Update app.py

app.py

@@ -14,31 +14,33 @@ def respond(
     """
     For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
     """
-#    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
     client = InferenceClient(token=hf_token.token, model="utter-project/EuroLLM-9B-Instruct")
     
     messages = [{"role": "system", "content": system_message}]
-
     messages.extend(history)
-
     messages.append({"role": "user", "content": message})
 
     response = ""
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
+    try:
+        for msg in client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            choices = msg.choices
+            if len(choices) and choices[0].delta.content:
+                token = choices[0].delta.content
+                response += token
+                yield response
+    except StopIteration:
+        pass
+    
+    # Osigurajte da se uvijek vrati barem jedan rezultat
+    if not response:
+        yield "Sorry, I couldn't generate a response."
 
 
 """
@@ -69,3 +71,4 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     demo.launch()
+#    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")