runtime auth

app.py

@@ -1,6 +1,13 @@
 import gradio as gr
 # from huggingface_hub import InferenceClient
 from transformers import pipeline
+import os
+
+# Retrieve the Hugging Face API token from environment variables
+hf_token = os.getenv("HF_TOKEN")
+
+if not api_token:
+    raise ValueError("API token is not set. Please set the HF_TOKEN environment variable in Space Settings.")
 
 """
 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
@@ -8,7 +15,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 # requires space hardware update to use large models (TODO)
 # client = InferenceClient("mistralai/Mistral-Large-Instruct-2407")
 # Note change in instantiation***
-text_generator = pipeline("text-generation", model="google/gemma-2-2b")
+text_generator = pipeline("text-generation", model="google/gemma-2-2b", use_auth_token=hf_token)
 
 def authenticate_and_generate(token, message, history, system_message, max_tokens, temperature, top_p):
     # Initialize the text-generation pipeline with the provided token