The response from o1 is not formatted correctly

[cloud-25683]

What happened?

UI rendering issue for o1 model's response, this only happens to o1, not o1-preview, o1-mini and gpt-4 models, see attached image

Steps to Reproduce

choose azure openai o1 model, ask this question: "what is black-scholes equation?", saw strange formatting issue on the UI

What browsers are you seeing the problem on?

No response

Relevant log output

Screenshots

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

LLM issue, try a later API version for Azure

[cloud-25683]

I just tried latest api version "2025-01-01-preview", the issue only appears randomly without any pattern (same prompt asked a few times, sometime works and sometime it doesn't). so this is definitely LLM issue then, right?

[otbu2]

I can reproduce this on a local installation of v0.7.6 using the Docker images. It seems to happen consistently.

Models used via API: gpt-4o-2024-11-20 (latest) and o1-2024-12-17. Browser is Google Chrome 132.0.6834.159 on Ubuntu 24.04.

[danny-avila]

Please read this:
https://platform.openai.com/docs/guides/reasoning#advice-on-prompting

Starting with o1-2024-12-17, reasoning models in the API will avoid generating responses with markdown formatting.