Update app.py

app.py

@@ -82,7 +82,7 @@ def get_retrieval_qa_chain(text_file, hf_model):
 
 # Generates response using the question answering chain defined earlier
 def generate(question, answer, text_file, max_new_tokens):
-  streamer = TextIteratorStreamer(tokenizer=tokenizer, skip_prompt=True)
+  streamer = TextIteratorStreamer(tokenizer=tokenizer, skip_prompt=True, skip_special_tokens=True, timeout=300.0)
   phi2_pipeline = pipeline(
       "text-generation", tokenizer=tokenizer, model=model, max_new_tokens=max_new_tokens, 
       pad_token_id=tokenizer.eos_token_id, eos_token_id=tokenizer.eos_token_id,