{"id":19435563,"url":"https://github.com/code-kern-ai/refinery-tokenizer","last_synced_at":"2025-07-24T07:08:40.621Z","repository":{"id":45660025,"uuid":"513921079","full_name":"code-kern-ai/refinery-tokenizer","owner":"code-kern-ai","description":"Tokenizer for refinery. Manages the creation and storage of spaCy tokens for text-based record attributes and supports multiple language models. It is used by the gateway.","archived":false,"fork":false,"pushed_at":"2025-07-17T15:01:19.000Z","size":104,"stargazers_count":1,"open_issues_count":2,"forks_count":1,"subscribers_count":3,"default_branch":"dev","last_synced_at":"2025-07-17T16:48:50.519Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://www.kern.ai","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/code-kern-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":"CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2022-07-14T13:54:05.000Z","updated_at":"2025-07-03T07:14:33.000Z","dependencies_parsed_at":"2023-02-18T05:45:29.223Z","dependency_job_id":"27bf297e-c4b4-46e7-a478-2cb0879c5a3c","html_url":"https://github.com/code-kern-ai/refinery-tokenizer","commit_stats":null,"previous_names":[],"tags_count":19,"template":false,"template_full_name":null,"purl":"pkg:github/code-kern-ai/refinery-tokenizer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code-kern-ai%2Frefinery-tokenizer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code-kern-ai%2Frefinery-tokenizer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code-kern-ai%2Frefinery-tokenizer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code-kern-ai%2Frefinery-tokenizer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/code-kern-ai","download_url":"https://codeload.github.com/code-kern-ai/refinery-tokenizer/tar.gz/refs/heads/dev","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/code-kern-ai%2Frefinery-tokenizer/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266807192,"owners_count":23987426,"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":"2025-07-24T02:00:09.469Z","response_time":99,"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":[],"created_at":"2024-11-10T15:07:02.117Z","updated_at":"2025-07-24T07:08:40.591Z","avatar_url":"https://github.com/code-kern-ai.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# refinery-tokenizer [![Build Status](https://drone.dev.kern.ai/api/badges/code-kern-ai/refinery-tokenizer/status.svg?ref=refs/heads/dev)](https://drone.dev.kern.ai/code-kern-ai/refinery-tokenizer)\n[![refinery's repository](https://uploads-ssl.webflow.com/61e47fafb12bd56b40022a49/62c2f30f935f4d37dc864eeb_Kern%20refinery.png)](https://github.com/code-kern-ai/refinery)\n\nTokenizer for [refinery](https://github.com/code-kern-ai/refinery). Manages the creation and storage of `spaCy` tokens for text-based record attributes and supports multiple language models. It is used by the [gateway](https://github.com/code-kern-ai/refinery-gateway).\n\nIf you like what we're working on, please leave a ⭐ for [refinery](https://github.com/code-kern-ai/refinery)!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcode-kern-ai%2Frefinery-tokenizer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcode-kern-ai%2Frefinery-tokenizer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcode-kern-ai%2Frefinery-tokenizer/lists"}