This is a web application that allows users to upload an image of a dish, and it provides a recipe for the same.
-
Image Upload: Users can upload an image of a dish item directly through the web interface.
-
AI Recipe Generation: The application analyzes the uploaded image and provide a recipe based on the recognized food item.
-
FastAPI: A modern, fast (high-performance), web framework for building APIs.
-
Replicate API: For running a pretrained multimodal model for recipe prediction.
-
Jinja2: A templating engine for rendering HTML templates.
-
uvicorn: ASGI server for hosting the FastAPI application.
-
Clone the Repository:
git clone https://github.com/your-username/recipe-predictor-app.git cd recipe-predictor-app
-
Install Dependencies:
pip install -r requirements.txt
-
Configure Replicate API:
- Sign up for a Replicate API account and obtain an API key.
- Create a .env file in your directory.
- Set your Replicate API key as an environment variable in the .env file.
-
Run the Application:
python main.py
-
Open your web browser and navigate to http://localhost:8000.
-
Click the "Choose File" button to upload an image of a food item.
-
Enter a description or caption for the image in the provided text field.
-
Click the "Submit" button to process the image and receive the recipe.