langchain/docs/docs/integrations/vectorstores/typesense.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Typesense\n",
    "\n",
    "> [Typesense](https://typesense.org) is an open-source, in-memory search engine, that you can either [self-host](https://typesense.org/docs/guide/install-typesense#option-2-local-machine-self-hosting) or run on [Typesense Cloud](https://cloud.typesense.org/).\n",
    ">\n",
    "> Typesense focuses on performance by storing the entire index in RAM (with a backup on disk) and also focuses on providing an out-of-the-box developer experience by simplifying available options and setting good defaults.\n",
    ">\n",
    "> It also lets you combine attribute-based filtering together with vector queries, to fetch the most relevant documents."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This notebook shows you how to use Typesense as your VectorStore."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's first install our dependencies:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "%pip install --upgrade --quiet  typesense openapi-schema-pydantic langchain-openai tiktoken"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-23T22:48:02.968822Z",
     "start_time": "2023-05-23T22:47:48.574094Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "import getpass\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-23T22:50:34.775893Z",
     "start_time": "2023-05-23T22:50:34.771889Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from langchain_community.document_loaders import TextLoader\n",
    "from langchain_community.vectorstores import Typesense\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "from langchain_text_splitters import CharacterTextSplitter"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's import our test dataset:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-05-23T22:56:19.093489Z",
     "start_time": "2023-05-23T22:56:19.089Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "loader = TextLoader(\"../../modules/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,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "docsearch = Typesense.from_documents(\n",
    "    docs,\n",
    "    embeddings,\n",
    "    typesense_client_params={\n",
    "        \"host\": \"localhost\",  # Use xxx.a1.typesense.net for Typesense Cloud\n",
    "        \"port\": \"8108\",  # Use 443 for Typesense Cloud\n",
    "        \"protocol\": \"http\",  # Use https for Typesense Cloud\n",
    "        \"typesense_api_key\": \"xyz\",\n",
    "        \"typesense_collection_name\": \"lang-chain\",\n",
    "    },\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Similarity Search"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "found_docs = docsearch.similarity_search(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "print(found_docs[0].page_content)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Typesense as a Retriever\n",
    "\n",
    "Typesense, as all the other vector stores, is a LangChain Retriever, by using cosine similarity."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "retriever = docsearch.as_retriever()\n",
    "retriever"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "retriever.invoke(query)[0]"
   ]
  }
 ],
 "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": 4
}