Files
Enterprise-Knowledge-Base/internal/application/service/knowledge_post_process.go
T
wizardchen e147209e77 feat: Implement comprehensive wiki feature for knowledge bases
This commit introduces the complete wiki feature for WeKnora, enabling AI-powered wiki page generation and management. The implementation includes:

**Backend Changes:**
- Wiki data model: WikiPage type with support for multiple page types (Summary, Entity, Concept, Index, Log)
- Database schema: wiki_pages table with full migration support
- WikiPageService: CRUD operations and page management
- WikiPageRepository: GORM-based persistence layer
- Wiki ingest pipeline: Automated generation of wiki pages from knowledge documents
  * Summary page generation using LLM
  * Entity and concept extraction in a single LLM call
  * Synthesis opportunity detection
  * Index page rebuilding
  * Log page maintenance
- Wiki boost feature: Enhance chat retrieval with wiki context
- Wiki linting: Maintenance and validation utilities
- Agent wiki tools: Enable agents to query and interact with wiki pages
- Wiki prompts: Comprehensive LLM prompt templates for all wiki generation tasks
- Language support: Reuse existing middleware language infrastructure for LLM prompts

**Frontend Changes:**
- Wiki browser UI: View all wiki pages with filtering and search
- Wiki API client: Knowledge base wiki management endpoints
- Knowledge base editor: Configure wiki settings (language, auto-ingest, synthesis model)
- i18n updates: Support for English, Korean, Russian, and Chinese interfaces

**Configuration:**
- Container DI: Wire up all wiki services
- Router: Register wiki API endpoints
- Task handling: Support async wiki ingest tasks

**Testing:**
- Unit tests for wiki page types
- Service layer tests
- Endpoint tests for wiki operations
- Integration tests with LLM mocking

**Documentation:**
- Language refactoring analysis and guides
- Implementation completion reports
- Quick reference guides for developers

**Key Features:**
✅ LLM-powered wiki page generation from documents
✅ Multi-language support (9+ languages)
✅ Automatic extraction of entities and concepts
✅ Synthesis opportunity detection
✅ Index and log page maintenance
✅ Progressive wiki building across multiple documents
✅ Agent-based wiki interaction
✅ Chat retrieval enhancement with wiki context
✅ Full frontend UI for wiki browsing

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-22 21:17:18 +08:00

188 lines
6.7 KiB
Go

package service
import (
"context"
"encoding/json"
"fmt"
"time"
"github.com/Tencent/WeKnora/internal/logger"
"github.com/Tencent/WeKnora/internal/types"
"github.com/Tencent/WeKnora/internal/types/interfaces"
"github.com/hibiken/asynq"
)
// KnowledgePostProcessService acts as an orchestrator for all post-processing tasks
// after a document has been parsed and split into chunks (including multimodal OCR/Caption).
type KnowledgePostProcessService struct {
knowledgeRepo interfaces.KnowledgeRepository
kbService interfaces.KnowledgeBaseService
chunkService interfaces.ChunkService
taskEnqueuer interfaces.TaskEnqueuer
}
func NewKnowledgePostProcessService(
knowledgeRepo interfaces.KnowledgeRepository,
kbService interfaces.KnowledgeBaseService,
chunkService interfaces.ChunkService,
taskEnqueuer interfaces.TaskEnqueuer,
) interfaces.TaskHandler {
return &KnowledgePostProcessService{
knowledgeRepo: knowledgeRepo,
kbService: kbService,
chunkService: chunkService,
taskEnqueuer: taskEnqueuer,
}
}
// Handle implements asynq handler for TypeKnowledgePostProcess.
func (s *KnowledgePostProcessService) Handle(ctx context.Context, task *asynq.Task) error {
var payload types.KnowledgePostProcessPayload
if err := json.Unmarshal(task.Payload(), &payload); err != nil {
return fmt.Errorf("unmarshal knowledge post process payload: %w", err)
}
logger.Infof(ctx, "[KnowledgePostProcess] Orchestrating post processing for knowledge: %s", payload.KnowledgeID)
ctx = context.WithValue(ctx, types.TenantIDContextKey, payload.TenantID)
if payload.Language != "" {
ctx = context.WithValue(ctx, types.LanguageContextKey, payload.Language)
}
// 1. Fetch Knowledge and KB
knowledge, err := s.knowledgeRepo.GetKnowledgeByIDOnly(ctx, payload.KnowledgeID)
if err != nil {
return fmt.Errorf("get knowledge %s: %w", payload.KnowledgeID, err)
}
if knowledge == nil {
logger.Warnf(ctx, "[KnowledgePostProcess] Knowledge %s not found, aborting.", payload.KnowledgeID)
return nil
}
kb, err := s.kbService.GetKnowledgeBaseByIDOnly(ctx, payload.KnowledgeBaseID)
if err != nil || kb == nil {
return fmt.Errorf("get knowledge base %s: %w", payload.KnowledgeBaseID, err)
}
// 2. Fetch all chunks
chunks, err := s.chunkService.ListChunksByKnowledgeID(ctx, payload.KnowledgeID)
if err != nil {
return fmt.Errorf("list chunks for knowledge %s: %w", payload.KnowledgeID, err)
}
// Gather all text-like chunks (including newly added OCR and Caption from multimodal tasks)
var textChunks []*types.Chunk
for _, c := range chunks {
if c.ChunkType == types.ChunkTypeText || c.ChunkType == types.ChunkTypeImageOCR || c.ChunkType == types.ChunkTypeImageCaption {
textChunks = append(textChunks, c)
}
}
// 3. Update ParseStatus to Completed
// (Except if it's already completed or if it was marked as failed/deleting, but we'll just set it to completed if it's processing)
if knowledge.ParseStatus == types.ParseStatusProcessing {
knowledge.ParseStatus = types.ParseStatusCompleted
knowledge.UpdatedAt = time.Now()
// Setup summary status
if len(textChunks) > 0 {
knowledge.SummaryStatus = types.SummaryStatusPending
} else {
knowledge.SummaryStatus = types.SummaryStatusNone
}
if err := s.knowledgeRepo.UpdateKnowledge(ctx, knowledge); err != nil {
logger.Warnf(ctx, "[KnowledgePostProcess] Failed to update knowledge status to completed: %v", err)
} else {
logger.Infof(ctx, "[KnowledgePostProcess] Knowledge %s marked as completed.", payload.KnowledgeID)
}
}
// 4. Spawn Summary and Question Tasks
if len(textChunks) > 0 {
s.enqueueSummaryGenerationTask(ctx, payload)
s.enqueueQuestionGenerationIfEnabled(ctx, payload, kb)
}
// 5. Spawn Graph RAG Tasks
if kb.ExtractConfig != nil && kb.ExtractConfig.Enabled {
logger.Infof(ctx, "[KnowledgePostProcess] Spawning Graph RAG extract tasks for %d text-like chunks", len(textChunks))
for _, chunk := range textChunks {
err := NewChunkExtractTask(ctx, s.taskEnqueuer, payload.TenantID, chunk.ID, kb.SummaryModelID)
if err != nil {
logger.Errorf(ctx, "[KnowledgePostProcess] Failed to create chunk extract task for %s: %v", chunk.ID, err)
}
}
}
// 6. Spawn Wiki Ingest Task for wiki-type knowledge bases
if kb.Type == types.KnowledgeBaseTypeWiki && len(textChunks) > 0 {
EnqueueWikiIngest(ctx, s.taskEnqueuer, payload.TenantID, payload.KnowledgeBaseID, payload.KnowledgeID)
logger.Infof(ctx, "[KnowledgePostProcess] Enqueued wiki ingest task for %s", payload.KnowledgeID)
}
return nil
}
func (s *KnowledgePostProcessService) enqueueSummaryGenerationTask(ctx context.Context, payload types.KnowledgePostProcessPayload) {
if s.taskEnqueuer == nil {
return
}
taskPayload := types.SummaryGenerationPayload{
TenantID: payload.TenantID,
KnowledgeBaseID: payload.KnowledgeBaseID,
KnowledgeID: payload.KnowledgeID,
Language: payload.Language,
}
payloadBytes, err := json.Marshal(taskPayload)
if err != nil {
logger.Warnf(ctx, "[KnowledgePostProcess] Failed to marshal summary generation payload: %v", err)
return
}
task := asynq.NewTask(types.TypeSummaryGeneration, payloadBytes, asynq.Queue("low"), asynq.MaxRetry(3))
if _, err := s.taskEnqueuer.Enqueue(task); err != nil {
logger.Warnf(ctx, "[KnowledgePostProcess] Failed to enqueue summary generation for %s: %v", payload.KnowledgeID, err)
} else {
logger.Infof(ctx, "[KnowledgePostProcess] Enqueued summary generation task for %s", payload.KnowledgeID)
}
}
func (s *KnowledgePostProcessService) enqueueQuestionGenerationIfEnabled(ctx context.Context, payload types.KnowledgePostProcessPayload, kb *types.KnowledgeBase) {
if s.taskEnqueuer == nil {
return
}
if kb.QuestionGenerationConfig == nil || !kb.QuestionGenerationConfig.Enabled {
return
}
questionCount := kb.QuestionGenerationConfig.QuestionCount
if questionCount <= 0 {
questionCount = 3
}
if questionCount > 10 {
questionCount = 10
}
taskPayload := types.QuestionGenerationPayload{
TenantID: payload.TenantID,
KnowledgeBaseID: payload.KnowledgeBaseID,
KnowledgeID: payload.KnowledgeID,
QuestionCount: questionCount,
Language: payload.Language,
}
payloadBytes, err := json.Marshal(taskPayload)
if err != nil {
logger.Warnf(ctx, "[KnowledgePostProcess] Failed to marshal question generation payload: %v", err)
return
}
task := asynq.NewTask(types.TypeQuestionGeneration, payloadBytes, asynq.Queue("low"), asynq.MaxRetry(3))
if _, err := s.taskEnqueuer.Enqueue(task); err != nil {
logger.Warnf(ctx, "[KnowledgePostProcess] Failed to enqueue question generation for %s: %v", payload.KnowledgeID, err)
} else {
logger.Infof(ctx, "[KnowledgePostProcess] Enqueued question generation task for %s (count=%d)", payload.KnowledgeID, questionCount)
}
}