DRIFT search and a knowledge graph for the AI assistant
Graph-augmented retrieval: entity extraction, community detection, global and local search, and DRIFT — a primer plus targeted follow-ups — for grounded, cited answers.
The AI assistant now builds and reasons over a knowledge graph of your content, not just a flat set of retrieved chunks.
Documents are processed into entities and relationships, deduplicated with embedding similarity so "Acme Corp" and "Acme Corporation" resolve to one node, then clustered into communities with multi-level Louvain detection. A global search summarizes across communities for broad questions; a local search traverses entity neighborhoods for specific ones; DRIFT search combines both — a primer answer plus a small number of targeted follow-up searches — for questions that need both breadth and depth.
Multi-query retrieval now fuses results from several reformulated variants of a question using reciprocal rank fusion, and the zero-hit broaden_query escalation is now a cheap, staged ladder instead of one big relaxation step. Recommendation hydration also picked up MMR diversification, so a set of recommended items is less likely to be five near-duplicates of the same product.