GenAI

107 results

The MongoDB AI Applications Program: Delivering Customer Value

When people ask me about MongoDB, I tell them that they’ve probably interacted with MongoDB without realizing it. In fact, many of the world’s leading companies—including 70% of the Fortune 100—are powered by MongoDB. Everything we do at MongoDB is about serving our customers, but that often happens in the background, where our work is invisible to many users. In my case, that means building an ecosystem of partners who enable customer innovation. A recent example is how MongoDB teamed up with Amazon Web Services (AWS) and Amazon Bedrock to help Base39 —a Brazilian fintech provider—automate loan analysis, decreasing decision time from three days to one hour, and reducing cost per loan analysis by 96%. And there’s the Indian company IndiaDataHub, which joined the MongoDB AI Applications Program (MAAP) to access AI expertise, in-depth support, and a full spectrum of technologies to enhance AI functionality within IndiaDataHub’s analytics platform. This includes connecting relevant data in MongoDB with Meta's AI models to perform sentiment analysis on text datasets. I could go on and on—after all, tens of thousands of MongoDB’s customers have success stories like these. Enabling customer success is precisely why we launched MAAP last summer, and why the program has evolved since. Customers tell us that they want to take advantage of AI, but they’re unsure how to navigate a fast-moving market, how to control costs, and how to unlock business value from their AI investments. So with MAAP, MongoDB offers customers a full AI stack and an integrated set of professional services to help them keep pace with the latest innovations, identify the best AI use cases, and to help them future-proof AI investments. With today’s announcement , Capgemini, Confluent, IBM, QuantumBlack, AI by McKinsey, and Unstructured have joined the 22 companies that now comprise the MAAP partner network. Which means that the MAAP ecosystem (which was founded with Accenture, Anthropic, Anyscale, Arcee AI, AWS, Cohere, Credal, Fireworks AI, Google Cloud, gravity9, LangChain, LlamaIndex, Microsoft Azure, Nomic, PeerIslands, Pureinsights, and Together AI) offers additional cutting-edge AI integration and solutions to customers—and more ways to set them on the path to AI success. CentralReach: Making an impact on autism with AI More than 150 customers have already gotten involved with MAAP, but I’m particularly excited to share the work of CentralReach . CentralReach provides an AI-powered electronic medical record (EMR) platform that is designed to improve outcomes for children and adults diagnosed with autism and related intellectual and developmental disabilities (IDD). Prior to working with MongoDB and MAAP, CentralReach was looking for an experienced partner to further connect and aggregate its more than 4 billion financial and clinical data points across its suite of solutions. CentralReach leveraged MongoDB’s document model to aggregate the company’s diverse forms of information from assessments to clinical data collection, so the company could build rich AI-assisted solutions on top of its database. Meanwhile, MAAP partners helped CentralReach to design and optimize multiple layers of its comprehensive buildout. All of this will enable CentralReach to support initiatives such as value-based outcome measurement, clinical supervision, and care delivery efficacy. With these new data layers in place, providers will be able to make substantial improvements to their clinical delivery to optimize care for all those they serve. “As a mission-driven organization, CentralReach is always looking to innovate on behalf of the clinical professionals—and the more than 350,000 autism and IDD learners—that we serve globally,” said Chris Sullens, CEO of CentralReach. “So being able to lean on MongoDBs database technology and draw on the collective expertise of the MAAP partner network—in addition to MongoDB’s tech expertise and services—to help us improve outcomes for our customers and their clients worldwide has been invaluable.” Working backward from customer needs The addition of Capgemini, Confluent, IBM, QuantumBlack, AI by McKinsey, and Unstructured to the MAAP partner network offers customers additional technology and AI support options. It also builds on MongoDB’s larger partner ecosystem , which is designed to give customers flexibility and choice. By working closely with our partners on product launches, integrations, and real-world challenges, MongoDB has been able to bring a better understanding of the challenges facing customers—and to give them the resources and confidence to move forward with groundbreaking technology like AI . Examples of support MAAP has offered customers include: Guidance on chunking strategies for an AI-native healthcare provider providing patient recommendations based on complex data sources Collaboration on advanced retrieval techniques to improve response accuracies for a large consultancy to automate manual research Evaluation of embedding models for multi-modal data stores for a well-known automaker developing diagnostic applications Guidance on architectures for complex agentic workflows for a mature enterprise technology provider augmenting customer service workflows One way we offer this support is through the MAAP Center of Excellence (CoE). The MAAP CoE comprises AI technical experts from across MongoDB and the MAAP partner ecosystem who collaborate with customers to understand their challenges, technical requirements, and timelines. The MAAP CoE can then recommend custom full-stack architectures and implementation best practices, optimized for the customer’s specific use case and requirements. Indeed, customization is intrinsic to MAAP: MongoDB and our MAAP partners will meet customers wherever they are to help them achieve their goals. For example, if an organization wants to fully own its AI application development, MongoDB and partners can provide guidance and expertise. And in cases where customers want hands-on support, we can help speed projects with professional services. Ultimately, we want MAAP customers—and anyone who works with MongoDB’s partner ecosystem at large—to feel empowered to own their application development, and to transform challenges into opportunities. Let’s build the next big thing together! To learn more about building AI-powered apps with MongoDB, see MongoDB’s AI Resources Hub , the Partner Ecosystem Catalog , or visit the MAAP page . And check out our partner Confluent’s own blog post about MAAP!

December 2, 2024

New Course for Building AI Applications with MongoDB on AWS

Developers everywhere want to expand the limits of what they can build with new generative AI technologies. But the AI market and its offerings have evolved so quickly that for many developers, keeping up can feel overwhelming. As we’ve entered the AI era, MongoDB and Amazon Web Services (AWS) have built upon our eight year partnership to deliver technology integrations—like MongoDB Atlas’s integrations with Amazon Bedrock and Amazon Q Developer (formerly CodeWhisperer)—that simplify the process of building and deploying gen AI applications. By combining MongoDB’s integrated operational and vector database capabilities with AWS’s AI infrastructure solutions, our goal is to make it easier for our developer community to innovate with AI. So, to help developers get started, we’re launching a new, free MongoDB Learning Badge focused on Building AI Applications with MongoDB on AWS . Building AI with MongoDB on AWS This is MongoDB University’s first AWS Learning Badge, and with it, we’ve focused on teaching developers how Amazon Bedrock and Atlas work together—including how to create a knowledge base in Amazon Bedrock, configure a knowledge base to use Atlas, inspect how a query is answered, create an Agent to answer questions based on data in Atlas, and configure guardrails that support responsible agentic behavior. In short, developers will learn how to remove the heavy lifting of infrastructure configuration and integration so they can get up and running with innovative new semantic search and RAG applications faster. Amazon Bedrock is a fully managed service from AWS that offers a choice of high-performing foundation models from leading AI companies via a single API, along with a broad set of capabilities organizations need to build secure, high-performing AI applications. Developers can connect Bedrock to MongoDB Atlas for blazing-fast vector searches and secure vector storage with minimal coding. With the integration, developers’ can use their proprietary data alongside industry-leading foundation models to launch AI applications that deliver hyper-intelligent and hyper-relevant results. Tens of thousands of customers are running MongoDB Atlas on AWS, and many have already embarked successfully on cutting-edge AI journeys. Take Scalestack for example, which used MongoDB Atlas Vector Search to build a RAG-powered AI copilot, named Spotlight, and is now using Bedrock’s customizable models to enhance Spotlight’s relevance and performance. Meanwhile, Base39 —a Brazilian fintech provider—used MongoDB Atlas and Amazon Bedrock to automate loan analysis, decreasing decision time from three days to one hour and reducing cost per loan analysis by 96%. Badge up with MongoDB MongoDB Learning Badges are a powerful way to demonstrate your dedication to continuous learning. These digital credentials not only validate your educational accomplishments but also stand as a testament to your expertise and skill. Whether you're a seasoned developer, an aspiring data scientist, or an enthusiastic student, earning a MongoDB badge can elevate your professional profile and unlock new opportunities in your field. Learn, prepare, and earn Complete the Learning Badge Path and pass a brief assessment to earn your badge. Upon completion, you'll receive an email with your official Credly badge and digital certificate, ready to share on social media, in email signatures, or on your resume. Additionally, you'll gain inclusion in the Credly Talent Directory, where you will be visible to recruiters from top employers. Millions of builders have been trained through MongoDB University courses—join them and get started building your AI future with MongoDB Atlas and AWS. And if you’re attending AWS re:Invent 2024, come find MongoDB at Booth #824. The first 100 people to receive their learning badge will receive a special gift! Start learning today

December 2, 2024

AI-Powered Call Centers: A New Era of Customer Service

Customer satisfaction is critical for insurance companies. Studies have shown that companies with superior customer experiences consistently outperform their peers. In fact, McKinsey found that life and property/casualty insurers with superior customer experiences saw a significant 20% and 65% increase in Total Shareholder Return , respectively, over five years. A satisfied customer is a loyal customer. They are 80% more likely to renew their policies, directly contributing to sustainable growth. However, one major challenge faced by many insurance companies is the inefficiency of their call centers. Agents often struggle to quickly locate and deliver accurate information to customers, leading to frustration and dissatisfaction. This article explores how Dataworkz and MongoDB can transform call center operations. By converting call recordings into searchable vectors (numerical representations of data points in a multi-dimensional space), businesses can quickly access relevant information and improve customer service. We'll dig into how the integration of Amazon Transcribe, Cohere, and MongoDB Atlas Vector Search—as well as Dataworkz's RAG-as-a-service platform— is achieving this transformation. From call recordings to vectors: A data-driven approach Customer service interactions are goldmines of valuable insights. By analyzing call recordings, we can identify successful resolution strategies and uncover frequently asked questions. In turn, by making this information—which is often buried in audio files— accessible to agents, they can give customers faster and more accurate assistance. However, the vast volume and unstructured nature of these audio files make it challenging to extract actionable information efficiently. To address this challenge, we propose a pipeline that leverages AI and analytics to transform raw audio recordings into vectors as shown in Figure 1: Storage of raw audio files: Past call recordings are stored in their original audio format Processing of the audio files with AI and analytics services (such as Amazon Transcribe Call Analytics ): speech-to-text conversion, summarization of content, and vectorization Storage of vectors and metadata: The generated vectors and associated metadata (e.g., call timestamps, agent information) are stored in an operational data store Figure 1: Customer service call insight extraction and vectorization flow Once the data is stored in vector format within the operational data store, it becomes accessible for real-time applications. This data can be consumed directly through vector search or integrated into a retrieval-augmented generation (RAG) architecture, a technique that combines the capabilities of large language models (LLMs) with external knowledge sources to generate more accurate and informative outputs. Introducing Dataworkz: Simplifying RAG implementation Building RAG pipelines can be cumbersome and time-consuming for developers who must learn yet another stack of technologies. Especially in this initial phase, where companies want to experiment and move fast, it is essential to leverage tools that allow us to abstract complexity and don’t require deep knowledge of each component in order to experiment with and realize the benefits of RAG quickly. Dataworkz offers a powerful and composable RAG-as-a-service platform that streamlines the process of building RAG applications for enterprises. To operationalize RAG effectively, organizations need to master five key capabilities: ETL for LLMs: Dataworkz connects with diverse data sources and formats, transforming the data to make it ready for consumption by generative AI applications. Indexing: The platform breaks down data into smaller chunks and creates embeddings that capture semantics, storing them in a vector database. Retrieval: Dataworkz ensures the retrieval of accurate information in response to user queries, a critical part of the RAG process. Synthesis: The retrieved information is then used to build the context for a foundational model, generating responses grounded in reality. Monitoring: With many moving parts in the RAG system, Dataworkz provides robust monitoring capabilities essential for production use cases. Dataworkz's intuitive point-and-click interface (as seen in Video 1) simplifies RAG implementation, allowing enterprises to quickly operationalize AI applications. The platform offers flexibility and choice in data connectors, embedding models, vector stores, and language models. Additionally, tools like A/B testing ensure the quality and reliability of generated responses. This combination of ease of use, optionality, and quality assurance is a key tenet of Dataworkz's "RAG as a Service" offering. Diving deeper: System architecture and functionalities Now that we’ve looked at the components of the pre-processing pipeline, let’s explore the proposed real-time system architecture in detail. It comprises the following modules and functions (see Figure 2): Amazon Transcribe , which receives the audio coming from the customer’s phone and converts it into text. Cohere ’s embedding model, served through Amazon Bedrock , vectorizes the text coming from Transcribe. MongoDB Atlas Vector Search receives the query vector and returns a document that contains the most semantically similar FAQ in the database. Figure 2: System architecture and modules Here are a couple of FAQs we used for the demo: Q: “Can you explain the different types of coverage available for my home insurance?” A: “Home insurance typically includes coverage for the structure of your home, your personal belongings, liability protection, and additional living expenses in case you need to temporarily relocate. I can provide more detailed information on each type if you'd like.” Q: “What is the process for adding a new driver to my auto insurance policy?" A: “To add a new driver to your auto insurance policy, I'll need some details about the driver, such as their name, date of birth, and driver's license number. We can add them to your policy over the phone, or you can do it through our online portal.” Note that the question is reported just for reference, and it’s not used for retrieval. The actual question is provided by the user through the voice interface and then matched in real-time with the answers in the database using Vector Search. This information is finally presented to the customer service operator in text form (see Fig. 3). The proposed architecture is simple but very powerful, easy to implement, and effective. Moreover, it can serve as a foundation for more advanced use cases that require complex interactions, such as agentic workflows , and iterative and multi-step processes that combine LLMs and hybrid search to complete sophisticated tasks. Figure 3: App interface, displaying what has been asked by the customer (left) and how the information is presented to the customer service operator (right) This solution not only impacts human operator workflows but can also underpin chatbots and voicebots, enabling them to provide more relevant and contextual customer responses. Building a better future for customer service By seamlessly integrating analytical and operational data streams, insurance companies can significantly enhance both operational efficiency and customer satisfaction. Our system empowers businesses to optimize staffing, accelerate inquiry resolution, and deliver superior customer service through data-driven, real-time insights. To embark on your own customer service transformation, explore our GitHub repository and take advantage of the Dataworkz free tier .

November 27, 2024

Better Digital Banking Experiences with AI and MongoDB

Interactive banking represents a new era in financial services where customers engage with digital platforms that anticipate, understand, and meet their needs in real-time. This approach encompasses AI-driven technologies such as chatbots, virtual assistants, and predictive analytics that allow banks to enhance digital self-service while delivering personalized, context-aware interactions. According to Accenture’s 2023 consumer banking study , 44% of consumers aged 18-44 reported difficulty accessing human support when needed, underscoring the demand for more responsive digital solutions that help bridge this gap between customers and financial services. Generative AI technologies like chatbots and virtual assistants can fill this need by instantly addressing inquiries, providing tailored financial advice, and anticipating future needs. This shift has tremendous growth potential; the global chatbot market is expected to grow at a CAGR of 23.3% from 2023 to 2030 , with the financial sector experiencing the fastest growth rate of 24.0%. This shift is more than just a convenience; it aims to create a smarter, more engaging, and intuitive banking journey for every user. Simplifying self-service banking with AI Navigating daily banking activities like transfers, payments, and withdrawals can often raise immediate questions for customers: “Can I overdraft my account?” “What will the penalties be?” or “How can I avoid these fees?” While the answers usually lie within the bank’s terms and conditions, these documents are often dense, complex, and overwhelming for the average user. At the same time, customers value their independence and want to handle their banking needs through self-service channels, but wading through extensive fine print isn't what they signed up for. By integrating AI-driven advisors into the digital banking experience, banks can provide a seamless, in-app solution that delivers instant, relevant answers. This removes the need for customers to leave the app to sift through pages of bank documentation in search of answers, or worse, endure the inconvenience of calling customer service. The result is a smoother and user-friendly interaction, where customers feel supported in their self-service journey, free from the frustration of navigating traditional, cumbersome information sources. The entire experience remains within the application, enhancing convenience and efficiency. Solution overview This AI-driven solution enhances the self-service experience in digital banking by applying Retrieval-Augmented Generation (RAG) principles, which combine the power of generative AI with reliable information retrieval, ensuring that the chatbot provides accurate, contextually relevant responses. The approach begins by processing dense, text-heavy documents, like terms and conditions, often the source of customer inquiries. These documents are divided into smaller, manageable chunks vectorized to create searchable data representations. Storing these vectorized chunks in MongoDB Atlas allows for efficient querying using MongoDB Atlas Vector Search , making it possible to instantly retrieve relevant information based on the customer’s question. Figure 1: Detailed solution architecture When a customer inputs a question in the banking app, the system quickly identifies and retrieves the most relevant chunks using semantic search. The AI then uses this information to generate clear, contextually relevant answers within the app, enabling a smooth, frustration-free experience without requiring customers to sift through dense documents or contact support. Figure 2: Leafy Bank mock-up chatbot in action How MongoDB supports AI-driven banking solutions MongoDB offers unique capabilities that empower financial institutions to build and scale AI-driven applications. Unified data model for flexibility: MongoDB’s flexible document model unifies structured and unstructured data, creating a consistent dataset that enhances the AI’s ability to understand and respond to complex queries. This model enables financial institutions to store and manage customer data, transaction history, and document content within a single system, streamlining interactions and making AI responses more contextually relevant. Vector search for enhanced querying: MongoDB Atlas Vector Search makes it easy to perform semantic searches on vectorized document chunks, quickly retrieving the most relevant information to answer user questions. This capability allows the AI to find precise answers within dense documents, enhancing the self-service experience for customers. Scalable integration with AI models: MongoDB is designed to work seamlessly with leading AI frameworks, allowing banks to integrate and scale AI applications quickly and efficiently. By aligning MongoDB Atlas with cloud-based LLM providers, banks can use the best tools available to interpret and respond to customer queries accurately, meeting demand with responsive, real-time answers. High performance and cost efficiency: MongoDB’s multi-cloud, developer-friendly platform allows financial institutions to innovate without costly infrastructure changes. It’s built to scale as data and AI needs to grow, ensuring banks can continually improve the customer experience with minimal disruptions. MongoDB’s built-in scalability allows banks to expand their AI capabilities effortlessly, offering a future-proof foundation for digital banking. Building future-proof applications Implementing generative AI presents several advantages, not only for end-users of the interactive banking applications but also for financial institutions: Enhanced user experience encourages customer satisfaction, ensures retention, boosts reputation, and reduces customer turnover while unlocking new opportunities for cross-selling and up-selling to increase revenue, drive growth and elevate customer value. Moreover, adopting AI-driven initiatives prepares the groundwork for businesses to develop innovative, creative, and future-proof applications to address customer needs and upgrade business applications with features that are shaping the industry and will continue to do so, here are some examples: Summarize and categorize transactional information by powering applications with MongoDB’s Real-Time Analytics . Understand and find trends based on customer behavior that could positively impact and leverage fraud prevention , anti-money laundering (AML) , and credit card application (just to mention a few). Offering investing, budgeting, and loan assessments through AI-powered conversational banking experience. In today’s data-driven world, companies face increasing pressure to stay ahead of rapid technological advancements and ever-evolving customer demands. Now more than ever, businesses must deliver intuitive, robust, and high-performing services through their applications to remain competitive and meet user expectations. Luckily, MongoDB provides businesses with comprehensive reference architectures for building generative AI applications, an end-to-end technology stack that includes integrations with leading technology providers, professional services, and a coordinated support system through the MongoDB AI Applications Program (MAAP) . By building AI-enriched applications with the leading multi-cloud developer data platform, companies can leverage low-cost, efficient solutions through MongoDB’s flexible and scalable document model which empowers businesses to unify real-time, operational, unstructured, and AI-related data, extending and customizing their applications to seize upcoming technological opportunities. Check out these additional resources to get started on your AI journey with MongoDB: How Leading Industries are Transforming with AI and MongoDB Atlas - E-book Our Solutions Library is where you can learn about different use cases for gen AI and other interesting topics that are applied to financial services and many other industries.

November 26, 2024

MongoDB, Microsoft Team Up to Enhance Copilot in VS Code

As modern applications grow increasingly complex, developers face the challenge of meeting market demands for faster, smarter solutions. To stay ahead, they need tools that streamline their workflows, available directly in the environments where they build. According to the 2024 Stack Overflow Developer Survey , Microsoft’s Visual Studio Code (VS Code) is the integrated development environment (IDE) of choice for 74% of professional developers, serving as a central hub for building, testing, and deploying applications. With the rise of AI-powered tools like GitHub Copilot—which is used by 44% of professional developers—there’s a growing demand for intelligent assistance in the development process without disrupting flow. At MongoDB, we believe that the future of development lies in democratizing the value of these experiences by incorporating domain-specific knowledge and capabilities directly into developer flows. That’s why we’re thrilled to announce the public preview of MongoDB’s extension to GitHub Copilot in VS Code. With this integration, developers can effortlessly generate MongoDB queries, inspect collection schemas, and get answers from the latest MongoDB docs—all without leaving their IDE. Our collaboration with MongoDB continues to bring powerful, integrated solutions to developers building the modern applications of the future. The new MongoDB extension for GitHub Copilot exemplifies a shared commitment to the developer experience, leveraging AI to ensure that workflows are optimized for developer productivity by keeping everything developers need within reach, without breaking their flow. Isidor Nikolic, Senior Product Manager for VS Code, Microsoft But we’re not stopping there. As AI continues to evolve, so will the ways developers interact with their tools. Stay tuned for more exciting developments next week at Microsoft Ignite , where we’ll unveil more ways we’re pushing the boundaries of what’s possible with AI through MongoDB and Microsoft’s partnership! What is MongoDB's Copilot extension? MongoDB’s Copilot extension supercharges your GitHub Copilot in VS Code with MongoDB domain knowledge. The Copilot integration is built into the MongoDB for VS Code extension , which has more than 1.8M downloads in the VS Code marketplace today. Type ‘@MongoDB’ in Copilot chat and take advantage of three transformative commands: Generate queries from natural language (/query) —this generates accurate MongoDB queries by passing collection schema as context to Github Copilot Query MongoDB documentation (/docs) —this answers any documentation questions using the latest MongoDB documentation through Retrieval-Augmented Generation (RAG) Browse collection schema (/schema) —this provides schema information for any collection and is useful for data modeling with the Copilot extension. Generate queries from natural language This command transforms natural language prompts into MongoDB queries, leveraging your collection schema to produce precise, valid queries. It eliminates the need to manually write complex query syntax, and allows developers to quickly extract data without taking their focus away from building applications. Whether you run the query directly from the Copilot chat or refine it in a MongoDB playground file, we’ve sped up the query-building process by deeply integrating these capabilities into the existing flow of MongoDB VS Code extension. Query MongoDB documentation The /docs command answers MongoDB documentation-specific questions, complemented by direct links to the official documentation site. There’s no need to switch back and forth between your browser and your IDE; the Copilot extension calls out to the MongoDB Documentation Chatbot API that leverages retrieval-augmented generation technology to generate responses that are informed by the most recent version of the MongoDB documentation. In the near future, these questions will be smartly routed to documentation for the specific server version of the cluster you are connected to in the MongoDB VS Code extension. Browse collection schema The /schema command offers quick access to collection schemas, making it easier for developers to access and interact with their data model in real-time. This can be helpful in situations where developers are debugging with Copilot or just want to know valid field names while developing their applications. Developers can additionally export collection schemas into JSON files or ask follow-up questions directly to brainstorm data modeling techniques with the MongoDB Copilot extension. On the Horizon This is just the start of our work on MongoDB’s Copilot extension. As we continue to improve the experience with new features—like translating and testing queries to and from popular programming languages, and in-line query generation in Playgrounds—we remain focused on democratizing AI-driven workflows, empowering developers to access the tools and knowledge they need to build smarter, faster, and more efficiently, right within their existing environments. Download MongoDB’s VS Code extension and enable the MongoDB chat experience to get started today.

November 13, 2024

Building Gen AI with MongoDB & AI Partners | October 2024

It’s no surprise that AI is a topic of seemingly every professional conversation and meeting nowadays—my friends joke that 11 out of 10 words that come out of my mouth are “gen AI.” But an important question remains: do organizations truly know how to harness AI, or do they simply feel pressured to join the crowd? Are they driven by FOMO more than anything else? One thing is for sure: adopting generative AI still presents a huge learning curve. Which is why we’ve been working to provide the right tools for companies to build innovative gen AI apps with, and why we offer organizations a variety of AI knowledge and guidance, regardless of where they are with gen AI. We’re fortunate to work with our industry-leading partners to help educate and shape this nascent market. Working so closely with them on product launches, integrations, and solving real-world challenges allows us to bring diverse perspectives and a better understanding of AI to our customers, giving them the technology and confidence to move forward even before engaging with tough use cases and specific technical problems (something that the MongoDB AI Applications Program can definitely help with). One of our main educational initiatives has been our webinar series with our top-tier MAAP partners. We’ve constantly launched video content to deepen understanding of topics essential to gen AI for enterprises answering broader questions such as “ how can my company generate AI-driven outcomes ” and “ how can I modernize my workload ,” to specific, tangible topics such as “ how to build a chatbot that knows my business .” Each session is designed to move beyond the basics, sharing insights from experts in AI, and addressing our customers’ burning questions and challenges that matter most to them. Welcoming new AI and tech partners In October, we also welcomed four new AI and tech partners that offer product integrations with MongoDB. Read on to learn more about each great new partner! Astronomer Astronomer empowers data teams to bring mission-critical software, analytics, and AI to life and is the company behind Astro, the industry-leading data orchestration and observability platform powered by Apache Airflow. " Astronomer's partnership with MongoDB is redefining RAG workflows for GenAI workloads. By integrating Astronomer's managed Apache Airflow platform with MongoDB Atlas' powerful vector database capabilities, we enable organizations to orchestrate complex data pipelines that fuel advanced AI and machine learning applications”, said Julian LaNeve, CTO at Astronomer. “This collaboration empowers data teams to manage real-time, high-dimensional data with ease, accelerating the journey from raw data to actionable insights and transforming how businesses harness the power of generative AI." CloudZero CloudZero is a cloud cost optimization platform that automates the collection, allocation, and analysis of cloud costs to identify savings opportunities and improve cloud efficiency rates. "Database spending is one of the shared costs that can make it tricky for organizations to reach 100% cost allocation. CloudZero eliminates that problem," said Anand Sundaram, Senior Vice President of Product at CloudZero. “ Our industry-leading allocation engine can organize MongoDB spend in a matter of hours , tracing it precisely to the products, features, customers, and/or teams responsible for it. This way, companies get a clear view of what’s driving their costs, who’s accountable, and how to optimize to maximize their cloud efficiency.” ObjectBox ObjectBox is an on-device vector database for mobile, IoT, and embedded devices that enables storing, syncing, and querying data locally online and offline. " We’re thrilled to partner with MongoDB to give developers an edge,” celebrated Vivien Dollinger, CEO and co-founder of ObjectBox. “By combining MongoDB’s cloud and scalability with ObjectBox’s high-performance on-device database and data sync, we empower developers to build fast, data-rich applications that feel right at home across devices and environments. Offline, online, edge, cloud, whenever, wherever... We’re here to enable your data with speed and reliability." Rasa Rasa is a flexible framework for building conversational AI platforms that lets companies develop scalable generative AI assistants that hit the market faster. “ Rasa is excited to partner with MongoDB to empower companies in building conversational AI experiences. Together, we’re helping create generative AI assistants that save costs, speed up development, and maintain full brand control and security,” said Melissa Gordon, CEO of Rasa. “With MongoDB, deploying production-ready generative AI assistants is seamless, and we’re eager to continue accelerating our customers’ journey toward trusted conversational AI solutions.” But wait, there's more! Whether you’re starting out or scaling up, MongoDB and our partners are here with the resources, expertise, and trusted guidance to help you succeed in your genAI strategy! And if you have any suggestions for a good webinar topic, don’t hesitate to reach out. To learn more about building AI-powered apps with MongoDB, check out our AI Resources Hub and stop by our Partner Ecosystem Catalog to read about our integrations with MongoDB’s ever-evolving AI partner ecosystem.

November 11, 2024

MongoDB and Partners: Building the AI Future, Together

If you’re like me, over the past year you’ve closely watched AI’s developments—and the world’s reactions to them. From infectious excitement about AI’s capabilities, to impatience with its cost and return on investment, every day has been filled with AI twists and turns. It’s been quite the roller coaster. During the ride, from time to time I’ve wondered where AI falls on the Gartner hype cycle, which gives "a view of how a technology or application will evolve over time." Have we hit the "peak of inflated expectations" only to fall into the "trough of disillusionment?" Or is the hype cycle an imperfect guide, as The Economist argues? The reality is that it takes time for any new technology—even transformative ones like AI—to take hold. And every advance, no matter how big, has had its detractors. A famous example is that of Picasso (!), who in 1968 said, “Computers are useless. They can only give you answers.” (!!) For our part, MongoDB is convinced that AI is a once-in-a-generation technology that will enhance every future application—a belief that has been reinforced by the incredible work our partners have shared at MongoDB’s 2024 events. Speeding AI development MongoDB is committed to helping organizations of all sizes succeed with AI, and one way we’re doing that is by collaborating with the MongoDB partner ecosystem to create powerful, user-friendly AI development tools and solutions. For example, Fireworks.ai —which is a member of the MongoDB AI Applications Program ecosystem —created an inference solution that hosts gen AI models and supports containerized deployments. This tool makes it easier for developers to build and deploy powerful applications with a range of easy-to-use tools and customization options. They can choose to use state-of-the-art, open-source language, image, and multimodal foundation models off the shelf, or they can customize and fine-tune models to their needs. Jointly, Fireworks.ai and MongoDB provide a solution for developers who want to leverage highly curated and optimized open-source models and combine these with their organization’s own proprietary data—and to do so with unparalleled speed and security. “MongoDB is one of the most sophisticated database providers, and it’s very easy to use,” said Benny Chen , cofounder of Fireworks.ai. "We want developers to be able to use these tools, and we want to work with providers who enable and empower developers." Nomic , another MAAP ecosystem member, also enables developers with best-in-class solutions across the entire unstructured data workflow. Their Embed offering, available through the Nomic API , allows users to vectorize large-scale datasets for use in text, image, and multimodal retrieval applications, including retrieval-augmented generation (RAG), using only their web browser. The Nomic-MongoDB solution is a highly efficient, open-weight model that developers can use to visualize the unstructured datasets they store in MongoDB Atlas . These insights help users quickly discover trends and articulate data-driven value propositions. Nomic also supported the recently announced vector quantization in MongoDB Atlas Vector Search , which reduces vector sizes while preserving performance. Last—but hardly least!—there’s our new reference architecture with MAAP partners AWS and Anthropic. Announced at MongoDB.local London , the reference architecture supports building memory-enhanced AI agents, and is designed to streamline complex processes and develop smarter, more responsive applications. For more—including a link to the code on Github— check out the MongoDB Developer Center . Making AI work for anyone and everyone The companies MongoDB partners with aren’t just making gen AI easier for developers—they’re building tools for everyone. For example, Capgemini has invested $2 billion in gen AI and is training 100,000 of its employees in the technology. GenYoda, a solution that helps insurance professionals with their daily work, is a product of this investment. GenYoda leverages MongoDB Atlas Vector Search to analyze large amounts of customer data, like policy statements, premiums, claims history, and health information. Using GenYoda, insurance professionals can quickly analyze underwriters’ reports to make informed decisions, create longitudinal health summaries, and streamline customer interactions to improve contact center efficiency. GenYoda can ingest 100,000 documents in just a few hours and respond to users’ queries in two to three seconds—a metric on par with the most widely used gen AI models. And it produces results: in one example, by using Capgemini’s solution an insurer was able to increase productivity by 15%, add new reports 25% faster (thus speeding decision-making), and reduce the manual effort of searching PDFs, increasing efficiency by 10%. Building the future of AI together So, what’s next? Honestly, I’m as curious as you are. But I’m also incredibly excited. At MongoDB, we’re active participants in the AI revolution, working to embrace the possibilities that lie ahead. The future of gen AI is bright, and I can’t wait to see what we’ll build together. To learn more about how MongoDB can accelerate your AI journey, explore the MongoDB AI Applications Program .

November 4, 2024

Reflections On Our Recent AI "Think-A-Thon"

Interesting ideas are bound to emerge when great minds come together, so there was no shortage of interesting ideas on October 2nd, when MongoDB’s Developer Relations team hosted our second-ever AI Build Together event at MongoDB.local London. In some ways, the event is similar to a hackathon: a group of developers come together to solve a problem. But in other ways, the event is quite different. While hackathons normally take an entire day and involve intensive coding, the AI Build Together events are organized to take place over just a few hours and don't involve any coding at all. Instead, it’s all based around discussion and ideation. For these reasons, MongoDB’s Developer Relations team likes to dub them “think-a-thons.” Our first AI Build Together event was held earlier this year at .local NYC. After seeing the energy in the room and the excitement from attendees, our Developer Relations team knew it wanted to host another one. The .local London event’s fifty attendees—which included developers from numerous industries and leading AI innovators who served as mentors—came together to brainstorm and discuss AI-based solutions to common industry problems. .local London AI Build Together attendees brainstorming AI solutions for the healthcare industry The AI mentors included: Loghman Zadeh (gravity9), Ben Gutkovich (Superlinked), Jesse Martin (Hasura), Marlene Mhangami (Microsoft), Igor Alekseev (AWS), and John Willis and Patrick Debois (co-founders of DevOps). Upon arrival, participants joined a workflow group best aligned with their industry and/or area of interest—AI for Education, AI for DevOps, AI for Healthcare, AI for Optimizing Travel, AI for Supply Chain, and AI for Productivity. The AI for Productivity group collaborating on their workflow The discussions were lively, and it was amazing to see how much energy these attendees brought to their discussions. For example, the AI for Education workflow group vigorously discussed developing a personalized AI education coach to help students develop their educational plans and support them with career advice. Meanwhile, the AI for Healthcare workflow group focused on the idea of creating an AI drive tool to provide personalized healthcare to patients and real-time insights to their providers. The AI for Productivity team came up with a clever product that helps you read, digest, and identify the key aspects of long legal documents. The AI for Optimizing Travel group seeking advice from AI mentor Marlene A talented artist was also brought in to visualize each workflow group’s problem statements and potential solutions—literally and figuratively illustrating their innovative ideas. Graphic recorder Maria Foulquié putting the final touches on the illustration Final illustration documenting the 2024 MongoDB.local London AI Build Together event All in all, our second time hosting this event was deemed a success by everyone involved. “It was impressive to see how attendees, regardless of their technical background, found ways to contribute to complex AI solutions,” says Loghman Zadeh, AI Director at gravity9, who served as one of the event’s advisors. “Engaging with so many creative and forward-thinking individuals, all eager to push the boundaries of AI innovation was refreshing. The collaborative atmosphere fostered dynamic discussions and allowed participants to explore new ideas in a supportive environment.” If you’re interested in taking part in events like these—which offer a range of networking opportunities—there are three more MongoDB.local events slated for 2024—Sao Paulo, Paris, and Stockholm. Additionally, you can join your local MongoDB user group to learn from and connect with other MongoDB developers in your area.

October 23, 2024

Announcing Hybrid Search Support for LlamaIndex

MongoDB is excited to announce enhancements to our LlamaIndex integration. By combining MongoDB’s robust database capabilities with LlamaIndex’s innovative framework for context-augmented large language models (LLMs), the enhanced MongoDB-LlamaIndex integration unlocks new possibilities for generative AI development. Specifically, it supports vector (powered by Atlas Vector Search ), full-text (powered by Atlas Search ), and hybrid search, enabling developers to blend precise keyword matching with semantic search for more context-aware applications, depending on their use case. Building AI applications with LlamaIndex LlamaIndex is one of the world’s leading AI frameworks for building with LLMs. It streamlines the integration of external data sources, allowing developers to combine LLMs with relevant context from various data formats. This makes it ideal for building application features like retrieval-augmented generation (RAG), where accurate, contextual information is critical. LlamaIndex empowers developers to build smarter, more responsive AI systems while reducing the complexities involved in data handling and query management. Advantages of building with LlamaIndex include: Simplified data ingestion with connectors that integrate structured databases, unstructured files, and external APIs, removing the need for manual processing or format conversion. Organizing data into structured indexes or graphs , significantly enhancing query efficiency and accuracy, especially when working with large or complex datasets. An advanced retrieval interface that responds to natural language prompts with contextually enhanced data, improving accuracy in tasks like question-answering, summarization, or data retrieval. Customizable APIs that cater to all skill levels—high-level APIs enable quick data ingestion and querying for beginners, while lower-level APIs offer advanced users full control over connectors and query engines for more complex needs. MongoDB's LlamaIndex integration Developers are able to build powerful AI applications using LlamaIndex as a foundational AI framework alongside MongoDB Atlas as the long term memory database. With MongoDB’s developer-friendly document model and powerful vector search capabilities within MongoDB Atlas, developers can easily store and search vector embeddings for building RAG applications. And because of MongoDB’s low-latency transactional persistence capabilities, developers can do a lot more with MongoDB integration in LlamIndex to build AI applications in an enterprise-grade manner. LlamaIndex's flexible architecture supports customizable storage components, allowing developers to leverage MongoDB Atlas as a powerful vector store and a key-value store. By using Atlas Vector Search capabilities, developers can: Store and retrieve vector embeddings efficiently ( llama-index-vector-stores-mongodb ) Persist ingested documents ( llama-index-storage-docstore-mongodb ) Maintain index metadata ( llama-index-storage-index-store-mongodb ) Store Key-value pairs ( llama-index-storage-kvstore-mongodb ) Figure adapted from Liu, Jerry and Agarwal, Prakul (May 2023). “Build a ChatGPT with your Private Data using LlamaIndex and MongoDB”. Medium. https://medium.com/llamaindex-blog/build-a-chatgpt-with-your-private-data-using-llamaindex-and-mongodb-b09850eb154c Adding hybrid and full-text search support Developers may use different approaches to search for different use cases. Full-text search retrieves documents by matching exact keywords or linguistic variations, making it efficient for quickly locating specific terms within large datasets, such as in legal document review where exact wording is critical. Vector search, on the other hand, finds content that is ‘semantically’ similar, even if it does not contain the same keywords. Hybrid search combines full-text search with vector search to identify both exact matches and semantically similar content. This approach is particularly valuable in advanced retrieval systems or AI-powered search engines, enabling results that are both precise and aligned with the needs of the end-user. It is super simple for developers to try out powerful retrieval capabilities on their data and improve the accuracy of their AI applications with this integration. In the LlamaIndex integration, the MongoDBAtlasVectorSearch class is used for vector search. All you have to do is enable full-text search, using VectorStoreQueryMode.TEXT_SEARCH in the same class. Similarly, to use Hybrid search, enable VectorStoreQueryMode.HYBRID . To learn more, check out the GitHub repository . With the MongoDB-LlamaIndex integration’s support, developers no longer need to navigate the intricacies of Reciprocal Rank Fusion implementation or to determine the optimal way to combine vector and text searches—we’ve taken care of the complexities for you. The integration also includes sensible defaults and robust support, ensuring that building advanced search capabilities into AI applications is easier than ever. This means that MongoDB handles the intricacies of storing and querying your vectorized data, so you can focus on building! We’re excited for you to work with our LlamaIndex integration. Here are some resources to expand your knowledge on this topic: Check out how to get started with our LlamaIndex integration Build a content recommendation system using MongoDB and LlamaIndex with our helpful tutorial Experiment with building a RAG application with LlamaIndex, OpenAI, and our vector database Learn how to build with private data using LlamaIndex, guided by one of its co-founders

October 17, 2024

Building Gen AI with MongoDB & AI Partners | September 2024

Last week I was in London for MongoDB.local London —the 19th stop of the 2024 MongoDB.local tour—where MongoDB, our customers, and our AI partners came together to share solutions we’ve been building that enable companies to accelerate their AI journey. I love attending these events because they offer an opportunity to celebrate our collective achievements, and because it’s great to meet so many (mainly Zoom) friends in person! One of the highlights of MongoDB.local London 2024 was the release of our reference architecture with our MAAP partners AWS and Anthropic , which supports memory-enhanced AI agents. This architecture is already helping businesses streamline complex processes and develop smarter, more responsive applications. We also announced a robust set of vector quantization capabilities in MongoDB Atlas Vector Search that will help developers build powerful semantic search and generative AI applications with more scale—and at a lower cost. Now, with support for the ingestion of scalar quantized vectors, you can import and work with quantized vectors from your embedding model providers of choice, including MAAP partners Cohere, Nomic, and others. A big thank you to all of MongoDB’s AI partners, who continually amaze me with their innovation. MongoDB.local London was another great reminder of the power of collaboration, and I’m excited for what lies ahead as we continue to shape the future of AI together. As the Brits say: Cheers! Welcoming new AI and tech partners In September we also welcomed seven new AI and tech partners that offer product integrations with MongoDB. Read on to learn more about each great new partner! Arize Arize AI is a platform that helps organizations visualize and debug the flow of data through AI applications by quickly identifying bottlenecks in LLM calls and understanding agentic paths. "At Arize AI, we are committed to helping AI teams build, evaluate, and troubleshoot cutting-edge agentic systems. Partnering with MongoDB allows us to provide a comprehensive solution for managing the memory and retrieval that these systems rely on”, said Jason Lopatecki, co-founder and CEO of Arize AI. “With MongoDB’s robust vector search and flexible document storage, combined with Arize’s advanced observability and evaluation tools, we’re empowering developers to confidently build and deploy AI applications." Baseten Baseten provides the applied AI research and infrastructure needed to serve custom and open-source machine learning models performantly, scalably, and cost-efficiently. " We're excited to partner with MongoDB to combine their scalable vector database with Baseten's high-performance inference infrastructure and high-performance models. Together, we're enabling companies to build and deploy generative AI applications, such as RAG apps, that not only scale infinitely but also deliver optimal performance per dollar,” said Tuhin Srivastava, CEO of Baseten. “This partnership empowers developers to bring mission-critical AI solutions to market faster, while maintaining cost-effectiveness at every stage of growth." Doppler Doppler is a cloud-based platform that helps teams manage, organize, and secure secrets across environments and applications that can be used throughout the entire development lifecycle. “Doppler rigorously focuses on making the easy path, the most secure path for developers. This is only possible with deep product partnerships with all the tooling developers have come to love. We are excited to join forces with MongoDB to make zero-downtime secrets rotation for non-relational databases effortlessly simple to set up and maintenance-free,” said Brian Vallelunga, founder and CEO of Doppler. “This will immediately bolster the security posture of a company’s most sensitive data without any additional overhead or distractions." Haize Labs Haize Labs automates language model stress testing at massive scales to discover and eliminate failure modes. This, alongside their inference-time mitigations and observability tools, enables the risk-free adoption of AI. " We're thrilled to partner with MongoDB in empowering companies to build RAG applications that are both powerful yet secure, safe, and reliable,” said Leonard Tang, co-founder and CEO of Haize Labs. “MongoDB Atlas has streamlined the process of developing production-ready GenAI systems, and we're excited to work together to accelerate customers' journey to trust and confidence in their GenAI initiatives." Modal Modal is a serverless platform for data and AI/ML engineers to run and deploy code in the cloud without having to think about infrastructure. Run generative AI models, large-scale batch jobs, job queues, and more, all faster than ever before. “The coming wave of intelligent applications will be built on the potent combination of foundation models, large-scale data, and fast search,” explained Charles Frye, AI Engineer at Modal. “MongoDB Atlas provides an excellent platform for storing, querying, and searching data, from hot new techniques like vector indices to old standbys like lexical search. It's the perfect counterpart to Modal's flexible compute, like serverless GPUs. Together, MongoDB and Modal make it easy to get started with this new paradigm, and then they make it easy to scale it out to millions of users querying billions of records & maxing out thousands of GPUs.” Portkey AI Portkey AI is an AI gateway and observability suite that helps companies develop, deploy, and manage LLM-based applications. " Our partnership with MongoDB is a game-changer for organizations looking to operationalize AI at scale. By combining Portkey's LLMOps expertise with MongoDB's comprehensive data solution, we're enabling businesses to deploy, manage, and scale AI applications with unprecedented efficiency and control,” said Ayush Garg, Chief Technology Officer of Portkey AI. “Together, we're not just streamlining the path from POC to production; we're setting a new standard for how businesses can leverage AI to drive innovation and deliver tangible value." Reka Reka offers fully multimodal models including images, videos with audio, text, and documents to empower AI agents that can see, hear, and speak. "At Reka, we know how challenging it can be to retrieve information buried in unstructured multimodal data. We are excited to join forces with MongoDB to help companies test and optimize multimodal RAG features for faster production deployment,” said Dani Yogatama, CEO of Reka. “Our models understand and reason over multimodal data including text, tables, and images in PDF documents or conversations in videos. Our joint solution streamlines the whole RAG development lifecycle, speeding up time to market and helping companies deliver real values to their customers faster." But wait, there's more! To learn more about building AI-powered apps with MongoDB, check out our AI Resources Hub , and stop by our Partner Ecosystem Catalog to read about our integrations with MongoDB’s ever-evolving AI partner ecosystem.

October 9, 2024

Introducing Two MongoDB Generative AI Learning Badges

Want to boost your resume quickly? MongoDB is introducing two new Learning Badges , Building gen AI Apps and Deploying and Evaluating gen AI Apps. Unlike high-stakes certifications, which cover a large breadth and depth of subjects, these digital credentials are focused on specific topics, making them easier and quicker to earn. Best of all, they’re free! The Building Gen AI Applications with MongoDB Learning Badge validates users’ knowledge of developing gen AI applications using MongoDB Atlas Vector Search. It recognizes your understanding of semantic search and how to build chatbots with retrieval-augmented generation (RAG), MongoDB, and Langchain. The Deploying and Evaluating Gen AI Applications with MongoDB Learning Badge validates users’ knowledge of optimizing the performance and evaluating the results of gen AI applications. It recognizes your understanding of chunking strategies, performance evaluation techniques, and deployment options within MongoDB for both prototyping and production stages. Learn, prepare, and earn To earn your badge, simply complete the Learning Badge Path and take a short assessment at the end. Once you pass the short assessment, you'll receive an email with your official Credly badge and digital certificate. You can share it on social media, in email signatures, or on digital resumes. Additionally, you'll gain inclusion in the Credly Talent Directory , where you will be visible to recruiters from top employers and can open up new career opportunities. Learning paths are like curated roadmaps that guide you through essential concepts and skills needed for the assessment. Each badge has its own learning path: Building Gen AI Apps Learning Badge Path: This learning path guides you through the foundations of building a gen AI application with MongoDB Atlas Vector Search. You'll learn what semantic search is and how you can leverage it across a variety of use cases. Then you'll learn how to build your own chatbot by creating a RAG application with MongoDB and Langchain. Deploying and Evaluating Gen AI Apps Learning Badge Path: This learning path will help you take a gen AI application from creation to full deployment, with a focus on optimizing performance and evaluating results. You'll explore chunking strategies, performance evaluation techniques, and deployment options in MongoDB for both prototyping and production stages. We recommend completing the Building gen AI Apps Learning Badge Path before beginning this path. Badge up with MongoDB MongoDB Learning Badges offer a valuable opportunity to showcase your commitment to continuous learning and expertise in specific topics. These digital credentials not only recognize your educational achievements but also serve as a testament to your knowledge and skills. Whether you're a seasoned developer, an aspiring data scientist, or an enthusiastic student, earning a MongoDB badge can significantly enhance your profile and open up new opportunities in your field. Start earning your badges today—it’s quick, effective, and free! Visit MongoDB Learning Badges to begin your journey toward becoming a gen AI application expert and boosting your career prospects.

October 8, 2024

Vector Quantization: Scale Search & Generative AI Applications

We are excited to announce a robust set of vector quantization capabilities in MongoDB Atlas Vector Search . These capabilities will reduce vector sizes while preserving performance, enabling developers to build powerful semantic search and generative AI applications with more scale—and at a lower cost. In addition, unlike relational or niche vector databases, MongoDB’s flexible document model—coupled with quantized vectors—allows for greater agility in testing and deploying different embedding models quickly and easily. Support for scalar quantized vector ingestion is now generally available, and will be followed by several new releases in the coming weeks. Read on to learn how vector quantization works and visit our documentation to get started! The challenges of large-scale vector applications While the use of vectors has opened up a range of new possibilities , such as content summarization and sentiment analysis, natural language chatbots, and image generation, unlocking insights within unstructured data can require storing and searching through billions of vectors—which can quickly become infeasible. Vectors are effectively arrays of floating-point numbers representing unstructured information in a way that computers can understand (ranging from a few hundred to billions of arrays), and as the number of vectors increases, so does the index size required to search over them. As a result, large-scale vector-based applications using full-fidelity vectors often have high processing costs and slow query times, hindering their scalability and performance. Vector quantization for cost-effectiveness, scalability, and performance Vector quantization, a technique that compresses vectors while preserving their semantic similarity, offers a solution to this challenge. Imagine converting a full-color image into grayscale to reduce storage space on a computer. This involves simplifying each pixel's color information by grouping similar colors into primary color channels or "quantization bins," and then representing each pixel with a single value from its bin. The binned values are then used to create a new grayscale image with smaller size but retaining most original details, as shown in Figure 1. Figure 1: Illustration of quantizing an RGB image into grayscale Vector quantization works similarly, by shrinking full-fidelity vectors into fewer bits to significantly reduce memory and storage costs without compromising the important details. Maintaining this balance is critical, as search and AI applications need to deliver relevant insights to be useful. Two effective quantization methods are scalar (converting a float point into an integer) and binary (converting a float point into a single bit of 0 or 1). Current and upcoming quantization capabilities will empower developers to maximize the potential of Atlas Vector Search. The most impactful benefit of vector quantization is increased scalability and cost savings through reduced computing resources and efficient processing of vectors. And when combined with Search Nodes —MongoDB’s dedicated infrastructure for independent scalability through workload isolation and memory-optimized infrastructure for semantic search and generative AI workloads— vector quantization can further reduce costs and improve performance, even at the highest volume and scale to unlock more use cases. "Cohere is excited to be one of the first partners to support quantized vector ingestion in MongoDB Atlas,” said Nils Reimers, VP of AI Search at Cohere. “Embedding models, such as Cohere Embed v3, help enterprises see more accurate search results based on their own data sources. We’re looking forward to providing our joint customers with accurate, cost-effective applications for their needs.” In our tests, compared to full-fidelity vectors, BSON-type vectors —MongoDB’s JSON-like binary serialization format for efficient document storage—reduced storage size by 66% (from 41 GB to 14 GB). And as shown in Figures 2 and 3, the tests illustrate significant memory reduction (73% to 96% less) and latency improvements using quantized vectors, where scalar quantization preserves recall performance and binary quantization’s recall performance is maintained with rescoring–a process of evaluating a small subset of the quantized outputs against full-fidelity vectors to improve the accuracy of the search results. Figure 2: Significant storage reduction + good recall and latency performance with quantization on different embedding models Figure 3: Remarkable improvement in recall performance for binary quantization when combining with rescoring In addition, thanks to the reduced cost advantage, vector quantization facilitates more advanced, multiple vector use cases that would have been too computationally-taxing or cost-prohibitive to implement. For example, vector quantization can help users: Easily A/B test different embedding models using multiple vectors produced from the same source field during prototyping. MongoDB’s document model —coupled with quantized vectors—allows for greater agility at lower costs. The flexible document schema lets developers quickly deploy and compare embedding models’ results without the need to rebuild the index or provision an entirely new data model or set of infrastructure. Further improve the relevance of search results or context for large language models (LLMs) by incorporating vectors from multiple sources of relevance, such as different source fields (product descriptions, product images, etc.) embedded within the same or different models. How to get started, and what’s next Now, with support for the ingestion of scalar quantized vectors, developers can import and work with quantized vectors from their embedding model providers of choice (such as Cohere, Nomic, Jina, Mixedbread, and others)—directly in Atlas Vector Search. Read the documentation and tutorial to get started. And in the coming weeks, additional vector quantization features will equip developers with a comprehensive toolset for building and optimizing applications with quantized vectors: Support for ingestion of binary quantized vectors will enable further reduction of storage space, allowing for greater cost savings and giving developers the flexibility to choose the type of quantized vectors that best fits their requirements. Automatic quantization and rescoring will provide native capabilities for scalar quantization as well as binary quantization with rescoring in Atlas Vector Search, making it easier for developers to take full advantage of vector quantization within the platform. With support for quantized vectors in MongoDB Atlas Vector Search, you can build scalable and high-performing semantic search and generative AI applications with flexibility and cost-effectiveness. Check out these resources to get started documentation and tutorial . Head over to our quick-start guide to get started with Atlas Vector Search today.

October 7, 2024