From cefac6399de135c633db0278e04584cadf82e086 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E6=9C=B1=E6=BD=AE?= <zhuchaowe@users.noreply.github.com>
Date: Fri, 19 Dec 2025 00:03:46 +0800
Subject: [PATCH] =?UTF-8?q?=E9=9F=B3=E8=A7=86=E9=A2=91=E6=94=AF=E6=8C=81?=
 =?UTF-8?q?=E5=88=86=E6=AE=B5?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 apps/knowledge/views/document.py | 33 +++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/apps/knowledge/views/document.py b/apps/knowledge/views/document.py
index 1100967f..2d93a967 100644
--- a/apps/knowledge/views/document.py
+++ b/apps/knowledge/views/document.py
@@ -430,8 +430,39 @@ class DocumentView(APIView):
                  'document_list': r.data}),
         )
         def put(self, request: Request, workspace_id: str, knowledge_id: str):
+            # 准备分块参数
+            from common.utils.logger import maxkb_logger
+            maxkb_logger.info(f"=== BatchCreate View ===")
+            maxkb_logger.info(f"request.data type: {type(request.data)}")
+            if isinstance(request.data, list):
+                maxkb_logger.info(f"request.data is list with {len(request.data)} items")
+                # 检查第一个文档的参数
+                if len(request.data) > 0:
+                    first_doc = request.data[0]
+                    maxkb_logger.info(f"First doc keys: {list(first_doc.keys())}")
+                    maxkb_logger.info(f"First doc limit: {first_doc.get('limit')}")
+                    maxkb_logger.info(f"First doc stt_model_id: {first_doc.get('stt_model_id')}")
+
+            # 准备 serializer 数据
+            serializer_data = {
+                'knowledge_id': knowledge_id,
+                'workspace_id': workspace_id
+            }
+
+            # 从第一个文档中提取分块参数（所有文档使用相同的分块设置）
+            if isinstance(request.data, list) and len(request.data) > 0:
+                first_doc = request.data[0]
+                if 'limit' in first_doc:
+                    serializer_data['limit'] = first_doc.get('limit')
+                if 'patterns' in first_doc:
+                    serializer_data['patterns'] = first_doc.get('patterns')
+                if 'with_filter' in first_doc:
+                    serializer_data['with_filter'] = first_doc.get('with_filter')
+
+            maxkb_logger.info(f"BatchCreate serializer_data: {serializer_data}")
+
             return result.success(DocumentSerializers.Batch(
-                data={'knowledge_id': knowledge_id, 'workspace_id': workspace_id}
+                data=serializer_data
             ).batch_save(request.data))
 
     class BatchSync(APIView):