remote::pgvector

Description

PGVector is a remote vector database provider for Llama Stack. It allows you to store and query vectors directly in memory. That means you’ll get fast and efficient vector retrieval.

Features

Easy to use
Fully integrated with Llama Stack

Usage

To use PGVector in your Llama Stack project, follow these steps:

Install the necessary dependencies.
Configure your Llama Stack project to use Faiss.
Start storing and querying vectors.

Installation

You can install PGVector using docker:

docker pull pgvector/pgvector:pg17

Documentation

See PGVector’s documentation for more details about PGVector in general.

Configuration

Field	Type	Required	Default
`host`	`str \| None`	No	localhost
`port`	`int \| None`	No	5432
`db`	`str \| None`	No	postgres
`user`	`str \| None`	No	postgres
`password`	`str \| None`	No	mysecretpassword

Sample Configuration

host: ${env.PGVECTOR_HOST:=localhost}
port: ${env.PGVECTOR_PORT:=5432}
db: ${env.PGVECTOR_DB}
user: ${env.PGVECTOR_USER}
password: ${env.PGVECTOR_PASSWORD}