use Anh Vu's prompting to develop structured metadata about Bioconductor packages, targeting EDAM ontology and bio.tools schema

Usage

curate_bioc(
  packageName = "chromVAR",
  devurl =
    "https://raw.githubusercontent.com/GreenleafLab/chromVAR/refs/heads/master/README.md",
  model = "claude-sonnet-4-5",
  provider = "anthropic"
)

Arguments

packageName: character(1) a Bioconductor software package name, its release landing page will be scraped
devurl: character(1) a URL for doc originating from the developer
model: character(1) model identifier for the selected provider; defaults to "claude-sonnet-4-5" (Anthropic)
provider: character(1) LLM provider for the Python path; defaults to "anthropic". The value of the corresponding environment variable (see llm_env_var) is used as the API key and the function stops with an informative error if the variable is not set.

Value

two python dicts, base_final and edam_processed

Note

Schema completion is done with temperature set to 0.0; see edamize function for more flexibility.

Examples

if (interactive()) {
  # ANTHROPIC_API_KEY must be set for the default provider
  lk = curate_bioc()
  str(lk)
}