Files
LocalAI/core/backend/rerank.go
LocalAI [bot] 06e777b75e feat(distributed): gated X-LocalAI-Node response header (middleware + wrapper) (#9976)
* feat(distributed): add per-request node ID context holder

Introduce pkg/distributedhdr, a leaf package carrying a per-request
*atomic.Value holder for the picked worker node ID from the
SmartRouter (core/services/nodes) up to the HTTP response writer
wrapper (core/http/middleware). Avoids the import cycle that a shared
key in either consumer would create.

Exposes NewHolder, WithHolder, Holder, Stamp, Load, Inherit. The
holder is atomic.Value so cross-goroutine publish from the router to
the response writer wrapper is race-clean.

Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(distributed): add ExposeNodeHeader middleware + response writer wrapper

New ApplicationConfig.ExposeNodeHeader bool + --expose-node-header CLI
flag / LOCALAI_EXPOSE_NODE_HEADER env var (default off; the node ID
reveals internal topology and is opt-in).

The middleware creates a per-request *atomic.Value holder, attaches it
to c.Request().Context() via distributedhdr.WithHolder, and wraps
c.Response().Writer with a custom http.ResponseWriter that sets the
X-LocalAI-Node header on first Write / WriteHeader / Flush by reading
the holder. Implements http.Flusher, http.Hijacker, Unwrap so it
composes cleanly with Echo and http.NewResponseController.

request.go propagates the holder onto derived contexts via
distributedhdr.Inherit so the holder survives the correlation-ID
context replacement.

Unit + race-clean concurrency + integration specs.

Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(distributed): stamp node ID in router and wire middleware to inference routes

ModelRouterAdapter.Route stamps the picked node ID into the
per-request holder via distributedhdr.Stamp(ctx, result.Node.ID) right
after replica selection.

Wire ExposeNodeHeader middleware to:
- OpenAI chat/completion/embeddings + audio transcriptions/speech + image generations/inpainting
- Anthropic /v1/messages
- Ollama /api/chat, /api/generate, /api/embed, /api/embeddings
- Jina /v1/rerank
- LocalAI /v1/vad

The middleware's wrapper reads the holder on first byte and sets the
X-LocalAI-Node response header before delegating to the underlying
writer. Per-request scope means no race under concurrent multi-replica
routing.

Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(distributed): thread request context through backend Load + cover ctx propagation

Five non-OpenAI backend helpers were silently using app.Context instead
of the request context for the gRPC backend call: transcription, TTS,
image generation, rerank, VAD. Effect: distributedhdr.Stamp in the
router callback was a silent no-op for these paths, AND client
cancellation didn't propagate to in-flight inference.

Thread c.Request().Context() (or the equivalent input.Context after
the request middleware has installed the correlation-ID derived
context) through each helper and into ModelOptions via
model.WithContext(ctx). ImageGeneration's signature gains a leading
ctx parameter; in-tree callers (openai image, openai inpainting,
openai inpainting_test) are updated to match.

ModelEmbedding gains a leading ctx parameter for the same reason; the
openai and ollama embedding handlers pass the request context through.

chat_stream_workers.go defers the initial role=assistant chunk
emission until the first token callback so the wrapper's lazy
X-LocalAI-Node lookup against the loader runs AFTER ml.Load has
stamped the per-modelID node ID; semantically identical for clients
(role still arrives before any text).

Regression test core/backend/ctx_propagation_test.go pins ctx
propagation for all five helpers.

Docs updated to enumerate the full endpoint coverage of the
--expose-node-header flag.

Assisted-by: Claude:claude-opus-4-7[1m]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-05-25 10:51:48 +02:00

106 lines
3.3 KiB
Go

package backend
import (
"context"
"fmt"
"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"
)
// RerankResult is the per-document score returned to consumers,
// narrowed from proto.RerankResult so callers don't need to depend on
// the proto package.
type RerankResult struct {
Index int
RelevanceScore float32
}
// Reranker scores a list of candidate documents against a query.
// Returns one RerankResult per input document (no top-N truncation -
// callers that need it can sort and slice).
type Reranker interface {
Rerank(ctx context.Context, query string, documents []string) ([]RerankResult, error)
}
// NewReranker binds (loader, modelConfig, appConfig) into a Reranker.
func NewReranker(loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig) Reranker {
return &modelReranker{loader: loader, modelConfig: modelConfig, appConfig: appConfig}
}
type modelReranker struct {
loader *model.ModelLoader
modelConfig config.ModelConfig
appConfig *config.ApplicationConfig
}
func (r *modelReranker) Rerank(ctx context.Context, query string, documents []string) ([]RerankResult, error) {
req := &proto.RerankRequest{
Query: query,
Documents: documents,
// TopN=0: backend returns scores for every document. Truncating
// here would silently zero out labels the reranker considered
// unlikely, which the router classifier needs.
}
res, err := Rerank(ctx, req, r.loader, r.appConfig, r.modelConfig)
if err != nil {
return nil, err
}
out := make([]RerankResult, 0, len(res.GetResults()))
for _, dr := range res.GetResults() {
out = append(out, RerankResult{Index: int(dr.GetIndex()), RelevanceScore: dr.GetRelevanceScore()})
}
return out, nil
}
func Rerank(ctx context.Context, request *proto.RerankRequest, loader *model.ModelLoader, appConfig *config.ApplicationConfig, modelConfig config.ModelConfig) (*proto.RerankResult, 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))
rerankModel, err := loader.Load(opts...)
if err != nil {
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
return nil, err
}
if rerankModel == nil {
return nil, fmt.Errorf("could not load rerank model")
}
var startTime time.Time
if appConfig.EnableTracing {
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
startTime = time.Now()
}
res, err := rerankModel.Rerank(ctx, request)
if appConfig.EnableTracing {
errStr := ""
if err != nil {
errStr = err.Error()
}
trace.RecordBackendTrace(trace.BackendTrace{
Timestamp: startTime,
Duration: time.Since(startTime),
Type: trace.BackendTraceRerank,
ModelName: modelConfig.Name,
Backend: modelConfig.Backend,
Summary: trace.TruncateString(request.Query, 200),
Error: errStr,
Data: map[string]any{
"query": request.Query,
"documents_count": len(request.Documents),
"top_n": request.TopN,
},
})
}
return res, err
}