fix(pipeline): make data-analysis stage opt-in per agent (#1244)

The legacy in-pipeline DuckDB SQL data-analysis stage used to run on every
quick-answer RAG request whose retrieved chunks included a CSV/Excel file,
adding one extra LLM round-trip (~3s) to generate a SQL query that most
plain Q&A users never wanted. There was no way to disable it.

Introduce a per-agent DataAnalysisEnabled flag (default off), wire it
through PipelineRequest, and gate the DATA_ANALYSIS stage on it. Surface
the toggle in the agent editor for quick-answer agents with at least one
knowledge base attached.

Refs: https://github.com/Tencent/WeKnora/issues/1244
This commit is contained in:
wizardchen
2026-05-12 19:36:28 +08:00
committed by lyingbug
parent 86b05d923e
commit 3f9b09e306
9 changed files with 49 additions and 1 deletions
+6
View File
@@ -42,6 +42,11 @@ type PipelineRequest struct {
FAQDirectAnswerThreshold float64 `json:"-"`
FAQScoreBoost float64 `json:"-"`
// DataAnalysisEnabled controls whether the in-pipeline DuckDB SQL
// data-analysis stage runs. Off by default to avoid an extra LLM call on
// every RAG request that happens to retrieve CSV/Excel chunks.
DataAnalysisEnabled bool `json:"-"`
// Image / multimodal support
Images []string `json:"-"`
VLMModelID string `json:"-"`
@@ -199,6 +204,7 @@ func (c *ChatManage) Clone() *ChatManage {
FAQPriorityEnabled: c.FAQPriorityEnabled,
FAQDirectAnswerThreshold: c.FAQDirectAnswerThreshold,
FAQScoreBoost: c.FAQScoreBoost,
DataAnalysisEnabled: c.DataAnalysisEnabled,
Images: append([]string(nil), c.Images...),
VLMModelID: c.VLMModelID,
ChatModelSupportsVision: c.ChatModelSupportsVision,
+7
View File
@@ -168,6 +168,13 @@ type CustomAgentConfig struct {
// When set, only files with matching extensions can be used with this agent
SupportedFileTypes []string `yaml:"supported_file_types" json:"supported_file_types"`
// ===== Data Analysis Settings =====
// Whether to run the legacy in-pipeline DuckDB SQL data-analysis stage when
// the retrieved chunks include CSV/Excel files. This issues an extra LLM
// call to generate a SQL query and is disabled by default because most
// quick-answer / RAG-style agents do not want the added latency.
DataAnalysisEnabled bool `yaml:"data_analysis_enabled" json:"data_analysis_enabled"`
// ===== FAQ Strategy Settings =====
// Whether FAQ priority strategy is enabled (FAQ answers prioritized over document chunks)
FAQPriorityEnabled bool `yaml:"faq_priority_enabled" json:"faq_priority_enabled"`