We have a Django application for chatting.
UI: Built in HTML, CSS, JS
Backend: ChatGPT API integrated in Python using below option to get word to word responses
stream = True
The flow is as follows:
An XMLHttpRequest is triggered on a button click from JavaScript which further calls an endpoint in Django which returns a word to word response(StreamingHttpResponse) from ChatGPT the UI is also parallelly updated with word to word approach. The word to word response works fine in local.
Problem:
When we try to host it in Google App Engine Flexible or Standard it waits for the whole response rather than showing it word to word, can anyone help me out with this ?
LinkedIn
Twitter
