This page covers how to use the PostgresPGVector ecosystem within LangChainIt is broken into two parts: installation and setup, and then references to specific PGVector wrappers.

Installation​

• Install the Python package withpip install pgvector

Setup​

1. The first step is to create a database with thepgvector extension installed.

   Follow the steps atPGVector Installation Steps to install the database and the extension. The docker image is the easiest way to get started.

Wrappers​

VectorStore​

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.pgvectorimport PGVector

Usage​

For a more detailed walkthrough of the PGVector Wrapper, seethis notebook