Skip to main content
This is lesson 4 of 8 in this module Course 21% complete
Prev Next Skip

Comparing Per-Turn Code Patterns

Premium Content

Sign in with your account or sign up to access this lesson.

Sign In Sign Up

We walk through the Python code patterns for both APIs step by step, showing how ChatCompletions manually manages the message array of system, user, and assistant roles while Responses API offloads history management to the cloud, and conclude with a lab to build a minimal LLM chat harness.

Previous Next
Previous Module The Principles of Responsible AI
This Module Develop a Generative AI Chat App
Develop a Generative AI Chat App with Microsoft Foundry
Develop a Generative AI Chat App with Microsoft Foundry
Choosing an Endpoint and SDK
Choosing an Endpoint and SDK
Comparing ChatCompletions and Responses API
Comparing ChatCompletions and Responses API
Comparing Per-Turn Code Patterns
Comparing Per-Turn Code Patterns
Tools and Agents
Tools and Agents
Using the Code Interpreter Tool
Using the Code Interpreter Tool
Using Web Search and File Search Tools
Using Web Search and File Search Tools
Using the Function Tool
Using the Function Tool
Next Module Optimizing Generative AI Chat Apps