MongoDB has made the engine behind its Search and Vector Search inspectable for self-managed users, giving developers greater control to build reliable AI and RAG systems.
MongoDB has released the source code for mongot, the engine powering MongoDB Search and Vector Search, under the Server Side Public License (SSPL). The move gives self-managed users increased visibility, control, and debugging capabilities, enabling the creation of production-grade retrieval-augmented generation (RAG) systems for AI workloads.
Previously an Atlas-only service, mongot was opaque to developers. Now, teams can inspect how text and vector queries are indexed, executed, and ranked.
“By making mongot’s source code publicly available, MongoDB is turning what was previously an Atlas-only…opaque service into inspectable components, allowing developers to understand how text and vector queries are indexed, executed, and ranked,” — Sanjeev Mohan, Principal Analyst, SanjMo.
While the SSPL allows developers to view, use, modify, and share the code, it is not fully open source. “Like open-source licenses, the SSPL enables developers to view, use, modify, and share the related source code. It does not meet all the criteria of the Open Source Initiative’s Open Source definition…,” — David Menninger, Executive Director of Software Research, ISG.
“Rather, the SSPL is ‘designed specifically’ to stop MongoDB’s competitors from taking its free code and selling it as a managed service without paying for it,” — Bradley Shimmin, Lead, Data & Analytics Practice, The Futurum Group.
Developers now gain access to full search capabilities without relying on Atlas.
“Previously, if a developer wanted the full MongoDB search experience, they had to be on its managed cloud, Atlas. By releasing the source code, MongoDB is effectively removing the functional wall between their cloud service and their self-managed/Community version,” — Stephanie Walter, Practice Lead, AI Stack, HyperFRAME Research.
MongoDB has also added automated vector embedding capability to the Community Edition, simplifying RAG pipelines and challenging vector-specialty databases.
“This is a direct shot at Pinecone. If the database you already use can handle the complex embedding pipeline for you, there’s really little reason to buy a separate vector-only database,” — Stephanie Walter.
“It also puts pressure on specialised vector database players to offer more than just storage,” — Bradley Shimmin.
Both mongot source code and automated embeddings are currently in preview.
