{"id":27957492,"url":"https://github.com/singletlinkage/matbot-ai-assistant","last_synced_at":"2026-05-01T21:33:07.337Z","repository":{"id":291385553,"uuid":"976949984","full_name":"SingletLinkage/MATBot-AI-Assistant","owner":"SingletLinkage","description":"MATBot is an intelligent assistant designed to troubleshoot MATLAB software-related issues. The application leverages RAG (Retrieval-Augmented Generation) architecture and LLM models to provide accurate, contextual solutions to common MATLAB problems by drawing from official MathWorks documentation.","archived":false,"fork":false,"pushed_at":"2025-05-04T09:23:35.000Z","size":4811,"stargazers_count":0,"open_issues_count":0,"forks_count":4,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-25T04:43:29.307Z","etag":null,"topics":["agentic-ai","diskann","gemini-api","rag","streamlit"],"latest_commit_sha":null,"homepage":"https://matbot-ai-assistant.streamlit.app","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/SingletLinkage.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":"2025-05-03T04:40:43.000Z","updated_at":"2025-05-20T15:03:33.000Z","dependencies_parsed_at":"2025-05-04T10:39:11.908Z","dependency_job_id":null,"html_url":"https://github.com/SingletLinkage/MATBot-AI-Assistant","commit_stats":null,"previous_names":["singletlinkage/matbot-ai-assistant"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/SingletLinkage/MATBot-AI-Assistant","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SingletLinkage%2FMATBot-AI-Assistant","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SingletLinkage%2FMATBot-AI-Assistant/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SingletLinkage%2FMATBot-AI-Assistant/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SingletLinkage%2FMATBot-AI-Assistant/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SingletLinkage","download_url":"https://codeload.github.com/SingletLinkage/MATBot-AI-Assistant/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SingletLinkage%2FMATBot-AI-Assistant/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":280906490,"owners_count":26411412,"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":"2025-10-25T02:00:06.499Z","response_time":81,"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":["agentic-ai","diskann","gemini-api","rag","streamlit"],"created_at":"2025-05-07T18:13:17.942Z","updated_at":"2025-10-25T04:43:29.926Z","avatar_url":"https://github.com/SingletLinkage.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MATBot: MATLAB AI Troubleshooting Assistant\n\n## Live Demo\n👉 [Try MATBot Now](https://matbot-ai-assistant.streamlit.app)\n\n## Overview\n\nMATBot is an intelligent assistant designed to troubleshoot MATLAB software-related issues. The application leverages RAG (Retrieval-Augmented Generation) architecture and LLM models to provide accurate, contextual solutions to common MATLAB problems by drawing from official MathWorks documentation.\n\n## Features\n\n- **AI-Powered Troubleshooting**: Identifies and resolves MATLAB errors with step-by-step solutions\n- **Semantic Clustering**: Organizes technical documentation into relevant clusters for better retrieval\n- **Interactive Chat Interface**: User-friendly Streamlit-based chat interface with real-time feedback\n- **Model Customization**: Select between different Gemini models with configurable system prompts\n- **Response Evaluation**: Automatic quality assessment of AI responses with detailed feedback\n- **Structured Content Output**: Presents solutions in an easy-to-follow format with problem summary, root cause, and resolution\n- **Self-Memory System**: Learns from previous high-quality interactions to provide better responses\n- **Adaptive Response Style**: Automatically detects whether to provide concise or detailed answers\n- **Visual Support**: Provides relevant images to help understand complex MATLAB concepts\n- **Query Enhancement**: Uses HyDE (Hypothetical Document Embeddings) to improve search quality\n\n## Architecture\n\nThe application follows a modular architecture:\n\n1. **Data Collection \u0026 Processing**:\n   - Web scraping of MATLAB documentation\n   - HTML to structured JSON conversion (`structurify.py`)\n\n2. **Knowledge Base**:\n   - Semantic clustering of documents (`clustering.py`)\n   - FAISS vector index for efficient similarity search\n\n3. **RAG Engine**:\n   - Query processing\n   - Relevant document retrieval\n   - Context-enhanced generation\n\n4. **Agent System**:\n   - Debugger agent for problem-solving (`debugger_agent.py`)\n   - Evaluator agent for quality assessment (`evaluator_agent.py`)\n   - Intent agent for response type detection (`intent_agent.py`)\n   - Concise agent for summarization (`concise_agent.py`)\n\n5. **User Interface**:\n   - Streamlit web application (`streamlit_chat_app.py`)\n   - Interactive RAG configuration parameters\n   - Admin dashboard for system monitoring\n\n## Technical Stack\n\n- **Python 3.10+**\n- **Machine Learning**: scikit-learn, sentence-transformers, FAISS\n- **LLM APIs**: Google Gemini\n- **Web Framework**: Streamlit\n- **Data Processing**: BeautifulSoup, pandas\n- **Vector Database**: FAISS (Facebook AI Similarity Search)\n- **Database**: PostgreSQL (via Neon DB)\n\n## Getting Started\n\n### Prerequisites\n\n- Python 3.10+\n- API key for Google Gemini\n\n### Installation\n\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/yourusername/matbot.git\n   cd matbot\n   ```\n\n2. Install dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n3. Set up environment variables:\n   - Create a `.env` file in the project root\n   - Add your API key:\n     ```\n     GEMINI_API_KEY=your_gemini_api_key\n     ```\n\n### Running the Application\n\nLaunch the chat interface:\n```bash\nstreamlit run Landing.py\n```\n\n## Usage\n\n1. Enter your MATLAB-related troubleshooting query in the chat input\n2. The system will:\n   - Retrieve relevant documentation from the knowledge base\n   - Generate a structured response with problem analysis and solution\n   - Evaluate the quality of the response\n3. Use the model parameters sidebar to configure the LLM and RAG parameters before starting the chat\n\n## Project Structure\n\n- `/agents/`: LLM agent implementations\n- `/utils/`: Utility functions and wrappers for LLM APIs\n- `/corpus/`: Processed knowledge base (generated)\n- `/pages/`: Streamlit pages for the application\n- `structurify.py`: HTML processing utilities\n- `clustering.py`: Document clustering implementation\n- `Landing.py`: Main entry point and authentication\n- `requirements.txt`: Project dependencies\n\n## Future Improvements\n\n- Expanded knowledge base with additional MATLAB documentation\n- Integration with MATLAB for direct code analysis\n- User feedback-based continuous learning\n- Support for more LLM providers\n- Enhanced visualization of technical solutions\n- Mobile-friendly responsive design\n- Fine-tuned domain-specific embeddings\n\n## License\n\nThis project was created as part of the HCL Tech CS671 Hackathon.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsingletlinkage%2Fmatbot-ai-assistant","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsingletlinkage%2Fmatbot-ai-assistant","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsingletlinkage%2Fmatbot-ai-assistant/lists"}