Download
RAG-Retrieval is an open-source framework for building and training retrieval systems used in retrieval-augmented generation pipelines. Retrieval-augmented generation combines large language models with external knowledge retrieval to improve factual accuracy and domain-specific reasoning. This repository provides end-to-end infrastructure for training retrieval models, performing inference, and distilling embedding models for improved performance. It includes implementations of modern embedding architectures designed to map documents and queries into vector spaces for efficient similarity search. The framework also supports reranking models that refine retrieved results using large language models or lightweight transformer architectures. Additional training techniques such as preference-based supervised fine-tuning and embedding distillation are included to improve retrieval quality.
Features
- End-to-end training pipeline for retrieval-augmented generation systems
- Embedding model training for vector-based document retrieval
- Support for reranker models that improve retrieval relevance
- Preference-based supervised fine-tuning for retrieval optimization
- Embedding model distillation for efficient deployment
- Integration with large language models for RAG pipelines
Project Samples
