OpenAI - API scripts - Exceed Max script execution time limit of 30 s

[morganngraom1]

OpenAI's API for GPT-4 constantly has an over 30sec delay in responding to larger token prompts. 

This makes automation in AirTable rather useless unless you go to the trouble of building cloud functions. 

I have multiple working automation steps to categories data, create short email replies etc. But if you want to do anything real with GPT-4 it's limited by the response time. 

Question - how can I get around this? Any thoughts? 

[Bill_French]

... I'm used to consume OpenAI API always with external automation tools

Okay. Then, you need to get used to using proxies to do so. Airtable will not likely extend the 30-second timeout, so that leaves you three possible options:

1. Use Airtable's integrate AI field
2. Use OpenAI's HTTP long-connection streaming feature
3. Create a proxy that buffers your AI calls

BTW - my tests with the Airtable AI field show it is about 2.6 times faster than calling OpenAI APIs directly.

[Mario_Granero]

Than you Bill, 

I just apply to the AI beta, let's test this! And evaluate if it fit and can avoid to use n8n, the tool that i'm using.

Happy weekend

[st_phan]

I only need the script for a data migration so your tip saved my day 🎉. Thanks a lot!