This page covers how to use the Postgres PGVector ecosystem within LangChain It is broken into two parts: installation and setup, and then references to specific PGVector wrappers.
- Install the Python package with
pip install pgvector
The first step is to create a database with the
Follow the steps at PGVector Installation Steps to install the database and the extension. The docker image is the easiest way to get started.
There exists a wrapper around Postgres vector databases, allowing you to use it as a vectorstore, whether for semantic search or example selection.
To import this vectorstore:
from langchain_community.vectorstores.pgvector import PGVector
For a more detailed walkthrough of the PGVector Wrapper, see this notebook