{"adoption": {"forks": 200, "observed_at": "2026-08-28T04:03:58.700562+00:00", "stars": 1203}, "canonical_url": "https://ross.abutalabs.com/products/open-semantic-search", "card": {"archived": false, "artifact_type": "application", "description": "Open Source research tool to search, browse, analyze and explore large document collections by Semantic Search Engine and Open Source Text Mining & Text Analytics platform (Integrates ETL for document processing, OCR for images & PDF, named entity recognition for persons, organizations & locations, metadata management by thesaurus & ontologies, search user interface & search apps for fulltext search, faceted search & knowledge graph)", "domain": ["developer-tools", "osint", "analytics", "self-hosted", "text-editors"], "enriched": true, "function": ["search-engine", "ocr", "nlp", "etl", "data-visualization", "web-scraping", "pdf", "analytics"], "health_score": 30, "homepage": "https://opensemanticsearch.org", "language": "Shell", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["opensemanticsearch/open-semantic-search"], "name": "opensemanticsearch/open-semantic-search", "platform": ["self-hosted", "python"], "pushed_at": "2025-04-19T14:57:11+00:00", "repo": "opensemanticsearch/open-semantic-search", "stars": 1203, "tags": ["semantic-search", "faceted-search", "fulltext-search", "named-entity-recognition", "text-mining", "knowledge-graph", "thesaurus", "ontologies", "investigative-journalism", "document-processing", "solr", "spacy", "tika", "exploratory-search", "collaborative-annotation", "desktop-search", "search", "natural-language-processing", "linux", "docker", "web-server"], "topics": ["search", "search-engine", "search-interface", "ocr", "ui", "python", "semantic", "skos", "thesaurus", "ontologies", "text-mining", "text-analysis", "annotation", "research-tool", "named-entity-recognition", "osint", "faceted-search", "fulltext-search", "journalism", "investigative-journalism"], "urls": [], "use_cases": ["search and explore large document collections with semantic and faceted search", "extract text and run OCR on PDFs and images for indexing", "perform named entity recognition for persons, organizations, and locations", "build a self-hosted research tool for investigative journalism", "monitor and analyze news and heterogeneous document sets", "tag and annotate documents collaboratively for knowledge management", "explore document sets with interactive filters and data visualization"], "what_it_is": "An open-source integrated search server and ETL framework for processing, analyzing, and exploring large document collections. It combines fulltext and faceted search with text mining, OCR, named entity recognition, and knowledge graph features on your own server.", "when_to_avoid": ["you only need a lightweight fulltext search for a small website", "you want a fully managed cloud search service without server administration", "your documents are already structured data that a plain database query would serve better", "you need real-time streaming search over rapidly changing data"], "when_to_choose": ["you need a self-hosted search engine over many file formats and data sources", "you want integrated ETL, OCR, and text analytics rather than assembling separate tools", "your team needs faceted, exploratory, and semantic search with thesaurus support", "you research large document sets and need entity extraction and knowledge graph navigation"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/open-semantic-search", "repo": "opensemanticsearch/open-semantic-search", "role": "main", "score": 40}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:58.700562+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:20:31.636666+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f642f655a385f15ff635bfa29b098dec34ae5602d7c68ac3809bb0ce49217de8", "fetched_at": "2026-08-28T04:03:58.700562+00:00", "kind": "readme", "missing": false, "url": "https://github.com/opensemanticsearch/open-semantic-search"}, {"content_hash": "e4d17f0552c8b6410c62ba529d9c044c0df9dbc07cc4f57f43872fea47f38fec", "fetched_at": "2026-08-29T12:27:29.856713+00:00", "kind": "homepage", "missing": false, "url": "https://opensemanticsearch.org"}, {"content_hash": "38a56be689a5823180e6d38272491a600bffc3839608e9a46ed2d82f38bf1365", "fetched_at": "2026-08-29T12:27:29.859376+00:00", "kind": "site_page", "missing": false, "url": "https://opensemanticsearch.org/doc/admin/install"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 17, "longevity": 100, "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": 3808, "days_push": 501, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 40, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}