{"adoption": {"forks": 95, "observed_at": "2026-08-28T04:05:34.183186+00:00", "stars": 1772}, "canonical_url": "https://ross.abutalabs.com/products/extractous", "card": {"archived": false, "artifact_type": "library", "description": "Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.", "domain": ["pdf", "files"], "enriched": true, "function": ["parser", "ocr", "pdf", "etl", "rag"], "health_score": 20, "homepage": null, "language": "Rust", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["yobix-ai/extractous"], "name": "yobix-ai/extractous", "platform": ["rust", "python", "cross-platform"], "pushed_at": "2024-12-21T10:13:30+00:00", "repo": "yobix-ai/extractous", "stars": 1772, "tags": ["unstructured-data", "document-extraction", "apache-tika", "text-extraction", "docx", "bindings", "natural-language-processing", "data-engineering", "retrieval-augmented-generation"], "topics": ["extraction", "pdf", "tika", "unstructured", "unstructured-data", "data-pipelines", "docx", "etl", "etl-pipelines", "llm", "machine-learning", "natural-language-processing", "nlp", "ocr", "pdf-parser", "rag", "rust"], "urls": [], "use_cases": ["extract text from pdf files", "parse docx documents into plain text", "build rag document ingestion pipelines", "extract content from emails and html locally without external apis", "replace unstructured-io for faster document parsing", "preprocess documents for llm pipelines"], "what_it_is": "Extractous is a fast Rust library for extracting content and metadata from unstructured documents like PDF, Word, Excel, HTML, CSV, and email, with bindings for multiple languages including Python. It uses a natively compiled Apache Tika internally for formats not natively supported and is positioned as a much faster alternative to unstructured-io.", "when_to_avoid": ["you need deep document structure analysis or chunking strategies rather than raw extraction", "you rely on unstructured-io's element classification features", "you need a managed extraction API service"], "when_to_choose": ["you need fast, in-process document extraction without calling external services", "performance and memory efficiency matter for large extraction workloads", "you want a Rust core with Python bindings for etl or rag pipelines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/extractous", "repo": "yobix-ai/extractous", "role": "main", "score": 24}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.183186+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:25:58.754166+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "2f387b4608a93e6bc4aa47c58e488ce3357c6266991c21eab2506760b52ef870", "fetched_at": "2026-08-28T04:05:34.183186+00:00", "kind": "readme", "missing": false, "url": "https://github.com/yobix-ai/extractous"}, {"content_hash": "ae7d1a88e20f6c92c8161e4c7b369c20ba1927f6c7e597d14500c4fc2b2c7a7a", "fetched_at": "2026-08-29T11:04:06.947005+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/extractous"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 58, "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": 820, "days_push": 620, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 24, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}