Uses regex to find candidate email addresses, phone numbers, and monetary amounts; Jev selects the requested candidate, and code copies and normalizes the original text.
Original by TypeSafe AIExtractionTypeSafe cookbookSource reviewed
Before you dive in
What you’ll find in the original
Collect literal spans before asking which one fills a semantic role.
Copy the chosen span verbatim rather than asking a model to retype it.
Normalize phone and monetary formats with explicit locale assumptions in code.
Worth knowing
The sample money parser assumes US-style separators; the cookbook calls out other locales as a limit.