{"adoption": {"forks": 11, "observed_at": "2026-08-28T04:03:38.443739+00:00", "stars": 1115}, "canonical_url": "https://ross.abutalabs.com/products/easydoc", "card": {"archived": false, "artifact_type": "service", "description": null, "domain": ["pdf", "artificial-intelligence", "large-language-models", "apis"], "enriched": true, "function": ["parser", "ocr", "pdf", "rag", "llm-inference", "nlp"], "health_score": 38, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["easydoc-ai/easydoc"], "name": "easydoc-ai/easydoc", "platform": ["cloud", "python", "self-hosted"], "pushed_at": "2025-07-08T09:25:18+00:00", "repo": "easydoc-ai/easydoc", "stars": 1115, "tags": ["document-parsing", "multimodal", "document-to-json", "llm-pipelines", "document-processing-api", "hierarchical-json", "table-extraction", "retrieval-augmented-generation", "data-engineering", "web-server"], "topics": [], "urls": [], "use_cases": ["convert pdf documents to structured json for llm pipelines", "extract tables and figures from documents into machine-readable format", "parse resumes and reports into hierarchical data", "prepare fine-tuning datasets from unstructured documents", "build rag pipelines over pdf documents", "reconstruct document hierarchy into mind maps for ai context"], "what_it_is": "EasyDoc is a multimodal document processing API that converts unstructured documents like PDFs into hierarchical, machine-readable JSON. It identifies content blocks, reconstructs document structure, and parses tables and figures to feed LLM pipelines with optimized context.", "when_to_avoid": ["you need fully offline processing without calling a hosted api", "you only need simple plain-text extraction from pdfs", "you require a self-contained library with no external service dependency"], "when_to_choose": ["you need high-quality structured extraction from complex pdfs with tables and figures", "you want an api-based document parser purpose-built for llm and rag applications", "you need content-block grouping rather than raw line-by-line text extraction"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/easydoc", "repo": "easydoc-ai/easydoc", "role": "main", "score": 35}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.443739+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:42:10.561192+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5bc5540680bdc976a31062c1df4849b28291d290a9b79ef9a95a0d0a44536a52", "fetched_at": "2026-08-28T04:03:38.443739+00:00", "kind": "readme", "missing": false, "url": "https://github.com/easydoc-ai/easydoc"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 30, "longevity": 44, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 616, "days_push": 421, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 35, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}