passings args to function again

app.py

@@ -2,7 +2,7 @@ import os
 import random
 import spaces
 import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer, BitsAndBytesConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, TextIteratorStreamer
 import gradio as gr
 from threading import Thread
 import logging
@@ -28,7 +28,7 @@ examples = ['🛁 Schreibe einen Werbetext über ein platzsparendes Badmöbel.',
            '🛌 Schreibe einen Werbetext über Quantenmechanik am Beispiel eines Babybetts.',
            '🗄️ Schreibe einen Werbetext über eine Kommode aus veganen Fleischbällchen.',
            ]
-nexted_examples = [[example] for example in random.sample(examples, 3)]
+nested_examples = [[example] for example in random.sample(examples, 3)]
 
 
 device = "cuda" # for GPU usage or "cpu" for CPU usage
@@ -51,14 +51,9 @@ def stream_chat(
 ):
     logging.debug(f'message: {message}, system_prompt: {system_prompt}, temperature: {temperature}, max_new_tokens: {max_new_tokens}')
 
-    """conversation = [
+    conversation = [
         {"role": "system", "content": ""}
     ]
-    for prompt, answer in history:
-        conversation.extend([
-            {"role": "user", "content": prompt}, 
-            {"role": "assistant", "content": answer},
-        ])
 
     conversation.append({"role": "user", "content": message})
 
@@ -85,8 +80,7 @@ def stream_chat(
     buffer = ""
     for new_text in streamer:
         buffer += new_text
-        yield buffer"""
-    return "OK"
+        yield buffer
 
             
 chatbot = gr.Chatbot(height=400, placeholder=PLACEHOLDER)
@@ -140,7 +134,7 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
                 render=False,
             ),
         ],
-        examples=nexted_examples,
+        examples=nested_examples,
         cache_examples=False,
     )