neondatabase/pgrag

Postgres extensions to support end-to-end Retrieval-Augmented Generation (RAG) pipelines

38
/ 100
Emerging

This tool helps you prepare various documents for use with large language models (LLMs) by extracting text from PDFs, Word documents, and HTML, then breaking it into smaller, manageable pieces. It also generates numerical representations (embeddings) of this text and can re-rank results for better relevance. This is designed for data scientists or engineers building custom AI applications who need to process unstructured data within their Postgres database.

Use this if you need to pre-process documents for Retrieval-Augmented Generation (RAG) directly within your PostgreSQL database, leveraging local or remote AI models.

Not ideal if you require advanced document parsing features like OCR for images, complex layout understanding, or support for a wider range of document types.

AI application development document processing text extraction semantic search database integration
No Package No Dependents
Maintenance 6 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

95

Forks

4

Language

Rust

License

Last pushed

Oct 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/neondatabase/pgrag"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.