pub fn embed_passage_with_choice(
models_dir: &Path,
text: &str,
choice: Option<LlmBackendChoice>,
) -> Result<Vec<f32>, AppError>Expand description
Embed a single passage using the LLM backend selected by the user via
--llm-backend. Routes to embed_with_fallback so failures fall
through to the next backend in the chain before giving up.
When choice is None (e.g. a sub-command that does not yet
expose the flag), behaviour matches embed_passage_local — the
active embedder from LlmEmbedding::detect_available decides the
backend.