{"data":{"slug":"ruc-nlpir-flashrag","name":"FlashRAG","tagline":"A Python toolkit for efficient RAG research","github_url":"https://github.com/RUC-NLPIR/FlashRAG","owner":"RUC-NLPIR","repo":"FlashRAG","owner_avatar_url":"https://avatars.githubusercontent.com/u/139615285?v=4","primary_language":"Python","stars":3542,"forks":311,"topics":["benchmark","datasets","large-language-models","retrieval-augmented-generation"],"archived":false,"github_pushed_at":"2026-08-09T05:52:43+00:00","maintenance_label":"Active","stars_delta_30d":20,"url":"https://www.graphcanon.com/tools/ruc-nlpir-flashrag","markdown_url":"https://www.graphcanon.com/tools/ruc-nlpir-flashrag.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ruc-nlpir-flashrag","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ruc-nlpir-flashrag","description":"⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)","homepage_url":"https://arxiv.org/abs/2405.13576","license":"MIT","open_issues":38,"watchers":20,"ai_summary":"FlashRAG provides tools and benchmarks for retrieval-augmented generation with large language models.","readme_excerpt":"## :wrench: Installation\n \n \n\n\nTo get started with FlashRAG, you can simply install it with pip:\n\n```base\npip install flashrag-dev --pre\n```\n\nOr you can clone it from Github and install (requires Python 3.10+):\n\n```bash\ngit clone https://github.com/RUC-NLPIR/FlashRAG.git\ncd FlashRAG\npip install -e .\n```\n\nIf you want to use vllm, sentence-transformers or pyserini, you can install the optional dependencies:\n\n```bash\n\n---\n\n# Install all extra dependencies\npip install flashrag-dev[full]\n\n---\n\n# Install vllm for faster speed\npip install vllm>=0.4.1\n\n---\n\n# Install sentence-transformers\npip install sentence-transformers\n\n---\n\n# Install pyserini for bm25\npip install pyserini\n```\n\nDue to the incompatibility when installing `faiss` using `pip`, it is necessary to use the following conda command for installation.\n\n```bash\n\n---\n\n## :bookmark: License\n\nFlashRAG is licensed under the [<u>MIT License</u>](./LICENSE).","github_created_at":"2024-03-14T01:40:33+00:00","created_at":"2026-07-07T17:35:41.561754+00:00","updated_at":"2026-08-18T00:01:51.247559+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"benchmark","name":"benchmark"},{"slug":"datasets","name":"datasets"},{"slug":"large-language-models","name":"large language models"},{"slug":"python","name":"python"},{"slug":"retrieval-augmented-generation","name":"retrieval-augmented-generation"}],"trust":{"provenance":{"is_fork":false,"github_id":771808616,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T00:01:48.298Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":0,"days_since_push":8,"last_release_at":"2025-08-18T09:22:42Z","stars_delta_30d":20,"open_issues_delta_30d":-2},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":59,"high_count":0,"last_scan_at":"2026-07-11T11:05:58.758Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T00:01:50.891Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-18T00:01:50.891Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-18T00:01:50.891Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python version greater than or equal to 3.10","Optional dependencies include vllm, sentence-transformers, pyserini. Faiss installation requires conda."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["When you need specialized tools for retrieval-augmented generation (RAG) within large-language-model environments, offering a direct pip install option simplifies quick integration into your projects.","If the project requires the use of vllm for speed improvements or sentence-transformers and pyserini for specific functionalities like bm25, FlashRAG offers distinct dependency installation commands."],"when_not_to_use":["Avoid using FlashRAG if you do not have Python version 3.10+, as the toolkit requires this minimum Python version.","Do not use FlashRAG when your research or project involves extensive use of faiss, because it needs to be installed via conda due to pip installation incompatibilities."],"source":"enrich:decision_facts","observed_at":"2026-07-14T18:21:17.818Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Python version greater than or equal to 3.10; Optional dependencies include vllm, sentence-transformers, pyserini. Faiss installation requires conda."},{"label":"Adopt for","value":"FlashRAG caters to Python-based RAG research with streamlined installation options and flexibility in optional dependency choices for improved performance."},{"label":"License detail","value":"FlashRAG is distributed under the MIT License"}]}}