PUBLIC PREVIEW
Vector Search
Build intelligent applications powered by semantic search and generative AI over any type of data.
_Spot%20(1).png?auto=format%252Ccompress)
What is Atlas Vector Search?
By integrating the operational database and vector store in a single, unified, and fully managed platform — along with support integrations into large language models (LLMs) — Atlas Vector Search is a fast and easy way to build semantic search and AI-powered applications.
Key use cases for Atlas Vector Search
Atlas Vector Search allows you to search any unstructured data. You can create vector embeddings using the machine learning model of your choice (OpenAI, Hugging Face, and more) and store them in Atlas. It powers use cases such as similarity search, recommendation engines, Q&A systems, dynamic personalization and long-term memory for LLMs.
Vector Search simplified
Atlas Vector Search enables developers to work with the database and vector search using the unified MongoDB Query API. Build AI-powered experiences on Atlas as part of a single, consistent developer experience where you can access all the data you need, however you need to query.
Avoid the synchronization tax
Store vector embeddings right next to your source data and metadata with the power of the document model. Vector data is integrated with application data and seamlessly indexed for semantic queries, enabling you to build simpler and faster._Spot.png?auto=format%252Ccompress)
Remove operational heavy lifting
Atlas Vector Search is built on the MongoDB Atlas developer data platform. The battle tested, fully managed Atlas platform automates 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 your application.FAQ
What is semantic search?
Semantic search is the concept of searching on the meaning of data rather than the data itself.
What is a vector?
A vector is a numeric representation of your data that can be searched over using advanced machine learning 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.
What is KNN?
KNN stands for "K Nearest Neighbors," which is the algorithm frequently used to find vectors near one another. 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 Vector Embeddings does Atlas Search support?
Atlas Vector Search Supports embeddings from any provider that are under the 2048 dimension width limit on the service.
Does Vector Search support any integrations in popular frameworks?
Yes, Atlas Vector Search is supported as a Vector Store in both LangChain and LlamaIndex, two popular frameworks for building services that utilize Large Language Models.
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.
Register Now
_Spot.png?auto=format%252Ccompress)