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

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "4e4f9a0f",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/run-llama/llama_index/blob/main/docs/examples/vector_stores/BagelAutoRetriever.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "307804a3-c02b-4a57-ac0d-172c30ddc851",
   "metadata": {},
   "source": [
    "# Bagel Vector Store"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "15119a5b",
   "metadata": {},
   "source": [
    "If you're opening this Notebook on colab, you will probably need to install LlamaIndex 🦙."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6d497859",
   "metadata": {},
   "outputs": [],
   "source": [
    "%pip install llama-index-vector-stores-bagel\n",
    "%pip install llama-index\n",
    "%pip install bagelML"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d48af8e1",
   "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": "bf49ac18",
   "metadata": {},
   "outputs": [],
   "source": [
    "# set up OpenAI\n",
    "import os\n",
    "import getpass\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
    "import openai\n",
    "\n",
    "openai.api_key = os.environ[\"OPENAI_API_KEY\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "465aef6e",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "# Set environment variable\n",
    "os.environ[\"BAGEL_API_KEY\"] = getpass.getpass(\"Bagel API Key:\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0ce3143d-198c-4dd2-8e5a-c5cdf94f017a",
   "metadata": {},
   "outputs": [],
   "source": [
    "import bagel\n",
    "from bagel import Settings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "667f3cb3-ce18-48d5-b9aa-bfc1a1f0f0f6",
   "metadata": {},
   "outputs": [],
   "source": [
    "server_settings = Settings(\n",
    "    bagel_api_impl=\"rest\", bagel_server_host=\"api.bageldb.ai\"\n",
    ")\n",
    "\n",
    "client = bagel.Client(server_settings)\n",
    "\n",
    "collection = client.get_or_create_cluster(\n",
    "    \"testing_embeddings_3\", embedding_model=\"custom\", dimension=1536\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0a2bcc07",
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.core import VectorStoreIndex, StorageContext\n",
    "from llama_index.vector_stores.bagel import BagelVectorStore"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "68cbd239-880e-41a3-98d8-dbb3fab55431",
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.core.schema import TextNode\n",
    "\n",
    "nodes = [\n",
    "    TextNode(\n",
    "        text=(\n",
    "            \"Michael Jordan is a retired professional basketball player,\"\n",
    "            \" widely regarded as one of the greatest basketball players of all\"\n",
    "            \" time.\"\n",
    "        ),\n",
    "        metadata={\n",
    "            \"category\": \"Sports\",\n",
    "            \"country\": \"United States\",\n",
    "        },\n",
    "    ),\n",
    "    TextNode(\n",
    "        text=(\n",
    "            \"Angelina Jolie is an American actress, filmmaker, and\"\n",
    "            \" humanitarian. She has received numerous awards for her acting\"\n",
    "            \" and is known for her philanthropic work.\"\n",
    "        ),\n",
    "        metadata={\n",
    "            \"category\": \"Entertainment\",\n",
    "            \"country\": \"United States\",\n",
    "        },\n",
    "    ),\n",
    "    TextNode(\n",
    "        text=(\n",
    "            \"Elon Musk is a business magnate, industrial designer, and\"\n",
    "            \" engineer. He is the founder, CEO, and lead designer of SpaceX,\"\n",
    "            \" Tesla, Inc., Neuralink, and The Boring Company.\"\n",
    "        ),\n",
    "        metadata={\n",
    "            \"category\": \"Business\",\n",
    "            \"country\": \"United States\",\n",
    "        },\n",
    "    ),\n",
    "    TextNode(\n",
    "        text=(\n",
    "            \"Rihanna is a Barbadian singer, actress, and businesswoman. She\"\n",
    "            \" has achieved significant success in the music industry and is\"\n",
    "            \" known for her versatile musical style.\"\n",
    "        ),\n",
    "        metadata={\n",
    "            \"category\": \"Music\",\n",
    "            \"country\": \"Barbados\",\n",
    "        },\n",
    "    ),\n",
    "    TextNode(\n",
    "        text=(\n",
    "            \"Cristiano Ronaldo is a Portuguese professional footballer who is\"\n",
    "            \" considered one of the greatest football players of all time. He\"\n",
    "            \" has won numerous awards and set multiple records during his\"\n",
    "            \" career.\"\n",
    "        ),\n",
    "        metadata={\n",
    "            \"category\": \"Sports\",\n",
    "            \"country\": \"Portugal\",\n",
    "        },\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ba1558b3",
   "metadata": {},
   "outputs": [],
   "source": [
    "vector_store = BagelVectorStore(collection=collection)\n",
    "storage_context = StorageContext.from_defaults(vector_store=vector_store)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "35369eda",
   "metadata": {},
   "outputs": [],
   "source": [
    "index = VectorStoreIndex(nodes, storage_context=storage_context)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bedbb693-725f-478f-be26-fa7180ea38b2",
   "metadata": {},
   "outputs": [],
   "source": [
    "from llama_index.core.retrievers import VectorIndexAutoRetriever\n",
    "from llama_index.core.vector_stores import MetadataInfo, VectorStoreInfo\n",
    "\n",
    "\n",
    "vector_store_info = VectorStoreInfo(\n",
    "    content_info=\"brief biography of celebrities\",\n",
    "    metadata_info=[\n",
    "        MetadataInfo(\n",
    "            name=\"category\",\n",
    "            type=\"str\",\n",
    "            description=(\n",
    "                \"Category of the celebrity, one of [Sports, Entertainment,\"\n",
    "                \" Business, Music]\"\n",
    "            ),\n",
    "        ),\n",
    "        MetadataInfo(\n",
    "            name=\"country\",\n",
    "            type=\"str\",\n",
    "            description=(\n",
    "                \"Country of the celebrity, one of [United States, Barbados,\"\n",
    "                \" Portugal]\"\n",
    "            ),\n",
    "        ),\n",
    "    ],\n",
    ")\n",
    "retriever = VectorIndexAutoRetriever(\n",
    "    index, vector_store_info=vector_store_info\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eeb18e9c",
   "metadata": {},
   "outputs": [],
   "source": [
    "retriever.retrieve(\"celebrity\")"
   ]
  }
 ],
 "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"
  },
  "vscode": {
   "interpreter": {
    "hash": "0ac390d292208ca2380c85f5bce7ded36a7a25670a97c40b8009630eb36cb06e"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}