Tencent/WeKnora · error

summary model is required for question generation

Error message

summary model is required for question generation

What it means

Configuration guard in RegenerateChunkQuestions: the chunk's knowledge base has no SummaryModelID set, so there is no LLM to generate questions with. Per-KB configuration is incomplete; nothing to retry.

Source

Thrown at internal/application/service/knowledge_process.go:2192

	tenantID := types.MustTenantIDFromContext(ctx)
	chunk, err := s.chunkRepo.GetChunkByID(ctx, tenantID, chunkID)
	if err != nil {
		return nil, err
	}
	if chunk.ChunkType != types.ChunkTypeText {
		return nil, fmt.Errorf("questions can only be generated for text chunks")
	}
	generationRevision := chunk.ContentRevision
	knowledge, err := s.repo.GetKnowledgeByID(ctx, tenantID, chunk.KnowledgeID)
	if err != nil {
		return nil, err
	}
	kb, err := s.kbService.GetKnowledgeBaseByID(ctx, chunk.KnowledgeBaseID)
	if err != nil {
		return nil, err
	}
	if kb.SummaryModelID == "" {
		return nil, fmt.Errorf("summary model is required for question generation")
	}
	chatModel, err := s.modelService.GetChatModel(ctx, kb.SummaryModelID)
	if err != nil {
		return nil, err
	}
	resolveNeighbor := func(id string) string {
		if id == "" {
			return ""
		}
		neighbor, getErr := s.chunkRepo.GetChunkByID(ctx, tenantID, id)
		if getErr != nil {
			return ""
		}
		return neighbor.Content
	}
	overrides, _ := knowledge.ProcessOverrides()
	config := ResolveProcessConfig(kb, overrides).QuestionGenerationConfig
	count := config.QuestionCount

View on GitHub (pinned to 988cbb0330)

Solutions

1. Configure a summary/chat model on the knowledge base
2. Retry chunk question regeneration afterwards
3. Add KB-level validation before exposing question regeneration

When it happens

Trigger: Thrown at internal/application/service/knowledge_process.go:2192 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of Tencent/WeKnora@988cbb0330 (2026-09-02). Data as JSON: /api/errors/3b3782aed36adb2e. Report an issue: GitHub.