{"id":22352214,"url":"https://github.com/shamspias/gpt3-data-preprocessing","last_synced_at":"2025-07-30T07:32:10.324Z","repository":{"id":111763394,"uuid":"591457608","full_name":"shamspias/gpt3-data-preprocessing","owner":"shamspias","description":"This repository containing code for preprocessing text data from PDF and DOCX files for use with GPT-3. It includes steps such as tokenization, removal of stop words and punctuation, and formatting for GPT-3 input.","archived":false,"fork":false,"pushed_at":"2023-01-29T10:46:34.000Z","size":12,"stargazers_count":4,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2023-03-05T11:07:48.877Z","etag":null,"topics":["artificial-intelligence","data-preprocessing","data-preprocessing-pipelines","data-science","gpt-3","machine-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/shamspias.png","metadata":{},"created_at":"2023-01-20T20:05:07.000Z","updated_at":"2023-03-02T09:29:55.000Z","dependencies_parsed_at":"2023-07-24T16:46:24.949Z","dependency_job_id":null,"html_url":"https://github.com/shamspias/gpt3-data-preprocessing","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shamspias%2Fgpt3-data-preprocessing","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shamspias%2Fgpt3-data-preprocessing/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shamspias%2Fgpt3-data-preprocessing/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shamspias%2Fgpt3-data-preprocessing/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shamspias","download_url":"https://codeload.github.com/shamspias/gpt3-data-preprocessing/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228106320,"owners_count":17870438,"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":["artificial-intelligence","data-preprocessing","data-preprocessing-pipelines","data-science","gpt-3","machine-learning"],"created_at":"2024-12-04T12:17:49.379Z","updated_at":"2024-12-04T12:17:49.848Z","avatar_url":"https://github.com/shamspias.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":null,"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshamspias%2Fgpt3-data-preprocessing","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshamspias%2Fgpt3-data-preprocessing","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshamspias%2Fgpt3-data-preprocessing/lists"}