Back Issues/Search Home → Calendar → Archive → RSS → Subscribe → Services → Vendors → Blog → Current Issue → Popular → Newsletters (LinkedIn, Substack)

All issues › Volume 344, Issue 2 › IT Vendor News › MongoDB

AI Search for Agents: Announcing Automated Embedding in MongoDB Atlas

MongoDB, Monday, November 9th, 2026

MongoDB brings Automated Embedding to Atlas Vector Search, keeping vectors in sync with data using Voyage AI embedding models.

MongoDB announced Automated Embedding for Vector Search on MongoDB Atlas in public preview, with an update noting general availability as of August 12, 2026.

The feature removes the need for a separate embedding pipeline by generating embeddings with Voyage AI models inside Atlas, and field-level delta detection re-embeds a document in near real time only when an indexed field changes, including through views.

Inference is split so index builds are throughput-optimized on a new Inference Flex Tier while queries are latency-optimized.

Configurable quantization, with scalar as the default at roughly 4x smaller than float32, and built-in dynamic batching reduce storage cost and failed jobs.

more →  ·  More from MongoDB →