async def response_streamer(response):
    for token in response:
        logger.info(token)
        yield f"{token}"

class ChatInput(BaseModel):
    query_text: str

@app.post("/chat")
async def query_index(chat_input: ChatInput):
    global index

    chat_engine = index.as_chat_engine(
        chat_mode="condense_question",
        verbose=True,
        llm=Settings.llm,
    )

    streaming_response = chat_engine.stream_chat(chat_input.query_text)
    return StreamingResponse(
        response_streamer(streaming_response.response_gen),
        media_type="text/event-stream",
        status_code=200,
    )

# Create index from requested docs
    indices = []
    summaries = []
    service_context = _create_service_context()
    for index_id in data["indexes"]:
        persist_dir = f"/az/indexes/{index_id}" # test index
        storage_context = StorageContext.from_defaults(persist_dir=persist_dir)
        index = load_index_from_storage(
            storage_context=storage_context,
            service_context=service_context,
        )
        summaries.append("")
        indices.append(index)
    graph = ComposableGraph.from_indices(GPTListIndex, indices, summaries, service_context=service_context)
    query_engine = graph.as_query_engine()

    response = str(query_engine.query(data['query'])).replace("\n", " ")

os.environ["OPENAI_API_KEY"] = args.openai_key
os.environ["OPENAI_API_BASE"] = args.openai_host

openai.api_type = "azure"
openai.api_version = "2023-03-15"
openai.api_base = os.getenv('OPENAI_API_BASE')
openai.api_key = os.getenv("OPENAI_API_KEY")