Efficient dense vector search boosts multimodal querying in knowledge graphs
Efficient Dense Vector Search within Knowledge Graph Content Embeddings
Databases
Summary
Searching large knowledge graphs is important for finding facts and reasoning, but it can be slow with complex data like vectors from language or images. The authors improved an existing system by adding fast methods to search dense vectors inside these graphs, making it possible to quickly combine text, images, and structured data in queries. They also created new tests showing their approach can be tens to hundreds of times faster than before. Their work helps connect traditional knowledge bases with modern AI data for better and faster answers.
What this means in practice
- •For knowledge base engineers: Run fast similarity searches using text and image vectors directly inside knowledge graph queries for richer data retrieval.
- •For enterprise search developers: Build search tools that combine structured facts with AI-generated embeddings for more accurate and multimodal query results.
Authors
Benedikt Kantz, Tobias Schreck, Gianmaria Silvello
Abstract
Knowledge graphs are a core component of today's knowledge infrastructure, supporting reasoning and anchoring knowledge systems to verifiable facts. RDF stores and SPARQL engines fulfill this function, enabling a range of retrieval and inference tasks on structured knowledge. Coupling them with Language Models (LMs) extends RAG toward neurosymbolic reasoning, where structured queries gate or re-rank generative outputs. This line of reasoning requires that SPARQL evaluation natively support tensor operations on dense embeddings, enabling multimodal querying and learned similarity-based ranking to be expressed together with graph-structural constraints. This approach is feasible only if the engine can efficiently perform dense vector search. We present QLever-Unified Indexed Vector Embedding Retrieval (QUIVER), an extension to QLever that adds native support for dense vector retrieval within RDF knowledge graphs. It implements three optimizations: engine-level registration of tensor functions, vocabulary-time parsing of JSON-encoded vectors, and a virtual SERVICE that exposes a vector index inside the query. We propose two new benchmarks: an extension of Berlin Sparql Benchmark (BSBM) with text embeddings and an extension of DBpedia with image embeddings. Against the baselines, vocabulary-time parsing alone yields median speedups of up to 41.9x on BSBM and 20x on DBpedia for single-type ranking; adding an approximate nearest-neighbor index yields speedups of 355x on BSBM and 97.8x on DBpedia. The index further makes cross-modal vector joins on DBpedia feasible in seconds, whereas all non-indexed configurations time out.