RAG铸造厂：增强LLM以实现检索增强生成的框架

RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation

August 5, 2024

作者: Daniel Fleischer, Moshe Berchansky, Moshe Wasserblat, Peter Izsak

cs.AI

摘要

实现检索增强生成（RAG）系统本质上是复杂的，需要对数据、使用案例和复杂设计决策有深刻的理解。此外，评估这些系统面临重大挑战，需要通过多方面的方法评估检索准确性和生成质量。我们介绍了RAG Foundry，这是一个用于增强大型语言模型以应用于RAG案例的开源框架。RAG Foundry将数据创建、训练、推理和评估整合为一个工作流程，促进了为在RAG环境中训练和评估大型语言模型而创建数据增强数据集。这种整合使得可以快速原型设计和尝试各种RAG技术，让用户能够轻松生成数据集并使用内部或专业知识源训练RAG模型。我们通过使用多样的RAG配置增强和微调Llama-3和Phi-3模型来展示框架的有效性，在三个知识密集型数据集上展示了一致的改进。代码已作为开源发布在https://github.com/IntelLabs/RAGFoundry。

English

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.