How to format Open AI JSON data using text to structured data into separate parameters and data?

[chickenwingalligator]

I’m using Open AI with the transform text to structured data module to parse CV/resume data from a file on One Drive.

It’s been okay some of the time but I’m getting the following issues

1. Occasionally it’ll parse the structured data well as per the below sample format at the bottom of the post however sometimes it will just return the name of the file or the file URL. Despite not changing the description or prompt.

2. Secondly when I get the structured data it is outputted as one bundle so all of the sample format would be one singular output. However, with another scenario built which parses emails it worked perfectly. Due to the fact I added data definitions for around 10 lots of data I needed. This then returned the below summary data which was great as it enabled me to then use specific bits of data like just the first name “John” for example.

3. As Resumes/CV’s could have endless amounts of different data definitions and outputted structured data for employment history and education. Is there a way of getting the module to automatically define the definitions based on the JSON data it’s returned? Seeing as it’s already picked up that Name is the parameter and John Smith is the data to return?

Summary Data:

First Name: (array)
Output 1. John

Surname: (array)
Output 1. Smith

Sample Format:

{
“name”: “John Smith”,
“location”: “England, United Kingdom”,
“mobile”: “+4400000000”,
“email”: “Sample@yahoo.com”,
“personal_profile”: {
“education”: [
{
“degree”: “MSc in Project Management”,
“institution”: “University of Life”,
“years”: “1901 – 1903”
},
work_experience": [
{
“position”: “Worker”,
“company”: “Employer”,
“duration”: “Sep 1905 till present”
},
{
“position”: “Worker”,
“company”: "Employer ",
“duration”: “Oct 2022- June 2023”

[Clayton_Prickett]

Did you ever figure out a solution? I’m running into the same problem

[samliew]

Welcome to the Make community!

You’ll probably need to use the ParseJSON module to parse the JSON output of this module to variables.

For further assistance, please provide the following:

1. Screenshots of module fields and filters

Please share screenshots of relevant module fields and filters in question? It would really help other community members to see what you’re looking at.

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

2. Scenario blueprint

Please export the scenario blueprint file to allow others to view the mappings and settings. At the bottom of the scenario editor, you can click on the three dots to find the Export Blueprint menu item.

^{(Note: Exporting your scenario will not include private information or keys to your connections)}

Uploading it here will look like this:

blueprint.json (12.3 KB)

3. And most importantly, Output bundles

Please provide the output bundles of the modules by running the scenario, then click the white speech bubble on the top-right of each module and select “Download output bundles”.

A.

Save the bundle contents in your text editor as a bundle.txt file, and upload it here into this discussion thread.

Uploading it here will look like this:

bundle.txt (12.3 KB)

B.

If you are unable to upload files on this forum, alternatively you can paste the formatted output bundle in this manner:

• Either add three backticks ``` before and after the code, like this:

  ```
  <sup>input/output bundle content goes here</sup>
  ```

• Or use the format code button in the editor:
  

Providing the output bundles will allow others to replicate what is going on in the scenario even if they do not use the external service.

Following these steps will allow others to assist you here. Thanks!

samliew – request private consultation

Join the unofficial Make Discord server to chat with us!