{"adoption": {"forks": 394, "observed_at": "2026-08-28T04:05:03.328724+00:00", "stars": 1557}, "canonical_url": "https://ross.abutalabs.com/products/docling-api", "card": {"archived": false, "artifact_type": "service", "description": "Easily deployable and scalable backend server that efficiently converts various document formats (pdf, docx, pptx, html, images, etc) into Markdown. With support for both CPU and GPU processing, it is Ideal for large-scale workflows, it offers text/table extraction, OCR, and batch processing with sync/async endpoints.", "domain": ["pdf", "files", "developer-tools", "self-hosted"], "enriched": true, "function": ["ocr", "pdf", "parser", "api-framework", "http-server", "etl"], "health_score": 78, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["drmingler/docling-api"], "name": "drmingler/docling-api", "platform": ["python", "self-hosted"], "pushed_at": "2026-08-04T08:06:41+00:00", "repo": "drmingler/docling-api", "stars": 1557, "tags": ["docling", "fastapi", "celery", "redis", "markdown-conversion", "document-conversion", "batch-processing", "pdf-to-markdown", "natural-language-processing", "docker", "web-server", "gpu"], "topics": ["api", "fastapi", "markdown-parser", "pdf-chatbot", "pdf-conversion", "pdf-converter", "pdf-parser", "pdf-parsing", "pdf-to-markdown"], "urls": [], "use_cases": ["convert pdf files to markdown via an api", "extract text and tables from docx and pptx documents", "ocr scanned pdfs into markdown", "batch convert documents for llm rag pipelines", "self-host a document parsing service with gpu acceleration", "parse pdfs for chatbot ingestion"], "what_it_is": "A self-hostable FastAPI backend service that converts documents (PDF, DOCX, PPTX, HTML, images, CSV, AsciiDoc, Markdown) into Markdown using IBM's Docling parser. It supports CPU and GPU processing, OCR, table/image extraction, and sync/async batch conversion with Celery and Redis job tracking.", "when_to_avoid": [], "when_to_choose": ["you need a scalable, deployable document-to-markdown conversion API rather than a library", "you need OCR, table extraction, and batch/async job processing in one service", "you want GPU-accelerated parsing for large-scale workflows"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/docling-api", "repo": "drmingler/docling-api", "role": "main", "score": 65}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:03.328724+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:29:56.872056+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "37c3f6dead83c049a4a6fc87b32690e37449d07fc6109b1b854603500fbc831d", "fetched_at": "2026-08-28T04:05:03.328724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/drmingler/docling-api"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 47, "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": 666, "days_push": 29, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 65, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}