Issues with GPT-4o Integration in Make

Hi @vendy. Is there any update on this? How much longer? It’s been a while. Many thanks.

3 Likes

Hi Vendy, really appriciate the update. I am struggling to understand if your devs are on vacation or if they are being hired just now as it has been a month since 4o release. (read as funny pinch)

Please let me know if it will be done in a day, week, month. I love your product, however this is headache and I need to either work on my app or reschedule work for my team for different project. Thank you in advance for sharing your timeline.

3 Likes

@Michaela and @vendy.
Would be great to get a timeline on this please? It’s a fairly simple process to upgrade so not sure why it is taking so long. Please let us know. Many thanks.

2 Likes

Is this being worked on at all? It is far too costly to stay on gpt-4-turbo. I simply can not stay with make if gpt-4o is not implemented immediately.

1 Like

Hey @here :wave:

I’m sorry for all the inconvenience that this has caused you.

Our devs are intensely working and the update will be released in the next couple of days. I’ll come back to this thread as soon as it’s out.

Thank you for your support and patience. :pray:

3 Likes

I’ve noticed my existing assistants are now flagged as “Deprecated” and a quick test adding a new module seems to be working with GPT-4o, have you just released an updated version?

1 Like

Just to confirm I’ve updated all my modules to the new version and Assistants are now working correctly with GPT-4o. The old OpenAI (v1 API) module is deprecated so you do have to change all your OpenAI modules over to the new version to get it working.

I am going to try this out now - I do not see deprecated as you do. So they must be phasing a roll out or something. My assistants don’t look any different in scenario editor.

This is now working! I am over the moon! Thank you. :smiley:

The message and assistant using GPT-4.0 are now working for me. Is there a tutorial or can anyone help with making it remember conversations with specific users?

I built a chatbot with Go High Level that sends a webhook to my GPT-4.o assistant and updates a contact, triggering an automation to reply via live chat.

However, it won’t remember the previous messages, making it less useful for conversational purposes. Any solutions or pointers? Thank you.

Hello everyone @here

I see you’ve already discovered the news, but I still wanted to let you know that our OpenAI modules are now compatible with GPT-4o! :tada:

You can find it readily available in the ‘Create a Completion’ module. If you’re using the ‘Message an Assistant’ module instead, please update the module in your scenarios.

Thank you for your patience, and enjoy exploring the new capabilities!

4 Likes

“you do have to change all your OpenAI modules over to the new version to get it working.”

is this true? I have to delete all openAI modules and replace them? And then update all the modules down the flow that reference the previously deleted openAI module?

Yes, this is how module upgrades work in Make. You can try using the Make API modules to update all instances of the module in all your scenarios.

samliewrequest private consultation

Join the unofficial Make Discord server to chat with other makers!

1 Like

When I select “Create a prompt completion” as the “Method”, I don’t see GPT-4o in the menu options. Is this an error or am I missing something?

Select method is incorrect, you want "Create a Chat Completion (GPT Models).

For some reason, the new “Message an Assistant” module takes ages to load and is a problem when I’m trying to copy data from the old module into the new, it takes far too long to load the new module… this seems to be a bug is it something you have previously noticed?

I choosed " Create a Chat Completion (GPT Models)" and still can’t see GPT 4o ( and I have GPT Plus plan). Any clue to solve the problem ?