Skip to content

Conversation

@aprilk-ms
Copy link
Contributor

@aprilk-ms aprilk-ms commented May 2, 2025

evaluate.py script output looks like this:

{A11917CC-E8B1-449A-A077-9A5457611AC7}

with:
azure-aiproject-connection-string: ${{ vars.AZURE_EXISTING_AIPROJECT_CONNECTION_STRING || vars.AZURE_AIPROJECT_CONNECTION_STRING }}
deployment-name: ${{ vars.AZURE_AI_AGENT_DEPLOYMENT_NAME }}
agent-ids: ${{ vars.AZURE_EXISTING_AGENT_ID || vars.AZURE_AI_AGENT_ID }}
Copy link
Contributor Author

Choose a reason for hiding this comment

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

Can we make sure AZURE_EXISTING_AGENT_ID gets written to .env during startup?

@@ -0,0 +1,10 @@
[
{
Copy link
Contributor Author

Choose a reason for hiding this comment

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

TODO: Update to queries more relevant for this app

tool_call_accuracy = ToolCallAccuracyEvaluator(model_config=model_config)
intent_resolution = IntentResolutionEvaluator(model_config=model_config)
task_adherence = TaskAdherenceEvaluator(model_config=model_config)
results = evaluate(
Copy link
Contributor Author

Choose a reason for hiding this comment

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

Need to make sure both the user (whoever did azd up) has access to storage, otherwise uploading to AI Foundry won't work out of the box

@aprilk-ms aprilk-ms closed this by deleting the head repository Oct 29, 2025
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