Atlas
MongoDB Atlas
A vector database, and much more
Enjoy the freedom and flexibility of using MongoDB Atlas as a vector database to store and search vectors alongside your operational data.
Native vector database features
Vector embeddings are numeric representations of data and related context. MongoDB Atlas unifies vector embeddings with live application data in a single, fully managed, multi-cloud database that handles transactional, search and retrieval, in-app analytics, geospatial, and streaming workload needs.
Make LLMs smarter with RAG
Retrieval augmented generation (RAG) gives large language models (LLMs) access to live, up-to-date data, filling the gaps in knowledge that LLMs aren't trained on. RAG enables you to build hyper-personalized experiences uniquely tailored to business needs using your own enterprise data.
Reduce complexity, increase productivity
Niche technologies lead to fragmented and inefficient developer experiences. Instead of bolting on a standalone vector database, Atlas gives you all the features you need to build gen AI-powered applications while reducing sprawl, complexity, and overhead for developers, all in a single platform.
Cloud flexibility and AI ecosystem integration
Some AI-enabled applications require specialized ML infrastructure from a particular cloud or model provider. MongoDB Atlas uniquely offers global, multi-cloud database clusters on all the major cloud providers, and supports embeddings generated by the vast majority of model providers.GEN AI CASE STUDYBrian Raymond
“As the world’s most widely used natural language ingestion and preprocessing platform, partnering with MongoDB was a natural choice for us. This collaboration allows for even faster development of intelligent applications. Together, we're paving the way businesses harness their data.”
Founder/CEO, Unstructured.io
GEN AI CASE STUDYHimanshu Sharma
“We use the sentences stored in MongoDB to train our models and support real-time inference. The flexibility of its document data model made MongoDB an ideal fit to store the diversity of structured and unstructured content and features our ML models translate.”
Co-founder/CEO, Devnagri
GEN AI CASE STUDYAmit Ben
“The MongoDB document model really allows us to spread our wings and freely explore new capabilities for the AI, such as new predictions, new insights, and new output data points. With any other platform, we would have to constantly go back to the underlying infrastructure and maintain it. Now, we can add, expand, and explore new capabilities on a continuous basis.”
CEO/Founder, One AI
GEN AI CASE STUDYRaj Thaker
“The introduction of Atlas Vector Search and the Building Generative AI Applications tutorial gave me a fast, ready-made blueprint that brings together a database for source data, vector search for AI-powered semantic search, and reactive, real-time data pipelines to keep everything updated, all in a single platform with a single copy of the data and a unified developer API.”
CTO and Co-Founder of Crewmate
Ready to get started?
Start leveraging RAG, LLMs, and your own private data to build transformative AI-powered applications using native vector database features in MongoDB Atlas.
_Thumbnail_BS_SpringGreen_1.svg?auto=format%252Ccompress)