Update app.py

app.py

@@ -45,7 +45,7 @@ def pull_relevant_info(query, top_k=3):
     relevant_info = "\n\n".join([cleaned_chunks[i] for i in top_indices])
     return relevant_info
 
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", provider="hf-inference")
+client = InferenceClient("microsoft/phi-4", provider="hf-inference")
 
 def respond(message, history):