[Bug]: Embedding error in file parsing

[RELmon25]

Is there an existing issue for the same bug?

• [X] I have checked the existing issues.

Branch name

main

Commit ID

unknown

Other environment information

macOS with chip Apple M2

Actual behavior

1. Customize user_default_llm in service_conf.yaml: factory: 'OpenAI' api_key: MY_API_KEY
2. Build Docker images and start up the server
3. Log in to RAGFlow
4. Set up knowledge base with gpt-4o as the embedding model
5. Upload file to knowledge base and start parsing

SUCCESS in parsing status but shows an embedding error:

[ERROR]Embedding error:Error code: 403 - {'error': {'message': 'You are not allowed to generate embeddings from this model', 'type': 'invalid_request_error', 'param': None, 'code': None}}

Tried again after configuring OpenAI API key on the Model Providers page. The same error happened.

Expected behavior

Succesful parsing.

Steps to reproduce

See Actual behavior.

Additional information

Error message: [ERROR]Embedding error:Error code: 403 - {'error': {'message': 'You are not allowed to generate embeddings from this model', 'type': 'invalid_request_error', 'param': None, 'code': None}}

I've verified that my OpenAI API key works and has credit.

[TeresaUscanga]

Same issue.

[euscanga-krasamo]

Updates?

[LloydNA]

yeah, same issue here :/, with M1 chip

[KevinHuSh]

gpt-4o is not a embedding model. All the non-embedding models have been filtered out in knowledge base setting.

[RELmon25]

Thanks!