Update app.py

app.py

@@ -1,6 +1,5 @@
 import os
 from pathlib import Path
-import requests
 import torch
 from threading import Event, Thread
 from transformers import AutoConfig, AutoTokenizer
@@ -113,7 +112,6 @@ with gr.Blocks() as iface:
             return input_tokens
         
         input_ids = convert_history_to_token(history)
-        streamer = gr.Textbox.update()
 
         generate_kwargs = dict(
             input_ids=input_ids,
@@ -121,22 +119,14 @@ with gr.Blocks() as iface:
             temperature=temperature,
             top_p=top_p,
             top_k=top_k,
-            repetition_penalty=repetition_penalty,
-            streamer=streamer
+            repetition_penalty=repetition_penalty
         )
         
-        event = Event()
-        def generate_and_signal_complete():
-            ov_model.generate(**generate_kwargs)
-            event.set()
-        
-        t1 = Thread(target=generate_and_signal_complete)
-        t1.start()
-
-        partial_text = ""
-        for new_text in streamer:
-            partial_text += new_text
-            history[-1][1] = partial_text
+        # Stream response to textbox
+        response = ""
+        for new_text in ov_model.generate(**generate_kwargs):
+            response += new_text
+            history[-1][1] = response
             yield history
 
     # Set up the interface with inputs and outputs