{"adoption": {"forks": 1307, "observed_at": "2026-08-28T04:11:09.685205+00:00", "stars": 15349}, "canonical_url": "https://ross.abutalabs.com/products/unstructured", "card": {"archived": false, "artifact_type": "library", "description": "Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models.  Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.", "domain": ["pdf", "large-language-models"], "enriched": true, "function": ["etl", "ocr", "pdf", "parser", "rag", "nlp", "data-science"], "health_score": 100, "homepage": "https://www.unstructured.io/", "language": "HTML", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["Unstructured-IO/unstructured"], "name": "Unstructured-IO/unstructured", "platform": ["python", "self-hosted", "cloud"], "pushed_at": "2026-08-24T18:59:56+00:00", "repo": "Unstructured-IO/unstructured", "stars": 15349, "tags": ["document-parsing", "pdf-to-text", "document-etl", "chunking", "preprocessing", "langchain", "llm-preparation", "natural-language-processing", "data-engineering", "retrieval-augmented-generation", "docker"], "topics": ["deep-learning", "document-parsing", "machine-learning", "nlp", "ocr", "information-retrieval", "data-pipelines", "ml", "preprocessing", "pdf-to-text", "natural-language-processing", "pdf", "pdf-to-json", "document-image-analysis", "donut", "document-image-processing", "document-parser", "docx", "langchain", "llm"], "urls": [], "use_cases": ["parse resumes from pdfs", "convert pdf documents to text for llm ingestion", "extract structured  from docx and html files", "build a rag pipeline over a document corpus", "ocr scanned documents into machine-readable text", "chunk documents for vector database embedding", "preprocess documents for chatbot knowledge bases"], "what_it_is": "Unstructured is an open-source ETL library and platform for converting complex documents (PDF, DOCX, HTML, images, and 65+ file types) into clean, structured JSON for language models. It provides partitioning, chunking, OCR, and enrichment pipelines that feed RAG and agentic AI workflows.", "when_to_avoid": ["you only need simple text extraction from plain text or well-structured markdown", "you need a lightweight tool without heavy ML dependencies", "your use case is real-time streaming transformation unrelated to documents"], "when_to_choose": ["you need to turn messy documents of many formats into LLM-ready structured data", "you want an open-source document parsing pipeline with optional hosted platform", "you're building RAG or agentic AI applications that ingest PDFs, Office files, or HTML"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/unstructured", "repo": "Unstructured-IO/unstructured", "role": "main", "score": 95}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.685205+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:06:21.684738+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "989b80ac88d3a3f5c79d10831766f5b1085cbf6a6c085938e73df25ab8677018", "fetched_at": "2026-08-28T04:11:09.685205+00:00", "kind": "readme", "missing": false, "url": "https://github.com/Unstructured-IO/unstructured"}, {"content_hash": "153a2febcdf50442605a3e30e0c605f2e49182f139ad49b7aeff7da3499bb564", "fetched_at": "2026-08-29T08:04:17.395047+00:00", "kind": "homepage", "missing": false, "url": "https://www.unstructured.io/"}, {"content_hash": "46f768b65f2dfaebd50afeb21b90c458b72111fb79729266ce9e0c44db853e83", "fetched_at": "2026-08-29T08:04:17.406992+00:00", "kind": "site_page", "missing": false, "url": "https://docs.unstructured.io"}, {"content_hash": "bcfc2067900dbc99b716ce89ab0911e01991b100f521c5ab8507cad9f3e2afdc", "fetched_at": "2026-08-29T08:04:17.404728+00:00", "kind": "site_page", "missing": false, "url": "https://www.unstructured.io/pricing"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 86}, "computed_at": "2026-09-03T02:39:23.370411+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1437, "days_push": 9, "days_rel": 12, "gap_med": 4.0, "n_releases_24m": 89}, "score": 95, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}