[Server]: Deployed Azure instances with endpoints do not run agents

[andrewhooker2]

⚠️ Search for existing issues first ⚠️

• [X] I have searched the existing issues, and there is no existing issue for my problem

Which Operating System are you using?

MacOS

Which version of AutoGPT are you using?

Latest Release

What LLM Provider do you use?

Azure

Which area covers your issue best?

Installation and setup

What commit or version are you using?

4bbbbd6e2153cfbbce38c78b1985aa14a10dccf4

Describe your issue.

While working with the Builder and adding LLM agent blocks we are not able to work with an Azure deployment of Open AI's 4o or other models.

We followed the guidance in the docs referenced here: Using a GPT Azure-instance but were not seeing our deployed instances become leveraged.

Screenshot:

Upload Activity Log Content

No response

Upload Error Log Content

The Server throws this error:

[ExecutionManager][graph-eid-90016001-9dc8-474d-acea-23f3033670eb|node-eid-df2a5c8e-2550-4099-a081-41617a51f9fa|-] Finished node execution
Error calling LLM: Connection error.
Error calling LLM: Connection error.
Error calling LLM: Connection error.
[ExecutionManager][graph-eid-90016001-9dc8-474d-acea-23f3033670eb|node-eid-d4512497-458f-4165-b7ff-63380f1d7e7b|TextLlmCallBlock] Executed, output [error]:`exceptions must derive from BaseException`
[ExecutionManager][graph-eid-90016001-9dc8-474d-acea-23f3033670eb|node-eid-d4512497-458f-4165-b7ff-63380f1d7e7b|-] Finished node execution
[ExecutionManager][graph-eid-90016001-9dc8-474d-acea-23f3033670eb|node-eid-*|-] Finished graph execution

[github-actions[bot]]

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

[github-actions[bot]]

This issue was closed automatically because it has been stale for 10 days with no activity.