mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-31 10:28:43 -04:00
* 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>
246 lines
7.3 KiB
Go
246 lines
7.3 KiB
Go
package base
|
|
|
|
// This is a wrapper to satisfy the GRPC service interface
|
|
// It is meant to be used by the main executable that is the server for the specific backend type (falcon, gpt3, etc)
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os"
|
|
|
|
"github.com/mudler/LocalAI/pkg/grpc/grpcerrors"
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
gopsutil "github.com/shirou/gopsutil/v3/process"
|
|
)
|
|
|
|
// Base is a base class for all backends to implement
|
|
// Note: the backends that does not support multiple requests
|
|
// should use SingleThread instead
|
|
type Base struct {
|
|
}
|
|
|
|
func (llm *Base) Locking() bool {
|
|
return false
|
|
}
|
|
|
|
func (llm *Base) Lock() {
|
|
panic("not implemented")
|
|
}
|
|
|
|
func (llm *Base) Unlock() {
|
|
panic("not implemented")
|
|
}
|
|
|
|
func (llm *Base) Busy() bool {
|
|
return false
|
|
}
|
|
|
|
func (llm *Base) Load(opts *pb.ModelOptions) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Predict(opts *pb.PredictOptions) (string, error) {
|
|
return "", fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) PredictStream(opts *pb.PredictOptions, results chan string) error {
|
|
close(results)
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Embeddings(opts *pb.PredictOptions) ([]float32, error) {
|
|
return []float32{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) GenerateImage(*pb.GenerateImageRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) GenerateVideo(*pb.GenerateVideoRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Generate3D(*pb.Generate3DRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioTranscription(context.Context, *pb.TranscriptRequest) (pb.TranscriptResult, error) {
|
|
return pb.TranscriptResult{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioTranscriptionStream(context.Context, *pb.TranscriptRequest, chan *pb.TranscriptStreamResponse) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) TTS(*pb.TTSRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) TTSStream(*pb.TTSRequest, chan []byte) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) SoundGeneration(*pb.SoundGenerationRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Detect(*pb.DetectOptions) (pb.DetectResponse, error) {
|
|
return pb.DetectResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Depth(*pb.DepthRequest) (pb.DepthResponse, error) {
|
|
return pb.DepthResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) FaceVerify(*pb.FaceVerifyRequest) (pb.FaceVerifyResponse, error) {
|
|
return pb.FaceVerifyResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) FaceAnalyze(*pb.FaceAnalyzeRequest) (pb.FaceAnalyzeResponse, error) {
|
|
return pb.FaceAnalyzeResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) VoiceVerify(*pb.VoiceVerifyRequest) (pb.VoiceVerifyResponse, error) {
|
|
return pb.VoiceVerifyResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) VoiceAnalyze(*pb.VoiceAnalyzeRequest) (pb.VoiceAnalyzeResponse, error) {
|
|
return pb.VoiceAnalyzeResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) VoiceEmbed(*pb.VoiceEmbedRequest) (pb.VoiceEmbedResponse, error) {
|
|
return pb.VoiceEmbedResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Diarize(*pb.DiarizeRequest) (pb.DiarizeResponse, error) {
|
|
return pb.DiarizeResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) SoundDetection(context.Context, *pb.SoundDetectionRequest) (*pb.SoundDetectionResponse, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) TokenizeString(opts *pb.PredictOptions) (pb.TokenizationResponse, error) {
|
|
return pb.TokenizationResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Detokenize(req *pb.DetokenizeRequest) (pb.DetokenizeResponse, error) {
|
|
return pb.DetokenizeResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) ModelMetadata(opts *pb.ModelOptions) (*pb.ModelMetadataResponse, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
// backends may wish to call this to capture the gopsutil info, then enhance with additional memory usage details?
|
|
func (llm *Base) Status() (pb.StatusResponse, error) {
|
|
return pb.StatusResponse{
|
|
Memory: memoryUsage(),
|
|
}, nil
|
|
}
|
|
|
|
func (llm *Base) StoresSet(*pb.StoresSetOptions) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StoresGet(*pb.StoresGetOptions) (pb.StoresGetResult, error) {
|
|
return pb.StoresGetResult{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StoresDelete(*pb.StoresDeleteOptions) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StoresFind(*pb.StoresFindOptions) (pb.StoresFindResult, error) {
|
|
return pb.StoresFindResult{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) VAD(*pb.VADRequest) (pb.VADResponse, error) {
|
|
return pb.VADResponse{}, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioEncode(*pb.AudioEncodeRequest) (*pb.AudioEncodeResult, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioDecode(*pb.AudioDecodeRequest) (*pb.AudioDecodeResult, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioTransform(*pb.AudioTransformRequest) (*pb.AudioTransformResult, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioTransformStream(in <-chan *pb.AudioTransformFrameRequest, out chan<- *pb.AudioTransformFrameResponse) error {
|
|
close(out)
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) AudioTranscriptionLive(in <-chan *pb.TranscriptLiveRequest, out chan<- *pb.TranscriptLiveResponse) error {
|
|
close(out)
|
|
return grpcerrors.LiveTranscriptionUnsupported("base", "not implemented by this backend")
|
|
}
|
|
|
|
func (llm *Base) AudioToAudioStream(in <-chan *pb.AudioToAudioRequest, out chan<- *pb.AudioToAudioResponse) error {
|
|
close(out)
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) Forward(ctx context.Context, in <-chan *pb.ForwardRequest, out chan<- *pb.ForwardReply) error {
|
|
close(out)
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StartFineTune(*pb.FineTuneRequest) (*pb.FineTuneJobResult, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) FineTuneProgress(*pb.FineTuneProgressRequest, chan *pb.FineTuneProgressUpdate) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StopFineTune(*pb.FineTuneStopRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) ListCheckpoints(*pb.ListCheckpointsRequest) (*pb.ListCheckpointsResponse, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) ExportModel(*pb.ExportModelRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StartQuantization(*pb.QuantizationRequest) (*pb.QuantizationJobResult, error) {
|
|
return nil, fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) QuantizationProgress(*pb.QuantizationProgressRequest, chan *pb.QuantizationProgressUpdate) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func (llm *Base) StopQuantization(*pb.QuantizationStopRequest) error {
|
|
return fmt.Errorf("unimplemented")
|
|
}
|
|
|
|
func memoryUsage() *pb.MemoryUsageData {
|
|
mud := pb.MemoryUsageData{
|
|
Breakdown: make(map[string]uint64),
|
|
}
|
|
|
|
pid := int32(os.Getpid())
|
|
|
|
backendProcess, err := gopsutil.NewProcess(pid)
|
|
|
|
if err == nil {
|
|
memInfo, err := backendProcess.MemoryInfo()
|
|
if err == nil {
|
|
mud.Total = memInfo.VMS // TEST, but rss seems reasonable first guess. Does include swap, but we might care about that.
|
|
mud.Breakdown["gopsutil-RSS"] = memInfo.RSS
|
|
}
|
|
}
|
|
return &mud
|
|
}
|
|
func (llm *Base) Free() error {
|
|
return nil
|
|
}
|