run-llama--llama_index/docs/examples/vector_stores/FaissIndexDemo.ipynb

{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "d7e0d5b7",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/vector_stores/FaissIndexDemo.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "307804a3-c02b-4a57-ac0d-172c30ddc851",
   "metadata": {},
   "source": [
    "# Faiss Vector Store"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "380a9254",
   "metadata": {},
   "source": [
    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d5580100",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install llama-index-vector-stores-faiss"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "375ec23d",
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install llama-index"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "f7010b1d-d1bb-4f08-9309-a328bb4ea396",
   "metadata": {},
   "source": [
    "#### Creating a Faiss Index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a1b5e530",
   "metadata": {},
   "outputs": [],
   "source": [
    "import logging\n",
    "import sys\n",
    "\n",
    "logging.basicConfig(stream=sys.stdout, level=logging.INFO)\n",
    "logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0c9f4d21-145a-401e-95ff-ccb259e8ef84",
   "metadata": {},
   "outputs": [],
   "source": [
    "import faiss\n",
    "\n",
    "# dimensions of text-ada-embedding-002\n",
    "d = 1536\n",
    "faiss_index = faiss.IndexFlatL2(d)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "8ee4473a-094f-4d0a-a825-e1213db07240",
   "metadata": {},
   "source": [
    "#### Load documents, build the VectorStoreIndex"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0a2bcc07",
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.core import (\n",
    "    SimpleDirectoryReader,\n",
    "    load_index_from_storage,\n",
    "    VectorStoreIndex,\n",
    "    StorageContext,\n",
    ")\n",
    "from llama_index.vector_stores.faiss import FaissVectorStore\n",
    "from IPython.display import Markdown, display"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "9096dae7",
   "metadata": {},
   "source": [
    "Download Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "335923ad",
   "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'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "68cbd239-880e-41a3-98d8-dbb3fab55431",
   "metadata": {},
   "outputs": [],
   "source": [
    "# load documents\n",
    "documents = SimpleDirectoryReader(\"./data/paul_graham/\").load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ba1558b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "vector_store = FaissVectorStore(faiss_index=faiss_index)\n",
    "storage_context = StorageContext.from_defaults(vector_store=vector_store)\n",
    "index = VectorStoreIndex.from_documents(\n",
    "    documents, storage_context=storage_context\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c36cadc1",
   "metadata": {},
   "outputs": [],
   "source": [
    "# save index to disk\n",
    "index.storage_context.persist()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "70b372a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# load index from disk\n",
    "vector_store = FaissVectorStore.from_persist_dir(\"./storage\")\n",
    "storage_context = StorageContext.from_defaults(\n",
    "    vector_store=vector_store, persist_dir=\"./storage\"\n",
    ")\n",
    "index = load_index_from_storage(storage_context=storage_context)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "id": "04304299-fc3e-40a0-8600-f50c3292767e",
   "metadata": {},
   "source": [
    "#### Query Index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "35369eda",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set Logging to DEBUG for more detailed outputs\n",
    "query_engine = index.as_query_engine()\n",
    "response = query_engine.query(\"What did the author do growing up?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bedbb693-725f-478f-be26-fa7180ea38b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "display(Markdown(f\"<b>{response}</b>\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99212d33",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set Logging to DEBUG for more detailed outputs\n",
    "query_engine = index.as_query_engine()\n",
    "response = query_engine.query(\n",
    "    \"What did the author do after his time at Y Combinator?\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "1a720ad6",
   "metadata": {},
   "outputs": [],
   "source": [
    "display(Markdown(f\"<b>{response}</b>\"))"
   ]
  }
 ],
 "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}