API Error When Assistants Do Not Utilize Attached Tools

[VRSEN]

Description

When adding tools to an assistant, the API throws an error if the assistant does not utilize them. In OpenAI, assistants can choose whether to use tools or not. This issue originates from the threads.py create_run method.

Steps to Reproduce

1. Create an assistant with any custom tool. (function)
2. Ask the assistant to say "hi."
3. Observe the error: "Could not extract function arguments from LLM response, may have not been properly formatted. Consider retrying or use a different model."

Expected Behavior

In OpenAI, tools can be attached to an assistant, allowing it to decide whether or not to use them. This autonomy in tool utilization is crucial for any agentic system.

Actual Behavior

The operation fails with the error:
ValueError("Could not extract function arguments from LLM response, may have not been properly formatted. Consider retrying or use a different model.")

Additional Information

• OpenAI version: 1.20.0
• Python version: 3.10.13
• Streaming assistants version: 0.16.0
• Operating System: macOS 14.1.1

[phact]

Working on this now

[phact]

Fix here - 921f687

Shipped in v0.1.20, live on the service.

@VRSEN feel free to try it on your end.

[phact]

@VRSEN should we close this one since it's been fixed for a while?