用声明式框架简化RAG流水线构建与评估。
Constructing and Evaluating Declarative RAG Pipelines in PyTerrier
- 基于PyTerrier的声明式语法，直观定义RAG流程
- 支持自然问题等标准数据集，高效搭建检索生成流水线
- 适合需要快速验证RAG方案的研究者和开发者
搜索引擎常采用流水线架构，通过复杂的重排序组件优化初始检索结果。检索增强生成（RAG）是这一架构的创新应用，最终组件从检索到的文档中生成连贯回答。本文演示如何在声明式PyTerrier框架中构建此类RAG流水线及其优势。PyTerrier-RAG扩展提供了对标准RAG数据集和评估指标的便捷访问，集成前沿LLM阅读器，并利用PyTerrier独特的操作符记法，实现简洁易构建的流水线。我们在自然问题（Natural Questions）等标准数据集上展示了索引与RAG流水线的简洁性，同时说明如何结合先进的稀疏、学习型稀疏及密集检索器与其他神经排序模型，拓展至更广泛的PyTerrier生态系统。
原文摘要 · Abstract (English)
Search engines often follow a pipeline architecture, where complex but effective reranking components are used to refine the results of an initial retrieval. Retrieval augmented generation (RAG) is an exciting application of the pipeline architecture, where the final component generates a coherent answer for the users from the retrieved documents. In this demo paper, we describe how such RAG pipelines can be formulated in the declarative PyTerrier architecture, and the advantages of doing so. Our PyTerrier-RAG extension for PyTerrier provides easy access to standard RAG datasets and evaluation measures, state-of-the-art LLM readers, and using PyTerrier's unique operator notation, easy-to-build pipelines. We demonstrate the succinctness of indexing and RAG pipelines on standard datasets (including Natural Questions) and how to build on the larger PyTerrier ecosystem with state-of-the-art sparse, learned-sparse, and dense retrievers, and other neural rankers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。