mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 18:09:05 -04:00
#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>
112 lines
3.1 KiB
Go
112 lines
3.1 KiB
Go
package backend
|
|
|
|
import (
|
|
"maps"
|
|
"time"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/trace"
|
|
"github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
model "github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
// VideoGenerationOptions is the backend-neutral request passed to video generators.
|
|
// Media fields contain staged local paths by the time they reach this layer.
|
|
type VideoGenerationOptions struct {
|
|
Height int32
|
|
Width int32
|
|
Prompt string
|
|
NegativePrompt string
|
|
StartImage string
|
|
EndImage string
|
|
Audio string
|
|
Destination string
|
|
NumFrames int32
|
|
FPS int32
|
|
Seed int32
|
|
CFGScale float32
|
|
Step int32
|
|
Params map[string]string
|
|
}
|
|
|
|
func VideoGeneration(options VideoGenerationOptions, loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig) (func() error, error) {
|
|
opts := ModelOptions(modelConfig, appConfig)
|
|
inferenceModel, err := loader.Load(opts...)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return nil, err
|
|
}
|
|
|
|
fn := func() error {
|
|
_, err := inferenceModel.GenerateVideo(
|
|
appConfig.Context,
|
|
&proto.GenerateVideoRequest{
|
|
// See the ModelIdentity note in image.go: this is the value
|
|
// ModelOptions passed to LoadModel a few lines above.
|
|
ModelIdentity: modelConfig.Model,
|
|
Height: options.Height,
|
|
Width: options.Width,
|
|
Prompt: options.Prompt,
|
|
NegativePrompt: options.NegativePrompt,
|
|
StartImage: options.StartImage,
|
|
EndImage: options.EndImage,
|
|
Audio: options.Audio,
|
|
NumFrames: options.NumFrames,
|
|
Fps: options.FPS,
|
|
Seed: options.Seed,
|
|
CfgScale: options.CFGScale,
|
|
Step: options.Step,
|
|
Dst: options.Destination,
|
|
Params: maps.Clone(options.Params),
|
|
},
|
|
)
|
|
return err
|
|
}
|
|
|
|
if appConfig.EnableTracing {
|
|
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
|
|
|
|
traceData := map[string]any{
|
|
"prompt": options.Prompt,
|
|
"negative_prompt": options.NegativePrompt,
|
|
"height": options.Height,
|
|
"width": options.Width,
|
|
"num_frames": options.NumFrames,
|
|
"fps": options.FPS,
|
|
"seed": options.Seed,
|
|
"cfg_scale": options.CFGScale,
|
|
"step": options.Step,
|
|
"has_start_image": options.StartImage != "",
|
|
"has_end_image": options.EndImage != "",
|
|
"has_audio": options.Audio != "",
|
|
}
|
|
|
|
startTime := time.Now()
|
|
originalFn := fn
|
|
fn = func() error {
|
|
err := originalFn()
|
|
duration := time.Since(startTime)
|
|
|
|
errStr := ""
|
|
if err != nil {
|
|
errStr = err.Error()
|
|
}
|
|
|
|
trace.RecordBackendTrace(trace.BackendTrace{
|
|
Timestamp: startTime,
|
|
Duration: duration,
|
|
Type: trace.BackendTraceVideoGeneration,
|
|
ModelName: modelConfig.Name,
|
|
Backend: modelConfig.Backend,
|
|
Summary: trace.TruncateString(options.Prompt, 200),
|
|
Error: errStr,
|
|
Data: traceData,
|
|
})
|
|
|
|
return err
|
|
}
|
|
}
|
|
|
|
return fn, nil
|
|
}
|