Skip to content
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.

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

Bug: Custom Endpoint Validation Breaks Feature Support #426

Closed
duncangrubbs opened this issue Jan 22, 2024 · 1 comment · Fixed by #429
Closed

Bug: Custom Endpoint Validation Breaks Feature Support #426

duncangrubbs opened this issue Jan 22, 2024 · 1 comment · Fixed by #429
Labels
bug Something isn't working feat/model Feature: models

Comments

@duncangrubbs
Copy link

In the v0.7.0 release, the following feature was added

Allow custom endpoints for all models to support usage of fine-tuned models (#390)

I am not sure what the exact specification for this feature was, and I filed an issue related to this a few months back, but I am not sure this feature works as expected. For example, the OpenAI REST model still contains this line which causes an error to be thrown if you pass an endpoint that is not in the Endpoints enum. For example, if your config looks something like

[components.llm_rel.model]
@llm_models = "spacy.GPT-4.v3"
endpoint = YOUR_CUSTOM_ENDPOINT
config = {{"temperature": 0.0}}
"""

Am I missing something about how this feature is intended to be used? Thanks! And thanks for the prompt follow-up from my previous issue!

@rmitsch rmitsch added bug Something isn't working feat/model Feature: models labels Jan 26, 2024
@rmitsch
Copy link
Collaborator

rmitsch commented Jan 26, 2024

Thanks for reporting this! Looking into it.

@rmitsch rmitsch linked a pull request Jan 26, 2024 that will close this issue
3 tasks
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working feat/model Feature: models
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants