What it is: Native Reranking enables developers to improve retrieval accuracy using Voyage AI reranking models directly from the MongoDB aggregation pipeline. A single new stage, $rerank, can improve retrieval accuracy by an average of 23.84% over full-text search and 10.82% over vector search when using Voyage rerank-2.5 compared to non-reranked results.Who it's for: Atlas developers building RAG applications, search and recommendation engines, or AI agents.Why it matters: Previously, adding a reranker model to your retrieval pipeline meant calling a separate API outside your query layer, handling reordering in application code, and managing additional credentials and billing. Native Reranking eliminates that complexity: $rerank is now a single stage in the same pipeline you're already using in MongoDB.How to get started: Native Reranking is now available in Atlas for clusters running Latest Version with Auto-Upgrades (MongoDB 8.3). Learn more in the documentation.

What it is: voyage-context-4 is the next-generation contextualized chunk embedding model and a drop-in replacement for voyage-context-3, producing one vector per chunk that captures full document context -- now with a new mixture-of-experts backbone, built-in auto-chunking, transparent handling of documents beyond the 32K-token window, and native overlapping-chunk support. It outperforms voyage-context-3 by 1.40% (document-level) and 2.08% (chunk-level) across 39 datasets and is priced at $0.12 per 1M tokens, down from $0.18.Who it's for: This feature is for developers and retrieval teams building semantic search, RAG, and agentic applications, especially with long documents and chunk-level retrieval. It's ideal for customers who want maximal retrieval accuracy without manually tuning their embedding pipeline.Why it matters: By capturing full document context in every chunk embedding, voyage-context-4 improves retrieval quality across nearly every domain while removing chunking as a design concern, with no extra LLM calls or preprocessing logic. As a drop-in replacement priced below voyage-context-3, it raises accuracy and lowers cost at the same time.How to get started: voyage-context-4 is available now through the Voyage AI API and the MongoDB Atlas Embedding and Reranking API -- simply swap in the model name voyage-context-4 or pass a full document with enable_auto_chunking=True. New users get 200 million free tokens.

What it is: MongoDB Search and Vector Search for Enterprise Advanced are now generally available, bringing integrated full-text and vector search to self-hosted enterprise MongoDB deployments. Customers can deploy dedicated search nodes in Kubernetes through MongoDB Controllers for Kubernetes (MCK), connect them securely to MongoDB Enterprise Advanced clusters, and run modern search and AI retrieval workloads directly on their MongoDB data. This allows teams to build keyword search, semantic search, recommendations, and retrieval-augmented application experiences without introducing a separate search platform. Why it matters: Organizations running MongoDB in on-premises, private cloud, hybrid, and regulated environments often need modern search and AI capabilities on data that cannot leave their infrastructure. Historically, that has meant adding separate search engines or vector databases and maintaining synchronization pipelines between systems. With general availability, Enterprise Advanced customers can now run integrated MongoDB Search and Vector Search on infrastructure they control, using the same MongoDB query model and security foundations they already rely on. The result is a simpler architecture, fewer moving parts to operate, and a clearer path to building production-grade search and AI-powered experiences in self-managed environments.Who it’s for: MongoDB Search and Vector Search for Enterprise Advanced are designed for enterprise customers running self-hosted MongoDB who need modern search and AI retrieval capabilities on infrastructure they control. This is especially relevant for organizations in regulated or security-sensitive environments, teams that want to eliminate separate search platforms and synchronization pipelines, and Enterprise Advanced customers looking to build semantic search, recommendations, and retrieval-augmented application experiences on data that must remain on-premises or in private and hybrid cloud environments.How to get started: MongoDB Search and Vector Search are available as a paid add-on to MongoDB Enterprise Advanced subscriptions. Contact your MongoDB account team for pricing details. To get started with deploying Search and Vector Search, use a supported MongoDB Enterprise Advanced deployment together with MongoDB Controllers for Kubernetes to deploy and manage dedicated search nodes. Search nodes can connect securely to existing Enterprise Advanced deployments, including databases running on virtual machines, bare metal, or Kubernetes, so customers can adopt search without replatforming their entire database estate. For deployment guidance, architecture details, and commercial information about the Enterprise Advanced Search add-on, refer to the MongoDB documentation and your MongoDB account team.