ChloroBot is a FastAPI-based web application that allows users to upload images and ask questions about the detected objects in the image. It utilizes the YOLOv8 model for object detection and GPT-4 Vision for generating contextual responses based on the detected objects.
- Upload images to detect objects using YOLOv8.
- Ask questions about the detected objects and receive answers generated by GPT-4 Vision.
- User-friendly interface for seamless interaction.
- FastAPI: For building the web application.
- Uvicorn: ASGI server for running the FastAPI application.
- YOLOv8: For real-time object detection.
- OpenAI GPT-4 Vision: For generating responses based on detected objects.
- Pydantic: For data validation.
- Python: The programming language used for development.
-
Clone the repository:
git clone https://github.com/HunterX461/Chlorobot.git cd Chlorobot
2.Create a virtual environment (optional but recommended):
python -m venv venv
source venv/bin/activate # On Windows use venv\Scripts\activate
3.Install the required dependencies: pip install -r requirements.txt Usage
Run the Application:
Start the FastAPI application using Uvicorn:
uvicorn main:app --reload
Open your web browser and go to http://127.0.0.1:8000 to access the application.
Use the upload section to select and upload an image. The application will detect objects in the image.
After the objects are detected, enter your question in the provided input field and click "Ask". The application will generate a response based on the detected objects.
Example :
Upload an image of a plant and ask, "What type of plant is this?" The application will detect the plant and provide a response based on the detected objects.
Contributing :
Contributions are welcome! If you have suggestions or improvements, feel free to create a pull request or open an issue.
YOLOv8 for object detection.
OpenAI for the GPT-4 Vision model.
Plant Village Dataset: @article{Mohanty_Hughes_Salathé_2016, title={Using deep learning for image-based plant disease detection}, volume={7}, DOI={10.3389/fpls.2016.01419}, journal={Frontiers in Plant Science}, author={Mohanty, Sharada P. and Hughes, David P. and Salathé, Marcel}, year={2016}, month={Sep}}