adding chat model

app.py

@@ -2,11 +2,21 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from langgraph.prebuilt import create_react_agent
 from search_agent import tools
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 """
 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")
-graph = create_react_agent(client, tools=tools)
+# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+llm = HuggingFaceEndpoint(
+    repo_id="HuggingFaceH4/zephyr-7b-beta",
+    task="text-generation",
+    max_new_tokens=512,
+    do_sample=False,
+    repetition_penalty=1.03,
+)
+
+chat_model = ChatHuggingFace(llm=llm)
+graph = create_react_agent(chat_model, tools=tools)
 
 
 def respond(