{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "40165f86", "metadata": {}, "source": [ "\"Open" ] }, { "attachments": {}, "cell_type": "markdown", "id": "db0855d0", "metadata": {}, "source": [ "# Supabase Vector Store\n", "In this notebook we are going to show how to use [Vecs](https://supabase.github.io/vecs/) to perform vector searches in LlamaIndex. \n", "See [this guide](https://supabase.github.io/vecs/hosting/) for instructions on hosting a database on Supabase " ] }, { "attachments": {}, "cell_type": "markdown", "id": "4c86a953", "metadata": {}, "source": [ "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙." ] }, { "cell_type": "code", "execution_count": null, "id": "3c0f557d", "metadata": {}, "outputs": [], "source": [ "%pip install llama-index-vector-stores-supabase" ] }, { "cell_type": "code", "execution_count": null, "id": "9144d757", "metadata": {}, "outputs": [], "source": [ "!pip install llama-index" ] }, { "cell_type": "code", "execution_count": null, "id": "c2d1c538", "metadata": {}, "outputs": [], "source": [ "import logging\n", "import sys\n", "\n", "# Uncomment to see debug logs\n", "# logging.basicConfig(stream=sys.stdout, level=logging.DEBUG)\n", "# logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))\n", "\n", "from llama_index.core import SimpleDirectoryReader, Document, StorageContext\n", "from llama_index.core import VectorStoreIndex\n", "from llama_index.vector_stores.supabase import SupabaseVectorStore\n", "import textwrap" ] }, { "attachments": {}, "cell_type": "markdown", "id": "26c71b6d", "metadata": {}, "source": [ "### Setup OpenAI\n", "The first step is to configure the OpenAI key. It will be used to created embeddings for the documents loaded into the index" ] }, { "cell_type": "code", "execution_count": null, "id": "67b86621", "metadata": {}, "outputs": [], "source": [ "import os\n", "\n", "os.environ[\"OPENAI_API_KEY\"] = \"[your_openai_api_key]\"" ] }, { "attachments": {}, "cell_type": "markdown", "id": "08889e66", "metadata": {}, "source": [ "Download Data" ] }, { "cell_type": "code", "execution_count": null, "id": "8fa0c69c", "metadata": {}, "outputs": [], "source": [ "!mkdir -p 'data/paul_graham/'\n", "!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'" ] }, { "attachments": {}, "cell_type": "markdown", "id": "f7010b1d-d1bb-4f08-9309-a328bb4ea396", "metadata": {}, "source": [ "### Loading documents\n", "Load the documents stored in the `./data/paul_graham/` using the SimpleDirectoryReader" ] }, { "cell_type": "code", "execution_count": null, "id": "c154dd4b", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Document ID: fb056993-ee9e-4463-80b4-32cf9509d1d8 Document Hash: 77ae91ab542f3abb308c4d7c77c9bc4c9ad0ccd63144802b7cbe7e1bb3a4094e\n" ] } ], "source": [ "documents = SimpleDirectoryReader(\"./data/paul_graham/\").load_data()\n", "print(\n", " \"Document ID:\",\n", " documents[0].doc_id,\n", " \"Document Hash:\",\n", " documents[0].doc_hash,\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "id": "c0232fd1", "metadata": {}, "source": [ "### Create an index backed by Supabase's vector store. \n", "This will work with all Postgres providers that support pgvector.\n", "If the collection does not exist, we will attempt to create a new collection \n", "\n", "> Note: you need to pass in the embedding dimension if not using OpenAI's text-embedding-ada-002, e.g. `vector_store = SupabaseVectorStore(..., dimension=...)`" ] }, { "cell_type": "code", "execution_count": null, "id": "8731da62", "metadata": {}, "outputs": [], "source": [ "vector_store = SupabaseVectorStore(\n", " postgres_connection_string=(\n", " \"postgresql://:@:/\"\n", " ),\n", " collection_name=\"base_demo\",\n", ")\n", "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n", "index = VectorStoreIndex.from_documents(\n", " documents, storage_context=storage_context\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "id": "8ee4473a-094f-4d0a-a825-e1213db07240", "metadata": {}, "source": [ "### Query the index\n", "We can now ask questions using our index." ] }, { "cell_type": "code", "execution_count": null, "id": "0a2bcc07", "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/Users/suo/miniconda3/envs/llama/lib/python3.9/site-packages/vecs/collection.py:182: UserWarning: Query does not have a covering index for cosine_distance. See Collection.create_index\n", " warnings.warn(\n" ] } ], "source": [ "query_engine = index.as_query_engine()\n", "response = query_engine.query(\"Who is the author?\")" ] }, { "cell_type": "code", "execution_count": null, "id": "8cf55bf7", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " The author of this text is Paul Graham.\n" ] } ], "source": [ "print(textwrap.fill(str(response), 100))" ] }, { "cell_type": "code", "execution_count": null, "id": "68cbd239-880e-41a3-98d8-dbb3fab55431", "metadata": {}, "outputs": [], "source": [ "response = query_engine.query(\"What did the author do growing up?\")" ] }, { "cell_type": "code", "execution_count": null, "id": "fdf5287f", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " The author grew up writing essays, learning Italian, exploring Florence, painting people, working\n", "with computers, attending RISD, living in a rent-stabilized apartment, building an online store\n", "builder, editing Lisp expressions, publishing essays online, writing essays, painting still life,\n", "working on spam filters, cooking for groups, and buying a building in Cambridge.\n" ] } ], "source": [ "print(textwrap.fill(str(response), 100))" ] }, { "attachments": {}, "cell_type": "markdown", "id": "c9407557", "metadata": {}, "source": [ "## Using metadata filters" ] }, { "cell_type": "code", "execution_count": null, "id": "39cae198", "metadata": {}, "outputs": [], "source": [ "from llama_index.core.schema import TextNode\n", "\n", "nodes = [\n", " TextNode(\n", " **{\n", " \"text\": \"The Shawshank Redemption\",\n", " \"metadata\": {\n", " \"author\": \"Stephen King\",\n", " \"theme\": \"Friendship\",\n", " },\n", " }\n", " ),\n", " TextNode(\n", " **{\n", " \"text\": \"The Godfather\",\n", " \"metadata\": {\n", " \"director\": \"Francis Ford Coppola\",\n", " \"theme\": \"Mafia\",\n", " },\n", " }\n", " ),\n", " TextNode(\n", " **{\n", " \"text\": \"Inception\",\n", " \"metadata\": {\n", " \"director\": \"Christopher Nolan\",\n", " },\n", " }\n", " ),\n", "]" ] }, { "cell_type": "code", "execution_count": null, "id": "5d58639c", "metadata": {}, "outputs": [], "source": [ "vector_store = SupabaseVectorStore(\n", " postgres_connection_string=(\n", " \"postgresql://:@:/\"\n", " ),\n", " collection_name=\"metadata_filters_demo\",\n", ")\n", "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n", "index = VectorStoreIndex(nodes, storage_context=storage_context)" ] }, { "attachments": {}, "cell_type": "markdown", "id": "9fb0618b", "metadata": {}, "source": [ "Define metadata filters" ] }, { "cell_type": "code", "execution_count": null, "id": "17b2ac01", "metadata": {}, "outputs": [], "source": [ "from llama_index.core.vector_stores import ExactMatchFilter, MetadataFilters\n", "\n", "filters = MetadataFilters(\n", " filters=[ExactMatchFilter(key=\"theme\", value=\"Mafia\")]\n", ")" ] }, { "attachments": {}, "cell_type": "markdown", "id": "d875f6b5", "metadata": {}, "source": [ "Retrieve from vector store with filters" ] }, { "cell_type": "code", "execution_count": null, "id": "79afe7f1", "metadata": {}, "outputs": [ { "data": { "text/plain": [ "[NodeWithScore(node=Node(text='The Godfather', doc_id='f837ed85-aacb-4552-b88a-7c114a5be15d', embedding=None, doc_hash='f8ee912e238a39fe2e620fb232fa27ade1e7f7c819b6d5b9cb26f3dddc75b6c0', extra_info={'theme': 'Mafia', 'director': 'Francis Ford Coppola'}, node_info={'_node_type': '1'}, relationships={}), score=0.20671339734643313)]" ] }, "execution_count": null, "metadata": {}, "output_type": "execute_result" } ], "source": [ "retriever = index.as_retriever(filters=filters)\n", "retriever.retrieve(\"What is inception about?\")" ] } ], "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" }, "vscode": { "interpreter": { "hash": "38a327e7bea9478b86ff5be1afa4768c851785146a2113bbf2930d1c8dbd310f" } } }, "nbformat": 4, "nbformat_minor": 5 }