{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "59895c73d1a0f3ca",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "# DashVector\n",
    "\n",
    "> [DashVector](https://help.aliyun.com/document_detail/2510225.html) is a fully managed vector DB service that supports high-dimension dense and sparse vectors, real-time insertion and filtered search. It is built to scale automatically and can adapt to different application requirements.\n",
    "> The vector retrieval service `DashVector` is based on the `Proxima` core of the efficient vector engine independently developed by `DAMO Academy`,\n",
    ">  and provides a cloud-native, fully managed vector retrieval service with horizontal expansion capabilities.\n",
    ">  `DashVector` exposes its powerful vector management, vector query and other diversified capabilities through a simple and\n",
    "> easy-to-use SDK/API interface, which can be quickly integrated by upper-layer AI applications, thereby providing services\n",
    "> including large model ecology, multi-modal AI search, molecular structure A variety of application scenarios, including analysis,\n",
    "> provide the required efficient vector retrieval capabilities.\n",
    "\n",
    "In this notebook, we'll demo the `SelfQueryRetriever` with a `DashVector` vector store."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "539ae9367e45a178",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Create DashVector vectorstore\n",
    "\n",
    "First we'll want to create a `DashVector` VectorStore and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
    "\n",
    "To use DashVector, you have to have `dashvector` package installed, and you must have an API key and an Environment. Here are the [installation instructions](https://help.aliyun.com/document_detail/2510223.html).\n",
    "\n",
    "NOTE: The self-query retriever requires you to have `lark` package installed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "67df7e1f8dc8cdd0",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "%pip install --upgrade --quiet  lark dashvector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "ff61eaf13973b5fe",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:58:46.905337Z",
     "start_time": "2023-08-24T02:58:46.252566Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "\n",
    "import dashvector\n",
    "\n",
    "client = dashvector.Client(api_key=os.environ[\"DASHVECTOR_API_KEY\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "de5c77957ee42d14",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from langchain_community.embeddings import DashScopeEmbeddings\n",
    "from langchain_community.vectorstores import DashVector\n",
    "from langchain_core.documents import Document\n",
    "\n",
    "embeddings = DashScopeEmbeddings()\n",
    "\n",
    "# create DashVector collection\n",
    "client.create(\"langchain-self-retriever-demo\", dimension=1536)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "8f40605548a4550",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:08.090031Z",
     "start_time": "2023-08-24T02:59:05.660295Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "docs = [\n",
    "    Document(\n",
    "        page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
    "        metadata={\"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={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\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={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
    "        metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"Toys come alive and have a blast doing so\",\n",
    "        metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
    "    ),\n",
    "    Document(\n",
    "        page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
    "        metadata={\n",
    "            \"year\": 1979,\n",
    "            \"director\": \"Andrei Tarkovsky\",\n",
    "            \"genre\": \"science fiction\",\n",
    "            \"rating\": 9.9,\n",
    "        },\n",
    "    ),\n",
    "]\n",
    "vectorstore = DashVector.from_documents(\n",
    "    docs, embeddings, collection_name=\"langchain-self-retriever-demo\"\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eb1340adafac8993",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Create your self-querying retriever\n",
    "\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": 4,
   "id": "d65233dc044f95a7",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:11.003940Z",
     "start_time": "2023-08-24T02:59:10.476722Z"
    },
    "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_community.llms import Tongyi\n",
    "\n",
    "metadata_field_info = [\n",
    "    AttributeInfo(\n",
    "        name=\"genre\",\n",
    "        description=\"The genre of the movie\",\n",
    "        type=\"string or list[string]\",\n",
    "    ),\n",
    "    AttributeInfo(\n",
    "        name=\"year\",\n",
    "        description=\"The year the movie was released\",\n",
    "        type=\"integer\",\n",
    "    ),\n",
    "    AttributeInfo(\n",
    "        name=\"director\",\n",
    "        description=\"The name of the movie director\",\n",
    "        type=\"string\",\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 = Tongyi(temperature=0)\n",
    "retriever = SelfQueryRetriever.from_llm(\n",
    "    llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a54af0d67b473db6",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "source": [
    "## Testing it out\n",
    "\n",
    "And now we can try actually using our retriever!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "dad9da670a267fe7",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:28.577901Z",
     "start_time": "2023-08-24T02:59:26.780184Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "query='dinosaurs' filter=None limit=None\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.699999809265137, 'genre': 'action'}),\n",
       " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),\n",
       " Document(page_content='Leo DiCaprio gets lost in a dream within a dream within a dream within a ...', metadata={'year': 2010, 'director': 'Christopher Nolan', 'rating': 8.199999809265137}),\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, 'director': 'Satoshi Kon', 'rating': 8.600000381469727})]"
      ]
     },
     "execution_count": 6,
     "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": 7,
   "id": "d486a64316153d52",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:32.370774Z",
     "start_time": "2023-08-24T02:59:30.614252Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "query=' ' filter=Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5) limit=None\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'rating': 9.899999618530273, 'genre': 'science fiction'}),\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, 'director': 'Satoshi Kon', 'rating': 8.600000381469727})]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example only specifies a filter\n",
    "retriever.invoke(\"I want to watch a movie rated higher than 8.5\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e05919cdead7bd4a",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:35.353439Z",
     "start_time": "2023-08-24T02:59:33.278255Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "query='Greta Gerwig' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'director': 'Greta Gerwig', 'rating': 8.300000190734863})]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example specifies a query and a filter\n",
    "retriever.invoke(\"Has Greta Gerwig directed any movies about women\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "ac2c7012379e918e",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:38.913707Z",
     "start_time": "2023-08-24T02:59:36.659271Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "query='science fiction' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction'), Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5)]) limit=None\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'director': 'Andrei Tarkovsky', 'rating': 9.899999618530273, 'genre': 'science fiction'})]"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example specifies a composite filter\n",
    "retriever.invoke(\"What's a highly rated (above 8.5) science fiction film?\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "af6aa93ae44af414",
   "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": 10,
   "id": "a8c8f09bf5702767",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:41.594073Z",
     "start_time": "2023-08-24T02:59:41.563323Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "retriever = SelfQueryRetriever.from_llm(\n",
    "    llm,\n",
    "    vectorstore,\n",
    "    document_content_description,\n",
    "    metadata_field_info,\n",
    "    enable_limit=True,\n",
    "    verbose=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "b1089a6043980b84",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2023-08-24T02:59:48.450506Z",
     "start_time": "2023-08-24T02:59:46.252944Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "query='dinosaurs' filter=None limit=2\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'rating': 7.699999809265137, 'genre': 'action'}),\n",
       " Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# This example only specifies a relevant query\n",
    "retriever.invoke(\"what are two movies about dinosaurs\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6d2d64e2ebb17d30",
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}