Pamela Fox

FYI @mattgotteiner, this is a write-up of what we discussed. Let me know if anything seems incorrect. I am tackling this now.

@jaspb I ended up going with a simpler approach of actually moving prepdocs entirely inside app/backend, to avoid that issue as well as avoid the complexity of polling for ingestion...

Closing since this is now a feature in the app.

Ah, that is because OPENAI_HOST="local" is only intended for use when testing locally, my assumption is that you'll switch it back to one of the other hosts when running the...

If you can set up the VM, then you should be able to access it via its URL. Here's the relevant constructor code for the OpenAI clients: https://github.com/Azure-Samples/azure-search-openai-demo/blob/c835b48a5b5f56eba9418fa93dc2d7f73e93fec7/app/backend/app.py#L320 For deployment,...

The speed of the response will be based on the speed of the various services. For the chat tab, that involves: 1. Call to ChatCompletion API to turn user query...

cc @srbalakr @mattgotteiner I think I saw this as well- I was noticing my citation filenames were missing page numbers and wondered where they went to.

I asked the AI Search team about this and got a few suggestions: * Through AI Document intelligence, using a custom skill, they would just need to modify this to...

Hi @d-paulus - I assume this is using the /chat endpoint? The first step of that endpoint uses a ChatGPT model to generate a query based on the user's question....

Interesting, so for the same inputs, you're getting different results from the Cognitive Search call? I'm not an ACS expert so I'll CC @srbalakr from the ACS team to see...