Update app.py

app.py

@@ -17,7 +17,7 @@ from langchain_community.document_loaders.directory import DirectoryLoader
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnablePassthrough
 from langchain_experimental.chat_models import Llama2Chat
-
+from langchain_community.chat_models.llamacpp import ChatLlamaCpp
 
 lang_api_key = os.getenv("lang_api_key")
 
@@ -160,7 +160,7 @@ def create_conversational_rag_chain(retriever):
 
     callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
 
-    llm = llamacpp.LlamaCpp(
+    llm = ChatLlamaCpp(
         model_path = "qwen2-0_5b-instruct-q8_0.gguf",
         seed = 41,
         n_gpu_layers=0,
@@ -174,9 +174,7 @@ def create_conversational_rag_chain(retriever):
         verbose=False,
     )
 
-    model = Llama2Chat(
-    llm=llm, 
-)
+   
     
     template = """Answer the question, based only on the following context:
     {context}. Be consise.
@@ -188,7 +186,7 @@ def create_conversational_rag_chain(retriever):
 
 
 
-    rag_chain = prompt | model | StrOutputParser()
+    rag_chain = prompt | llm | StrOutputParser()
 
 
     return rag_chain