Vector database

Last updated

A vector database, vector store or vector search engine is a database that can store vectors (fixed-length lists of numbers) along with other data items. Vector databases typically implement one or more Approximate Nearest Neighbor algorithms, [1] [2] [3] so that one can search the database with a query vector to retrieve the closest matching database records.

Contents

Vectors are mathematical representations of data in a high-dimensional space. In this space, each dimension corresponds to a feature of the data, with the number of dimensions ranging from a few hundred to tens of thousands, depending on the complexity of the data being represented. A vector's position in this space represents its characteristics. Words, phrases, or entire documents, as well as images, audio, and other types of data, can all be vectorized. [4]

These feature vectors may be computed from the raw data using machine learning methods such as feature extraction algorithms, word embeddings [5] or deep learning networks. The goal is that semantically similar data items receive feature vectors close to each other.

Vector databases can be used for similarity search, semantic search, multi-modal search, recommendations engines, large language models (LLMs), object detection, etc. [6]

Vector databases are also often used to implement retrieval-augmented generation (RAG), a method to improve domain-specific responses of large language models. The retrieval component of a RAG can be any search system, but is most often implemented as a vector database. Text documents describing the domain of interest are collected, and for each document or document section, a feature vector (known as an "embedding") is computed, typically using a deep learning network, and stored in a vector database. Given a user prompt, the feature vector of the prompt is computed, and the database is queried to retrieve the most relevant documents. These are then automatically added into the context window of the large language model, and the large language model proceeds to create a response to the prompt given this context. [7]

Techniques

The most important techniques for similarity search on high-dimensional vectors include:

and combinations of these techniques.[ citation needed ]

In recent benchmarks, HNSW-based implementations have been among the best performers. [8] [9] Conferences such as the International Conference on Similarity Search and Applications, SISAP and the Conference on Neural Information Processing Systems (NeurIPS) host competitions on vector search in large databases.

Implementations

This is a dynamic list and may never be able to satisfy particular standards for completeness. You can help by adding missing items with reliable sources.
NameLicense
Aerospike [10] [11] Proprietary
AllegroGraph [12] [13] Proprietary (Managed Service)
Apache Cassandra [14] [15] Apache License 2.0
Chroma [16] [17] Apache License 2.0 [18]
Azure Cosmos DB [19] Proprietary (Managed Service)
Couchbase [20] [21] BSL 1.1 [22]
CrateDB [23] Apache License 2.0
DataStax [24] Proprietary (Managed Service)
Elasticsearch [25] Server Side Public License, Elastic License [26]
HDF5 Query Indexing [27] BSD 3-Clause [28]
Lantern [29] BSL 1.1 [30]
LlamaIndex [31] MIT License [32]
MariaDB [33] [34] GPL v2 [35]
Marqo [36] Apache License 2.0 [37]
Meilisearch [38] MIT License [39]
Milvus [40] [41] Apache License 2.0
MongoDB Atlas [42] Server Side Public License (Managed service)
Neo4j [43] [44] GPL v3 (Community Edition) [45]
ObjectBox [46] Apache License 2.0 [47]
OpenSearch [48] [49] [50] Apache License 2.0 [51]
Oracle Database [52] Proprietary (Managed Service or License)
Pinecone [53] Proprietary (Managed Service)
Postgres with pgvector [54] PostgreSQL License [55]
Qdrant [56] Apache License 2.0 [57]
Redis Stack [58] [59] Redis Source Available License [60]
Snowflake [61] Proprietary (Managed Service)
SurrealDB [62] BSL 1.1 [63]
Typesense [64] GPL v3 (Community Edition) [65]
Vespa [66] Apache License 2.0 [67]
Weaviate [68] BSD 3-Clause [69]

See also

Related Research Articles

Memcached is a general-purpose distributed memory-caching system. It is often used to speed up dynamic database-driven websites by caching data and objects in RAM to reduce the number of times an external data source must be read. Memcached is free and open-source software, licensed under the Revised BSD license. Memcached runs on Unix-like operating systems and on Microsoft Windows. It depends on the libevent library.

Source-available software is software released through a source code distribution model that includes arrangements where the source can be viewed, and in some cases modified, but without necessarily meeting the criteria to be called open-source. The licenses associated with the offerings range from allowing code to be viewed for reference to allowing code to be modified and redistributed for both commercial and non-commercial purposes.

A time series database is a software system that is optimized for storing and serving time series through associated pairs of time(s) and value(s). In some fields, time series may be called profiles, curves, traces or trends. Several early time series databases are associated with industrial applications which could efficiently store measured values from sensory equipment, but now are used in support of a much wider range of applications. In many cases, the repositories of time-series data will utilize compression algorithms to manage the data efficiently. Although it is possible to store time-series data in many different database types, the design of these systems with time as a key index is distinctly different from relational databases which reduce discrete relationships through referential models.

A spatial database is a general-purpose database that has been enhanced to include spatial data that represents objects defined in a geometric space, along with tools for querying and analyzing such data.

<span class="mw-page-title-main">Apache CouchDB</span> Document-oriented NoSQL database

Apache CouchDB is an open-source document-oriented NoSQL database, implemented in Erlang.

Redis is a source-available, in-memory storage, used as a distributed, in-memory key–value database, cache and message broker, with optional durability. Because it holds all data in memory and because of its design, Redis offers low-latency reads and writes, making it particularly suitable for use cases that require a cache. Redis is the most popular NoSQL database, and one of the most popular databases overall. Redis is used in companies like Twitter, Airbnb, Tinder, Yahoo, Adobe, Hulu, Amazon and OpenAI.

<span class="mw-page-title-main">Neo4j</span> Graph database implemented in Java

Neo4j is a graph database management system (GDBMS) developed by Neo4j Inc.

FlockDB was an open-source distributed, fault-tolerant graph database for managing wide but shallow network graphs. It was initially used by Twitter to store relationships between users, e.g. followings and favorites. FlockDB differs from other graph databases, e.g. Neo4j in that it was not designed for multi-hop graph traversal but rather for rapid set operations, not unlike the primary use-case for Redis sets. FlockDB was posted on GitHub shortly after Twitter released its Gizzard framework, which it used to query the FlockDB distributed datastore. The database is licensed under the Apache License.

<span class="mw-page-title-main">Couchbase Server</span> Open-source NoSQL database

Couchbase Server, originally known as Membase, is a source-available, distributed multi-model NoSQL document-oriented database software package optimized for interactive applications. These applications may serve many concurrent users by creating, storing, retrieving, aggregating, manipulating and presenting data. In support of these kinds of application needs, Couchbase Server is designed to provide easy-to-scale key-value, or JSON document access, with low latency and high sustainability throughput. It is designed to be clustered from a single machine to very large-scale deployments spanning many machines.

<span class="mw-page-title-main">Open-core model</span> Business model monetizing commercial open-source software

The open-core model is a business model for the monetization of commercially produced open-source software. The open-core model primarily involves offering a "core" or feature-limited version of a software product as free and open-source software, while offering "commercial" versions or add-ons as proprietary software. The term was coined by Andrew Lampitt in 2008.

Elasticsearch is a search engine based on Apache Lucene. It provides a distributed, multitenant-capable full-text search engine with an HTTP web interface and schema-free JSON documents. Official clients are available in Java, .NET (C#), PHP, Python, Ruby and many other languages. According to the DB-Engines ranking, Elasticsearch is the most popular enterprise search engine.

Lightning Memory-Mapped Database (LMDB) is an embedded transactional database in the form of a key-value store. LMDB is written in C with API bindings for several programming languages. LMDB stores arbitrary key/data pairs as byte arrays, has a range-based search capability, supports multiple data items for a single key and has a special mode for appending records (MDB_APPEND) without checking for consistency. LMDB is not a relational database, it is strictly a key-value store like Berkeley DB and DBM.

<span class="mw-page-title-main">RocksDB</span> Embedded key-value database

RocksDB is a high performance embedded database for key-value data. It is a fork of Google's LevelDB optimized to exploit multi-core processors (CPUs), and make efficient use of fast storage, such as solid-state drives (SSD), for input/output (I/O) bound workloads. It is based on a log-structured merge-tree data structure. It is written in C++ and provides official language bindings for C++, C, and Java. Many third-party language bindings exist. RocksDB is free and open-source software, released originally under a BSD 3-clause license. However, in July 2017 the project was migrated to a dual license of both Apache 2.0 and GPLv2 license. This change helped its adoption in Apache Software Foundation's projects after blacklist of the previous BSD+Patents license clause.

TerminusDB is an open source knowledge graph and document store. It is used to build versioned data products. It is a native revision control database that is architecturally similar to Git. It is listed on DB-Engines.

LangChain is a software framework that helps facilitate the integration of large language models (LLMs) into applications. As a language model integration framework, LangChain's use-cases largely overlap with those of language models in general, including document analysis and summarization, chatbots, and code analysis.

MindsDB is an artificial intelligence company headquartered in California, an innovator bringing AI and Data together and is focused on enabling developers to build AI capabilities that can Reason, Plan and Orchestrate over enterprise data.

<span class="mw-page-title-main">Hierarchical navigable small world</span> Clustering and community detection algorithm

The Hierarchical navigable small world (HNSW) algorithm is a graph-based approximate nearest neighbor search technique used in many vector databases. Nearest neighbor search without an index involves computing the distance from the query to each point in the database, which for large datasets is computationally prohibitive. For high-dimensional data, tree-based exact vector search techniques such as the k-d tree and R-tree do not perform well enough because of the curse of dimensionality. To remedy this, approximate k-nearest neighbor searches have been proposed, such as locality-sensitive hashing (LSH) and product quantization (PQ) that trade performance for accuracy. The HNSW graph offers an approximate k-nearest neighbor search which scales logarithmically even in high-dimensional data.

<span class="mw-page-title-main">Valkey</span> Freely available in-memory key–value database

Valkey is an open-source in-memory storage, used as a distributed, in-memory key–value database, cache and message broker, with optional durability. Because it holds all data in memory and because of its design, Valkey offers low-latency reads and writes, making it particularly suitable for use cases that require a cache. Valkey is the successor to Redis, the most popular NoSQL database, and one of the most popular databases overall. Valkey or its predecessor Redis are used in companies like Twitter, Airbnb, Tinder, Yahoo, Adobe, Hulu, Amazon and OpenAI.

Milvus is a distributed vector database developed by Zilliz. It is available as both open-source software and a cloud service.

References

  1. ↑ Roie Schwaber-Cohen. "What is a Vector Database & How Does it Work". Pinecone. Retrieved 18 November 2023.
  2. ↑ "What is a vector database". Elastic . Retrieved 18 November 2023.
  3. ↑ "What is a Vector Database?" . Retrieved 10 July 2023.
  4. ↑ "Vector database". learn.microsoft.com. 2023-12-26. Retrieved 2024-01-11.
  5. ↑ Evan Chaki (2023-07-31). "What is a vector database?". Microsoft. A vector database is a type of database that stores data as high-dimensional vectors, which are mathematical representations of features or attributes.
  6. ↑ "Vector database". learn.microsoft.com. 2023-12-26. Retrieved 2024-01-11.
  7. ↑ Lewis, Patrick; Perez, Ethan; Piktus, Aleksandra; Petroni, Fabio; Karpukhin, Vladimir; Goyal, Naman; Küttler, Heinrich (2020). "Retrieval-augmented generation for knowledge-intensive NLP tasks". Advances in Neural Information Processing Systems 33: 9459–9474. arXiv: 2005.11401 .
  8. ↑ Aumüller, Martin; Bernhardsson, Erik; Faithfull, Alexander (2017), Beecks, Christian; Borutta, Felix; Kröger, Peer; Seidl, Thomas (eds.), "ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms", Similarity Search and Applications, vol. 10609, Cham: Springer International Publishing, pp. 34–49, arXiv: 1807.05614 , doi:10.1007/978-3-319-68474-1_3, ISBN   978-3-319-68473-4 , retrieved 2024-03-19
  9. ↑ Aumüller, Martin; Bernhardsson, Erik; Faithfull, Alexander (2017). "ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms". In Beecks, Christian; Borutta, Felix; Kröger, Peer; Seidl, Thomas (eds.). Similarity Search and Applications. Lecture Notes in Computer Science. Vol. 10609. Cham: Springer International Publishing. pp. 34–49. arXiv: 1807.05614 . doi:10.1007/978-3-319-68474-1_3. ISBN   978-3-319-68474-1.
  10. ↑ "Aerospike Recognized by Independent Research Firm Among Notable Vendors in Vector Databases Report". Morningstar. 2024-05-07. Retrieved 2024-08-01.
  11. ↑ "Aerospike raises $109M for its real-time database platform to capitalize on the AI boom". TechCrunch. 2024-04-04. Retrieved 2024-08-01.
  12. ↑ "AllegroGraph 8.0 Incorporates Neuro-Symbolic AI, a Pathway to AGI". TheNewStack. 2023-12-29. Retrieved 2024-06-06.
  13. ↑ "Franz Inc. Introduces AllegroGraph Cloud: A Managed Service for Neuro-Symbolic AI Knowledge Graphs". Datanami. 2024-01-18. Retrieved 2024-06-06.
  14. ↑ "5 Hard Problems in Vector Search, and How Cassandra Solves Them". TheNewStack. 2023-09-22. Retrieved 2023-09-22.
  15. ↑ "Vector Search quickstart" . Retrieved 2023-11-21.
  16. ↑ Palazzolo, Stephanie. "Vector database Chroma scored $18 million in seed funding at a $75 million valuation. Here's why its technology is key to helping generative AI startups". Business Insider. Retrieved 2023-11-16.
  17. ↑ MSV, Janakiram (2023-07-28). "Exploring Chroma: The Open Source Vector Database for LLMs". The New Stack. Retrieved 2023-11-16.
  18. ↑ "chroma/LICENSE at main · chroma-core/chroma". GitHub.
  19. ↑ "Vector database". learn.microsoft.com. 26 December 2023. Retrieved 2024-01-10.
  20. ↑ "Couchbase aims to boost developer database productivity with Capella IQ AI tool". VentureBeat. 2023-08-30.
  21. ↑ "Investor Presentation Third Quarter Fiscal 2024". Couchbase Investor Relations. 2023-12-06.
  22. ↑ Anderson, Scott (2021-03-26). "Couchbase Adopts BSL License". The Couchbase Blog. Retrieved 2024-02-14.
  23. ↑ "Open Source Vector Database". CrateDB Blog. 16 November 2023. Retrieved 2024-11-06.
  24. ↑ Sean Michael Kerner (18 July 2023). "DataStax brings vector database search to multicloud with Astra DB". Venture Beat.
  25. ↑ Kerner, Sean (23 May 2023). "Elasticsearch Relevance Engine brings new vectors to generative AI". VentureBeat . Retrieved 18 November 2023.
  26. ↑ "elasticsearch/LICENSE.txt at main · elastic/elasticsearch". GitHub.
  27. ↑ "HDF5 Query Indexing". GitHub . 27 Sep 2019. Retrieved 3 May 2024.
  28. ↑ "HDFGroup/COPYING at master · HDFGroup/hdf5". GitHub. Retrieved 2023-10-29.
  29. ↑ "Lantern". 2024-04-05. Retrieved 2024-04-05.
  30. ↑ "lantern/LICENSE at main /lanterndata/lantern". GitHub. Retrieved 2024-04-10.
  31. ↑ Wiggers, Kyle (2023-06-06). "LlamaIndex adds private data to large language models". TechCrunch. Retrieved 2023-10-29.
  32. ↑ "llama_index/LICENSE at main · run-llama/llama_index". GitHub. Retrieved 2023-10-29.
  33. ↑ "MariaDB Vector". MariaDB.org. Retrieved 2024-07-30.
  34. ↑ "Vector search in old and modern databases". manticoresearch.com. Retrieved 2024-07-30.
  35. ↑ "Licensing FAQ". MariaDB KnowledgeBase. Retrieved 2024-07-30.
  36. ↑ Sawers, Paul (2023-08-16). "Meet Marqo, an open source vector search engine for AI applications". TechCrunch. Retrieved 2024-08-20.
  37. ↑ marqo-ai/marqo, Marqo, 2024-08-20, retrieved 2024-08-20
  38. ↑ "Meilisearch Homepage". Meilisearch. 2024-10-08. Retrieved 2023-10-29.
  39. ↑ "meilisearch/LICENSE at main · meilisearch/meilisearch". GitHub. Retrieved 2024-10-08.
  40. ↑ "Open Source Vector Database – Milvus – LFAI & DATA" . Retrieved 29 October 2023.
  41. ↑ Liao, Ingrid Lunden and Rita (2022-08-24). "Zilliz raises $60M, relocates to SF". TechCrunch. Retrieved 2023-10-29.
  42. ↑ "Introducing Atlas Vector Search: Build Intelligent Applications with Semantic Search and AI Over Any Type of Data". MongoDB. 2023-06-22.
  43. ↑ "Neo4j enhances its graph database with vector search". itbrief. 2023-08-22.
  44. ↑ "Vector search indexes". neo4j.
  45. ↑ "Neo4j licensing".
  46. ↑ "Top Fifteen Vector Databases". db-engines.com. 2024-07-03. Retrieved 2024-07-03.
  47. ↑ "ObjectBox Java license". github.
  48. ↑ "Using OpenSearch as a Vector Database". OpenSearch.org. 2023-08-02. Retrieved 2024-02-07.
  49. ↑ Pan, James Jie; Wang, Jianguo; Li, Guoliang (2023-10-21), Survey of Vector Database Management Systems, arXiv: 2310.14021
  50. ↑ "AWS debuts new AI-powered data management and analysis tools". SiliconANGLE. 2023-07-26. Retrieved 2024-02-07.
  51. ↑ "OpenSearch license". github.
  52. ↑ Hook(1) and Priyadarshi(2), Doug(1) and Ranjan(2) (May 2, 2024). "Oracle Announces General Availability of AI Vector Search in Oracle Database 23ai". oracle. Retrieved July 9, 2024.{{cite web}}: CS1 maint: numeric names: authors list (link)
  53. ↑ "Pinecone leads 'explosion' in vector databases for generative AI". VentureBeat. 2023-07-14. Retrieved 2023-10-29.
  54. ↑ "pgvector". GitHub. Retrieved 2023-11-27.
  55. ↑ "pgvector/License". GitHub. Retrieved 2023-11-27.
  56. ↑ Sawers, Paul (2023-04-19). "Qdrant, an open-source vector database startup, wants to help AI developers leverage unstructured data". TechCrunch. Retrieved 2023-10-29.
  57. ↑ "qdrant/LICENSE at master · qdrant/qdrant". GitHub. Retrieved 2023-10-29.
  58. ↑ "Using Redis as a Vector Database with OpenAI | OpenAI Cookbook". cookbook.openai.com. Retrieved 2024-02-10.
  59. ↑ "Redis as a vector database quick start guide". Redis. Retrieved 2024-01-31.
  60. ↑ "Search and query". Redis. Retrieved 2024-02-10.
  61. ↑ "Vector data type and vector similarity functions — General Availability". Snowflake. 2024-05-17. Retrieved 2024-05-17.
  62. ↑ Wiggers, Kyle (2023-01-04). "SurrealDB raises $6M for its database-as-a-service offering". TechCrunch. Retrieved 2024-01-19.
  63. ↑ "SurrealDB | License FAQs | The ultimate multi-model database". SurrealDB. Retrieved 2024-02-14.
  64. ↑ Martinez, Miguel (2024-06-20). "Typesense Homepage". Typesense. Retrieved 2024-06-20.
  65. ↑ "Typesense licensing". GitHub .
  66. ↑ Riley, Duncan (4 October 2023). "Yahoo spins off AI scaling engine Vespa as an independent company". siliconANGLE. Retrieved 18 November 2023.
  67. ↑ "vespa/LICENSE at master · vespa-engine/vespa". GitHub.
  68. ↑ "Weaviate reels in $50M for its AI-optimized vector database". SiliconANGLE. 2023-04-21. Retrieved 2023-10-29.
  69. ↑ "weaviate/LICENSE at master · weaviate/weaviate". GitHub. Retrieved 2023-10-29.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.