GPT-4o Assistant Connection in Make Workflows - Error. [400]

How To
,
1

Hi Makers,

In an effort to update the GPT Assistants in my MAKE workflows, I am receiving a [400] error stating ‘gpt-4o’ cannot be used with the Assistants API in v1.

When on the GPT assistants side, the playground interface, the API is at the latest and should be able to be called within the workflow.

Here is the error

The operation failed with an error. [400] The requested model ‘gpt-4o’ cannot be used with the Assistants API in v1. Follow the migration guide to upgrade to v2: https://platform.openai.com/docs/assistants/migration

Has anyone fixed this?

Cheers

2

Welcome to the Make community!

GPT-4o is still not available for use with Assistants in Make yet.

samliew – request private consultation

Join the unofficial Make Discord server to chat with us!

5 Likes
3

Thanks for the quick heads up Samliew :slight_smile:

2 Likes
4

It looks like the HTTP request just needs to be updated to post to the V2 URL at https://api.openai.com/v2/assistant

2 Likes
5

That’s a great idea! I’m sure others would agree that this is a nice feature to have.

You can submit this suggestion to the Idea exchange, under App improvements.

Don’t forget to search for it first, just in case someone already suggested it, so that you don’t end up creating a duplicate.
Screenshot_2024-01-17_130153

Don’t forget to upvote the feature request so that it helps make support prioritise the feature first!

samliew – request private consultation

Join the unofficial Make Discord server to chat with us!

3 Likes
6

Does this mean that once the Make module is updated, we will need to go in and manually change all the “Message an Assistant” modules in all our Make automations?

Also, it seems this is taking quite a while to be updated… should we expect to have to wait a week (weeks?) every time OpenAI updates their model before being able to use them in our Make automations?

7

OpenAI did not just update their model, but changed the way external servers connect and make requests to it via the API.

So, it takes times to update and test the new changes to the modules.

2 Likes
8

This needs adding asap - i get that it can take time but not this long and the demand is there - no-one wants to implement work arounds to make it happen - chop chop Make.com

9

Thanks. Will keep an eye on the thread.

10

Thanks for the heads up. Looking fwd to an update soon.

11

Hello everyone @here

I just want to confirm that this is unfortunately a known issue of the “4o” model. Our dev team is aware of this and is working on updating our ChatGPT module to the latest API version.

We will let you know once the update is rolled out.

Thank you very much for your patience and understanding. :pray:

As a temporary workaround, you could use an older assistant model or use the “Make an API Call” module with the custom API call to OpenAI API with the “OpenAI-Beta: assistants=v2” header.
The below guide might provide general help on how to use the “Make an API Call” modules.

:arrow_right: How to make an API call: tutorial

4 Likes
12

Hi everyone, we updated the Assistant Module inside makemarket to support both GPT-4o and functions. Check this post for more details: Open AI Assistant Module with GPT-4o and functions

13

Hi its been 4 days already. How far?

14

Yeah, burn module executions while polling for my run status. Not a good solution.

15

Any ETA when this will work?

16

I am trying to use the ^make an API callˆ option to access my assistant (already running 4o). What should I add to the URL field? What about header key and volume? Is the body field just my message to my assistant? I tried looking at the URL mentioned above but did not find any answers. Can anyone help? Thanks!

17

Welcome to the Make community!

It should be as simple as this

Screenshot_2024-05-28_091827

For more information, see https://platform.openai.com/docs/assistants/migration

samliew – request private consultation

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

1 Like
20

Hello everyone @here

I’m happy 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!

3 Likes