LocalAI/pkg/grpc/backend.go
Richard Palethorpe bf6426aef2
Some checks are pending
Explorer deployment / build-linux (push) Waiting to run
GPU tests / ubuntu-latest (1.21.x) (push) Waiting to run
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Waiting to run
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, extras, latest-gpu-hipblas-extras, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, auto, -hipblas-extras) (push) Waiting to run
build container images / hipblas-jobs (rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, extras, latest-gpu-intel-f16-extras, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16-… (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, extras, latest-gpu-intel-f32-extras, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32-… (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, extras, latest-gpu-nvidia-cuda-11-extras, latest-aio-gpu-nvidia-cuda-11, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda11-extras) (push) Waiting to run
build container images / self-hosted-jobs (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, extras, latest-gpu-nvidia-cuda-12-extras, latest-aio-gpu-nvidia-cuda-12, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -cublas-cuda12-extras) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, latest-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (push) Waiting to run
build container images / self-hosted-jobs (quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, latest-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (push) Waiting to run
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, ) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Waiting to run
build container images / core-image-build (ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (push) Waiting to run
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Waiting to run
Security Scan / tests (push) Waiting to run
Tests extras backends / tests-transformers (push) Waiting to run
Tests extras backends / tests-rerankers (push) Waiting to run
Tests extras backends / tests-diffusers (push) Waiting to run
Tests extras backends / tests-coqui (push) Waiting to run
tests / tests-linux (1.21.x) (push) Waiting to run
tests / tests-aio-container (push) Waiting to run
tests / tests-apple (1.21.x) (push) Waiting to run
feat: Realtime API support reboot (#5392)
* feat(realtime): Initial Realtime API implementation

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore: go mod tidy

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* feat: Implement transcription only mode for realtime API

Reduce the scope of the real time API for the initial realease and make
transcription only mode functional.

Signed-off-by: Richard Palethorpe <io@richiejp.com>

* chore(build): Build backends on a separate layer to speed up core only changes

Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2025-05-25 22:25:05 +02:00

59 lines
2.6 KiB
Go

package grpc
import (
"context"
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
"google.golang.org/grpc"
)
var embeds = map[string]*embedBackend{}
func Provide(addr string, llm LLM) {
embeds[addr] = &embedBackend{s: &server{llm: llm}}
}
func NewClient(address string, parallel bool, wd WatchDog, enableWatchDog bool) Backend {
if bc, ok := embeds[address]; ok {
return bc
}
return buildClient(address, parallel, wd, enableWatchDog)
}
func buildClient(address string, parallel bool, wd WatchDog, enableWatchDog bool) Backend {
if !enableWatchDog {
wd = nil
}
return &Client{
address: address,
parallel: parallel,
wd: wd,
}
}
type Backend interface {
IsBusy() bool
HealthCheck(ctx context.Context) (bool, error)
Embeddings(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.EmbeddingResult, error)
LoadModel(ctx context.Context, in *pb.ModelOptions, opts ...grpc.CallOption) (*pb.Result, error)
PredictStream(ctx context.Context, in *pb.PredictOptions, f func(reply *pb.Reply), opts ...grpc.CallOption) error
Predict(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.Reply, error)
GenerateImage(ctx context.Context, in *pb.GenerateImageRequest, opts ...grpc.CallOption) (*pb.Result, error)
GenerateVideo(ctx context.Context, in *pb.GenerateVideoRequest, 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)
AudioTranscription(ctx context.Context, in *pb.TranscriptRequest, opts ...grpc.CallOption) (*pb.TranscriptResult, error)
TokenizeString(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.TokenizationResponse, error)
Status(ctx context.Context) (*pb.StatusResponse, error)
StoresSet(ctx context.Context, in *pb.StoresSetOptions, opts ...grpc.CallOption) (*pb.Result, error)
StoresDelete(ctx context.Context, in *pb.StoresDeleteOptions, opts ...grpc.CallOption) (*pb.Result, error)
StoresGet(ctx context.Context, in *pb.StoresGetOptions, opts ...grpc.CallOption) (*pb.StoresGetResult, error)
StoresFind(ctx context.Context, in *pb.StoresFindOptions, opts ...grpc.CallOption) (*pb.StoresFindResult, error)
Rerank(ctx context.Context, in *pb.RerankRequest, opts ...grpc.CallOption) (*pb.RerankResult, error)
GetTokenMetrics(ctx context.Context, in *pb.MetricsRequest, opts ...grpc.CallOption) (*pb.MetricsResponse, error)
VAD(ctx context.Context, in *pb.VADRequest, opts ...grpc.CallOption) (*pb.VADResponse, error)
}