Check out the tutorial.

1. Build and tag the Docker image:

   $ docker build -t fastapi-prophet .

2. Spin up the container:

   $ docker run --name fastapi-ml -e PORT=8008 -p 8008:8008 -d fastapi-prophet:latest

3. Train the model:

   $ docker exec -it fastapi-ml python
   
   >>> from model import train, predict, convert
   >>> train()

4. Test:

   $ curl \
     --header "Content-Type: application/json" \
     --request POST \
     --data '{"ticker":"MSFT"}' \
     https://localhost:8008/predict

1. Create and activate a virtual environment:

   $ python3 -m venv venv && source venv/bin/activate

2. Install the requirements:

   (venv)$ pip install -r requirements.txt

3. Train the model:

   (venv)$ python
   
   >>> from model import train, predict, convert
   >>> train()

4. Run the app:

   (venv)$ uvicorn main:app --reload --workers 1 --host 0.0.0.0 --port 8008

5. Test:

   $ curl \
     --header "Content-Type: application/json" \
     --request POST \
     --data '{"ticker":"MSFT"}' \
     https://localhost:8008/predict