Updated app.py

app.py

@@ -12,6 +12,7 @@ from langchain.text_splitter import CharacterTextSplitter
 from langchain.schema import Document
 from langchain_openai import OpenAIEmbeddings, ChatOpenAI
 from langchain_chroma import Chroma
+from langchain.chat_models import ChatHuggingFace
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
 from langchain_ollama import ChatOllama
@@ -82,7 +83,7 @@ def process_files(files):
     # HF Pipeline
     hf_pipeline = pipeline("document-question-answering", model="impira/layoutlm-document-qa")
 
-    llm = HuggingFacePipeline(pipeline=hf_pipeline)
+    llm = ChatHuggingFace(model_name="HuggingFaceH4/zephyr-7b-alpha")
     memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
     retriever = vectorstore.as_retriever(search_kwargs={"k": 10})
     global conversation_chain