{"id":14849062,"url":"https://github.com/data-prep-kit/data-prep-kit","last_synced_at":"2026-02-11T17:17:07.825Z","repository":{"id":232647686,"uuid":"783968898","full_name":"data-prep-kit/data-prep-kit","owner":"data-prep-kit","description":"Open source project for data preparation for GenAI applications","archived":false,"fork":false,"pushed_at":"2025-12-12T14:48:14.000Z","size":257015,"stargazers_count":861,"open_issues_count":224,"forks_count":230,"subscribers_count":18,"default_branch":"dev","last_synced_at":"2025-12-14T06:11:20.141Z","etag":null,"topics":["code-quality","data","data-prep","data-preparation","data-preprocessing","data-preprocessing-pipelines","datacuration","datarecipes","deduplication","finetuning","large-language-models","large-scale-data-processing","llm","llmapps","malware","python","ray","spark"],"latest_commit_sha":null,"homepage":"https://data-prep-kit.github.io/data-prep-kit/","language":"HTML","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/data-prep-kit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":"GOVERNANCE.md","roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":"MAINTAINERS.md","copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-04-08T23:43:52.000Z","updated_at":"2025-12-12T15:57:15.000Z","dependencies_parsed_at":"2025-08-18T21:07:13.620Z","dependency_job_id":"dacccc46-d4b6-4df0-a07d-ac63ae8782f2","html_url":"https://github.com/data-prep-kit/data-prep-kit","commit_stats":null,"previous_names":["ibm/data-prep-lab","ibm/data-prep-kit","data-prep-kit/data-prep-kit"],"tags_count":15,"template":false,"template_full_name":null,"purl":"pkg:github/data-prep-kit/data-prep-kit","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/data-prep-kit%2Fdata-prep-kit","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/data-prep-kit%2Fdata-prep-kit/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/data-prep-kit%2Fdata-prep-kit/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/data-prep-kit%2Fdata-prep-kit/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/data-prep-kit","download_url":"https://codeload.github.com/data-prep-kit/data-prep-kit/tar.gz/refs/heads/dev","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/data-prep-kit%2Fdata-prep-kit/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":27755896,"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","status":"online","status_checked_at":"2025-12-15T02:00:09.782Z","response_time":96,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["code-quality","data","data-prep","data-preparation","data-preprocessing","data-preprocessing-pipelines","datacuration","datarecipes","deduplication","finetuning","large-language-models","large-scale-data-processing","llm","llmapps","malware","python","ray","spark"],"created_at":"2024-09-19T14:00:47.691Z","updated_at":"2025-12-15T19:03:17.020Z","avatar_url":"https://github.com/data-prep-kit.png","language":"HTML","readme":null,"funding_links":[],"categories":["大型语言模型（LLM）排行榜","LLM Data"],"sub_categories":["LLM 数据"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdata-prep-kit%2Fdata-prep-kit","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdata-prep-kit%2Fdata-prep-kit","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdata-prep-kit%2Fdata-prep-kit/lists"}