Create pipeline configuration

AI SDK How-To

Product: AI Software Development Kit
Product Version: 2.4.0
Language: en-US

Prepare your environment
Setting up the work environment
Setting up an environment manager
Installing AI SDK
How to setup up a notebook editor
How to setup environment manager environments to work with tutorials
Create PythonComponents
How to define PythonComponents
How to create the entrypoint
How to use variable types
How to handle Python dependencies
How to handle file resources
How to return the processing results
How to add custom metrics
How to use persistent storage on AI Inference Server
What versions of major Python dependencies are supported?
Process different data types
How to process time series of signals
How to process images
How to use Binary format for images
How to use Object format for images
How to use TensorFlow instead of TensorFlow Light
Create pipeline configuration
How to use pipeline parameters
How to write components for earlier versions (<1.2) of the AI Inference Server
How to version packages and how to use Package ID
How to package models into an inference pipeline
Test pipelines
How to mock AI Inference Server logger locally
How to test edge configuration package locally
How to test pipelines on an Edge Device
Create pipeline packages
How to convert and deploy the packaged inference pipeline to AI@Edge
How to create Delta packages

Back to home page