RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation
This addresses the challenge for developers and researchers in building and assessing RAG systems, though it is incremental as it provides a tool rather than a new method.
The paper tackles the complexity of implementing and evaluating Retrieval-Augmented Generation (RAG) systems by introducing RAG Foundry, an open-source framework that integrates data creation, training, inference, and evaluation into a single workflow, resulting in consistent improvements for Llama-3 and Phi-3 models across three knowledge-intensive datasets.
Implementing Retrieval-Augmented Generation (RAG) systems is inherently complex, requiring deep understanding of data, use cases, and intricate design decisions. Additionally, evaluating these systems presents significant challenges, necessitating assessment of both retrieval accuracy and generative quality through a multi-faceted approach. We introduce RAG Foundry, an open-source framework for augmenting large language models for RAG use cases. RAG Foundry integrates data creation, training, inference and evaluation into a single workflow, facilitating the creation of data-augmented datasets for training and evaluating large language models in RAG settings. This integration enables rapid prototyping and experimentation with various RAG techniques, allowing users to easily generate datasets and train RAG models using internal or specialized knowledge sources. We demonstrate the framework effectiveness by augmenting and fine-tuning Llama-3 and Phi-3 models with diverse RAG configurations, showcasing consistent improvements across three knowledge-intensive datasets. Code is released as open-source in https://github.com/IntelLabs/RAGFoundry.