{"data":{"slug":"wikipedia2vec-wikipedia2vec","name":"wikipedia2vec","tagline":"A tool for learning vector representations of words and entities from Wikipedia","github_url":"https://github.com/wikipedia2vec/wikipedia2vec","owner":"wikipedia2vec","repo":"wikipedia2vec","owner_avatar_url":"https://avatars.githubusercontent.com/u/39626598?v=4","primary_language":"Python","stars":971,"forks":100,"topics":["embeddings","natural-language-processing","nlp","python","text-classification","wikipedia"],"archived":false,"github_pushed_at":"2024-05-03T21:51:02+00:00","maintenance_label":"Dormant","stars_delta_30d":4,"url":"https://www.graphcanon.com/tools/wikipedia2vec-wikipedia2vec","markdown_url":"https://www.graphcanon.com/tools/wikipedia2vec-wikipedia2vec.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/wikipedia2vec-wikipedia2vec","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=wikipedia2vec-wikipedia2vec","description":"A tool for learning vector representations of words and entities from Wikipedia","homepage_url":"http://wikipedia2vec.github.io/","license":"Other","open_issues":8,"watchers":32,"ai_summary":"wikipedia2vec is a Python-based tool designed to generate embeddings for words and entities derived from Wikipedia content, aiding in natural language processing tasks like text classification.","readme_excerpt":"## License\n\n[Apache License 2.0](http://www.apache.org/licenses/LICENSE-2.0)","github_created_at":"2015-10-26T10:37:06+00:00","created_at":"2026-07-11T11:31:39.278037+00:00","updated_at":"2026-08-22T18:01:53.409991+00:00","categories":[{"slug":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"embeddings","name":"embeddings"},{"slug":"natural-language-processing","name":"natural-language-processing"},{"slug":"nlp","name":"nlp"},{"slug":"python","name":"python"},{"slug":"text-classification","name":"text-classification"},{"slug":"wikipedia","name":"wikipedia"}],"trust":{"provenance":{"is_fork":false,"github_id":44961854,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-22T18:01:52.534Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":840,"last_release_at":"2024-01-11T07:43:49Z","stars_delta_30d":4,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:31:40.483Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-22T18:01:53.037Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-08-22T18:01:53.037Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-08-22T18:01:53.037Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["You need to generate word and entity embeddings based on extensive Wikipedia data","Your project focuses specifically on leveraging Wikipedia's breadth of knowledge in NLP tasks"],"when_not_to_use":["Your dataset doesn't intersect with or benefit from Wikipedia content","You require real-time updating capabilities that exceed static Wikipedia dumps"],"source":"enrich:decision_facts","observed_at":"2026-07-12T14:42:44.515Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"A Python-based tool for generating embeddings derived from Wikipedia content."}]}}