# facebookresearch/DrQA

Reading Wikipedia to Answer Open-Domain Questions

Repository: https://github.com/facebookresearch/DrQA
Canonical: https://ross.abutalabs.com/products/drqa
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2023-10-01T21:46:08+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3344, "days_push": 1067, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4468, forks 881 (observed 2026-08-28T04:08:50.913211+00:00)

## What it is
DrQA is a PyTorch implementation of a system for open-domain question answering that combines document retrieval over Wikipedia with a neural machine comprehension model. It includes code, data, and pre-trained models, and can be applied to any large collection of unstructured documents.

## Use cases
- answer factoid questions against wikipedia
- build an open-domain question answering system
- retrieve relevant documents from a large corpus then extract answer spans
- apply machine reading comprehension to my own document collection
- run an interactive qa demo over wikipedia
- evaluate a reading comprehension model on qa datasets

## When to choose
- you need a classic retrieve-then-read open-domain QA pipeline with pre-trained models
- you want to run machine reading at scale over Wikipedia or a custom document set
- you need a research baseline for extractive question answering in PyTorch

## When to avoid
- you want a modern LLM or RAG stack with vector embeddings rather than a 2017-era span-extraction model
- you need actively maintained software with recent updates and broad community support
- you need generative answers rather than extracted answer spans

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, machine-learning, search-engine, rag
- domain: artificial-intelligence, large-language-models
- platform: python
- tags: question-answering, reading-comprehension, wikipedia, pytorch, document-retrieval, open-domain-qa, research, natural-language-processing, search, linux, macos

## Member repositories
- facebookresearch/DrQA (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:50.913211+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 2026-08-29T18:20:37.542304+00:00, confidence not recorded.
  - readme: https://github.com/facebookresearch/DrQA (fetched 2026-08-28T04:08:50.913211+00:00, sha 605961549b44)
- Data as of 2026-08-30T08:39:29.467469+00:00.