Article Source

• Awesome Vector Database

Awesome Vector Database

A curated list of awesome works related to high dimensional structure/vector search & database

Services

• Google Vector Search (Vertex AI)
• Pinecone
• Weaviate [Beginner Guide]
• Vespa
• txtai
• marqo
• cohere
• vectara

Libraries & Engines

Multidimensional data / Vectors

• Faiss
• Typesense
• Qdrant
  • Video tutorial, Notebook
• annoy
• NGT
• pgvector
• Chroma
• LlamaIndex
• vectordb
• jvector
• RAFT
• Vald
• Voyager
• tinyvector

Texts

• OpenSearch
• PISA
• Tantivy
• sonic

Others

• SimSIMD: Efficient Alternative to scipy.spatial.distance and numpy.inner

Benchmarks & Databases

• ANN Benchmarks [Paper].
• Billion-scale ANNS Benchmarks
• BEIR

📚 Books

• Foundations of Multidimensional and Metric Data Structures
• Introduction to Information Retrieval
• Deep Learning for Search

Conferences & Workshops

• VLDB
• Tutorial:
  • New Trends in High-D Vector Similarity Search [slides, video, paper]
• Image Retrieval in the Wild (CVPR20) [Video]
• Haystack
• Neural Search In Action
• ACM MM 2020: Effective and Efficient: Toward Open-world Instance Re-identification
  • Billion-scale Approximate Nearest Neighbor Search: [Slides, Video]
  • Is instance search a solved problem? [Slides, Video]
• Retrieval Augmented Generation and Vespa [Slides]

  Courses

• Long Term Memory in AI - Vector Search and Databases (COS 495 - Princeton) [Class Notes]

Publications

Survey

• Pan, James Jie, Jianguo Wang, and Guoliang Li. “Survey of Vector Database Management Systems.” arXiv preprint arXiv:2310.14021 (2023). [Paper]
• Nearest neighbor search: the old, the new, and the impossible. Andoni, Alexandr. [Paper]

  Quantization

  Source: A survey of product quantization.

• PQ: Product quantization for nearest neighbor search. Jegou, Herve, Matthijs Douze, and Cordelia Schmid. [Paper, Code, Julia Code, nanopq]
• k-selection on GPU: Billion-scale similarity search with gpus. Johnson, Jeff, Matthijs Douze, and Hervé Jégou [Paper, Code]
• A survey of product quantization. Matsui, Yusuke, Yusuke Uchida, Hervé Jégou, and Shin’ichi Satoh [Paper]
• OPQ: Optimized Product Quantization. Ge, Tiezheng, Kaiming He, Qifa Ke, and Jian Sun [Homepage, Paper, Code, nanopq]
• Quicker adc: Unlocking the hidden potential of product quantization with simd. André, Fabien, Anne-Marie Kermarrec, and Nicolas Le Scouarnec [Paper, Code]
  • Accelerated nearest neighbor search with quick adc. André, Fabien, Anne-Marie Kermarrec, and Nicolas Le Scouarnec [Paper].
  • Cache locality is not enough: High-performance nearest neighbor search with product quantization fast scan. Fabien André, Anne-Marie Kermarrec, Nicolas Le Scouarnec [Paper]
• ScaNN: Accelerating Large-Scale Inference with Anisotropic Vector Quantization. Guo, Ruiqi, Philip Sun, Erik Lindgren, Quan Geng, David Simcha, Felix Chern, and Sanjiv Kumar [Paper, Python/C++ Inference, Julia Training/Inference]
• The inverted multi-index. Babenko, Artem, and Victor Lempitsky [Paper, Code]
• Are We There Yet? Product Quantization and its Hardware Acceleration. Fernandez-Marques, Javier, Ahmed F. AbouElhamayed, Nicholas D. Lane, and Mohamed S. Abdelfattah. [Paper]
• LibVQ: A Toolkit for Optimizing Vector Quantization and Efficient Neural Retrieval. Li, Chaofan, Zheng Liu, Shitao Xiao, Yingxia Shao, Defu Lian, and Zhao Cao. [Paper, Code]

Graph-based Methods

• A comprehensive survey and experimental comparison of graph-based approximate nearest neighbor search. Wang, Mengzhao, Xiaoliang Xu, Qiang Yue, and Yuxiang Wang. [Paper, Code]
• HNSW: Efficient and robust approximate nearest neighbor search using hierarchical navigable small world graphs. Malkov, Yu A., and Dmitry A. Yashunin. [Paper, Code], Rust Version
• Scaling Graph-Based ANNS Algorithms to Billion-Size Datasets: A Comparative Analysis. Dobson, Magdalen, Zheqi Shen, Guy E. Blelloch, Laxman Dhulipala, Yan Gu, Harsha Vardhan Simhadri, and Yihan Sun. [Paper]
• FINGER: Fast Inference for Graph-based Approximate Nearest Neighbor Search. Chen, Patrick, Wei-Cheng Chang, Jyun-Yu Jiang, Hsiang-Fu Yu, Inderjit Dhillon, and Cho-Jui Hsieh [Paper, Video]
• NSG : Navigating Spread-out Graph For Approximate Nearest Neighbor Search. Fu, Cong, Chao Xiang, Changxu Wang, and Deng Cai. [Paper, Code]
• EFANNA : Extremely Fast Approximate Nearest Neighbor Search Algorithm Based on kNN Graph. Cong Fu, Deng Cai. [Paper, Code]

Hashing

• Awesome Papers on Learning to Hash
• A survey on learning to hash. Wang, Jingdong, Ting Zhang, Nicu Sebe, and Heng Tao Shen [Paper]
• A survey on deep hashing methods. Luo, Xiao, Haixin Wang, Daqing Wu, Chong Chen, Minghua Deng, Jianqiang Huang, and Xian-Sheng Hua. [Paper]
• Iterative quantization: A procrustean approach to learning binary codes for large-scale image retrieval. Gong, Yunchao, Svetlana Lazebnik, Albert Gordo, and Florent Perronnin [Paper, Python code, Matlab code]

Evaluation & Metrics

• Which BM25 do you mean? A large-scale reproducibility study of scoring variants. Kamphuis, Chris, Arjen P. de Vries, Leonid Boytsov, and Jimmy Lin [Paper]

📰 Articles & Talks

• What is a Vector Database? [Article]
• Vector databases (Part 1): What makes each one different?
• eBay’s Blazingly Fast Billion-Scale Vector Similarity Engine [Article]
• Computer Vision Meetup: Computer Vision Applications at Scale with Vector Databases [Video]
• How to choose your vector database in 2023?
• Do we really need a specialized vector database?
• Vector database is not a separate database category
• Vector Databases: A First-Principles Approach