# neuml/paperai

📄 🤖 AI for medical and scientific papers

Repository: https://github.com/neuml/paperai
Canonical: https://ross.abutalabs.com/products/paperai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: python, machine-learning, nlp, medical, search, scientific-papers, document-search, txtai, ai, artificial-intelligence
Last push: 2026-07-14T13:48:56+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 16, longevity 100
- inputs: {"age_days": 2234, "days_push": 50, "days_rel": 428, "gap_med": 92.0, "n_releases_24m": 3}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1779, forks 146 (observed 2026-08-28T04:05:35.288315+00:00)

## What it is
paperai is an AI application for medical and scientific papers that runs bulk LLM inference and RAG pipelines over article repositories to answer questions and generate reports. It outputs reports in Markdown, CSV, and can annotate answers directly on PDFs.

## Use cases
- answer questions across a corpus of medical papers
- generate bulk LLM reports over scientific literature
- run RAG pipelines over research article repositories
- annotate answers directly on PDF papers
- search medical literature with embeddings
- kick off hundreds of ChatGPT-style prompts over my own documents

## When to choose
- you need bulk question-answering or report generation over medical/scientific paper collections
- you want RAG-backed answers with citations annotated on PDFs
- you want a Python/Docker app built on txtai for literature analysis

## When to avoid
- you need a general-purpose chatbot UI rather than batch report generation
- your documents are not medical/scientific papers and you need a fully generic pipeline
- you need a hosted SaaS solution with no local setup

## Facets
- artifact type: application
- maturity: active
- function: search-engine, rag, llm-inference, nlp, machine-learning, pdf, data-visualization
- domain: artificial-intelligence, healthcare, pdf
- platform: python, cli
- tags: medical-papers, scientific-papers, txtai, document-search, report-generation, natural-language-processing, search, docker

## Member repositories
- neuml/paperai (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:35.288315+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 2026-08-30T03:25:07.814970+00:00, confidence not recorded.
  - readme: https://github.com/neuml/paperai (fetched 2026-08-28T04:05:35.288315+00:00, sha ec443964d114)
  - registry_pypi: https://pypi.org/pypi/paperai/json (fetched 2026-08-29T11:03:16.330627+00:00, sha 2ac87b73343c)
- Data as of 2026-08-30T08:39:29.467469+00:00.