add verification

app.py

@@ -1,5 +1,6 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
 # RAG imports
 import os
@@ -11,7 +12,12 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+hf_token = os.environ.get("HUGGINGFACEHUB_API_TOKEN")
+client = InferenceClient(
+                            model="HuggingFaceH4/zephyr-7b-beta",
+                            token=hf_token  # <-- This is critical
+                    )
+
 
 # We'll load the existing FAISS index at the start
 INDEX_FOLDER = "faiss_index"