Llm4sEmbeddingModel

An llm4s embedding client as a Spring AI EmbeddingModel (#2278), so a Spring AI vector store or evaluator embeds through any llm4s embedding provider.

EmbeddingModel model = new Llm4sEmbeddingModel(Llm4s.createEmbeddingClient(config).get());
float[] vector = model.embed("hello");

The request's texts are sent in one llm4s request, as documents; its options are not read (the model is the client's own). The response's metadata names the model that answered. A failure throws the LlmException the client's result holds. dimensions() is the model's declared length when its provider module lists it, and otherwise Spring AI's default, which embeds a test string.