NovaSearch-Team/RAG-Retrieval

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

39
/ 100
Emerging

Supports knowledge distillation from larger models (including 7B+ LLMs) into compact variants like BERT-base or 0.5B LLMs, and implements advanced training techniques like MRL loss and preference-based fine-tuning. Provides a unified inference library (`rag-retrieval` pip package) with a consistent API across heterogeneous reranker architectures (cross-encoders, decoder-only LLMs) and flexible long-document handling strategies. Integrates with popular open-source models (BGE, BCE, GTE) and supports distributed training via DeepSpeed and FSDP.

1,103 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 9 / 25
Community 18 / 25

How are scores calculated?

Stars

1,103

Forks

90

Language

Python

License

MIT

Last pushed

Jul 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/NovaSearch-Team/RAG-Retrieval"

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