updated imports and model arguments

app.py

@@ -6,7 +6,7 @@ from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.callbacks.manager import CallbackManager
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-# from langchain.llms import LlamaCpp
+from langchain.llms import LlamaCpp
 from langchain.vectorstores import Qdrant
 from qdrant_client.http import models
 # from langchain.llms import CTransformers
@@ -28,8 +28,10 @@ print("loading the LLM......................................")
 
 llm = LlamaCpp(
     model_path="./llama-2-7b-chat.Q3_K_S.gguf",
+    temperature = 0.2,
     n_ctx=2048,
     f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls
+    max_tokens = 500,
     callback_manager=callback_manager,
     verbose=True,
 )