{"id":20424903,"url":"https://github.com/chetanxpro/document-ai","last_synced_at":"2025-10-11T21:34:52.911Z","repository":{"id":208786702,"uuid":"717659927","full_name":"ChetanXpro/Document-AI","owner":"ChetanXpro","description":"A app to extract structured data from a pdf document","archived":false,"fork":false,"pushed_at":"2023-11-30T18:56:14.000Z","size":1028,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"feat/typescript","last_synced_at":"2025-03-05T04:44:18.102Z","etag":null,"topics":["extract-data"],"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/ChetanXpro.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-12T06:29:01.000Z","updated_at":"2024-01-26T19:30:33.000Z","dependencies_parsed_at":"2023-11-29T17:27:12.688Z","dependency_job_id":"7474b2e6-01d0-4783-ae91-de1eff475688","html_url":"https://github.com/ChetanXpro/Document-AI","commit_stats":null,"previous_names":["chetanxpro/extract-data-from-pdf","chetanxpro/document-ai"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ChetanXpro/Document-AI","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChetanXpro%2FDocument-AI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChetanXpro%2FDocument-AI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChetanXpro%2FDocument-AI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChetanXpro%2FDocument-AI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChetanXpro","download_url":"https://codeload.github.com/ChetanXpro/Document-AI/tar.gz/refs/heads/feat/typescript","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChetanXpro%2FDocument-AI/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279008858,"owners_count":26084518,"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":"2025-10-11T02:00:06.511Z","response_time":55,"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":["extract-data"],"created_at":"2024-11-15T07:11:25.833Z","updated_at":"2025-10-11T21:34:52.873Z","avatar_url":"https://github.com/ChetanXpro.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Extract Data from PDF\n\nThis script extracts structured data from PDF files.\n\n## Prerequisites\n\nBefore you run the script, make sure you have:\n\n- `Node.js` installed on your machine\n- An API key for `gpt-4`.\n\n## Setup Instructions\n\n- First, define all the possible document types in the `types/documentType.ts` file.\n- Then, specify all the document schemas in the `constants/schema.ts` file.\n\n- To configure the script to work with your `gpt-4` API key and any other settings, you'll need to set up environment variables:\n\nRename the provided `.example.env` file to `.env` in the root directory of the project:\n\n```mv .example.env .env```\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchetanxpro%2Fdocument-ai","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchetanxpro%2Fdocument-ai","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchetanxpro%2Fdocument-ai/lists"}