| title | emoji | colorFrom | colorTo | sdk | sdk_version | app_file | pinned |
|---|---|---|---|---|---|---|---|
IoT Sensor Data RAG for Smart Buildings |
🏢 |
blue |
indigo |
streamlit |
1.42.1 |
app.py |
false |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
I created a complete RAG (Retrieval-Augmented Generation) system for smart buildings that:
- Processes real-time IoT sensor data (temperature, humidity, power)
- Integrates maintenance manuals and building specifications
- Provides predictive maintenance insights
- Detects anomalies in sensor data
- Gives operational optimization recommendations
- Real-time IoT Monitoring: Live sensor data streaming with anomaly detection
- Smart Document Search: Ask questions about maintenance and get AI-powered answers
- Predictive Analytics: Equipment failure prediction and maintenance tips
- Modern Dashboard: Clean Streamlit interface with real-time visualizations
git clone https://github.com/itsnewcoder/iot-smart-building-rag.git
cd iot-smart-building-ragpip install -r requirements.txtstreamlit run app.pyYour app will open at: http://localhost:8501
Try it online: https://huggingface.co/spaces/imnikhilraj/iot-smart-building-rag
- Click "Start Stream" to begin sensor data simulation
- View real-time temperature, humidity, and power readings
- See detected anomalies and maintenance recommendations
- Ask questions like "How to reset chiller pump?"
- Get AI-powered answers based on maintenance manuals
- View source documents and relevance scores
- Test the system with custom queries
- See retrieval performance metrics
- Check response latency and accuracy
- View indexed documents
- Upload new PDFs/TXTs to expand knowledge base
iot-smart-building-rag/
├── app.py # Main Streamlit app
├── requirements.txt # Python packages
├── rag/ # RAG system core
│ ├── ingest.py # Document processing
│ ├── retrieval.py # Search engine
│ ├── generate.py # AI responses
│ └── evaluate.py # Performance metrics
├── models/ # Predictive models
│ └── predictive.py # Anomaly detection
├── data/ # Sample data
│ ├── manuals/ # Maintenance guides
│ ├── specs/ # Building specs
│ └── sensors/ # IoT sensor data
└── .streamlit/ # App configuration
- HVAC Sensor Data: Temperature, humidity, power consumption readings
- Chiller Manual: Maintenance procedures and fault codes
- Building Specifications: System requirements and configurations
- Embeddings: Sentence-Transformers (all-MiniLM-L6-v2)
- Vector Database: ChromaDB with cosine similarity
- LLM: Local Transformers + OpenAI API (optional)
- Anomaly Detection: Rolling z-score analysis
- Chunking: 500 tokens with 50 token overlap
✅ IoT Data Processing: Real-time sensor streaming and analysis ✅ Document RAG: Intelligent search through manuals and specs ✅ Predictive Maintenance: Equipment failure prediction algorithms ✅ Anomaly Detection: Statistical analysis for sensor anomalies ✅ Modern UI: Professional Streamlit dashboard ✅ Evaluation Metrics: Performance testing and quality assessment
This project demonstrates:
- Complete RAG system implementation
- IoT data integration and processing
- Predictive analytics for smart buildings
- Vector database usage (ChromaDB)
- Modern web application development
streamlit run app.pystreamlit run app.py --server.port 8501 --server.address 0.0.0.0- GitHub Issues: Report bugs here
- Live Demo: https://huggingface.co/spaces/imnikhilraj/iot-smart-building-rag
- Source Code: https://github.com/itsnewcoder/iot-smart-building-rag
Built by Nikhil Raj 🚀