Skip to content

Conversation

@Dhruvkumar-Microsoft
Copy link
Contributor

Purpose

This pull request updates the Azure deployment configuration to support multiple AI model types and improves parameter clarity. The main changes include adding parameters for new model variants (such as GPT-4.1 and a reasoning model), updating default values for existing model parameters, and ensuring the infrastructure templates (main.parameters.json and main.waf.parameters.json) are aligned with these changes.

Model configuration enhancements:

  • Added new environment parameters for GPT-4.1 and a reasoning model, including deployment type, model name, version, and capacity to docs/CustomizingAzdParameters.md.
  • Updated default values for the main GPT model to use gpt-4.1-mini and version 2025-04-14, and reduced its default capacity from 150 to 50.
  • Added and updated Docker image tag parameter to use latest_v3 by default.

Infrastructure parameter alignment:

  • Synchronized new and updated model parameters in infra/main.parameters.json and infra/main.waf.parameters.json to accept values for the new model variants and capacities. [1] [2]

Parameter organization and clarity:

  • Reordered and clarified the documentation table in CustomizingAzdParameters.md for better readability, and ensured all parameters are consistently documented.

Does this introduce a breaking change?

  • Yes
  • No

How to Test

  • Get the code
git clone [repo-address]
cd [repo-name]
git checkout [branch-name]
npm install
  • Test the code

What to Check

Verify that the following are valid

  • ...

Other Information

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant