{"adoption": {"forks": 260, "observed_at": "2026-08-28T04:08:09.896090+00:00", "stars": 3564}, "canonical_url": "https://ross.abutalabs.com/products/gptpdf", "card": {"archived": false, "artifact_type": "library", "description": "Using GPT to parse PDF", "domain": ["pdf", "large-language-models", "developer-tools"], "enriched": true, "function": ["pdf", "ocr", "llm-inference", "parser"], "health_score": 30, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["CosmosShadow/gptpdf"], "name": "CosmosShadow/gptpdf", "platform": ["python", "cross-platform"], "pushed_at": "2025-04-17T07:20:29+00:00", "repo": "CosmosShadow/gptpdf", "stars": 3564, "tags": ["pdf-to-markdown", "vision-language-model", "document-parsing", "openai-api"], "topics": [], "urls": [], "use_cases": ["convert pdf to markdown", "extract math formulas from pdf", "parse tables and charts from pdf documents", "ocr pdf with gpt-4o", "convert research papers to markdown", "extract images from pdf while converting text"], "what_it_is": "A small Python library that parses PDF files into Markdown using a vision-capable LLM such as GPT-4o. It uses PyMuPDF to detect non-text areas and sends them to a multimodal model to handle formulas, tables, charts, and images.", "when_to_avoid": ["you need fully offline or free parsing with no LLM API costs", "you must process large volumes of PDFs where per-page API charges are prohibitive", "you need pixel-perfect layout reproduction rather than Markdown output"], "when_to_choose": ["you need high-fidelity PDF-to-Markdown conversion including formulas, tables, and charts", "you have access to an OpenAI-compatible vision model API and per-page cost (~$0.013) is acceptable", "you want a simple, minimal Python API (parse_pdf) rather than a heavy pipeline"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gptpdf", "repo": "CosmosShadow/gptpdf", "role": "main", "score": 31}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:09.896090+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:34:10.905734+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6fe2e5e57a76d95e826976a2f13abe1125aa9740428f822bee098ec94ad8d08b", "fetched_at": "2026-08-28T04:08:09.896090+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CosmosShadow/gptpdf"}, {"content_hash": "272ed6a1d07b77167f3788f4e89c0485b700258b9f84cac52f0e9c313d92aaaf", "fetched_at": "2026-08-29T09:27:46.847729+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/gptpdf/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 17, "longevity": 56, "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": 796, "days_push": 503, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 31, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}