{"adoption": {"forks": 417, "observed_at": "2026-08-28T04:09:59.749717+00:00", "stars": 7413}, "canonical_url": "https://ross.abutalabs.com/products/megaparse", "card": {"archived": false, "artifact_type": "library", "description": "File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs. ", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "rag", "llm-inference"], "health_score": 36, "homepage": "https://megaparse.com", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["QuivrHQ/MegaParse"], "name": "QuivrHQ/MegaParse", "platform": ["python", "cross-platform", "self-hosted"], "pushed_at": "2025-02-21T15:21:14+00:00", "repo": "QuivrHQ/MegaParse", "stars": 7413, "tags": ["document-parsing", "pdf-to-markdown", "docx", "pptx", "llm-ingestion", "data-preparation", "natural-language-processing", "retrieval-augmented-generation", "docker"], "topics": ["docx", "llm", "parser", "pdf", "powerpoint"], "urls": [], "use_cases": ["parse pdfs for llm ingestion", "convert docx to markdown for rag", "extract tables from pdf without losing data", "prepare powerpoint slides for a chatbot knowledge base", "build a document ingestion pipeline for a vector database", "run a self-hosted document parsing api"], "what_it_is": "MegaParse is a Python library that parses PDFs, Word, PowerPoint, Excel, CSV, and text documents into LLM-friendly formats with a focus on zero information loss, including tables, headers, footers, and images. It offers both standard parsing and a vision-based mode using multimodal models like GPT-4o and Claude, and can also be run as an API service.", "when_to_avoid": ["you only need plain-text extraction from simple text-based PDFs", "you cannot provide an OpenAI or Anthropic API key for the vision parser", "you need a fully offline solution without installing poppler and tesseract", "your environment runs Python below 3.11"], "when_to_choose": ["you need high-fidelity document parsing for RAG or LLM pipelines", "your documents contain tables, headers, footers, or images that naive parsers drop", "you want a benchmarked parser with vision-model support", "you prefer an open-source, self-hostable alternative to paid parsing APIs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/megaparse", "repo": "QuivrHQ/MegaParse", "role": "main", "score": 29}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:59.749717+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:37:46.969669+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52385b3a0adf3e8dddd6664d87cf805438ee92be411ebd7300d2b5dc4322bf6d", "fetched_at": "2026-08-28T04:09:59.749717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/QuivrHQ/MegaParse"}, {"content_hash": "f1b197872b3d5c35f564e2a000908cb3f0fd177813820c5357510994338ecfad", "fetched_at": "2026-08-29T08:33:29.828362+00:00", "kind": "homepage", "missing": false, "url": "https://megaparse.com"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 7, "longevity": 59, "rhythm": 40}, "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": 826, "days_push": 558, "days_rel": 565, "gap_med": 0, "n_releases_24m": 32}, "score": 29, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}