This topic was automatically generated from Slack. You can find the original thread here.
Has anyone else got the following error when trying to use GPT-4o?
"AxiosError - Request failed with status code 400
{“error”:{“message”:“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.",“type”:“invalid_request_error”,“param”:“model”,“code”:"unsuppor”
I haven’t seen that specifically, but I know you need to include this header to use v2 of the Assistants API:
"OpenAI-Beta": "assistants=v2"
If you’re using one of our built-in components, there will be some changes to those soon, including using v2 of the Assistants API. OpenAI Improvements by michelle0927 · Pull Request #11930 · PipedreamHQ/pipedream · GitHub
Yes I am using your built in components. Let me know when they release and I will try them as 4o is much faster and cheaper then 4-turbo
These have been updated - let us know what you think! We also refactored a lot of our components related to the Assistants API, with a new “Chat with Assistant” action as well.
Wow! That has just made everything so so simple!! Thank you… all working and I can progress with my project!
Loving the “chat with assistant”