github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-08 14:31:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add integration for Timescale Vector(Postgres) (#10650)

Browse Source 
**Description:**
This commit adds a vector store for the Postgres-based vector database
(`TimescaleVector`).

Timescale Vector(https://www.timescale.com/ai) is PostgreSQL++ for AI
applications. It enables you to efficiently store and query billions of
vector embeddings in `PostgreSQL`:
- Enhances `pgvector` with faster and more accurate similarity search on
1B+ vectors via DiskANN inspired indexing algorithm.
- Enables fast time-based vector search via automatic time-based
partitioning and indexing.
- Provides a familiar SQL interface for querying vector embeddings and
relational data.

Timescale Vector scales with you from POC to production:
- Simplifies operations by enabling you to store relational metadata,
vector embeddings, and time-series data in a single database.
- Benefits from rock-solid PostgreSQL foundation with enterprise-grade
feature liked streaming backups and replication, high-availability and
row-level security.
- Enables a worry-free experience with enterprise-grade security and
compliance.

Timescale Vector is available on Timescale, the cloud PostgreSQL
platform. (There is no self-hosted version at this time.) LangChain
users get a 90-day free trial for Timescale Vector.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Avthar Sewrathan <avthar@timescale.com>
This commit is contained in:
Matvey Arye
2023-09-21 09:33:37 -05:00
committed by GitHub
parent 55570e54e1
commit 6e02c45ca4
10 changed files with 3863 additions and 470 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1696
docs/extras/integrations/vectorstores/timescalevector.ipynb Normal file
View File

File diff suppressed because it is too large Load Diff

534
docs/extras/modules/data_connection/retrievers/self_query/timescalevector_self_query.ipynb Normal file
View File

@@ -0,0 +1,534 @@
{
"cells": [
{
"attachments": {},
"cell_type": "markdown",
"id": "13afcae7",
"metadata": {},
"source": [
"# Timescale Vector (Postgres) self-querying \n",
"\n",
"[Timescale Vector](https://www.timescale.com/ai) is PostgreSQL++ for AI applications. It enables you to efficiently store and query billions of vector embeddings in `PostgreSQL`.\n",
"\n",
"This notebook shows how to use the Postgres vector database (`TimescaleVector`) to perform self-querying. In the notebook we'll demo the `SelfQueryRetriever` wrapped around a TimescaleVector vector store. \n",
"\n",
"## What is Timescale Vector?\n",
"**[Timescale Vector](https://www.timescale.com/ai) is PostgreSQL++ for AI applications.**\n",
"\n",
"Timescale Vector enables you to efficiently store and query millions of vector embeddings in `PostgreSQL`.\n",
"- Enhances `pgvector` with faster and more accurate similarity search on 1B+ vectors via DiskANN inspired indexing algorithm.\n",
"- Enables fast time-based vector search via automatic time-based partitioning and indexing.\n",
"- Provides a familiar SQL interface for querying vector embeddings and relational data.\n",
"\n",
"Timescale Vector is cloud PostgreSQL for AI that scales with you from POC to production:\n",
"- Simplifies operations by enabling you to store relational metadata, vector embeddings, and time-series data in a single database.\n",
"- Benefits from rock-solid PostgreSQL foundation with enterprise-grade feature liked streaming backups and replication, high-availability and row-level security.\n",
"- Enables a worry-free experience with enterprise-grade security and compliance.\n",
"\n",
"## How to access Timescale Vector\n",
"Timescale Vector is available on [Timescale](https://www.timescale.com/ai), the cloud PostgreSQL platform. (There is no self-hosted version at this time.)\n",
"\n",
"LangChain users get a 90-day free trial for Timescale Vector.\n",
"- To get started, [signup](https://console.cloud.timescale.com/signup?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral) to Timescale, create a new database and follow this notebook!\n",
"- See the [Timescale Vector explainer blog](https://www.timescale.com/blog/how-we-made-postgresql-the-best-vector-database/?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral) for more details and performance benchmarks.\n",
"- See the [installation instructions](https://github.com/timescale/python-vector) for more details on using Timescale Vector in python.\n"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "68e75fb9",
"metadata": {},
"source": [
"## Creating a TimescaleVector vectorstore\n",
"First we'll want to create a Timescale Vector vectorstore 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`). We also need the `timescale-vector` package."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "63a8af5b",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"#!pip install lark"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "22431060-52c4-48a7-a97b-9f542b8b0928",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"#!pip install timescale-vector "
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
"metadata": {},
"source": [
"In this example, we'll use `OpenAIEmbeddings`, so let's load your OpenAI API key."
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"# Get openAI api key by reading local .env file\n",
"# The .env file should contain a line starting with `OPENAI_API_KEY=sk-`\n",
"import os\n",
"from dotenv import load_dotenv, find_dotenv\n",
"_ = load_dotenv(find_dotenv())\n",
"\n",
"OPENAI_API_KEY = os.environ['OPENAI_API_KEY']\n",
"# Alternatively, use getpass to enter the key in a prompt\n",
"#import os\n",
"#import getpass\n",
"#os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "766e9c4b",
"metadata": {},
"source": [
"To connect to your PostgreSQL database, you'll need your service URI, which can be found in the cheatsheet or `.env` file you downloaded after creating a new database. \n",
"\n",
"If you haven't already, [signup for Timescale](https://console.cloud.timescale.com/signup?utm_campaign=vectorlaunch&utm_source=langchain&utm_medium=referral), and create a new database.\n",
"\n",
"The URI will look something like this: `postgres://tsdbadmin:<password>@<id>.tsdb.cloud.timescale.com:<port>/tsdb?sslmode=require`"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "6bd6877e",
"metadata": {},
"outputs": [],
"source": [
"# Get the service url by reading local .env file\n",
"# The .env file should contain a line starting with `TIMESCALE_SERVICE_URL=postgresql://`\n",
"_ = load_dotenv(find_dotenv())\n",
"TIMESCALE_SERVICE_URL = os.environ[\"TIMESCALE_SERVICE_URL\"]\n",
"\n",
"# Alternatively, use getpass to enter the key in a prompt\n",
"#import os\n",
"#import getpass\n",
"#TIMESCALE_SERVICE_URL = getpass.getpass(\"Timescale Service URL:\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "cb4a5787",
"metadata": {
"tags": []
},
"outputs": [],
"source": [
"from langchain.schema import Document\n",
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
"from langchain.vectorstores.timescalevector import TimescaleVector\n",
"\n",
"embeddings = OpenAIEmbeddings()"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "a4f863f5",
"metadata": {},
"source": [
"Here's the sample documents we'll use for this demo. The data is about movies, and has both content and metadata fields with information about particular movie."
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "bcbe04d9",
"metadata": {
"tags": []
},
"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\": \"science fiction\"},\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",
" \"rating\": 9.9,\n",
" \"director\": \"Andrei Tarkovsky\",\n",
" \"genre\": \"science fiction\",\n",
" \"rating\": 9.9,\n",
" },\n",
" ),\n",
"]"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "7d0d771e",
"metadata": {},
"source": [
"Finally, we'll create our Timescale Vector vectorstore. Note that the collection name will be the name of the PostgreSQL table in which the documents are stored in."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "2428d1ba",
"metadata": {},
"outputs": [],
"source": [
"COLLECTION_NAME = \"langchain_self_query_demo\"\n",
"vectorstore = TimescaleVector.from_documents(\n",
" embedding=embeddings,\n",
" documents=docs,\n",
" collection_name=COLLECTION_NAME,\n",
" service_url=TIMESCALE_SERVICE_URL,\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "5ecaab6d",
"metadata": {},
"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": 14,
"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",
"# Give LLM info about the metadata fields\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",
"\n",
"# Instantiate the self-query retriever from an LLM\n",
"llm = OpenAI(temperature=0)\n",
"retriever = SelfQueryRetriever.from_llm(\n",
" llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
")"
]
},
{
"attachments": {},
"cell_type": "markdown",
"id": "ea9df8d4",
"metadata": {},
"source": [
"## Self Querying Retrieval with Timescale Vector\n",
"And now we can try actually using our retriever!\n",
"\n",
"Run the queries below and note how you can specify a query, filter, composite filter (filters with AND, OR) in natural language and the self-query retriever will translate that query into SQL and perform the search on the Timescale Vector (Postgres) vectorstore.\n",
"\n",
"This illustrates the power of the self-query retriever. You can use it to perform complex searches over your vectorstore without you or your users having to write any SQL directly!"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "38a126e9",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/Users/avtharsewrathan/sideprojects2023/timescaleai/tsv-langchain/langchain/libs/langchain/langchain/chains/llm.py:275: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
" warnings.warn(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='dinosaur' 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, 'genre': 'science fiction', 'rating': 7.7}),\n",
" Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
" Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),\n",
" Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example only specifies a relevant query\n",
"retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "fc3f1e6e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=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, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\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, 'rating': 8.6, 'director': 'Satoshi Kon'}),\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, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 17,
"id": "b19d4da0",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='women' 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, 'rating': 8.3, 'director': 'Greta Gerwig'}),\n",
" Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'rating': 8.3, 'director': 'Greta Gerwig'})]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"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": 18,
"id": "f900e40e",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) 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, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'})]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a composite filter\n",
"retriever.get_relevant_documents(\n",
" \"What's a highly rated (above 8.5) science fiction film?\"\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "12a51522",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='animated')]) limit=None\n"
]
},
{
"data": {
"text/plain": [
"[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 specifies a query and composite filter\n",
"retriever.get_relevant_documents(\n",
" \"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\"\n",
")"
]
},
{
"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": 19,
"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": 22,
"id": "2758d229-4f97-499c-819f-888acaf8ee10",
"metadata": {
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"query='dinosaur' 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, 'genre': 'science fiction', 'rating': 7.7}),\n",
" Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7})]"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# This example specifies a query with a LIMIT value\n",
"retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
}
},
"nbformat": 4,
"nbformat_minor": 5
}