From 502921159a06aecf31cc3be939ebf125667a5dbd Mon Sep 17 00:00:00 2001
From: buua436 <sz_buua@foxmail.com>
Date: Wed, 5 Aug 2026 19:27:17 +0800
Subject: [PATCH] fix: use updated RAPTOR options for skill generation (#17859)

---
 rag/svr/task_executor_refactor/dataset_skill_generator.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/rag/svr/task_executor_refactor/dataset_skill_generator.py b/rag/svr/task_executor_refactor/dataset_skill_generator.py
index c447d1fb03..77ce8e3fff 100644
--- a/rag/svr/task_executor_refactor/dataset_skill_generator.py
+++ b/rag/svr/task_executor_refactor/dataset_skill_generator.py
@@ -366,9 +366,10 @@ async def run_corpus2skill(
         llm_model=chat_mdl,
         embd_model=embedding_model,
         prompt="Please write a concise summary of the following texts:\n{cluster_content}",
-        max_token=256,
-        threshold=0.1,
+        max_token=512,
         max_errors=3,
+        clustering_threshold=0.3,
+        clustering_ratio=0.5,
     )
 
     # ---- Phase 1: per-doc summaries.