https://github.com/dudeperf3ct/4-ml-fastapi-azure-serverless
https://github.com/dudeperf3ct/4-ml-fastapi-azure-serverless
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/dudeperf3ct/4-ml-fastapi-azure-serverless
- Owner: dudeperf3ct
- Created: 2021-12-08T16:52:05.000Z (over 3 years ago)
- Default Branch: master
- Last Pushed: 2021-12-09T12:41:46.000Z (over 3 years ago)
- Last Synced: 2024-12-31T10:17:46.652Z (5 months ago)
- Language: Jupyter Notebook
- Size: 1.16 MB
- Stars: 2
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
### Deploy ML model to Azure using FastAPI
Azure app: https://wine-ratings.azurewebsites.net/
In this exercise, we will build a fastapi ML application and deploy it with continuous delivery on Azure using Azure App Services and Azure DevOps Pipelines.
### ML
To build a ML model, refer the colab notebook under `notebooks` folder.
### FastAPI
To validate the fastapi application locally,
```bash
docker build -t wine .
docker run --rm -it -v $(pwd):/app -p 8000:8000 wine
```
### Azure
To deploy the fastapi application on Azure following steps were taken.
1. Add Azure Pipelines from Github Marketplace while creating the github repo.
2. Create a Azure DevOps account and create a build pipeline for this repo. Check if the build was successful.
3. Create a Azure account and from `Container registries` -> `Repositories`, using the proper docker image created from previous step and tag, click `Deploy to web app` option.