mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-21 21:54:52 -04:00
Ettore Di Giacinto
9cf4b7f5de
Wire the vllm-cpp backend to the C ABI NER surface (vllm_gliner_ner, ABI v27) so LocalAI can serve zero-shot named entity recognition through the existing TokenClassify gRPC method. backend.go: TokenClassify method on *VllmCpp calls vllm_gliner_ner with the text and labels, copies the C-owned entity array into protobuf TokenClassifyEntity messages, and frees the result. govllmcpp.go: cNerEntity and cNerResult Go POD mirrors matching the C structs; vllmGlinerNer and vllmNerResultFree purego bindings; abiVersion bumped 26 -> 27. options.go: ner_labels, ner_threshold, ner_max_width parsed from engine_args. pkg/grpc: ClassifyModel interface and TokenClassify server handler (follows the Embedding locking pattern). core/config: vllm-cpp backend declares MethodTokenClassify and UsecaseTokenClassify. docs/content/features/vllm-cpp.md: NER section documenting the engine_args keys and the host-forward contract. Assisted-by: MAKI:regolo/glm5.2 [maki]
110 lines
4.9 KiB
Go
110 lines
4.9 KiB
Go
package grpc
|
|
|
|
import (
|
|
"context"
|
|
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
)
|
|
|
|
type AIModel interface {
|
|
Busy() bool
|
|
Lock()
|
|
Unlock()
|
|
Locking() bool
|
|
Predict(*pb.PredictOptions) (string, error)
|
|
PredictStream(*pb.PredictOptions, chan string) error
|
|
Load(*pb.ModelOptions) error
|
|
Free() error
|
|
Embeddings(*pb.PredictOptions) ([]float32, error)
|
|
GenerateImage(*pb.GenerateImageRequest) error
|
|
UpscaleImage(*pb.UpscaleImageRequest) error
|
|
GenerateVideo(*pb.GenerateVideoRequest) error
|
|
Generate3D(*pb.Generate3DRequest) error
|
|
Animate3D(*pb.Animate3DRequest) error
|
|
Detect(*pb.DetectOptions) (pb.DetectResponse, error)
|
|
Depth(*pb.DepthRequest) (pb.DepthResponse, error)
|
|
FaceVerify(*pb.FaceVerifyRequest) (pb.FaceVerifyResponse, error)
|
|
FaceAnalyze(*pb.FaceAnalyzeRequest) (pb.FaceAnalyzeResponse, error)
|
|
VoiceVerify(*pb.VoiceVerifyRequest) (pb.VoiceVerifyResponse, error)
|
|
VoiceAnalyze(*pb.VoiceAnalyzeRequest) (pb.VoiceAnalyzeResponse, error)
|
|
VoiceEmbed(*pb.VoiceEmbedRequest) (pb.VoiceEmbedResponse, error)
|
|
AudioTranscription(context.Context, *pb.TranscriptRequest) (pb.TranscriptResult, error)
|
|
AudioTranscriptionStream(context.Context, *pb.TranscriptRequest, chan *pb.TranscriptStreamResponse) error
|
|
AudioTranscriptionLive(in <-chan *pb.TranscriptLiveRequest, out chan<- *pb.TranscriptLiveResponse) error
|
|
TTS(*pb.TTSRequest) error
|
|
TTSStream(*pb.TTSRequest, chan []byte) error
|
|
SoundGeneration(*pb.SoundGenerationRequest) error
|
|
TokenizeString(*pb.PredictOptions) (pb.TokenizationResponse, error)
|
|
Detokenize(*pb.DetokenizeRequest) (pb.DetokenizeResponse, error)
|
|
Status() (pb.StatusResponse, error)
|
|
|
|
StoresSet(*pb.StoresSetOptions) error
|
|
StoresDelete(*pb.StoresDeleteOptions) error
|
|
StoresGet(*pb.StoresGetOptions) (pb.StoresGetResult, error)
|
|
StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error)
|
|
|
|
VAD(*pb.VADRequest) (pb.VADResponse, error)
|
|
Diarize(*pb.DiarizeRequest) (pb.DiarizeResponse, error)
|
|
SoundDetection(context.Context, *pb.SoundDetectionRequest) (*pb.SoundDetectionResponse, error)
|
|
|
|
AudioEncode(*pb.AudioEncodeRequest) (*pb.AudioEncodeResult, error)
|
|
AudioDecode(*pb.AudioDecodeRequest) (*pb.AudioDecodeResult, error)
|
|
|
|
AudioTransform(*pb.AudioTransformRequest) (*pb.AudioTransformResult, error)
|
|
AudioTransformStream(in <-chan *pb.AudioTransformFrameRequest, out chan<- *pb.AudioTransformFrameResponse) error
|
|
AudioToAudioStream(in <-chan *pb.AudioToAudioRequest, out chan<- *pb.AudioToAudioResponse) error
|
|
|
|
// Forward proxies a raw HTTP request to an upstream provider for
|
|
// passthrough-mode cloud-proxy backends. ctx is the gRPC stream
|
|
// context — cancellation propagates to the upstream HTTP request
|
|
// so client disconnect closes the upstream connection.
|
|
Forward(ctx context.Context, in <-chan *pb.ForwardRequest, out chan<- *pb.ForwardReply) error
|
|
|
|
ModelMetadata(*pb.ModelOptions) (*pb.ModelMetadataResponse, error)
|
|
|
|
// Fine-tuning
|
|
StartFineTune(*pb.FineTuneRequest) (*pb.FineTuneJobResult, error)
|
|
FineTuneProgress(*pb.FineTuneProgressRequest, chan *pb.FineTuneProgressUpdate) error
|
|
StopFineTune(*pb.FineTuneStopRequest) error
|
|
ListCheckpoints(*pb.ListCheckpointsRequest) (*pb.ListCheckpointsResponse, error)
|
|
ExportModel(*pb.ExportModelRequest) error
|
|
|
|
// Quantization
|
|
StartQuantization(*pb.QuantizationRequest) (*pb.QuantizationJobResult, error)
|
|
QuantizationProgress(*pb.QuantizationProgressRequest, chan *pb.QuantizationProgressUpdate) error
|
|
StopQuantization(*pb.QuantizationStopRequest) error
|
|
}
|
|
|
|
func newReply(s string) *pb.Reply {
|
|
return &pb.Reply{Message: []byte(s)}
|
|
}
|
|
|
|
// AIModelRich is an optional extension to AIModel for backends that
|
|
// can produce a full *pb.Reply — including tool-call deltas and
|
|
// usage tokens — rather than just a content string. The gRPC server
|
|
// type-asserts and prefers the rich path when implemented; otherwise
|
|
// it wraps Predict's string return in a Reply.
|
|
//
|
|
// Cloud-proxy translate mode is the motivating use case: the upstream
|
|
// emits structured tool_calls that would be lost through the legacy
|
|
// (string, error) signature.
|
|
//
|
|
// PredictStreamRich contract: send replies into the channel and
|
|
// return when finished. Do NOT close the channel — the server closes
|
|
// it after the call returns. This is opposite to legacy PredictStream
|
|
// which expects the impl to defer close().
|
|
type AIModelRich interface {
|
|
PredictRich(*pb.PredictOptions) (*pb.Reply, error)
|
|
PredictStreamRich(*pb.PredictOptions, chan<- *pb.Reply) error
|
|
}
|
|
|
|
// ClassifyModel is an optional extension to AIModel for backends that
|
|
// implement the TokenClassify RPC (zero-shot NER). The gRPC server
|
|
// type-asserts to this interface; backends that do not implement it
|
|
// fall through to the UnimplementedBackendServer default. This mirrors
|
|
// the AIModelRich pattern: adding a method to AIModel itself would
|
|
// break every backend, so the capability is opt-in.
|
|
type ClassifyModel interface {
|
|
TokenClassify(context.Context, *pb.TokenClassifyRequest) (*pb.TokenClassifyResponse, error)
|
|
}
|