reverting the changes

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
@@ -26,23 +26,23 @@ callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
 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,
-)
+# 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,
+# )
 
-# llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF", 
-#                                            model_file="llama-2-7b-chat.Q3_K_S.gguf", 
-#                                            model_type="llama", 
-#                                            temperature = 0.2,
-#                                            repetition_penalty = 1.5,
-#                                            max_new_tokens = 300,
-#                                            )
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/Llama-2-7B-Chat-GGUF", 
+                                           model_file="llama-2-7b-chat.Q3_K_S.gguf", 
+                                           model_type="llama", 
+                                           temperature = 0.2,
+                                           repetition_penalty = 1.5,
+                                           max_new_tokens = 300,
+                                           )