Tag
This paper introduces LLM-Guided Graph Pruning (LGP), a framework that uses LLM reasoning to refine graph-based ANN indices (e.g., HNSW, DiskANN) by pruning low-value neighbors, addressing the geometry–semantic mismatch in how these indices are built versus evaluated, and improving end-to-end retrieval over vanilla greedy search and LLM reranking.
Turbovec, based on Google's TurboQuant algorithm, compresses 10 million vectors from 31GB to 4GB, with search speed 12-20% faster than FAISS, supports filtered search, and offers a Rust implementation with a Python package.