LocalAI/core/backend
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
..
backend_suite_test.go feat: extract output with regexes from LLMs (#3491) 2024-09-13 13:27:36 +02:00
embeddings.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
image.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
llm_test.go feat: extract output with regexes from LLMs (#3491) 2024-09-13 13:27:36 +02:00
llm.go feat: include tokens usage for streamed output (#4282) 2024-11-28 14:47:56 +01:00
options.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
rerank.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
soundgeneration.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
stores.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
token_metrics.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
tokenize.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
transcript.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00
tts.go chore(refactor): drop unnecessary code in loader (#4096) 2024-11-08 21:54:25 +01:00