I’m working on a custom GPT. 1 Action, 7 endpoints.
Environment: Flask, Ngrok, SQL Server db.
Tests in Chrome browser, GPT / Builder / Preview chat.
Test runs in ChatGPT app on Android.
Workflow:
-
user upload 100 kb PDF, 1 invoice page.
-
in few seconds, ‘Starting action’ message displayed.
-
… waiting time 30-90 seconds …
-
‘GPT wants to talk to ngrok’ message displayed.
This delay is huge for processing 100 kb pdf one page invoice! It’s simple not feasible for the production stage.
Any idea what’s going on ? In my understanding, that time is consumed by the front-end (aka chat conversation interface provided by chatgpt.openai.com or ChatGPT app for android).
Any solution ?