Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
Tuple[Keywords, VectorQuery] -> ContextSubgraph
Retrieve relevant entities, relations, and text chunks matching both vector embeddings and keyword-indexed graph nodes, merging them into a unified context.
Problem it solves
Pure vector search lacks relational context, while pure graph search lacks semantic similarity matching.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.