Vector Search

Semantic search is the practice of searching on the meaning of data rather than the data itself.

A vector is a numeric representation of data and associated context that can be efficiently searched for using advanced algorithms.

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).

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 for indexing, retrieval, and building performant gen AI applications.

KNN, or K Nearest Neighbors, is the algorithm frequently used to find vectors near one another.

ANN, or Approximate Nearest Neighbors, 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.

ENN, or Exact Nearest Neighbors, is an approach to finding similar vectors that trades some performance in favor of accuracy. This method returns 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.

$vectorSearch is an aggregation stage in MongoDB Atlas that lets you execute an Approximate Nearest Neighbor (ANN) or Exact Nearest Neighbor (ENN) query with MongoDB Query API filtering (e.g., “$eq” or “$gte”). This stage will be supported on Atlas clusters version 6.0 and higher. The Atlas Search knnVector field type and knnBeta operator in $search are now deprecated.

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.

Atlas Vector Search supports embeddings from any provider that is under the 4096-dimension limit on the service. We currently support the ingestion, indexing, and querying of scalar quantized vector embeddings from your provider of choice. Coming soon, we will be adding support for binary quantized vector ingestion as well as automatic scalar and binary quantization with rescoring in Atlas, enabling cost and storage efficiency without compromising accuracy.

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.