fix: update GPT model capacity and fix aiDeploymentsLocation issue

[Priyanka-Microsoft]

Purpose

• ...
  This pull request updates the default capacities for AI models, adjusts environment variables in the deployment workflow, and ensures documentation reflects these changes. The most important changes include modifying model capacities, adding a new environment variable for deployment location, and updating scripts and documentation to align with the new capacities.

Deployment Workflow Updates:

• .github/workflows/deploy.yml: Reduced GPT_MIN_CAPACITY from 250 to 150 and increased TEXT_EMBEDDING_MIN_CAPACITY from 40 to 80. Added AZURE_LOCATION as a new environment variable for AI deployments. [1] [2]

Documentation Updates:

• docs/QuotaCheck.md: Updated default capacities for gpt4.1 and gpt-4 to 150, ensuring consistency with the new deployment settings. Adjusted example commands to reflect the updated capacities. [1] [2]

Script Updates:

• scripts/quota_check_params.sh: Updated DEFAULT_MODEL_CAPACITY to use the new capacities (gpt4.1:150 and text-embedding-ada-002:80).

Does this introduce a breaking change?

• Yes
• No

Golden Path Validation

• I have tested the primary workflows (the "golden path") to ensure they function correctly without errors.

Deployment Validation

• I have validated the deployment process successfully and all services are running as expected with this change.

What to Check

Verify that the following are valid

• I have built and tested the code locally and in a deployed app
• For frontend changes, I have pulled the latest code from main, built the frontend, and committed all static files.
• This is a change for all users of this app. No code or asset is specific to my use case or my organization.

Other Information

[github-actions]

🎉 This PR is included in version 1.6.0 🎉

The release is available on GitHub release

Your semantic-release bot 📦🚀