Skip to content

Conversation

@Roopan-Microsoft
Copy link
Collaborator

Purpose

  • This pull request updates the Azure deployment configuration to support multiple GPT model types and improves parameter clarity and flexibility. The most important changes are the addition of new parameters for different GPT models and reasoning models, updates to default values, and corresponding changes in infrastructure parameter files.

Support for multiple GPT models and reasoning models:

  • Added new environment parameters for a dedicated GPT-4.1 model and a reasoning model, including deployment type, name, version, and capacity in docs/CustomizingAzdParameters.md, infra/main.parameters.json, and infra/main.waf.parameters.json. [1] [2] [3]

Parameter and default value updates:

  • Updated default GPT model parameters to use gpt-4.1-mini (name), 2025-04-14 (version), and reduced capacity to 50. Also updated the Docker image tag default to latest_v3.
  • Changed the ordering and grouping of parameters in documentation to reflect the new model options and defaults.

Documentation improvements:

  • Removed outdated parameter descriptions from docs/DeploymentGuide.md to avoid confusion and ensure documentation matches the new configuration options.

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

@Roopan-Microsoft Roopan-Microsoft merged commit 6e99dad into main Nov 3, 2025
12 checks passed
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.

4 participants