Hello! I am fairly new to Make.com and I’ve been using monday to heighten our workflow. For aggregation of data I am extremely new, and I’m not even sure its exactly what I am looking for.
My use case is that multiple files are uploaded to chatgpt with a custom API token- they’re analyzed and exported as “True” or “False” text results. If ANY of these results come back false it sends it to one specific monday.com command- while if ALL of them are True they are sent to a different command.
I’m having trouble with filters/aggregating the text so it’s not separate operations. Sometimes the files uploaded might only be one, but it also may be 10 files. Here’s the visualization of my scenario right now.
Any guidance in the correct direction is appreciated! I’ve spent hours reading documentation but can’t seem to find anything with a straightforward answer in terms I understand 
would love the help!
1 Like
Welcome to the Make community!
You simply need to set the Source Module field of the aggregator to the Iterator module, and NOT the OpenAI module.
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
2 Likes
This was the easiest solution ever- and now the iterator makes a LOT more sense. Thank you!
1 Like
Follow up question since I’m in hopes of minimizing the operations usage- I don’t NEED the Monday.com “download file” to upload to OpenAi - I’ve noticed I can directly upload the “public URL” to which it works successfully for the single URL. The problem I am running into is my iterator is inputting a bundle, with an array, but only 1 collection from an array that actually has 3 collections (each with a file link that I want to make a bundle). How might I be going wrong with the parsing of this array? I’ve changed the monday.com module to a “get item” which gives me the array of public URLs.
And I’m starting to wonder if there’s a way the GPT can handle all of the file links at once for one output so 1.) doesn’t cost as many tokens, and 2.) Loses the need for a aggregator since it would naturally only output one response right?
I’d love your thoughts. I’m working diligently on the Make Academy! Thanks for this resource.
I’m thinking a more simple version can look like this;
No problem, glad I could help!
1. If anyone has 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.
For the OpenAI files field, you can try this trick with an Iterator-Aggregator on the Assets array.
Aggregators
Every result (item/record) from iterator/list/search/match modules will output a bundle. This can result in multiple bundles, which then trigger multiple operations in future modules (one operation per bundle). To “combine” multiple bundles into a single variable, you’ll need to use an aggregator of some sort.
Aggregators are modules that accumulate multiple bundles into one single bundle. An example of a commonly-used aggregator module is the Array aggregator module.
Array Aggregator – mapping multiple bundles into a complex field
The Array Aggregator module is very powerful because it allows you to build a complex array of collections for a later module’s field to map multiple items (collections) to it.
This is done using the “Target structure type” of an Array Aggregator module.
Here is an example:
As you can see, the “Map” toggle on complex fields are used when you have an array. You can easily build an array variable to map to a future module’s field, by using an Array Aggregator module and select the “Target Structure Type” as the future module’s field you have mapped the array into.
Hope this helps! Let me know if there are any further questions or issues.
— @samliew
P.S.: Investing some effort into the Make Academy will save you lots of time and frustration using Make.
