What is the output of running the following commands in a rails console?
strategy = DiscourseAi::Embeddings::Strategies::Truncation.new
vector_rep = DiscourseAi::Embeddings::VectorRepresentations::Base.current_representation(strategy)
vector_rep.vector_from("test")
Also, our API is designed to work against someone running GitHub - huggingface/text-embeddings-inference: A blazing fast inference solution for text embeddings models themselves per the documentation so it’s possible that it doesn’t work against the hosted version.
If you provide the backtrace we can look into making it work.