langchain/docs/extras/modules/data_connection/vectorstores/integrations/opensearch.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "683953b3",
   "metadata": {},
   "source": [
    "# OpenSearch\n",
    "\n",
    "> [OpenSearch](https://opensearch.org/) is a scalable, flexible, and extensible open-source software suite for search, analytics, and observability applications licensed under Apache 2.0. `OpenSearch` is a distributed search and analytics engine based on `Apache Lucene`.\n",
    "\n",
    "\n",
    "This notebook shows how to use functionality related to the `OpenSearch` database.\n",
    "\n",
    "To run, you should have an OpenSearch instance up and running: [see here for an easy Docker installation](https://hub.docker.com/r/opensearchproject/opensearch).\n",
    "\n",
    "`similarity_search` by default performs the Approximate k-NN Search which uses one of the several algorithms like lucene, nmslib, faiss recommended for\n",
    "large datasets. To perform brute force search we have other search methods known as Script Scoring and Painless Scripting.\n",
    "Check [this](https://opensearch.org/docs/latest/search-plugins/knn/index/) for more details."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "94963977-9dfc-48b7-872a-53f2947f46c6",
   "metadata": {},
   "source": [
    "## Installation\n",
    "Install the Python client."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6e606066-9386-4427-8a87-1b93f435c57e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!pip install opensearch-py"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b1fa637e-4fbf-4d5a-9188-2cad826a193e",
   "metadata": {},
   "source": [
    "We want to use OpenAIEmbeddings so we have to get the OpenAI API Key."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "28e5455e-322d-4010-9e3b-491d522ef5db",
   "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": "aac9563e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
    "from langchain.text_splitter import CharacterTextSplitter\n",
    "from langchain.vectorstores import OpenSearchVectorSearch\n",
    "from langchain.document_loaders import TextLoader"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "a3c3999a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.document_loaders import TextLoader\n",
    "\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": "markdown",
   "id": "01a9a035",
   "metadata": {},
   "source": [
    "### similarity_search using Approximate k-NN\n",
    "\n",
    "`similarity_search` using `Approximate k-NN` Search with Custom Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "803fe12b",
   "metadata": {},
   "outputs": [],
   "source": [
    "docsearch = OpenSearchVectorSearch.from_documents(\n",
    "    docs, embeddings, opensearch_url=\"http://localhost:9200\"\n",
    ")\n",
    "\n",
    "# If using the default Docker installation, use this instantiation instead:\n",
    "# docsearch = OpenSearchVectorSearch.from_documents(\n",
    "#     docs,\n",
    "#     embeddings,\n",
    "#     opensearch_url=\"https://localhost:9200\",\n",
    "#     http_auth=(\"admin\", \"admin\"),\n",
    "#     use_ssl = False,\n",
    "#     verify_certs = False,\n",
    "#     ssl_assert_hostname = False,\n",
    "#     ssl_show_warn = False,\n",
    "# )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "db3fa309",
   "metadata": {},
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "docs = docsearch.similarity_search(query, k=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c160d5bb",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(docs[0].page_content)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "96215c90",
   "metadata": {},
   "outputs": [],
   "source": [
    "docsearch = OpenSearchVectorSearch.from_documents(\n",
    "    docs,\n",
    "    embeddings,\n",
    "    opensearch_url=\"http://localhost:9200\",\n",
    "    engine=\"faiss\",\n",
    "    space_type=\"innerproduct\",\n",
    "    ef_construction=256,\n",
    "    m=48,\n",
    ")\n",
    "\n",
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "docs = docsearch.similarity_search(query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "62a7cea0",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(docs[0].page_content)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0d0cd877",
   "metadata": {},
   "source": [
    "### similarity_search using Script Scoring\n",
    "\n",
    "`similarity_search` using `Script Scoring` with Custom Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0a8e3c0e",
   "metadata": {},
   "outputs": [],
   "source": [
    "docsearch = OpenSearchVectorSearch.from_documents(\n",
    "    docs, embeddings, opensearch_url=\"http://localhost:9200\", is_appx_search=False\n",
    ")\n",
    "\n",
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "docs = docsearch.similarity_search(\n",
    "    \"What did the president say about Ketanji Brown Jackson\",\n",
    "    k=1,\n",
    "    search_type=\"script_scoring\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "92bc40db",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(docs[0].page_content)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a4af96cc",
   "metadata": {},
   "source": [
    "### similarity_search using Painless Scripting\n",
    "\n",
    "`similarity_search` using `Painless Scripting` with Custom Parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6d9f436e",
   "metadata": {},
   "outputs": [],
   "source": [
    "docsearch = OpenSearchVectorSearch.from_documents(\n",
    "    docs, embeddings, opensearch_url=\"http://localhost:9200\", is_appx_search=False\n",
    ")\n",
    "filter = {\"bool\": {\"filter\": {\"term\": {\"text\": \"smuggling\"}}}}\n",
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "docs = docsearch.similarity_search(\n",
    "    \"What did the president say about Ketanji Brown Jackson\",\n",
    "    search_type=\"painless_scripting\",\n",
    "    space_type=\"cosineSimilarity\",\n",
    "    pre_filter=filter,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8ca50bce",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(docs[0].page_content)"
   ]
  },
  {
   "cell_type": "markdown",
   "source": [
    "### Maximum marginal relevance search (MMR)\n",
    "If you’d like to look up for some similar documents, but you’d also like to receive diverse results, MMR is method you should consider. Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "query = \"What did the president say about Ketanji Brown Jackson\"\n",
    "docs = docsearch.max_marginal_relevance_search(query, k=2, fetch_k=10, lambda_param=0.5)"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "markdown",
   "id": "73264864",
   "metadata": {},
   "source": [
    "### Using a preexisting OpenSearch instance\n",
    "\n",
    "It's also possible to use a preexisting OpenSearch instance with documents that already have vectors present."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "82a23440",
   "metadata": {},
   "outputs": [],
   "source": [
    "# this is just an example, you would need to change these values to point to another opensearch instance\n",
    "docsearch = OpenSearchVectorSearch(\n",
    "    index_name=\"index-*\",\n",
    "    embedding_function=embeddings,\n",
    "    opensearch_url=\"http://localhost:9200\",\n",
    ")\n",
    "\n",
    "# you can specify custom field names to match the fields you're using to store your embedding, document text value, and metadata\n",
    "docs = docsearch.similarity_search(\n",
    "    \"Who was asking about getting lunch today?\",\n",
    "    search_type=\"script_scoring\",\n",
    "    space_type=\"cosinesimil\",\n",
    "    vector_field=\"message_embedding\",\n",
    "    text_field=\"message\",\n",
    "    metadata_field=\"message_metadata\",\n",
    ")"
   ]
  }
 ],
 "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": "3.11.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}