Update app.py

app.py

@@ -171,7 +171,7 @@ class OpenAIApi:
         http_client = httpx.Client()
         try:
             self.client = AzureOpenAI(
-                azure_endpoint=endpoint,
+                azure_endpoint=endpoint.rstrip('/'),  # Ensure no trailing slash
                 api_key=api_key or os.getenv("AZURE_OPENAI_API_KEY"),
                 api_version="2024-02-15-preview",
                 http_client=http_client
@@ -278,7 +278,8 @@ class OpenAIApi:
         logger.info(f"Sending request to model: {self.model}, endpoint: {self.client._base_url}, messages: {json.dumps(messages, ensure_ascii=False)}")
         
         try:
-            response = await self.client.chat.completions.create(
+            # Synchronous call to create stream
+            response = self.client.chat.completions.create(
                 model=self.model,
                 messages=messages,
                 temperature=0.5,
@@ -292,7 +293,9 @@ class OpenAIApi:
             
             full_response = ""
             tool_calls = []
+            # Asynchronous iteration over stream
             async for chunk in response:
+                logger.debug(f"Received chunk: {chunk}")
                 if chunk.choices and chunk.choices[0].delta.content:
                     full_response += chunk.choices[0].delta.content
                 if chunk.choices and chunk.choices[0].delta.tool_calls: