Files
LocalAI/pkg/grpc/base/base.go
Richard Palethorpe 6a80e23733 feat(middleware): Model routing, PII filtering, Cloud model proxies (#9802)
Add a routing middleware stack and a cloud-proxy backend.

* cloud-proxy: a Go gRPC backend that forwards OpenAI- and
  Anthropic-shaped chat requests to upstream providers, with an
  optional translate mode (OpenAI request -> Anthropic /v1/messages
  -> OpenAI response) and full tool-calling support.

* routing: admission control, content-aware model routing
  (embedding cache + classifier + rerank + Arch-Router score),
  PII detection/redaction (regex + NER) with streaming filter and
  OpenAI/Anthropic adapters, and a per-user/per-key billing recorder
  backed by GORM or in-memory storage.

* middleware: UsageMiddleware records usage via the billing recorder,
  plus admission, route-model, usage-stamp and trace middlewares.

* observability: BackendTrace ring buffer stores full request bodies
  (capped), MITM proxy emits structured trace events, and router
  classifier decisions surface at /api/router/decide.

* gallery: Arch-Router-1.5B (Q4_K_M and Q8_0).

* UI: cloud-proxy model-editor fields, classifier system-prompt and
  score-normalization config, and a Traces page rendering request
  bodies.

Assisted-by: claude-code:claude-opus-4-7 [Read] [Edit] [Bash]

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2026-05-25 09:28:27 +02:00

224 lines
6.5 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"
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) 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) 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) TokenizeString(opts *pb.PredictOptions) (pb.TokenizationResponse, error) {
return pb.TokenizationResponse{}, 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) 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
}