pgvector
Postgres extension.
This guide provides a quick overview for getting started with PGVector vector stores. For detailed documentation of all PGVectorStore
features and configurations head to the API reference.
Overview
Integration details
Class | Package | PY support | Version |
---|---|---|---|
PGVectorStore | @langchain/community | ✅ |
Setup
To use PGVector vector stores, you’ll need to set up a Postgres instance with thepgvector
extension enabled. You’ll also need to install the @langchain/community
integration package with the pg
package as a peer dependency.
This guide will also use OpenAI embeddings, which require you to install the @langchain/openai
integration package. You can also use other supported embeddings models if you wish.
We’ll also use the uuid
package to generate ids in the required format.
Setting up an instance
There are many ways to connect to Postgres depending on how you’ve set up your instance. Here’s one example of a local setup using a prebuilt Docker image provided by thepgvector
team.
Create a file with the below content named docker-compose.yml:
docker compose up
to start the container.
You can find more information on how to setup pgvector in the official repository.
Credentials
To connect to you Postgres instance, you’ll need corresponding credentials. For a full list of supported options, see thenode-postgres
docs.
If you are using OpenAI embeddings for this guide, you’ll need to set your OpenAI key as well:
Instantiation
To instantiate the vector store, call the.initialize()
static method. This will automatically check for the presence of a table, given by tableName
in the passed config
. If it is not there, it will create it with the required columns.
Manage vector store
Add items to vector store
Delete items from vector store
Query vector store
Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent.Query directly
Performing a simple similarity search can be done as follows:Using the in
operator
Using the notIn
operator
Using the arrayContains
operator
Query by turning into retriever
You can also transform the vector store into a retriever for easier usage in your chains.Usage for retrieval-augmented generation
For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:Advanced: reusing connections
You can reuse connections by creating a pool, then creating newPGVectorStore
instances directly via the constructor.
Note that you should call .initialize()
to set up your database at least once to set up your tables properly before using the constructor.
Create HNSW Index
By default, the extension performs a sequential scan search, with 100% recall. You might consider creating an HNSW index for approximate nearest neighbor (ANN) search to speed upsimilaritySearchVectorWithScore
execution time. To create the HNSW index on your vector column, use the createHnswIndex()
method.
The method parameters include:
-
dimensions
: Defines the number of dimensions in your vector data type, up to 2000. For example, use 1536 for OpenAI’s text-embedding-ada-002 and Amazon’s amazon.titan-embed-text-v1 models. -
m?
: The max number of connections per layer (16 by default). Index build time improves with smaller values, while higher values can speed up search queries. -
efConstruction?
: The size of the dynamic candidate list for constructing the graph (64 by default). A higher value can potentially improve the index quality at the cost of index build time. -
distanceFunction?
: The distance function name you want to use, is automatically selected based on the distanceStrategy.
Closing connections
Make sure you close the connection when you are finished to avoid excessive resource consumption:API reference
For detailed documentation of allPGVectorStore
features and configurations head to the API reference.