LocalAI/pkg/grpc
mintyleaf 0d6c3a7d57
feat: include tokens usage for streamed output (#4282)
Use pb.Reply instead of []byte with Reply.GetMessage() in llama grpc to get the proper usage data in reply streaming mode at the last [DONE] frame

Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2024-11-28 14:47:56 +01:00
..
base feat(silero): add Silero-vad backend (#4204) 2024-11-20 14:48:40 +01:00
backend.go feat: include tokens usage for streamed output (#4282) 2024-11-28 14:47:56 +01:00
client.go feat: include tokens usage for streamed output (#4282) 2024-11-28 14:47:56 +01:00
embed.go feat: include tokens usage for streamed output (#4282) 2024-11-28 14:47:56 +01:00
interface.go feat(silero): add Silero-vad backend (#4204) 2024-11-20 14:48:40 +01:00
server.go feat(silero): add Silero-vad backend (#4204) 2024-11-20 14:48:40 +01:00