Hann: A Fast Approximate Nearest Neighbor Search Library for Go

Hann A fast approximate nearest neighbor search library for Go Hann is a high-performance approximate nearest neighbor search (ANN) library for Go. It provides a collection of index data structures for efficient similarity search in high-dimensional spaces. Currently, supported indexes include Hierarchical Navigable Small World (HNSW), Product Quantization Inverted File (PQIVF), and Random Projection Tree (RPT). Hann can be seen as a core component of a vector database (like Milvus, Pinecone, Weaviate, Qdrant, etc.). It can be used to add fast in-memory similarity search capabilities to your Go applications. Features Unified interface for different indexes (see core/index.go) Support for indexing and searching vectors of arbitrary dimension Fast distance computation using SIMD (AVX) instructions (see core/simd_distance.c) Support for bulk insertion, deletion, and update of vectors Support for saving indexes to disk and loading them back Indexes Index Name Space Complexity B ... Read full article.