yuyuma
yuyuma
On Slack https://livekit-users.slack.com/archives/C07FY8WHGPM/p1729050553562499 David pointed me to this issue. I just wanted to add that I'm also looking for usage data from plugin responses, specifically for realtime agent framework. The...
@davidzhao perhaps I've missed something but I took a brief look through #984 and didn't see anything related to exposing token usage for openai realtime plugin. was this issue only...
It looks like some basic considerations were made for the realtime model with a `Usage` model defined here: https://github.com/livekit/agents/blob/22f06bf321532a92e12b7a469692f0c8e5503dd4/livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/realtime/api_proto.py#L144 I just wanted to add that the exposed usage details should...
@davidzhao done, thanks!
+1 as another very interested in Whatsapp Calling and unable to proceed due to lack of Opus support
https://kb.livekit.io/articles/5987869072-whatsapp-integration-with-livekit source: https://livekit-users.slack.com/archives/C07FRP66XGE/p1755638133569199?thread_ts=1752642962.140529&cid=C07FRP66XGE
Related slack discussion: https://livekit-users.slack.com/archives/C07FY8WHGPM/p1745063954228409?thread_ts=1745063954.228409&cid=C07FY8WHGPM
I filed an issue yesterday https://github.com/livekit/agents/issues/1955 that is a manifestation of tools being represented by python functions in Livekit. I'm in favor of any way that allows us to specify...
@ishaan-jaff responding to your Discord question here. Regarding your question on litellm proxy vs python SDK, I think proxy? For chat completions endpoint we use essentially this setup (https://docs.litellm.ai/docs/observability/langfuse_integration), except...