diff --git a/dsRag/StartEs.py b/dsRag/StartEs.py
index f59350d2..e69dcbf2 100644
--- a/dsRag/StartEs.py
+++ b/dsRag/StartEs.py
@@ -41,13 +41,14 @@ async def lifespan(app: FastAPI):
     # 初始化阿里云大模型工具
     app.state.aliyun_util = ALiYunUtil()
     yield
+
+
 app = FastAPI(lifespan=lifespan)
 
 # 挂载静态文件目录
 app.mount("/static", StaticFiles(directory="Static"), name="static")
 
 
-
 class QueryRequest(BaseModel):
     query: str = Field(..., description="用户查询的问题")
     documents: List[str] = Field(..., description="用户上传的文档")
@@ -114,10 +115,10 @@ async def rag_stream(request: Request):
         data = await request.json()
         query = data.get('query', '')
         query_tags = data.get('tags', [])
-        
+
         # 获取EsSearchUtil实例
         es_search_util = EsSearchUtil(ES_CONFIG)
-        
+
         # 执行混合搜索
         es_conn = es_search_util.es_pool.get_connection()
         try:
@@ -125,13 +126,13 @@ async def rag_stream(request: Request):
             logger.info(f"\n=== 开始执行查询 ===")
             logger.info(f"原始查询文本: {query}")
             logger.info(f"查询标签: {query_tags}")
-            
+
             logger.info("\n=== 向量搜索阶段 ===")
             logger.info("1. 文本分词和向量化处理中...")
             query_embedding = es_search_util.text_to_embedding(query)
             logger.info(f"2. 生成的查询向量维度: {len(query_embedding)}")
             logger.info(f"3. 前3维向量值: {query_embedding[:3]}")
-            
+
             logger.info("4. 正在执行Elasticsearch向量搜索...")
             vector_results = es_conn.search(
                 index=ES_CONFIG['index_name'],
@@ -160,7 +161,7 @@ async def rag_stream(request: Request):
                 }
             )
             logger.info(f"5. 向量搜索结果数量: {len(vector_results['hits']['hits'])}")
-            
+
             # 文本精确搜索
             logger.info("\n=== 文本精确搜索阶段 ===")
             logger.info("1. 正在执行Elasticsearch文本精确搜索...")
@@ -187,30 +188,30 @@ async def rag_stream(request: Request):
                 }
             )
             logger.info(f"2. 文本搜索结果数量: {len(text_results['hits']['hits'])}")
-            
+
             # 合并结果
             logger.info("\n=== 最终搜索结果 ===")
             logger.info(f"向量搜索结果: {len(vector_results['hits']['hits'])}条")
             for i, hit in enumerate(vector_results['hits']['hits'], 1):
                 logger.info(f"   {i}. 文档ID: {hit['_id']}, 相似度分数: {hit['_score']:.2f}")
                 logger.info(f"      内容: {hit['_source']['user_input']}")
-            
+
             logger.info("文本精确搜索结果:")
             for i, hit in enumerate(text_results['hits']['hits']):
-                logger.info(f"  {i+1}. 文档ID: {hit['_id']}, 匹配分数: {hit['_score']:.2f}")
+                logger.info(f"  {i + 1}. 文档ID: {hit['_id']}, 匹配分数: {hit['_score']:.2f}")
                 logger.info(f"      内容: {hit['_source']['user_input']}")
-            
+
             search_results = {
                 "vector_results": [hit['_source'] for hit in vector_results['hits']['hits']],
                 "text_results": [hit['_source'] for hit in text_results['hits']['hits']]
             }
-            
+
             # 调用阿里云大模型整合结果
             aliyun_util = request.app.state.aliyun_util
-            
+
             # 构建提示词
             context = "\n".join([
-                f"结果{i+1}: {res['tags']['full_content']}" 
+                f"结果{i + 1}: {res['tags']['full_content']}"
                 for i, res in enumerate(search_results['vector_results'] + search_results['text_results'])
             ])
 
@@ -237,23 +238,25 @@ async def rag_stream(request: Request):
             # 调用阿里云大模型
             if len(context) > 0:
                 # 调用大模型生成回答
+                logger.info("正在调用阿里云大模型生成回答...")
                 html_content = aliyun_util.chat(prompt)
+                logger.info(f"调用阿里云大模型生成回答成功完成!")
                 return {"data": html_content}
             else:
                 logger.warning(f"未找到查询'{query}'的相关数据，tags: {query_tags}")
-            return {"data": "没有在知识库中找到相关的信息，无法回答此问题。", "debug": {"query": query, "tags": query_tags}}
+            return {"data": "没有在知识库中找到相关的信息，无法回答此问题。",
+                    "debug": {"query": query, "tags": query_tags}}
         except Exception as e:
             return {"data": f"生成报告时出错: {str(e)}"}
-            
+
 
         finally:
             es_search_util.es_pool.release_connection(es_conn)
-            
+
     except Exception as e:
         logger.error(f"RAG search error: {str(e)}")
         raise HTTPException(status_code=500, detail=str(e))
 
 
-
 if __name__ == "__main__":
     uvicorn.run(app, host="0.0.0.0", port=8000)