Scalable Nearest Neighbors
PulseAugur coverage of Scalable Nearest Neighbors — every cluster mentioning Scalable Nearest Neighbors across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
SOLO index offers certified recall for similarity search with reduced memory
Researchers have introduced SOLO, a novel index for approximate nearest-neighbor search in metric spaces that offers certified recall without requiring heuristic ranking. This method computes recall directly from the in…
-
Advanced RAG techniques focus on scalability, efficiency, and observability
This cluster explores advanced techniques for Retrieval-Augmented Generation (RAG) systems, moving beyond simple three-step architectures. The first article details a multi-stage RAG pipeline designed for production rea…
-
RAG Evals Flawed by Non-Deterministic Retrieval, Developer Finds
A developer encountered issues with their Retrieval-Augmented Generation (RAG) evaluation pipeline, initially suspecting the language model was degrading. However, upon closer inspection, the problem was traced to non-d…
-
Vector Search Libraries Benchmarked for Speed and Memory
A developer has benchmarked several vector search libraries, evaluating their performance across speed, memory usage, and similarity results. The tests included datasets ranging from 500 samples up to 1 million, compari…
-
IVF-TQ paper proposes calibration-free streaming vector search
A new paper introduces IVF-TQ, a novel approach to streaming vector search designed to maintain recall accuracy over time. Unlike existing methods that require frequent codebook retraining, IVF-TQ utilizes a data-indepe…
-
Eugene Yan details Mac installation of Google's ScaNN for vector search
Eugene Yan has published a guide detailing the process of installing Google's Scalable Nearest Neighbors (ScaNN) library on a Mac operating system. The guide addresses the complexities encountered during installation, p…