Adaptive Query-Aware Hybrid Search in Vector Databases

Hybrid search, which integrates vector and structured retrieval, is essential for efficient and accurate information access over large-scale data in modern AI-based applications. We build upon HNSW, a state-of-the-art approximate nearest neighbor index for efficient hybrid search that organizes data in multi-layer prox- imity graphs. We exploit information from previously executed queries to inform new ones to start with the right foot—i.e., by selecting more effective entry points for the proximity graph ex- ploration. This strategy accelerates convergence from the earliest search steps and improves accuracy. Finally, we experimentally evaluate our approach on six diverse datasets under varying settings, demonstrating consistent improvements.