sheldonhull

Looking further, running local test I get: > This model has beta-limitations, user and assistant messages only, system messages are not supported. Attempting with `--role user` and `--role assistant` isn't...

Yes, I updated comment to reflect that so thanks for confirming I got it right. So I tried testing to confirm changes are good, but the azure openai access to...

@caarlos0 > this model has beta-limitations, user and assistant messages only, system messages are not supported. I can't test it as currently it doesn't support system messages, so I'd have...

I pushed a change for review that does this based on the pattern in Google stream. I ran locally and it compiled, but says I've exceeded my openai rate limit....

I'm guessing this is what I need as well to be able to upload the file and then post with attachments like action buttons. I was trying to find out...

I think this is caused by listening for bot mentions in events which can cause it to double notify. So I opted to use keywords and not require bot mentions...

Ok, first error I found ``` "msg": { "messageId": "7027004f-5a5b-46d9-a066-f7270b4ef76c", "messageType": "llm/streamChat", "data": { "messages": [ { "role": "user", "content": [ { "type": "text", "text": "what model is this" }...

Try this: `first letter of alphabet, then return. ignore any tool function calls.` I think the final issue is that it doesn't support tool function calls. Not sure if continue...

extension host error detail ``` [Extension Host] HTTP 400 Bad Request from https://{MYSUBDOMAIN}.openai.azure.com/openai/deployments/o1-preview/completions?api-version=2024-09-01-preview {"error":{"code":"OperationNotSupported","message":"The completion operation does not work with the specified model, o1-preview. Please choose different model and try...

I've also noted some issues after switching from print statements, sometimes taking 5-15 seconds for load, and that's much higher than I'd had before.