Update app.py

app.py

@@ -1,11 +1,16 @@
 import streamlit as st
 from langchain.llms import HuggingFaceHub
+from huggingface_hub import InferenceClient
 
 
+huggingfacehub_api_token = os.environ["HUGGINGFACEHUB_API_TOKEN"]
 
 #Function to return the response 
 def generate_answer(query):
-    llm = HuggingFaceHub(repo_id="huggingfaceh4/zephyr-7b-alpha", model_kwargs={"temperature": 0.5, "max_length": 64,"max_new_tokens":512})
+    client = InferenceClient(
+    repo_id="huggingfaceh4/zephyr-7b-alpha",  
+    token=huggingfacehub_api_token,
+)
     prompt = f"""
              <|system|>
             You are an AI assistant that follows instruction extremely well. Please be truthful and give direct answers
@@ -14,7 +19,7 @@ def generate_answer(query):
              {query}</s>
              <|assistant|>
             """
-    result = llm.predict(prompt)
+    result = client.predict(prompt)
     return result