Update app.py

app.py

@@ -2,11 +2,11 @@ import streamlit as st
 from ctransformers import AutoModelForCausalLM
 from fastapi import FastAPI
 from pydantic import BaseModel
-import time
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
 import numpy as np
 import PyPDF2
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import time
 
 # Load the model
 @st.cache_resource
@@ -69,7 +69,10 @@ def stream_response(prompt, context, placeholder):
     response = ""
     for token in generate_llama_response(prompt, context):
         response += token
-        placeholder.markdown(response + "▌")
+        if len(response.split()) >= 50:  # Minimum 50 tokens
+            placeholder.markdown(response + "▌")
+        if len(response.split()) >= 100:  # Maximum 100 tokens
+            break
     placeholder.markdown(response)
 
 def summarize_pdf(documents, placeholder):