Collected sources and patterns will appear here. Add from search or the patterns library.
VectorQuery -> List<DocumentChunk>
Query a vector index with a text embedding to retrieve the top-K most semantically similar document chunks.
Problem it solves
Retrieving relevant context for RAG requires semantic rather than exact-match keyword searching.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.