check

app.py

@@ -1,10 +1,13 @@
 import gradio as gr
+import os
 from huggingface_hub import InferenceClient
 from langgraph.prebuilt import create_react_agent
 from search_agent import tools
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 from search_agent import tools
 from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
+huggingfacehub_api_token = os.getenv('api-token')
+
 """
 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
 """
@@ -12,9 +15,7 @@ For more information on `huggingface_hub` Inference API support, please check th
 llm = HuggingFaceEndpoint(
     repo_id="meta-llama/Llama-3.2-1B-Instruct",
     task="text-generation",
-    max_new_tokens=512,
-    do_sample=False,
-    repetition_penalty=1.03,
+    huggingfacehub_api_token=huggingfacehub_api_token,
 )
 
 chat_model = ChatHuggingFace(llm=llm)