Survey of Vector Database Management Systems
A comprehensive 2023 survey that systematically analyzes the design, architecture, indexing techniques, and system implementations of modern vector database management systems, serving as a foundational reference for understanding the vector database ecosystem used in AI applications.
About this tool
Survey of Vector Database Management Systems
Type: Academic paper / survey (2023)
Category: Curated Resource Lists
Source: arXiv:2310.14021
Length: 25 pages
Discipline: Computer Science – Databases (cs.DB)
Overview
“Survey of Vector Database Management Systems” is a 25‑page academic survey that analyzes the design and architecture of modern vector database management systems. It focuses on how these systems store, index, and serve high-dimensional vector data, particularly for AI and machine learning applications.
Features
- Comprehensive 2023 survey of vector database management systems and their ecosystem.
- Systematic analysis of design and architecture, including how vector DBMSs are structured and how they differ from traditional databases.
- Coverage of indexing techniques for high-dimensional vectors (e.g., ANN and related vector search methods).
- Discussion of system implementations, describing how modern vector databases are built in practice.
- Positioning within AI workflows, focusing on how vector DBMSs support AI and ML applications that rely on vector search and embeddings.
- Foundational reference for understanding the broader vector database ecosystem, suitable for researchers, practitioners, and engineers working with vector data.
Access
- ArXiv record: https://arxiv.org/abs/2310.14021
- DOI: https://doi.org/10.48550/arXiv.2310.14021
Pricing
- Access via arXiv is typically free to read and download (no listed pricing on the source page).
Loading more......
Information
Categories
Similar Products
6 result(s)MongoDB Vector Search turns MongoDB into a full-featured vector database, enabling approximate and exact nearest neighbor search over vector embeddings stored alongside operational data. It supports semantic similarity search, retrieval-augmented generation (RAG) for AI applications, and lets you combine vector search with full‑text search and structured filters in the same query. Available on supported MongoDB Atlas clusters, it integrates with popular AI frameworks and services for building intelligent, agentic systems.
A collaboratively maintained Google Sheets matrix comparing features, capabilities, and characteristics of many vector databases and approximate nearest neighbor libraries, useful for selecting solutions for AI and similarity search applications.
Algolia’s vector search capability that augments its search-as-a-service platform with semantic and similarity search using embeddings.
Alibaba Cloud’s OpenSearch service with vector search support for semantic retrieval and intelligent search applications.
Chroma is an open-source AI-native vector database that provides semantic, full-text, and regex search as a memory layer for LLM and RAG applications.
chromem-go is a Go client and implementation for Chroma-like vector database functionality, enabling embedding storage and similarity search in Go applications.