{"id":30839011,"url":"https://github.com/invincible1602/document-extraction-agent","last_synced_at":"2025-09-06T18:51:41.801Z","repository":{"id":310798928,"uuid":"1041271031","full_name":"Invincible1602/Document-Extraction-Agent","owner":"Invincible1602","description":null,"archived":false,"fork":false,"pushed_at":"2025-08-20T09:03:31.000Z","size":12,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-20T10:28:46.562Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/Invincible1602.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,"zenodo":null}},"created_at":"2025-08-20T08:36:14.000Z","updated_at":"2025-08-20T09:03:34.000Z","dependencies_parsed_at":"2025-08-20T10:28:48.438Z","dependency_job_id":"980cc0ef-c4cd-4bea-9186-2b61b80c3c9d","html_url":"https://github.com/Invincible1602/Document-Extraction-Agent","commit_stats":null,"previous_names":["invincible1602/document-extraction-agent"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Invincible1602/Document-Extraction-Agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Invincible1602%2FDocument-Extraction-Agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Invincible1602%2FDocument-Extraction-Agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Invincible1602%2FDocument-Extraction-Agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Invincible1602%2FDocument-Extraction-Agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Invincible1602","download_url":"https://codeload.github.com/Invincible1602/Document-Extraction-Agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Invincible1602%2FDocument-Extraction-Agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273948803,"owners_count":25196398,"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":"2025-09-06T02:00:13.247Z","response_time":2576,"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":"2025-09-06T18:51:39.693Z","updated_at":"2025-09-06T18:51:41.788Z","avatar_url":"https://github.com/Invincible1602.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Document-Extraction-Agent\n\n# 📄 Document Extraction Agent\n\nAn AI-powered Python project to **extract structured data from documents** such as invoices, medical bills, and prescriptions. The app provides **confidence scoring and validation** for each extracted field. It features a **Streamlit UI** and supports **Google Gemini** API for deployment and Hugging Face models for local testing.\n\n---\n\n## Features\n\n- Upload documents in PDF, PNG, JPG, or JPEG format\n- Automatic document type detection (Invoice, Medical Bill, Prescription)\n- AI-powered field extraction using:\n  - **Google Gemini** (for deployment)\n  - **Hugging Face GPT-OSS-20B** (for local testing)\n- Confidence scoring and validation rules for extracted data\n- Download results as JSON\n- Clean and interactive Streamlit UI\n\n---\n\n## Installation\n\n1. Clone the repository:\n\n```bash\ngit clone https://github.com/Invincible1602/Document-Extraction-Agent.git\ncd Document-Extraction-Agent/app\n```\n\n## Project Structure\n\n```bash\napp/\n├── main.py            # Streamlit frontend\n├── extraction.py      # LLM-based extraction logic\n├── agent_loop.py      # Orchestrates document processing\n├── document_processor.py  # Handles PDF/image parsing\n├── schemas.py         # Pydantic models for structured output\n├── confidence.py      # Confidence scoring logic\n└── requirements.txt\nutils/\n├── helpers.py # Text cleaning, date/amount validation, and other helpers\n└── constants.py # Constants like supported file types, default fields\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finvincible1602%2Fdocument-extraction-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Finvincible1602%2Fdocument-extraction-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Finvincible1602%2Fdocument-extraction-agent/lists"}