Update app.py

app.py

@@ -4,7 +4,7 @@ from langchain.chains import RetrievalQA
 from langchain_community.vectorstores import Pinecone
 from langchain.prompts import PromptTemplate
 from langchain_community.llms import CTransformers
-#from flask_limiter import Limiter
+from flask_limiter import Limiter
 from flask_limiter.util import get_remote_address
 from langchain_community.llms import LlamaCpp
 import time 
@@ -13,11 +13,11 @@ import time
 app = Flask(__name__)
 
 # Setup Flask-Limiter
-#limiter = Limiter(
- #   app=app,
-  #  key_func=get_remote_address,  # Correctly specify key_func as a keyword argument
-   # default_limits=["200 per day", "20 per hour"]
-#)
+limiter = Limiter(
+    app=app,
+    key_func=get_remote_address,  # Correctly specify key_func as a keyword argument
+    default_limits=["200 per day", "20 per hour"]
+)
 
 
 # Initialize embeddings directly    
@@ -40,7 +40,7 @@ llm = LlamaCpp(
     model_path="model/phi-2.Q2_K.gguf",
     temperature=0.1,
     max_tokens=128,
-   # repetition_penalty=1,
+    repetition_penalty=1,
     top_p=1,
     verbose=True,  # Verbose is required to pass to the callback manager
 )
@@ -65,7 +65,7 @@ messages = []
 
 
 @app.route("/", methods=["GET"])
-#@limiter.limit("10/minute")  
+@limiter.limit("10/minute")  
 def home():
     return render_template("home.html", messages=messages)
 
@@ -90,5 +90,5 @@ def post_message():
 
 
 if __name__ == "__main__":
-    app.run(host='0.0.0.0', port=7860, debug=True)
+    app.run(host='0.0.0.0', port=7860)