Learn
Vector Database 101: Everything You Need to Know

What is a Vector Database and How Does It Work?

Mar 01, 202412 min read

A vector database stores, indexes, and searches vector embeddings generated by machine learning models for fast information retrieval and similarity search. This post explains how vector databases work, their key features and use cases, and the ecosystem.

By Frank Liu

Read the entire series

Lastest Update: Jan 17

Welcome back to Vector Database 101.

In the previous tutorial, we took a quick look at the ever-increasing amount of data that is being generated on a daily basis. We then covered how these bits of data can be split into structured/semi-structured and unstructured data types, the differences between them, and how modern machine learning can be used to understand unstructured data through embeddings. Finally, we briefly touched upon unstructured data processing via ANN search.

Through all of this information, it’s now clear that the ever-increasing amount of unstructured data requires a paradigm shift and a new category of database management system - the vector database.

Before we jump in, let’s briefly discuss the key differences between vector databases and traditional databases.

Traditional relational database systems excel at managing structured data with predefined formats and executing precise search operations. In contrast, vector databases specialize in storing and retrieving unstructured data types, such as images, audio, videos, and textual content, through high-dimensional numerical representations known as vector embeddings. Vector databases store data by assigning vectors to capture various characteristics of objects, allowing the database to quickly identify similar items based on distance measures between these vectors.

Vector databases are used to perform semantic similarity searches using techniques like the Approximate Nearest Neighbor (ANN) algorithm. They are popular in building widespread applications in various domains, including recommender systems, chatbots, and tools for searching for similar images, videos, and audio content. With the rise of AI and large language models (LLMs) like ChatGPT, vector databases are also beneficial in addressing LLM hallucinations.

A vector database is a fully managed, no-frills solution for storing, indexing and searching across a massive dataset of unstructured data that leverages the power of embeddings from machine learning models.

A large language model (LLM) is a machine learning model that can perform various natural language processing (NLP) tasks based on pre-trained knowledge. However, LLMs are prone to hallucinations because of their lack of domain-specific knowledge. Vector databases are a vital technology that can address this hallucinatory issue by providing LLMs with domain-specific, up-to-date, or confidential private data.

Let’s use the Zilliz Cloud vector database as an example. Zilliz Cloud stores domain-specific, up-to-date, and confidential private data outside LLMs in the form of vector embeddings. When a user asks a question, Zilliz Cloud transforms the question into vectors and then performs ANN searches for the Top-K results most relevant to the question by comparing the spatial distance between the query vectors and those stored in the vector database. Finally, these results are combined with the original question to create a prompt that provides a comprehensive context for the LLM.

This framework, which includes a vector database, an LLM, and Prompts as code, is also known as retrieval augmented generation (RAG) and serves as the foundation for developing LLM-powered applications.

Guess how many curators it took to label the now-famous ImageNet dataset. Ready for the answer?

25000 people (that’s a lot).

Being able to search across images, video, text, audio, and other forms of unstructured data via their content rather than human-generated labels or tags is exactly what vector databases were meant to solve. When combined with powerful machine learning models, these databases like Milvus have the ability to revolutionize e-commerce solutions, recommendation systems, semantic search, computer security, pharmaceuticals, and many other industries.

Let’s think about it from a user perspective. What good is a piece of technology without strong usability and a good user API? In concert with the underlying technology, multi-tenancy and usability are also incredibly important attributes. Let’s list out all of the vector database features to look out for (many of these features overlap with those of databases for structured/semi-structured data):

Introduction to Vector Databases

Vector databases are a specialized type of database designed to efficiently store, manage, and query high-dimensional vector data. These databases have become increasingly important in fields such as artificial intelligence, machine learning, and natural language processing. Unlike traditional relational databases, which are optimized for structured data, vector databases are tailored to handle the unique challenges posed by vector data, including high dimensionality and complex similarity searches. By leveraging advanced algorithms and data structures, vector databases provide the performance and scalability needed for modern AI applications.

Vector Database Fundamentals

What are Vectors and Vector Embeddings?

Vectors are arrays of numbers that can represent complex objects, such as words, images, and audio. These numerical representations, known as vector embeddings, capture the semantic meaning of data points. Generated by machine learning models, including large language models, vector embeddings are used to represent data in a high-dimensional vector space. This transformation allows for the efficient processing and analysis of unstructured data, making vector embeddings essential for applications in natural language processing, computer vision, and recommendation systems.

How Does a Vector Database Work?

A vector database operates by indexing and storing vector embeddings in a manner that enables fast and efficient similarity searches. To achieve this, the database employs various algorithms, such as hashing, quantization, and graph-based search, which optimize the search process. When a query vector is submitted, the database uses a similarity metric—such as cosine similarity or Euclidean distance—to identify the most similar vectors within the database. The system then returns the top-k most similar vectors, along with their corresponding metadata, providing users with relevant and contextually accurate results.

Vector Data and Applications

Similarity and Semantic Search

Vector databases excel at performing similarity and semantic searches, which are crucial for many AI applications. Similarity search involves finding vectors that closely match a given query vector, while semantic search focuses on identifying vectors with similar meanings or contexts. To optimize these searches, vector databases use techniques such as filtering and ranking to ensure the most relevant results are returned. Common applications of vector databases include recommendation systems, image and video retrieval, and natural language processing, where the ability to quickly and accurately find similar data points is invaluable.

By understanding these fundamental concepts and applications, it becomes clear why vector databases are a powerful tool in the modern data landscape. They provide the necessary infrastructure to handle the complexities of high-dimensional vector data, enabling advanced AI and machine learning applications to thrive.

Scalability and tunability in vector databases

As the number of unstructured data elements stored in a vector database grows into the hundreds of millions or billions, horizontal scaling across multiple nodes becomes paramount (scaling up by manually inserting sticks of RAM into a server rack every 3 months is no fun). Furthermore, differences in insert rate, query rate, and underlying hardware may result in different application needs, making overall system tunability mandatory for the best vector databases.

Multi-tenancy and data isolation in vector databases

Supporting multiple users is an obvious feature for all database systems. However, going guns blazing and creating a new vector database for every new user will probably turn out poorly for everyone. Parallel to this notion is data isolation - the idea that any inserts, deletes, or queries made to one collection in a database should be invisible to the rest of the system unless the collection owner explicitly wishes to share the information.

A database without a full suite of APIs and SDKs is, frankly speaking, not a real database. For example, Milvus maintains Python, Node, Go, and Java SDKs for communicating with and administering a Milvus vector database.

User interfaces can help significantly reduce the learning curve associated with VectorDBs. These interfaces also expose new features and tools that would otherwise be inaccessible.

Phew. That was quite a bit of info, so we'll summarize it right here: a vector database should have the following features: 1) scalability and tunability, 2) multi-tenancy and data isolation, 3) a complete suite of APIs, and 4) an intuitive user interface/administrative console. In the next two sections, we'll follow up on this concept by comparing vector databases versus vector search libraries and vector search plugins, respectively.

Vector databases like Milvus Zilliz (fully managed Milvus) are purpose-built to store, process, and search unstructured data through the use of vector embeddings. In other words, vector databases mainly operate on vector embeddings and closely collaborate with machine learning models that transform unstructured data into embeddings.

Below is a typical pipeline for a vector database (Here, we use Zilliz as an example).

A machine learning model transforms all types of unstructured data into vector embeddings.
Vector embeddings are stored in Zilliz Cloud.
Users perform a query.
The machine learning model converts the query into vector embeddings.
Zilliz Cloud compares the distance between the query vector and the vector held in the dataset using an approximate nearest neighbor (ANN) algorithm and finds the Top-K results most relevant to the query.
Zilliz Cloud returns the results to the user.

Earlier in this tutorial, I listed the desired features a vector database should implement, before comparing vector databases to vector search libraries and to vector databases excel to search plugins. Now, let’s briefly go over some high-level technical challenges of vector databases. In future tutorials, we’ll provide an overview of how Milvus tackles each of these, in addition to how these technical decisions improve Milvus’ performance over other open-source vector databases.

Picture an airplane. The airplane itself contains a number of interconnected mechanical, electrical, and embedded systems, all working on harmony to provide us with a smooth and pleasurable in-flight experience. Likewise, a VectorDB are composed of a number of evolving software components. Roughly speaking, these can be broken down into the storage, the index, and the service. Although these three components are tightly integrated[1], companies such as Snowflake have shown the broader storage industry that "shared nothing" database architectures are arguably superior to the traditional "shared storage" cloud database models. Thus, the first technical challenge associated with these databases is designing a flexible and scalable data model.

Great, so we have a data model. What's next? With data already stored in a vector db, being able to search across that vector data store, i.e. vector querying and indexing, is the next important component. The compute-heavy nature of machine learning and multi-layer neural networks has allowed GPUs, NPUs/TPUs, FPGAs, and other general purpose compute hardware to flourish. Vector indexing and querying is also compute-heavy, operating at maximum speed and efficiency when run on accelerators. This diverse set of compute resources gives way to the second main technical challenge, developing a heterogeneous computing architecture.

With a data model, query engine, and architecture in place, the last step is making sure your application can, well, read from the database - this ties closely into the API and user interface bullet points mentioned in the first section. While a new category of database necessitates a new architecture in order to extract maximal performance at minimal cost, the majority of vector database users are still acclimated to traditional CRUD operations (e.g. INSERT, SELECT, UPDATE, and DELETE in SQL). Therefore, the final primary challenge is developing a set of APIs and GUIs that leverage existing user interface conventions while maintaining compatibility with the underlying architecture.

Note how each of the three components corresponds to a primary technical challenge. With that being said, there is no one-size-fits-all vector database architecture. The best vector databases will fulfill all of these technical challenges by focusing on delivering the features mentioned in the first section.

Advantages of Vector Databases

Vector databases offer several advantages over traditional relational and leading vector databases, for use cases that involve vector similarity search, semantic searches, machine learning, and AI applications. Here are some of the benefits of vector databases:

High-dimensional search: perform efficient similarity searches on high dimensional vectors, commonly used in machine learning and Generative AI (GenAI) applications, such as image recognition, natural language processing, and recommendation systems. They can quickly find data points that are most similar to a given query, which is crucial for applications like recommendation engines, image recognition, and natural language processing.
Scalability: scale horizontally, efficiently storing and retrieving large amounts of high dimensional vectors. Scalability is significant for applications that require real-time search and retrieval of large amounts of data.
Flexibilitywith hybrid search: handle various vector data types, including sparse and dense vectors. They can also handle multiple data types, including numerical, text, and binary.
Performance: perform vector similarity searches efficiently, often providing faster search times than traditional databases.
Customizable indexing: allow custom indexing schemes for specific use cases and data types.

Overall, they offer significant advantages for applications that involve efficient similarity search, semantic searches complex data,, and machine learning, providing fast and efficient search and retrieval of high dimensional vector data in a vector space.

Which one is the fastest vector database? Benchmark them.

ANN-Benchmarks is a benchmarking environment to evaluate the performance of various vector databases and nearest neighbor search algorithms. The main functions of ANN Benchmarks include the following:

Dataset and parameter specification: The benchmark provides a variety of datasets of different sizes and dimensions, along with a set of parameters for each dataset, such as the number of neighbors to search for and the distance metric to use.
Search recall calculation: The benchmark calculates the search recall, the proportion of queries for which the true nearest neighbors are found among the k returned neighbors. Search recall is a metric for evaluating the accuracy of nearest-neighbor search algorithms.
RPS calculation: The benchmark also calculates the RPS (queries per second), the rate at which the vector database or search algorithm can process queries. This metric is vital for evaluating the speed and scalability of the system.

Using the ANN Benchmarks, users can compare the performance of different vectordbs and search algorithms under a standardized set of conditions, making it easier to identify the most suitable option for a particular use case.

Vector databases comparison

No matter what your semantic search use case is, your application will require storing lots of vector embeddings while being able to retrieve the most relevant vectors with low latency. You also want to choose a vector database that you can use long-term and adhere to the compliance requirements of the target application.

When comparing a vector database to an alternative, you should consider these factors: architecture, scalability, performance, use cases, and costs. Each alternative database may have different strengths and weaknesses in these areas, so evaluating them based on specific requirements and priorities is essential. The following is a list of resources that will help you choose the right tool for your use case:

Wrapping up

In this tutorial, we took a quick tour of vector databases. Specifically, we looked at 1) what features go into a mature example, 2) how a vector database differs from vector search libraries, 3) how a vector database differs from vector search plugins in traditional databases or search systems, and 4) the key challenges associated with building a vector database.

This tutorial is not meant to be a deep dive, nor is it meant to show how it can be used in applications. Rather, the goal is to provide an overview. This is where your journey truly begins!

In the next tutorial, we’ll provide an introduction to Milvus, the world’s most popular open-source vector database:

Provide a brief history of Milvus, including the most important question - where does the name come from!
Cover how Milvus 1.0 differs from Milvus 2.0 and where the future of Milvus lies.
Discuss the differences between Milvus and other VectorDBs such as Google Vertex AI’s Matching Engine.
Go over some common vector database applications.

Take another look at the Vector Database 101 courses

Frank Liu
Frank Liu is the Director of Operations & ML Architect at Zilliz, where he serves as a maintainer for the Towhee open-source project. Prior to Zilliz, Frank co-founded Orion Innovations, an ML-powered indoor positioning startup based in Shanghai and worked as an ML engineer at Yahoo in San Francisco. In his free time, Frank enjoys playing chess, swimming, and powerlifting. Frank holds MS and BS degrees in Electrical Engineering from Stanford University.

Next: Understanding Vector Databases: Compare Vector Databases, Vector Search Libraries, and Vector Search Plugins