Update app.py

app.py

@@ -10,9 +10,8 @@ client = InferenceClient()
 
 async def generate_text(prompt):
     # Use the Hugging Face client to generate text asynchronously
-    async with client.chat(model_id=model_id) as chat:
-        response = await chat(prompt)
-        return response['generated_text']
+    response = await client.text_generation(model=model_id, inputs=prompt)
+    return response['generated_text']
 
 # Create Gradio interface
 inputs = gr.Textbox(label="Enter a prompt", lines=2)
@@ -26,4 +25,3 @@ iface = gr.Interface(fn=predict, inputs=inputs, outputs=outputs, title="Hugging
 
 if __name__ == "__main__":
     iface.launch()
-