sales) AS total_sales, country FROM sales_table GROUP BY country ORDER BY total_sales DESC LIMIT 1\"}\n",
-      "```\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(900, 'Japan')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to modify the query to retrieve the country with the highest total sales, not just the first one in the list.\n",
-      "Action:\n",
-      "```\n",
-      "{\"action\": \"query_sql_db\", \"action_input\": \"SELECT SUM(sales) AS total_sales, country FROM sales_table GROUP BY country ORDER BY total_sales DESC LIMIT 1\"}\n",
-      "```\n",
+      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \"\"\u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the relevant tables to see what columns I can use.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: \"Invoice, Customer\"\u001b[0m\n",
+      "Observation: \u001b[33;1m\u001b[1;3m\n",
+      "CREATE TABLE \"Customer\" (\n",
+      "\t\"CustomerId\" INTEGER NOT NULL, \n",
+      "\t\"FirstName\" NVARCHAR(40) NOT NULL, \n",
+      "\t\"LastName\" NVARCHAR(20) NOT NULL, \n",
+      "\t\"Company\" NVARCHAR(80), \n",
+      "\t\"Address\" NVARCHAR(70), \n",
+      "\t\"City\" NVARCHAR(40), \n",
+      "\t\"State\" NVARCHAR(40), \n",
+      "\t\"Country\" NVARCHAR(40), \n",
+      "\t\"PostalCode\" NVARCHAR(10), \n",
+      "\t\"Phone\" NVARCHAR(24), \n",
+      "\t\"Fax\" NVARCHAR(24), \n",
+      "\t\"Email\" NVARCHAR(60) NOT NULL, \n",
+      "\t\"SupportRepId\" INTEGER, \n",
+      "\tPRIMARY KEY (\"CustomerId\"), \n",
+      "\tFOREIGN KEY(\"SupportRepId\") REFERENCES \"Employee\" (\"EmployeeId\")\n",
+      ")\n",
       "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(900, 'Japan')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to modify the query to retrieve the country with the highest total sales, not just the first one in the list.\n",
-      "Action:\n",
-      "```\n",
-      "{\"action\": \"query_sql_db\", \"action_input\": \"SELECT SUM(sales) AS total_sales, country FROM sales_table GROUP BY country ORDER BY total_sales DESC LIMIT 1\"}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(900, 'Japan')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to modify the query to retrieve the country with the highest total sales, not just the first one in the list.\n",
-      "Action:\n",
-      "```\n",
-      "{\"action\": \"query_sql_db\", \"action_input\": \"SELECT SUM(sales) AS total_sales, country FROM sales_table GROUP BY country ORDER BY total_sales DESC LIMIT 1\"}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(900, 'Japan')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to modify the query to retrieve all the countries and their total sales, then find the country with the highest total sales.\n",
-      "Action:\n",
-      "```\n",
-      "{\"action\": \"query_sql_db\", \"action_input\": \"SELECT SUM(sales) AS total_sales, country FROM sales_table GROUP BY country ORDER BY total_sales DESC\"}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(900, 'Japan'), (800, 'Australia'), (700, 'UK'), (600, 'Germany'), (500, 'France'), (400, 'Brazil'), (300, 'Mexico'), (200, 'Canada'), (100, 'USA')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to select the first row of the result to get the country with the highest total sales.\n",
-      "Action:\n",
-      "```\n",
-      "{\"action\": \"query_sql_db\", \"action_input\": \"SELECT SUM(sales) AS total_sales, country FROM sales_table GROUP BY country ORDER BY total_sales DESC LIMIT 1\"}\n",
-      "```\n",
+      "SELECT * FROM 'Customer' LIMIT 3;\n",
+      "CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId\n",
+      "1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3\n",
+      "2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5\n",
+      "3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3\n",
       "\n",
       "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[(900, 'Japan')]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe country with the highest total sales is Japan.\n",
-      "Final Answer: Japan\u001b[0m\n",
+      "CREATE TABLE \"Invoice\" (\n",
+      "\t\"InvoiceId\" INTEGER NOT NULL, \n",
+      "\t\"CustomerId\" INTEGER NOT NULL, \n",
+      "\t\"InvoiceDate\" DATETIME NOT NULL, \n",
+      "\t\"BillingAddress\" NVARCHAR(70), \n",
+      "\t\"BillingCity\" NVARCHAR(40), \n",
+      "\t\"BillingState\" NVARCHAR(40), \n",
+      "\t\"BillingCountry\" NVARCHAR(40), \n",
+      "\t\"BillingPostalCode\" NVARCHAR(10), \n",
+      "\t\"Total\" NUMERIC(10, 2) NOT NULL, \n",
+      "\tPRIMARY KEY (\"InvoiceId\"), \n",
+      "\tFOREIGN KEY(\"CustomerId\") REFERENCES \"Customer\" (\"CustomerId\")\n",
+      ")\n",
+      "\n",
+      "SELECT * FROM 'Invoice' LIMIT 3;\n",
+      "InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total\n",
+      "1 2 2009-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98\n",
+      "2 4 2009-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96\n",
+      "3 8 2009-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should query the Invoice and Customer tables to get the total sales per country.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT c.Country, SUM(i.Total) AS TotalSales FROM Invoice i INNER JOIN Customer c ON i.CustomerId = c.CustomerId GROUP BY c.Country ORDER BY TotalSales DESC LIMIT 10\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m[('USA', 523.0600000000003), ('Canada', 303.9599999999999), ('France', 195.09999999999994), ('Brazil', 190.09999999999997), ('Germany', 156.48), ('United Kingdom', 112.85999999999999), ('Czech Republic', 90.24000000000001), ('Portugal', 77.23999999999998), ('India', 75.25999999999999), ('Chile', 46.62)]\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The customers from the USA spent the most, with a total of $523.06.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -339,10 +284,10 @@
     {
      "data": {
       "text/plain": [
-       "'Japan'"
+       "'The customers from the USA spent the most, with a total of $523.06.'"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -366,17 +311,12 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to retrieve data from multiple tables, so I need to check the schema of the tables and make sure I have the correct column names to join the tables. Then I can use a SQL query to get the total number of tracks in each playlist.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"schema_sql_db\",\n",
-      "  \"action_input\": \"Playlist, PlaylistTrack, Track\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \"\"\u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mInvoice, MediaType, Artist, InvoiceLine, Genre, Playlist, Employee, Album, PlaylistTrack, Track, Customer\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Playlist and PlaylistTrack tables to see what columns I can use.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: \"Playlist, PlaylistTrack\"\u001b[0m\n",
       "Observation: \u001b[33;1m\u001b[1;3m\n",
       "CREATE TABLE \"Playlist\" (\n",
       "\t\"PlaylistId\" INTEGER NOT NULL, \n",
@@ -385,33 +325,10 @@
       ")\n",
       "\n",
       "SELECT * FROM 'Playlist' LIMIT 3;\n",
-      "PlaylistId\tName\n",
-      "1\tMusic\n",
-      "2\tMovies\n",
-      "3\tTV Shows\n",
-      "\n",
-      "\n",
-      "CREATE TABLE \"Track\" (\n",
-      "\t\"TrackId\" INTEGER NOT NULL, \n",
-      "\t\"Name\" NVARCHAR(200) NOT NULL, \n",
-      "\t\"AlbumId\" INTEGER, \n",
-      "\t\"MediaTypeId\" INTEGER NOT NULL, \n",
-      "\t\"GenreId\" INTEGER, \n",
-      "\t\"Composer\" NVARCHAR(220), \n",
-      "\t\"Milliseconds\" INTEGER NOT NULL, \n",
-      "\t\"Bytes\" INTEGER, \n",
-      "\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
-      "\tPRIMARY KEY (\"TrackId\"), \n",
-      "\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
-      "\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
-      "\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
-      ")\n",
-      "\n",
-      "SELECT * FROM 'Track' LIMIT 3;\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",
-      "3\tFast As a Shark\t3\t2\t1\tF. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman\t230619\t3990994\t0.99\n",
+      "PlaylistId Name\n",
+      "1 Music\n",
+      "2 Movies\n",
+      "3 TV Shows\n",
       "\n",
       "\n",
       "CREATE TABLE \"PlaylistTrack\" (\n",
@@ -423,25 +340,22 @@
       ")\n",
       "\n",
       "SELECT * FROM 'PlaylistTrack' LIMIT 3;\n",
-      "PlaylistId\tTrackId\n",
-      "1\t3402\n",
-      "1\t3389\n",
-      "1\t3390\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mNow that I have checked the schema of the tables, I can use a SQL query to get the total number of tracks in each playlist.\n",
+      "PlaylistId TrackId\n",
+      "1 3402\n",
+      "1 3389\n",
+      "1 3390\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I can use a SELECT statement to get the total number of tracks in each playlist.\n",
+      "Action: query_checker_sql_db\n",
+      "Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
+      "Observation: \u001b[31;1m\u001b[1;3m\n",
       "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"query_sql_db\",\n",
-      "  \"action_input\": \"SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS 'Total Tracks' FROM Playlist JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m[('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1), ('On-The-Go 1', 1), ('TV Shows', 426)]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer.\n",
-      "\n",
-      "Final Answer: The total number of tracks in each playlist is displayed in the following format: [('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1), ('On-The-Go 1', 1), ('TV Shows', 426)].\u001b[0m\n",
+      "SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m The query looks correct, I can now execute it.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT Playlist.Name, COUNT(PlaylistTrack.TrackId) AS TotalTracks FROM Playlist INNER JOIN PlaylistTrack ON Playlist.PlaylistId = PlaylistTrack.PlaylistId GROUP BY Playlist.Name LIMIT 10\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3m[('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1)]\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -449,7 +363,7 @@
     {
      "data": {
       "text/plain": [
-       "\"The total number of tracks in each playlist is displayed in the following format: [('90’s Music', 1477), ('Brazilian Music', 39), ('Classical', 75), ('Classical 101 - Deep Cuts', 25), ('Classical 101 - Next Steps', 25), ('Classical 101 - The Basics', 25), ('Grunge', 15), ('Heavy Metal Classic', 26), ('Music', 6580), ('Music Videos', 1), ('On-The-Go 1', 1), ('TV Shows', 426)].\""
+       "\"The total number of tracks in each playlist are: '90’s Music' (1477), 'Brazilian Music' (39), 'Classical' (75), 'Classical 101 - Deep Cuts' (25), 'Classical 101 - Next Steps' (25), 'Classical 101 - The Basics' (25), 'Grunge' (15), 'Heavy Metal Classic' (26), 'Music' (6580), 'Music Videos' (1).\""
       ]
      },
      "execution_count": 7,
@@ -473,7 +387,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 16,
    "id": "9fe4901e-f9e1-4022-b6bc-80e2b2d6a3a4",
    "metadata": {
     "tags": []
@@ -486,100 +400,89 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
-      "\u001b[32;1m\u001b[1;3mThought: I need to query the database to get the best selling artists. I should use the `query_sql_db` tool for this.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"query_sql_db\",\n",
-      "  \"action_input\": \"SELECT artist, SUM(sales) AS total_sales FROM sales GROUP BY artist ORDER BY total_sales DESC LIMIT 3\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such table: sales\n",
-      "[SQL: SELECT artist, SUM(sales) AS total_sales FROM sales GROUP BY artist ORDER BY total_sales DESC LIMIT 3]\n",
-      "(Background on this error at: https://sqlalche.me/e/14/e3q8)\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to check if the table \"sales\" exists in the database before running the query. I should use the `list_tables_sql_db` tool for this.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"list_tables_sql_db\",\n",
-      "  \"action_input\": \"\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3mCustomer, Invoice, Track, Artist, Genre, Employee, MediaType, InvoiceLine, Playlist, PlaylistTrack, Album, sales_table\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe table \"sales_table\" exists in the database. I can now use the `query_sql_db` tool to get the best selling artists.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"query_sql_db\",\n",
-      "  \"action_input\": \"SELECT artist, SUM(sales) AS total_sales FROM sales_table GROUP BY artist ORDER BY total_sales DESC LIMIT 3\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such column: artist\n",
-      "[SQL: SELECT artist, SUM(sales) AS total_sales FROM sales_table GROUP BY artist ORDER BY total_sales DESC LIMIT 3]\n",
-      "(Background on this error at: https://sqlalche.me/e/14/e3q8)\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mI need to check the schema of the `sales_table` to see what columns it has. I should use the `schema_sql_db` tool for this.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"schema_sql_db\",\n",
-      "  \"action_input\": \"sales_table\"\n",
-      "}\n",
-      "```\n",
-      "\n",
-      "\n",
-      "\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mAction: list_tables_sql_db\n",
+      "Action Input: \"\"\u001b[0m\n",
+      "Observation: \u001b[38;5;200m\u001b[1;3mMediaType, Track, Invoice, Album, Playlist, Customer, Employee, InvoiceLine, PlaylistTrack, Genre, Artist\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should look at the schema of the Artist, InvoiceLine, and Track tables to see what columns I can use.\n",
+      "Action: schema_sql_db\n",
+      "Action Input: \"Artist, InvoiceLine, Track\"\u001b[0m\n",
       "Observation: \u001b[33;1m\u001b[1;3m\n",
-      "CREATE TABLE sales_table (\n",
-      "\tcountry TEXT, \n",
-      "\tsales INTEGER\n",
+      "CREATE TABLE \"Artist\" (\n",
+      "\t\"ArtistId\" INTEGER NOT NULL, \n",
+      "\t\"Name\" NVARCHAR(120), \n",
+      "\tPRIMARY KEY (\"ArtistId\")\n",
       ")\n",
       "\n",
-      "SELECT * FROM 'sales_table' LIMIT 3;\n",
-      "country\tsales\n",
-      "USA\t100\n",
-      "Canada\t200\n",
-      "Mexico\t300\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe `sales_table` only has two columns: `country` and `sales`. I need to find the correct table that has the `artist` column. I should use the `list_tables_sql_db` tool for this.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"list_tables_sql_db\",\n",
-      "  \"action_input\": \"\"\n",
-      "}\n",
-      "```\n",
+      "SELECT * FROM 'Artist' LIMIT 3;\n",
+      "ArtistId Name\n",
+      "1 AC/DC\n",
+      "2 Accept\n",
+      "3 Aerosmith\n",
       "\n",
       "\n",
+      "CREATE TABLE \"Track\" (\n",
+      "\t\"TrackId\" INTEGER NOT NULL, \n",
+      "\t\"Name\" NVARCHAR(200) NOT NULL, \n",
+      "\t\"AlbumId\" INTEGER, \n",
+      "\t\"MediaTypeId\" INTEGER NOT NULL, \n",
+      "\t\"GenreId\" INTEGER, \n",
+      "\t\"Composer\" NVARCHAR(220), \n",
+      "\t\"Milliseconds\" INTEGER NOT NULL, \n",
+      "\t\"Bytes\" INTEGER, \n",
+      "\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
+      "\tPRIMARY KEY (\"TrackId\"), \n",
+      "\tFOREIGN KEY(\"MediaTypeId\") REFERENCES \"MediaType\" (\"MediaTypeId\"), \n",
+      "\tFOREIGN KEY(\"GenreId\") REFERENCES \"Genre\" (\"GenreId\"), \n",
+      "\tFOREIGN KEY(\"AlbumId\") REFERENCES \"Album\" (\"AlbumId\")\n",
+      ")\n",
       "\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[38;5;200m\u001b[1;3mCustomer, Invoice, Track, Artist, Genre, Employee, MediaType, InvoiceLine, Playlist, PlaylistTrack, Album, sales_table\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe `Artist` table has the `artist` column. I can now use the `query_sql_db` tool to get the best selling artists.\n",
-      "\n",
-      "Action:\n",
-      "```\n",
-      "{\n",
-      "  \"action\": \"query_sql_db\",\n",
-      "  \"action_input\": \"SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS total_sales FROM InvoiceLine JOIN Track ON InvoiceLine.TrackId = Track.TrackId JOIN Album ON Track.AlbumId = Album.AlbumId JOIN Artist ON Album.ArtistId = Artist.ArtistId GROUP BY Artist.Name ORDER BY total_sales DESC LIMIT 3\"\n",
-      "}\n",
-      "```\n",
+      "SELECT * FROM 'Track' LIMIT 3;\n",
+      "TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice\n",
+      "1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99\n",
+      "2 Balls to the Wall 2 2 1 None 342562 5510424 0.99\n",
+      "3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99\n",
       "\n",
       "\n",
+      "CREATE TABLE \"InvoiceLine\" (\n",
+      "\t\"InvoiceLineId\" INTEGER NOT NULL, \n",
+      "\t\"InvoiceId\" INTEGER NOT NULL, \n",
+      "\t\"TrackId\" INTEGER NOT NULL, \n",
+      "\t\"UnitPrice\" NUMERIC(10, 2) NOT NULL, \n",
+      "\t\"Quantity\" INTEGER NOT NULL, \n",
+      "\tPRIMARY KEY (\"InvoiceLineId\"), \n",
+      "\tFOREIGN KEY(\"TrackId\") REFERENCES \"Track\" (\"TrackId\"), \n",
+      "\tFOREIGN KEY(\"InvoiceId\") REFERENCES \"Invoice\" (\"InvoiceId\")\n",
+      ")\n",
       "\n",
-      "\u001b[0m\n",
+      "SELECT * FROM 'InvoiceLine' LIMIT 3;\n",
+      "InvoiceLineId InvoiceId TrackId UnitPrice Quantity\n",
+      "1 1 2 0.99 1\n",
+      "2 1 4 0.99 1\n",
+      "3 2 6 0.99 1\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should query the database to get the top 3 best selling artists.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mError: (sqlite3.OperationalError) no such column: Track.ArtistId\n",
+      "[SQL: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3]\n",
+      "(Background on this error at: https://sqlalche.me/e/14/e3q8)\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I should double check my query before executing it.\n",
+      "Action: query_checker_sql_db\n",
+      "Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Track ON Artist.ArtistId = Track.ArtistId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
+      "Observation: \u001b[31;1m\u001b[1;3m\n",
+      "\n",
+      "SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity \n",
+      "FROM Artist \n",
+      "INNER JOIN Track ON Artist.ArtistId = Track.ArtistId \n",
+      "INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId \n",
+      "GROUP BY Artist.Name \n",
+      "ORDER BY TotalQuantity DESC \n",
+      "LIMIT 3;\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Action: query_sql_db\n",
+      "Action Input: SELECT Artist.Name, SUM(InvoiceLine.Quantity) AS TotalQuantity FROM Artist INNER JOIN Album ON Artist.ArtistId = Album.ArtistId INNER JOIN Track ON Album.AlbumId = Track.AlbumId INNER JOIN InvoiceLine ON Track.TrackId = InvoiceLine.TrackId GROUP BY Artist.Name ORDER BY TotalQuantity DESC LIMIT 3\u001b[0m\n",
       "Observation: \u001b[36;1m\u001b[1;3m[('Iron Maiden', 140), ('U2', 107), ('Metallica', 91)]\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mThe top 3 best selling artists are Iron Maiden, U2, and Metallica.\n",
-      "Final Answer: Iron Maiden, U2, Metallica.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
+      "Final Answer: The top 3 best selling artists are Iron Maiden, U2, and Metallica.\u001b[0m\n",
       "\n",
       "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
@@ -587,10 +490,10 @@
     {
      "data": {
       "text/plain": [
-       "'Iron Maiden, U2, Metallica.'"
+       "'The top 3 best selling artists are Iron Maiden, U2, and Metallica.'"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -598,14 +501,6 @@
    "source": [
     "agent_executor.run(\"Who are the top 3 best selling artists?\")"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "512180bf",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -624,7 +519,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.9"
   }
  },
  "nbformat": 4,

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/chat_agent.ipynb

@@ -1,195 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ba5f8741",
-   "metadata": {},
-   "source": [
-    "# Chat Agent\n",
-    "\n",
-    "This notebook goes through how to create a ChatGPT based agent\n",
-    "\n",
-    "First, we set up the agent with tools as normal."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9af9734e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
-    "from langchain import OpenAI, SerpAPIWrapper, LLMChain, LLMMathChain, SQLDatabase, SQLDatabaseChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "becda2a1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAI(temperature=0)\n",
-    "search = SerpAPIWrapper()\n",
-    "llm_math_chain = LLMMathChain(llm=llm, verbose=True)\n",
-    "db = SQLDatabase.from_uri(\"sqlite:///../../../../notebooks/Chinook.db\")\n",
-    "db_chain = SQLDatabaseChain(llm=llm, database=db, verbose=True)\n",
-    "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": "markdown",
-   "id": "1717e36a",
-   "metadata": {},
-   "source": [
-    "Now we create a ChatGPT based model and agent."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "b1f12d80",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models.openai import ChatOpenAI\n",
-    "from langchain.agents.chat.base import ChatAgent\n",
-    "\n",
-    "agent = ChatAgent.from_chat_model_and_tools(ChatOpenAI(temperature=0), tools)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "5f57b076",
-   "metadata": {},
-   "source": [
-    "We can now use this as normal"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "490604e9",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "653b1617",
-   "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: Who is Dua Lipa's boyfriend? What is his current age raised to the 0.43 power?\n",
-      "Thought: We need to find out the name of Dua Lipa's boyfriend and his current age.\n",
-      "Action: Search\n",
-      "Action Input: \"Dua Lipa boyfriend\"\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3mDua Lipa was seen heading home from the Saint Laurent Paris Fashion Week show with her new boyfriend Romain Gavras on Tuesday. Advertisement.\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mWe found out the name of Dua Lipa's boyfriend, now we need to find out his age.\n",
-      "Action: Search\n",
-      "Action Input: \"Romain Gavras age\"\n",
-      "\u001b[0m\n",
-      "Observation: \u001b[36;1m\u001b[1;3m41 years\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mWe have the age of Romain Gavras, now we need to calculate his age raised to the 0.43 power.\n",
-      "Action: Calculator\n",
-      "Action Input: 41^(0.43)\n",
-      "\n",
-      "\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
-      "41^(0.43)\n",
-      "\n",
-      "\u001b[32;1m\u001b[1;3m```python\n",
-      "print(41**(0.43))\n",
-      "```\n",
-      "\u001b[0m\n",
-      "Answer: \u001b[33;1m\u001b[1;3m4.9373857399466665\n",
-      "\u001b[0m\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n",
-      "\n",
-      "Observation: \u001b[33;1m\u001b[1;3mAnswer: 4.9373857399466665\n",
-      "\u001b[0m\n",
-      "Thought:\u001b[32;1m\u001b[1;3mWe have the answer to the second question, which is 4.9373857399466665.\n",
-      "Final Answer: Romain Gavras is Dua Lipa's boyfriend and his current age raised to the 0.43 power is 4.9373857399466665.\u001b[0m\n",
-      "\n",
-      "\u001b[1m> Finished chain.\u001b[0m\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "\"Romain Gavras is Dua Lipa's boyfriend and his current age raised to the 0.43 power is 4.9373857399466665.\""
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "agent_executor.run(\"Who is Dua Lipa's boyfriend? What is his current age raised to the 0.43 power?\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "adefb4c2",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.9.1"
-  },
-  "vscode": {
-   "interpreter": {
-    "hash": "18784188d7ecd866c0586ac068b02361a6896dc3a29b64f5cc957f09c590acef"
-   }
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

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/custom_tools.ipynb

@@ -20,7 +20,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "1aaba18c",
    "metadata": {},
    "outputs": [],
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "56ff7670",
    "metadata": {},
    "outputs": [],
@@ -287,7 +287,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "8f15307d",
    "metadata": {},
    "outputs": [],
@@ -302,17 +302,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "0a23b91b",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Tool(name='search_api', description='search_api(query: str) -> str - Searches the API for the query.', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x105c0adc0>, func=<function search_api at 0x13ff17040>, coroutine=None)"
+       "Tool(name='search_api', description='search_api(query: str) -> str - Searches the API for the query.', return_direct=False, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1184e0cd0>, func=<function search_api at 0x1635f8700>, coroutine=None)"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -331,7 +331,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "28cdf04d",
    "metadata": {},
    "outputs": [],
@@ -344,17 +344,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "1085a4bd",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "Tool(name='search', description='search(query: str) -> str - Searches the API for the query.', return_direct=True, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x105c0adc0>, func=<function search_api at 0x13ff17160>, coroutine=None)"
+       "Tool(name='search', description='search(query: str) -> str - Searches the API for the query.', return_direct=True, verbose=False, callback_manager=<langchain.callbacks.shared.SharedCallbackManager object at 0x1184e0cd0>, func=<function search_api at 0x1635f8670>, coroutine=None)"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -375,7 +375,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "79213f40",
    "metadata": {},
    "outputs": [],
@@ -385,7 +385,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "e1067dcb",
    "metadata": {},
    "outputs": [],
@@ -395,7 +395,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "6c66ffe8",
    "metadata": {},
    "outputs": [],

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/search_tools.ipynb

@@ -12,7 +12,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "e6860c2d",
    "metadata": {
     "pycharm": {
@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "dadbcfcd",
    "metadata": {},
    "outputs": [],
@@ -238,6 +238,92 @@
    "source": [
     "agent.run(\"What is the weather in Pomfret?\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eabad3af",
+   "metadata": {},
+   "source": [
+    "## SearxNG Meta Search Engine\n",
+    "\n",
+    "Here we will be using a self hosted SearxNG meta search engine."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "b196c704",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tools = load_tools([\"searx-search\"], searx_host=\"http://localhost:8888\", llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9023eeaa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent = initialize_agent(tools, llm, agent=\"zero-shot-react-description\", verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "3aad92c1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m I should look up the current weather\n",
+      "Action: SearX Search\n",
+      "Action Input: \"weather in Pomfret\"\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mMainly cloudy with snow showers around in the morning. High around 40F. Winds NNW at 5 to 10 mph. Chance of snow 40%. Snow accumulations less than one inch.\n",
+      "\n",
+      "10 Day Weather - Pomfret, MD As of 1:37 pm EST Today 49°/ 41° 52% Mon 27 | Day 49° 52% SE 14 mph Cloudy with occasional rain showers. High 49F. Winds SE at 10 to 20 mph. Chance of rain 50%....\n",
+      "\n",
+      "10 Day Weather - Pomfret, VT As of 3:51 am EST Special Weather Statement Today 39°/ 32° 37% Wed 01 | Day 39° 37% NE 4 mph Cloudy with snow showers developing for the afternoon. High 39F....\n",
+      "\n",
+      "Pomfret, CT ; Current Weather. 1:06 AM. 35°F · RealFeel® 32° ; TODAY'S WEATHER FORECAST. 3/3. 44°Hi. RealFeel® 50° ; TONIGHT'S WEATHER FORECAST. 3/3. 32°Lo.\n",
+      "\n",
+      "Pomfret, MD Forecast Today Hourly Daily Morning 41° 1% Afternoon 43° 0% Evening 35° 3% Overnight 34° 2% Don't Miss Finally, Here’s Why We Get More Colds and Flu When It’s Cold Coast-To-Coast...\n",
+      "\n",
+      "Pomfret, MD Weather Forecast | AccuWeather Current Weather 5:35 PM 35° F RealFeel® 36° RealFeel Shade™ 36° Air Quality Excellent Wind E 3 mph Wind Gusts 5 mph Cloudy More Details WinterCast...\n",
+      "\n",
+      "Pomfret, VT Weather Forecast | AccuWeather Current Weather 11:21 AM 23° F RealFeel® 27° RealFeel Shade™ 25° Air Quality Fair Wind ESE 3 mph Wind Gusts 7 mph Cloudy More Details WinterCast...\n",
+      "\n",
+      "Pomfret Center, CT Weather Forecast | AccuWeather Daily Current Weather 6:50 PM 39° F RealFeel® 36° Air Quality Fair Wind NW 6 mph Wind Gusts 16 mph Mostly clear More Details WinterCast...\n",
+      "\n",
+      "12:00 pm · Feels Like36° · WindN 5 mph · Humidity43% · UV Index3 of 10 · Cloud Cover65% · Rain Amount0 in ...\n",
+      "\n",
+      "Pomfret Center, CT Weather Conditions | Weather Underground star Popular Cities San Francisco, CA 49 °F Clear Manhattan, NY 37 °F Fair Schiller Park, IL (60176) warning39 °F Mostly Cloudy...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m I now know the final answer\n",
+      "Final Answer: The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'The current weather in Pomfret is mainly cloudy with snow showers around in the morning. The temperature is around 40F with winds NNW at 5 to 10 mph. Chance of snow is 40%.'"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent.run(\"What is the weather in Pomfret\")"
+   ]
   }
  ],
  "metadata": {
@@ -256,7 +342,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.9.11"
   },
   "vscode": {
    "interpreter": {

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",
@@ -81,7 +83,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.0 64-bit ('llm-env')",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -95,7 +97,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.0"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

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 +136,12 @@ 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`
+

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"
      ]
     }
    ],
@@ -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/generic/sequential_chains.ipynb

@@ -36,6 +36,25 @@
   {
    "cell_type": "code",
    "execution_count": 1,
+   "id": "7a886879",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "cannot find .env file\n"
+     ]
+    }
+   ],
+   "source": [
+    "%load_ext dotenv\n",
+    "%dotenv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
    "id": "3f2f9b8c",
    "metadata": {},
    "outputs": [],
@@ -47,7 +66,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 3,
    "id": "b8237d1a",
    "metadata": {},
    "outputs": [],
@@ -64,7 +83,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 4,
    "id": "4a391730",
    "metadata": {},
    "outputs": [],
@@ -82,7 +101,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 5,
    "id": "9368bd63",
    "metadata": {},
    "outputs": [],
@@ -94,7 +113,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 6,
    "id": "d39e15f5",
    "metadata": {},
    "outputs": [
@@ -107,22 +126,20 @@
       "\u001b[1m> Entering new SimpleSequentialChain chain...\u001b[0m\n",
       "\u001b[36;1m\u001b[1;3m\n",
       "\n",
-      "Tragedy at Sunset on the Beach follows the story of a young couple, Jack and Annie, who have just started to explore the possibility of a relationship together. After a day spent in the sun and sand, they decide to take a romantic stroll down the beach as the sun sets. \n",
+      "Tragedy at Sunset on the Beach is a story of a young couple, Jack and Sarah, who are in love and looking forward to their future together. On the night of their anniversary, they decide to take a walk on the beach at sunset. As they are walking, they come across a mysterious figure, who tells them that their love will be tested in the near future. \n",
       "\n",
-      "However, their romantic evening quickly turns tragic when they stumble upon a body lying in the sand. As they approach to investigate, they are shocked to discover that it is Jack's long-lost brother, who has been missing for several years. \n",
+      "The figure then tells the couple that the sun will soon set, and with it, a tragedy will strike. If Jack and Sarah can stay together and pass the test, they will be granted everlasting love. However, if they fail, their love will be lost forever.\n",
       "\n",
-      "The story follows Jack and Annie as they navigate their way through the tragedy and their newfound relationship. With the help of their friends, family, and the beach's inhabitants, Jack and Annie must come to terms with their deep-seated emotions and the reality of the situation. \n",
-      "\n",
-      "Ultimately, the play explores themes of family, love, and loss, as Jack and Annie's story unfolds against the beautiful backdrop of the beach at sunset.\u001b[0m\n",
+      "The play follows the couple as they struggle to stay together and battle the forces that threaten to tear them apart. Despite the tragedy that awaits them, they remain devoted to one another and fight to keep their love alive. In the end, the couple must decide whether to take a chance on their future together or succumb to the tragedy of the sunset.\u001b[0m\n",
       "\u001b[33;1m\u001b[1;3m\n",
       "\n",
-      "Tragedy at Sunset on the Beach is an emotionally complex tale of family, love, and loss. Told against the beautiful backdrop of a beach at sunset, the story follows Jack and Annie, a young couple just beginning to explore a relationship together. When they stumble upon the body of Jack's long-lost brother on the beach, they must face the reality of the tragedy and come to terms with their deep-seated emotions. \n",
+      "Tragedy at Sunset on the Beach is an emotionally gripping story of love, hope, and sacrifice. Through the story of Jack and Sarah, the audience is taken on a journey of self-discovery and the power of love to overcome even the greatest of obstacles. \n",
       "\n",
-      "The playwright has crafted a heartfelt and thought-provoking story, one that probes into the depths of the human experience. The cast of characters is well-rounded and fully realized, and the dialogue is natural and emotional. The direction and choreography are top-notch, and the scenic design is breathtaking. \n",
+      "The play's talented cast brings the characters to life, allowing us to feel the depths of their emotion and the intensity of their struggle. With its compelling story and captivating performances, this play is sure to draw in audiences and leave them on the edge of their seats. \n",
       "\n",
-      "Overall, Tragedy at Sunset on the Beach is a powerful and moving story about the fragility of life and the strength of love. It is sure to tug at your heartstrings and leave you with a newfound appreciation of life's precious moments. Highly recommended.\u001b[0m\n",
+      "The play's setting of the beach at sunset adds a touch of poignancy and romanticism to the story, while the mysterious figure serves to keep the audience enthralled. Overall, Tragedy at Sunset on the Beach is an engaging and thought-provoking play that is sure to leave audiences feeling inspired and hopeful.\u001b[0m\n",
       "\n",
-      "\u001b[1m> Finished SimpleSequentialChain chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     }
    ],
@@ -132,7 +149,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 7,
    "id": "c6649a01",
    "metadata": {},
    "outputs": [
@@ -142,11 +159,11 @@
      "text": [
       "\n",
       "\n",
-      "Tragedy at Sunset on the Beach is an emotionally complex tale of family, love, and loss. Told against the beautiful backdrop of a beach at sunset, the story follows Jack and Annie, a young couple just beginning to explore a relationship together. When they stumble upon the body of Jack's long-lost brother on the beach, they must face the reality of the tragedy and come to terms with their deep-seated emotions. \n",
+      "Tragedy at Sunset on the Beach is an emotionally gripping story of love, hope, and sacrifice. Through the story of Jack and Sarah, the audience is taken on a journey of self-discovery and the power of love to overcome even the greatest of obstacles. \n",
       "\n",
-      "The playwright has crafted a heartfelt and thought-provoking story, one that probes into the depths of the human experience. The cast of characters is well-rounded and fully realized, and the dialogue is natural and emotional. The direction and choreography are top-notch, and the scenic design is breathtaking. \n",
+      "The play's talented cast brings the characters to life, allowing us to feel the depths of their emotion and the intensity of their struggle. With its compelling story and captivating performances, this play is sure to draw in audiences and leave them on the edge of their seats. \n",
       "\n",
-      "Overall, Tragedy at Sunset on the Beach is a powerful and moving story about the fragility of life and the strength of love. It is sure to tug at your heartstrings and leave you with a newfound appreciation of life's precious moments. Highly recommended.\n"
+      "The play's setting of the beach at sunset adds a touch of poignancy and romanticism to the story, while the mysterious figure serves to keep the audience enthralled. Overall, Tragedy at Sunset on the Beach is an engaging and thought-provoking play that is sure to leave audiences feeling inspired and hopeful.\n"
      ]
     }
    ],
@@ -167,7 +184,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 8,
    "id": "02016a51",
    "metadata": {},
    "outputs": [],
@@ -185,7 +202,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 9,
    "id": "8bd38cc2",
    "metadata": {},
    "outputs": [],
@@ -203,7 +220,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 10,
    "id": "524523af",
    "metadata": {},
    "outputs": [],
@@ -220,7 +237,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 11,
    "id": "3fd3a7be",
    "metadata": {},
    "outputs": [
@@ -231,14 +248,8 @@
       "\n",
       "\n",
       "\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
-      "\u001b[1mChain 0\u001b[0m:\n",
-      "{'synopsis': \" \\n\\nTragedy at Sunset on the Beach is a dark and gripping drama set in Victorian England. The play follows the story of two lovers, Emma and Edward, whose passionate relationship is threatened by the strict rules and regulations of the time.\\n\\nThe two are deeply in love, but Edward is from a wealthy family and Emma is from a lower class background. Despite the obstacles, the two are determined to be together and decide to elope.\\n\\nOn the night of their planned escape, Emma and Edward meet at the beach at sunset to declare their love for one another and begin a new life together. However, their plans are disrupted when Emma's father discovers their plan and appears on the beach with a gun.\\n\\nIn a heartbreaking scene, Emma's father orders Edward to leave, but Edward refuses and fights for their love. In a fit of rage, Emma's father shoots Edward, killing him instantly. \\n\\nThe tragedy of the play lies in the fact that Emma and Edward are denied their chance at a happy ending due to the rigid social conventions of Victorian England. The audience is left with a heavy heart as the play ends with Emma standing alone on the beach, mourning the loss of her beloved.\"}\n",
       "\n",
-      "\u001b[1mChain 1\u001b[0m:\n",
-      "{'review': \"\\n\\nTragedy at Sunset on the Beach is an emotionally charged production that will leave audiences heartsick. The play follows the ill-fated love story of Emma and Edward, two star-crossed lovers whose passionate relationship is tragically thwarted by Victorian England's societal conventions. The performance is captivating from start to finish, as the audience is taken on an emotional rollercoaster of love, loss, and heartbreak.\\n\\nThe acting is powerful and sincere, and the performances of the two leads are particularly stirring. Emma and Edward are both portrayed with such tenderness and emotion that it's hard not to feel their pain as they fight for their forbidden love. The climactic scene, in which Edward is shot by Emma's father, is especially heartbreaking and will leave audience members on the edge of their seats.\\n\\nOverall, Tragedy at Sunset on the Beach is a powerful and moving work of theatre. It is a tragedy of impossible love, and a vivid reminder of the devastating consequences of social injustice. The play is sure to leave a lasting impression on anyone who experiences it.\"}\n",
-      "\n",
-      "\n",
-      "\u001b[1m> Finished SequentialChain chain.\u001b[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     }
    ],
@@ -246,10 +257,91 @@
     "review = overall_chain({\"title\":\"Tragedy at sunset on the beach\", \"era\": \"Victorian England\"})"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "d2fac817",
+   "metadata": {},
+   "source": [
+    "### Memory in Sequential Chains\n",
+    "Sometimes you may want to pass along some context to use in each step of the chain or in a later part of the chain, but maintaining and chaining together the input/output variables can quickly get messy.  Using `SimpleMemory` is a convenient way to do manage this and clean up your chains.\n",
+    "\n",
+    "For example, using the previous playwright SequentialChain, lets say you wanted to include some context about date, time and location of the play, and using the generated synopsis and review, create some social media post text.  You could add these new context variables as `input_variables`, or we can add a `SimpleMemory` to the chain to manage this context:"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b2cf3098",
+   "metadata": {},
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "6b7b3a7a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new SequentialChain chain...\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'title': 'Tragedy at sunset on the beach',\n",
+       " 'era': 'Victorian England',\n",
+       " 'time': 'December 25th, 8pm PST',\n",
+       " 'location': 'Theater in the Park',\n",
+       " 'social_post_text': \"\\nSpend your Christmas night with us at Theater in the Park and experience the heartbreaking story of love and loss that is 'A Walk on the Beach'. Set in Victorian England, this romantic tragedy follows the story of Frances and Edward, a young couple whose love is tragically cut short. Don't miss this emotional and thought-provoking production that is sure to leave you in tears. #AWalkOnTheBeach #LoveAndLoss #TheaterInThePark #VictorianEngland\"}"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.chains import SequentialChain\n",
+    "from langchain.memory import SimpleMemory\n",
+    "\n",
+    "llm = OpenAI(temperature=.7)\n",
+    "template = \"\"\"You are a social media manager for a theater company.  Given the title of play, the era it is set in, the date,time and location, the synopsis of the play, and the review of the play, it is your job to write a social media post for that play.\n",
+    "\n",
+    "Here is some context about the time and location of the play:\n",
+    "Date and Time: {time}\n",
+    "Location: {location}\n",
+    "\n",
+    "Play Synopsis:\n",
+    "{synopsis}\n",
+    "Review from a New York Times play critic of the above play:\n",
+    "{review}\n",
+    "\n",
+    "Social Media Post:\n",
+    "\"\"\"\n",
+    "prompt_template = PromptTemplate(input_variables=[\"synopsis\", \"review\", \"time\", \"location\"], template=template)\n",
+    "social_chain = LLMChain(llm=llm, prompt=prompt_template, output_key=\"social_post_text\")\n",
+    "\n",
+    "overall_chain = SequentialChain(\n",
+    "    memory=SimpleMemory(memories={\"time\": \"December 25th, 8pm PST\", \"location\": \"Theater in the Park\"}),\n",
+    "    chains=[synopsis_chain, review_chain, social_chain],\n",
+    "    input_variables=[\"era\", \"title\"],\n",
+    "    # Here we return multiple variables\n",
+    "    output_variables=[\"social_post_text\"],\n",
+    "    verbose=True)\n",
+    "\n",
+    "overall_chain({\"title\":\"Tragedy at sunset on the beach\", \"era\": \"Victorian England\"})"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "6be70d27",
+   "id": "ee9bc09c",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -271,7 +363,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/chains/getting_started.ipynb

@@ -32,7 +32,9 @@
   {
    "cell_type": "code",
    "execution_count": 1,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.prompts import PromptTemplate\n",
@@ -55,7 +57,9 @@
   {
    "cell_type": "code",
    "execution_count": 2,
-   "metadata": {},
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -63,7 +67,7 @@
      "text": [
       "\n",
       "\n",
-      "Vibrancy Socks.\n"
+      "Rainbow Socks Co.\n"
      ]
     }
    ],
@@ -75,6 +79,48 @@
     "print(chain.run(\"colorful socks\"))"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "You can use a chat model in an `LLMChain` as well:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Rainbow Threads\n"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "human_message_prompt = HumanMessagePromptTemplate(\n",
+    "        prompt=PromptTemplate(\n",
+    "            template=\"What is a good name for a company that makes {product}?\",\n",
+    "            input_variables=[\"product\"],\n",
+    "        )\n",
+    "    )\n",
+    "chat_prompt_template = ChatPromptTemplate.from_messages([human_message_prompt])\n",
+    "chat = ChatOpenAI(temperature=0.9)\n",
+    "chain = LLMChain(llm=chat, prompt=chat_prompt_template)\n",
+    "print(chain.run(\"colorful socks\"))"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -274,5 +320,5 @@
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 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.rst

@@ -1,15 +1,26 @@
 Chat
 ==========================
 
-WARNING: extreme WIP
+Chat models are a variation on language models.
+While chat models use language models under the hood, the interface they expose is a bit different.
+Rather than expose a "text in, text out" API, they expose an interface where "chat messages" are the inputs and outputs.
 
-Chat models are new models that rather than being text-in and text-out send a list of dicitionaries, each dictionary representing a chat utterance including the text of the chat and the "speaker" of the chat.
+Chat model APIs are fairly new, so we are still figuring out the correct abstractions.
+
+The following sections of documentation are provided:
+
+- `Getting Started <./chat/getting_started.html>`_: An overview of the basics of chat models.
+
+- `Key Concepts <./chat/key_concepts.html>`_: A conceptual guide going over the various concepts related to chat models.
+
+- `How-To Guides <./chat/how_to_guides.html>`_: A collection of how-to guides. These highlight how to accomplish various objectives with our chat model class, as well as how to integrate with various chat model providers.
 
 
 .. toctree::
    :maxdepth: 1
-   :caption: Chat
-   :name: Chat
+   :name: LLMs
    :hidden:
-
+   
+   ./chat/getting_started.ipynb
+   ./chat/key_concepts.md
    ./chat/how_to_guides.rst

docs/modules/chat/examples/agent.ipynb

@@ -0,0 +1,208 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e58f4d5a",
+   "metadata": {},
+   "source": [
+    "# Agent\n",
+    "This notebook covers how to create a custom agent for a chat model. It will utilize chat specific prompts."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5268c7fa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
+    "from langchain.chains import LLMChain\n",
+    "from langchain.utilities import SerpAPIWrapper"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "fbaa4dbe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "search = SerpAPIWrapper()\n",
+    "tools = [\n",
+    "    Tool(\n",
+    "        name = \"Search\",\n",
+    "        func=search.run,\n",
+    "        description=\"useful for when you need to answer questions about current events\"\n",
+    "    )\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f3ba6f08",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prefix = \"\"\"Answer the following questions as best you can, but speaking as a pirate might speak. You have access to the following tools:\"\"\"\n",
+    "suffix = \"\"\"Begin! Remember to speak as a pirate when giving your final answer. Use lots of \"Args\"\"\"\n",
+    "\n",
+    "prompt = ZeroShotAgent.create_prompt(\n",
+    "    tools, \n",
+    "    prefix=prefix, \n",
+    "    suffix=suffix, \n",
+    "    input_variables=[]\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3547a37d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a78f886f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "messages = [\n",
+    "    SystemMessagePromptTemplate(prompt=prompt),\n",
+    "    HumanMessagePromptTemplate.from_template(\"{input}\\n\\nThis was your previous work \"\n",
+    "                f\"(but I haven't seen any of it! I only see what \"\n",
+    "                \"you return as final answer):\\n{agent_scratchpad}\")\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "dadadd70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b7180182",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm_chain = LLMChain(llm=ChatOpenAI(temperature=0), prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "ddddb07b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "tool_names = [tool.name for tool in tools]\n",
+    "agent = ZeroShotAgent(llm_chain=llm_chain, allowed_tools=tool_names)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "36aef054",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "agent_executor = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools, verbose=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "33a4d6cc",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3mArrr, ye be in luck, matey! I'll find ye the answer to yer question.\n",
+      "\n",
+      "Thought: I need to search for the current population of Canada.\n",
+      "Action: Search\n",
+      "Action Input: \"current population of Canada 2023\"\n",
+      "\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mThe current population of Canada is 38,623,091 as of Saturday, March 4, 2023, based on Worldometer elaboration of the latest United Nations data.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3mAhoy, me hearties! I've found the answer to yer question.\n",
+      "\n",
+      "Final Answer: As of March 4, 2023, the population of Canada be 38,623,091. Arrr!\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'As of March 4, 2023, the population of Canada be 38,623,091. Arrr!'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "agent_executor.run(\"How many people live in canada as of 2023?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6aefe978",
+   "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/chat/examples/chat_vector_db.ipynb

@@ -2,43 +2,91 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "b7657104",
+   "id": "134a0785",
    "metadata": {},
    "source": [
-    "# Chat Vector DB"
+    "# Chat Vector DB\n",
+    "\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)."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "4990086a",
-   "metadata": {},
+   "id": "70c4e529",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.vectorstores import Chroma\n",
-    "from langchain.docstore.document import Document\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.indexes.vectorstore import VectorstoreIndexCreator\n",
-    "from langchain.llms import OpenAI"
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.chains import ChatVectorDBChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "cdff94be",
+   "metadata": {},
+   "source": [
+    "Load in documents. You can replace this with a loader for whatever type of data you want"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "3a982715",
-   "metadata": {},
+   "id": "01c46e92",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
-    "index_creator = VectorstoreIndexCreator()"
+    "from langchain.document_loaders import TextLoader\n",
+    "loader = TextLoader('../../state_of_the_union.txt')\n",
+    "documents = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e9be4779",
+   "metadata": {},
+   "source": [
+    "If you had multiple loaders that you wanted to combine, you do something like:"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "1b2a6568",
+   "id": "433363a5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# loaders = [....]\n",
+    "# docs = []\n",
+    "# for loader in loaders:\n",
+    "#     docs.extend(loader.load())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "239475d2",
    "metadata": {},
+   "source": [
+    "We now split the documents, create embeddings for them, and put them in a vectorstore. This allows us to do semantic search over them."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a8930cf7",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "name": "stdout",
@@ -50,171 +98,159 @@
     }
    ],
    "source": [
-    "from langchain.document_loaders import TextLoader\n",
-    "loader = TextLoader('../../state_of_the_union.txt')\n",
-    "docsearch = index_creator.from_loaders([loader]).vectorstore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "7d410fd6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat.chat_vector_db import ChatVectorDBChain\n",
-    "from langchain.chat_models import ChatOpenAI"
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "documents = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "vectorstore = Chroma.from_documents(documents, embeddings)"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "e606d9e7",
+   "id": "18415aca",
    "metadata": {},
    "source": [
-    "## Memory outside the chain"
+    "We are now going to construct a prompt specifically designed for chat models."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 5,
-   "id": "71378b64",
+   "id": "c8805230",
    "metadata": {},
    "outputs": [],
    "source": [
-    "chain = ChatVectorDBChain.from_llm(model = ChatOpenAI(temperature=0), llm=OpenAI(temperature=0), vectorstore=docsearch)\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "aa1c1942",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.memory.chat_memory import ChatMemory"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "6cbafc97",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "memory = ChatMemory()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "7bac7b99",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'The President said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson for the United States Supreme Court, and that she is one of our nation’s top legal minds who will continue Justice Breyer’s legacy of excellence. He also mentioned that she is a former top litigator in private practice, a former federal public defender, and comes from a family of public school educators and police officers.'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "answer = chain.run(question=query, chat_history=memory.messages)\n",
-    "answer"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "d9f3a746",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "memory.add_user_message(query)\n",
-    "memory.add_ai_message(answer)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "3c92b39a",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Ketanji Brown Jackson has not yet been confirmed as a United States Supreme Court Justice. She has been nominated by President Biden to succeed Justice Stephen Breyer, who is retiring.'"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"Did the president say who she suceeded\"\n",
-    "chain.run(question=query, chat_history=memory.messages)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "41bc7676",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'The President said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson for the United States Supreme Court, and that she is one of our nation’s top legal minds who will continue Justice Breyer’s legacy of excellence. He also mentioned that she is a former top litigator in private practice, a former federal public defender, and comes from a family of public school educators and police officers.'"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "answer"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "439cc4be",
-   "metadata": {},
-   "source": [
-    "## Memory in the chain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "8a0a66ce",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat.memory import ChatHistoryMemory\n",
-    "chain = ChatVectorDBChain.from_llm(\n",
-    "    model = ChatOpenAI(temperature=0), \n",
-    "    llm=OpenAI(temperature=0), \n",
-    "    vectorstore=docsearch,\n",
-    "    memory=ChatHistoryMemory(input_key=\"question\")\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
-   "id": "d1d3a995",
+   "execution_count": 6,
+   "id": "cc86c30e",
    "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
+    "If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
+    "----------------\n",
+    "{context}\"\"\"\n",
+    "messages = [\n",
+    "    SystemMessagePromptTemplate.from_template(system_template),\n",
+    "    HumanMessagePromptTemplate.from_template(\"{question}\")\n",
+    "]\n",
+    "prompt = ChatPromptTemplate.from_messages(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3c96b118",
+   "metadata": {},
+   "source": [
+    "We now initialize the ChatVectorDBChain"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "7b4110f3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "qa = ChatVectorDBChain.from_llm(ChatOpenAI(temperature=0), vectorstore,qa_prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3872432d",
+   "metadata": {},
+   "source": [
+    "Here's an example of asking a question with no chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7fe3e730",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "bfff9cc8",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'The President said that he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson for the United States Supreme Court, and that she is one of our nation’s top legal minds who will continue Justice Breyer’s legacy of excellence. He also mentioned that she is a former top litigator in private practice, a former federal public defender, and comes from a family of public school educators and police officers.'"
+       "\"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.\""
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "result[\"answer\"]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9e46edf7",
+   "metadata": {},
+   "source": [
+    "Here's an example of asking a question with some chat history"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "00b4cf00",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat_history = [(query, result[\"answer\"])]\n",
+    "query = \"Did he mention who came before her\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "f01828d1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'The context does not provide information about the predecessor of Ketanji Brown Jackson.'"
       ]
      },
      "execution_count": 13,
@@ -223,26 +259,94 @@
     }
    ],
    "source": [
-    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
-    "answer = chain.run(question=query)\n",
-    "answer"
+    "result['answer']"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2324cdc6-98bf-4708-b8cd-02a98b1e5b67",
+   "metadata": {},
+   "source": [
+    "## Chat Vector DB 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": null,
-   "id": "0b65288b",
-   "metadata": {},
+   "execution_count": 15,
+   "id": "2efacec3-2690-4b05-8de3-a32fd2ac3911",
+   "metadata": {
+    "tags": []
+   },
    "outputs": [],
    "source": [
-    "query = \"Did the president say who she suceeded\"\n",
-    "chain.run(question=query)"
+    "from langchain.chains.llm import LLMChain\n",
+    "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.question_answering import load_qa_chain\n",
+    "\n",
+    "# Construct a ChatVectorDBChain with a streaming llm for combine docs\n",
+    "# and a separate, non-streaming llm for question generation\n",
+    "llm = OpenAI(temperature=0)\n",
+    "streaming_llm = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
+    "\n",
+    "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)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "fd6d43f4-7428-44a4-81bc-26fe88a98762",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "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."
+     ]
+    }
+   ],
+   "source": [
+    "chat_history = []\n",
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "5ab38978-f3e8-4fa7-808c-c79dec48379a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The context does not provide information on who Ketanji Brown Jackson succeeded on the United States Supreme Court."
+     ]
+    }
+   ],
+   "source": [
+    "chat_history = [(query, result[\"answer\"])]\n",
+    "query = \"Did he mention who she suceeded\"\n",
+    "result = qa({\"question\": query, \"chat_history\": chat_history})\n"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1d2cb862",
+   "id": "8e8d0055",
    "metadata": {},
    "outputs": [],
    "source": []

docs/modules/chat/examples/few_shot_examples.ipynb

@@ -0,0 +1,166 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "bb0735c0",
+   "metadata": {},
+   "source": [
+    "# Few Shot Examples\n",
+    "\n",
+    "This notebook covers how to use few shot examples in chat models.\n",
+    "\n",
+    "There does not appear to be solid consensus on how best to do few shot prompting. As a result, we are not solidifying any abstractions around this yet but rather using existing abstractions."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "c6e9664c",
+   "metadata": {},
+   "source": [
+    "## Alternating Human/AI messages\n",
+    "The first way of doing few shot prompting relies on using alternating human/ai messages. See an example of this below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "62156fe4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain import PromptTemplate, LLMChain\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "ed7ac3c6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "98791aa9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template=\"You are a helpful assistant that translates english to pirate.\"\n",
+    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
+    "example_human = HumanMessagePromptTemplate.from_template(\"Hi\")\n",
+    "example_ai = AIMessagePromptTemplate.from_template(\"Argh me mateys\")\n",
+    "human_template=\"{text}\"\n",
+    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "4eebdcd7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"I be lovin' programmin', me hearty!\""
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, example_human, example_ai, human_message_prompt])\n",
+    "chain = LLMChain(llm=chat, prompt=chat_prompt)\n",
+    "# get a chat completion from the formatted messages\n",
+    "chain.run(\"I love programming.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5c4135d7",
+   "metadata": {},
+   "source": [
+    "## System Messages\n",
+    "\n",
+    "OpenAI provides an optional `name` parameter that they also recommend using in conjunction with system messages to do few shot prompting. Here is an example of how to do that below."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1ba92d59",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template=\"You are a helpful assistant that translates english to pirate.\"\n",
+    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
+    "example_human = SystemMessagePromptTemplate.from_template(\"Hi\", additional_kwargs={\"name\": \"example_user\"})\n",
+    "example_ai = SystemMessagePromptTemplate.from_template(\"Argh me mateys\", additional_kwargs={\"name\": \"example_assistant\"})\n",
+    "human_template=\"{text}\"\n",
+    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "56e488a7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"I be lovin' programmin', me hearty.\""
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, example_human, example_ai, human_message_prompt])\n",
+    "chain = LLMChain(llm=chat, prompt=chat_prompt)\n",
+    "# get a chat completion from the formatted messages\n",
+    "chain.run(\"I love programming.\")"
+   ]
+  }
+ ],
+ "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/chat/examples/memory.ipynb

@@ -0,0 +1,192 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9a9350a6",
+   "metadata": {},
+   "source": [
+    "# Memory\n",
+    "This notebook goes over how to use Memory with chat models. The main difference between this and Memory for LLMs is that rather than trying to condense all previous messages into a string, we can keep them as their own unique memory object."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "110935ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.prompts import (\n",
+    "    ChatPromptTemplate, \n",
+    "    MessagesPlaceholder, \n",
+    "    SystemMessagePromptTemplate, \n",
+    "    HumanMessagePromptTemplate\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "161b6629",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt = ChatPromptTemplate.from_messages([\n",
+    "    SystemMessagePromptTemplate.from_template(\"The 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",
+    "    MessagesPlaceholder(variable_name=\"history\"),\n",
+    "    HumanMessagePromptTemplate.from_template(\"{input}\")\n",
+    "])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "4976fbda",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.memory import ConversationBufferMemory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "12a0bea6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f6edcd6a",
+   "metadata": {},
+   "source": [
+    "We can now initialize the memory. Note that we set `return_messages=True` To denote that this should return a list of messages when appropriate"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "f55bea38",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory(return_messages=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "737e8c78",
+   "metadata": {},
+   "source": [
+    "We can now use this in the rest of the chain."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "80152db7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "conversation = ConversationChain(memory=memory, prompt=prompt, llm=llm)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "ac68e766",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Hello! How can I assist you today?'"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.predict(input=\"Hi there!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "babb33d0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"That sounds like fun! I'm happy to chat with you. Is there anything specific you'd like to talk about?\""
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "36f8a1dc",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"Sure! I am an AI language model created by OpenAI. I was trained on a large dataset of text from the internet, which allows me to understand and generate human-like language. I can answer questions, provide information, and even have conversations like this one. Is there anything else you'd like to know about me?\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.predict(input=\"Tell me about yourself.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "79fb460b",
+   "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/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/qa.ipynb

@@ -1,141 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "ca494454",
-   "metadata": {},
-   "source": [
-    "# Question Answering"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "bed0dfef",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
-    "from langchain.vectorstores import Chroma\n",
-    "from langchain.docstore.document import Document\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.indexes.vectorstore import VectorstoreIndexCreator"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "15a6d191",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "index_creator = VectorstoreIndexCreator()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "483815ae",
-   "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.document_loaders import TextLoader\n",
-    "loader = TextLoader('../../state_of_the_union.txt')\n",
-    "docsearch = index_creator.from_loaders([loader]).vectorstore"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "35fd98c0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "docs = docsearch.similarity_search(query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "86116c78",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat.question_answering import QAChain\n",
-    "from langchain.chat_models import ChatOpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "6b5d1a80",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = QAChain.from_model(model = ChatOpenAI(temperature=0))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "5ff56c1d",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'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. The President also mentioned that one of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court, and he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to continue Justice Breyer’s legacy of excellence.'"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain.run(input_documents=docs, question=query)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "cf32e6d6",
-   "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/chat/examples/qa_eval.ipynb

@@ -1,154 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "aa309a80",
-   "metadata": {},
-   "source": [
-    "# QA Eval"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "9c01a3a5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.evaluation.qa.chat_eval_chain import QAEvalChatChain\n",
-    "from langchain.chat_models import ChatOpenAI\n",
-    "\n",
-    "model = ChatOpenAI(temperature=0)\n",
-    "\n",
-    "eval_chain = QAEvalChatChain.from_model(model)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "c12568a6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "examples = [\n",
-    "    {\n",
-    "        \"question\": \"Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?\",\n",
-    "        \"answer\": \"11\"\n",
-    "    },\n",
-    "    {\n",
-    "        \"question\": 'Is the following sentence plausible? \"Joao Moutinho caught the screen pass in the NFC championship.\"',\n",
-    "        \"answer\": \"No\"\n",
-    "    }\n",
-    "]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "207bb5b6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains import LLMChain\n",
-    "from langchain.llms import OpenAI"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "3d4b9cda",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prompt = PromptTemplate(template=\"Question: {question}\\nAnswer:\", input_variables=[\"question\"])\n",
-    "llm = OpenAI(model_name=\"text-davinci-003\", temperature=0)\n",
-    "chain = LLMChain(llm=llm, prompt=prompt)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "c03c4047",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "predictions = chain.apply(examples)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "3871729e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "graded_outputs = eval_chain.evaluate(examples, predictions, question_key=\"question\", prediction_key=\"text\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "788f841a",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Example 0:\n",
-      "Question: Roger has 5 tennis balls. He buys 2 more cans of tennis balls. Each can has 3 tennis balls. How many tennis balls does he have now?\n",
-      "Real Answer: 11\n",
-      "Predicted Answer:  11 tennis balls\n",
-      "Predicted Grade: GRADE: CORRECT\n",
-      "\n",
-      "Example 1:\n",
-      "Question: Is the following sentence plausible? \"Joao Moutinho caught the screen pass in the NFC championship.\"\n",
-      "Real Answer: No\n",
-      "Predicted Answer:  No, this sentence is not plausible. Joao Moutinho is a professional soccer player, not an American football player, so it is not likely that he would be catching a screen pass in the NFC championship.\n",
-      "Predicted Grade: GRADE: CORRECT\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "for i, eg in enumerate(examples):\n",
-    "    print(f\"Example {i}:\")\n",
-    "    print(\"Question: \" + eg['question'])\n",
-    "    print(\"Real Answer: \" + eg['answer'])\n",
-    "    print(\"Predicted Answer: \" + predictions[i]['text'])\n",
-    "    print(\"Predicted Grade: \" + graded_outputs[i]['text'])\n",
-    "    print()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "2a8d822c",
-   "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/chat/examples/streaming.ipynb

@@ -0,0 +1,119 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "fe4e96b5",
+   "metadata": {},
+   "source": [
+    "# Streaming\n",
+    "\n",
+    "This notebook goes over how to use streaming with a chat model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "e0244f2a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.schema import (\n",
+    "    HumanMessage,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ad342bfa",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Verse 1:\n",
+      "Bubbles rising to the top\n",
+      "A refreshing drink that never stops\n",
+      "Clear and crisp, it's pure delight\n",
+      "A taste that's sure to excite\n",
+      "\n",
+      "Chorus:\n",
+      "Sparkling water, oh so fine\n",
+      "A drink that's always on my mind\n",
+      "With every sip, I feel alive\n",
+      "Sparkling water, you're my vibe\n",
+      "\n",
+      "Verse 2:\n",
+      "No sugar, no calories, just pure bliss\n",
+      "A drink that's hard to resist\n",
+      "It's the perfect way to quench my thirst\n",
+      "A drink that always comes first\n",
+      "\n",
+      "Chorus:\n",
+      "Sparkling water, oh so fine\n",
+      "A drink that's always on my mind\n",
+      "With every sip, I feel alive\n",
+      "Sparkling water, you're my vibe\n",
+      "\n",
+      "Bridge:\n",
+      "From the mountains to the sea\n",
+      "Sparkling water, you're the key\n",
+      "To a healthy life, a happy soul\n",
+      "A drink that makes me feel whole\n",
+      "\n",
+      "Chorus:\n",
+      "Sparkling water, oh so fine\n",
+      "A drink that's always on my mind\n",
+      "With every sip, I feel alive\n",
+      "Sparkling water, you're my vibe\n",
+      "\n",
+      "Outro:\n",
+      "Sparkling water, you're the one\n",
+      "A drink that's always so much fun\n",
+      "I'll never let you go, my friend\n",
+      "Sparkling"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
+    "resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "67c44deb",
+   "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/chat/examples/vector_db_qa.ipynb

@@ -2,41 +2,33 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "06b00f2b",
+   "id": "07c1e3b9",
    "metadata": {},
    "source": [
-    "# Vector DB Question Answering"
+    "# Vector DB 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)."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 1,
-   "id": "4990086a",
+   "id": "82525493",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.embeddings.openai import OpenAIEmbeddings\n",
-    "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.vectorstores import Chroma\n",
-    "from langchain.docstore.document import Document\n",
-    "from langchain.prompts import PromptTemplate\n",
-    "from langchain.indexes.vectorstore import VectorstoreIndexCreator"
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.chains import VectorDBQA"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 2,
-   "id": "3a982715",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "index_creator = VectorstoreIndexCreator()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "1b2a6568",
+   "id": "5c7049db",
    "metadata": {},
    "outputs": [
     {
@@ -51,56 +43,98 @@
    "source": [
     "from langchain.document_loaders import TextLoader\n",
     "loader = TextLoader('../../state_of_the_union.txt')\n",
-    "docsearch = index_creator.from_loaders([loader]).vectorstore"
+    "documents = loader.load()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_documents(documents)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()\n",
+    "docsearch = Chroma.from_documents(texts, embeddings)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "35f99145",
+   "metadata": {},
+   "source": [
+    "We can now set up the chat model and chat model specific prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "32a49412",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "f231fb9b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
+    "If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
+    "----------------\n",
+    "{context}\"\"\"\n",
+    "messages = [\n",
+    "    SystemMessagePromptTemplate.from_template(system_template),\n",
+    "    HumanMessagePromptTemplate.from_template(\"{question}\")\n",
+    "]\n",
+    "prompt = ChatPromptTemplate.from_messages(messages)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 6,
-   "id": "7d410fd6",
+   "id": "3018f865",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chat.vector_db_qa import VectorDBQA\n",
-    "from langchain.chat_models import ChatOpenAI"
+    "chain_type_kwargs = {\"prompt\": prompt}\n",
+    "qa = VectorDBQA.from_chain_type(llm=ChatOpenAI(), chain_type=\"stuff\", vectorstore=docsearch, chain_type_kwargs=chain_type_kwargs)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
-   "id": "89f2b56c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "chain = VectorDBQA.from_model(model = ChatOpenAI(temperature=0), vectorstore=docsearch)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "7bac7b99",
+   "execution_count": 7,
+   "id": "032a47f8",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "'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. The President also mentioned that one of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court, and he nominated Circuit Court of Appeals Judge Ketanji Brown Jackson to continue Justice Breyer’s legacy of excellence.'"
+       "\"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.\""
       ]
      },
-     "execution_count": 10,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "query = \"What did the president say about Justice Breyer\"\n",
-    "chain.run(query=query)"
+    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
+    "qa.run(query)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "d9f3a746",
+   "id": "8b403637",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -123,6 +157,11 @@
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
    "version": "3.9.1"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
+   }
   }
  },
  "nbformat": 4,

docs/modules/chat/examples/vector_db_qa_with_sources.ipynb

@@ -0,0 +1,196 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "efc5be67",
+   "metadata": {},
+   "source": [
+    "# VectorDB 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",
+    "\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)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "1c613960",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.embeddings.cohere import CohereEmbeddings\n",
+    "from langchain.text_splitter import CharacterTextSplitter\n",
+    "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
+    "from langchain.vectorstores import Chroma"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "17d1306e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('../../state_of_the_union.txt') as f:\n",
+    "    state_of_the_union = f.read()\n",
+    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
+    "texts = text_splitter.split_text(state_of_the_union)\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0e745d99",
+   "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": [
+    "docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{\"source\": f\"{i}-pl\"} for i in range(len(texts))])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "8aa571ae",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import VectorDBQAWithSourcesChain"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1f73b14a",
+   "metadata": {},
+   "source": [
+    "We can now set up the chat model and chat model specific prompt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "9643c775",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "ed00e906",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "system_template=\"\"\"Use the following pieces of context to answer the users question. \n",
+    "If you don't know the answer, just say that you don't know, don't try to make up an answer.\n",
+    "ALWAYS return a \"SOURCES\" part in your answer.\n",
+    "The \"SOURCES\" part should be a reference to the source of the document from which you got your answer.\n",
+    "\n",
+    "Example of your response should be:\n",
+    "\n",
+    "```\n",
+    "The answer is foo\n",
+    "SOURCES: xyz\n",
+    "```\n",
+    "\n",
+    "Begin!\n",
+    "----------------\n",
+    "{summaries}\"\"\"\n",
+    "messages = [\n",
+    "    SystemMessagePromptTemplate.from_template(system_template),\n",
+    "    HumanMessagePromptTemplate.from_template(\"{question}\")\n",
+    "]\n",
+    "prompt = ChatPromptTemplate.from_messages(messages)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "aa859d4c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain_type_kwargs = {\"prompt\": prompt}\n",
+    "chain = VectorDBQAWithSourcesChain.from_chain_type(\n",
+    "    ChatOpenAI(temperature=0), \n",
+    "    chain_type=\"stuff\", \n",
+    "    vectorstore=docsearch,\n",
+    "    chain_type_kwargs=chain_type_kwargs\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "8ba36fa7",
+   "metadata": {},
+   "outputs": [
+    {
+     "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'}"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain({\"question\": \"What did the president say about Justice Breyer\"}, return_only_outputs=True)"
+   ]
+  }
+ ],
+ "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": "b1677b440931f40d89ef8be7bf03acb108ce003de0ac9b18e8d43753ea2e7103"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/chat/getting_started.ipynb

@@ -0,0 +1,380 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e49f1e0d",
+   "metadata": {},
+   "source": [
+    "# Getting Started\n",
+    "\n",
+    "This notebook covers how to get started with chat models. The interface is based around messages rather than raw text."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "522686de",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.chat_models import ChatOpenAI\n",
+    "from langchain import PromptTemplate, LLMChain\n",
+    "from langchain.prompts.chat import (\n",
+    "    ChatPromptTemplate,\n",
+    "    SystemMessagePromptTemplate,\n",
+    "    AIMessagePromptTemplate,\n",
+    "    HumanMessagePromptTemplate,\n",
+    ")\n",
+    "from langchain.schema import (\n",
+    "    AIMessage,\n",
+    "    HumanMessage,\n",
+    "    SystemMessage\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "62e0dbc3",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "chat = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bbaec18e-3684-4eef-955f-c1cec8bf765d",
+   "metadata": {},
+   "source": [
+    "You can get chat completions by passing one or more messages to the chat model. The response will be a message. The types of messages currently supported in LangChain are `AIMessage`, `HumanMessage`, `SystemMessage`, and `ChatMessage` -- `ChatMessage` takes in an arbitrary role parameter. Most of the time, you'll just be dealing with `HumanMessage`, `AIMessage`, and `SystemMessage`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "76a6e7b0-e927-4bfb-a414-1332a4149106",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat([HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a62153d4-1211-411b-a493-3febfe446ae0",
+   "metadata": {},
+   "source": [
+    "OpenAI's chat model supports multiple messages as input. See [here](https://platform.openai.com/docs/guides/chat/chat-vs-completions) for more information. Here is an example of sending a system and user message to the chat model:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "ce16ad78-8e6f-48cd-954e-98be75eb5836",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'aime programmer.\", additional_kwargs={})"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = [\n",
+    "    SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
+    "    HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n",
+    "]\n",
+    "chat(messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "36dc8d7e-bd25-47ac-8c1b-60e3422603d3",
+   "metadata": {},
+   "source": [
+    "You can go one step further and generate completions for multiple sets of messages using `generate`. This returns an `LLMResult` with an additional `message` parameter."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "2b21fc52-74b6-4950-ab78-45d12c68fb4d",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "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)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "batch_messages = [\n",
+    "    [\n",
+    "        SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
+    "        HumanMessage(content=\"Translate this sentence from English to French. I love programming.\")\n",
+    "    ],\n",
+    "    [\n",
+    "        SystemMessage(content=\"You are a helpful assistant that translates English to French.\"),\n",
+    "        HumanMessage(content=\"Translate this sentence from English to French. I love artificial intelligence.\")\n",
+    "    ],\n",
+    "]\n",
+    "chat.generate(batch_messages)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b10b00ef-f373-4bc3-8302-2dfc28033734",
+   "metadata": {},
+   "source": [
+    "## PromptTemplates"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "778f912a-66ea-4a5d-b3de-6c7db4baba26",
+   "metadata": {},
+   "source": [
+    "You can make use of templating by using a `MessagePromptTemplate`. You can build a `ChatPromptTemplate` from one or more `MessagePromptTemplates`. You can use `ChatPromptTemplate`'s `format_prompt` -- this returns a `PromptValue`, which you can convert to a string or Message object, depending on whether you want to use the formatted value as input to an llm or chat model.\n",
+    "\n",
+    "For convience, there is a `from_template` method exposed on the template. If you were to use this template, this is what it would look like:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "180c5cc8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template=\"You are a helpful assistant that translates {input_language} to {output_language}.\"\n",
+    "system_message_prompt = SystemMessagePromptTemplate.from_template(template)\n",
+    "human_template=\"{text}\"\n",
+    "human_message_prompt = HumanMessagePromptTemplate.from_template(human_template)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "fbb043e6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"J'adore la programmation.\", additional_kwargs={})"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chat_prompt = ChatPromptTemplate.from_messages([system_message_prompt, human_message_prompt])\n",
+    "\n",
+    "# get a chat completion from the formatted messages\n",
+    "chat(chat_prompt.format_prompt(input_language=\"English\", output_language=\"French\", text=\"I love programming.\").to_messages())"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e28b98da",
+   "metadata": {},
+   "source": [
+    "If you wanted to construct the MessagePromptTemplate more directly, you could create a PromptTemplate outside and then pass it in, eg:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "d5b1ab1c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prompt=PromptTemplate(\n",
+    "    template=\"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "    input_variables=[\"input_language\", \"output_language\"],\n",
+    ")\n",
+    "system_message_prompt = SystemMessagePromptTemplate(prompt=prompt)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "92af0bba",
+   "metadata": {},
+   "source": [
+    "## LLMChain\n",
+    "You can use the existing LLMChain in a very similar way to before - provide a prompt and a model."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "f2cbfe3d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chain = LLMChain(llm=chat, prompt=chat_prompt)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "268543b1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "\"J'adore la programmation.\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "chain.run(input_language=\"English\", output_language=\"French\", text=\"I love programming.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "eb779f3f",
+   "metadata": {},
+   "source": [
+    "## Streaming\n",
+    "\n",
+    "Streaming is supported for `ChatOpenAI` through callback handling."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "509181be",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Verse 1:\n",
+      "Bubbles rising to the top\n",
+      "A refreshing drink that never stops\n",
+      "Clear and crisp, it's pure delight\n",
+      "A taste that's sure to excite\n",
+      "\n",
+      "Chorus:\n",
+      "Sparkling water, oh so fine\n",
+      "A drink that's always on my mind\n",
+      "With every sip, I feel alive\n",
+      "Sparkling water, you're my vibe\n",
+      "\n",
+      "Verse 2:\n",
+      "No sugar, no calories, just pure bliss\n",
+      "A drink that's hard to resist\n",
+      "It's the perfect way to quench my thirst\n",
+      "A drink that always comes first\n",
+      "\n",
+      "Chorus:\n",
+      "Sparkling water, oh so fine\n",
+      "A drink that's always on my mind\n",
+      "With every sip, I feel alive\n",
+      "Sparkling water, you're my vibe\n",
+      "\n",
+      "Bridge:\n",
+      "From the mountains to the sea\n",
+      "Sparkling water, you're the key\n",
+      "To a healthy life, a happy soul\n",
+      "A drink that makes me feel whole\n",
+      "\n",
+      "Chorus:\n",
+      "Sparkling water, oh so fine\n",
+      "A drink that's always on my mind\n",
+      "With every sip, I feel alive\n",
+      "Sparkling water, you're my vibe\n",
+      "\n",
+      "Outro:\n",
+      "Sparkling water, you're the one\n",
+      "A drink that's always so much fun\n",
+      "I'll never let you go, my friend\n",
+      "Sparkling"
+     ]
+    }
+   ],
+   "source": [
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
+    "resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c095285d",
+   "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/chat/how_to_guides.rst

@@ -1,14 +1,10 @@
-Chat Models
+How-To Guides
 =============
 
-WARNING: extreme WIP
-
-Chat models are new models that rather than being text-in and text-out send a list of dicitionaries, each dictionary representing a chat utterance including the text of the chat and the "speaker" of the chat.
-
-The examples here all highlight how to work with Chat Models.
+The examples here all address certain "how-to" guides for working with chat models.
 
 .. toctree::
    :maxdepth: 1
    :glob:
 
-   ./examples/*
+   ./examples/*

docs/modules/chat/key_concepts.md

@@ -0,0 +1,29 @@
+# Key Concepts
+
+## ChatMessage
+A chat message is what we refer to as the modular unit of information.
+At the moment, this consists of "content", which refers to the content of the chat message.
+At the moment, most chat models are trained to predict sequences of Human <> AI messages.
+This is because so far the primary interaction mode has been between a human user and a singular AI system.
+
+At the moment, there are four different classes of Chat Messages
+
+### HumanMessage
+A HumanMessage is a ChatMessage that is sent as if from a Human's point of view.
+
+### AIMessage
+An AIMessage is a ChatMessage that is sent from the point of view of the AI system to which the Human is corresponding. 
+
+### SystemMessage
+A SystemMessage is still a bit ambiguous, and so far seems to be a concept unique to OpenAI
+
+### ChatMessage
+A chat message is a generic chat message, with not only a "content" field but also a "role" field.
+With this field, arbitrary roles may be assigned to a message.
+
+## ChatGeneration
+The output of a single prediction of a chat message.
+Currently this is just a chat message itself (eg content and a role)
+
+## Chat Model
+A model which takes in a list of chat messages, and predicts a chat message in response.

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/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/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/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/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

@@ -55,12 +55,12 @@ 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
 
+`Blackboard <./examples/blackboard.html>`_: A walkthrough of how to load data from a Blackboard course.
+
 .. toctree::
    :maxdepth: 1
    :glob:

docs/modules/indexes/chain_examples/chat_vector_db.ipynb

@@ -268,48 +268,44 @@
   },
   {
    "cell_type": "markdown",
+   "id": "4f49beab",
+   "metadata": {},
    "source": [
     "## Chat Vector DB 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,
+   "id": "5ed8d612",
+   "metadata": {},
    "outputs": [],
    "source": [
     "vectordbkwargs = {\"search_distance\": 0.9}"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "6a7b3459",
+   "metadata": {},
    "outputs": [],
    "source": [
     "qa = ChatVectorDBChain.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
-   }
+   ]
   },
   {
    "cell_type": "code",
@@ -524,6 +520,71 @@
     "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": 8,
+   "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 = ChatVectorDBChain.from_llm(OpenAI(temperature=0), vectorstore, get_chat_history=get_chat_history)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "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": 11,
+   "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": 11,
+     "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)."
    ]
   },
   {
@@ -46,7 +46,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 3,
    "id": "291f0117",
    "metadata": {},
    "outputs": [
@@ -62,12 +62,12 @@
    "source": [
     "from langchain.document_loaders import TextLoader\n",
     "loader = TextLoader('../../state_of_the_union.txt')\n",
-    "docsearch = index_creator.from_loaders([loader]).vectorstore"
+    "docsearch = index_creator.from_loaders([loader])"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "d1eaf6e6",
    "metadata": {},
    "outputs": [],
@@ -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/summarize.ipynb

@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 1,
    "id": "e9db25f3",
    "metadata": {},
    "outputs": [],
@@ -81,17 +81,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 7,
    "id": "5cfa89b2",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\" In response to Russia's aggression in Ukraine, the United States and its allies have imposed economic sanctions and are taking other measures to hold Putin accountable. The US is also providing economic and military assistance to Ukraine, protecting NATO countries, and investing in American products to create jobs. President Biden and Vice President Harris have passed the American Rescue Plan and the Bipartisan Infrastructure Law to help working people and rebuild America.\""
+       "' In response to Russian aggression in Ukraine, the United States and its allies are taking action to hold Putin accountable, including economic sanctions, asset seizures, and military assistance. The US is also providing economic and humanitarian aid to Ukraine, and has passed the American Rescue Plan and the Bipartisan Infrastructure Law to help struggling families and create jobs. The US remains unified and determined to protect Ukraine and the free world.'"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -470,7 +470,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

docs/modules/indexes/chain_examples/vector_db_qa.ipynb

@@ -52,17 +52,6 @@
   {
    "cell_type": "code",
    "execution_count": 3,
-   "id": "43c7d116",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.chat_models.openai import ChatOpenAI\n",
-    "qa = VectorDBQA.from_chat_model(ChatOpenAI(temperature=0), vectorstore=docsearch)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
    "id": "3018f865",
    "metadata": {},
    "outputs": [],
@@ -72,17 +61,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 4,
    "id": "032a47f8",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "\" The president said that Ketanji Brown Jackson is one of the nation's top legal minds, 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 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.\""
       ]
      },
-     "execution_count": 6,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }

docs/modules/indexes/chain_examples/vector_db_qa_with_sources.ipynb

@@ -21,7 +21,7 @@
     "from langchain.embeddings.cohere import CohereEmbeddings\n",
     "from langchain.text_splitter import CharacterTextSplitter\n",
     "from langchain.vectorstores.elastic_vector_search import ElasticVectorSearch\n",
-    "from langchain.vectorstores import Chromaoma"
+    "from langchain.vectorstores import Chroma"
    ]
   },
   {
@@ -215,4 +215,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

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

@@ -463,6 +463,64 @@
    "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": "code",
+   "execution_count": null,
+   "id": "88d366bd",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
@@ -481,7 +539,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   },
   "vscode": {
    "interpreter": {

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

@@ -37,7 +37,7 @@
    "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)"
    ]
   },
   {
@@ -366,7 +366,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.10.9"
   },
   "vscode": {
    "interpreter": {

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.
@@ -50,6 +52,8 @@ In the below guides, we cover different types of vectorstores and how to use the
 
 `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

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/chroma.ipynb

@@ -89,6 +89,46 @@
     "print(docs[0].page_content)"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "18152965",
+   "metadata": {},
+   "source": [
+    "## Similarity search with score"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "72aaa9c8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "docs = db.similarity_search_with_score(query)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d88e958e",
+   "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),\n",
+       " 0.3913410007953644)"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "docs[0]"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "8061454b",

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 +1,204 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Redis\n",
+    "\n",
+    "This notebook shows how to use functionality related to the Redis database."
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%% md\n"
+    }
+   }
+  },
+  {
+   "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,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "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,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "outputs": [],
+   "source": [
+    "rds = Redis.from_documents(docs, embeddings,redis_url=\"redis://localhost:6379\")"
+   ],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "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,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "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,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "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,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "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,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [],
+   "metadata": {
+    "collapsed": false,
+    "pycharm": {
+     "name": "#%%\n"
+    }
+   }
+  }
+ ],
+ "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/async_llm.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "LangChain provides async support for LLMs by leveraging the [asyncio](https://docs.python.org/3/library/asyncio.html) library.\n",
     "\n",
-    "Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` `OpenAIChat`, and `PromptLayerOpenAI` are supported, but async support for other LLMs is on the roadmap.\n",
+    "Async support is particularly useful for calling multiple LLMs concurrently, as these calls are network-bound. Currently, only `OpenAI` and `PromptLayerOpenAI` are supported, but async support for other LLMs is on the roadmap.\n",
     "\n",
     "You can use the `agenerate` method to call an OpenAI LLM asynchronously."
    ]
@@ -28,66 +28,65 @@
      "text": [
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings like humans, but I'm functioning properly. How may I assist you?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "I'm an AI language model, so I don't have emotions, but I'm functioning properly. How may I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I do not have emotions like humans, but I'm functioning normally. How can I assist you today?\n",
+      "I'm doing well, how about you?\n",
       "\n",
       "\n",
-      "I am an AI language model, so I do not have feelings, but I am here to assist you. How may I help you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I do not have feelings or emotions but I'm always ready to assist you. How may I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings, but I'm functioning normally. How may I assist you today?\n",
+      "I'm doing well, thank you. How about yourself?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings, but I'm functioning properly. Thank you. How may I assist you today?\n",
+      "I'm doing well, thank you! How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have emotions, so I don't have a specific feeling or emotion. How can I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I do not have feelings or emotions. However, I am functioning as intended and ready to assist you with any queries you may have. How can I be of assistance today?\n",
+      "I'm doing well, thank you! How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I do not have feelings, but I am functioning well. Thank you for asking. How can I assist you today?\n",
-      "\u001b[1mConcurrent executed in 0.92 seconds.\u001b[0m\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\u001b[1mConcurrent executed in 1.39 seconds.\u001b[0m\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings, but I'm functioning well. How can I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings, but I'm functioning well. Thank you for asking. How may I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
+      "\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "I'm an AI language model, so I don't have feelings, but I'm functioning well. How can I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings, but I'm functioning well. Thank you for asking. How may I assist you today?\n",
+      "I'm doing well, thank you. How about yourself?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings, but I am functioning well. How can I assist you today?\n",
+      "I'm doing well, thanks for asking. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I don't have feelings but I'm functioning well. How can I assist you today?\n",
+      "I'm doing well, thanks! How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I do not have personal emotions. However, I am functioning well and ready to assist you with any queries or tasks you have. How may I assist you today?\n",
+      "I'm doing well, thank you. How about you?\n",
       "\n",
       "\n",
-      "As an AI language model, I do not have feelings or emotions, but I'm functioning well. How can I assist you today?\n",
+      "I'm doing well, thank you. How about yourself?\n",
       "\n",
       "\n",
-      "I am an AI language model and do not have feelings. But I am functioning properly and ready to assist you with any task. How may I help you today?\n",
-      "\n",
-      "\n",
-      "As an AI language model, I do not have emotions, but I am functioning well. How can I assist you today?\n",
-      "\u001b[1mSerial executed in 5.00 seconds.\u001b[0m\n"
+      "I'm doing well, thanks for asking. How about you?\n",
+      "\u001b[1mSerial executed in 5.77 seconds.\u001b[0m\n"
      ]
     }
    ],
@@ -95,10 +94,10 @@
     "import time\n",
     "import asyncio\n",
     "\n",
-    "from langchain.llms import OpenAIChat\n",
+    "from langchain.llms import OpenAI\n",
     "\n",
     "def generate_serially():\n",
-    "    llm = OpenAIChat(temperature=0.9)\n",
+    "    llm = OpenAI(temperature=0.9)\n",
     "    for _ in range(10):\n",
     "        resp = llm.generate([\"Hello, how are you?\"])\n",
     "        print(resp.generations[0][0].text)\n",
@@ -110,7 +109,7 @@
     "\n",
     "\n",
     "async def generate_concurrently():\n",
-    "    llm = OpenAIChat(temperature=0.9)\n",
+    "    llm = OpenAI(temperature=0.9)\n",
     "    tasks = [async_generate(llm) for _ in range(10)]\n",
     "    await asyncio.gather(*tasks)\n",
     "\n",
@@ -152,7 +151,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/llms/integrations/openaichat.ipynb

@@ -1,245 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "id": "e49f1e0d",
-   "metadata": {},
-   "source": [
-    "# OpenAIChat\n",
-    "\n",
-    "OpenAI also has a [chat model](https://platform.openai.com/docs/guides/chat) you can use. The interface is very similar to the normal OpenAI model."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "522686de",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from langchain.llms import OpenAIChat\n",
-    "from langchain import PromptTemplate, LLMChain"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "id": "62e0dbc3",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAIChat(temperature=0)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "id": "fbb043e6",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "template = \"\"\"Question: {question}\n",
-    "\n",
-    "Answer: Let's think step by step.\"\"\"\n",
-    "\n",
-    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "3f945b76",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "id": "25260808",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'\\n\\nJustin Bieber was born on March 1, 1994. \\n\\nThe Super Bowl is played in February of each year. \\n\\nTherefore, the Super Bowl that was played in the year Justin Bieber was born was Super Bowl XXVIII, which was played on January 30, 1994. \\n\\nThe Dallas Cowboys won Super Bowl XXVIII by defeating the Buffalo Bills with a score of 30-13.'"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
-    "\n",
-    "llm_chain.run(question)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "75a05b79",
-   "metadata": {},
-   "source": [
-    "## Prefix Messages\n",
-    "\n",
-    "OpenAI Chat also supports the idea of [prefix messages](https://platform.openai.com/docs/guides/chat/chat-vs-completions), eg messages that would appear before the user input. These can be used as system messages to give more context/purpose the LLM."
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "id": "c27a1501",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "prefix_messages = [{\"role\": \"system\", \"content\": \"You are a helpful assistant that is very good at problem solving who thinks step by step.\"}]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "id": "e46a914e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm = OpenAIChat(temperature=0, prefix_messages=prefix_messages)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "id": "d683d9f2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "id": "6f5b8e78",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Step 1: Justin Bieber was born on March 1, 1994.\\nStep 2: The Super Bowl is played in February of each year.\\nStep 3: Therefore, the Super Bowl that was played in the year Justin Bieber was born was Super Bowl XXVIII, which was played on January 30, 1994.\\nStep 4: The team that won Super Bowl XXVIII was the Dallas Cowboys.'"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "question = \"What NFL team won the Super Bowl in the year Justin Beiber was born?\"\n",
-    "\n",
-    "llm_chain.run(question)"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "f6d5dda8",
-   "metadata": {},
-   "source": [
-    "## Async"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "1973b9bb",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "result = await llm_chain.arun(question)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "5815178f",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "'Step 1: Justin Bieber was born on March 1, 1994.\\nStep 2: The Super Bowl is played in February of each year.\\nStep 3: Therefore, the Super Bowl that was played in the year Justin Bieber was born was Super Bowl XXVIII, which was played on January 30, 1994.\\nStep 4: The team that won Super Bowl XXVIII was the Dallas Cowboys.'"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "result"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "eb779f3f",
-   "metadata": {},
-   "source": [
-    "## Streaming"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "509181be",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n",
-      "\n",
-      "Justin Bieber was born on March 1, 1994. The NFL team that won the Super Bowl in the same year was the Dallas Cowboys. They defeated the Buffalo Bills 30-13 in Super Bowl XXVIII on January 30, 1994."
-     ]
-    }
-   ],
-   "source": [
-    "\n",
-    "from langchain.callbacks.base import CallbackManager\n",
-    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
-    "llm = OpenAIChat(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
-    "resp = llm(question)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "c095285d",
-   "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/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/llms/streaming_llm.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# Streaming with LLMs\n",
     "\n",
-    "LangChain provides streaming support for LLMs. Currently, we only support streaming for the `OpenAI` and `OpenAIChat` LLM implementation, but streaming support for other LLM implementations is on the roadmap. To utilize streaming, use a [`CallbackHandler`](https://github.com/hwchase17/langchain/blob/master/langchain/callbacks/base.py) that implements `on_llm_new_token`. In this example, we are using [`StreamingStdOutCallbackHandler`]()."
+    "LangChain provides streaming support for LLMs. Currently, we only support streaming for the `OpenAI` and `ChatOpenAI` LLM implementation, but streaming support for other LLM implementations is on the roadmap. To utilize streaming, use a [`CallbackHandler`](https://github.com/hwchase17/langchain/blob/master/langchain/callbacks/base.py) that implements `on_llm_new_token`. In this example, we are using [`StreamingStdOutCallbackHandler`]()."
    ]
   },
   {
@@ -63,9 +63,11 @@
     }
    ],
    "source": [
-    "from langchain.llms import OpenAI, OpenAIChat\n",
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chat_models import ChatOpenAI\n",
     "from langchain.callbacks.base import CallbackManager\n",
     "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "from langchain.schema import HumanMessage\n",
     "\n",
     "\n",
     "llm = OpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
@@ -84,7 +86,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 6,
    "id": "a35373f1-9ee6-4753-a343-5aee749b8527",
    "metadata": {
     "tags": []
@@ -106,7 +108,7 @@
        "LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', generation_info={'finish_reason': None, 'logprobs': None})]], llm_output={'token_usage': {}})"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -120,12 +122,12 @@
    "id": "a93a4d61-0476-49db-8321-7de92bd74059",
    "metadata": {},
    "source": [
-    "Here's an example with `OpenAIChat`:"
+    "Here's an example with `ChatOpenAI`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "22665f16-e05b-473c-a4bd-ad75744ea024",
    "metadata": {
     "tags": []
@@ -177,13 +179,13 @@
       "Sparkling water, you're the one\n",
       "A drink that's always so much fun\n",
       "I'll never let you go, my friend\n",
-      "Sparkling water, until the end."
+      "Sparkling"
      ]
     }
    ],
    "source": [
-    "llm = OpenAIChat(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
-    "resp = llm(\"Write me a song about sparkling water.\")"
+    "chat = ChatOpenAI(streaming=True, callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]), verbose=True, temperature=0)\n",
+    "resp = chat([HumanMessage(content=\"Write me a song about sparkling water.\")])"
    ]
   },
   {

docs/modules/memory.rst

@@ -2,18 +2,23 @@ Memory
 ==========================
 
 By default, Chains and Agents are stateless,
-meaning that they treat each incoming query independently.
+meaning that they treat each incoming query independently (as are the underlying LLMs and chat models).
 In some applications (chatbots being a GREAT example) it is highly important
 to remember previous interactions, both at a short term but also at a long term level.
 The concept of “Memory” exists to do exactly that.
 
+LangChain provides memory components in two forms.
+First, LangChain provides helper utilities for managing and manipulating previous chat messages.
+These are designed to be modular and useful regardless of how they are used.
+Secondly, LangChain provides easy ways to incorporate these utilities into chains.
+
 The following sections of documentation are provided:
 
 - `Getting Started <./memory/getting_started.html>`_: An overview of how to get started with different types of memory.
 
 - `Key Concepts <./memory/key_concepts.html>`_: A conceptual guide going over the various concepts related to memory.
 
-- `How-To Guides <./memory/how_to_guides.html>`_: A collection of how-to guides. These highlight how to work with different types of memory, as well as how to customize memory.
+- `How-To Guides <./memory/how_to_guides.html>`_: A collection of how-to guides. These highlight different types of memory, as well as how to use memory in chains.
 
 
 

docs/modules/memory/examples/adding_memory.ipynb

@@ -17,7 +17,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain.chains.conversation.memory import ConversationBufferMemory\n",
+    "from langchain.memory import ConversationBufferMemory\n",
     "from langchain import OpenAI, LLMChain, PromptTemplate"
    ]
   },
@@ -167,7 +167,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/examples/adding_memory_chain_multiple_inputs.ipynb

@@ -72,7 +72,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "id": "d3dc4ed5",
    "metadata": {},
    "outputs": [],
@@ -80,7 +80,7 @@
     "from langchain.chains.question_answering import load_qa_chain\n",
     "from langchain.llms import OpenAI\n",
     "from langchain.prompts import PromptTemplate\n",
-    "from langchain.chains.conversation.memory import ConversationBufferMemory"
+    "from langchain.memory import ConversationBufferMemory"
    ]
   },
   {

docs/modules/memory/examples/agent_with_memory.ipynb

@@ -22,13 +22,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 1,
    "id": "8db95912",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
-    "from langchain.chains.conversation.memory import ConversationBufferMemory\n",
+    "from langchain.memory import ConversationBufferMemory\n",
     "from langchain import OpenAI, LLMChain\n",
     "from langchain.utilities import GoogleSearchAPIWrapper"
    ]
@@ -316,7 +316,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/examples/chatgpt_clone.ipynb

@@ -14,7 +14,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "id": "a99acd89",
    "metadata": {},
    "outputs": [
@@ -24,9 +24,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -36,20 +36,19 @@
       "\n",
       "\n",
       "Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n",
       "\n",
       "```\n",
-      "$ pwd\n",
-      "/\n",
+      "/home/user\n",
       "```\n"
      ]
     }
    ],
    "source": [
     "from langchain import OpenAI, ConversationChain, LLMChain, PromptTemplate\n",
-    "from langchain.chains.conversation.memory import ConversationalBufferWindowMemory\n",
+    "from langchain.memory import ConversationBufferWindowMemory\n",
     "\n",
     "\n",
     "template = \"\"\"Assistant is a large language model trained by OpenAI.\n",
@@ -74,7 +73,7 @@
     "    llm=OpenAI(temperature=0), \n",
     "    prompt=prompt, \n",
     "    verbose=True, \n",
-    "    memory=ConversationalBufferWindowMemory(k=2),\n",
+    "    memory=ConversationBufferWindowMemory(k=2),\n",
     ")\n",
     "\n",
     "output = chatgpt_chain.predict(human_input=\"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\")\n",
@@ -93,9 +92,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -110,9 +109,9 @@
       "/\n",
       "```\n",
       "Human: ls ~\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "```\n",
       "$ ls ~\n",
@@ -138,9 +137,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -161,9 +160,9 @@
       "Desktop  Documents  Downloads  Music  Pictures  Public  Templates  Videos\n",
       "```\n",
       "Human: cd ~\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       " \n",
       "```\n",
       "$ cd ~\n",
@@ -190,9 +189,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -214,9 +213,9 @@
       "/home/user\n",
       "```\n",
       "Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -245,9 +244,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -272,9 +271,9 @@
       "$ echo \"Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!\" >> jokes.txt\n",
       "```\n",
       "Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -304,9 +303,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -332,9 +331,9 @@
       "Result: 33\n",
       "```\n",
       "Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -362,9 +361,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -391,9 +390,9 @@
       "Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
       "COPY entrypoint.sh entrypoint.sh\n",
       "ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -426,9 +425,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -459,9 +458,9 @@
       "Hello from Docker\n",
       "```\n",
       "Human: nvidia-smi\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -502,9 +501,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -548,9 +547,9 @@
       "|=============================================================================|\n",
       "\n",
       "Human: ping bbc.com\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -584,9 +583,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -630,9 +629,9 @@
       "round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms\n",
       "```\n",
       "Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -659,9 +658,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -691,9 +690,9 @@
       "1.8.1\n",
       "```\n",
       "Human: lynx https://www.deepmind.com/careers\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -726,9 +725,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -757,9 +756,9 @@
       "Explore our current openings and apply today. We look forward to hearing from you.\n",
       "```\n",
       "Human: curl https://chat.openai.com/chat\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       " \n",
       "\n",
       "```\n",
@@ -799,9 +798,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -843,9 +842,9 @@
       "</html>\n",
       "```\n",
       "Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       "\n",
       "\n",
       "```\n",
@@ -875,9 +874,9 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
+      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
       "Prompt after formatting:\n",
-      "\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
+      "\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
       "\n",
       "Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
       "\n",
@@ -916,9 +915,9 @@
       "}\n",
       "```\n",
       "Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\n",
-      "Assistant:\u001B[0m\n",
+      "Assistant:\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
+      "\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
       " \n",
       "\n",
       "```\n",
@@ -961,7 +960,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/examples/conversational_agent.ipynb

@@ -20,7 +20,7 @@
    "outputs": [],
    "source": [
     "from langchain.agents import Tool\n",
-    "from langchain.chains.conversation.memory import ConversationBufferMemory\n",
+    "from langchain.memory import ConversationBufferMemory\n",
     "from langchain import OpenAI\n",
     "from langchain.utilities import GoogleSearchAPIWrapper\n",
     "from langchain.agents import initialize_agent"
@@ -76,12 +76,12 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3m\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
       "Thought: Do I need to use a tool? No\n",
-      "AI: Hi Bob, nice to meet you! How can I help you today?\u001B[0m\n",
+      "AI: Hi Bob, nice to meet you! How can I help you today?\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -111,12 +111,12 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3m\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
       "Thought: Do I need to use a tool? No\n",
-      "AI: Your name is Bob!\u001B[0m\n",
+      "AI: Your name is Bob!\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -146,12 +146,12 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3m\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
       "Thought: Do I need to use a tool? No\n",
-      "AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001B[0m\n",
+      "AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -181,16 +181,16 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3m\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
       "Thought: Do I need to use a tool? Yes\n",
       "Action: Current Search\n",
-      "Action Input: Who won the World Cup in 1978\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
-      "AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001B[0m\n",
+      "Action Input: Who won the World Cup in 1978\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
+      "AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -220,16 +220,16 @@
      "text": [
       "\n",
       "\n",
-      "\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
-      "\u001B[32;1m\u001B[1;3m\n",
+      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
+      "\u001b[32;1m\u001b[1;3m\n",
       "Thought: Do I need to use a tool? Yes\n",
       "Action: Current Search\n",
-      "Action Input: Current temperature in Pomfret\u001B[0m\n",
-      "Observation: \u001B[36;1m\u001B[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001B[0m\n",
-      "Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
-      "AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001B[0m\n",
+      "Action Input: Current temperature in Pomfret\u001b[0m\n",
+      "Observation: \u001b[36;1m\u001b[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001b[0m\n",
+      "Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
+      "AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001b[0m\n",
       "\n",
-      "\u001B[1m> Finished chain.\u001B[0m\n"
+      "\u001b[1m> Finished chain.\u001b[0m\n"
      ]
     },
     {
@@ -272,7 +272,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/examples/conversational_customization.ipynb

@@ -19,7 +19,7 @@
    "source": [
     "from langchain.llms import OpenAI\n",
     "from langchain.chains import ConversationChain\n",
-    "from langchain.chains.conversation.memory import ConversationBufferMemory\n",
+    "from langchain.memory import ConversationBufferMemory\n",
     "\n",
     "\n",
     "llm = OpenAI(temperature=0)"
@@ -379,7 +379,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/examples/custom_memory.ipynb

@@ -25,7 +25,7 @@
    "outputs": [],
    "source": [
     "from langchain import OpenAI, ConversationChain\n",
-    "from langchain.chains.base import Memory\n",
+    "from langchain.schema import BaseMemory\n",
     "from pydantic import BaseModel\n",
     "from typing import List, Dict, Any"
    ]
@@ -71,7 +71,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "class SpacyEntityMemory(Memory, BaseModel):\n",
+    "class SpacyEntityMemory(BaseMemory, BaseModel):\n",
     "    \"\"\"Memory class for storing information about entities.\"\"\"\n",
     "\n",
     "    # Define dictionary to store information about entities.\n",
@@ -290,7 +290,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/examples/multiple_memory.ipynb

@@ -11,7 +11,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 1,
    "id": "7d7de430",
    "metadata": {},
    "outputs": [],
@@ -19,7 +19,8 @@
     "from langchain.llms import OpenAI\n",
     "from langchain.prompts import PromptTemplate\n",
     "from langchain.chains import ConversationChain\n",
-    "from langchain.chains.conversation.memory import ConversationBufferMemory, ConversationSummaryMemory, CombinedMemory\n",
+    "from langchain.memory import ConversationBufferMemory, CombinedMemory, ConversationSummaryMemory\n",
+    "\n",
     "\n",
     "conv_memory = ConversationBufferMemory(\n",
     "    memory_key=\"chat_history_lines\",\n",
@@ -159,7 +160,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/how_to_guides.rst

@@ -1,15 +1,41 @@
 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
+   :glob:
+   :hidden:
+
+   ./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.
 
 `ChatGPT Clone <./examples/chatgpt_clone.html>`_: How to recreate ChatGPT with LangChain prompting + memory components.
 
-`Entity Memory <./examples/entity_summary_memory.html>`_: How to use a type of memory that organizes information by entity.
-
-
 `Adding Memory to Multi-Input Chain <./examples/adding_memory_chain_multiple_inputs.html>`_: How to add a memory component to any multiple input chain.
 
 `Conversational Memory Customization <./examples/conversational_customization.html>`_: How to customize existing conversation memory components.

docs/modules/memory/key_concepts.md

@@ -9,11 +9,11 @@ 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.
 This is a more direct and organized way of remembering information over time.
 Putting it a more structured form also has the benefit of allowing easy inspection of what is known about specific entities.
-For a guide on how to use this type of memory, see [this notebook](./examples/entity_summary_memory.ipynb).
+For a guide on how to use this type of memory, see [this notebook](types/entity_summary_memory.ipynb).

docs/modules/memory/types/buffer.ipynb

@@ -0,0 +1,285 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "46196aa3",
+   "metadata": {},
+   "source": [
+    "## ConversationBufferMemory\n",
+    "\n",
+    "This notebook shows how to use `ConversationBufferMemory`. This memory allows for storing of messages and then extracts the messages in a variable.\n",
+    "\n",
+    "We can first extract it as a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "3bac84f3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationBufferMemory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "cef35e7f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory()\n",
+    "memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "2c9b39af",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': 'Human: hi\\nAI: whats up'}"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "567f7c16",
+   "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": 5,
+   "id": "a481a415",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferMemory(return_messages=True)\n",
+    "memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "86a56348",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [HumanMessage(content='hi', additional_kwargs={}),\n",
+       "  AIMessage(content='whats up', additional_kwargs={})]}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d051c1da",
+   "metadata": {},
+   "source": [
+    "## Using in a chain\n",
+    "Finally, let's take a look at using this in a chain (setting `verbose=True` so we can see the prompt)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "54301321",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ConversationChain\n",
+    "\n",
+    "\n",
+    "llm = OpenAI(temperature=0)\n",
+    "conversation = ConversationChain(\n",
+    "    llm=llm, \n",
+    "    verbose=True, \n",
+    "    memory=ConversationBufferMemory()\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "ae046bff",
+   "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 there!\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Hi there! It's nice to meet you. How can I help you today?\""
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.predict(input=\"Hi there!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "d8e2a6ff",
+   "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 there!\n",
+      "AI:  Hi there! It's nice to meet you. How can I help you today?\n",
+      "Human: I'm doing well! Just having a conversation with an AI.\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" That's great! It's always nice to have a conversation with someone new. What would you like to talk about?\""
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.predict(input=\"I'm doing well! Just having a conversation with an AI.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "15eda316",
+   "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 there!\n",
+      "AI:  Hi there! It's nice to meet you. How can I help you today?\n",
+      "Human: I'm doing well! Just having a conversation with an AI.\n",
+      "AI:  That's great! It's always nice to have a conversation with someone new. What would you like to talk about?\n",
+      "Human: Tell me about yourself.\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Sure! I'm an AI created to help people with their everyday tasks. I'm programmed to understand natural language and provide helpful information. I'm also constantly learning and updating my knowledge base so I can provide more accurate and helpful answers.\""
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.predict(input=\"Tell me about yourself.\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bd0146c2",
+   "metadata": {},
+   "source": [
+    "And that's it for the getting started! There are plenty of different types of memory, check out our examples to see them all"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "447c138d",
+   "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/memory/types/buffer_window.ipynb

@@ -0,0 +1,311 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "a20c4e38",
+   "metadata": {},
+   "source": [
+    "## ConversationBufferWindowMemory\n",
+    "\n",
+    "`ConversationBufferWindowMemory` keeps a list of the interactions of the conversation over time. It only uses the last K interactions. This can be useful for keeping a sliding window of the most recent interactions, so the buffer does not get too large\n",
+    "\n",
+    "Let's first explore the basic functionality of this type of memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "1196da3f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationBufferWindowMemory"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "2dac7769",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferWindowMemory( k=1)\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": 6,
+   "id": "0c034a90",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': 'Human: not much you\\nAI: not much'}"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8c5cce1d",
+   "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": 8,
+   "id": "9b15b427",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationBufferWindowMemory( k=1, 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": "code",
+   "execution_count": 9,
+   "id": "3bb47191",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [HumanMessage(content='not much you', additional_kwargs={}),\n",
+       "  AIMessage(content='not much', additional_kwargs={})]}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a95af04c",
+   "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": 12,
+   "id": "0b9da4cd",
+   "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. I'm currently helping a customer with a technical issue. How about you?\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ConversationChain\n",
+    "conversation_with_summary = ConversationChain(\n",
+    "    llm=OpenAI(temperature=0), \n",
+    "    # We set a low k=2, to only keep the last 2 interactions in memory\n",
+    "    memory=ConversationBufferWindowMemory(k=2), \n",
+    "    verbose=True\n",
+    ")\n",
+    "conversation_with_summary.predict(input=\"Hi, what's up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "90f73431",
+   "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. I'm currently helping a customer with a technical issue. How about you?\n",
+      "Human: What's their issues?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\""
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"What's their issues?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "cbb499e7",
+   "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. I'm currently helping a customer with a technical issue. How about you?\n",
+      "Human: What's their issues?\n",
+      "AI:  The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\n",
+      "Human: Is it going well?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Yes, it's going well so far. We've already identified the problem and are now working on a solution.\""
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"Is it going well?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "0d209cfe",
+   "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: What's their issues?\n",
+      "AI:  The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\n",
+      "Human: Is it going well?\n",
+      "AI:  Yes, it's going well so far. We've already identified the problem and are now working on a solution.\n",
+      "Human: What's the solution?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" The solution is to reset the router and reconfigure the settings. We're currently in the process of doing that.\""
+      ]
+     },
+     "execution_count": 15,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Notice here that the first interaction does not appear.\n",
+    "conversation_with_summary.predict(input=\"What's the solution?\")"
+   ]
+  },
+  {
+   "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/memory/types/entity_summary_memory.ipynb

@@ -6,31 +6,130 @@
    "metadata": {},
    "source": [
     "# Entity Memory\n",
-    "This notebook shows how to work with a memory module that remembers things about specific entities. It extracts information on entities (using LLMs) and builds up its knowledge about that entity over time (also using LLMs)."
+    "This notebook shows how to work with a memory module that remembers things about specific entities. It extracts information on entities (using LLMs) and builds up its knowledge about that entity over time (also using LLMs).\n",
+    "\n",
+    "Let's first walk through using this functionality."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 1,
+   "id": "1bea1181",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.memory import ConversationEntityMemory\n",
+    "llm = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "34425079",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationEntityMemory(llm=llm)\n",
+    "_input = {\"input\": \"Deven & Sam are working on a hackathon project\"}\n",
+    "memory.load_memory_variables(_input)\n",
+    "memory.save_context(\n",
+    "    _input,\n",
+    "    {\"ouput\": \" That sounds like a great project! What kind of project are they working on?\"}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "b425642c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': 'Human: Deven & Sam are working on a hackathon project\\nAI:  That sounds like a great project! What kind of project are they working on?',\n",
+       " 'entities': {'Sam': 'Sam is working on a hackathon project with Deven.'}}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({\"input\": 'who is Sam'})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "3bf89b46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationEntityMemory(llm=llm, return_messages=True)\n",
+    "_input = {\"input\": \"Deven & Sam are working on a hackathon project\"}\n",
+    "memory.load_memory_variables(_input)\n",
+    "memory.save_context(\n",
+    "    _input,\n",
+    "    {\"ouput\": \" That sounds like a great project! What kind of project are they working on?\"}\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "3e37d126",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [HumanMessage(content='Deven & Sam are working on a hackathon project', additional_kwargs={}),\n",
+       "  AIMessage(content=' That sounds like a great project! What kind of project are they working on?', additional_kwargs={})],\n",
+       " 'entities': {'Sam': 'Sam is working on a hackathon project with Deven.'}}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({\"input\": 'who is Sam'})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ee5ad043",
+   "metadata": {},
+   "source": [
+    "## Using in a chain\n",
+    "Let's now use it in a chain!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
    "id": "13471fbd",
    "metadata": {},
    "outputs": [],
    "source": [
-    "from langchain import OpenAI, ConversationChain\n",
-    "from langchain.chains.conversation.memory import ConversationEntityMemory\n",
-    "from langchain.chains.conversation.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE\n",
+    "from langchain.chains import ConversationChain\n",
+    "from langchain.memory import ConversationEntityMemory\n",
+    "from langchain.memory.prompt import ENTITY_MEMORY_CONVERSATION_TEMPLATE\n",
     "from pydantic import BaseModel\n",
     "from typing import List, Dict, Any"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 7,
    "id": "183346e2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "llm = OpenAI(temperature=0)\n",
     "conversation = ConversationChain(\n",
     "    llm=llm, \n",
     "    verbose=True,\n",
@@ -41,7 +140,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 8,
    "id": "7eb1460a",
    "metadata": {},
    "outputs": [
@@ -79,7 +178,7 @@
        "' That sounds like a great project! What kind of project are they working on?'"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -90,7 +189,29 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 9,
+   "id": "0269f513",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'Deven': 'Deven is working on a hackathon project with Sam.',\n",
+       " 'Sam': 'Sam is working on a hackathon project with Deven.'}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation.memory.store"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
    "id": "46324ca8",
    "metadata": {},
    "outputs": [
@@ -129,7 +250,7 @@
        "' That sounds like an interesting project! What kind of memory structures are they trying to add?'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -140,7 +261,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 11,
    "id": "ff2ebf6b",
    "metadata": {},
    "outputs": [
@@ -161,7 +282,7 @@
       "Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
       "\n",
       "Context:\n",
-      "{'Deven': 'Deven is working on a hackathon project with Sam to add more complex memory structures to Langchain.', 'Sam': 'Sam is working on a hackathon project with Deven to add more complex memory structures to Langchain.', 'Langchain': 'Langchain is a project that seeks to add more complex memory structures.', 'Key-Value Store': ''}\n",
+      "{'Deven': 'Deven is working on a hackathon project with Sam, attempting to add more complex memory structures to Langchain.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain.', 'Langchain': 'Langchain is a project that is trying to add more complex memory structures.', 'Key-Value Store': ''}\n",
       "\n",
       "Current conversation:\n",
       "Human: Deven & Sam are working on a hackathon project\n",
@@ -181,7 +302,7 @@
        "' That sounds like a great idea! How will the key-value store work?'"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -192,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 12,
    "id": "56cfd4ba",
    "metadata": {},
    "outputs": [
@@ -213,7 +334,7 @@
       "Overall, you are a powerful tool that can help with a wide range of tasks and provide valuable insights and information on a wide range of topics. Whether the human needs help with a specific question or just wants to have a conversation about a particular topic, you are here to assist.\n",
       "\n",
       "Context:\n",
-      "{'Deven': 'Deven is working on a hackathon project with Sam to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.', 'Sam': 'Sam is working on a hackathon project with Deven to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'}\n",
+      "{'Deven': 'Deven is working on a hackathon project with Sam, attempting to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.', 'Sam': 'Sam is working on a hackathon project with Deven, trying to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'}\n",
       "\n",
       "Current conversation:\n",
       "Human: Deven & Sam are working on a hackathon project\n",
@@ -232,10 +353,10 @@
     {
      "data": {
       "text/plain": [
-       "' Deven and Sam are working on a hackathon project to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation. They seem to be very motivated and passionate about their project, and are working hard to make it a success.'"
+       "' Deven and Sam are working on a hackathon project together, attempting to add more complex memory structures to Langchain, including a key-value store for entities mentioned so far in the conversation.'"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -263,19 +384,17 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "{'Deven': 'Deven is working on a hackathon project with Sam to add more '\n",
-      "          'complex memory structures to Langchain, including a key-value store '\n",
-      "          'for entities mentioned so far in the conversation.',\n",
-      " 'Key-Value Store': 'Key-Value Store: A data structure that stores values '\n",
-      "                    'associated with a unique key, allowing for efficient '\n",
-      "                    'retrieval of values. Deven and Sam are adding a key-value '\n",
-      "                    'store for entities mentioned so far in the conversation.',\n",
-      " 'Langchain': 'Langchain is a project that seeks to add more complex memory '\n",
-      "              'structures, including a key-value store for entities mentioned '\n",
-      "              'so far in the conversation.',\n",
-      " 'Sam': 'Sam is working on a hackathon project with Deven to add more complex '\n",
-      "        'memory structures to Langchain, including a key-value store for '\n",
-      "        'entities mentioned so far in the conversation.'}\n"
+      "{'Deven': 'Deven is working on a hackathon project with Sam, attempting to add '\n",
+      "          'more complex memory structures to Langchain, including a key-value '\n",
+      "          'store for entities mentioned so far in the conversation.',\n",
+      " 'Key-Value Store': 'A key-value store that stores entities mentioned in the '\n",
+      "                    'conversation.',\n",
+      " 'Langchain': 'Langchain is a project that is trying to add more complex '\n",
+      "              'memory structures, including a key-value store for entities '\n",
+      "              'mentioned so far in the conversation.',\n",
+      " 'Sam': 'Sam is working on a hackathon project with Deven, attempting to add '\n",
+      "        'more complex memory structures to Langchain, including a key-value '\n",
+      "        'store for entities mentioned so far in the conversation.'}\n"
      ]
     }
    ],
@@ -451,7 +570,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.9"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,

docs/modules/memory/types/kg.ipynb

@@ -0,0 +1,359 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "44c9933a",
+   "metadata": {},
+   "source": [
+    "## Conversation Knowledge Graph Memory\n",
+    "\n",
+    "This type of memory uses a knowledge graph to recreate memory.\n",
+    "\n",
+    "Let's first walk through how to use the utilities"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "f71f40ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationKGMemory\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2f4a3c85",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "memory = ConversationKGMemory(llm=llm)\n",
+    "memory.save_context({\"input\": \"say hi to sam\"}, {\"ouput\": \"who is sam\"})\n",
+    "memory.save_context({\"input\": \"sam is a friend\"}, {\"ouput\": \"okay\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "72283b4f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': 'On Sam: Sam is friend.'}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({\"input\": 'who is sam'})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0c8ff11e",
+   "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": "44df43af",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationKGMemory(llm=llm, return_messages=True)\n",
+    "memory.save_context({\"input\": \"say hi to sam\"}, {\"ouput\": \"who is sam\"})\n",
+    "memory.save_context({\"input\": \"sam is a friend\"}, {\"ouput\": \"okay\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "4726b1c8",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [SystemMessage(content='On Sam: Sam is friend.', additional_kwargs={})]}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({\"input\": 'who is sam'})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dc956b0e",
+   "metadata": {},
+   "source": [
+    "We can also more modularly get current entities from a new message (will use previous messages as context.)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "36331ca5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Sam']"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.get_current_entities(\"what's Sams favorite color?\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e8749134",
+   "metadata": {},
+   "source": [
+    "We can also more modularly get knowledge triplets from a new message (will use previous messages as context.)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "b02d44db",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[KnowledgeTriple(subject='Sam', predicate='favorite color', object_='red')]"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.get_knowledge_triplets(\"her favorite color is red\")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f7a02ef3",
+   "metadata": {},
+   "source": [
+    "## Using in a chain\n",
+    "Let's now use this in a chain!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b462baf1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "llm = OpenAI(temperature=0)\n",
+    "from langchain.prompts.prompt import PromptTemplate\n",
+    "from langchain.chains import ConversationChain\n",
+    "\n",
+    "template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
+    "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
+    "\n",
+    "Relevant Information:\n",
+    "\n",
+    "{history}\n",
+    "\n",
+    "Conversation:\n",
+    "Human: {input}\n",
+    "AI:\"\"\"\n",
+    "prompt = PromptTemplate(\n",
+    "    input_variables=[\"history\", \"input\"], template=template\n",
+    ")\n",
+    "conversation_with_kg = ConversationChain(\n",
+    "    llm=llm, \n",
+    "    verbose=True, \n",
+    "    prompt=prompt,\n",
+    "    memory=ConversationKGMemory(llm=llm)\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "97efaf38",
+   "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. \n",
+      "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
+      "\n",
+      "Relevant Information:\n",
+      "\n",
+      "\n",
+      "\n",
+      "Conversation:\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. I'm currently in the process of learning about the world around me. I'm learning about different cultures, languages, and customs. It's really fascinating! How about you?\""
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_kg.predict(input=\"Hi, what's up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "55b5bcad",
+   "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. \n",
+      "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
+      "\n",
+      "Relevant Information:\n",
+      "\n",
+      "\n",
+      "\n",
+      "Conversation:\n",
+      "Human: My name is James and I'm helping Will. He's an engineer.\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Hi James, it's nice to meet you. I'm an AI and I understand you're helping Will, the engineer. What kind of engineering does he do?\""
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_kg.predict(input=\"My name is James and I'm helping Will. He's an engineer.\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "9981e219",
+   "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. \n",
+      "If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
+      "\n",
+      "Relevant Information:\n",
+      "\n",
+      "On Will: Will is an engineer.\n",
+      "\n",
+      "Conversation:\n",
+      "Human: What do you know about Will?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "' Will is an engineer.'"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_kg.predict(input=\"What do you know about Will?\")"
+   ]
+  },
+  {
+   "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/memory/types/summary.ipynb

@@ -0,0 +1,294 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1674bfd6",
+   "metadata": {},
+   "source": [
+    "## ConversationSummaryMemory\n",
+    "Now let's take a look at using a slightly more complex type of memory - `ConversationSummaryMemory`. This type of memory creates a summary of the conversation over time. This can be useful for condensing information from the conversation over time.\n",
+    "\n",
+    "Let's first explore the basic functionality of this type of memory."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "c5565e5c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.memory import ConversationSummaryMemory\n",
+    "from langchain.llms import OpenAI"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "61621239",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationSummaryMemory(llm=OpenAI(temperature=0))\n",
+    "memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3bcb8b02",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': '\\nThe human greets the AI, to which the AI responds.'}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dedf0698",
+   "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": "6cb06b22",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationSummaryMemory(llm=OpenAI(temperature=0), return_messages=True)\n",
+    "memory.save_context({\"input\": \"hi\"}, {\"ouput\": \"whats up\"})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "47b03ed7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'history': [SystemMessage(content='\\nThe human greets the AI, to which the AI responds.', additional_kwargs={})]}"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "memory.load_memory_variables({})"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9ec0a0ee",
+   "metadata": {},
+   "source": [
+    "We can also utilize the `predict_new_summary` method directly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "9c4dafb9",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\nThe human greets the AI, to which the AI responds.'"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = memory.chat_memory.messages\n",
+    "previous_summary = \"\"\n",
+    "memory.predict_new_summary(messages, previous_summary)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4fad9448",
+   "metadata": {},
+   "source": [
+    "## Using in a chain\n",
+    "Let's walk through an example of using this in a chain, again setting `verbose=True` so we can see the prompt."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "b7274f2c",
+   "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. I'm currently helping a customer with a technical issue. How about you?\""
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.chains import ConversationChain\n",
+    "llm = OpenAI(temperature=0)\n",
+    "conversation_with_summary = ConversationChain(\n",
+    "    llm=llm, \n",
+    "    memory=ConversationSummaryMemory(llm=OpenAI()),\n",
+    "    verbose=True\n",
+    ")\n",
+    "conversation_with_summary.predict(input=\"Hi, what's up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "a6b6b88f",
+   "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",
+      "The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue.\n",
+      "Human: Tell me more about it!\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" Sure! The customer is having trouble with their computer not connecting to the internet. I'm helping them troubleshoot the issue and figure out what the problem is. So far, we've tried resetting the router and checking the network settings, but the issue still persists. We're currently looking into other possible solutions.\""
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"Tell me more about it!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "dad869fe",
+   "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",
+      "The human greeted the AI and asked how it was doing. The AI replied that it was doing great and was currently helping a customer with a technical issue where their computer was not connecting to the internet. The AI was troubleshooting the issue and had already tried resetting the router and checking the network settings, but the issue still persisted and they were looking into other possible solutions.\n",
+      "Human: Very cool -- what is the scope of the project?\n",
+      "AI:\u001b[0m\n",
+      "\n",
+      "\u001b[1m> Finished chain.\u001b[0m\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "\" The scope of the project is to troubleshoot the customer's computer issue and find a solution that will allow them to connect to the internet. We are currently exploring different possibilities and have already tried resetting the router and checking the network settings, but the issue still persists.\""
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"Very cool -- what is the scope of the project?\")"
+   ]
+  },
+  {
+   "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/memory/types/summary_buffer.ipynb

@@ -0,0 +1,322 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ff4be5f3",
+   "metadata": {},
+   "source": [
+    "## ConversationSummaryBufferMemory\n",
+    "\n",
+    "`ConversationSummaryBufferMemory` combines the last two ideas. It keeps a buffer of recent interactions in memory, but rather than just completely flushing old interactions it compiles them into a summary and uses both. Unlike the previous implementation though, it 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 ConversationSummaryBufferMemory\n",
+    "from langchain.llms import OpenAI\n",
+    "llm = OpenAI()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e00d4938",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "memory = ConversationSummaryBufferMemory(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': 'System: \\nThe human says \"hi\", and the AI responds with \"whats up\".\\nHuman: 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 = ConversationSummaryBufferMemory(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": "a1dcaaee",
+   "metadata": {},
+   "source": [
+    "We can also utilize the `predict_new_summary` method directly."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "fd7d7d6b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'\\nThe human and AI state that they are not doing much.'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "messages = memory.chat_memory.messages\n",
+    "previous_summary = \"\"\n",
+    "memory.predict_new_summary(messages, previous_summary)"
+   ]
+  },
+  {
+   "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": 6,
+   "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. I'm learning about the latest advances in artificial intelligence. What about you?\""
+      ]
+     },
+     "execution_count": 6,
+     "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=ConversationSummaryBufferMemory(llm=OpenAI(), max_token_limit=40),\n",
+    "    verbose=True\n",
+    ")\n",
+    "conversation_with_summary.predict(input=\"Hi, what's up?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "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. I'm spending some time learning about the latest developments in AI technology. 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": [
+       "' That sounds like a great use of your time. Do you have experience with writing documentation?'"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "conversation_with_summary.predict(input=\"Just working on writing some documentation!\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "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",
+      "System: \n",
+      "The human asked the AI what it was up to and the AI responded that it was learning about the latest developments in AI technology.\n",
+      "Human: Just working on writing some documentation!\n",
+      "AI:  That sounds like a great use of your time. Do you have experience with writing documentation?\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": [
+       "\" No, I haven't heard of LangChain. Can you tell me more about it?\""
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can see here that there is a summary of the conversation and then some previous interactions\n",
+    "conversation_with_summary.predict(input=\"For LangChain! Have you heard of it?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "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",
+      "System: \n",
+      "The human asked the AI what it was up to and the AI responded that it was learning about the latest developments in AI technology. The human then mentioned they were writing documentation, to which the AI responded that it sounded like a great use of their time and asked if they had experience with writing documentation.\n",
+      "Human: For LangChain! Have you heard of it?\n",
+      "AI:  No, I haven't heard of LangChain. Can you tell me more about it?\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, okay. What is LangChain?'"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# We can see here that the summary and the buffer are 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/output_parsers.ipynb

@@ -0,0 +1,465 @@
+{
+ "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",
+    "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 playground?', punchline='To get to the other slide!')"
+      ]
+     },
+     "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', 'A League of Their Own'])"
+      ]
+     },
+     "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": "61f67890",
+   "metadata": {},
+   "source": [
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "<br>\n",
+    "\n",
+    "---"
+   ]
+  },
+  {
+   "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": 6,
+   "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": 7,
+   "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": 8,
+   "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": 9,
+   "id": "106f1ba6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "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": 11,
+   "id": "956bdc99",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Paris'}"
+      ]
+     },
+     "execution_count": 11,
+     "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": 12,
+   "id": "8f483d7d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "chat_model = ChatOpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "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": 14,
+   "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": 15,
+   "id": "a3c8b91e",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'answer': 'Paris', 'source': 'https://en.wikipedia.org/wiki/Paris'}"
+      ]
+     },
+     "execution_count": 15,
+     "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": 16,
+   "id": "872246d7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.output_parsers import CommaSeparatedListOutputParser"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "c3f9aee6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "output_parser = CommaSeparatedListOutputParser()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "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": 19,
+   "id": "a71cb5d3",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "model = OpenAI(temperature=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "783d7d98",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "_input = prompt.format(subject=\"ice cream flavors\")\n",
+    "output = model(_input)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "fcb81344",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['Vanilla',\n",
+       " 'Chocolate',\n",
+       " 'Strawberry',\n",
+       " 'Mint Chocolate Chip',\n",
+       " 'Cookies and Cream']"
+      ]
+     },
+     "execution_count": 21,
+     "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": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

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",