mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 18:09:05 -04:00
1cd7d63c7b
#10970 gave the four PredictOptions RPCs a model-identity check so a backend reached through a stale distributed route rejects the request instead of answering from whatever model it holds (#10952). Every other modality shares that exposure: the route is cached by host:port, a worker can recycle a stopped backend's port for another model's backend, and a liveness-only probe cannot tell a stale row from a valid one. Extends the same mechanism to the 21 remaining request messages that reach a backend through the router, using the pattern #10970 established rather than a parallel one: - proto: ModelIdentity on each modality request message. - controller: populated from ModelConfig.Model at the call site that also builds ModelOptions, so load-time and request-time values are equal by construction. - backends: one generic guard in pkg/grpc/server.go (27 Go backends), the method set in backend/python/common (36 Python backends), llama-cpp (AudioTranscription/Stream, Rerank, Score) and privacy-filter (TokenClassify). - reconcile already drops the stale row on IsModelMismatch; no change. TTSRequest and SoundGenerationRequest get a SEPARATE ModelIdentity field rather than reusing their existing `model`: FileStagingClient rewrites `model` to a worker-local path, so comparing it would reject valid requests in exactly the configuration this guards. AudioEncode/AudioDecode are deliberately left unguarded: the opus codec backend is loaded from a literal rather than a ModelConfig, so no value carries the equality guarantee the comparison depends on. The four bidirectional stream RPCs are out of scope; they bypass reconcile. Empty means skip on both sides, so an old controller, an old backend, and the bare request structs in tests/e2e-backends all keep working. Assisted-by: Claude Code:claude-opus-4-8 [Read] [Edit] [Bash] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
45 lines
1.2 KiB
Go
45 lines
1.2 KiB
Go
package backend
|
|
|
|
import (
|
|
"context"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/schema"
|
|
"github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
func VAD(request *schema.VADRequest,
|
|
ctx context.Context,
|
|
ml *model.ModelLoader,
|
|
appConfig *config.ApplicationConfig,
|
|
modelConfig config.ModelConfig) (*schema.VADResponse, error) {
|
|
// model.WithContext(ctx) overrides the app-context default set in
|
|
// ModelOptions so distributed routing decisions reach the request's
|
|
// X-LocalAI-Node holder via distributedhdr.Stamp.
|
|
opts := ModelOptions(modelConfig, appConfig, model.WithContext(ctx))
|
|
vadModel, err := ml.Load(opts...)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return nil, err
|
|
}
|
|
|
|
req := proto.VADRequest{
|
|
ModelIdentity: modelConfig.Model,
|
|
Audio: request.Audio,
|
|
}
|
|
resp, err := vadModel.VAD(ctx, &req)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
segments := []schema.VADSegment{}
|
|
for _, s := range resp.Segments {
|
|
segments = append(segments, schema.VADSegment{Start: s.Start, End: s.End})
|
|
}
|
|
|
|
return &schema.VADResponse{
|
|
Segments: segments,
|
|
}, nil
|
|
}
|