Update app.py

app.py

@@ -1,16 +1,12 @@
 import streamlit as st
 from langchain.llms import HuggingFaceHub
-from huggingface_hub import InferenceClient
-import os 
-
-huggingfacehub_api_token = os.environ["HUGGINGFACEHUB_API_TOKEN"]
 
 #Function to return the response 
 def generate_answer(query):
-    client = InferenceClient(
-    model="huggingfaceh4/zephyr-7b-alpha",  
-    token=huggingfacehub_api_token,
-)
+    llm = HuggingFaceHub(
+        repo_id = "huggingfaceh4/zephyr-7b-alpha", 
+        model_kwargs={"temperature": 0.5, "max_length": 64,"max_new_tokens":512}
+    )
     prompt = f"""
              <|system|>
             You are an AI assistant that follows instruction extremely well. Please be truthful and give direct answers
@@ -19,7 +15,7 @@ def generate_answer(query):
              {query}</s>
              <|assistant|>
             """
-    result = client.generated_text(prompt)
+    result = llm.predict(prompt)
     return result