{"id":30060951,"url":"https://github.com/hiborn4/invoiceiq","last_synced_at":"2025-08-08T01:51:53.758Z","repository":{"id":308520898,"uuid":"1033110628","full_name":"HiBorn4/invoiceIQ","owner":"HiBorn4","description":"AI-powered Invoice Data Extraction Tool – Upload any document (PDF/image) and extract key information in structured JSON format using OCR and vision-based LLM techniques, including robust stamp detection.","archived":false,"fork":false,"pushed_at":"2025-08-06T10:17:29.000Z","size":8093,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-08-06T12:10:49.167Z","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/HiBorn4.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":"2025-08-06T10:08:43.000Z","updated_at":"2025-08-06T10:17:33.000Z","dependencies_parsed_at":"2025-08-06T12:20:58.374Z","dependency_job_id":null,"html_url":"https://github.com/HiBorn4/invoiceIQ","commit_stats":null,"previous_names":["hiborn4/invoiceiq"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/HiBorn4/invoiceIQ","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FinvoiceIQ","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FinvoiceIQ/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FinvoiceIQ/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FinvoiceIQ/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HiBorn4","download_url":"https://codeload.github.com/HiBorn4/invoiceIQ/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FinvoiceIQ/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269351896,"owners_count":24402677,"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":"2025-08-07T02:00:09.698Z","response_time":73,"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":"2025-08-08T01:51:51.432Z","updated_at":"2025-08-08T01:51:53.735Z","avatar_url":"https://github.com/HiBorn4.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 📄 InvoiceIQ – Intelligent Invoice Data Extraction System\n\n![Invoice Upload UI](./public/Selection_001.png)\n\n---\n\n## 🧠 Project Overview\n\n**InvoiceIQ** is a powerful document intelligence system that performs **OCR-based data extraction** from uploaded invoices and other structured documents. It reliably parses key information such as:\n\n- Invoice Number  \n- Invoice Date  \n- Vendor Code  \n- PO Number  \n- Item Details (Name, Quantity, Rate)  \n- Total \u0026 Grand Total  \n- Stamp Verification (Highly accurate)\n\nThe system is designed to **work with diverse layouts** and file formats, extracting data even from **complex or noisy documents**. A major challenge of stamp-based verification has also been successfully tackled using robust **image embedding comparisons**.\n\nWhether the file is a scan, image, or PDF—if a human can read it, **InvoiceIQ** can parse it.\n\n---\n\n## 🚀 Getting Started\n\n### 🖥 Frontend (Streamlit UI)\n\n```bash\nstreamlit run app.py\n````\n\n### 🛠 Backend (FastAPI + Embedding + Utils)\n\n```bash\n# Step 1: Install requirements\npip install -r requirements.txt\n\n# Step 2: Start the backend server\ncd backend\nuvicorn app:app --reload\n```\n\nThe backend provides:\n\n* OCR processing\n* Image preprocessing\n* Embedding-based stamp comparison\n* JSON output formatting\n\n---\n\n## 🎥 Demo Video\n\n⬇️ *(Demo coming soon here)*\n\nhttps://github.com/user-attachments/assets/3c9cdbfc-f0f0-422c-83ac-b047b23a81b6\n\n---\n\n## 🔍 Features\n\n✅ Human-readable document parsing\n✅ Highly flexible input support (PDF, PNG, JPG, etc.)\n✅ Strict positional \u0026 format constraints for accuracy\n✅ Fast and scalable backend using FastAPI\n✅ Accurate stamp detection with `text-embedding-ada-002`\n\n---\n\n## 🛠 Tech Stack\n\n* **Frontend**: Streamlit\n* **Backend**: FastAPI\n* **OCR Engine**: Tesseract\n* **Embedding**: Azure OpenAI `text-embedding-ada-002`\n* **Stamp Matching**: Vector similarity + base64 image handling\n* **File Types Supported**: PDF, PNG, JPG\n\n---\n\n## 📦 Folder Structure\n\n```\nInvoiceIQ/\n│\n├── app.py                  # Streamlit Frontend\n├── backend/\n│   ├── app.py              # FastAPI backend\n│   ├── utils/              # OCR, Preprocessing, Embedding scripts\n│   └── model/              # Embedding logic, Stamp comparison\n│\n├── public/\n│   └── invoice_ui_1.png\n│   └── invoice_ui_2.png\n│\n└── requirements.txt\n```\n\n![Extracted Output](./public/Selection_002.png)\n\n---\n\n## 🌍 Use Cases\n\n* Automated invoice digitization\n* Bill processing systems\n* Procurement systems\n* KYC or stamp-based validation systems\n* Document archiving with searchable metadata\n\n---\n\n## 💼 Ideal For\n\n✅ Freelance project delivery on **Upwork** / **Fiverr**\n✅ AI / OCR portfolios\n✅ Enterprise document processing workflows\n\n---\n\n## 📬 Contact\n\nFeel free to reach out if you'd like a custom solution or integration!\n\n---\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiborn4%2Finvoiceiq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhiborn4%2Finvoiceiq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiborn4%2Finvoiceiq/lists"}