How to send image URLs one by one from Google Sheets to OpenAI in Make.com

[Welex]

Hello,

I am trying to create a scenario in Make.com where I take multiple image URLs from a single row in Google Sheets and send them one by one to OpenAI (ChatGPT) for image description generation.

Current setup:

1. Google Sheets → Watch Rows (retrieves a row with multiple image URLs in separate columns: A3, B3, C3, etc.).
2. Set Variable (stores the URLs as an array).
3. Iterator (splits the array into individual URLs).
4. OpenAI → ChatGPT (analyzes the image and generates a description).
5. Array Aggregator (combines all responses into a single text).
6. WordPress → Create Post (publishes the article).

Issue:

• Right now, all URLs get sent to OpenAI at once, instead of one by one through the Iterator.
• I need to ensure that OpenAI receives only one image URL per request, generates a description, and then moves on to the next one.
• The final result should be a structured blog post containing all descriptions.

Question:

How do I correctly configure Make.com to ensure that OpenAI processes one image URL at a time instead of sending them all at once?

P.S: my scheme is too big because I send to each openai module 5 links at a time, if I send more - it refuses to write a big article. Each module has promt for developer and for user, which increases token consumption. Maybe somehow I can shorten the script by using Assistant so that I don’t have to send the promt repeatedly in each module (it’s the same, only the links to the photo are changed). ?

Thank you!

[samliew]

Welcome to the Make community!

Your screenshot is too small, and you did not take a screenshot of the scenario execution (with white speech bubbles above each module).

To allow others to assist you with your scenario, please provide the following:

1. Relevant Screenshots

Could you please share screenshots of your scenario? Also include screenshots of any error messages, module configuration fields, and any filter settings. We need to see what you’re working with to give you the best advice.

You can upload images here using the Upload icon in the text editor:

2. Scenario Blueprint

Please export the scenario blueprint. Providing your scenario blueprint file will allow others to quickly recreate and see how you have set up the mappings in each module, and also allows us take screenshots or provide module exports of any solutions we have for you in return - this would greatly benefit you in implementing our suggestions as you can simply paste module exports back into your scenario editor!

To export your scenario blueprint, click the three dots at the bottom of the editor then choose ‘Export Blueprint’.

You can upload the file here by clicking on this button:

3. Output Bundles of Modules

Please provide the output bundles of each of the relevant modules by running the scenario (you can also get this without re-running your scenario from the History tab).

Click on the white speech bubbles on the top-right of each module and select “Download input/output bundles”.

A. Upload as a Text File

Save each bundle contents in a plain text editor (without formatting) as a bundle.txt file.

You can upload the file here by clicking on this button:

B. Insert as Formatted Code Block

If you are unable to upload files on this forum, alternatively you can paste the formatted bundles.
These are the two ways to format text so that it won’t be modified by the forum:

• Method 1: Type code block manually

  Add three backticks ``` before and after the content/bundle, like this:

  ```
  <sup>content goes here</sup>
  ```

• Method 2. Highlight and click the format button in the editor

  

Providing the input/output bundles will allow others to replicate what is going on in the scenario, especially if there are complex data structures (nested arrays and collections) or if external services are involved.

Sharing these details will make it easier for others to assist you.