Update app.py

app.py

@@ -33,13 +33,25 @@ def generate(
 
     formatted_prompt = format_prompt(prompt, history)
 
-    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    output = ""
+    try:
+        stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+        output = ""
+        for response in stream:
+            if response.token.text:  # Ensuring that there is text to add
+                output += response.token.text
+                yield output  # Yield the updated output each time a new token is received
+    except Exception as e:
+        yield f"An error occurred: {str(e)}"  # Handle any exceptions that might occur
+    
+    # stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    # output = ""
+
+    # for response in stream:
+    #     output += response.token.text
+    #     yield output
+    # return output
+
 
-    for response in stream:
-        output += response.token.text
-        yield output
-    return output
 
 
 additional_inputs=[
@@ -56,7 +68,7 @@ additional_inputs=[
         label="Max new tokens",
         value=256,
         minimum=0,
-        maximum=1048,
+        maximum=524,
         step=64,
         interactive=True,
         info="The maximum numbers of new tokens",