Update app.py

app.py

@@ -70,15 +70,14 @@ repo_id = "Qwen/Qwen2.5-7B-Instruct"
 # repo_id = "microsoft/Phi-3.5-mini-instruct"
 
 
-llm = HuggingFaceEndpoint(
-    repo_id=repo_id,
-    task="text-generation",
+from langchain_huggingface import ChatHuggingFace
+
+llm = ChatHuggingFace(
+    model=repo_id,
     max_new_tokens=512,
+    temperature=0.1,
     huggingfacehub_api_token=os.getenv("HF_TOKEN"),
-    provider = 'auto',
-    model_kwargs={"wait_for_model": True}
 )
-
 # 2. ChatHuggingFace will correctly route this to the /v1/chat/completions 
 # endpoint which the Llama-3.1-8B-Instruct model supports.
 # llm = ChatHuggingFace(llm=llm_endpoint)