RAG and search
CASTLE: training natural language search before the first real query
Our short summary of Airbnb’s engineering write-up. The full story, with all the detail, is on their blog.
Read the full write-up on medium.com (opens in a new tab)Problem
Airbnb needed natural‑language search but had no real user queries or relevance labels to train on.
Solution
They created CASTLE, a system that synthesises realistic search queries and relevance labels from booking data, then trains a retrieval model on this joint synthetic data.
Want the architecture, code and numbers? They’re in the original post.
Read the full write-up on medium.com (opens in a new tab)
Elastic
Vespa