Configure Triton for selected embedding model

[EndlessReform]

User Story:

As a developer, I want to reconfigure Nvidia Triton to work with the embedding model I select, so that I can efficiently serve my model.
Acceptance Criteria:

Select the appropriate embedding model.
Update the Triton configuration to include this model.
Verify that the model is correctly loaded into Triton and perform a sample inference to confirm.

Definition of Done:

Triton configuration updated.
Model successfully loaded and sample inference complete.