Bug: Custom Endpoint Validation Breaks Feature Support

[duncangrubbs]

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]

Thanks for reporting this! Looking into it.