New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[FEATURE] Support for Azure OpenAI Fine-Tuned Models #3894

Open

alexh2b opened this issue Jan 18, 2025 · 2 comments

Labels

question

alexh2b commented Jan 18, 2025

Currently, the endpoint is hard-coded:
https://${azureOpenAIApiInstanceName}.openai.azure.com

This approach won't work with fine-tuned models.

Endpoints typically look like:
https://xxxxxxxxxx.services.ai.azure.com/

However, this could potentially change in the future.

It would be better to adopt a more flexible approach, allowing users to input the full URL.

Contributor

HenryHengZJ commented Jan 20, 2025

Can you try using Custom OpenAI node and use the Base Path for your fine tuned endpoint?

HenryHengZJ added the question label

Author

alexh2b commented Jan 21, 2025 •

edited

Loading

Getting:

404 Resource not found

Troubleshooting URL:
https://js.langchain.com/docs/troubleshooting/errors/MODEL_NOT_FOUND/

///

Tried as model name:

the model name as displayed in the Azure dashboard
Deployment name
gpt-4o-mini

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment