Merge pull request #2 from mpskex/master

Expanded Self-Query Retriever and Self-Query Retriever with MyScale

docs/modules/indexes/retrievers/examples/myscale_self_query.ipynb

@@ -0,0 +1,370 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "13afcae7",
+   "metadata": {},
+   "source": [
+    "# Self-querying with MyScale\n",
+    "\n",
+    ">[MyScale](https://docs.myscale.com/en/) is an integrated vector database. You can access your database in SQL and also from here, LangChain. MyScale can make a use of [various data types and functions for filters](https://blog.myscale.com/2023/06/06/why-integrated-database-solution-can-boost-your-llm-apps/#filter-on-anything-without-constraints). It will boost up your LLM app no matter if you are scaling up your data or expand your system to broader application.\n",
+    "\n",
+    "In the notebook we'll demo the `SelfQueryRetriever` wrapped around a MyScale vector store with some extra piece we contributed to LangChain. In short, it can be concluded into 4 points:\n",
+    "1. Add `contain` comparator to match list of any if there is more than one element matched\n",
+    "2. Add `timestamp` data type for datetime match (ISO-format, or YYYY-MM-DD)\n",
+    "3. Add `like` comparator for string pattern search\n",
+    "4. Add arbitrary function capability"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "68e75fb9",
+   "metadata": {},
+   "source": [
+    "## Creating a MyScale vectorstore\n",
+    "MyScale has already been integrated to LangChain for a while. So you can follow [this notebook](../../vectorstores/examples/myscale.ipynb) to create your own vectorstore for a self-query retriever.\n",
+    "\n",
+    "NOTE: All self-query retrievers requires you to have `lark` installed (`pip install lark`). We use `lark` for grammar definition. Before you proceed to the next step, we also want to remind you that `clickhouse-connect` is also needed to interact with your MyScale backend."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "63a8af5b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "! pip install lark clickhouse-connect"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
+   "metadata": {},
+   "source": [
+    "In this tutorial we follow other example's setting and use `OpenAIEmbeddings`. Remember to get a OpenAI API Key for valid accesss to LLMs."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import getpass\n",
+    "\n",
+    "os.environ['OPENAI_API_KEY'] = getpass.getpass('OpenAI API Key:')\n",
+    "os.environ['MYSCALE_HOST'] = getpass.getpass('MyScale URL:')\n",
+    "os.environ['MYSCALE_PORT'] = getpass.getpass('MyScale Port:')\n",
+    "os.environ['MYSCALE_USERNAME'] = getpass.getpass('MyScale Username:')\n",
+    "os.environ['MYSCALE_PASSWORD'] = getpass.getpass('MyScale Password:')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cb4a5787",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.schema import Document\n",
+    "from langchain.embeddings.openai import OpenAIEmbeddings\n",
+    "from langchain.vectorstores import MyScale\n",
+    "\n",
+    "embeddings = OpenAIEmbeddings()"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "bf7f6fc4",
+   "metadata": {},
+   "source": [
+    "## Create some sample data\n",
+    "As you can see, the data we created has some difference to other self-query retrievers. We replaced keyword `year` to `date` which gives you a finer control on timestamps. We also altered the type of keyword `gerne` to list of strings, where LLM can use a new `contain` comparator to construct filters. We also provides comparator `like` and arbitrary function support to filters, which will be introduced in next few cells.\n",
+    "\n",
+    "Now let's look at the data first."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bcbe04d9",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "docs = [\n",
+    "    Document(page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\", metadata={\"date\": \"1993-07-02\", \"rating\": 7.7, \"genre\": [\"science fiction\"]}),\n",
+    "    Document(page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\", metadata={\"date\": \"2010-12-30\", \"director\": \"Christopher Nolan\", \"rating\": 8.2}),\n",
+    "    Document(page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\", metadata={\"date\": \"2006-04-23\", \"director\": \"Satoshi Kon\", \"rating\": 8.6}),\n",
+    "    Document(page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\", metadata={\"date\": \"2019-08-22\", \"director\": \"Greta Gerwig\", \"rating\": 8.3}),\n",
+    "    Document(page_content=\"Toys come alive and have a blast doing so\", metadata={\"date\": \"1995-02-11\", \"genre\": [\"animated\"]}),\n",
+    "    Document(page_content=\"Three men walk into the Zone, three men walk out of the Zone\", metadata={\"date\": \"1979-09-10\", \"rating\": 9.9, \"director\": \"Andrei Tarkovsky\", \"genre\": [\"science fiction\", \"adventure\"], \"rating\": 9.9})\n",
+    "]\n",
+    "vectorstore = MyScale.from_documents(\n",
+    "    docs, \n",
+    "    embeddings, \n",
+    ")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "5ecaab6d",
+   "metadata": {},
+   "source": [
+    "## Creating our self-querying retriever\n",
+    "Just like other retrievers... Simple and nice."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "86e34dbf",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from langchain.llms import OpenAI\n",
+    "from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
+    "from langchain.chains.query_constructor.base import AttributeInfo\n",
+    "\n",
+    "metadata_field_info=[\n",
+    "    AttributeInfo(\n",
+    "        name=\"genre\",\n",
+    "        description=\"The genres of the movie\", \n",
+    "        type=\"list[string]\", \n",
+    "    ),\n",
+    "    # If you want to include length of a list, just define it as a new column\n",
+    "    # This will teach the LLM to use it as a column when constructing filter.\n",
+    "    AttributeInfo(\n",
+    "        name=\"length(genre)\",\n",
+    "        description=\"The lenth of genres of the movie\", \n",
+    "        type=\"integer\", \n",
+    "    ),\n",
+    "    # Now you can define a column as timestamp. By simply set the type to timestamp.\n",
+    "    AttributeInfo(\n",
+    "        name=\"date\",\n",
+    "        description=\"The date the movie was released\", \n",
+    "        type=\"timestamp\", \n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"director\",\n",
+    "        description=\"The name of the movie director\", \n",
+    "        type=\"string\", \n",
+    "    ),\n",
+    "    AttributeInfo(\n",
+    "        name=\"rating\",\n",
+    "        description=\"A 1-10 rating for the movie\",\n",
+    "        type=\"float\"\n",
+    "    ),\n",
+    "]\n",
+    "document_content_description = \"Brief summary of a movie\"\n",
+    "llm = OpenAI(temperature=0)\n",
+    "retriever = SelfQueryRetriever.from_llm(llm, vectorstore, document_content_description, metadata_field_info, verbose=True)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "ea9df8d4",
+   "metadata": {},
+   "source": [
+    "## Testing it out with self-query retriever's existing functionalities\n",
+    "And now we can try actually using our retriever!"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "38a126e9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example only specifies a relevant query\n",
+    "retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc3f1e6e",
+   "metadata": {
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "# This example only specifies a filter\n",
+    "retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b19d4da0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example specifies a query and a filter\n",
+    "retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f900e40e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example specifies a composite filter\n",
+    "retriever.get_relevant_documents(\"What's a highly rated (above 8.5) science fiction film?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12a51522",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# This example specifies a query and composite filter\n",
+    "retriever.get_relevant_documents(\"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "86371ac8",
+   "metadata": {},
+   "source": [
+    "# Wait a second... What else?\n",
+    "\n",
+    "Self-query retriever with MyScale can do more! Let's find out."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d043096",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# You can use length(genres) to do anything you want\n",
+    "retriever.get_relevant_documents(\"What's a movie that have more than 1 genres?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d570d33c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Fine-grained datetime? You got it already.\n",
+    "retriever.get_relevant_documents(\"What's a movie that release after feb 1995?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fbe0b21b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Don't know what your exact filter should be? Use string pattern match!\n",
+    "retriever.get_relevant_documents(\"What's a movie whose name is like Andrei?\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6a514104",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Contain works for lists: so you can match a list with contain comparator!\n",
+    "retriever.get_relevant_documents(\"What's a movie who has genres science fiction and adventure?\")"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
+   "metadata": {},
+   "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": null,
+   "id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
+   "metadata": {
+    "tags": []
+   },
+   "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": null,
+   "id": "2758d229-4f97-499c-819f-888acaf8ee10",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# This example only specifies a relevant query\n",
+    "retriever.get_relevant_documents(\"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": "3.8.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}