langchain/docs/docs/integrations/vectorstores/jaguar.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "671e9ec1-fa00-4c92-a2fb-ceb142168ea9",
   "metadata": {},
   "source": [
    "# Jaguar Vector Database\n",
    "\n",
    "1. It is a distributed vector database\n",
    "2. The “ZeroMove” feature of JaguarDB enables instant horizontal scalability\n",
    "3. Multimodal: embeddings, text, images, videos, PDFs, audio, time series, and geospatial\n",
    "4. All-masters: allows both parallel reads and writes\n",
    "5. Anomaly detection capabilities\n",
    "6. RAG support: combines LLM with proprietary and real-time data\n",
    "7. Shared metadata: sharing of metadata across multiple vector indexes\n",
    "8. Distance metrics: Euclidean, Cosine, InnerProduct, Manhatten, Chebyshev, Hamming, Jeccard, Minkowski"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1a87dc28-1344-4003-b31a-13e4cb71bf48",
   "metadata": {},
   "source": [
    "## Prerequisites\n",
    "\n",
    "There are two requirements for running the examples in this file.\n",
    "1. You must install and set up the JaguarDB server and its HTTP gateway server.\n",
    "   Please refer to the instructions in:\n",
    "   [www.jaguardb.com](http://www.jaguardb.com)\n",
    "   For quick setup in docker environment:\n",
    "   docker pull jaguardb/jaguardb_with_http\n",
    "   docker run -d -p 8888:8888 -p 8080:8080 --name jaguardb_with_http  jaguardb/jaguardb_with_http\n",
    "\n",
    "2. You must install the http client package for JaguarDB:\n",
    "   ```\n",
    "       pip install -U jaguardb-http-client\n",
    "   ```\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c7d56993-4809-4e42-a409-94d3a7305ad8",
   "metadata": {},
   "source": [
    "## RAG With Langchain\n",
    "\n",
    "This section demonstrates chatting with LLM together with Jaguar in the langchain software stack.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d62c2393-5c7c-4bb6-8367-c4389fa36a4e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.chains import RetrievalQAWithSourcesChain\n",
    "from langchain_community.document_loaders import TextLoader\n",
    "from langchain_community.vectorstores.jaguar import Jaguar\n",
    "from langchain_core.output_parsers import StrOutputParser\n",
    "from langchain_core.prompts import ChatPromptTemplate\n",
    "from langchain_core.runnables import RunnablePassthrough\n",
    "from langchain_openai import ChatOpenAI, OpenAI, OpenAIEmbeddings\n",
    "from langchain_text_splitters import CharacterTextSplitter\n",
    "\n",
    "\"\"\" \n",
    "Load a text file into a set of documents \n",
    "\"\"\"\n",
    "loader = TextLoader(\"../../modules/state_of_the_union.txt\")\n",
    "documents = loader.load()\n",
    "text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=300)\n",
    "docs = text_splitter.split_documents(documents)\n",
    "\n",
    "\"\"\"\n",
    "Instantiate a Jaguar vector store\n",
    "\"\"\"\n",
    "### Jaguar HTTP endpoint\n",
    "url = \"http://192.168.5.88:8080/fwww/\"\n",
    "\n",
    "### Use OpenAI embedding model\n",
    "embeddings = OpenAIEmbeddings()\n",
    "\n",
    "### Pod is a database for vectors\n",
    "pod = \"vdb\"\n",
    "\n",
    "### Vector store name\n",
    "store = \"langchain_rag_store\"\n",
    "\n",
    "### Vector index name\n",
    "vector_index = \"v\"\n",
    "\n",
    "### Type of the vector index\n",
    "# cosine: distance metric\n",
    "# fraction: embedding vectors are decimal numbers\n",
    "# float: values stored with floating-point numbers\n",
    "vector_type = \"cosine_fraction_float\"\n",
    "\n",
    "### Dimension of each embedding vector\n",
    "vector_dimension = 1536\n",
    "\n",
    "### Instantiate a Jaguar store object\n",
    "vectorstore = Jaguar(\n",
    "    pod, store, vector_index, vector_type, vector_dimension, url, embeddings\n",
    ")\n",
    "\n",
    "\"\"\"\n",
    "Login must be performed to authorize the client.\n",
    "The environment variable JAGUAR_API_KEY or file $HOME/.jagrc\n",
    "should contain the API key for accessing JaguarDB servers.\n",
    "\"\"\"\n",
    "vectorstore.login()\n",
    "\n",
    "\n",
    "\"\"\"\n",
    "Create vector store on the JaguarDB database server.\n",
    "This should be done only once.\n",
    "\"\"\"\n",
    "# Extra metadata fields for the vector store\n",
    "metadata = \"category char(16)\"\n",
    "\n",
    "# Number of characters for the text field of the store\n",
    "text_size = 4096\n",
    "\n",
    "#  Create a vector store on the server\n",
    "vectorstore.create(metadata, text_size)\n",
    "\n",
    "\"\"\"\n",
    "Add the texts from the text splitter to our vectorstore\n",
    "\"\"\"\n",
    "vectorstore.add_documents(docs)\n",
    "# or tag the documents:\n",
    "# vectorstore.add_documents(more_docs, text_tag=\"tags to these documents\")\n",
    "\n",
    "\"\"\" Get the retriever object \"\"\"\n",
    "retriever = vectorstore.as_retriever()\n",
    "# retriever = vectorstore.as_retriever(search_kwargs={\"where\": \"m1='123' and m2='abc'\"})\n",
    "\n",
    "template = \"\"\"You are an assistant for question-answering tasks. Use the following pieces of retrieved context to answer the question. If you don't know the answer, just say that you don't know. Use three sentences maximum and keep the answer concise.\n",
    "Question: {question}\n",
    "Context: {context}\n",
    "Answer:\n",
    "\"\"\"\n",
    "prompt = ChatPromptTemplate.from_template(template)\n",
    "\n",
    "\"\"\" Obtain a Large Language Model \"\"\"\n",
    "LLM = ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0)\n",
    "\n",
    "\"\"\" Create a chain for the RAG flow \"\"\"\n",
    "rag_chain = (\n",
    "    {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
    "    | prompt\n",
    "    | LLM\n",
    "    | StrOutputParser()\n",
    ")\n",
    "\n",
    "resp = rag_chain.invoke(\"What did the president say about Justice Breyer?\")\n",
    "print(resp)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "11178867-d143-4a10-93bf-278f5f10dc1a",
   "metadata": {},
   "source": [
    "## Interaction With Jaguar Vector Store\n",
    "\n",
    "Users can interact directly with the Jaguar vector store for similarity search and anomaly detection.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c9a53cb5-e298-4125-9ace-0d851198869a",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.vectorstores.jaguar import Jaguar\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "\n",
    "# Instantiate a Jaguar vector store object\n",
    "url = \"http://192.168.3.88:8080/fwww/\"\n",
    "pod = \"vdb\"\n",
    "store = \"langchain_test_store\"\n",
    "vector_index = \"v\"\n",
    "vector_type = \"cosine_fraction_float\"\n",
    "vector_dimension = 10\n",
    "embeddings = OpenAIEmbeddings()\n",
    "vectorstore = Jaguar(\n",
    "    pod, store, vector_index, vector_type, vector_dimension, url, embeddings\n",
    ")\n",
    "\n",
    "# Login for authorization\n",
    "vectorstore.login()\n",
    "\n",
    "# Create the vector store with two metadata fields\n",
    "# This needs to be run only once.\n",
    "metadata_str = \"author char(32), category char(16)\"\n",
    "vectorstore.create(metadata_str, 1024)\n",
    "\n",
    "# Add a list of texts\n",
    "texts = [\"foo\", \"bar\", \"baz\"]\n",
    "metadatas = [\n",
    "    {\"author\": \"Adam\", \"category\": \"Music\"},\n",
    "    {\"author\": \"Eve\", \"category\": \"Music\"},\n",
    "    {\"author\": \"John\", \"category\": \"History\"},\n",
    "]\n",
    "ids = vectorstore.add_texts(texts=texts, metadatas=metadatas)\n",
    "\n",
    "#  Search similar text\n",
    "output = vectorstore.similarity_search(\n",
    "    query=\"foo\",\n",
    "    k=1,\n",
    "    metadatas=[\"author\", \"category\"],\n",
    ")\n",
    "assert output[0].page_content == \"foo\"\n",
    "assert output[0].metadata[\"author\"] == \"Adam\"\n",
    "assert output[0].metadata[\"category\"] == \"Music\"\n",
    "assert len(output) == 1\n",
    "\n",
    "# Search with filtering (where)\n",
    "where = \"author='Eve'\"\n",
    "output = vectorstore.similarity_search(\n",
    "    query=\"foo\",\n",
    "    k=3,\n",
    "    fetch_k=9,\n",
    "    where=where,\n",
    "    metadatas=[\"author\", \"category\"],\n",
    ")\n",
    "assert output[0].page_content == \"bar\"\n",
    "assert output[0].metadata[\"author\"] == \"Eve\"\n",
    "assert output[0].metadata[\"category\"] == \"Music\"\n",
    "assert len(output) == 1\n",
    "\n",
    "# Anomaly detection\n",
    "result = vectorstore.is_anomalous(\n",
    "    query=\"dogs can jump high\",\n",
    ")\n",
    "assert result is False\n",
    "\n",
    "# Remove all data in the store\n",
    "vectorstore.clear()\n",
    "assert vectorstore.count() == 0\n",
    "\n",
    "# Remove the store completely\n",
    "vectorstore.drop()\n",
    "\n",
    "# Logout\n",
    "vectorstore.logout()"
   ]
  }
 ],
 "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}