pgai 0.12.1

AI workflows in your PostgreSQL database

Power your RAG and Agentic applications with PostgreSQL

Docs · Join the pgai Discord! · Try timescale for free! · Changelog

A Python library that transforms PostgreSQL into a robust, production-ready retrieval engine for RAG and Agentic applications.

• 🔄 Automatically create and synchronize vector embeddings from PostgreSQL data and S3 documents. Embeddings update automatically as data changes.

• 🔍 Powerful vector and semantic search with pgvector and pgvectorscale.

• 🛡️ Production-ready out-of-the-box: Supports batch processing for efficient embedding generation, with built-in handling for model failures, rate limits, and latency spikes.

• 🐘 Works with any PostgreSQL database, including Timescale Cloud, Amazon RDS, Supabase and more.

Getting Started

Install:

pip install pgai

pgai install -d "postgresql://postgres:postgres@localhost:5432/postgres"

The key "secret sauce" of pgai Vectorizer is its declarative approach to embedding generation. Simply define your pipeline and let Vectorizer handle the operational complexity of keeping embeddings in sync, even when embedding endpoints are unreliable. You can define a simple version of the pipeline as follows:

SELECT ai.create_vectorizer(
     'wiki'::regclass,
     loading => ai.loading_column(column_name=>'text'),
     embedding => ai.embedding_openai(model=>'text-embedding-ada-002', dimensions=>'1536'),
     destination => ai.destination_table(target_table=>'wiki_embedding_storage')
    )

The vectorizer will automatically create embeddings for all the rows in the wiki table, and, more importantly, will keep the embeddings synced with the underlying data as it changes. Think of it almost like declaring an index on the wiki table, but instead of the database managing the index datastructure for you, the vectorizer is managing the embeddings.

Checkout our full quick start on github