Open AI not seeing all JSON's results to feed

Hi everyone,

I’ve designed a scenario where, after I have a call with a client, I fill in a Jotform questionnaire with the summary of the call. Then it triggers a webhook that helps me put the answers through OpenAI to create a Google Slides proposal.

I was having trouble feeding the answers from Jotform to OpenAI, so I added a Parse Json module in between. This does work, and I can see all the clean answers in the JSON output; however, I don’t understand why when I try to connect them with OpenAI, I can only see the first one.

I’m attaching the screenshots below. I know I am doing something wrong, could you please help me with this?

Thanks so much.

Marcela

Picture with Json’s output

Picture of OpenAi trying to connect with the Json module. It shows just Last and First name when it should show all the answers above.

Picture of the entire scenario

You can use the built-in functions last to access the last item within an array variable.

e.g.:

{{ last(99.email) }}

(copy-paste the above into the field, or type it exactly as shown)

For more information, the function’s documentation can be found in the Help Centre and the “Mapping with Arrays” link below. You should also complete the tutorials in the Make Academy, especially Using get() and map() functions.

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 —

Getting Started

Help Centre Basics

Articles & Videos

Hope this helps! Let me know if there are any further questions or issues.

@samliew

Thanks Sam for the info. However that is not the problem. The issue is that when I try to connect them on OpenAI, I don’t see them in the output. Only the name and email. the rest are gone.

Do you know why this may be?

Thanks!

Please provide an example output bundle of the Jotform module 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.
Here are some ways to provide text content in a way that it won’t be modified by the forum.

  • Method 1: Type code fence manually
    Add three backticks ``` in a separate line before and after the content, like this,

    ```
    text goes here
    ```
    
  • Method 2: Highlight and click the “preformatted text” button in the editor

  • Method 3: Upload your file and share the public link
    (this method is only recommended for large files exceeding the forum upload limit)

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, and help you with mapping the raw property names from collections.

@samliew

Thanks Sam for your reply. Here’s the screenshot of the Jotform output. I have tried everything, taking the “last” from the bult-in functions, and taking the n 2, but nothing works. I just can’t take the data either from the Jotform or the JSON output. It’s not the first time I build a scenario like this, but I don’t understand why it’s giving me such trouble for the OpenAI to process the information. It just can’t see it. Can you please help me? Thanks so much.

There isn’t enough information for me to look at and advice on this issue.

If you would like further assistance, please provide the following:

1. Screenshots of scenario, the individual module fields (mappings), error messages, etc.
2. Scenario Blueprint
3. Exported JSON output bundles of the modules (not just screenshots)

Please refer to the previous post for further instructions on how to provide them.

You can also use the Hire a Pro category to request for private 1-to-1 assistance via video call/screenshare/private messaging/etc. This may help you get your issue resolved faster especially if it is urgent or contain sensitive information. It is important to post your request in the Hire a Pro category, as forum members are not allowed to advertise their services in other categories like here (even if it’s free/unpaid). Posting in the Hire a Pro category will allow other members to assist you over other forms of communication.

Alternatively, you can use the private messaging feature to directly reach out to other forum members. To do this, go to your profile, and click on the “New Message” button:


Hope this helps! Let me know if there are any further questions or issues.

@samliew