Emilio Garcia

@abhibongale I saw your PR was closed, do you still want to work on this, or can another contributor pick this up?

We plan to just switch versions over when the release lands. Thanks for alerting us, we will close this when 1.23.0 releases and we update the CI template

To answer your question about tool calls more literally, "Function Tools" refers to a design pattern where a model returns a tool execution command to the client, and then a...

This is blocked by https://github.com/llamastack/llama-stack/issues/3806. I want to steer llama stack towards using automatic instrumentation as the default way to capture telemetry data in llama stack, and we should get...

This is an important note: OpenAI clients currently have telemetry automatically due to there being an OTEL library to detect and instrument them. This is not the case for llama...

The mock OTLP collector is a basic abstraction and we are really trying to keep it as simple as possible for it to work as nothing more than a testing...

@skamenan7 Sorry to say, my changes are going to make a bit of work for you. I would really suggest working in the bounds of the changes I made and...

I think we are doing this backwards @mattf. @skamenan7 and I are going to pair on this to position this change as a follow up PR to #4127. I can...

I think this fix is fine in cases where llama stack is your only model registry, but the caching mechanism might need some more thought. It seems prone to data...