Files
LocalAI/core/backend/stores.go
Richard Palethorpe 085fc53bbc fix(router): production-ready request router + auto-size batch for embedding/rerank (#10104)
* fix(router): score classifier production-readiness

Conversation trimming runs through the classifier model's chat template
and trims by exact token count, sized to the model's n_batch which is
now scaled to context so long probes can't crash the backend. Missing
chat_message templates are a hard error at router build time. Router-
facing factories (Embedder/Scorer/Reranker/TokenCounter) re-resolve
ModelConfig per call so a model installed post-startup doesn't bind a
stub Backend="" config and silently fall into the loader's auto-
iterate path.

New 'vector_store' backend trace recorded inside localVectorStore on
every Search/Insert — including the backend-load-failure path that
previously vanished into an xlog.Warn — with outcome tagging
(hit/miss/empty_store/backend_load_error/find_error/insert_error/ok).
Companion cleanup drops misleading similarity:0 and input_tokens_count:0
from non-hit and text-mode traces.

Gallery local-store-development aliases to 'local-store' so the master
image satisfies pkg/model.LocalStoreBackend lookups from the embedding
cache.

Misc: llama-cpp TokenizeString reads the correct 'prompt' JSON key
(the original bug); ModelTokenize nil-guard; non-fatal mitm proxy
startup; PII 'route_local' renamed to 'allow' with docs/UI in sync;
model-editor footer no longer eats the edit area on small screens;
several config-editor template/dropdown/section fixes.

Tests: e2e router specs (casual/code-hint + long-conversation trim),
vector_store trace specs, lazy-factory specs, gallery dev-alias
resolution, Playwright trace badge + scroll regression.

Assisted-by: Claude:claude-opus-4-7 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>

* feat(backend): auto-size batch to context for embedding and rerank models

Embedding and rerank models pool over the whole input in a single physical batch (n_ubatch). With batch left at the 512 default, the backend rejects longer inputs with "input is too large to process", silently capping a large-context embedder (e.g. 8k/32k) at 512 tokens. Size n_batch to the context for these single-pass usecases, mirroring the existing FLAG_SCORE behaviour; an explicit batch: still wins.

Extracts EffectiveContextSize/EffectiveBatchSize from grpcModelOpts so the effective decode window has one home for other callers to reuse.

Adds an e2e-aio regression test that embeds a >512-token input. The AIO embedding model is switched to nomic-embed-text-v1.5 (2048 context) because the previous granite model was capped at 512 tokens and could not exercise the larger batch.

Assisted-by: claude-code:claude-opus-4-8 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>

* fix(gallery): raise arch-router scoring output cap via parallel:64

Scoring decodes the whole prompt+candidate in a single llama_decode and
reads one logit row per candidate token. The vendored llama.cpp server
caps causal output rows at n_parallel, so the default of 1 aborts with
GGML_ASSERT(n_outputs_max <= cparams.n_outputs_max) on multi-token route
labels. Set options: [parallel:64] on both arch-router quant entries to
lift the cap; kv_unified (the grpc-server default) keeps the full context
per sequence, so this does not split the KV cache.

Assisted-by: claude-code:claude-opus-4-8 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2026-06-12 16:21:15 +02:00

144 lines
4.7 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"
"github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/LocalAI/pkg/store"
)
// VectorStore is the narrowed KNN store used by the router's embedding
// cache. Search returns the top-1 match (cosine similarity in [-1, 1])
// and the serialised payload, or ok=false on a clean miss.
type VectorStore interface {
Search(ctx context.Context, vec []float32) (similarity float64, payload []byte, ok bool, err error)
Insert(ctx context.Context, vec []float32, payload []byte) error
}
// NewVectorStore returns a VectorStore backed by the local-store
// gRPC backend, namespaced by storeName so two routers don't collide.
func NewVectorStore(loader *model.ModelLoader, appConfig *config.ApplicationConfig, storeName string) VectorStore {
if storeName == "" {
return nil
}
return &localVectorStore{loader: loader, appConfig: appConfig, storeName: storeName}
}
type localVectorStore struct {
loader *model.ModelLoader
appConfig *config.ApplicationConfig
storeName string
}
func (s *localVectorStore) backend(_ context.Context) (grpc.Backend, error) {
return StoreBackend(s.loader, s.appConfig, s.storeName, "")
}
func (s *localVectorStore) Search(ctx context.Context, vec []float32) (sim float64, payload []byte, ok bool, err error) {
start := time.Now()
outcome := "hit"
defer func() {
s.recordTrace(start, "search", len(vec), sim, outcome, err)
}()
be, berr := s.backend(ctx)
if berr != nil {
outcome = "backend_load_error"
return 0, nil, false, fmt.Errorf("vector store load: %w", berr)
}
_, values, similarities, ferr := store.Find(ctx, be, vec, 1)
if ferr != nil {
outcome = "find_error"
return 0, nil, false, fmt.Errorf("vector store find: %w", ferr)
}
if len(values) == 0 || len(similarities) == 0 {
outcome = "miss"
return 0, nil, false, nil
}
return float64(similarities[0]), values[0], true, nil
}
func (s *localVectorStore) Insert(ctx context.Context, vec []float32, payload []byte) (err error) {
start := time.Now()
outcome := "ok"
defer func() {
s.recordTrace(start, "insert", len(vec), 0, outcome, err)
}()
be, berr := s.backend(ctx)
if berr != nil {
outcome = "backend_load_error"
return fmt.Errorf("vector store load: %w", berr)
}
if serr := store.SetSingle(ctx, be, vec, payload); serr != nil {
outcome = "insert_error"
return serr
}
return nil
}
// recordTrace surfaces vector-store calls in /api/backend-traces, including
// the backend-load-failure path that otherwise vanishes into an xlog.Warn.
// modelName uses the store namespace (e.g. "router-cache-smart-router") so
// admins can tell which router's cache misbehaved; the backend is always
// "local-store" and can't disambiguate.
func (s *localVectorStore) recordTrace(start time.Time, op string, vecDim int, sim float64, outcome string, err error) {
if s.appConfig == nil || !s.appConfig.EnableTracing {
return
}
trace.InitBackendTracingIfEnabled(s.appConfig.TracingMaxItems, s.appConfig.TracingMaxBodyBytes)
errStr := ""
if err != nil {
errStr = err.Error()
}
summary := op + " " + outcome
if op == "search" && outcome == "hit" {
summary = fmt.Sprintf("search hit (sim=%.3f)", sim)
}
data := map[string]any{
"op": op,
"outcome": outcome,
"vector_dim": vecDim,
}
// Only include similarity for a real neighbor — miss/empty_store would
// otherwise render "similarity: 0" and read as a measured value.
if op == "search" && outcome == "hit" {
data["similarity"] = sim
}
trace.RecordBackendTrace(trace.BackendTrace{
Timestamp: start,
Duration: time.Since(start),
Type: trace.BackendTraceVectorStore,
ModelName: s.storeName,
Backend: model.LocalStoreBackend,
Summary: summary,
Error: errStr,
Data: data,
})
}
func StoreBackend(sl *model.ModelLoader, appConfig *config.ApplicationConfig, storeName string, backend string) (grpc.Backend, error) {
if backend == "" {
backend = model.LocalStoreBackend
}
// ModelLoader caches backend processes by `modelID`, not by the `model`
// passed via WithModel. Without a distinct modelID, every StoreBackend
// call collapses to the same `modelID=""` cache slot — face (512-D) and
// voice (192-D) biometrics would then share the same local-store process
// and the second enrollment would fail with
// Try to add key with length N when existing length is M
// Use the store namespace as modelID so each namespace gets its own
// process instance and its own in-memory Store{}.
sc := []model.Option{
model.WithBackendString(backend),
model.WithModelID(storeName),
model.WithModel(storeName),
}
return sl.Load(sc...)
}