From 6b6269441cefd97fcf7a7fc31bf715c553cc5af7 Mon Sep 17 00:00:00 2001 From: Christophe Bornet Date: Tue, 16 Jan 2024 18:50:30 +0100 Subject: [PATCH] docs: Add page for AstraDB self retriever (#16077) Preview: https://langchain-git-fork-cbornet-astra-self-retriever-docs-langchain.vercel.app/docs/integrations/retrievers/self_query/astradb --- .../retrievers/self_query/astradb.ipynb | 322 ++++++++++++++++++ 1 file changed, 322 insertions(+) create mode 100644 docs/docs/integrations/retrievers/self_query/astradb.ipynb diff --git a/docs/docs/integrations/retrievers/self_query/astradb.ipynb b/docs/docs/integrations/retrievers/self_query/astradb.ipynb new file mode 100644 index 0000000000000..43386e6a94b47 --- /dev/null +++ b/docs/docs/integrations/retrievers/self_query/astradb.ipynb @@ -0,0 +1,322 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "# Astra DB\n", + "\n", + "DataStax [Astra DB](https://docs.datastax.com/en/astra/home/astra.html) is a serverless vector-capable database built on Cassandra and made conveniently available through an easy-to-use JSON API.\n", + "\n", + "In the walkthrough, we'll demo the `SelfQueryRetriever` with an `Astra DB` vector store." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Creating an Astra DB vector store\n", + "First we'll want to create an Astra DB VectorStore and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n", + "\n", + "NOTE: The self-query retriever requires you to have `lark` installed (`pip install lark`). We also need the `astrapy` package." + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [], + "source": [ + "%pip install --upgrade --quiet lark astrapy langchain-openai" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "import os\n", + "from getpass import getpass\n", + "\n", + "from langchain_openai.embeddings import OpenAIEmbeddings\n", + "\n", + "os.environ[\"OPENAI_API_KEY\"] = getpass(\"OpenAI API Key:\")\n", + "\n", + "embeddings = OpenAIEmbeddings()" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": false, + "pycharm": { + "name": "#%% md\n" + } + }, + "source": [ + "Create the Astra DB VectorStore:\n", + "\n", + "- the API Endpoint looks like `https://01234567-89ab-cdef-0123-456789abcdef-us-east1.apps.astra.datastax.com`\n", + "- the Token looks like `AstraCS:6gBhNmsk135....`" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "ASTRA_DB_API_ENDPOINT = input(\"ASTRA_DB_API_ENDPOINT = \")\n", + "ASTRA_DB_APPLICATION_TOKEN = getpass(\"ASTRA_DB_APPLICATION_TOKEN = \")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from langchain.schema import Document\n", + "from langchain.vectorstores import AstraDB\n", + "\n", + "docs = [\n", + " Document(\n", + " page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n", + " metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n", + " ),\n", + " Document(\n", + " page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n", + " metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n", + " ),\n", + " Document(\n", + " page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n", + " metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n", + " ),\n", + " Document(\n", + " page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n", + " metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n", + " ),\n", + " Document(\n", + " page_content=\"Toys come alive and have a blast doing so\",\n", + " metadata={\"year\": 1995, \"genre\": \"animated\"},\n", + " ),\n", + " Document(\n", + " page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n", + " metadata={\n", + " \"year\": 1979,\n", + " \"director\": \"Andrei Tarkovsky\",\n", + " \"genre\": \"science fiction\",\n", + " \"rating\": 9.9,\n", + " },\n", + " ),\n", + "]\n", + "\n", + "vectorstore = AstraDB.from_documents(\n", + " docs,\n", + " embeddings,\n", + " collection_name=\"astra_self_query_demo\",\n", + " api_endpoint=ASTRA_DB_API_ENDPOINT,\n", + " token=ASTRA_DB_APPLICATION_TOKEN,\n", + ")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Creating our self-querying retriever\n", + "Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "from langchain.chains.query_constructor.base import AttributeInfo\n", + "from langchain.llms import OpenAI\n", + "from langchain.retrievers.self_query.base import SelfQueryRetriever\n", + "\n", + "metadata_field_info = [\n", + " AttributeInfo(\n", + " name=\"genre\",\n", + " description=\"The genre of the movie\",\n", + " type=\"string or list[string]\",\n", + " ),\n", + " AttributeInfo(\n", + " name=\"year\",\n", + " description=\"The year the movie was released\",\n", + " type=\"integer\",\n", + " ),\n", + " AttributeInfo(\n", + " name=\"director\",\n", + " description=\"The name of the movie director\",\n", + " type=\"string\",\n", + " ),\n", + " AttributeInfo(\n", + " name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n", + " ),\n", + "]\n", + "document_content_description = \"Brief summary of a movie\"\n", + "llm = OpenAI(temperature=0)\n", + "\n", + "retriever = SelfQueryRetriever.from_llm(\n", + " llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n", + ")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Testing it out\n", + "And now we can try actually using our retriever!" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# This example only specifies a relevant query\n", + "retriever.get_relevant_documents(\"What are some movies about dinosaurs?\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# This example specifies a filter\n", + "retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# This example only specifies a query and a filter\n", + "retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women\")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# This example specifies a composite filter\n", + "retriever.get_relevant_documents(\n", + " \"What's a highly rated (above 8.5), science fiction movie ?\"\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# This example specifies a query and composite filter\n", + "retriever.get_relevant_documents(\n", + " \"What's a movie about toys after 1990 but before 2005, and is animated\"\n", + ")" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## Filter k\n", + "\n", + "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n", + "\n", + "We can do this by passing `enable_limit=True` to the constructor." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "retriever = SelfQueryRetriever.from_llm(\n", + " llm,\n", + " vectorstore,\n", + " document_content_description,\n", + " metadata_field_info,\n", + " verbose=True,\n", + " enable_limit=True,\n", + ")" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# This example only specifies a relevant query\n", + "retriever.get_relevant_documents(\"What are two movies about dinosaurs?\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "collapsed": false + }, + "source": [ + "## Cleanup\n", + "\n", + "If you want to completely delete the collection from your Astra DB instance, run this.\n", + "\n", + "_(You will lose the data you stored in it.)_" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "collapsed": false + }, + "outputs": [], + "source": [ + "vectorstore.delete_collection()" + ] + } + ], + "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": "3.11.5" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}