Update app.py

app.py

@@ -19,6 +19,7 @@ from transformers import pipeline
 import os
 import transformers
 import torch
+from langchain_community.llms import LlamaCpp
 # from langchain_retrieval import BaseRetrieverChain
 # from dotenv import load_dotenv
 
@@ -100,8 +101,8 @@ def get_conversational_rag_chain(retriever_chain,llm):
 
     def safe_llm(input_str: str) -> str:
         if isinstance(input_str, langchain_core.prompts.chat.ChatPromptValue):
-            # input_str = str(input_str)
-            input_str = input_str.to_messages()
+            input_str = str(input_str)
+            # input_str = input_str.to_messages()
 
         # Call the original llm, which should now work correctly
         return llm(input_str)
@@ -144,7 +145,15 @@ def get_response(user_input):
     #     task="text2text-generation",
     #     # model_kwargs={"temperature": 0.2},
     # )
-    llm = pipeline(task="conversational", model="facebook/blenderbot-400M-distill")
+    # llm = pipeline(task="conversational", model="facebook/blenderbot-400M-distill")
+    llm = LlamaCpp(
+    model_path="TheBloke/OpenOrca-Platypus2-13B-GGUF",
+    temperature=0.75,
+    max_tokens=2000,
+    top_p=1,
+    # callback_manager=callback_manager,
+    verbose=True,  # Verbose is required to pass to the callback manager
+)
 
     # llm = HuggingFacePipeline.from_model_id(
     #     model_id="lmsys/fastchat-t5-3b-v1.0",