mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-31 10:28:43 -04:00
ef724a3c9d
* feat(api): add /v1/detokenize endpoint Closes #1649. Mirror of the existing /v1/tokenize path, requested by @benniekiss in the issue thread for "complete API workflow" use cases that need to turn token IDs back into text without local processing. - Add Detokenize gRPC RPC with DetokenizeRequest{tokens} / DetokenizeResponse{content} messages. - Implement in the llama.cpp backend using common_token_to_piece, the same primitive TokenizeString already uses internally. - Other backends inherit the default Unimplemented from base.Base, in line with how Detect, Rerank, etc. are gated per-backend. - Wire up the Go gRPC interface, server, client, and in-process embed wrapper alongside their TokenizeString counterparts. - Add the schema types, ModelDetokenize wrapper, HTTP handler, route registration, RouteFeatureRegistry entry (gated by FeatureTokenize so no new feature flag is needed), and the discovery map entry under ai_functions. - Regenerated swagger reflects the new endpoint and types. - Update authentication.md to list /v1/detokenize alongside /v1/tokenize. Assisted-by: Claude:claude-opus-4-7 Signed-off-by: Adira Denis Muhando <dennisadira@gmail.com> * test(e2e): add mock backend tests for /v1/detokenize Add Detokenize to the mock gRPC backend and wire up two e2e tests in the MockBackend suite: one that posts known token IDs and asserts a non-empty content response, and a round-trip that tokenizes first then detokenizes the returned IDs. Addresses reviewer feedback on #9620. Assisted-by: Claude:claude-sonnet-4-6 Signed-off-by: Adira Denis Muhando <dennisadira@gmail.com> * fix(kokoros): implement detokenize in the Rust backend service The Detokenize RPC added in this PR grows the tonic-generated Backend trait. Unlike the other languages there is nothing to inherit a default from — Rust trait impls must list every method — so backend/rust/kokoros failed to compile: error[E0046]: not all trait items implemented, missing: `detokenize` --> src/service.rs:72:1 72 | impl Backend for KokorosService { Go backends pick up the Unimplemented default from base.Base, and the generated C++/Python servicer bases default to UNIMPLEMENTED, which is why the Rust backend was the only one that broke. kokoros is the sole Rust crate in the tree, so this is the full extent of the fallout. Return Status::unimplemented("Not supported"), matching how this same file already gates tokenize_string and ~20 other unsupported RPCs. Fixes the tests-kokoros and backend-jobs-singlearch-4 (-cpu-kokoros) failures on the previous head. Assisted-by: Claude:claude-opus-5 cargo Signed-off-by: Adira Denis Muhando <dennisadira@gmail.com> --------- Signed-off-by: Adira Denis Muhando <dennisadira@gmail.com> Co-authored-by: localai-org-maint-bot <bot-opensource@localaisrl.com>
98 lines
4.3 KiB
Go
98 lines
4.3 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
|
|
GenerateVideo(*pb.GenerateVideoRequest) error
|
|
Generate3D(*pb.Generate3DRequest) 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
|
|
}
|