Update app.py

app.py

@@ -106,7 +106,7 @@ top_results = get_top_chunks("How does water get into the sky?", chunk_embedding
 # Print the top results
 print(top_results)
 
-client = InferenceClient("google/gemma-7b-it")
+client = InferenceClient("microsoft/phi-3-mini-4k-instruct")
 
 def respond(message, history, name, mood):
     duck_chunks = get_top_chunks(message, chunk_embeddings, cleaned_chunks)