NovaSearch-Team/RAG-Retrieval
An open-source library for unified fine-tuning and inference of RAG retrieval models including embedding, ColBERT, and reranker architectures.
Not currently ranked — collecting fresh signals.
star history
RAG-Retrieval provides code for training, inference, and distillation of RAG retrieval systems. It supports fine-tuning any open-source RAG retrieval model including embedding models (BERT-based and LLM-based), late interaction models like ColBERT, and reranker models. The project includes a Python library that offers a unified API to call different ranking models for inference. It also supports knowledge distillation from larger models to smaller ones.
Frequently asked
- What is NovaSearch-Team/RAG-Retrieval?
- An open-source library for unified fine-tuning and inference of RAG retrieval models including embedding, ColBERT, and reranker architectures.
- Is RAG-Retrieval open source?
- Yes — NovaSearch-Team/RAG-Retrieval is open source, released under the MIT license.
- What language is RAG-Retrieval written in?
- NovaSearch-Team/RAG-Retrieval is primarily written in Python.
- How popular is RAG-Retrieval?
- NovaSearch-Team/RAG-Retrieval has 1.1k stars on GitHub.
- Where can I find RAG-Retrieval?
- NovaSearch-Team/RAG-Retrieval is on GitHub at https://github.com/NovaSearch-Team/RAG-Retrieval.