https://github.com/hassan11196/ml-model-ship-and-deploy

How to properly ship and deploy your machine learning model with FastAPI, Docker, and GitHub Actions
https://github.com/hassan11196/ml-model-ship-and-deploy

docker docker-image fastapi hacktoberfest machine-learning ml python uvicorn

Last synced: 3 months ago
JSON representation

How to properly ship and deploy your machine learning model with FastAPI, Docker, and GitHub Actions

• Host: GitHub
• URL: https://github.com/hassan11196/ml-model-ship-and-deploy
• Owner: hassan11196
• License: mit
• Created: 2020-02-01T09:25:16.000Z (about 5 years ago)
• Default Branch: master
• Last Pushed: 2023-11-03T17:59:42.000Z (over 1 year ago)
• Last Synced: 2023-11-03T22:24:34.199Z (over 1 year ago)
• Topics: docker, docker-image, fastapi, hacktoberfest, machine-learning, ml, python, uvicorn
• Language: Python
• Homepage: https://ml-fastapi-model.herokuapp.com/docs
• Size: 686 KB
• Stars: 8
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# How to properly ship and deploy your machine learning model

A practical guide with FastAPI, Docker and GitHub Actions

## Project setup

1. Create the virtual environment.

```

virtualenv /path/to/venv --python=/path/to/python3

```

You can find out the path to your `python3` interpreter with the command `which python3`.

2. Activate the environment and install dependencies.

```

source /path/to/venv/bin/activate

pip install -r requirements.txt

```

3. Launch the service

```

uvicorn api.main:app

```

## Posting requests locally

When the service is running, try

```

127.0.0.1/docs

```

or 

```

curl

```

## Deployment with Docker

1. Build the Docker image

```

docker build --file Dockerfile --tag fastapi-ml-quickstart .

```

2. Running the Docker image

```

docker run -p 8000:8000 fastapi-ml-quickstart

```

3. Entering into the Docker image

```

docker run -it --entrypoint /bin/bash fastapi-ml-quickstart

```

## docker-compose

1. Launching the service

```

docker-compose up

```

This command looks for the `docker-compose.yaml` configuration file. If you want to use another configuration file,

it can be specified with the `-f` switch. For example  

2. Testing

```

docker-compose -f docker-compose.test.yaml up --abort-on-container-exit --exit-code-from fastapi-ml-quickstart

```

Reference: 

https://towardsdatascience.com/how-to-properly-ship-and-deploy-your-machine-learning-model-8a8664b763c4