get_token_limit, build_messages for o series model

[NangMPLwin]

I'm trying to change o3-model and testing it on https://github.com/Azure-Samples/azure-search-openai-demo for the chatbot, can you please share me the resource or any update for the code for o3-mini.

[pamelafox]

We're going to remove use of this package for that repo:
Azure-Samples/azure-search-openai-demo#2449

But if you do want to keep it, you'd need to change the MODELS_2_TOKEN_LIMITS in this file:
https://github.com/pamelafox/openai-messages-token-helper/blob/main/src/openai_messages_token_helper/model_helper.py

[pamelafox]

I don't think this would work for reasoning models anyway, since we can't estimate the reasoning tokens that would be used?

By the way, my colleague Matt is adding support for o3-mini, check out his PR here:
Azure-Samples/azure-search-openai-demo#2448