NEWMultitenant vector search is now simpler and more efficient with Flat Indexes Read the blog >
NewSearch & Vector Search now in public preview for Community Edition Read the blog >
AnnouncementAtlas Vector Search benchmarks: Test, evaluate, and improve your vector search Read the guide >

MongoDB Vector Search Features

Explore how you can leverage MongoDB Vector Search capabilities for modern search and gen AI use cases.

Fully managed, modern, multi-cloud database

Unlike standalone vector databases, Atlas lets you store and work with operational data, metadata, and vectors, all in a unified, secure, scalable database.

Learn about Atlas
general_action_best_practices

Flexibility and agility with the document model

Use rich, nested data structures for effortless organization and querying. Model multiple fields with embedding models and jointly consider them at query time for optimal performance.

Learn about document databases
mdb_replica_set

Independent scaling with Search Nodes

Ensure higher availability and performance with independent scalability through workload isolation and memory-optimized, multi-cloud dedicated infrastructure.

Read blog post
technical_mdb_quantization

Cost efficiency with vector quantization

Increase scale and reduce costs by compressing vectors for more efficient storage, processing, and retrieval while preserving search accuracy.

Read blog post

Robust vector search capabilities

Utilize flexible search approaches to optimize relevance and performance for your needs.

realm_fast_queries

Approximate Nearest Neighbor (ANN) search

Designed to support efficiency in complex, highly dimensional vector use cases by balancing accuracy with computational feasibility.

Learn more about ANN search
general_action_checkmark

Exact Nearest Neighbor (ENN) search

Designed to focus on precision, especially in small-scale datasets where improving benchmarking and development speed are critical.

Learn more about ENN search
atlas_search

Hybrid search

Combine text and vector search for enhanced accuracy by flexibly adjusting weights to prioritize vector similarity or keyword relevance.

See tutorial

Get started with MongoDB Vector Search

See how you can convert your data into vector embeddings, retrieve them with search capabilities, and build intelligent applications quickly and easily in MongoDB.
Get Started
Start building with:
  • Simplified deployment
  • Unified developer experience
  • Horizontal, vertical, independent scale
  • Integrated AI ecosystem
  • 125+ regions worldwide