# impira/docquery

An easy way to extract information from documents

Repository: https://github.com/impira/docquery
Canonical: https://ross.abutalabs.com/products/docquery
Language: Python
License: MIT
License Family: permissive
Last push: 2023-05-03T07:43:26+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 1486, "days_push": 1218, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1775, forks 133 (observed 2026-08-28T04:05:34.461492+00:00)

## What it is
DocQuery is a Python library and CLI tool that uses large language models to answer questions about semi-structured and unstructured documents such as PDFs and scanned images. It provides a document-question-answering pipeline and a Document abstraction for parsing files, with OCR support via tesseract.

## Use cases
- extract invoice numbers from pdf invoices
- ask questions about scanned documents
- find effective dates in a folder of contracts
- parse information from unstructured documents
- document question answering with python
- ocr and query scanned images

## When to choose
- you need to extract specific fields from PDFs or scanned images via natural language questions
- you want both a CLI for batch document scanning and a Python library
- you want a simple document-question-answering pipeline built on transformers

## When to avoid
- you need actively maintained software with recent updates and support
- you need high-throughput production document processing at scale
- you need general-purpose OCR only, without question answering

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, ocr, pdf, machine-learning, llm-inference, cli
- domain: pdf, machine-learning, developer-tools
- platform: python, cli, windows
- tags: document-question-answering, document-parsing, invoice-extraction, ocr, transformers, natural-language-processing, documents, macos, linux

## Member repositories
- impira/docquery (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:34.461492+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 2026-08-30T03:25:20.670831+00:00, confidence not recorded.
  - readme: https://github.com/impira/docquery (fetched 2026-08-28T04:05:34.461492+00:00, sha ac579bfa2e57)
  - registry_pypi: https://pypi.org/pypi/docquery/json (fetched 2026-08-29T11:03:50.333209+00:00, sha b2a59f3e56df)
- Data as of 2026-08-30T08:39:29.467469+00:00.