Skip to main content
Solved

Error on Tutorial 'Using the OpenAICompletionsConnector'


galigis
Enthusiast
Forum|alt.badge.img+20

Hi All,

Has anyone tried to follow the steps for ‘Using the OpenAICompletionsConnector’ tutorial? 

Link here: https://support.safe.com/hc/en-us/articles/25407431621517-Using-the-OpenAICompletionsConnector

I have used the FMWT attached to the tutorial but I have the following error when trying to run it:

 

A few considerations below:

  • I’m using FME(R) 2024.2.4.0 (20250318 - Build 24831 - WIN64)
  • I have created my own API Key 

Thanks

Best answer by virtualcitymatt

virtualcitymatt wrote:

without looking into it too much my guess is that it’s probably an outdated  model being used in the requets. Teh default model used in the transformer is: text-davinci-003

I can’t see this listed in the available models on OpenAI’s API page. Try switching it out for ‘gpt-4o-mini’

Note: you should be able to look at the feature coming out of the rejected port for the response from OpenAI - that should give you more info

ok yeah I just tested it and confirmed the issue:

{
    "error": {
        "message": "The model `text-davinci-003` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations",
        "type": "invalid_request_error",
        "param": null,
        "code": "model_not_found"
    }
}

“gpt-4o-mini” works

View original
Did this help you find an answer to your question?

3 replies

virtualcitymatt
Celebrity
Forum|alt.badge.img+38

without looking into it too much my guess is that it’s probably an outdated  model being used in the requets. Teh default model used in the transformer is: text-davinci-003

I can’t see this listed in the available models on OpenAI’s API page. Try switching it out for ‘gpt-4o-mini’

Note: you should be able to look at the feature coming out of the rejected port for the response from OpenAI - that should give you more info


virtualcitymatt
Celebrity
Forum|alt.badge.img+38
virtualcitymatt wrote:

without looking into it too much my guess is that it’s probably an outdated  model being used in the requets. Teh default model used in the transformer is: text-davinci-003

I can’t see this listed in the available models on OpenAI’s API page. Try switching it out for ‘gpt-4o-mini’

Note: you should be able to look at the feature coming out of the rejected port for the response from OpenAI - that should give you more info

ok yeah I just tested it and confirmed the issue:

{
    "error": {
        "message": "The model `text-davinci-003` has been deprecated, learn more here: https://platform.openai.com/docs/deprecations",
        "type": "invalid_request_error",
        "param": null,
        "code": "model_not_found"
    }
}

“gpt-4o-mini” works


galigis
Enthusiast
Forum|alt.badge.img+20
  • Author
  • Enthusiast
  • June 6, 2025

Thanks ​@virtualcitymatt I have followed your suggestion and seems working,

 

I have also had to upgrade my OpenAI account and upgrade the plan as well as add some credtis to get it working,

 

cheers


Cookie policy

We use cookies to enhance and personalize your experience. If you accept you agree to our full cookie policy. Learn more about our cookies.

 
Cookie settings