hienhayho/rag-colls
Collection of recent advanced RAG techniques.
Implements modular RAG pipelines with pluggable components for document parsing (Docling, MarkItDown, MegaParse), vector storage (Chromadb), and hybrid retrieval (BM25s integration). Supports techniques like ContextualRAG combining dense and sparse retrievers, and RAFT for retriever-augmented fine-tuning to improve answer quality through supervised learning.
Available on PyPI.
Stars
18
Forks
6
Language
Python
License
MIT
Category
Last pushed
Oct 24, 2025
Monthly downloads
90
Commits (30d)
0
Dependencies
20
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/hienhayho/rag-colls"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...
0verL1nk/PaperSage
📚 AI-powered research reading workbench. Project-based paper Q&A with Hybrid RAG, multi-agent...
RapidFireAI/rapidfireai
RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning