mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-25 07:34:58 -04:00
Ettore Di Giacinto
644481fffb
Replace the model-specific SystemOne gRPC approach with a generic Score RPC extension. The pre-existing Score RPC (previously unused by any backend) now carries question_type and response_json fields: - question_type="systemone" routes kev/laya decision-pipeline requests through the unified vllm_decide C ABI (v29), returning the full response JSON in response_json. - question_type empty routes cua-s1-forms candidate scoring through the same vllm_decide ABI, returning CandidateScore probabilities. The vllm-cpp backend's Score() method calls vllm_decide and dispatches by architecture internally. The /v1/systemone HTTP endpoint checks whether the model's backend supports Score; if so, it forwards the raw request JSON and returns the backend response as-is. Other backends fall through to the existing NER-based path. This mirrors the vllm.cpp C ABI refactor (PR #3301) that replaced vllm_systemone + vllm_score with a single vllm_decide function. The purego bindings bump abiVersion from 27 to 29 and resolve vllm_decide and vllm_decide_free symbols. Also fixes validModelPath to accept cua-s1-forms.json and rl_agent_config.json alongside config.json, matching the engine's model_loader.cpp config-filename ordering. AI-Assisted: true Assisted-by: Maki:regolo/glm5.2 [maki] Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
77 lines
2.4 KiB
Go
77 lines
2.4 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"
|
|
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
model "github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
// ModelSystemOne loads the backend for modelConfig and returns a closure
|
|
// that runs the kev/laya decision pipeline via the Score gRPC RPC with
|
|
// question_type set to "systemone". requestJSON is the raw /v1/systemone
|
|
// POST body; the closure returns the full response JSON from the backend.
|
|
func ModelSystemOne(requestJSON string, loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig) (func(ctx context.Context) (string, error), error) {
|
|
modelOpts := ModelOptions(modelConfig, appConfig)
|
|
inferenceModel, err := loader.Load(modelOpts...)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return nil, err
|
|
}
|
|
b, ok := inferenceModel.(grpc.Backend)
|
|
if !ok {
|
|
return nil, fmt.Errorf("systemone not supported by backend %q", modelConfig.Backend)
|
|
}
|
|
return func(ctx context.Context) (string, error) {
|
|
release, err := AcquireGlobalBackendSlot()
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
defer release()
|
|
var startTime time.Time
|
|
var traceID string
|
|
if appConfig.EnableTracing {
|
|
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
|
|
startTime = time.Now()
|
|
traceID = trace.BeginBackendTrace(trace.BackendTrace{
|
|
Timestamp: startTime,
|
|
Type: trace.BackendTraceScore,
|
|
ModelName: modelConfig.Name,
|
|
Backend: modelConfig.Backend,
|
|
Summary: trace.TruncateString(requestJSON, 200),
|
|
})
|
|
}
|
|
defer trace.CancelBackendTrace(traceID)
|
|
resp, err := b.Score(ctx, &pb.ScoreRequest{
|
|
Prompt: requestJSON,
|
|
QuestionType: "systemone",
|
|
ModelIdentity: modelConfig.Model,
|
|
})
|
|
if appConfig.EnableTracing {
|
|
errStr := ""
|
|
if err != nil {
|
|
errStr = err.Error()
|
|
}
|
|
trace.RecordBackendTrace(trace.BackendTrace{
|
|
ID: traceID,
|
|
Timestamp: startTime,
|
|
Duration: time.Since(startTime),
|
|
Type: trace.BackendTraceScore,
|
|
ModelName: modelConfig.Name,
|
|
Backend: modelConfig.Backend,
|
|
Summary: trace.TruncateString(requestJSON, 200),
|
|
Error: errStr,
|
|
})
|
|
}
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
return resp.GetResponseJson(), nil
|
|
}, nil
|
|
}
|