- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
03-12-2024 06:55 AM
Hello,
I am trying to get Chat GPT (OpenAI) integration to work on my PDI. The API yet is correct however, it keeps coming back with the error -
{
"error": {
"message": "you must provide a model parameter",
"type": "invalid_request_error",
"param": null,
"code": null
}
}
This is my current configuration, I've also tried other models such as, gpt-3.5-turbo, gpt-4 and gpt-4-turbo and getting the same result. Would appreciate it if anyone's managed to get around this?
Solved! Go to Solution.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
03-14-2024 04:05 PM
Hi, I did fix this only to be met with the max number of queries have been reached even though I’d not requested anything. As such I created a new account and BINGO!
Although content-type wasn’t the only issue, the model parameters noted on the documentation is out of date and needed to be “gpt-3.5-turbo” which unless you’re on GPT-4 so would need to be “gpt-4” or “gpt-4-turbo”.
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
03-14-2024 12:50 AM
Hi Andrew,
In the HTTP header, the content type should be in this format in the name: Content-Type.
Use 'davinci-002' as your model parameter.
The model `text-davinci-003` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations
Do change these and it should work.
Regards,
Jasmine
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
03-14-2024 04:05 PM
Hi, I did fix this only to be met with the max number of queries have been reached even though I’d not requested anything. As such I created a new account and BINGO!
Although content-type wasn’t the only issue, the model parameters noted on the documentation is out of date and needed to be “gpt-3.5-turbo” which unless you’re on GPT-4 so would need to be “gpt-4” or “gpt-4-turbo”.