I just run this example and it exceeded

from llama_index import VectorStoreIndex, SimpleDirectoryReader
from llama_index import ServiceContext
from llama_index.llms import OpenAI
from llama_index.embeddings import OpenAIEmbedding

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

embedding_model = OpenAIEmbedding(
    api_key="sk-XXXXXXXXXXXXXXXXXXXXXX",
    organization="org-XXXXXXXXXXXXXXXXXXXXXXXXX",
)


llm = OpenAI(
    api_key="sk-XXXXXXXXXXXXXXXXXXXXXXXXX",
    organization="org-XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
    model="gpt-4-1106-preview",
)

service_context = ServiceContext.from_defaults(llm=llm, embed_model=embedding_model)

def main():
    documents = SimpleDirectoryReader("data2").load_data(show_progress=True)
    index = VectorStoreIndex.from_documents(documents, show_progress=True, service_context=service_context)

    query_engine = index.as_query_engine(service_context=service_context)
    response = query_engine.query("What did the author do growing up?")
    print(response)

if __name__ == "__main__":
    main()