Skip to content

Conversation

@Kanchan-Microsoft
Copy link
Contributor

Purpose

This pull request adds a new documentation file to guide users on deploying the Document Knowledge Mining Solution Accelerator when their Azure OpenAI quota is limited. The document explains how to adjust deployment settings to accommodate lower token-per-minute (TPM) limits, outlines configuration steps, and provides performance considerations.

Documentation improvements:

  • Added docs/DeployWithLimitedQuota.md to provide step-by-step instructions for deploying with reduced Azure OpenAI quota, including options to bypass or modify quota validation in infra/main.bicep.
  • Included guidance on updating environment variables and explained the impact of reduced TPM on application performance.
  • Linked to related resources for further information, such as the deployment guide and quota check script.
  • Clarified why quota validation is necessary and how to avoid deployment failures due to hardcoded thresholds in the infrastructure file.

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

  • ...

Other Information

})
```

### Option 2: Modify Quota Thresholds (Recommended)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Recommended option should be on top

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.

3 participants