Update app.py

app.py

@@ -34,13 +34,6 @@ def generate(prompt, history, system_prompt, temperature=0.9, max_new_tokens=904
         yield output
     return output
 
-    for response in stream:
-        output += response.token.text
-        if "http" in output:  # assuming the AI writes a direct image link in its response
-            yield {"image": output}  # Gradio will display the image
-        else:
-            yield output
-
 additional_inputs = [
     gr.Textbox(label="System Prompt", max_lines=1, interactive=True),
     gr.Slider(label="Temperature", value=0.9, minimum=0.0, maximum=1.0, step=0.05, interactive=True, info="Higher values produce more diverse outputs"),
@@ -49,14 +42,14 @@ additional_inputs = [
     gr.Slider(label="Repetition penalty", value=1.2, minimum=1.0, maximum=2.0, step=0.05, interactive=True, info="Penalize repeated tokens")
 ]
 
- # Apply the Soft theme
-
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.ChatInterface(
-        fn=generate,
-        chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
-        additional_inputs=additional_inputs,
-        title="ConvoLite",
-        description="Remember! The AI might give incorrect information about people, locations, history, etc...",
-        concurrency_limit=20,
-    ).launch(show_api=False,)
+# Apply the Soft theme
+gr.Interface.theme = gr.themes.Soft
+
+gr.ChatInterface(
+    fn=generate,
+    chatbot=gr.Chatbot(show_label=True, show_share_button=True, show_copy_button=True, likeable=True, layout="panel"),
+    additional_inputs=additional_inputs,
+    title="ConvoLite",
+    description="Remember! The AI might give incorrect information about people, locations, history, etc...",
+    concurrency_limit=20,
+).launch(show_api=False,)