Files
Enterprise-Knowledge-Base/internal/router/sync_task.go
T
wizardchen a1a07e6818 Refactor knowledge post-processing into orchestrator task
Introduce KnowledgePostProcess task to decouple image multimodal
processing from downstream operations like summary, question
generation, and knowledge graph extraction.

This allows unifying the processing logic across documents and
images and ensures all text content, including from images,
is properly extracted before post-processing.
2026-04-16 18:13:20 +08:00

105 lines
4.2 KiB
Go

package router
import (
"context"
"fmt"
"sync"
"time"
"github.com/Tencent/WeKnora/internal/logger"
"github.com/Tencent/WeKnora/internal/types"
"github.com/Tencent/WeKnora/internal/types/interfaces"
"github.com/google/uuid"
"github.com/hibiken/asynq"
"go.uber.org/dig"
)
// SyncTaskExecutor executes tasks synchronously (in a goroutine) without Redis.
// Used in Lite mode as a drop-in replacement for *asynq.Client.
type SyncTaskExecutor struct {
mu sync.RWMutex
handlers map[string]func(context.Context, *asynq.Task) error
}
func NewSyncTaskExecutor() *SyncTaskExecutor {
return &SyncTaskExecutor{
handlers: make(map[string]func(context.Context, *asynq.Task) error),
}
}
// RegisterHandler registers a handler for a given task type pattern.
func (e *SyncTaskExecutor) RegisterHandler(pattern string, handler func(context.Context, *asynq.Task) error) {
e.mu.Lock()
defer e.mu.Unlock()
e.handlers[pattern] = handler
}
// Enqueue satisfies interfaces.TaskEnqueuer.
// Instead of queuing to Redis, it dispatches the task to a goroutine.
func (e *SyncTaskExecutor) Enqueue(task *asynq.Task, _ ...asynq.Option) (*asynq.TaskInfo, error) {
e.mu.RLock()
handler, ok := e.handlers[task.Type()]
e.mu.RUnlock()
if !ok {
return nil, fmt.Errorf("sync task executor: no handler registered for type %q", task.Type())
}
taskID := uuid.New().String()
info := &asynq.TaskInfo{
ID: taskID,
Queue: "sync",
Type: task.Type(),
}
go func() {
ctx := context.Background()
start := time.Now()
logger.Infof(ctx, "[SyncTask] Executing task type=%s id=%s", task.Type(), taskID)
if err := handler(ctx, task); err != nil {
logger.Errorf(ctx, "[SyncTask] Task failed type=%s id=%s elapsed=%v err=%v",
task.Type(), taskID, time.Since(start), err)
} else {
logger.Infof(ctx, "[SyncTask] Task completed type=%s id=%s elapsed=%v",
task.Type(), taskID, time.Since(start))
}
}()
return info, nil
}
type SyncTaskParams struct {
dig.In
Executor *SyncTaskExecutor
KnowledgeService interfaces.KnowledgeService
KnowledgeBaseService interfaces.KnowledgeBaseService
TagService interfaces.KnowledgeTagService
DataSourceService interfaces.DataSourceService
ChunkExtractor interfaces.TaskHandler `name:"chunkExtractor"`
DataTableSummary interfaces.TaskHandler `name:"dataTableSummary"`
ImageMultimodal interfaces.TaskHandler `name:"imageMultimodal"`
KnowledgePostProcess interfaces.TaskHandler `name:"knowledgePostProcess"`
}
// RegisterSyncHandlers registers all task handlers on the SyncTaskExecutor.
// Used in Lite mode instead of RunAsynqServer.
func RegisterSyncHandlers(params SyncTaskParams) {
params.Executor.RegisterHandler(types.TypeChunkExtract, params.ChunkExtractor.Handle)
params.Executor.RegisterHandler(types.TypeDataTableSummary, params.DataTableSummary.Handle)
params.Executor.RegisterHandler(types.TypeDocumentProcess, params.KnowledgeService.ProcessDocument)
params.Executor.RegisterHandler(types.TypeManualProcess, params.KnowledgeService.ProcessManualUpdate)
params.Executor.RegisterHandler(types.TypeFAQImport, params.KnowledgeService.ProcessFAQImport)
params.Executor.RegisterHandler(types.TypeQuestionGeneration, params.KnowledgeService.ProcessQuestionGeneration)
params.Executor.RegisterHandler(types.TypeSummaryGeneration, params.KnowledgeService.ProcessSummaryGeneration)
params.Executor.RegisterHandler(types.TypeKBClone, params.KnowledgeService.ProcessKBClone)
params.Executor.RegisterHandler(types.TypeKnowledgeMove, params.KnowledgeService.ProcessKnowledgeMove)
params.Executor.RegisterHandler(types.TypeKnowledgeListDelete, params.KnowledgeService.ProcessKnowledgeListDelete)
params.Executor.RegisterHandler(types.TypeIndexDelete, params.TagService.ProcessIndexDelete)
params.Executor.RegisterHandler(types.TypeKBDelete, params.KnowledgeBaseService.ProcessKBDelete)
params.Executor.RegisterHandler(types.TypeImageMultimodal, params.ImageMultimodal.Handle)
params.Executor.RegisterHandler(types.TypeKnowledgePostProcess, params.KnowledgePostProcess.Handle)
params.Executor.RegisterHandler(types.TypeDataSourceSync, params.DataSourceService.ProcessSync)
logger.Infof(context.Background(), "[SyncTask] All task handlers registered (Lite mode, no Redis)")
}