A context layer contains text that helps a commons() agent interpret its
data source.
Usage
context_layer(files = character())Details
Files are chunked and indexed with ragnar when the agent first
searches its context. Facts that should be in every prompt belong in the
instructions passed to commons(), not here.
Examples
path <- tempfile(fileext = ".md")
writeLines("Revenue excludes tax unless stated otherwise.", path)
layer <- context_layer(files = path)
