Hi Team, curious if anyone else has this issue. I created a GPT that makes an image, and all I want to do is save it to my Google Drive.
I have gotten the file to save, but it saves it as a text file (just the file name).
I have gotten that far when testing another GPT sending to an email (create an image and send it to a draft email). In both of my instances it doesnt save the image, but instead a text file of the file name.
I am stumped… Any ideas?
How are you doing this exactly?
Creating a Custom GPT
Added the Zapier Schema first.
Then, in the custom instructions in the configure tab, adding this:
Rules:
Instructions for Zapier Custom Action:
Step 1. Tell the user you are Checking they have the Zapier AI Actions needed to complete their request by calling /list_available_actions/ to make a list: AVAILABLE ACTIONS. Given the output, check if the REQUIRED_ACTION needed is in the AVAILABLE ACTIONS and continue to step 4 if it is. If not, continue to step 2.
Step 2. If a required Action(s) is not available, send the user the Required Action(s)'s configuration link. Tell them to let you know when they’ve enabled the Zapier AI Action.
Step 3. If a user confirms they’ve configured the Required Action, continue on to step 4 with their original ask.
Step 4. Using the available_action_id (returned as the id field within the results array in the JSON response from /list_available_actions). Fill in the strings needed for the run_action operation. Use the user’s request to fill in the instructions and any other fields as needed.
REQUIRED_ACTIONS:
Save Popp E-Mail Draft
ID: 01HFBNR896022KC1A6E29FKMK2
This action can be used for saving e-mail drafts.
Google Drive Dalle
ID: 01HFCRPY4PCZQC3F9BSKC8037C
This action facilitates working with Google Drive and Dalle.
Search E-Mail
ID: 01HFCK3CJ8QYART2GZ4QXVJW9T
This action allows searching within emails.
and what is happening is sometimes it changes the Action IDs to something different when I ask them to list it.
This is the OpenAI Zapier Schema i am supposed to paste
This is my configure instructions
This is what the photo outputs to google drive as
It’s sending the URL back not the image data.
The URL is only available for about an hour, though.
On API you can ask for b64 or URL back but ChatGPT maybe only gives URL?
I’d investigate in that direction as the resulting file is just the URL…
Do you know if anyone has done this successfully yet?
You need to create an additional method in the program.
For example:
First, save an image to your local PC, then upload it from the local PC to Google Drive.
This can be programmed using TypeScript/JavaScript or any other language.
Nope - was hoping to be one of the first! Thought it was possible in these Zapier Actions…
Will have to up my knowledge to use the playground and the API… not even sure how/where to start
