I am using an index in JSON format which

# define llm predictor
llm_predictor = LLMPredictor(
    llm=ChatOpenAI(
        model_name="gpt-3.5-turbo",
        max_tokens=1024,
        openai_api_key=api_key,
        temperature=0.2,
        streaming=False,
    )
)

# define prompt helper
# set maximum input size
max_input_size = 4096
# set number of output tokens
num_output = 512
# set maximum chunk overlap
max_chunk_overlap = 20
prompt_helper = PromptHelper(max_input_size, num_output, max_chunk_overlap)

service_context = ServiceContext.from_defaults(
    llm_predictor=llm_predictor,
    prompt_helper=prompt_helper,
    chunk_size_limit=2048,
)


index_file = 'indices/index.json'
os.makedirs('indices', exist_ok=True)

if os.path.exists(index_file):
    index = GPTSimpleVectorIndex.load_from_disk(index_file, service_context=service_context)
else:
    index = GPTSimpleVectorIndex.from_documents(documents, service_context=service_context)
    index.save_to_disk(index_file)

result = index.query(
            query_text,
            text_qa_template=QA_PROMPT,
            response_mode="tree_summarize",
            similarity_top_k=4,
            mode=QueryMode.EMBEDDING,
            streaming=False,
        )