Merge branch 'main' into feat/model-config

backend/package/yuxi/knowledge/implementations/lightrag.py

@@ -302,7 +302,7 @@ class LightRagKB(KnowledgeBase):
             ),
         )
 
-    async def index_file(self, db_id: str, file_id: str, operator_id: str | None = None) -> dict:
+    async def index_file(self, db_id: str, file_id: str, operator_id: str | None = None, params: dict | None = None) -> dict:
         """
         Index parsed file (Status: INDEXING -> INDEXED/ERROR_INDEXING)
 
@@ -310,6 +310,7 @@ class LightRagKB(KnowledgeBase):
             db_id: Database ID
             file_id: File ID
             operator_id: ID of the user performing the operation
+            params: Override processing params to apply during indexing (merged on top of stored params)
 
         Returns:
             Updated file metadata
@@ -366,14 +367,15 @@ class LightRagKB(KnowledgeBase):
                 markdown_content = await self._read_markdown_from_minio(file_meta["markdown_file"])
                 file_path = file_meta.get("path")
                 filename = file_meta.get("filename") or file_id
-                processing_params = resolve_chunk_processing_params(
+                params = resolve_chunk_processing_params(
                     kb_additional_params=self.databases_meta.get(db_id, {}).get("metadata"),
                     file_processing_params=file_meta.get("processing_params"),
+                    request_params=params,
                 )
-                self.files_meta[file_id]["processing_params"] = processing_params
+                self.files_meta[file_id]["processing_params"] = params
                 await self._save_metadata()
 
-                chunks = chunk_markdown(markdown_content, file_id, filename, processing_params)
+                chunks = chunk_markdown(markdown_content, file_id, filename, params)
                 chunk_input, split_by_character, split_by_character_only = self._prepare_lightrag_insert_payload(chunks)
                 if not chunk_input:
                     chunk_input = markdown_content

backend/package/yuxi/knowledge/implementations/milvus.py

@@ -284,7 +284,7 @@ class MilvusKB(KnowledgeBase):
         """将文本分割成块"""
         return chunk_markdown(text, file_id, filename, params)
 
-    async def index_file(self, db_id: str, file_id: str, operator_id: str | None = None) -> dict:
+    async def index_file(self, db_id: str, file_id: str, operator_id: str | None = None, params: dict | None = None) -> dict:
         """
         Index parsed file (Status: INDEXING -> INDEXED/ERROR_INDEXING)
 
@@ -292,6 +292,7 @@ class MilvusKB(KnowledgeBase):
             db_id: Database ID
             file_id: File ID
             operator_id: ID of the user performing the operation
+            params: Override processing params to apply during indexing (merged on top of stored params)
 
         Returns:
             Updated file metadata
@@ -342,10 +343,11 @@ class MilvusKB(KnowledgeBase):
             if operator_id:
                 self.files_meta[file_id]["updated_by"] = operator_id
 
-            # Read processing params inside lock to ensure we get the latest values
+            # 将传入的 params 作为 request_params，确保用户指定的参数始终覆盖存储的参数
             params = resolve_chunk_processing_params(
                 kb_additional_params=self.databases_meta.get(db_id, {}).get("metadata"),
                 file_processing_params=file_meta.get("processing_params"),
+                request_params=params,
             )
             self.files_meta[file_id]["processing_params"] = params
             await self._save_metadata()

backend/package/yuxi/knowledge/manager.py

@@ -415,10 +415,10 @@ class KnowledgeBaseManager:
         kb_instance = await self._get_kb_for_database(db_id)
         return await kb_instance.parse_file(db_id, file_id, operator_id)
 
-    async def index_file(self, db_id: str, file_id: str, operator_id: str | None = None) -> dict:
+    async def index_file(self, db_id: str, file_id: str, operator_id: str | None = None, params: dict | None = None) -> dict:
         """Index parsed file"""
         kb_instance = await self._get_kb_for_database(db_id)
-        return await kb_instance.index_file(db_id, file_id, operator_id)
+        return await kb_instance.index_file(db_id, file_id, operator_id, params=params)
 
     async def update_file_params(self, db_id: str, file_id: str, params: dict, operator_id: str | None = None) -> None:
         """Update file processing params"""

backend/server/routers/knowledge_router.py

@@ -442,8 +442,8 @@ async def add_documents(
                         await knowledge_base.update_file_params(
                             db_id, file_id, indexing_params, operator_id=current_user.user_id
                         )
-                        # 2. 执行入库
+                        # 2. 执行入库（传入 indexing_params 确保使用的参数与用户设置一致）
-                        result = await knowledge_base.index_file(db_id, file_id, operator_id=current_user.user_id)
+                        result = await knowledge_base.index_file(db_id, file_id, operator_id=current_user.user_id, params=indexing_params)
                         processed_items.append(result)
                     except Exception as index_error:
                         logger.error(f"自动入库失败 {item} (file_id={file_id}): {index_error}")
@@ -605,7 +605,7 @@ async def index_documents(
                 await context.set_progress(progress, f"正在入库第 {idx}/{total} 个文档")
 
                 try:
-                    result = await knowledge_base.index_file(db_id, file_id, operator_id=operator_id)
+                    result = await knowledge_base.index_file(db_id, file_id, operator_id=operator_id, params=params)
                     processed_items.append(result)
                 except Exception as e:
                     logger.error(f"Index failed for {file_id}: {e}")