Update app.py

app.py

@@ -9,8 +9,16 @@ TOKEN = os.getenv("HUGGINGFACE_API_TOKEN")
 if not TOKEN:
     raise ValueError("API token is not set. Please set the HUGGINGFACE_API_TOKEN environment variable.")
 
+print(f"API Token: {TOKEN[:5]}...{TOKEN[-5:]}")  # Check API token
+
 memory = deque(maxlen=10)
 
+async def test_api():
+    headers = {"Authorization": f"Bearer {TOKEN}"}
+    async with aiohttp.ClientSession() as session:
+        async with session.get("https://api-inference.huggingface.co/models/mistralai/Mistral-Nemo-Instruct-2407", headers=headers) as response:
+            print(f"Test API response: {await response.text()}")
+
 async def respond(
     message,
     history: list[tuple[str, str]],
@@ -19,7 +27,7 @@ async def respond(
     temperature=0.7,
     top_p=0.95,
 ):
-    system_prefix = "System: 입력어의 언어(영어, 한국어, 중국어, 일본어 등)에 따라 동일한 언어로 답변하라."
+    system_prefix = "System: Respond in the same language as the input (English, Korean, Chinese, Japanese, etc.)."
     full_system_message = f"{system_prefix}{system_message}"
 
     memory.append((message, None))
@@ -46,6 +54,13 @@ async def respond(
     try:
         async with aiohttp.ClientSession() as session:
             async with session.post("https://api-inference.huggingface.co/v1/chat/completions", headers=headers, json=payload) as response:
+                print(f"Response status: {response.status}")
+                if response.status != 200:
+                    error_text = await response.text()
+                    print(f"Error response: {error_text}")
+                    yield "An API response error occurred. Please try again."
+                    return
+
                 response_text = ""
                 async for chunk in response.content:
                     if chunk:
@@ -62,6 +77,7 @@ async def respond(
                 if not response_text:
                     yield "I apologize, but I couldn't generate a response. Please try again."
     except Exception as e:
+        print(f"Exception occurred: {str(e)}")
         yield f"An error occurred: {str(e)}"
 
     memory[-1] = (message, response_text)
@@ -72,8 +88,6 @@ async def chat(message, history, system_message, max_tokens, temperature, top_p)
         response = chunk
         yield response
 
-
-                
 theme = "Nymbo/Nymbo_Theme"
 
 css = """
@@ -95,4 +109,6 @@ demo = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
+    import asyncio
+    asyncio.run(test_api())  # Run API test
     demo.queue().launch(max_threads=20)