{"adoption": {"forks": 4697, "observed_at": "2026-08-28T04:12:19.317615+00:00", "stars": 65603}, "canonical_url": "https://ross.abutalabs.com/products/docling", "card": {"archived": false, "artifact_type": "library", "description": "Get your documents ready for gen AI", "domain": ["artificial-intelligence", "pdf", "files", "large-language-models"], "enriched": true, "function": ["parser", "pdf", "ocr", "nlp", "machine-learning", "rag"], "health_score": 100, "homepage": "https://docling-project.github.io/docling", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["docling-project/docling", "docling-project/docling-serve"], "name": "Docling", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-26T16:15:06+00:00", "repo": "docling-project/docling", "stars": 65603, "tags": ["document-parsing", "document-conversion", "pdf-to-markdown", "genai", "table-extraction", "docx", "pptx", "xlsx", "html-parsing", "natural-language-processing", "retrieval-augmented-generation"], "topics": ["ai", "convert", "documents", "pdf", "tables", "document-parser", "document-parsing", "docx", "html", "markdown", "pdf-converter", "pdf-to-json", "pdf-to-text", "pptx", "xlsx"], "urls": [], "use_cases": ["convert pdfs to markdown for llm ingestion", "extract tables from pdf documents", "parse docx and pptx files into structured", "prepare documents for rag pipelines", "ocr scanned pdf documents", "batch convert office documents to text", "extract document structure and reading order"], "what_it_is": "Docling is a Python library that parses and converts documents across many formats (PDF, DOCX, PPTX, XLSX, HTML, images, audio, and more) into structured representations like Markdown and JSON, with advanced PDF understanding including layout, tables, and reading order. It integrates with the generative AI ecosystem to prepare documents for RAG pipelines and LLM consumption.", "when_to_avoid": ["you only need simple plain-text extraction with no structure", "you need a lightweight dependency-free converter", "your documents are already clean structured data like CSV or JSON"], "when_to_choose": ["you need high-quality PDF parsing with layout and table understanding", "you want a unified parser for many document formats in Python", "you are building RAG or gen AI pipelines that ingest documents", "you need local, self-hosted document conversion without cloud APIs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/docling-project/docling", "repo": "docling-project/docling", "role": "main", "score": 86}, {"path": "/repos/docling-project/docling-serve", "repo": "docling-project/docling-serve", "role": "backend", "score": 85}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:19.317615+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:17:24.057272+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7e3ae5210b3be509a5eee4691fb9840f8eae81aafcfece534e828fe3ee6c7d4c", "fetched_at": "2026-08-28T04:12:19.317615+00:00", "kind": "readme", "missing": false, "url": "https://github.com/docling-project/docling"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 56, "rhythm": 87}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 785, "days_push": 7, "days_rel": 7, "gap_med": 3.0, "n_releases_24m": 181}, "score": 86, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}