Skip to contents

Sends a compact, source-free summary of the score's features to a local LLM (via ellmer's Ollama backend) and returns a short prose "reading" of why the image and music turned out as they did. Optional, non-deterministic, and never part of the core mapping.

Usage

syn_interpret(
  score,
  model = .DEFAULT_LLM_MODEL,
  ...,
  call = rlang::caller_env()
)

Arguments

score

A prosody_score from syn_score().

model

Model name. Default "mistral-small" (local Ollama).

...

Passed to the underlying ellmer chat call.

call

The calling environment, for error reporting. Experts only.

Value

A character string. Requires ellmer and a reachable backend.

Examples

if (FALSE) { # \dontrun{
# Not run: needs the ellmer package and a running local Ollama server
# with the model available.
score <- syn_score(syn_read_text(syn_example_text("en"), lang = "en"))
syn_interpret(score)
} # }