# Future-House/paper-qa

High accuracy RAG for answering questions from scientific documents with citations

Repository: https://github.com/Future-House/paper-qa
Canonical: https://ross.abutalabs.com/products/paper-qa
Homepage: https://futurehouse.gitbook.io/futurehouse-cookbook
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, rag, search, science
Last push: 2026-08-26T11:53:52+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 85, longevity 93
- inputs: {"age_days": 1306, "days_push": 7, "days_rel": 21, "gap_med": 3.0, "n_releases_24m": 65}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 9103, forks 913 (observed 2026-08-28T04:10:28.390281+00:00)

## What it is
PaperQA2 is a Python library and CLI for high-accuracy retrieval augmented generation (RAG) over PDFs, text, Office documents, and source code, focused on scientific literature. It answers questions with inline citations and supports agentic or manual document indexing and querying.

## Use cases
- answer questions from scientific papers with citations
- build a RAG pipeline over PDFs
- summarize scientific literature
- detect contradictions across papers
- search and query a corpus of research documents
- run literature question answering from the command line

## When to choose
- you need cited, high-accuracy QA over scientific PDFs
- you want a Python RAG library tuned for academic literature
- you need agentic document querying with local or hosted LLMs

## When to avoid
- you need a general-purpose chatbot without document grounding
- you want a no-code hosted research platform rather than a library
- your documents are not text-extractable (e.g., scanned images without OCR)

## Facets
- artifact type: library
- maturity: active
- function: rag, search-engine, llm-inference, pdf, nlp
- domain: large-language-models, pdf
- platform: python, cli, cross-platform
- tags: paperqa2, scientific-literature, citations, question-answering, pdf-qa, retrieval-augmented-generation, natural-language-processing, science

## Member repositories
- Future-House/paper-qa (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:28.390281+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:23:58.762556+00:00, confidence not recorded.
  - readme: https://github.com/Future-House/paper-qa (fetched 2026-08-28T04:10:28.390281+00:00, sha bf6a01f07fd9)
  - homepage: https://futurehouse.gitbook.io/futurehouse-cookbook (fetched 2026-08-29T08:23:44.584917+00:00, sha 3dcaad503ca5)
  - registry_pypi: https://pypi.org/pypi/paper-qa/json (fetched 2026-08-29T08:23:44.587479+00:00, sha 1fc88d346592)
- Data as of 2026-08-30T08:39:29.467469+00:00.