MongoDB is excited to announce the public preview of search and vector search capabilities for use with MongoDB Community Edition and MongoDB Enterprise Server. These new capabilities empower developers to prototype, iterate, and build sophisticated, AI-powered applications directly in self-managed environments with robust search functionality.

Versatility is one of the reasons why developers love MongoDB. MongoDB can run anywhere.1 This includes local setups where many developers kickstart their MongoDB journey, to the largest enterprise data centers when it is time to scale, and MongoDB’s fully managed cloud service, MongoDB Atlas. Regardless of where development takes place, MongoDB effortlessly integrates with any developer’s workflow.

MongoDB Community Edition is the free, source-available version of MongoDB that millions of developers use to learn, test, and grow their skills. MongoDB Enterprise Server is the commercial version of MongoDB’s core database. It offers additional enterprise-grade features for companies that prefer to self-manage their deployments on-premises or in public, private, or hybrid cloud environments.

With native search and vector search capabilities now available for use with Community Edition and Enterprise Server, MongoDB aims to deliver a simpler and consistent experience for building great applications wherever they are deployed.

What is search and vector search?

Similar to the offerings in MongoDB Atlas, MongoDB Community Edition and MongoDB Enterprise Server now support two distinct yet complementary search capabilities:

Full-text search is an embedded capability that delivers a seamless, scalable experience for building relevance-based app features. Vector search enables developers to build intelligent applications powered by semantic search and generative AI using native, full-featured vector database capabilities. There are no functional limitations on the core search aggregation stages in this public preview. Therefore, $search, $searchMeta, and $vectorSearch are all supported with functional parity to what is available in Atlas, excluding features in a preview state. For more information, check out the search and vector search documentation pages.

Solving developer challenges with integrated search

Historically, integrating advanced search features into self-managed applications often required bolting on external search engines or vector databases to MongoDB. This approach created friction at every stage for developers and organizations, leading to:

Architectural complexity: Managing and synchronizing data across multiple, disparate systems added layers of complexity, demanded additional skills, and complicated development workflows. Operational overhead: Handling separate provisioning, security, upgrades, and monitoring for each system placed a heavy load on DevOps teams. Decreased developer productivity: Developers are forced to learn and use different query APIs and languages for both the database and the search engine. This resulted in frequent context switching, steeper learning curves, and slower release cycles. Consistency challenges: Aligning the primary database with separate search or vector indexes risked producing out-of-sync results. Despite promotions of transactional guarantees and data consistency, these indexes were only eventually consistent. This led to incomplete results in rapidly changing environments. With search and vector search now integrated into MongoDB Community Edition and MongoDB Enterprise Server, these trade–offs disappear. Developers can now create powerful search capabilities using MongoDB’s familiar query framework, removing the synchronization burden and the need to manage multiple single-purpose systems. This release simplifies data architecture, reduces operational overhead, and accelerates application development.

With these capabilities, developers can harness sophisticated out-of-the-box capabilities to build a variety of powerful applications. Potential use cases include:

Use Case Description Keyword/Full-text search Autocomplete and fuzzy search Create real-time suggestions and correct spelling errors as users type, improving the search experience Search faceting Apply quick filtering options in applications like e-commerce, so users can narrow down search results based on categories, price ranges, and more Internal search tools Build search tools for internal use or for applications with sensitive data that require on-premises deployment Vector search AI-powered semantic search Implement semantic search and recommendation systems to provide more relevant results than traditional keyword matching Retrieval-augmented generation (RAG) Use search to retrieve factual data from a knowledge base to bring accurate, context-aware data into large language model (LLM) applications AI agents Create agents that utilize tools to collect context, communicate with external systems, and execute actions Hybrid search Hybrid search Combine keyword and vector search techniques Data processing Text analysis Perform text analysis directly in the MongoDB database MongoDB offers native integrations with frameworks such as LangChain, LangGraph, and LlamaIndex. This streamlines workflows, accelerates development, and embeds RAG or agentic features directly into applications. To learn more about other AI frameworks supported by MongoDB, check out this documentation.

MongoDB’s partners and champions are already experiencing the benefits from utilizing search and vector search across a wider range of environments:

“We’re thrilled that MongoDB search and vector search are now accessible in the already popular MongoDB Community Edition. Now our customers can leverage MongoDB and LangChain in either deployment mode and in their preferred environment to build cutting-edge LLM applications.”—Harrison Chase, CEO, LangChain.

“MongoDB has helped Clarifresh build awesome software, and I’ve always been impressed with its rock-solid foundations. With search and vector search capabilities now available in MongoDB Community Edition, we gain the confidence of accessible source code, the flexibility to deploy anywhere, and the promise of community-driven extensibility. It’s an exciting milestone that reaffirms MongoDB’s commitment to developers.”—Luke Thompson, MongoDB Champion, Clarifresh.

“We’re excited about the next interaction of search experiences in MongoDB Community Edition. Our customers want the highest flexibility to be able to run their search and gen AI-enabled applications, and bringing this functionality to Community unlocks a whole new way to build and test anywhere.”—Jerry Liu, CEO, LlamaIndex.

“Participating in the Private Preview of Full-text and Vector Search for MongoDB Community has been an exciting opportunity. Having $search, $searchMeta, and $vectorSearch directly in Community Edition brings the same powerful capabilities we use in Atlas—without additional systems or integrations. Even in early preview, it’s already streamlining workflows and producing faster, more relevant results.”—Michael Höller, MongoDB Champion, akazia Consulting.

Accessing the public preview

The public preview is available for free and is intended for testing, evaluation, and feedback purposes only.

Search and Vector Search with MongoDB Community Edition. The new capabilities are compatible with MongoDB version 8.2+, and operate on a separate binary, mongot, which interacts with the standard mongodb database binary.

To get started, ensure that:

A MongoDB Community Server cluster is running using one of the following three methods:

• Download MongoDB Community Server version 8.2 from the MongoDB Downloads page. As of public preview, this feature is available for self-managed deployments on supported Linux distributions and architectures for MongoDB Community Edition version 8.2+.
• Download the ```mongot``` binary from the MongoDB Downloads page.
• Pull the container image for Community Server 8.2 from a public Docker Hub repository.
• Coming soon: Deploy using the MongoDB Controllers for Kubernetes Operator (Search Support for Community Server is planned for version 1.5+). Search and Vector Search for use with MongoDB Enterprise Server. The new capabilities are deployed as self-managed search nodes in a customer’s Kubernetes environment. This will seamlessly connect to any MongoDB Enterprise Server clusters, residing inside or outside Kubernetes itself.

To get started, ensure that:

A MongoDB Enterprise Server cluster is running.

• version 8.0.10+ (for MongoDB Controllers for Kubernetes operator 1.4).
• version 8.2+ (for MongoDB Controllers for Kubernetes operator 1.5+). A Kubernetes environment. The MongoDB Controllers for Kubernetes Operator are installed in the Kubernetes cluster. Find installation instructions here. Comprehensive documentation for setup for MongoDB Community Edition and MongoDB Enterprise Server is also available.

What’s next?

During the public preview, MongoDB will deliver additional updates and roadmap features based on customer feedback. After the public preview, these search and vector search capabilities are anticipated to be generally available for use with on-premise deployments. For Community Edition, these capabilities will be available at no additional cost as part of the Server Side Public License (SSPL).

For MongoDB Enterprise Server, these capabilities will be included in a new paid subscription offering that will launch in the future. Pricing and packaging details for the subscription will be available closer to launch. For developers seeking a fully managed experience in the cloud, MongoDB Atlas offers a production-ready version of these capabilities today.

MongoDB would love to hear feedback! Suggest new features or vote on existing ideas at feedback.mongodb.com. The input is critical for shaping the future of this product. Users can contact their MongoDB account team to provide more comprehensive feedback.

---

1 MongoDB can be deployed as a fully managed multi-cloud service across all major public cloud providers, in private clouds, locally, on-premises and hybrid environments.