{"id":28098109,"url":"https://github.com/baughmann/tikara","last_synced_at":"2026-02-16T17:33:40.989Z","repository":{"id":274123495,"uuid":"921996238","full_name":"baughmann/tikara","owner":"baughmann","description":"The metadata and text content extractor for almost every file type.","archived":false,"fork":false,"pushed_at":"2025-02-03T16:24:58.000Z","size":168674,"stargazers_count":1,"open_issues_count":4,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-05-06T08:17:01.089Z","etag":null,"topics":["apache-tika","content-extraction","document-parsing","document-processing","docx","image-to-text","java","language-detection","llm","metadata","metadata-extraction","ml","natural-language-processing","ocr","pdf-to-text","retrieval-augmented-generation","text-extraction","text-mining"],"latest_commit_sha":null,"homepage":"https://baughmann.github.io/tikara/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/baughmann.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":"SUPPORTED_MIME_TYPES.md","governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-01-25T03:36:34.000Z","updated_at":"2025-01-28T16:26:25.000Z","dependencies_parsed_at":null,"dependency_job_id":"0f4c8d35-296d-4001-aa99-f3bd2598a5b5","html_url":"https://github.com/baughmann/tikara","commit_stats":null,"previous_names":["baughmann/tikara"],"tags_count":5,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baughmann%2Ftikara","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baughmann%2Ftikara/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baughmann%2Ftikara/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/baughmann%2Ftikara/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/baughmann","download_url":"https://codeload.github.com/baughmann/tikara/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253997338,"owners_count":21996841,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["apache-tika","content-extraction","document-parsing","document-processing","docx","image-to-text","java","language-detection","llm","metadata","metadata-extraction","ml","natural-language-processing","ocr","pdf-to-text","retrieval-augmented-generation","text-extraction","text-mining"],"created_at":"2025-05-13T17:49:43.424Z","updated_at":"2025-10-03T15:43:37.896Z","avatar_url":"https://github.com/baughmann.png","language":"Python","readme":null,"funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbaughmann%2Ftikara","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbaughmann%2Ftikara","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbaughmann%2Ftikara/lists"}