diff --git a/metagpt/llm.py b/metagpt/llm.py
index 1f6a6bb1a..e9b80d7a8 100644
--- a/metagpt/llm.py
+++ b/metagpt/llm.py
@@ -14,7 +14,7 @@ from metagpt.provider.zhipuai_api import ZhiPuAIGPTAPI
 from metagpt.provider.spark_api import SparkAPI
 
 
-def LLM():
+def LLM() -> "BaseGPTAPI":
     """ initialize different LLM instance according to the key field existence"""
     # TODO a little trick, can use registry to initialize LLM instance further
     if CONFIG.openai_api_key and CONFIG.openai_api_key.starswith("sk-"):
diff --git a/metagpt/provider/zhipuai/async_sse_client.py b/metagpt/provider/zhipuai/async_sse_client.py
index 7a4275982..b819fdc63 100644
--- a/metagpt/provider/zhipuai/async_sse_client.py
+++ b/metagpt/provider/zhipuai/async_sse_client.py
@@ -1,6 +1,7 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 # @Desc   : async_sse_client to make keep the use of Event to access response
+#           refs to `https://github.com/zhipuai/zhipuai-sdk-python/blob/main/zhipuai/utils/sse_client.py`
 
 from zhipuai.utils.sse_client import SSEClient, Event, _FIELD_SEPARATOR
 
diff --git a/metagpt/provider/zhipuai/zhipu_model_api.py b/metagpt/provider/zhipuai/zhipu_model_api.py
index e1d52061d..618b2e865 100644
--- a/metagpt/provider/zhipuai/zhipu_model_api.py
+++ b/metagpt/provider/zhipuai/zhipu_model_api.py
@@ -29,8 +29,12 @@ class ZhiPuModelAPI(ModelAPI):
     @classmethod
     def split_zhipu_api_url(cls, invoke_type: InvokeType, kwargs):
         # use this method to prevent zhipu api upgrading to different version.
+        # and follow the GeneralAPIRequestor implemented based on openai sdk
         zhipu_api_url = cls._build_api_url(kwargs, invoke_type)
-        # example: https://open.bigmodel.cn/api/paas/v3/model-api/{model}/{invoke_method}
+        """
+            example:
+                zhipu_api_url: https://open.bigmodel.cn/api/paas/v3/model-api/{model}/{invoke_method}
+        """
         arr = zhipu_api_url.split("/api/")
         # ("https://open.bigmodel.cn/api/" , "/paas/v3/model-api/chatglm_turbo/invoke")
         return f"{arr[0]}/api", f"/{arr[1]}"
diff --git a/metagpt/provider/zhipuai_api.py b/metagpt/provider/zhipuai_api.py
index 4e8e6b760..2ad1944c2 100644
--- a/metagpt/provider/zhipuai_api.py
+++ b/metagpt/provider/zhipuai_api.py
@@ -68,7 +68,7 @@ class ZhiPuAIGPTAPI(BaseGPTAPI):
 
     def get_choice_text(self, resp: dict) -> str:
         """ get the first text of choice from llm response """
-        assist_msg = resp.get("data").get("choices")[-1]
+        assist_msg = resp.get("data", {}).get("choices", [{"role": "error"}])[-1]
         assert assist_msg["role"] == "assistant"
         return assist_msg.get("content")
 
@@ -121,16 +121,15 @@ class ZhiPuAIGPTAPI(BaseGPTAPI):
 
         self._update_costs(usage)
         full_content = "".join(collected_content)
-        logger.info(f"full_content: {full_content} !!")
         return full_content
 
-    # @retry(
-    #     stop=stop_after_attempt(3),
-    #     wait=wait_fixed(1),
-    #     after=after_log(logger, logger.level("WARNING").name),
-    #     retry=retry_if_exception_type(ConnectionError),
-    #     retry_error_callback=log_and_reraise
-    # )
+    @retry(
+        stop=stop_after_attempt(3),
+        wait=wait_fixed(1),
+        after=after_log(logger, logger.level("WARNING").name),
+        retry=retry_if_exception_type(ConnectionError),
+        retry_error_callback=log_and_reraise
+    )
     async def acompletion_text(self, messages: list[dict], stream=False) -> str:
         """ response in async with stream or non-stream mode """
         if stream: