Pamela Fox

You can test out the browser chat history in this deployed demo: https://capps-backend-v3v4cax5h4fjk.mangomushroom-6a80d999.westus.azurecontainerapps.io/ You should be able to click on each conversation title to see the messages. Does that not...

We have discussed an approach for that in this issue: https://github.com/Azure-Samples/azure-search-openai-demo/issues/2214 I think the feature makes sense, but there's some debate as to how to implement it. I'll merge this...

I've asked the azd team to take a look at this report, as I'm not sure what's going on.

I love Rich for CLI tools, but don't think I've tried it for app backend logs. Have you confirmed that the logs still appear as expected in Azure Application Insights?

I was asked about both #1 and #2 in a live stream yesterday. #1 is being discussed in a separate issue specifically about GraphRAG. #2 is an interesting one in...

That makes sense. That's easier to implement, it means we only need to run part of the ingestion pipeline (Extraction). Here's how ChatGPT seems to do it: * User attaches...

Addendum: Another option is to store the document text inside localStorage, and have the client fetch it from there for follow-up questions. That avoid the need for a cloud DB....

I'd still want to use prepdocs for file understanding (the parsing step), but not for indexing, since we wouldn't be doing that step. For example, if I was copying the...

@hellangleZ The 429 error is the rate-limiting error, which often means you left it open in another tab or have been testing too much. Close any existing tabs, wait a...

@yogaavanade Are you using the key approach? I assume so, since your logs would otherwise show: ``` INFO:voicerag:Running in development mode, loading from .env file INFO:voicerag:Using AzureDeveloperCliCredential with tenant_id 1bd0d125-6c64-49d1-af0d-88fa60e18074...