langchain/docs/modules/indexes/vectorstores/examples/weaviate.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "683953b3",
   "metadata": {},
   "source": [
    "# Weaviate\n",
    "\n",
    ">[Weaviate](https://weaviate.io/) is an open-source vector database. It allows you to store data objects and vector embeddings from your favorite ML-models, and scale seamlessly into billions of data objects.\n",
    "\n",
    "This notebook shows how to use functionality related to the `Weaviate`vector database.\n",
    "\n",
    "See the `Weaviate` [installation instructions](https://weaviate.io/developers/weaviate/installation)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e9ab167c-fffc-4d30-b1c1-37cc1b641698",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!pip install weaviate-client"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6b34828d-e627-4d85-aabd-eeb15d9f4b00",
   "metadata": {},
   "source": [
    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "37697b9f-fbb2-430e-b95d-28d6eb83486d",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import getpass\n",
    "\n",
    "os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "fea2dbae-a609-4458-a05f-f1c8e1f37c6f",
   "metadata": {},
   "outputs": [],
   "source": [
    "WEAVIATE_URL = getpass.getpass('WEAVIATE_URL:')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "53b7ce2d-3c09-4d1c-b66b-5769ce6746ae",
   "metadata": {},
   "outputs": [],
   "source": [
    "os.environ['WEAVIATE_API_KEY'] = getpass.getpass('WEAVIATE_API_KEY:')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "aac9563e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "from langchain.text_splitter import CharacterTextSplitter\n",
    "from langchain.vectorstores import Weaviate\n",
    "from langchain.document_loaders import TextLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a3c3999a",
   "metadata": {},
   "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()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5888dcc7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import weaviate\n",
    "import os\n",
    "\n",
    "WEAVIATE_URL = \"\"\n",
    "client = weaviate.Client(\n",
    "    url=WEAVIATE_URL,\n",
    "    additional_headers={\n",
    "        'X-OpenAI-Api-Key': os.environ[\"OPENAI_API_KEY\"]\n",
    "    }\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f004e8ee",
   "metadata": {},
   "outputs": [],
   "source": [
    "client.schema.delete_all()\n",
    "client.schema.get()\n",
    "schema = {\n",
    "    \"classes\": [\n",
    "        {\n",
    "            \"class\": \"Paragraph\",\n",
    "            \"description\": \"A written paragraph\",\n",
    "            \"vectorizer\": \"text2vec-openai\",\n",
    "              \"moduleConfig\": {\n",
    "                \"text2vec-openai\": {\n",
    "                  \"model\": \"ada\",\n",
    "                  \"modelVersion\": \"002\",\n",
    "                  \"type\": \"text\"\n",
    "                }\n",
    "              },\n",
    "            \"properties\": [\n",
    "                {\n",
    "                    \"dataType\": [\"text\"],\n",
    "                    \"description\": \"The content of the paragraph\",\n",
    "                    \"moduleConfig\": {\n",
    "                        \"text2vec-openai\": {\n",
    "                          \"skip\": False,\n",
    "                          \"vectorizePropertyName\": False\n",
    "                        }\n",
    "                      },\n",
    "                    \"name\": \"content\",\n",
    "                },\n",
    "            ],\n",
    "        },\n",
    "    ]\n",
    "}\n",
    "\n",
    "client.schema.create(schema)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ef6d5d04",
   "metadata": {},
   "outputs": [],
   "source": [
    "vectorstore = Weaviate(client, \"Paragraph\", \"content\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "06e8c1ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "docs = vectorstore.similarity_search(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "38b86be6",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(docs[0].page_content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a359ed74",
   "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": "3.10.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}