NovaSearch-Team/RAG-Retrieval

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

46
/ 100
Emerging

This tool helps improve how well your AI applications find and rank relevant information from large document collections. It takes existing search models (like embedding, ColBERT, or reranker models) and fine-tunes them to be more accurate for your specific content. The output is a more efficient and precise search component for applications like chatbots or document retrieval systems. This is ideal for AI product managers or data scientists building advanced search and question-answering systems.

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

Use this if you need to significantly improve the accuracy and relevance of search results within your RAG (Retrieval Augmented Generation) applications by training custom retrieval models.

Not ideal if you are looking for a pre-built, ready-to-use search engine or a simple API to query documents without needing to fine-tune underlying models.

information-retrieval natural-language-processing search-relevance AI-application-development document-search
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 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.