Hey Logan M 8260

from langchain.chat_models import ChatOpenAI
from llama_index import ServiceContext, LLMPredictor, GPTVectorStoreIndex

llm = ChatOpenAI(model_name='gpt-3.5-turbo', temperature=0, streaming=True)
service_context = ServiceContext.from_defaults(llm_predictor=LLMPredictor(llm=llm))

index = GPTVectorStoreIndex.from_documents(documents, service_context=service_context)
query_engine = index.as_query_engine(streaming=True)

response = query_engine.query('...')

# print the stream to terminal
response.print_response_stream()

# OR get the actual token generator object
for token in response.response_gen:
   # do a thing with the token?