{"id":31765770,"url":"https://github.com/bharath-tars/hemamind","last_synced_at":"2025-10-10T00:26:47.664Z","repository":{"id":318595023,"uuid":"1071947025","full_name":"Bharath-tars/HemaMind","owner":"Bharath-tars","description":"HemaMind - AI Agent to analyze blood reports and provide detailed health insights","archived":false,"fork":false,"pushed_at":"2025-10-08T04:19:39.000Z","size":3758,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-10-08T05:41:42.505Z","etag":null,"topics":["ai-agents","analytics","generativeai","groq","healthcare"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Bharath-tars.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-08T03:39:19.000Z","updated_at":"2025-10-08T04:19:43.000Z","dependencies_parsed_at":"2025-10-08T05:41:45.863Z","dependency_job_id":"f940fc0a-f4bf-4bc1-9121-5540a0205c4c","html_url":"https://github.com/Bharath-tars/HemaMind","commit_stats":null,"previous_names":["bharath-tars/hemamind"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/Bharath-tars/HemaMind","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FHemaMind","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FHemaMind/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FHemaMind/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FHemaMind/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Bharath-tars","download_url":"https://codeload.github.com/Bharath-tars/HemaMind/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Bharath-tars%2FHemaMind/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279002359,"owners_count":26083356,"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":"2025-10-09T02:00:07.460Z","response_time":59,"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":["ai-agents","analytics","generativeai","groq","healthcare"],"created_at":"2025-10-10T00:26:43.570Z","updated_at":"2025-10-10T00:26:47.660Z","avatar_url":"https://github.com/Bharath-tars.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🩺 HemaMind (\"Hema\" = Blood, + \"Mind\" = Intelligence)\n\nAI Agent to analyze blood reports and provide detailed health insights.\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/Bharath-tars/HemaMind/issues\"\u003e\u003cimg src=\"https://img.shields.io/github/issues/Bharath-tars/HemaMind\"\u003e\u003c/a\u003e \n  \u003ca href=\"https://github.com/Bharath-tars/HemaMind/stargazers\"\u003e\u003cimg src=\"https://img.shields.io/github/stars/Bharath-tars/HemaMind\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/Bharath-tars/HemaMind/network/members\"\u003e\u003cimg src=\"https://img.shields.io/github/forks/Bharath-tars/HemaMind\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://github.com/Bharath-tars/HemaMind/blob/main/LICENSE\"\u003e\n    \u003cimg src=\"https://img.shields.io/badge/License-MIT-blue.svg\"\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"#-features\"\u003eFeatures\u003c/a\u003e |\n  \u003ca href=\"#%EF%B8%8F-tech-stack\"\u003eTech Stack\u003c/a\u003e |\n  \u003ca href=\"#-installation\"\u003eInstallation\u003c/a\u003e |\n\u003c/p\u003e\n\n\n## Example Result\n![result](https://raw.githubusercontent.com/Bharath-tars/HemaMind/main/public/db/example_report.jpeg)\n\n## 🌟 Features\n\n- Intelligent agent-based architecture with multi-model cascade system\n- In-context learning from previous analyses and knowledge base building\n- Medical report analysis with personalized health insights\n- PDF upload, validation and text extraction (up to 20MB)\n- Supports both text-parsable documents and scanned documents (scanned files may take longer to process since GPU acceleration isn’t available)\n- Secure user authentication and session management\n- Session history with report analysis tracking\n- Modern, responsive UI with real-time feedback\n\n## 🛠️ Tech Stack\n\n- **Frontend Framework**: Streamlit\n- **AI Integration**: Multi-model architecture via Groq\n  - Primary: meta-llama/llama-4-maverick-17b-128e-instruct\n  - Secondary: llama-3.3-70b-versatile\n  - Tertiary: llama-3.1-8b-instant\n  - Fallback: llama3-70b-8192\n- **Database**: Supabase\n- **PDF Processing**: PDFPlumber\n- **Authentication**: Supabase Auth\n\n## 🚀 Installation\n\n#### Requirements 📋\n\n- Python 3.8+\n- Streamlit 1.30.0+\n- Supabase account\n- Groq API key\n- PDFPlumber\n- Python-magic-bin (Windows) or Python-magic (Linux/Mac)\n- streamlit\u003e=1.42.0\n- Pillow\n- Easyocr\n- Numpy\n\n#### Getting Started 📝\n\n1. Clone the repository:\n\n```bash\ngit clone https://github.com/Bharath-tars/HemaMind.git\ncd HemaMind\n```\n\n2. Install dependencies:\n\n```bash\npip install -r requirements.txt\n```\n\n3. Required environment variables (in `.streamlit/secrets.toml`):\n\n```toml\nSUPABASE_URL = \"your-supabase-url\"\nSUPABASE_KEY = \"your-supabase-key\"\nGROQ_API_KEY = \"your-groq-api-key\"\n```\n\n4. Set up Supabase database schema:\n\nThe application requires the following tables in your Supabase database:\n\n![database schema](https://raw.githubusercontent.com/Bharath-tars/HemaMind/main/public/db/schema.png)\n\nYou can use the SQL script provided at `public/db/script.sql` \u003ca href=\"https://www.github.com/Bharath-tars/HemaMind/blob/main/public/db/script.sql\"\u003e[link]\u003c/a\u003e to set up the required database schema.\n\n(PS: You can turn off the email confimation on signup in Supabase settings -\u003e signup -\u003e email)\n\n5. Run the application:\n\n```bash\nstreamlit run src\\main.py\n```\n\n## 📁 Project Structure\n\n```\nhia/\n├── requirements.txt\n├── README.md\n├── src/\n│   ├── main.py                 # Application entry point\n│   ├── auth/                   # Authentication related modules\n│   │   ├── auth_service.py     # Supabase auth integration\n│   │   └── session_manager.py  # Session management\n│   ├── components/             # UI Components\n│   │   ├── analysis_form.py    # Report analysis form\n│   │   ├── auth_pages.py       # Login/Signup pages\n│   │   ├── footer.py          # Footer component\n│   │   └── sidebar.py         # Sidebar navigation\n│   ├── config/                # Configuration files\n│   │   ├── app_config.py      # App settings\n│   │   └── prompts.py         # AI prompts\n│   ├── services/              # Service integrations\n│   │   └── ai_service.py      # AI service integration\n│   ├── agents/                # Agent-based architecture components\n│   │   ├── agent_manager.py   # Agent management\n│   │   └── model_fallback.py  # Model fallback logic\n│   └── utils/                 # Utility functions\n│       ├── validators.py      # Input validation\n│       └── pdf_extractor.py   # PDF processing\n```\n\n## 👥 Contributing\n\nContributions are welcome! Please read our [Contributing Guidelines](CONTRIBUTING.md) for details on how to submit pull requests, the development workflow, coding standards, and more.\n\nWe appreciate all contributions, from reporting bugs and improving documentation to implementing new features.\n\n## 📄 License\n\nThis project is licensed under the MIT License - see the [LICENSE](https://github.com/Bharath-tars/HemaMind/blob/main/LICENSE) file for details.\n\n## 🙋‍♂️ Author\n\nCreated by [Sudarsanam Bharath](https://b4rpro.netlify.app)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbharath-tars%2Fhemamind","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbharath-tars%2Fhemamind","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbharath-tars%2Fhemamind/lists"}