{"adoption": {"forks": 241, "observed_at": "2026-08-28T04:05:36.406724+00:00", "stars": 1788}, "canonical_url": "https://ross.abutalabs.com/products/docconv", "card": {"archived": false, "artifact_type": "library", "description": "Converts PDF, DOC, DOCX, XML, HTML, RTF, etc to plain text", "domain": ["files", "pdf", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "http-server", "cli"], "health_score": 24, "homepage": null, "language": "Go", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["sajari/docconv"], "name": "sajari/docconv", "platform": ["go", "cli"], "pushed_at": "2024-07-01T12:41:17+00:00", "repo": "sajari/docconv", "stars": 1788, "tags": ["document-conversion", "text-extraction", "plain-text", "docx", "rtf", "html-to-text", "docd", "search", "linux", "macos", "docker", "web-server"], "topics": ["rtf", "docx", "xml", "html", "rtf-files", "docs", "conversion", "pdf", "pdf-converter", "word", "go"], "urls": [], "use_cases": ["extract plain text from pdf files in go", "convert docx documents to text for indexing", "run a document-to-text conversion service", "parse html pages into clean readable text", "ocr images to extract text", "convert rtf and odt files to plain text"], "what_it_is": "A Go library (with a companion docd CLI/HTTP service) that converts PDF, DOC, DOCX, XML, HTML, RTF, ODT, Pages documents and images into plain text. It can be used as a library, a command-line tool, or a Dockerized HTTP service that accepts multipart uploads and returns extracted text and metadata as JSON.", "when_to_avoid": ["you need to preserve formatting or layout rather than plain text", "you're not in a Go/Unix environment and can't install external dependencies like poppler or wv", "you need high-fidelity PDF parsing with tables and structure"], "when_to_choose": ["you need text extraction from many document formats in a Go application", "you want a ready-made HTTP service or Docker container for document conversion", "you're building a search pipeline that needs documents normalized to plain text"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/docconv", "repo": "sajari/docconv", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:36.406724+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:23:27.439273+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "751edc4b26f3cc0631dae79f3c089f4d68fde65808892fee7c76d7c493e290e3", "fetched_at": "2026-08-28T04:05:36.406724+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sajari/docconv"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4688, "days_push": 793, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}