A list of papers in the field of approximate nearest neighbor search on high-dimensional vectors.

Navigating Spreading-out Graph For Approximate Nearest Neighbor Search

[SIGMOD 2025] Practical and Asymptotically Optimal Quantization of High-Dimensional Vectors in Euclidean Space for Approximate Nearest Neighbor Search

vsag is a vector indexing library used for similarity search.

This is the source code of the method proposed in paper: Subspace Collision: An Efficient and Accurate Framework for High-dimensional Approximate Nearest Neighbor Search (accepted by SIGMOD 2025).

AlayaLite – A Fast, Flexible Vector Database for Everyone.

Starter code for working with the YouTube-8M dataset.

[SIGMOD 2024] RaBitQ: Quantizing High-Dimensional Vectors with a Theoretical Error Bound for Approximate Nearest Neighbor Search

BigVectorBench advances vector database benchmarking by defining and evaluating the embedding performance of heterogeneous data and abstracting compound queries, which can be multimodal or single-m…

Fast Open-Source Search & Clustering engine × for Vectors & 🔜 Strings × in C++, C, Python, JavaScript, Rust, Java, Objective-C, Swift, C#, GoLang, and Wolfram 🔍

Source code for "Empowering High-Dimensional Multi-Vector Search"

⚡ Faster vector search with PDX: A vertical data layout for vectors

DumpyOS: A Data-Adaptive Multi-ary Index for Scalable Data Series Similarity Search (VLDB Journal under review)

📚 Awesome papers and technical blogs on vector DB (database), semantic-based vector search or approximate nearest neighbor search (ANN Search, ANNS). Vector search is the key component of large-sca…

cuVS - a library for vector search and clustering on the GPU

Framework for evaluating ANNS algorithms on billion scale datasets.

VLDB 2024 paper repo. RoarGraph: A Projected Bipartite Graph for Efficient Cross-Modal Approximate Nearest Neighbor Search

Boosting Accuracy and Efficiency for Vector Retrieval with Local Scaling Graph

A lightweight, user-friendly data-plane for LLM training.

A new query hardness measure for graph-based ANN indexes. Build unbiased workloads with this hardness to see the actual performance of your ANN indexes.

Source code for the paper: "Accelerating Graph Indexing for ANNS on Modern CPUs"

OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent features for training and inference.

Learning-based Approximate k-NN Search in Graph Databases

Vector search engine inside Milvus, integrating FAISS, HNSW, DiskANN.

Official implementation for paper "Navigating Labels and Vectors: A Unified Approach to Filtered Approximate Nearest Neighbor Search"