Update app.py

app.py

@@ -1,5 +1,5 @@
 import streamlit as st
-import requests
+from huggingface_hub import InferenceClient
 
 # -----------------------------
 # Hugging Face API setup
@@ -10,46 +10,9 @@ if not HF_API_TOKEN:
     st.error("HF_API_TOKEN not found in Secrets.")
     st.stop()
 
-MODEL_ID = "HuggingFaceH4/zephyr-7b-beta"
-API_URL = f"https://api-inference.huggingface.co/models/{MODEL_ID}"
-HEADERS = {"Authorization": f"Bearer {HF_API_TOKEN}"}
-
-# -----------------------------
-# Helper function to query model
-# -----------------------------
-def query_hf_model(prompt, max_length=256):
-    payload = {
-        "inputs": prompt,
-        "parameters": {
-            "max_new_tokens": max_length,
-            "temperature": 0.7,
-            "return_full_text": False
-        },
-    }
-
-    try:
-        response = requests.post(API_URL, headers=HEADERS, json=payload, timeout=120)
-
-        if response.status_code == 200:
-            result = response.json()
-
-            if isinstance(result, list) and "generated_text" in result[0]:
-                return result[0]["generated_text"].strip()
-
-            if isinstance(result, dict) and "error" in result:
-                return "Model error: " + result["error"]
-
-            return str(result)
-
-        elif response.status_code == 503:
-            return "Model is loading. Please try again in a few seconds."
-
-        else:
-            return f"Request failed with status code {response.status_code}"
-
-    except Exception as e:
-        return f"Error: {str(e)}"
+client = InferenceClient(token=HF_API_TOKEN)
 
+MODEL_ID = "HuggingFaceH4/zephyr-7b-beta"
 
 # -----------------------------
 # Streamlit UI
@@ -70,8 +33,16 @@ user_input = st.text_input("Your Question:")
 
 if st.button("Submit") and user_input:
     with st.spinner("Generating AI answer..."):
-        answer = query_hf_model(user_input)
-    st.session_state.last_answer = answer
+        try:
+            response = client.text_generation(
+                prompt=user_input,
+                model=MODEL_ID,
+                max_new_tokens=200,
+                temperature=0.7,
+            )
+            st.session_state.last_answer = response
+        except Exception as e:
+            st.session_state.last_answer = f"Error: {str(e)}"
 
 # Display answer
 if st.session_state.last_answer: