I’ve 3 modules, WordPress (Watch Post) → Chat-GPT (Edit) → Wordpress (Create Post).
3 inputs (Title, Excerpt, Content) are passed to GPT for edit (Translation) then new post will be created in another language. In the 3rd module, Create Post, there isn’t options of Title, Excerpt, Content to map New Post inputs with.
Welcome to the Make community!
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:
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)
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, save the bundle contents in your text editor as a bundle.txt file, and upload it here into this discussion thread.
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!
Hey @ptssw
To resolve this, you might need to:
Check the capabilities of the WordPress plugin or integration tool you are using for the"Create Post" module.
After that you see the all option like this :
Wordpress input fields work fine but with initial Wordpress inputs are feeded into Chat-GPT, they’re combined into array. From Chat-GPT to new Wordpress post, there’s no input options from Chat-GPT to multiple fields of Wordpress post creation.
The output is stored in the Choices property. While the content is a single variable, you’ll need to process the text based on how you want the title to be formatted. E.g.: If the output of GPT returns your title on the first line, you need to “split” the text into title and content.
@ptssw
According to your need i think you need 3 chatgpt module
And you will get your generated text here.
Why do we need separate GPT calls? Can’t a single request to GPT generate a post title and content at the same time?
For the excerpt, isn’t it just a shortened form of the content, which you can take the first X words of the content?
@samliew
While generating titles from Chat-GPT for content is possible, it is not considered best practice. If you choose to generate titles along with content using Chat-GPT, you can do so.
And I am just suggesting that it could be beneficial for @ptssw
In a single call, all 3 components of 1. For title
2. For content
3. For Excerpt
are combined and translated probably as array by Chat GPT. I’m struggling to break the array into 3 different component again so they can be mapped into their relevant input fields to create new post.
Hey @ptssw
Acoording to your need you can add this prompt in your chat gpt module
after that you can use this module “parse json”
and you will get output like this
I tried following but struggling to get the last image. I’m getting this “19:33
The operation failed with an error. [400] Invalid parameter: ‘response_format’ of type ‘json_object’ is not supported with this model.”.
blueprint (1).json (24.5 KB)
Click on ‘Choices,’ then go to ‘Messages,’ where you will find the content.
