dronefreak/local_rag_pipeline

An advanced, fully local, and GPU-accelerated RAG pipeline. Features a sophisticated LLM-based preprocessing engine, state-of-the-art Parent Document Retriever with RAG Fusion, and a modular, Hydra-configurable architecture. Built with LangChain, Ollama, and ChromaDB for 100% private, high-performance document Q&A.

34
/ 100
Emerging

This tool helps researchers, analysts, or anyone working with large collections of documents to quickly find answers to their specific questions. You feed it your own PDFs, text files, and CSVs, and it allows you to ask questions in plain language, receiving concise answers drawn directly from your documents. This is ideal for professionals needing to extract precise information from extensive private datasets, like technical specifications or research papers.

No commits in the last 6 months.

Use this if you need to build a private, intelligent Q&A system for your own documents that runs entirely on your local computer, ensuring data privacy and quick responses.

Not ideal if you need a publicly available chatbot, do not have access to a dedicated NVIDIA GPU, or primarily work with very small, easily searchable document sets.

document-qa private-data-analysis research-assistance technical-documentation information-retrieval
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 15 / 25
Community 13 / 25

How are scores calculated?

Stars

8

Forks

2

Language

Python

License

MIT

Last pushed

Aug 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/dronefreak/local_rag_pipeline"

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