{"data":{"slug":"future-house-paper-qa","name":"paper-qa","tagline":"High accuracy RAG for answering questions from scientific documents with citations","github_url":"https://github.com/Future-House/paper-qa","owner":"Future-House","repo":"paper-qa","owner_avatar_url":"https://avatars.githubusercontent.com/u/131727825?v=4","primary_language":"Python","stars":9048,"forks":907,"topics":["ai","rag","science","search"],"archived":false,"github_pushed_at":"2026-08-12T15:33:57+00:00","maintenance_label":"Very active","stars_delta_30d":154,"url":"https://www.graphcanon.com/tools/future-house-paper-qa","markdown_url":"https://www.graphcanon.com/tools/future-house-paper-qa.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/future-house-paper-qa","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=future-house-paper-qa","description":"High accuracy RAG for answering questions from scientific documents with citations","homepage_url":"https://futurehouse.gitbook.io/futurehouse-cookbook","license":"Apache-2.0","open_issues":141,"watchers":62,"ai_summary":"PaperQA2 version 5 offers a robust retrieval-augmented generation (RAG) approach specifically tailored for processing and querying scientific document content, using LLMs to enhance its capabilities.","readme_excerpt":"## Installation\n\nFor a non-development setup,\ninstall PaperQA2 (aka version 5) from [PyPI](https://pypi.org/project/paper-qa/).\nNote version 5 requires Python 3.11+.\n\n```bash\npip install paper-qa>=5\n```\n\nFor development setup,\nplease refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file.\n\nPaperQA2 uses an LLM to operate,\nso you'll need to either set an appropriate [API key environment variable][LiteLLM providers]\n(i.e. `export OPENAI_API_KEY=sk-...`)\nor set up an open source LLM server (i.e. using [llamafile](https://github.com/Mozilla-Ocho/llamafile).\nAny LiteLLM compatible model can be configured to use with PaperQA2.\n\nIf you need to index a large set of papers (100+),\nyou will likely want an API key for both\n[Crossref](https://www.crossref.org/documentation/metadata-plus/metadata-plus-keys/)\nand [Semantic Scholar](https://www.semanticscholar.org/product/api#api-key),\nwhich will allow you to avoid hitting public rate limits using these metadata services.\nThose can be exported as `CROSSREF_API_KEY` and `SEMANTIC_SCHOLAR_API_KEY` variables.","github_created_at":"2023-02-05T01:07:25+00:00","created_at":"2026-07-07T17:37:20.696504+00:00","updated_at":"2026-08-18T12:01:10.383424+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":"ai","name":"ai"},{"slug":"rag","name":"rag"},{"slug":"science","name":"science"},{"slug":"search","name":"search"}],"trust":{"provenance":{"is_fork":false,"github_id":597583114,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-18T12:01:09.572Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":5,"last_release_at":"2026-08-12T15:32:44Z","stars_delta_30d":154,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:09:21.661Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-18T12:01:10.018Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-08-18T12:01:10.018Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-18T12:01:10.018Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-18T12:01:10.018Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":4,"requires_docker":false},"constraints":{"min_ram_gb":4,"requires_docker":false},"when_to_use":["Your project specifically requires processing and querying scientific documents, as PaperQA2 offers specialized capabilities tuned for this domain.","You are integrating high-fidelity search functionalities into a tool targeting researchers or students who need to query scientific literature with accuracy."],"when_not_to_use":["If your use case does not involve scientific document processing, another RAG system better suited to your specific type of documents (e.g., legal, medical) might be more fitting.","In scenarios where real-time performance is critical and extensive indexing or access to external APIs for large-scale paper handling becomes a bottleneck."],"source":"enrich:decision_facts","observed_at":"2026-07-12T09:45:41.159Z"},"constraint_facets":{"min_ram_gb":4,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Min 4 GB RAM"},{"label":"Adopt for","value":"PaperQA2 version 5 is a retrieval-augmented generation (RAG) system optimized for extracting information from scientific documents, enhancing user queries with citations."},{"label":"License detail","value":"'Apache-2.0' - Permissive free software license that allows for both non-commercial use and commercial exploitation of the package."}]}}