diff --git a/api/app.py b/api/app.py
index 0ba13f054354a6..4e5fd1f24bd368 100644
--- a/api/app.py
+++ b/api/app.py
@@ -6,9 +6,9 @@
 if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
     from gevent import monkey
     monkey.patch_all()
-    if os.environ.get("VECTOR_STORE") == 'milvus':
-        import grpc.experimental.gevent
-        grpc.experimental.gevent.init_gevent()
+    # if os.environ.get("VECTOR_STORE") == 'milvus':
+    import grpc.experimental.gevent
+    grpc.experimental.gevent.init_gevent()
 
     import langchain
     langchain.verbose = True
diff --git a/api/core/model_runtime/model_providers/tongyi/llm/llm.py b/api/core/model_runtime/model_providers/tongyi/llm/llm.py
index cce740b53b7378..a0070f6d0d0214 100644
--- a/api/core/model_runtime/model_providers/tongyi/llm/llm.py
+++ b/api/core/model_runtime/model_providers/tongyi/llm/llm.py
@@ -161,6 +161,7 @@ def _handle_generate_response(self, model: str, credentials: dict, response: Das
         result = LLMResult(
             model=model,
             message=assistant_prompt_message,
+            prompt_messages=prompt_messages,
             usage=usage,
         )
 
diff --git a/api/core/model_runtime/model_providers/zhipuai/text_embedding/text_embedding.py b/api/core/model_runtime/model_providers/zhipuai/text_embedding/text_embedding.py
index fbaeaf6bcfb99b..603840a4a86ae0 100644
--- a/api/core/model_runtime/model_providers/zhipuai/text_embedding/text_embedding.py
+++ b/api/core/model_runtime/model_providers/zhipuai/text_embedding/text_embedding.py
@@ -37,7 +37,7 @@ def _invoke(self, model: str, credentials: dict,
 
         return TextEmbeddingResult(
             embeddings=embeddings,
-            usage=self._calc_response_usage(model, embedding_used_tokens),
+            usage=self._calc_response_usage(model, credentials_kwargs, embedding_used_tokens),
             model=model
         )
 
@@ -115,7 +115,7 @@ def embed_query(self, text: str) -> List[float]:
         """
         return self.embed_documents([text])[0]
     
-    def _calc_response_usage(self, model: str, tokens: int) -> EmbeddingUsage:
+    def _calc_response_usage(self, model: str,credentials: dict, tokens: int) -> EmbeddingUsage:
         """
         Calculate response usage
 
@@ -126,6 +126,7 @@ def _calc_response_usage(self, model: str, tokens: int) -> EmbeddingUsage:
         # get input price info
         input_price_info = self.get_price(
             model=model,
+            credentials=credentials,
             price_type=PriceType.INPUT,
             tokens=tokens
         )