Repeating OpenAI request to generate similar results on same row of Google Sheet

I have a Google sheet with multiple rows of products for ecomm store. Column E has a long description of the product. I would like to run OpenAI multiple times on each row, each time referencing Column E to output to F, G, H, and Column I. Each description will vary in creativity and length, but I think that once I open the API request, it’s not closing and i’m unable to do the second leg of the repeater. It will output the first generated description, then fail saying that the module that was just used successfully the first time isn’t available [Referenced module 'OpenAI (ChatGPT, Whisper, DALL-E) - Create a Completion (GPT-3, GPT-3.5, GPT-4)' [2] is not accessible.](https://us1.make.com/#).

I tried using multiple User Messages and mapping is still a little unclear.

My question is, how can i iterate over each row on the Google sheet, have OpenAI generate 4 different / modified descriptions based on Column E, and paste each result back to Column F, G, H, and I of the same row in the sheet? Thank you!

I know this is incorrect, but i’ve tried so many different ways. This is where i’m at now and still not having any luck.

How do i get each row from a Google Sheet, tell openAI to take Column E, reword it and save it to Column F, G, H, I, as different lengths and for different purposes?

I would like to prompt it to take the long description of the product and create something like META description, Page Title, Short Description, and Catalog Description.

Welcome to the Make community!

You can remove the router and chain the AI modules, then perform a single “Update a row” at the end.

Why do you need a repeater there? I suggest you delete the repeater if you don’t know what it does.

samliewrequest private consultation

Join the unofficial Make Discord server to chat with other makers!

2 Likes

Thank you! I was trying to overcomplicate it.

All it needed was a linear path. It works! I appreciate your assistance.

1 Like

No problem, glad I could help!

1. If you have a new question in the future, please start a new thread. This makes it easier for others with the same problem to search for the answers to specific questions, and you are more likely to receive help since newer questions are monitored closely.

2. The Make Community guidelines encourages users to try to mark helpful replies as solutions to help keep the Community organized.

This marks the topic as solved, so that:

  • others can save time when catching up with the latest activity here, and
  • allows others to quickly jump to the solution if they come across the same problem

To do this, simply click the checkbox at the bottom of the post that answers your question:
Screenshot_2023-10-04_161049

3. Don’t forget to like and bookmark this topic so you can get back to it easily in future!

Here are some useful links and guides you can use to learn more on how to use the Make platform, apps, and app modules. I found these useful when I was learning Make, and hope they might benefit you too —

General

Help Center Basics

Articles & Videos

Partner & Custom Apps

samliewrequest private consultation

Join the unofficial Make Discord server to chat with other makers!

2 Likes

Just a suggestion, unless you are passing completely different prompts, can you try asking OpenAI for more than one response? You can save operations on Make that way?

2 Likes

I was unaware of that setting. I’ll have to test it out. The OpenAI system prompt is the same (written in the same tone of voice for example), but the user prompts vary slightly in length and purpose. Aside from the length, some of the product descriptions have hyperlinks embedded in them to other similar products. These html tags get stripped out for the shorter iterations.

In order to do it this way, I assume I would need to parse the data/response that is returned and break it up to put into each respective cell in the sheet.

This makes much more sense than the way i have it currently as i’m sure it would be much more efficient!