MongoDB Vector Search

Getting started with MongoDB Vector Search

Follow step-by-step instructions to set up your Atlas cluster, create a sample vector search index, and run sample semantic search queries.

Get Started Now

Run vector search in three easy steps

Create vector embeddings, or let us do it for you

Stop orchestrating API calls. Use an open-source model of your choice, or leverage Automated Embedding (in preview) in Community Edition.

Learn how

Create a vector search index

Define the index for the vector embeddings that you want to query and the fields that you want to use to pre-filter data for efficient searches.

Learn more about indexes

Run vector search queries

Use the $vectorSearch stage in the aggregation pipeline to perform an Approximate Nearest Neighbor or Exact Nearest Neighbor vector search.

Learn how to run search queries

Explore more resources

Check out our docs

Get the most out of MongoDB Vector Search with our in-depth documentation.

View documentation

Build a chatbot right in your browser

Build a Q&A chatbot without writing a single line of code using the latest MongoDB Search Playground tool, Chatbot Demo Builder.

Start Building

Boost your gen AI skills

Explore our AI learning hub resources with three self-paced tracks, including technical content you need to build AI applications with MongoDB.

Start learning

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