dearwolf/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2025-05-20 10:35:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 21

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

Browse source 
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>
This commit is contained in:
mintyleaf 2024-11-28 17:47:56 +04:00 • committed by GitHub
parent e001fada6c
commit 0d6c3a7d57
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 25 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

2
pkg/grpc/backend.go
View file

@ -37,7 +37,7 @@ type Backend interface {
Embeddings(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.EmbeddingResult, error)
Predict(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.Reply, error)
LoadModel(ctx context.Context, in *pb.ModelOptions, opts ...grpc.CallOption) (*pb.Result, error)
PredictStream(ctx context.Context, in *pb.PredictOptions, f func(s []byte), opts ...grpc.CallOption) error
PredictStream(ctx context.Context, in *pb.PredictOptions, f func(reply *pb.Reply), opts ...grpc.CallOption) error
GenerateImage(ctx context.Context, in *pb.GenerateImageRequest, opts ...grpc.CallOption) (*pb.Result, error)
TTS(ctx context.Context, in *pb.TTSRequest, opts ...grpc.CallOption) (*pb.Result, error)
SoundGeneration(ctx context.Context, in *pb.SoundGenerationRequest, opts ...grpc.CallOption) (*pb.Result, error)