{"id":14567405,"url":"https://github.com/yixuantt/MultiHop-RAG","last_synced_at":"2025-09-04T09:32:08.209Z","repository":{"id":219861464,"uuid":"747052840","full_name":"yixuantt/MultiHop-RAG","owner":"yixuantt","description":"Repository for \"MultiHop-RAG: A Dataset for Evaluating Retrieval-Augmented Generation Across Documents\" (COLM 2024)","archived":false,"fork":false,"pushed_at":"2024-11-19T09:24:38.000Z","size":8198,"stargazers_count":205,"open_issues_count":6,"forks_count":14,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-11-19T10:27:14.804Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yixuantt.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-01-23T07:00:54.000Z","updated_at":"2024-11-19T09:24:42.000Z","dependencies_parsed_at":"2024-01-30T03:38:35.433Z","dependency_job_id":"3f09ea24-333f-4b74-b8a5-62dfd0cc663f","html_url":"https://github.com/yixuantt/MultiHop-RAG","commit_stats":null,"previous_names":["yixuantt/multihop-rag"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yixuantt%2FMultiHop-RAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yixuantt%2FMultiHop-RAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yixuantt%2FMultiHop-RAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yixuantt%2FMultiHop-RAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yixuantt","download_url":"https://codeload.github.com/yixuantt/MultiHop-RAG/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":231949213,"owners_count":18450456,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-09-07T05:01:16.000Z","updated_at":"2024-12-31T05:32:15.194Z","avatar_url":"https://github.com/yixuantt.png","language":"Python","funding_links":[],"categories":["Retrieval Augmented Generation (RAG) Datasets \u003ca id=\"retrieval-augmented-generation-rag-datasets\"\u003e\u003c/a\u003e","A01_文本生成_文本对话"],"sub_categories":["Evaluation Datasets \u003ca id=\"evaluation02\"\u003e\u003c/a\u003e","大语言对话模型及数据"],"readme":"# 💡 MultiHop-RAG\nA Dataset for **Evaluating Retrieval-Augmented Generation Across Documents**  \n\n   \n## 🚀 Overview\n**MultiHop-RAG**: a QA dataset to evaluate retrieval and reasoning across documents with metadata in the RAG pipelines. It contains 2556 queries, with evidence for each query distributed across 2 to 4 documents. The queries also involve document metadata, reflecting complex scenarios commonly found in real-world RAG applications.  \n\n📄 Paper Link **(Accepted by COLM 2024)**: [MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries](https://arxiv.org/pdf/2401.15391.pdf)  \n🤗 [Hugging Face dataloader](https://huggingface.co/datasets/yixuantt/MultiHopRAG)\n\n![rag.png](resource/rag.png)\n\n## Simple Use Case\n\n**1. For Retrieval**\n\nPlease try '**simple_retrieval.py**,' a sample use case demonstrating retrieval using this dataset. \n```\npip install llama-index==0.9.40\n```\n```shell\n# test simple retrieval and save results\npython simple_retrieval.py --retriever BAAI/llm-embedder\n\n# test simple retrieval with rerank and save results\npython simple_retrieval.py --retriever BAAI/llm-embedder --rerank\n```\n\n**2. For QA**\n\nPlease try '**qa_llama.py**,' a sample use case demonstrating query and answer with llama using this dataset. \n\n```\npython qa_llama.py\n```\n## Evaluation\n\n**1. For Retrieval**: 'retrieval_evaluate.py' \n\n**2. For QA**: 'qa_evaluate.py' \n```\npython retrieval_evaluate.py --file {saved_file_path}\n```\n## Construction Pipeline\n\nFor research purposes, we open-sourced part of the code to construct the dataset. However, the current structure of the code is not very tidy. We will organize it in the future.\n\n💡 Just For Reference: pipeline/\n\n## Citation\n```\n@misc{tang2024multihoprag,\n      title={MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries}, \n      author={Yixuan Tang and Yi Yang},\n      year={2024},\n      eprint={2401.15391},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n```\n## License\nMultiHop-RAG is licensed under [ODC-BY](https://opendatacommons.org/licenses/by/1-0/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyixuantt%2FMultiHop-RAG","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyixuantt%2FMultiHop-RAG","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyixuantt%2FMultiHop-RAG/lists"}