How aryangiri03/carbonsense works
Carbon Sense is a vehicle-emissions awareness application. Its documented workflow runs from plate capture and fuel-entry through vehicle/visit data, emissions prediction and a personalized alert. The sampled Streamlit app directly connects to MongoDB and includes OCR and prediction-related logic; the README documents SMS delivery and Groq messaging. The camera utility is a separate camera-based recognizer in the sampled code. Some integrations and model details are documented but not fully visible in the excerpts.
Main entry points: app.py Streamlit Dashboard · message.py LLM Message · camera.py Camera Recognizer · Vehicle.js Vehicle Records
Components 13
Dashboard and Capture
- Streamlit Dashboard
app.py - Plate OCR
app.py - Camera Recognizer
camera.py
Emissions and Alerts
- Emission Prediction
app.py - LLM Message
message.py
Vehicle Records
- Vehicle Records
models/Vehicle.js - Fuel Visits
models/PetrolPumpVisit.js - Monthly Metrics
models/VehicleMetrics.js - PUC Certificates
models/PucDetails.js
Other components
- Driver
- MongoDB
- Groq LLM
- Twilio SMS
Connections 12
- Driver → Streamlit Dashboard: uses
README.md - Streamlit Dashboard → Plate OCR: extracts plate
app.py - Driver → Camera Recognizer: scans plate
camera.py - Streamlit Dashboard → MongoDB: reads and writes
app.py - Streamlit Dashboard → Emission Prediction: prepares prediction
app.py - Streamlit Dashboard → LLM Message: generates message
README.md - LLM Message → Groq LLM: invokes
message.py - Streamlit Dashboard → Twilio SMS: sends alert
README.md - Streamlit Dashboard → Vehicle Records: uses vehicle details
README.md - Streamlit Dashboard → Fuel Visits: tracks fuel visits
README.md - Streamlit Dashboard → Monthly Metrics: tracks metrics
README.md - Streamlit Dashboard → PUC Certificates: checks certificate
app.py