ATLAS

Vector Search

Build intelligent applications powered by semantic search and generative AI over any type of data using a full-featured vector database.
Atlas Vector Search illustration.
What is Atlas Vector Search?
Integrate your operational database and vector search in a single, unified, fully managed platform with full vector database capabilities. Store your operational data, metadata, and vector embeddings on Atlas while using Atlas Vector Search to build intelligent gen AI-powered applications.Watch 3-minute video
illustration of cup and awards
MongoDB Atlas Vector Search voted most loved vector database
Once again, Atlas Vector Search takes the prize as the most loved vector database according to the new 2024 State of AI report from Retool.Read the Blog

Featured Integrations

LangChain
LlamaIndex
OpenAI
Hugging Face
Cohere
Microsoft Semantic Kernel
AWS
Key use cases for Atlas Vector Search

Key use cases for Atlas Vector Search

Atlas Vector Search lets you search unstructured data. You can create vector embeddings with machine learning models like OpenAI and Hugging Face, and store and index them in Atlas for retrieval augmented generation (RAG), semantic search, recommendation engines, dynamic personalization, and other use cases.What is retrieval augmented generation?
Vector Search simplified

Vector Search simplified

With Atlas Vector Search, developers can build AI-powered experiences while accessing all the data they need through a unified and consistent developer experience in the form of the MongoDB Query API. Our new $vectorSearch aggregation stage makes it even easier for those already using MongoDB.Vector Search explained in 3 minutes
Illustration of a couple of graphs representing MongoDB's auto-scaling capabilities.

Workload isolation for more scalability and availability

Set up dedicated infrastructure for Atlas Search and Vector Search workloads. Optimize compute resources to scale search and database independently, delivering better performance at scale and higher availability.View the docs
Illustration of robot representing AI applications

The Versatility of Atlas as a Vector Database

Rather than use a standalone or bolt-on vector database, the versatility of our platform empowers users to store their operational data, metadata, and vector embeddings on Atlas and seamlessly use Atlas Vector Search to index, retrieve, and build performant gen AI applications.
Avoid the synchronization tax

Avoid the synchronization tax

Store vector embeddings right next to your source data and metadata with the power of the document model. Vector embeddings are integrated with application data and seamlessly indexed for semantic queries, enabling you to build easier and faster.What is a document database?
Remove operational heavy lifting

Remove operational heavy lifting

Atlas Vector Search is built on the MongoDB Atlas developer data platform. Easily automate provisioning, patching, upgrades, scaling, security, and disaster recovery while providing deep visibility into performance for both the database and Vector Search so you can focus on building applications.Learn how to build intelligent applications

Robust ecosystem of AI integrations

Atlas Vector Search accelerates your journey to building advanced search and generative AI applications by integrating with a wide variety of top LLMs and frameworks.
“Everything in gen AI is new — you can’t just go to GitHub and repurpose code others have written. Only MongoDB Atlas gives us the flexibility and scale at the data platform layer to experiment in how to harness one of the biggest technical advancements the industry has ever seen.”
Louise Lind Skov
Head of Content Digitalisation, Novo Nordisk
“Atlas Vector Search was the solution to our problems. It simplifies a lot of the work that goes into making Okta Inbox super user friendly for customers.”
Suchit Agarwal
Director of Engineering, Okta
“With Atlas Vector Search we can compose sophisticated queries that quickly filter across product data, customer preferences, and vector embeddings to precisely identify hyper-relevant product recommendations in real time.”
Mundher Al-Shabi
Senior Data Scientist, Delivery Hero
“It was incredibly easy to deploy our search data to Atlas Search Nodes, requiring only a few button clicks. Furthermore, the memory requirements of vector search can now match our Atlas Search Node deployment exactly. This is a crucial consideration for keeping vector search fast and streamlined.”
Pierce Lamb
Senior Software Engineer, VISO TRUST
“We want to make it possible for users of our customers’ knowledge base to receive instant, trustworthy, and accurate answers to their questions using conversational search powered by MongoDB Atlas Vector Search and Generative AI capabilities.”
Saravana Kumar
CEO, Kovai

Resources for building AI-powered applications

Discover how to leverage MongoDB to streamline development for the next generation of AI-powered applications.
What does the Future of Search look like?
Read our white paper to learn how generative AI is shaping the future of search, and how to future-proof your own search strategy. Read the White Paper
Generative AI illustration.

FAQ

What is semantic search?
Semantic search is the practice of searching on the meaning of data rather than the data itself.
What is a vector?
A vector is a numeric representation of data and associated context that can be efficiently searched for using advanced algorithms.
How does Atlas Vector Search differ from Atlas Search?
Atlas Vector Search allows searching through data based on semantic meaning captured in vectors, whereas Atlas Search allows for keyword search (i.e., based on the actual text and any defined synonym mappings).
Can I use MongoDB Atlas instead of a standalone vector database?
Yes, MongoDB Atlas is a vector database. Atlas is a fully managed, multi-cloud developer data platform with a rich array of capabilities that includes text or lexical and vector search. Rather than use a standalone or bolt-on vector database, the versatility of our platform empowers users to store their operational data, metadata, and vector embeddings on Atlas and seamlessly use Atlas Vector Search to index, retrieve, and build performant gen AI applications.
What's the difference between K-Nearest Neighbor Search and Approximate K-Nearest Neighbor Search? When to use what?

KNN stands for "K Nearest Neighbors," which is the algorithm frequently used to find vectors near one another. Learn more.

ANN stands for "Approximate Nearest Neighbors" and it is an approach to finding similar vectors that trades accuracy in favor of performance. This is one of the core algorithms used to power Atlas Vector Search. Our algorithm for Approximate Nearest Neighbor search uses the Hierarchical Navigable Small World (HNSW) graph for efficient indexing and querying of millions of vectors.

In MongoDB Atlas, you can implement exact K nearest neighbor search via the $vectorSearch stage. This method would guarantee to return the exact closest vectors to a query vector, with the number of vectors specified by the variable limit. Exact vector search query execution can maintain sub-second latency for unfiltered queries up to 10,000 documents. It can also provide low-latency responses for highly selective filters that restrict a broad set of documents into 10,000 documents or less, ordered by vector relevance.

Learn more
What is $vectorSearch and how does it differ from the knnBeta operator in $search?
$vectorSearch is a new aggregation stage in MongoDB Atlas that lets you execute an Approximate Nearest Neighbor (ANN) query with MongoDB Query Language filtering (e.g., “$eq” or “$gte”). This stage will be supported on Atlas clusters version 6.0 and higher. The knnBeta operator in $search will continue to be supported as well.
Learn more
What is ANN?
ANN stands for "Approximate Nearest Neighbors" and it is an approach to finding similar vectors that trades accuracy in favor of performance. This is one of the core algorithms used to power Atlas Vector Search. Our algorithm for Approximate Nearest Neighbor search uses the Hierarchical Navigable Small World (HNSW) graphs.
What are Search Nodes?
Search Nodes provide dedicated infrastructure for Atlas Search and Vector Search workloads, allowing you to optimize compute resources and fully scale search needs independent of the database. Search Nodes provide better performance at scale, delivering workload isolation, higher availability, and the ability to better optimize resource usage.
Learn more
Which Vector embeddings does Atlas Search support?
Atlas Vector Search Supports embeddings from any provider that is under the 4096-dimension limit on the service.
Does Vector Search work with images, media files, and other types of data?
Yes, Atlas Vector Search can query any kind of data that can be turned into an embedding. One of the benefits of the document model is that you can store your embeddings right alongside your rich data in your documents.

Get the most out of Atlas

Power more data-driven experiences and insights with the rest of our developer data platform.
Register Now
Magnifying glass with documents.

Ready to get started?

Head over to our tutorial to see how you can quickly create embeddings of your MongoDB data and search it with our Vector Search capability.Get Started