PyTerrier RAG ======================================================= `pyterrier-rag `__ is an extension for `PyTerrier `__ that makes it easier to produce retrieval augmented generation pipelines. PyTerrier-RAG supports: #. Easy access to common QA datasets #. Pre-built indices for common corpora #. Popular reader models, such as Fusion-in-Decoder, LLama #. Evaluation measures As well as access to all of the retrievers (sparse, learned sparse, and dense) and rerankers (from MonoT5 to RankGPT) accessible through the wider `PyTerrier ecosystem `__. .. toctree:: :maxdepth: 1 datamodel measures backends Example Notebooks --------------------------------- Try out the following example notebooks to get started with PyTerrier RAG: - Sparse Retrieval on Natural Questions with FiD and FlanT5 readers: `sparse_retrieval_FiD_FlanT5.ipynb `_ - Sparse Retrieval on Natural Questions with Mistral: `sparse_retrieval_Mistral.ipynb `_ - E5 Dense Retrieval with FiD on Natural Questions: `dense_e5_retrieval_FiD.ipynb `_ - Agentic RAG: R1-Searcher `r1searcher.ipynb `_ - Agentic RAG: Search-R1 `search-r1.ipynb `_ - Agentic RAG: Search-O1 `search-o1.ipynb `_ Credits --------------------------------- - Craig Macdonald, University of Glasgow - Jinyuan Fang, University of Glasgow - Andrew Parry, University of Glasgow - Zaiqiao Meng, University of Glasgow - Sean MacAvaney, University of Glasgow