Building Gen AI with MongoDB & AI Partners | February 2025

February was big for MongoDB—and, more importantly, for anyone looking to build AI applications that deliver highly accurate, relevant information (in other words, for everyone building AI apps). MongoDB announced the acquisition of Voyage AI, a pioneer in state-of-the-art embedding and reranking models that power next-generation AI applications.

Because generative AI is by nature probabilistic, models can “hallucinate”, and generate false or misleading information. This can lead to serious risks, especially in cases or industries (e.g., financial services) where accurate information is paramount. To address this, organizations building AI apps need high-quality retrieval; they need to trust that the most relevant information is extracted from their data with precision.

Voyage AI’s advanced embedding and reranking models enable applications to extract meaning from highly specialized and domain-specific text and unstructured data. With roots at Stanford and MIT, Voyage AI’s world-class team is trusted by AI innovators like Anthropic, LangChain, Harvey, and Replit. Integrating Voyage AI’s technology with MongoDB will enable organizations to easily build trustworthy, AI-powered applications by offering highly accurate and relevant information retrieval deeply integrated with operational data.

For more, check out MongoDB CEO Dev Ittycheria’s blog post about Voyage AI, and what this means for developers and businesses (in short, delivering high-quality results at scale). Onward!

P.S. If you’re in Vegas for HumanX this week, stop by booth 412 to say hi to MongoDB!

Welcoming new AI and tech partners

The Voyage AI news was hardly the only exciting development last month. In February 2025, MongoDB welcomed three new AI and tech partners that offer product integrations with MongoDB. Read on to learn more about each great new partner!

CopilotKit

Logo for CopilotKit

Seattle-based CopilotKit provides open source infrastructure for in-app AI copilots. CopilotKit helps organizations build production-ready copilots and agents effortlessly.

“We’re excited to be partnering with MongoDB to help companies build best-in-class copilots that leverage RAG & take action based on internal data,” said Uli Barkai, Co-Founder and Chief Marketing Officer at CopilotKit. “MongoDB made it dead simple to build a scalable vector database with operational data. This collaboration enables developers to easily ship production-grade RAG applications.”

Varonis

Logo for Varonis

Varonis is the leader in data security, protecting data wherever it lives—across SaaS, IaaS, and hybrid cloud environments. Varonis’ cloud-native Data Security Platform continuously discovers and classifies critical data, removes exposures, and detects advanced threats with AI-powered automation.

“Varonis’s mission is to protect data wherever it lives,” said David Bass, Executive Vice President of Engineering and Chief Technology Officer at Varonis. “We are thrilled to further advance our mission by offering AI-powered data security and compliance for MongoDB, the database of choice for high-performance application and AI development. With this integration, joint customers can automatically discover and classify sensitive data, detect abnormal activities, secure AI data pipelines, and prevent data leaks.”

Xlrt

Xlrt is an automated insight-generation platform that enables financial institutions to create innovative financial credit products at scale by simplifying the financial spreading process.

“We are excited to partner with MongoDB Atlas to transform AI-driven financial workflows,” said Rupesh Chaudhuri, Chief Operating Officer and Co-Founder of Xlrt. “XLRT.ai leverages agentic AI, combining graph-based contextualization, vector search, and LLMs to redefine data-driven decision-making. With MongoDB's robust NoSQL and vector search capabilities, we’re delivering unparalleled efficiency, accuracy, and scalability in automating financial processes.”

To learn more about building AI-powered apps with MongoDB, check out our AI Learning Hub and stop by our Partner Ecosystem Catalog to read about our integrations with MongoDB’s ever-evolving AI partner ecosystem. And visit the MongoDB AI Applications Program (MAAP) page to learn how MongoDB and the MAAP ecosystem helps organizations build applications with advanced AI capabilities.

← Previous

ZEE5: A Masterclass in Migrating Microservices to MongoDB Atlas

ZEE5 is a leading Indian over-the-top (OTT) video-streaming platform that delivers streamed content via Internet-connected devices. The platform offers a wide variety of content—movies, TV shows, web series, and original programming—across multiple genres and languages. Owned by Zee Entertainment Enterprises Limited , ZEE5 produces over 260 hours of content daily, with a monthly active user base of more than 119.5 million users across 190 countries. ZEE5’s operations and customer satisfaction are dependent on its backend infrastructure being robust and scalable to handle immense traffic and complex workflows. In order to future-proof its infrastructure and to maintain its competitive edge, the company needed to streamline operations and enhance its database management capabilities. This included the migration of its entire OTT platform, including a total of 100+ microservices and 80+ databases to Google Cloud. Pramod Prakash, Senior Vice President of Engineering at ZEE5, was on the stage of MongoDB.local Bangalore in 2024 . He shared insights into how ZEE5 managed this migration without hindering performance or disrupting its services. “It was a massive project which required a very carefully orchestrated migration plan,” said Prakash. Massive migration, zero downtime: Challenge accepted ZEE5’s team embarked on an ambitious journey to migrate a total of 40+ microservices (out of its 100+ microservices) to MongoDB Atlas . These were previously running on the Community Edition of MongoDB and on other NoSQL databases. One of the challenges of this migration was to ensure continuous data flow for the platform’s 119.5 million streaming users. To do so, Prakash and his team created multiple environments using a change data capture tool . This ensured continuous replication of data so the user experience would not be impacted. “We had to build four environments: dev, QA [Quality Assurance], UAT [User Acceptance Testing], and production,” explained Prakash. “We needed to keep testing and verifying each environment, and then finally enter the production phase when we migrated the data and moved the traffic.” The approach involved migrating production data twice: first for testing and then for the final cutover. This was to minimize any data loss. ZEE5 used MongoDB Atlas’ integrated tools mongosync and mongomirror . The tools helped achieve an essential goal: avoiding any downtime. “We migrated this entire mammoth application with zero downtime!” said Prakash. “We have not stopped ZEE5’s operations at all.” “The second important thing is the performance: you want to be 100% sure that the entire scale and peak traffic will work seamlessly within the new cloud environment,” added Prakash. ZEE5 relied on MongoDB Professional Services (PS)’s support. The PS team helped architect and plan the entire migration strategy. They also accompanied Prakash’s team step by step to ensure there would be no unexpected disruptions. The production environment was built and tested rigorously before the final migration to ensure seamless performance at peak traffic levels. “We iterated until we were 100% sure that the new environment was ready to take up ZEE5’s peak traffic. Functionally, it was all perfect,” said Prakash. The power of the Atlas platform According to Prakash, the power of MongoDB Atlas lies in the fact that it offers a fully managed platform. “There is no maintenance overhead at all,” he said. “All upgrades happen automatically without any downtime. We are also leveraging auto-scaling capabilities and point-in-time recovery.” All of this enables efficient handling of varying traffic loads without manual intervention. Additionally, data recovery capabilities are enhanced, and most importantly, the engineering team can prioritise application development rather than operational maintenance. As of February 2025, MongoDB Atlas supports a total of seven key use cases at ZEE5: payments, subscriptions, plans and coupons, video engineering, Zee Music (users’ preferences and playlists), content metadata, and the platform’s communication engine (SMS and email notifications). Looking ahead, ZEE5 is working on more use cases powered by MongoDB. For example, the company is looking to completely migrate their master data source for content metadata to MongoDB Atlas. ZEE5 is also considering relying on MongoDB Atlas to support and enhance its search and recommendations capabilities. Interested in learning how MongoDB is powering other companies applications? Head over to our customer case studies hub to read the latest stories. Visit our product page to learn more about MongoDB Atlas .

March 11, 2025
Next →

ORiGAMi: A Machine Learning Architecture for the Document Model

The document model has proven to be the optimal paradigm for modern application schemas. At MongoDB, we've long understood that semi-structured data formats like JSON offer superior expressiveness compared to traditional tabular and relational representations. Their flexible schema accommodates dynamic and nested data structures, naturally representing complex relationships between data entities. However, the machine learning (ML) community has faced persistent challenges when working with semi-structured formats. Traditional ML algorithms, as implemented in popular libraries like scikit-learn and pandas , operate on the assumption of fixed-dimensional tabular data consisting of rows and columns. This fundamental mismatch forces data scientists to manually convert JSON documents into tabular form—a time-consuming process that requires significant domain expertise. Recent advances in natural language processing (NLP) demonstrate the power of Transformers in learning from unstructured data but their application to semi-structured data has been under-studied. To bridge this gap, MongoDB's ML research group has developed a novel Transformer-based architecture designed for supervised learning on semi-structured data (e.g., JSON data in a document model database). We call this new architecture ORiGAMi (Object Representation through Generative, Autoregressive Modelling), and we're excited to make it available to the community at github.com/mongodb-labs/origami . It includes components that make training a Transformer model feasible on datasets entailing as few as 200 labeled samples. By combining this data efficiency with the flexibility of Transformers, ORiGAMi enables prediction directly from semi-structured documents, without the cumbersome flattening and manual feature extraction required for tabular data representation. You can read more about our model on arXiv . Technical innovation The key insight behind ORiGAMi lies in its tokenization strategy: documents are transformed into sequences of key-value pairs and special structural tokens that encode nested types like arrays and subdocuments: These token sequences serve as input to the Transformer model trained to predict the next token given a portion of the document, similar to how large language models (LLMs) are trained on text tokens. What’s more, our modifications to the standard Transformer architecture include guardrails to ensure that the model only generates valid, well-formed documents, and a novel position encoding strategy that respects the order invariance of key/value pairs in JSON. These modifications also allow for much smaller models compared to LLMs, which can thus be trained on consumer hardware in minutes to hours depending on dataset size and complexity, versus days to weeks for LLMs. By reformulating classification as a next-token prediction task, ORiGAMi can predict any field within a document, including complex types like arrays and nested subdocuments. This unified approach eliminates the need for separate models or preprocessing pipelines for different prediction tasks. Example use case Our initial focus has been supervised learning: training models from labeled data to make predictions on unseen documents. Let's explore a practical example of user segmentation. Consider a collection where each document represents a user profile, containing both simple fields and complex nested structures: { "_id": "user_7842", "email": "sarah.chen@example.com", "signup_date": "2024-01-15", "device_history": [ { "device": "mobile_ios", "first_seen": "2024-01-15", "last_seen": "2024-02-11" }, { "device": "desktop_chrome", "first_seen": "2024-01-16", "last_seen": "2024-02-10" } ], "subscription": { "plan": "pro", "billing_cycle": "annual", "features_used": ["analytics", "api_access", "team_sharing"], "usage_metrics": { "storage_gb": 45.2, "api_calls_per_day": 1250, "active_projects": 8 } }, "user_segment": "enterprise_power_user" // <-- target field } Suppose you want to automatically classify users into segments like "enterprise_power_user", "smb_growth", or "early_stage_startup" based on their behavior and characteristics. Some documents in your collection already have correct labels, perhaps assigned through manual analysis or customer interviews. Traditional ML approaches would require flattening this rich document structure, leading to very sparse tables and potentially losing important hierarchical relationships. With ORiGAMi, you can: Train directly on the raw documents with existing labels Preserve the full context of nested structures and arrays Make predictions for the "user_segment" field on new users immediately after signup Update predictions as user behavior evolves without rebuilding feature pipelines Getting started with ORiGAMi We're excited to be open-sourcing ORiGAMi ( github.com/mongodb-labs/origami ) and you can read more about our model on arXiv . We've also included a command-line interface that lets users make predictions without writing any code. Training a model is as simple as pointing ORiGAMi to your MongoDB collection: origami train <mongo-uri> -d app -c users Once trained, you can generate predictions and seamlessly integrate them back into your MongoDB workflow. For example, to predict user segments for new signups (from the analytics.signups collection ) and write the resulting predictions back to MongoDB to an analytics.predicted collection: origami predict <mongo-uri> -d analytics -c signups --target user_segment --json | mongoimport -d analytics -c predicted For those looking to dive deeper, we've also included several Jupyter notebooks in the repository that demonstrate advanced features and customization options. Model performance can be improved by adjusting the hyperparameters. We're just scratching the surface of what's possible with document-native machine learning, and have many more use cases in mind. We invite you to explore the repository, contribute to the project, and share how you use ORiGAMi to solve real-world problems. Head over to the ORiGAMi github repo , play around with it, and tell us about new ways of applying it and problems it’s well-suited to solving.

March 11, 2025