Llama_index index.query returns proper response when .py file is run via CLI but return "None" when used with (Django)api call

Question

I am trying to het a response from openai. This works fine when I run the file form the CLI.(see code below) Because it prints the response to the command line.

from django.views.decorators.csrf import csrf_exempt
from llama_index import GPTSimpleVectorIndex, SimpleDirectoryReader
import os


os.environ["OPENAI_API_KEY"] = "<MY_OPENAI_API_KEY>"

@csrf_exempt
def ask_ai( prompt ):
    print( prompt )
    documents = SimpleDirectoryReader("data").load_data()
    index = GPTSimpleVectorIndex.from_documents( documents )

    response = index.query( prompt )
    print(  response )



ask_ai("<my prompt>")

However, when I use Django to call the mostly the same but slightly modified file(see below) the response is always printed as "None" and returned as null.

from django.views.decorators.csrf import csrf_exempt
from llama_index import GPTSimpleVectorIndex, SimpleDirectoryReader
import os


os.environ["OPENAI_API_KEY"] = "<MY_OPENAI_API_KEY>"

@csrf_exempt
def ask_ai( prompt ):
    print( prompt )
    documents = SimpleDirectoryReader("data").load_data()
    index = GPTSimpleVectorIndex.from_documents( documents )

    response = index.query( prompt )
    print(  response )
    return  response.response

What can I do to make it print/return the response for the API call in the same way that it does for the CLI?

I have tried:

• async/await. This returns an error. TypeError: Object of type coroutine is not JSON serializable
• adding a second function with async await applied that returns the query response to ask_ai which then returns it to the requester but this results in the same type error
• printing/returning as string str(response)
• returning as json

I was hoping to have the code print and return the expected response to index.query(prompt)