FuseRank: Filtered Vector Search in Multimodal Structured Data

Single-stage filtering in vector search offers a significant advancement over conventional two-stage metadata filtering, which tends to suffer from high latency or low recall. We introduce FuseRank – a new multimodal filtered retrieval framework based on the extended vector space model, which unifies retrieval and filtering into a single approximate nearest neighbor query. FuseRank supports numerical, categorical, binary, and spatial tabular modalities through dedicated modality vectorizers. We implement FuseRank on a well-known filterless vector database as a reproducible pre-production prototype. Experiments on two real-world datasets yield retrieval results comparable to traditional two-stage filtered search, demonstrating the feasibility of platform-independent single-stage retrieval. This enables native modality filtering across any vector database backend via dot product computation, effectively avoiding vendor lock-in and reliance on platform-specific filtering logic and syntax. FuseRank also allows flexible weighting of each modality’s contribution to the final ranking score, while remaining easy to implement and extend to other modalities.