{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "1ad7250ddd99fba9",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "# Databricks Vector Search\n",
    "\n",
    ">[Databricks Vector Search](https://docs.databricks.com/en/generative-ai/vector-search.html) is a serverless similarity search engine that allows you to store a vector representation of your data, including metadata, in a vector database. With Vector Search, you can create auto-updating vector search indexes from Delta tables managed by Unity Catalog and query them with a simple API to return the most similar vectors.\n",
    "\n",
    "\n",
    "In the walkthrough, we'll demo the `SelfQueryRetriever` with a Databricks Vector Search."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "209652d4ab38ba7f",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## create Databricks vector store index\n",
    "First we'll want to create a databricks vector store index and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
    "\n",
    "**Note:** The self-query retriever requires you to have `lark` installed (`pip install lark`) along with integration-specific requirements."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "b68da3303b0625f2",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:39:28.887634Z",
     "start_time": "2024-03-29T02:39:27.277978Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    }
   ],
   "source": [
    "%pip install --upgrade --quiet  langchain-core databricks-vectorsearch langchain-openai tiktoken"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a1113af6008f3f3d",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "c243e15bcf72d539",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:40:59.788206Z",
     "start_time": "2024-03-29T02:40:59.783798Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdin",
     "output_type": "stream",
     "text": [
      "OpenAI API Key: ········\n",
      "Databricks host: ········\n",
      "Databricks token: ········\n"
     ]
    }
   ],
   "source": [
    "import getpass\n",
    "import os\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
    "databricks_host = getpass.getpass(\"Databricks host:\")\n",
    "databricks_token = getpass.getpass(\"Databricks token:\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "fd0c70c0be7d7130",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:42:28.467682Z",
     "start_time": "2024-03-29T02:42:21.255335Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[NOTICE] Using a Personal Authentication Token (PAT). Recommended for development only. For improved performance, please use Service Principal based authentication. To disable this message, pass disable_notice=True to VectorSearchClient().\n"
     ]
    }
   ],
   "source": [
    "from databricks.vector_search.client import VectorSearchClient\n",
    "from langchain_openai import OpenAIEmbeddings\n",
    "\n",
    "embeddings = OpenAIEmbeddings()\n",
    "emb_dim = len(embeddings.embed_query(\"hello\"))\n",
    "\n",
    "vector_search_endpoint_name = \"vector_search_demo_endpoint\"\n",
    "\n",
    "\n",
    "vsc = VectorSearchClient(\n",
    "    workspace_url=databricks_host, personal_access_token=databricks_token\n",
    ")\n",
    "vsc.create_endpoint(name=vector_search_endpoint_name, endpoint_type=\"STANDARD\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "3ead3943-7dd6-448c-bead-01157a000221",
   "metadata": {},
   "outputs": [],
   "source": [
    "index_name = \"udhay_demo.10x.demo_index\"\n",
    "\n",
    "index = vsc.create_direct_access_index(\n",
    "    endpoint_name=vector_search_endpoint_name,\n",
    "    index_name=index_name,\n",
    "    primary_key=\"id\",\n",
    "    embedding_dimension=emb_dim,\n",
    "    embedding_vector_column=\"text_vector\",\n",
    "    schema={\n",
    "        \"id\": \"string\",\n",
    "        \"page_content\": \"string\",\n",
    "        \"year\": \"int\",\n",
    "        \"rating\": \"float\",\n",
    "        \"genre\": \"string\",\n",
    "        \"text_vector\": \"array<float>\",\n",
    "    },\n",
    ")\n",
    "\n",
    "index.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "3e62fc39-51d9-4757-a449-f543638b3cd1",
   "metadata": {},
   "outputs": [],
   "source": [
    "index = vsc.get_index(endpoint_name=vector_search_endpoint_name, index_name=index_name)\n",
    "\n",
    "index.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "13863677-8123-4b36-82bc-2c28ee2a90fb",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_core.documents import Document\n",
    "\n",
    "docs = [\n",
    "    Document(\n",
    "        page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
    "        metadata={\"id\": 1, \"year\": 1993, \"rating\": 7.7, \"genre\": \"action\"},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
    "        metadata={\"id\": 2, \"year\": 2010, \"genre\": \"thriller\", \"rating\": 8.2},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
    "        metadata={\"id\": 3, \"year\": 2019, \"rating\": 8.3, \"genre\": \"drama\"},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
    "        metadata={\"id\": 4, \"year\": 1979, \"rating\": 9.9, \"genre\": \"science fiction\"},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
    "        metadata={\"id\": 5, \"year\": 2006, \"genre\": \"thriller\", \"rating\": 9.0},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"Toys come alive and have a blast doing so\",\n",
    "        metadata={\"id\": 6, \"year\": 1995, \"genre\": \"animated\", \"rating\": 9.3},\n",
    "    ),\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "6fdc8f55-5b4c-4506-97ac-59d9b9ef8ffc",
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain_community.vectorstores import DatabricksVectorSearch\n",
    "\n",
    "vector_store = DatabricksVectorSearch(\n",
    "    index,\n",
    "    text_column=\"page_content\",\n",
    "    embedding=embeddings,\n",
    "    columns=[\"year\", \"rating\", \"genre\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "826375af-3fd7-4d41-9c7b-c273653c46b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "vector_store.add_documents(docs)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3810b731a981a957",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Creating our self-querying retriever\n",
    "Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "7095b68ea997468c",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:42:37.901230Z",
     "start_time": "2024-03-29T02:42:36.836827Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from langchain.chains.query_constructor.base import AttributeInfo\n",
    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
    "from langchain_openai import OpenAI\n",
    "\n",
    "metadata_field_info = [\n",
    "    AttributeInfo(\n",
    "        name=\"genre\",\n",
    "        description=\"The genre of the movie\",\n",
    "        type=\"string\",\n",
    "    ),\n",
    "    AttributeInfo(\n",
    "        name=\"year\",\n",
    "        description=\"The year the movie was released\",\n",
    "        type=\"integer\",\n",
    "    ),\n",
    "    AttributeInfo(\n",
    "        name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
    "    ),\n",
    "]\n",
    "document_content_description = \"Brief summary of a movie\"\n",
    "llm = OpenAI(temperature=0)\n",
    "retriever = SelfQueryRetriever.from_llm(\n",
    "    llm, vector_store, document_content_description, metadata_field_info, verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65ff2054be9d5236",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Test it out\n",
    "And now we can try actually using our retriever!\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "267e2a68f26505b1",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:42:51.526470Z",
     "start_time": "2024-03-29T02:42:48.328191Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993.0, 'rating': 7.7, 'genre': 'action', 'id': 1.0}),\n",
       " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995.0, 'rating': 9.3, 'genre': 'animated', 'id': 6.0}),\n",
       " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979.0, 'rating': 9.9, 'genre': 'science fiction', 'id': 4.0}),\n",
       " Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006.0, 'rating': 9.0, 'genre': 'thriller', 'id': 5.0})]"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example only specifies a relevant query\n",
    "retriever.invoke(\"What are some movies about dinosaurs\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "3afd98ca20782dda",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:42:55.179002Z",
     "start_time": "2024-03-29T02:42:53.057022Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995.0, 'rating': 9.3, 'genre': 'animated', 'id': 6.0}),\n",
       " Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979.0, 'rating': 9.9, 'genre': 'science fiction', 'id': 4.0})]"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example specifies a filter\n",
    "retriever.invoke(\"What are some highly rated movies (above 9)?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "9974f641e11abfe8",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:42:58.472620Z",
     "start_time": "2024-03-29T02:42:56.131594Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006.0, 'rating': 9.0, 'genre': 'thriller', 'id': 5.0}),\n",
       " Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010.0, 'rating': 8.2, 'genre': 'thriller', 'id': 2.0})]"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example specifies both a relevant query and a filter\n",
    "retriever.invoke(\"What are the thriller movies that are highly rated?\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "edd31040-ede0-40bb-bfcd-962118df4ffb",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993.0, 'rating': 7.7, 'genre': 'action', 'id': 1.0})]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example specifies a query and composite filter\n",
    "retriever.invoke(\n",
    "    \"What's a movie after 1990 but before 2005 that's all about dinosaurs, \\\n",
    "    and preferably has a lot of action\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "be593d3a6c508517",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Filter k\n",
    "\n",
    "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
    "\n",
    "We can do this by passing `enable_limit=True` to the constructor."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7e17a10f-4187-4164-ab8f-b427c6b86cc0",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Filter k\n",
    "\n",
    "We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
    "\n",
    "We can do this by passing `enable_limit=True` to the constructor."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "e255b69c937fa424",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:43:02.779337Z",
     "start_time": "2024-03-29T02:43:02.759900Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "retriever = SelfQueryRetriever.from_llm(\n",
    "    llm,\n",
    "    vector_store,\n",
    "    document_content_description,\n",
    "    metadata_field_info,\n",
    "    verbose=True,\n",
    "    enable_limit=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "45674137c7f8a9d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-03-29T02:43:07.357830Z",
     "start_time": "2024-03-29T02:43:04.854323Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "retriever.invoke(\"What are two movies about dinosaurs?\")"
   ]
  }
 ],
 "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": "3.9.16"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}