Pamela Fox

Curiously, it appears we never had that instruction for the Ask tab, even before the Prompty change: https://github.com/Azure-Samples/azure-search-openai-demo/pull/2178/files#diff-8457664fc3e0fe6195bebe311a95cd6d1b59418ed7448327d871078b076867e9L20 I agree that it's helpful for the LLM however, so I will...

The backend asks the model (using "tools") to decide on a search query based off what it hears, so either the model heard correctly but then translated it into a...

I've heard another developer say that they got better performance with different temperatures when the model didn't parse their voice, that might be worth trying?

Hm, how would we detect which field is viable? Wouldn't that require a network call?

Thanks for the report, I assume you're using the latest version of the chat history code? (There was an update a few months ago).

Did you close on purpose?

Okay, re-opening, you're all set!

Yes, this is considered your submission.

Hm, we should be adding a vectorizer with the latest code. searchmanager.py is the file that sets up the vectorizer for both existing and new indexes. Here's the code that...

As far as I know, C# does not yet have: * User authentication * Data access control * User uploads * Integrated vectorization support * GPT-4-vision support * ADLS2 support...