{"id":30060957,"url":"https://github.com/hiborn4/kpidociq","last_synced_at":"2025-08-08T01:52:54.939Z","repository":{"id":242273457,"uuid":"807978911","full_name":"HiBorn4/KPIDocIQ","owner":"HiBorn4","description":"AI-powered document intelligence system for extracting KPIs from industrial reports, PDFs, and scanned tables using computer vision, OCR, and LLMs.","archived":false,"fork":false,"pushed_at":"2025-08-06T18:31:23.000Z","size":54157,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-06T20:36:12.637Z","etag":null,"topics":[],"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/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}},"created_at":"2024-05-30T06:33:27.000Z","updated_at":"2025-08-06T18:33:07.000Z","dependencies_parsed_at":"2024-06-12T22:18:49.484Z","dependency_job_id":null,"html_url":"https://github.com/HiBorn4/KPIDocIQ","commit_stats":null,"previous_names":["hiborn4/ai-powered-document-processing-and-extraction-system"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/HiBorn4/KPIDocIQ","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FKPIDocIQ","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FKPIDocIQ/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FKPIDocIQ/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FKPIDocIQ/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/HiBorn4","download_url":"https://codeload.github.com/HiBorn4/KPIDocIQ/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/HiBorn4%2FKPIDocIQ/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":269351898,"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":"2025-08-08T01:52:52.379Z","updated_at":"2025-08-08T01:52:54.922Z","avatar_url":"https://github.com/HiBorn4.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🧠 i4Ideas: AI-Powered Document Processing \u0026 Extraction System\n\n![Banner](/public/test1.png)\n\n\u003e An advanced AI-based system that extracts complex tabular and structured information from technical documents with unmatched precision. Built for manufacturing, steel, and QA/QC workflows.\n\n---\n\n### 📸 Visual Workflow — Document ➝ Table ➝ KPI Extraction\n\n\u003ctable\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cimg src=\"/public/test2.png\" width=\"100%\"\u003e\u003cbr\u003e\u003ccenter\u003e📄 Raw Document\u003c/center\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cimg src=\"/public/table.jpg\" width=\"100%\"\u003e\u003cbr\u003e\u003ccenter\u003e✂️ Cropped Table\u003c/center\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n  \u003ctr\u003e\n    \u003ctd\u003e\u003cimg src=\"/public/final.jpg\" width=\"100%\"\u003e\u003cbr\u003e\u003ccenter\u003e🧠 KPIs\u003c/center\u003e\u003c/td\u003e\n  \u003c/tr\u003e\n\u003c/table\u003e\n\n---\n\n## 🔍 Overview\n\n**i4Ideas** is a state-of-the-art, production-grade document parsing system designed to extract meaningful data from industrial reports like tensile strength sheets, quality certificates, and lab reports. The system leverages deep learning, OCR, and vision-language models to output structured, human-verified JSON for downstream analytics or compliance.\n\nThis solution has been **field-tested across diverse document formats**, including JSW, Tata, Hyundai, and Jamshedpur technical data sheets.\n\n---\n\n## 🧠 Core Capabilities\n\n- 📄 **PDF → Table/Image Extraction**\n- 🔍 **Object Detection (YOLOv5 / ResNet50)** to locate tabular blocks\n- 🧾 **PaddleOCR / Adobe OCR** integration for clean text extraction\n- 🤖 **LLM-Powered Parsing (GPT)** using domain-specific prompts\n- 📊 **Aesthetic JSON Output** with units and data validation\n- 🔄 **Multi-format switch handling** (JSW, Tata, Hyundai, etc.)\n\n---\n\n## 📸 Supported Formats\n\n| Company         | Keys Extracted                                                              |\n|----------------|------------------------------------------------------------------------------|\n| JSW Steel       | `Coil No`, `YS`, `UTS`, `EL`, `Ra`                                          |\n| Tata Steel      | `Mother Coil`, `YS`, `UTS`, `EL`, `rBAR`, `n`, `Ra`                         |\n| Jamshedpur      | `Coil No`, `YS`, `UTS`, `EL`, `rVALUE`, `NVALM`, `RaMICROM`                |\n| Hyundai         | `Dimension`, `YP`, `TS`, `EL`, `Ra`                                         |\n| Maharashtra     | `Product No`, `YP`, `TS`, `EL`, `Ra`                                        |\n\n---\n\n## 🚀 Installation\n\n```bash\ngit clone https://github.com/HiBorn4/AI-powered-document-processing-and-extraction-system.git\ncd AI-powered-document-processing-and-extraction-system\npip install -r requirements.txt\n````\n\n---\n\n## 🎥 Demo\n\n*(Add video preview here)*\n\n---\n\n## 🧪 Example Output\n\n```json\n{\n  \"NC65081000\": {\n    \"YS\": \"347 MPa\",\n    \"UTS\": \"294 MPa\",\n    \"EL\": \"45%\",\n    \"Ra\": \"67.39 μm\"\n  },\n  \"NC65082000\": {\n    \"YS\": \"364 MPa\",\n    \"UTS\": \"470 MPa\",\n    \"EL\": \"80%\",\n    \"Ra\": \"28.10 μm\"\n  }\n}\n```\n\n---\n\n## 📁 Project Structure\n\n```\n📦 AI-powered-document-processing-and-extraction-system\n├── bulk_table_extraction.py         # Batch document processing\n├── extract_keys.py                  # Prompt-based LLM key-value extraction\n├── table_detection.py               # YOLO/ResNet table detection pipeline\n├── pdf_to_image.py                  # Converts PDF to image for OCR\n├── paddleocr_implemented/          # PaddleOCR model directory\n├── jcap_tsr.py, tata_tsr.py, jsw_tsr.py  # Custom flows per company\n├── image_postprocess.py             # Image cleaning and noise reduction\n├── summarize_prompts.py             # Prompt engineering and format matching\n```\n\n---\n\n## 📦 Tech Stack\n\n* 🧠 **OpenAI GPT (Function Calling + Vision)**\n* 🧾 **PaddleOCR / Adobe Acrobat OCR**\n* 🖼️ **YOLOv5 / ResNet50** for layout detection\n* 🧪 **Prompt Engineering** for reliable key mapping\n* 📄 **PDF2Image**, **Pillow**, **Pandas**\n\n---\n\n## 🔐 Use Cases\n\n* Steel Manufacturing QA Automation\n* Compliance \u0026 Lab Test Report Digitization\n* Quality Certificate Parsing \u0026 Validation\n* Document Indexing for Enterprise Search\n\n---\n\n## 💼 Portfolio \u0026 Freelance Suitability\n\nThis project is ideal to showcase:\n\n* LLMOps / Document AI skills\n* OCR + Vision + GPT integration\n* Custom multi-format prompt engineering\n* PDF/Scan processing pipelines\n\n---\n\n## 📬 Contact\n\nFor collaboration or freelance work:\n\n* 💼 **Upwork**: [HiBorn4](https://www.upwork.com/freelancers/~hiborn4)\n* 💻 **GitHub**: [HiBorn4](https://github.com/HiBorn4)\n* 📫 **Email**: [reach.hiborn@gmail.com](mailto:reach.hiborn4@gmail.com)\n\n---\n\n## 📝 License\n\nMIT License. © 2025 HiBorn4","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiborn4%2Fkpidociq","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhiborn4%2Fkpidociq","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhiborn4%2Fkpidociq/lists"}