Vector database
| Part of a series on |
| Machine learning and data mining |
|---|
A vector database management system (VDBMS) or simply vector database or vector store 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 (ANN) algorithms,[1][2] so that one can search the database with a query vector to retrieve the closest matching database records.
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 few hundreds 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, and images, audio, and other types of data can all be vectorized.[3]
These feature vectors may be computed from the raw data using machine learning methods such as feature extraction algorithms, word embeddings[4] or deep learning networks. The goal is that semantically similar data items receive feature vectors that are close to each other.
Vector databases can be used for similarity search, multi-modal search, recommendations engines, large language models (LLMs), etc.[5]
Vector databases are also used to implement Retrieval-Augmented Generation (RAG), a method to improve domain-specific responses of large language models. Text documents describing the domain of interest are collected and for each document 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.[6]
Techniques[edit]
The most important techniques for similarity search on high-dimensional vectors include:
- Hierarchical Navigable Small World (HNSW) graphs
- Locality-sensitive Hashing (LSH) and Sketching
- Product Quantization (PQ)
- Inverted Files
and combinations of these techniques.[citation needed]
In recent benchmarks HNSW-based implementations are among the best performers.[7][8] 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[edit]
| Name | License |
|---|---|
| Apache Cassandra[9][10] | Apache License 2.0 |
| Chroma[11][12] | Apache License 2.0[13] |
| Azure Cosmos DB Integrated Vector Database [14] | Proprietary (Managed Service) |
| Couchbase[15][16] | BSL 1.1[17] |
| Elasticsearch[18] | Server Side Public License, Elastic License[19] |
| Lantern[20] | BSL 1.1[21] |
| LlamaIndex[22] | MIT License[23] |
| Milvus[24][25] | Apache License 2.0 |
| MongoDB Atlas[26] | Server Side Public License (Managed service) |
| OpenSearch[27][28][29] | Apache License 2.0[30] |
| Pinecone[31] | Proprietary (Managed Service) |
| Postgres with pgvector[32] | PostgreSQL License[33] |
| Qdrant[34] | Apache License 2.0[35] |
| Redis Stack[36][37] | Redis Source Available License[38] |
| SurrealDB[39] | BSL 1.1[40] |
| Vespa[41] | Apache License 2.0[42] |
| Weaviate[43] | BSD 3-Clause[44] |
See also[edit]
- Curse of dimensionality – Difficulties arising when analyzing data with many aspects ("dimensions")
- Machine learning – Study of algorithms that improve automatically through experience
- Nearest neighbor search – Optimization problem in computer science
- Recommender system – Information filtering system to predict users' preferences
References[edit]
- ^ Roie Schwaber-Cohen. "What is a Vector Database & How Does it Work". Pinecone. Retrieved 18 November 2023.
- ^ "What is a vector database". Elastic. Retrieved 18 November 2023.
- ^ "Vector database". learn.microsoft.com. 2023-12-26. Retrieved 2024-01-11.
- ^ 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.
- ^ "Vector database". learn.microsoft.com. 2023-12-26. Retrieved 2024-01-11.
- ^ 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.
- ^ 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
- ^ 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. Cham: Springer International Publishing: 34–49. arXiv:1807.05614. doi:10.1007/978-3-319-68474-1_3. ISBN 978-3-319-68474-1.
- ^ "5 Hard Problems in Vector Search, and How Cassandra Solves Them". TheNewStack. 2023-09-22. Retrieved 2023-09-22.
- ^ "Vector Search quickstart". Retrieved 2023-11-21.
- ^ 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.
- ^ MSV, Janakiram (2023-07-28). "Exploring Chroma: The Open Source Vector Database for LLMs". The New Stack. Retrieved 2023-11-16.
- ^ "chroma/LICENSE at main · chroma-core/chroma". GitHub.
- ^ "Vector database". learn.microsoft.com. 26 December 2023. Retrieved 2024-01-10.
- ^ "Couchbase aims to boost developer database productivity with Capella IQ AI tool". VentureBeat. 2023-08-30.
- ^ "Investor Presentation Third Quarter Fiscal 2024". Couchbase Investor Relations. 2023-12-06.
- ^ Anderson, Scott (2021-03-26). "Couchbase Adopts BSL License". The Couchbase Blog. Retrieved 2024-02-14.
- ^ Kerner, Sean (23 May 2023). "Elasticsearch Relevance Engine brings new vectors to generative AI". VentureBeat. Retrieved 18 November 2023.
- ^ "elasticsearch/LICENSE.txt at main · elastic/elasticsearch". GitHub.
- ^ "Lantern". 2024-04-05. Retrieved 2024-04-05.
- ^ "lantern/LICENSE at main /lanterndata/lantern". GitHub. Retrieved 2024-04-10.
- ^ Wiggers, Kyle (2023-06-06). "LlamaIndex adds private data to large language models". TechCrunch. Retrieved 2023-10-29.
- ^ "llama_index/LICENSE at main · run-llama/llama_index". GitHub. Retrieved 2023-10-29.
- ^ "Open Source Vector Database – Milvus – LFAI & DATA". Retrieved 29 October 2023.
- ^ Liao, Ingrid Lunden and Rita (2022-08-24). "Zilliz raises $60M, relocates to SF". TechCrunch. Retrieved 2023-10-29.
- ^ "Introducing Atlas Vector Search: Build Intelligent Applications with Semantic Search and AI Over Any Type of Data". MongoDB. 2023-06-22.
- ^ "Using OpenSearch as a Vector Database". OpenSearch.org. 2023-08-02. Retrieved 2024-02-07.
- ^ Pan, James Jie; Wang, Jianguo; Li, Guoliang (2023-10-21), Survey of Vector Database Management Systems, arXiv:2310.14021, retrieved 2024-02-07
- ^ "AWS debuts new AI-powered data management and analysis tools". SiliconANGLE. 2023-07-26. Retrieved 2024-02-07.
- ^ "OpenSearch license". github.
- ^ "Pinecone leads 'explosion' in vector databases for generative AI". VentureBeat. 2023-07-14. Retrieved 2023-10-29.
- ^ "pgvector". GitHub. Retrieved 2023-11-27.
- ^ "pgvector/License". GitHub. Retrieved 2023-11-27.
- ^ 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.
- ^ "qdrant/LICENSE at master · qdrant/qdrant". GitHub. Retrieved 2023-10-29.
- ^ "Using Redis as a Vector Database with OpenAI | OpenAI Cookbook". cookbook.openai.com. Retrieved 2024-02-10.
- ^ "Redis as a vector database quick start guide". Redis. Retrieved 2024-01-31.
- ^ "Search and query". Redis. Retrieved 2024-02-10.
- ^ Wiggers, Kyle (2023-01-04). "SurrealDB raises $6M for its database-as-a-service offering". TechCrunch. Retrieved 2024-01-19.
- ^ "SurrealDB | License FAQs | The ultimate multi-model database". SurrealDB. Retrieved 2024-02-14.
- ^ Riley, Duncan (4 October 2023). "Yahoo spins off AI scaling engine Vespa as an independent company". siliconANGLE. Retrieved 18 November 2023.
- ^ "vespa/LICENSE at master · vespa-engine/vespa". GitHub.
- ^ "Weaviate reels in $50M for its AI-optimized vector database". SiliconANGLE. 2023-04-21. Retrieved 2023-10-29.
- ^ "weaviate/LICENSE at master · weaviate/weaviate". GitHub. Retrieved 2023-10-29.
External links[edit]
- Sawers, Paul (2024-04-20). "Why vector databases are having a moment as the AI hype cycle peaks". TechCrunch. Retrieved 2024-04-23.