neondatabase/pgrag
Postgres extensions to support end-to-end Retrieval-Augmented Generation (RAG) pipelines
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.
Stars
95
Forks
4
Language
Rust
License
—
Category
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.
Higher-rated alternatives
aws-samples/aws-genai-llm-chatbot
A modular and comprehensive solution to deploy a Multi-LLM and Multi-RAG powered chatbot (Amazon...
Aquiles-ai/Aquiles-RAG
Is a high-performance Augmented Recovery-Generation (RAG) solution based on Redis, Qdrant or...
tavily-ai/crawl2rag
Crawl any website with Tavily, embed the content, and deploy the RAG on MongoDB Atlas vector search.
mithun50/groq-rag
Extended Groq SDK with RAG (Retrieval-Augmented Generation), web browsing, and AI agent...
redis-developer/llm-redisrail
RAG with Redis. Parallel implementations with/without guardrails.