by onel on 1/9/25, 4:05 PM with 5 comments
by bfeynman on 1/9/25, 4:35 PM
For LLM aspect - My take is the better approach is similar context enrichment for rag - you ask the LLM to generate a summary for a page, and that can easily be cached against a digest/hash for any code changes - and will always be up to date.
by mtrovo on 1/10/25, 5:12 PM
by PaulHoule on 1/9/25, 4:14 PM
Tests can be examples of how to do things. If examples in your documentation aren't backed by unit tests they don't work.