Update app.py

app.py

@@ -9,8 +9,8 @@ from langchain_community.llms import llamacpp, huggingface_pipeline
 from langchain.prompts import PromptTemplate
 from langchain.chains import LLMChain
 from langchain.chains.question_answering import load_qa_chain
-from huggingface_hub import hf_hub_download
-from dotenv import load_dotenv
+from huggingface_hub import hf_hub_download, login
+login(os.environ['hf_token'])
 
 _template = """Given the following conversation and a follow up question, rephrase the follow up question to be a 
 standalone question without changing the content in given question.
@@ -22,8 +22,6 @@ system_prompt = """You are a helpful assistant, you will use the provided contex
 Read the given context before answering questions and think step by step. If you can not answer a user question based on the provided context, inform the user.
 Do not use any other information for answering the user. Provide a detailed answer to the question."""
 
-load_dotenv()
-
 def load_quantized_model(model_id=None):
     MODEL_ID, MODEL_BASENAME = "TheBloke/zephyr-7B-beta-GGUF","zephyr-7b-beta.Q5_K_S.gguf"
     try: