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

..

assistant_test.go

docs(swagger): core more localai/openai endpoints (#2904)

2024-07-18 00:38:41 -04:00

assistant.go

fix: roll out bluemonday Sanitize more widely (#3794)

2024-10-12 09:45:47 +02:00

chat.go

feat: include tokens usage for streamed output (#4282)

2024-11-28 14:47:56 +01:00

completion.go

feat(api): add correlationID to Track Chat requests (#3668)

2024-09-28 17:23:56 +02:00

edit.go

docs(swagger): core more localai/openai endpoints (#2904)

2024-07-18 00:38:41 -04:00

embeddings.go

feat(model-list): be consistent, skip known files from listing (#2760)

2024-07-10 15:28:39 +02:00

files_test.go

docs(swagger): core more localai/openai endpoints (#2904)

2024-07-18 00:38:41 -04:00

files.go

fix: roll out bluemonday Sanitize more widely (#3794)

2024-10-12 09:45:47 +02:00

image.go

fix(diffusers): correctly parse height and width request without parametrization (#4082)

2024-11-06 08:53:02 +01:00

inference.go

feat(api): allow to pass audios to backends (#3603)

2024-09-19 12:26:53 +02:00

list.go

groundwork: ListModels Filtering Upgrade (#2773)

2024-10-01 18:55:46 +00:00

request.go

chore(refactor): imply modelpath (#4208)

2024-11-20 18:06:35 +01:00

transcription.go

feat(model-list): be consistent, skip known files from listing (#2760)

2024-07-10 15:28:39 +02:00