AGRISENSE is an intelligent IoT-based farming assistant that leverages sensor data and AI to provide farmers with actionable insights and recommendations. The system collects real-time data from various sensors, processes this data using OpenAI's GPT-4, and sends recommendations to farmers via SMS. The platform supports both English and Kiswahili languages.
- Real-time Sensor Data Collection: Collects data on soil moisture, temperature, and humidity.
- AI-Powered Recommendations: Uses OpenAI's GPT-4 model to provide insights and recommendations based on sensor data.
- Multi-Language Support: Supports English and Kiswahili for both data input and recommendations.
- SMS Notifications: Sends AI-generated recommendations to farmers via SMS.
- User Interaction: Allows farmers to ask questions based on the sensor data and receive intelligent responses.
- Data Visualization: Displays sensor data using interactive charts.
- Python 3.9+
- Streamlit
- Plotly
- Requests
- PySerial
- Pandas
-
Clone the repository:
git clone https://github.com/yourusername/AGRISENSE.git cd AGRISENSE -
Install the required Python packages:
pip install -r requirements.txt
-
Add your OpenAI API key in the
openai_api_keyvariable in the script. -
Connect your HSUPA modem and LoRa Waziup board to the appropriate COM ports.
-
Run the Streamlit application:
streamlit run test2_streamlit_app.py
-
Access the application in your browser at
http://localhost:8501.
-
Enter the sensor data, crop type, and phone number.
-
Click "Get Recommendations" to receive AI-generated advice based on the input data.
-
Use the chat input to ask questions related to the sensor data and receive instant responses.
- The system continuously listens for incoming IoT data and SMS messages, processes them, and updates the recommendations accordingly.
Feel free to fork the repository, make improvements, and submit pull requests. For major changes, please open an issue first to discuss what you would like to change.
This project is licensed under the MIT License.
For any inquiries or support, please contact:
- Your Name: [email protected]
- GitHub: yourusername