{"adoption": {"forks": 133, "observed_at": "2026-08-28T04:05:34.461492+00:00", "stars": 1775}, "canonical_url": "https://ross.abutalabs.com/products/docquery", "card": {"archived": false, "artifact_type": "library", "description": "An easy way to extract information from documents", "domain": ["pdf", "machine-learning", "developer-tools"], "enriched": true, "function": ["nlp", "ocr", "pdf", "machine-learning", "llm-inference", "cli"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["impira/docquery"], "name": "impira/docquery", "platform": ["python", "cli", "windows"], "pushed_at": "2023-05-03T07:43:26+00:00", "repo": "impira/docquery", "stars": 1775, "tags": ["document-question-answering", "document-parsing", "invoice-extraction", "ocr", "transformers", "natural-language-processing", "documents", "macos", "linux"], "topics": [], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/docquery", "repo": "impira/docquery", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.461492+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:25:20.670831+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ac579bfa2e570c93340cba2236954d34585e6b963c21acfe170ce4c683dec1fe", "fetched_at": "2026-08-28T04:05:34.461492+00:00", "kind": "readme", "missing": false, "url": "https://github.com/impira/docquery"}, {"content_hash": "b2a59f3e56df796e9d554361eb76f55beb04c0e68716125a24d60862e0045776", "fetched_at": "2026-08-29T11:03:50.333209+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/docquery/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1486, "days_push": 1218, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}