Update app.py

app.py

@@ -8,7 +8,7 @@ client = InferenceClient()
 # Generator function for streaming AI response
 def generate_response(prompt_template, **kwargs):
     prompt = os.getenv(prompt_template).format(**kwargs)
-    stream = client.chat.completions.create(
+    response = client.chat.completions.create(
         model="Qwen/Qwen2.5-Math-1.5B-Instruct",
         messages=[{"role": "user", "content": prompt}],
         temperature=0.7,
@@ -16,9 +16,7 @@ def generate_response(prompt_template, **kwargs):
         top_p=0.8,
         stream=True
     )
-    for chunk in stream:
-        yield chunk.choices[0].delta.content  # Yield chunks as they are generated
-
+    return response.choices[0].message["content"]
 
 # Gradio app interface
 with gr.Blocks() as app:
@@ -49,8 +47,7 @@ with gr.Blocks() as app:
                 fn=lambda *args: generate_response(prompt_template, **dict(zip([inp["key"] for inp in inputs], args))),
                 inputs=input_fields,
                 outputs=output,
-                api_name=f"/{tab_name.lower().replace(' ', '_')}_execute",
-                stream=True
+                api_name=f"/{tab_name.lower().replace(' ', '_')}_execute"
             )
 
     # Tabs for functionalities