| title | description | icon |
|---|---|---|
Wyvern Application |
layer-group |
Wyvern is a machine learning platform that empowers data scientists to independently build and deploy production-grade machine learning pipelines for the e-commerce industry, reducing the engineering involvement in the entire process.
Wyvern's application is built to make it easy to serve your ML application to your production. It is built on top of fastapi with lots of built-in Wyvern functionalities. It is a web framework that holds all the Wyvern ML pipelines and serves them through API.
Let's see how to build the wyvern app:
from wyvern import WyvernService
# the app is a fastapi application
app = WyvernService.generate_app()The app is an fastapi app. You can run the application with wyvern run:
wyvern run --path pipelines.main:appOutput:
Running your ML application
INFO: Started server process [17449]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:5001 (Press CTRL+C to quit)
Next, let's see how what is an Wyvern ML pipeline is.