Artificial Intelligence
Building AI-powered Apps with MongoDB
Building Gen AI with MongoDB & AI Partners | June 2024
Even for those of us who work in AI, keeping up with the latest news in the AI space can be head-spinning. In just the last few weeks, OpenAI introduced their newest model (GPT-4o), Anthropic continued to develop Claude with the launch of Claude 3.5 Sonnet, and Mistral launched Mixtral 8x22B, their most efficient open model to date. And those are only a handful of recent releases! In such an ever-changing space, partnerships are critical to combining the strengths of organizations to create solutions that would be challenging to develop independently. Also, it can be overwhelming for any one business to keep track of so much change. So there’s a lot of value in partnering with industry leaders and new players alike to bring the latest innovations to customers. I’ve been at MongoDB for less than a year, but in that time our team has already built dozens of strategic partnerships that are helping companies and developers build AI applications faster and safer. I love to see these collaborations take off! A compelling example is MongoDB’s recent work with Vercel. Our team developed an exciting sample application that allows users to deploy a retrieval-augmented generation (RAG) application on Vercel in just a few minutes. By leveraging a MongoDB URI and an OpenAI key, users can one-click deploy this application on Vercel. Another recent collaboration was with Netlify. Our team also developed a starter template that implements a RAG chatbot on top of their platform using LangChain and MongoDB Atlas Vector Search capabilities for storing and searching the knowledge base that powers the chatbot's responses. These examples demonstrate the power of combining MongoDB's robust database capabilities with other deployment platforms. They also show how quickly and efficiently users can set up fully functional RAG applications, and highlight the significant advantages that partnerships bring to the AI ecosystem. And the best part? We’re just getting started! Stay tuned for more information about the MongoDB AI Applications Program later this month. Welcoming new AI partners Speaking of partnerships, in June we welcomed seven AI partners that offer product integrations with MongoDB. Read on to learn more about each great new partner. AppMap is an open source personal observability platform to help developers keep their software secure, clear, and aligned. Elizabeth Lawler, CEO of AppMap, commented on our joint value for developers. “AppMap is thrilled to join forces with MongoDB to help developers improve and optimize their code. MongoDB is the go-to data store for web and mobile applications, and AppMap makes it easier than ever for developers to migrate their code from other data stores to MongoDB and to keep their code optimized as their applications grow and evolve.” Read more about our partnership and how to use AppMapp to improve the quality of code running with MongoDB. Mendable is a platform that automates customer services providing quick and accurate answers to questions without human intervention. Eric Ciarla, co-founder of Mendable, highlighted the importance of our partnership. "Our partnership with MongoDB is unlocking massive potential in AI applications, from go to market copilots to countless other innovative use cases,” he said. “We're excited to see teams at MongoDB and beyond harnessing our combined technologies to create transformative AI solutions across all kinds of industries and functions." Learn how Mendable and MongoDB Atlas Vector Search power customer service applications. OneAI is an API-first platform built for developers to create and manage trusted GPT chatbots. Amit Ben, CEO of One AI, shared his excitement about the partnership. "We're thrilled to partner with MongoDB to help customers bring trusted GenAI to production. OneAI's platform, with RAG pipelines, LLM-based chatbots, goal-based AI, anti-hallucination guardrails, and language analytics, empowers customers to leverage their language data and engage users even more effectively on top of MongoDB Atlas." Check out some One AI’s GPT agents & advanced RAG pipelines built on MongoDB. Prequel allows companies to sync data to and from their customers' data warehouses, databases, or object storage so they get better data access with less engineering effort. "Sharing MongoDB data just got easier with our partnership,” celebrated Charles Chretien, co-founder of Prequel. “Software companies running on MongoDB can use Prequel to instantly share billions of records with customers on every major data warehouse, database, and object storage service.” Learn how you can share MongoDB data using Prequel. Qarbine complements summary data visualization tools allowing for better informed decision-making across teams. Bill Reynolds, CTO of Qarbine, mentioned the impact of our integration to distill better insights from data: “We’re excited to extend the many MongoDB Atlas benefits upward in the modern application stack to deliver actionable insights from publication quality drill-down analysis. The native integrations enhance in-app real-time decisions, business productivity and operational data ROI, fueling modern application innovation.” Want to power up your insights with MongoDB Atlas and Qarbine? Read more . Temporal is a durable execution platform for building and scaling invincible applications faster. "Organizations of all sizes have built AI applications that are ‘durable by design’ using MongoDB and Temporal. The burden of managing data and agent task orchestration is effortlessly abstracted away by Temporal's development primitives and MongoDB's Atlas Developer Data Platform”, says Jay Sivachelvan, VP of Partnerships at Temporal. He also highlighted the benefits of this partnership. “These two solutions, together, provide compounding benefits by increasing product velocity while also seamlessly automating the complexities of scalability and enterprise-grade resilience." Learn how to build microservices in a more efficient way with MongoDB and Temporal. Unstructured is a platform that connects any type of enterprise data for use with vector databases and any LLM framework. Read more about enhancing your gen AI application accuracy using MongoDB and Unstructured. 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.
AI Apps: What the World Sees vs. What Developers See
Imagine you’re in the market for a new home in, say, Atlanta. And you’re on vacation in a different city. You see an amazing-looking house, whose design you love. You open up your favorite real estate app, snap a picture of this house, and type: “Find me a home that looks like this in Atlanta, in my price range, and within my budget, that’s also next to a park.” Seconds later, you’re served a list of homes that not only resemble this one, but match all your other specifications. This is what the world—specifically, consumers—expects when it comes to AI-powered applications. But when developers see the possibilities for these hyper-personalized, interactive, and conversational apps, they also see what goes into building them. A video showing the behind-the-scenes of an AI-powered real estate app. To make these advanced apps a reality, developers need to be able to unify operational and vector data . They also want to be able to use their preferred tools and popular LLMs. Most of all, developers are looking for a platform that makes their jobs easier—while, at the same time, providing a development experience that’s both seamless and secure. And it’s critical that developers have all of this. Because as in previous tech revolutions (the software revolution, the birth of the World Wide Web, the dawn of the smartphone, etc.), it’s developers who are leading the new AI revolution. And it’s developers who will use different kinds of data to push the boundaries of what’s possible. Take for instance audio data. Imagine a diagnostic application that records real-time sounds and turns those sounds into vectors. Then an AI model checks those sounds against a database of known issues: all of which pinpoints the specific sound that signals a potential problem that can now be fixed. Until recently, this kind of innovation wasn't possible. A video showing an AI-powered advanced diagnostics use case. This is also just the tip of the iceberg when it comes to the types of new applications that developers will build in this new era of AI. Especially when given a platform that not only makes working with operational and vector data easier, but provides an experience that developers actually love . To learn more about how developers are shaping the AI revolution, and how we at MongoDB not only celebrate them, but support them, visit www.mongodb.com/LoveYourDevelopers . There you can explore other AI use cases, see data requirements for building these more intelligent applications, discover developers who are innovating in this space, and get started with MongoDB Atlas for free .
Building Gen AI-Powered Predictive Maintenance with MongoDB
In today’s fast-evolving industrial landscape, digital transformation has become a necessity. From manufacturing plants to connected vehicles, the push towards predictive maintenance excellence is driving organizations to embrace smarter, more efficient ways of managing operations. One of the most compelling advancements in this domain is predictive maintenance powered by generative AI , a cutting-edge approach that will revolutionize how industries maintain and optimize their equipment. For manufacturers seeking maintenance excellence, a unified data store and a developer data platform are key enablers. These tools provide the foundation for integrating AI applications that can analyze sensor data, predict failures, and optimize maintenance schedules. MongoDB Atlas is the only multi-cloud developer data platform available that is designed to streamline and speed up developers' data handling. With MongoDB Atlas, developers can enhance end-to-end value chain optimization through AI/ML, advanced analytics, and real-time data processing, supporting cutting-edge mobile, edge, and IoT applications. In this post, we’ll explore the basics of predictive maintenance and how MongoDB can be used for maintenance excellence. Understanding the need for predictive maintenance Predictive maintenance is about anticipating and addressing equipment failures before they occur, ensuring minimal disruption to operations. Traditional maintenance strategies, like time-based or usage-based maintenance, are less effective than predictive maintenance because they don’t account for the varying conditions and complexities of machinery. Unanticipated equipment breakdown can result in line stoppage and substantial throughput losses, potentially leading to millions of dollars in revenue loss. Since the pandemic, many organizations have begun significant digital transformations to improve efficiency and resilience. However, a concerning gap exists between tech adoption and return on investment. While 89% of organizations have begun digital and AI transformations, only 31% have seen the expected revenue lift, and only 25% have realized the expected cost savings. These numbers highlight the importance of implementing new technologies strategically. Manufacturers need to carefully consider how AI can address their specific challenges and then integrate them into existing processes effectively. Predictive maintenance boosts efficiency and saves money Predictive maintenance uses data analysis to identify problems in machines before they fail. This allows organizations to schedule maintenance at the optimal time, maximizing machine reliability and efficiency. Indeed, according to Deloitte , predictive maintenance can lead to a variety of benefits, including: 3-5% reduction in new equipment costs 5-20% increase in labor productivity 15-20% reduction in facility downtime 10-30% reduction in inventory levels 5-20% reduction in carrying costs Since the concept was introduced, predictive maintenance has constantly evolved. We've moved beyond basic threshold-based monitoring to advanced techniques like machine learning (ML) models. These models can not only predict failures but also diagnose the root cause, allowing for targeted repairs. The latest trend in predictive maintenance is automated strategy creation. This involves using AI to not only predict equipment breakdowns but also to generate repair plans, ensuring the right fixes are made at the right time. Generative AI in predictive maintenance To better understand how gen AI can be used to build robust predictive maintenance solutions, let's dig into the characteristics of organizations that have successfully implemented AI. They exhibit common traits across five key areas: Identifying high-impact value drivers and AI use cases: Efforts should be concentrated on domains where artificial intelligence yields maximal utility rather than employing it arbitrarily. Aligning AI strategy with data strategy: Organizations must establish a strong data foundation with a data strategy that directly supports their AI goals. Continuous data enrichment and accessibility: High-quality data, readily available and usable across the organization, is essential for the success of AI initiatives. Empowering talent and fostering development: By equipping their workforce with training and resources, organizations can empower them to leverage AI effectively. Enabling scalable AI adoption: Building a strong and scalable infrastructure is key to unlocking the full potential of AI by enabling its smooth and ongoing integration across the organization. Implementing predictive maintenance using MongoDB Atlas When combined with a robust data management platform like MongoDB Atlas, gen AI can predict failures with remarkable accuracy and suggest optimal maintenance schedules. MongoDB Atlas is the only multi-cloud developer data platform designed to accelerate and simplify how developers work with data. Developers can power end-to-end value chain optimization with AI/ML, advanced analytics, and real-time data processing for innovative mobile, edge, and IoT applications. MongoDB Atlas offers a suite of features perfectly suited for building a predictive maintenance system, as shown in Figure 1 below. Its ability to handle both structured and unstructured data allows for comprehensive condition monitoring and anomaly detection. Here’s how you can build a generative AI-powered predictive maintenance software using MongoDB Atlas: Machine prioritization: This stage prioritizes machines for the maintenance excellence program using a retrieval-augmented generation (RAG) system that takes in structured and unstructured data related to maintenance costs and past failures. Generative AI revolutionizes this process by reducing manual analysis time and minimizing investment risks. At the end of this stage, the organization knows exactly which equipment or assets are well-suited for sensorization. Utilizing MongoDB Atlas, which stores both structured and unstructured data, allows for semantic searches that provide accurate context to AI models. This results in precise machine prioritization and criticality analysis. Failure prediction: MongoDB Atlas provides the necessary tools to implement failure prediction, offering a unified view of operational data, real-time processing, integrated monitoring, and seamless machine learning integration. Sensors on machines, like milling machines, collect data (e.g., air temperature and torque) and process it through Atlas Stream Processing , allowing continuous, real-time data handling. This data is then analyzed by trained models in MongoDB, with results visualized using Atlas Charts and alerts pushed via Atlas Device Sync to mobile devices, establishing an end-to-end failure prediction system. Repair plan generation: To implement a comprehensive repair strategy, generating a detailed maintenance work order is crucial. This involves integrating structured data, such as repair instructions and spare parts, with unstructured data from machine manuals. MongoDB Atlas serves as the operational data layer, seamlessly combining these data types. By leveraging Atlas Vector Search and aggregation pipelines , the system extracts and vectorizes information from manuals and past work orders. This data feeds into a large language model (LLM), which generates the work order template, including inventory and resource details, resulting in an accurate and efficient repair plan. Maintenance guidance generation: Generative AI is used to integrate service notes and additional information with the repair plan, providing enhanced guidance for technicians. For example, if service notes in another language are found in the maintenance management system, we extract and translate the text to suit our application. This information is then combined with the repair plan using a large language model. The updated plan is pushed to the technician’s mobile app via Atlas Device Sync. The system generates step-by-step instructions by analyzing work orders and machine manuals, ensuring comprehensive guidance without manually sifting through extensive documents. Figure 1: Achieving end-to-end predictive maintenance with MongoDB Atlas Developer Data Platform In the quest for operational excellence, predictive maintenance powered by generative AI and MongoDB Atlas stands out as a game-changer. This innovative approach not only enhances the reliability and efficiency of industrial operations but also sets the stage for a future where AI-driven insights and actions become the norm. By leveraging the advanced capabilities of MongoDB Atlas, manufacturers can unlock new levels of performance and productivity, heralding a new era of smart manufacturing and connected systems. If you would like to learn more about generative AI-powered predictive maintenance, visit the following resources: [Video] How to Build a Generative AI-Powered Predictive Maintenance Software [Whitepaper] Generative AI in Predictive Maintenance Applications [Whitepaper] Critical AI Use Cases in Manufacturing and Motion: Realizing AI-powered innovation with MongoDB Atlas
AI-Powered Media Personalization: MongoDB and Vector Search
In recent years, the media industry has grappled with a range of serious challenges, from adapting to digital platforms and on-demand consumption, to monetizing digital content, and competing with tech giants and new media upstarts. Economic pressures from declining sources of revenue like advertising, trust issues due to misinformation, and the difficulty of navigating regulatory environments have added to the complexities facing the industry. Additionally, keeping pace with technological advancements, ensuring cybersecurity, engaging audiences with personalized and interactive content, and addressing globalization issues all require significant innovation and investment to maintain content quality and relevance. In particular, a surge in digital content has saturated the media market, making it increasingly difficult to capture and retain audience attention. Furthermore, a decline in referral traffic—primarily from social media platforms and search engines—has put significant pressure on traditional media outlets. An industry survey from a sample of more than 300 digital leaders from more than 50 countries and territories shows that traffic to news sites from Facebook fell 48% in 2023, with traffic from X/Twitter declining by 27%. As a result, publishers are seeking ways to stabilize their user bases and to enhance engagement sustainably, with 77% looking to invest more in direct channels to deal with the loss of referrals. Enter artificial intelligence: generative AI-powered personalization has become a critical tool for driving the future of media channels. The approach we discuss here offers a roadmap for publishers navigating the shifting dynamics of news consumption and user engagement. Indeed, using AI for backend news automation ( 56% ) is considered the most important use of the technology by publishers. In this post, we’ll walk you through using MongoDB Atlas and Atlas Vector Search to transform how content is delivered to users. The shift in news consumption Today's audiences rarely rely on a single news source. Instead, they use multiple platforms to stay informed, a trend that's been driven by the rise of social media, video-based news formats, and skepticism towards traditional media due to the prevalence (or fear) of "fake news." This diversification in news sources presents a dilemma for publishers, who have come to depend on traffic from social media platforms like Facebook and Twitter. However, both platforms have started to deprioritize news content in favor of posts from individual creators and non-news content, leading to a sharp decline in media referrals. The key to retaining audiences lies in making content personalized and engaging. AI-powered personalization and recommendation systems are essential tools for achieving this. Content suggestions and personalization By drawing on user data, behavior analytics, and the multi-dimensional vectorization of media content, MongoDB Atlas and Atlas Vector Search can be applied to multiple AI use cases to revolutionize media channels and improve end-user experiences. By doing so, media organizations can suggest content that aligns more closely with individual preferences and past interactions. This not only enhances user engagement but also increases the likelihood of converting free users into paying subscribers. The essence of leveraging Atlas and Vector Search is to understand the user. By analyzing interactions and consumption patterns, the solution not only grasps what content resonates but also predicts what users are likely to engage with in the future. This insight allows for crafting a highly personalized content journey. The below image shows a reference architecture highlighting where MongoDB can be leveraged to achieve AI-powered personalization. To achieve this, you can integrate several advanced capabilities: Content suggestions and personalization: The solution can suggest content that aligns with individual preferences and past interactions. This not only enhances user engagement but also increases the likelihood of converting free users into paying subscribers. By integrating MongoDB's vector search to perform k-nearest neighbor (k-NN) searches , you can streamline and optimize how content is matched. Vectors are embedded directly in MongoDB documents, which has several advantages. For instance: No complexities of a polyglot persistence architecture. No need to extract, transform, and load (ETL) data between different database systems, which simplifies the data architecture and reduces overhead. MongoDB’s built-in scalability and resilience can support vector search operations more reliably. Organizations can scale their operations vertically or horizontally, even choosing to scale search nodes independently from operational database nodes, flexibly adapting to the specific load scenario. Content summarization and reformatting: In an age of information overload, this solution provides concise summaries and adapts content formats based on user preferences and device specifications. This tailored approach addresses the diverse consumption habits of users across different platforms. Keyword extraction: Essential information is drawn from content through advanced keyword extraction, enabling users to grasp key news dimensions quickly and enhancing the searchability of content within the platform. Keywords are fundamental to how content is indexed and found in search engines, and they significantly influence the SEO (search engine optimization) performance of digital content. In traditional publishing workflows, selecting these keywords can be a highly manual and labor-intensive task, requiring content creators to identify and incorporate relevant keywords meticulously. This process is not only time-consuming but also prone to human error, with significant keywords often overlooked or underutilized, which can diminish the content's visibility and engagement. With the help of the underlying LLM, the solution extracts keywords automatically and with high sophistication. Automatic creation of Insights and dossiers: The solution can automatically generate comprehensive insights and dossiers from multiple articles. This feature is particularly valuable for users interested in deep dives into specific topics or events, providing them with a rich, contextual experience. This capability leverages the power of one or more Large Language Models (LLMs) to generate natural language output, enhancing the richness and accessibility of information derived from across multiple source articles. This process is agnostic to the specific LLMs used, providing flexibility and adaptability to integrate with any leading language model that fits the publisher's requirements. Whether the publisher chooses to employ more widely recognized models (like OpenAI's GPT series) or other emerging technologies, our solution seamlessly incorporates these tools to synthesize and summarize vast amounts of data. Here’s a deeper look at how this works: Integration with multiple sources: The system pulls content from a variety of articles and data sources, retrieved with MongoDB Atlas Vector Search. Found items are then compiled into dossiers, which provide users with a detailed and contextual exploration of topics, curated to offer a narrative or analytical perspective that adds value beyond the original content. Customizable output: The output is highly customizable. Publishers can set parameters based on their audience’s preferences or specific project requirements. This includes adjusting the level of detail, the use of technical versus layman terms, and the inclusion of multimedia elements to complement the text. This feature significantly enhances user engagement by delivering highly personalized and context-rich content. It caters to users looking for quick summaries as well as those seeking in-depth analyses, thereby broadening the appeal of the platform and encouraging deeper interaction with the content. By using LLMs to automate these processes, publishers can maintain a high level of productivity and innovation in content creation, ensuring they remain at the cutting edge of media delivery. Future directions As media consumption habits continue to evolve, AI-powered personalization stands out as a vital tool for publishers. By using AI to deliver tailored content and to automate back end processes, publishers can address the decline in traditional referrals and build stronger, more direct relationships with their audiences. If you would like to learn more about AI-Powered Media Personalization, visit the following resources: AI-Powered Personalization to Drive Next-Generation Media Channels AI-Powered Innovation in Telecommunications and Media GitHub Repository : Create a local version of this solution by following the instructions in the repository
Building Gen AI with MongoDB & AI Partners: May 2024
Since I joined MongoDB last September, each month has seemed more action-packed than the last. But it’s possible that May was the busiest of all: May 2024 was a month of big milestones for MongoDB! First, we held MongoDB.local NYC on May 2, our biggest .local event so far, with 2,500 attendees from around the world. It was the first MongoDB.local event I attended since joining the company, and suffice it to say I was thrilled to meet with so many colleagues and partners in person. I was particularly excited to discuss the impact of MongoDB Atlas on the generative AI space, since we also announced the new MongoDB AI Applications Program (MAAP) in May. MongoDB’s CEO, Dev Ittycheria, on the MongoDB .Local NYC keynote stage MAAP was launched to help organizations quickly build, integrate, and deploy gen AI-enriched applications at scale. We do this by providing customers a complete package that includes strategic advisory, professional services, and a robust tech stack through MongoDB and our amazing partners: Anthropic, Anyscale, Amazon Web Services (AWS), Cohere, Credal.ai, Fireworks.ai, Google Cloud, gravity9, LangChain, LlamaIndex, Microsoft Azure, Nomic, PeerIslands, Pureinsights, and Together AI. I really look forward to seeing how MAAP will empower customers to create secure, reliable, and high-performing gen AI applications after the program becomes publicly available in July. Stay tuned for more! And if you’re interested in hearing more about MongoDB’s approach to AI partnerships, and how MAAP will help organizations of all sizes build gen AI applications, check out my interview with theCUBE at MongoDB.local NYC alongside Benny Chen, co-founder of Fireworks.ai. Upcoming AI partner events Are you in San Francisco in late June? We’re proud to sponsor the AI Engineer World’s Fair this year! Stop by the MongoDB booth to chat about gen AI development, and make sure to attend our panel “Building Your AI Stack with MongoDB, Cohere, LlamaIndex, and Together AI” on June 27. Welcoming new AI partners In addition to .local NYC and announcing MAAP in May, we also welcomed four AI partners that offer product integrations with MongoDB: Haystack, Mixpeek, Quotient AI, and Radiant. Read on to learn more about each great new partner. Haystack is an open source Python framework for building custom apps with large language models (LLMs). It allows users to try out the latest models in natural language processing (NLP) while being flexible and easy to use. “We’re excited to partner with MongoDB to help developers build top-tier LLM applications,” said Malte Pietsch, co-founder and CTO of deepset , makers of Haystack and deepset Cloud. “The new Haystack and MongoDB Atlas integration lets developers seamlessly use MongoDB data in Haystack, a reliable framework for creating quality LLM pipelines for use cases like RAG, QA, and agentic pipelines. Whether you're an experienced developer or just starting, your gen AI projects can quickly progress from prototype to adoption, accelerating value for your business and end-users." Learn more about Haystack’s MongoDBAtlasDocumentStore to improve your AI applications. Mixpeek is a multimodal indexing pipeline that gets a database ready for generative AI. It allows developers to treat an object store and a transactional database as a single entity. Ethan Steininger, founder of Mixpeek, explained the value of the MongoDB-Mixpeek integration. “With MongoDB, developers store vectors, metadata, text and all the indexes needed for hyper-targeted retrieval,” he said. “Combined with Mixpeek, they can ensure their S3 buckets and all the documents, images, video, audio and text objects are always consistent with their transactional database, accelerating the path to production by instilling confidence that multimodal RAG results will always be up-to-date." Read more about our partnership and learn how to build real-time multimodal vectors in a MongoDB cluster. Quotient AI is a solution that offers developers the capability to evaluate their AI products with specialized datasets and frameworks to accelerate the experimentation cycle. Julia Neagu, CEO of Quotient AI, highlighted the importance of our partnership. "We are excited to join forces with MongoDB and revolutionize how developers and enterprises are building AI products,” she said. “We share the common goal of helping developers get their ideas to market faster with a first-class developer experience. MongoDB Atlas scalable and versatile vector database technology complements Quotient's mission to ship high-quality, reliable AI applications through rapid, domain-specific evaluation." Learn more how Quotient AI enables evaluation and refinement of RAG-powered AI products built on MongoDB Atlas. Radiant offers a monitoring and evaluation framework for production AI use cases. Nitish Kulnani, CEO of Radiant, shared his excitement about the partnership with MongoDB to enhance the reliability of AI applications. “By combining Radiant's anomaly detection with MongoDB Atlas Vector Search, we enable developers to swiftly identify and mitigate risks, and quickly deploy high-quality AI solutions, delivering real value to customers faster,” he said. “MongoDB trusts Radiant to accelerate its own AI applications, and we're excited to deliver the same experience to MongoDB customers.'' Read more about how to deploy Radiant with MongoDB Atlas to accelerate your journey from development to production. 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.
Transforming Predictive Maintenance with AI: Real-Time Audio-Based Diagnostics with Atlas Vector Search
Wind turbines are a critical component in the shift away from fossil fuels toward more sustainable, green sources of energy. According to the International Energy Agency (IEA), the global capacity of wind energy has been growing rapidly, reaching over 743 gigawatts by 2023. Wind energy, in particular, has one of the greatest potentials to increase countries' renewable capacity growth. Solar PV and wind additions are forecast to more than double by 2028 compared with 2022, continuously breaking records over the forecast period. This growth highlights the increasing reliance on wind power and, consequently, the need for effective maintenance strategies. Keeping wind turbines operating at maximum capacity is essential to ensuring their continued contribution to the energy grid. Like any mechanical device, wind turbines must undergo periodic maintenance to keep them operating at optimal levels. In recent years, advancements in technology—particularly in AI and machine learning—have played a significant role by introducing predictive maintenance breakthroughs to industrial processes like periodic maintenance. By integrating AI into renewable energy systems, organizations of all sizes can reduce costs and gain efficiencies. In this post, we will dig into an AI application use case for real-time anomaly detection through sound input, showcasing the impact of AI and MongoDB Atlas Vector Search for predictive maintenance of wind turbines. Predictive Maintenance in Modern Industries Companies increasingly invest in predictive maintenance to optimize their operations and drive efficiency. Research from Deloitte indicates that predictive maintenance can reduce equipment downtime by 5–15 percent, increase labor productivity by 5–20 percent, and reduce overall new equipment costs by 3–5 percent. This helps organizations maximize their investment in equipment and infrastructure. By implementing predictive maintenance strategies, companies can anticipate equipment failures before they occur, ultimately resulting in longer equipment lifetimes, tighter budget control, and higher overall throughput. More concretely, businesses aim to reduce mean time to repair, optimal ordering of replacement parts, efficient people management, and reduced overall maintenance costs. Leveraging data interoperability, real-time analysis, modeling and simulation, and machine learning techniques, predictive maintenance enables companies to thrive in today's competitive landscape. However, despite its immense potential, predictive maintenance also presents significant challenges. One major hurdle is the consolidation of heterogeneous data, as predictive maintenance systems often need to integrate data from various formats and sources that can be difficult to integrate. Scalability also becomes a concern when dealing with the high volumes of IoT signals generated by numerous devices and sensors. And lastly, managing and analyzing this vast amount of data in real-time poses challenges that must be overcome to realize the full benefits of predictive maintenance initiatives. At its core, predictive maintenance begins with real-time diagnostics, enabling proactive identification and mitigation of potential equipment failures in real-time. Figure 1: Predictive Maintenance starts with real-time diagnostics However, while AI has been employed for real-time diagnostics for some time, the main challenge has been acquiring and utilizing the necessary data for training AI models. Traditional methods have struggled with incorporating unstructured data into these models effectively. Enter gen AI and vector search technologies, positioned to revolutionize this landscape. Flexible data platforms working together with AI algorithms can help generate insights from diverse data types, including images, video, audio, geospatial data, and more, paving the way for more robust and efficient maintenance strategies. In this context, MongoDB Atlas Vector Search stands out as a foundational element for effective and efficient gen AI-powered predictive maintenance models. Why MongoDB and Atlas Vector Search? For several reasons, MongoDB stands out as the preferred database solution for modern applications. Figure 2: MongoDB Atlas Developer Data Platform Document data model One of the reasons why the document model is well-suited to the needs of modern applications is its ability to store diverse data types in BSON (Binary JSON) format, ranging from structured to unstructured. This flexibility essentially eliminates the middle layer necessary to convert to a SQL-like format, resulting in easier-to-maintain applications, lower development times, and faster response to changes. Time series collections MongoDB excels in handling time-series data generated by edge devices, IoT sensors, PLCs, SCADA systems, and more. With dedicated time-series collections, MongoDB provides efficient storage and retrieval of time-stamped data, enabling real-time monitoring and analysis. Real-time data processing and aggregation MongoDB's adeptness in real-time data processing is crucial for immediate diagnostics and responses, ensuring timely interventions to prevent costly repairs and downtime. Its powerful aggregation capabilities facilitate the synthesis of data from multiple sources, providing comprehensive insights into fleet-wide performance trends. Developer data platform Beyond just storing data, MongoDB Atlas is a multi-cloud developer data platform, providing the flexibility required to build a diverse range of applications. Atlas includes features like transactional processing, text-based search, vector search, in-app analytics, and more through an elegant and integrated suite of data services. It offers developers a top-tier experience through a unified query interface, all while meeting the most demanding requirements for resilience, scalability, and cybersecurity. Atlas Vector Search Among the out-of-the-box features offered by MongoDB Atlas, Atlas Vector Search stands out, enabling the search of unstructured data effortlessly. You can generate vector embeddings with machine learning models like the ones found in OpenAI or Hugging Face, and store and index them in Atlas. This feature facilitates the indexing of vector representations of objects and retrieves those that are semantically most similar to your query. Explore the capabilities of Atlas Vector Search . This functionality is especially interesting for unstructured data that was previously hard to leverage, such as text, images, and audio, allowing searches that combine audio, video, metadata, production equipment data, or sensor measurements to provide an answer to a query. Let's delve into how simple it is to leverage AI to significantly enhance the sophistication of predictive maintenance models with MongoDB Atlas. Real-time audio-based diagnostics with Atlas Vector Search In our demonstration, we'll showcase real-time audio-based diagnostics applied to a wind turbine. It's important to note that while we focus on wind turbines here, the concept can be extrapolated to any machine, vehicle, or device emitting sound. To illustrate this concept, we'll utilize a handheld fan as our makeshift wind turbine. Wind turbines emit different sounds depending on their operational status. By continuously monitoring the turbine’s audio, our system can accurately specify the current operational status of the equipment and reduce the risk of unexpected breakdowns. Early detection of potential issues allows for enhanced operational efficiency, minimizing the time and resources required for manual inspections. Additionally, timely identification can prevent costly repairs and reduce overall turbine downtime, thus enhancing cost-effectiveness. Now, let’s have a look at how this demo works! Figure 3: Application Architecture Audio Preparation We begin by capturing the audio from the equipment in different situations (normal operation, high vs. low load, equipment obstructed, not operating, etc.). Once each sound is collected, we use an embedding model to process the audio data to convert it to a vector. This step is crucial because by generating embeddings for each audio track, which are high-dimensional vector representations, we are essentially capturing the unique characteristics of the sound. We then upload these vector embeddings to MongoDB Atlas. By adding just a few examples of sounds in our database, they are ready to be searched (and essentially compared) with the sound emitted by our equipment during its operation in real-time. Audio-based diagnosis Now, we put our equipment into normal operation and start capturing the sound it is making in real-time. In this demonstration, we capture one-second clips of audio. Then, with the same embedding model used before, we take our audio clips and convert them to vector embeddings in real-time. This process happens in milliseconds, allowing us to have real-time monitoring of the audio. The one-second audio clips, now converted to vector embeddings, are then sent to MongoDB Atlas Vector Search, which can search for and find the most similar vectors from the ones we previously recorded in our audio preparation phase. The result is given back with a percentage of similarity, enabling a very accurate prediction of the current status of the operation of the wind turbine. These steps are performed repeatedly every second, leveraging fast embedding of vectors and quick searches, allowing for real-time monitoring based on sound. Check out the video below to see it in action! Transforming Predictive Maintenance with AI and MongoDB Predictive maintenance offers substantial benefits but poses challenges like data integration and scalability. MongoDB stands out as a preferred database solution, offering scalability, flexibility, and real-time data processing. As technology advances, AI integration promises to further revolutionize the industry. Thank you to Ralph Johnson and Han Heloir for their valuable contributions to this demo! Ready to revolutionize your predictive maintenance strategy with AI and MongoDB Atlas Vector Search? Try it out yourself by following the simple steps outlined in our Github repo ! Explore how MongoDB empowers manufacturing operations by visiting these resources: Generative AI in Predictive Maintenance Applications Transforming Industries with MongoDB and AI: Manufacturing and Motion MongoDB for Automotive: Driving Innovation from Factory to Finish Line
How the NFSA is Using MongoDB Atlas and AI to Make Aussie Culture Accessible
Where can you find everything from facts about Kylie Minogue, to more than 6,000 Australian home movies, to a 60s pop group playing a song with a drum-playing kangaroo ? The NFSA! Founded in 1935, the National Film and Sound Archive of Australia (NFSA) is one of the oldest archives of its kind in the world. It is tasked with collecting, preserving, and sharing Australia’s audiovisual culture. According to its website, the NFSA “represents not only [Australia’s] technical and artistic achievements, but also our stories, obsessions and myths; our triumphs and sorrows; who we were, are, and want to be.” The NFSA’s collection includes petabytes of audiovisual data—including broadcast-quality news footage, TV shows, and movies, high-resolution photographs, radio shows, and video games—plus millions of physical and contextual items like costumes, scripts, props, photographs, and promotional materials, all tucked away in a warehouse. “Today, we have eight petabytes of data, and our data is growing from one to two petabytes each year,” said Shahab Qamar, software engineering manager at NFSA. Making this wealth of data easily accessible to users across Australia (not to mention all over the world) has led to a number of challenges, which is where MongoDB Atlas—which helps developers simplify and accelerate building with data—comes in. Don’t change (but apply a few updates) Because of its broad appeal, the NFSA's collection website alone receives an average of 100,000 visitors each month. When Qamar joined the NFSA in 2020, he saw an opportunity to improve the organization’s web platform. His aim was to ensure the best possible experience for the site’s high number of daily visitors, which had begun to plateau. This included a website refresh, as well as addressing technical issues related to handling site traffic, due to the site being hosted on on-premises servers. The site also wasn’t “optimized for Google Analytics,” said Qamar. In fact, the NFSA website was invisible to Google and other search engines, so he knew it was time for a significant update, which also presented an opportunity to set up strong data foundations to build deeper capabilities down the line. But first, Qamar and team needed to find a setup that could serve the needs of the NFSA and Australia’s 26 million residents more robustly than their previous solution. Specifically, Qamar said, the NFSA was looking for a fully managed database that could also implement search at scale, as well as a system that his small team of five could easily manage. It also needed to ensure high levels of resiliency and the ability to work with more than one cloud provider. The previous NFSA site also didn’t support content delivery networks , he added. MongoDB Atlas supported all of the use cases the NFSA was looking for, Qamar said, including the ability to support multi-cloud hosting. And because Atlas is fully managed, it would readily meet the NFSA's requirements. In July 2023, after months of development, the new and greatly improved NFSA website was launched. The redesign was immediately impactful: Since the NFSA’s redesigned site was launched, the number of users visiting the collection search website has gone up 200%, and content requests—which the NFSA access team responds to on a case-by-case basis—have gone up 16%. (Getting search) back in black While the previous version of the NFSA site included search, the prior functionality was prone to crashing, and the quality of the results was often poor, Qamar said. For example, search results were delivered alphabetically rather than based on relevance, and the previous search didn’t support fine-tuning of relevance based on matches in specific fields. So, as part of its site redesign, the NFSA was looking to add full text search, relevance-based search results, faceting, and pagination. MongoDB Atlas Search —which integrates the database, search engine, and sync mechanism into a single, unified, fully managed platform—ticked all of those boxes. A search results page on the NFSA website Indeed, the NFSA compared search results from its old site to its new MongoDB Atlas site and “found that MongoDB Atlas-based searches were more relevant and targeted,” Qamar said. Previously, configuring site search required manual coding and meant downtime for the site, he noted. “The whole setup wasn’t very developer friendly and, therefore, a barrier to working efficiently with search configuration and fine-tuning,” Qamar said. In comparison, MongoDB Atlas allowed for simple configuration and fine-tuning of the NFSA's search requirements. The NFSA has also been using MongoDB Atlas Charts . Charts help the NFSA easily visualize its collection by custom grouping (like production year or genre), as well as helping the NFSA see which items are most popular with users. “Charts have helped us understand how our collection is growing and evolving over time,” Qamar said. NFSA’s use of MongoDB Charts Can’t get you (AI) out of my head Now, the NFSA—inspired by Qamar’s own training in machine learning and the broad interest in all things AI—is exploring how it can use Atlas Vector Search and generative AI tools to allow users to explore content buried in the NFSA collection. One example cited is putting transcriptions of audiovisual files in NFSA’s collection into a vector database for retrieval-augmented generation (RAG). The NFSA has approximately 27 years worth—meaning, it would take 27 years to play it all back—of material to transcribe, and is currently developing a model to accurately capture the Australian dialect so the work is transcribed correctly. Ultimately, the NFSA is interested in building a RAG-powered AI bot to provide historically and contextually accurate information about work in the NFSA’s archive. The NFSA is also exploring how it can use RAG to deliver accurate, conversation-like search results without training large language models itself, and whether it can leverage AI to help restore some of the older videos in its collection. Qamar and team are also interested in vectorizing audio-visual material for semantic analysis and genre-based classification of collection material at scale, he said. “Historically, we’ve been very metadata-driven and keyword-driven, and I think that’s a missed opportunity. Because when we talk about what an archive does, we archive stories,” Qamar said of the possibilities offered by vectors. “An example I use is, what if the world ended tomorrow? And what if aliens came to Earth and only saw our metadata, what image of Australia would they see? Is that a true image of what Australia is really like?” Qamar said. “How content is described is important, but content’s imagery, the people in it, and the audio and words being spoken are really important. Full-text search can take you somewhere along the way, but vector search allows you to look things up in a semantic manner. So it’s more about ideas and concepts than very specific keywords,” he said. If you’re interested in learning how MongoDB helps accelerate and simplify time-to-mission for federal, state, and local governments, defense agencies, education, and across the public sector, check out MongoDB for Public Sector . Check out MongoDB Atlas Vector Search to learn more about how Vector Search helps organizations like the NFSA build applications powered by semantic search and gen AI. *Note that this story’s subheads come from Australian song titles!
Top AI Announcements at MongoDB.local NYC
The AI landscape is evolving so quickly that it’s no surprise customers are overwhelmed by their choices. Between foundation models for everything from text to code, AI frameworks, and the steady stream of AI-related companies being founded daily, developers and organizations face a dizzying array of AI choices. MongoDB empowers customers through a developer data platform that helps them avoid vendor lock-in from cloud providers or AI vendors in this fast-moving space. This freedom allows customers to choose the large language model (LLM) that best suits their needs - now or in the future, whether it's open source or proprietary. Today at MongoDB.local NYC, we announced many new product capabilities, partner integrations, services, and solution offering that enable development teams to get started and build customer-facing solutions with AI. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . Run everywhere, with whatever technology you are using in your AI stack MongoDB’s flexible document model is built on the ethos of “data that is accessed and used together is stored together.” Vectors are a natural extension of this capability, meaning customers can store their source data, metadata, and related vector embeddings in the same document. All of this is accessed and queried with a common Query API, making vector data easy to combine and work with other types of data stored within MongoDB. MongoDB Atlas—our fully managed, multi-cloud developer data platform—makes it easy to build AI-powered applications and experiences, with the breadth and depth of MongoDB’s AI partnerships and integrations—no matter which language, application framework, foundation model, or technology partner is used or preferred by developers. This year, we’re continuing to focus on our AI partnerships and integrations to make it easier for developers to build innovative applications with generative AI, including: Python and JavaScript using the dedicated Langchain-MongoDB package Python and C# Microsoft Semantic Kernel integration for Atlas Vector Search AI models from Mistral and Cohere AI models on the Fireworks AI platform Addition of Atlas Vector Search as a knowledge base in Amazon Bedrock Atlas as a datastore enabling storage, query, and retrieval using natural language in ChatGPT Atlas Vector Search as a datastore on Haystack Atlas Vector Search as a datastore on DocArray Collaboration with Google Gemini Code Assist and Amazon Q to quickly prototype new features and accelerate application development. Google Vertex AI Extension to harness natural language with MongoDB queries MongoDB integrates well with a rich ecosystem of AI developer frameworks, LLMs, and embedding providers. We continue investing in making the entire AI stack work seamlessly, enabling developers to take advantage of generative AI capabilities in their applications easily. MongoDB’s integrations and our industry-leading multi-cloud capabilities allow organizations to move quickly and avoid lock-in to any particular cloud provider or AI technology in a rapidly evolving space. Build high-performance AI applications securely and at scale Workload isolation, without data isolation, is critical for building performant, scalable AI applications. Search Nodes in MongoDB Atlas provide dedicated computing and enable users to isolate memory-intensive AI workloads for superior performance and higher availability. Users can optimize resource consumption for their use case, upsizing or downsizing the hardware for that specific node irrespective of the rest of the database cluster. Search Nodes make optimizing performance for vector search queries easy without over or under-provisioning an entire cluster. The IaC integrations with Hashicorp Terraform Atlas Provider and Cloudformation enable developers to configure and programmatically deploy Search Nodes at scale. Search Nodes are an integral part of Atlas - our fully managed, battle-tested, multi-cloud platform. Previously, we announced the availability of Search Nodes for our AWS and Google Cloud customers. We are excited to announce the preview of Search Nodes for our Azure customers at MongoDB.local NYC. Search Nodes on Atlas helps developers move faster by removing the friction of integrating, securing, and maintaining the essential data components required to build and deploy modern AI applications. Improve developer productivity with AI-powered experiences Today, we also announced new and improved releases of our intelligent developer experiences in MongoDB Compass , MongoDB Relational Migrator , and MongoDB Atlas Charts , aiming to enhance developer productivity and velocity. With the updated releases, developers can use natural language to query their data using MongoDB Compass, troubleshoot common problems during development, perform SQL-to-Query API conversion right from within MongoDB Relational Migrator , and quickly build charts and dashboards using natural language prompts in MongoDB Atlas Charts. Collectively, these intelligent experiences will help developers build differentiated features with greater control and flexibility, making it easier than ever to build applications with MongoDB. Enable development teams to get started and build customer-facing solutions faster and easier with AI MongoDB makes it easy for companies of all sizes to build AI-powered applications. To provide customers with a straightforward way to get started with generative AI, MongoDB is announcing the MongoDB AI Application Program (MAAP). Based on usage patterns for common AI use cases, customers receive a functioning application built on a reference architecture backed by MongoDB Atlas, vetted AI models and hosting solutions, technical support, and a full-service engagement led by our Professional Services team. We’re launching with an incredible group of industry-leading partners, including Anthropic, Anyscale, AWS, Cohere, Credal.ai, Fireworks.ai, Google Cloud, gravity9, LangChain, LlamaIndex, Microsoft Azure, Nomic, PeerIslands, Pureinsights, and Together AI. MongoDB is in a unique position in the market to be able to pull together such an impressive AI partner ecosystem in a single customer-focused program, and we’re excited to see how MAAP will help customers more easily go from ideation to fully functioning generative AI applications. Last year, to further enable startups to build AI solutions with MongoDB Atlas, we launched the AI Innovators Program , an extension of MongoDB for Startups , which offers an additional $5000 in Atlas credits to our AI startups. This year, we are expanding the program by introducing an AI Startup Hub , which features a curated guide for getting started with MongoDB and AI, quickstarts for MongoDB and select AI partners, and startup credit offerings from our AI partners. We provide two new AI Accelerator consulting packages for larger enterprise companies: AI Essentials and AI Implementation. While MAAP is aimed exclusively at building highly vetted reference architectures, these consulting packages allow customers to design, build, and deploy open-ended AI prototypes and solutions into their applications. Data has always been a competitive advantage for organizations, and MongoDB makes it easy, fast, and flexible to innovate with data. We continue to invest in making all the other parts of the AI stack easy for organizations: vetting top partners to ensure compatibility with different parts of the application stack, building a managed service that spans multiple clouds in operation, and ensuring the openness that's always been a part of MongoDB which avoids vendor lock-in. How does MongoDB Atlas unify operational, analytical, and generative AI data services to streamline building AI-enriched applications? Check out our MongoDB for AI page to learn more.
MongoDB AI Applications Program Partner Spotlight: Cohere Brings Leading AI Foundation Models to the Enterprise
Today, Cohere, a leading enterprise AI platform, will join MongoDB’s new AI Applications Program (MAAP) as part of its first cohort of partners. The MAAP program is designed to help organizations rapidly build and deploy modern generative AI applications at enterprise scale. Enterprises will be able to utilize MAAP to more easily and quickly leverage Cohere’s industry-leading AI technology, such as its highly performant and scalable Command R series of generative models, into their businesses. Cohere's enterprise AI suite supports end-to-end retrieval augmented generation (RAG, which has become a foundational building block for enterprises adopting large language models (LLMs) and customizing them with their own proprietary data. Cohere’s Command R model series is optimized for business-critical capabilities like advanced RAG with citations to mitigate hallucinations, along with tools used to automate complex business processes. It also offers multilingual coverage in 10 key languages to support global business operations. These models are highly scalable, balancing high efficiency with strong accuracy for customers. Cohere’s best-in-class embed models complement its R Series generative models, offering enhanced enterprise search capabilities in 100+ languages to support powerful RAG applications. Using Cohere’s technology with MAAP will help companies overcome many of the obstacles that they face when implementing generative AI into their everyday operations. Enterprises can now seamlessly integrate Cohere’s state-of-the-art LLMs to move into large-scale production with AI to address real-world business challenges. MAAP provides a strategic framework utilizing MongoDB’s industry expertise, strategic roadmaps, and technology to design AI solutions that can meaningfully improve workforce productivity and deliver new types of application experiences to end users. “Organizations of all sizes across industries are eager to get started with applications enriched with generative AI capabilities but many are unsure how to get started effectively,” said Alan Chhabra, EVP of Worldwide Partners at MongoDB. “The MongoDB AI Applications Program helps address this challenge, and we’re excited to have Cohere as a launch partner for the program. With Cohere’s leading embedding models, support for more than 100 languages, and its Command R foundation models optimized for retrieval augmented generation using an organization’s proprietary data, customers can more easily help improve the accuracy and trustworthiness of outputs from AI-powered applications.” “MongoDB’s unique position in the market allows them to work with companies as they evaluate their current technology stack, and identify the best opportunities to use Cohere’s industry-leading Command and Embed LLMs to drive efficiency at scale,” said Vinod Devan, Cohere’s Global Head of Partnerships. “MAAP is an incredible opportunity for companies to work with a trusted partner as they look to meaningfully ramp up their use of Cohere’s enterprise-grade AI solutions to deliver real business value.” We look forward to building on this partnership to deliver impactful AI solutions for businesses globally. Cohere works with all major cloud providers as well as on-prem for regulated industries and privacy-sensitive use cases, to make their models universally available for customers wherever their data resides. MongoDB and Cohere will work together to be a trusted AI partner for enterprises and build cutting-edge applications with data privacy and security in mind for companies that need highly secure solutions for sensitive proprietary data. Learn more about the MongoDB AI Applications Program on the program website .
Search PDFs at Scale with MongoDB and Nomic
Data is only valuable if it’s accessible. For example, storing photos, audio files, or PDFs without the ability to extract information from them is like keeping junk in your basement, thinking you might need it someday. The problem is finding what you need to dig through your junk when the day comes. Until now, companies have followed a similar approach to unstructured data : store everything in data lakes for future use. But whether it’s junk in a basement or data in a data lake, the result is the same: accessibility is hard or impossible. However, the latest advancements in AI have disrupted this status quo. AI can effectively and efficiently compare similar objects by generating a vector representation or embedding a data object. This capability has revolutionized industries by enabling faster and more precise search, categorization, and recommendation systems than ever before. Whether it's being used to compare text, documents, images, or complex patterns in data, embeddings allow for nuanced interpretations and connections that were impossible with traditional methods. By taking advantage of AI, users can uncover insights and make unprecedented speed and accuracy decisions. A particularly interesting use case is PDF search, since every company in the world deals with PDFs in one way or another. While PDFs allow portability across platforms and operating systems, most PDF readers only allow for basic exact-match queries. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. PDF search powered by MongoDB and Nomic Enter MongoDB and Nomic: MongoDB Atlas Vector Search with Nomic Embed equips organizations with a powerful and affordable AI-powered search solution for large PDF collections. A machine learning company specializing in explainable and accessible AI, Nomic Embed is the company’s flagship text embedding model with out-of-the-box features suitable for scalable PDF search. Its features include: Long context: Nomic Embed breaks new ground by supporting a long context length of 8192 tokens, exceeding the standard 2048. This extended context makes the model ideal for real-world applications that involve processing large PDFs and documents. High throughput: While achieving top performance on the MTEB embedding benchmark, Nomic Embed is smaller than similarly performing models. At only 137 million parameters and 548MB, Nomic Embed enables high-throughput embedding generation for data-heavy workflows or streaming applications. Flexible storage: Nomic Embed provides adjustable embedding size via Matryoshka representation learning. Users can freely choose to store the first 64, 128, 256, or 512 embedding dimensions out of the full 768, depending on their project requirements. Smaller embedding sizes come at a minimal performance loss while providing lower storage costs and faster computing benefits. To put Nomic Embed’s abilities in context, consider a company that processes a high volume of PDFs—say 100,000 documents per month—with an average length of 20 pages each. To improve database retrieval speed, these documents can be partitioned into smaller chunks, such as 2 pages per chunk (see Figure 1 below). Assuming a full page typically contains around 500 words, each document chunk would consist of approximately 1000 words. Figure 1: PDF chunking, embedding creation with Nomic, and storage into MongoDB Embedding models process words as numerical tokens where a general rule of thumb is 3/4 word = 1 token. One embedding is more than sufficient to represent a document chunk in this case, as 4/3 * 1000 tokens fit nicely in Nomic Embed’s long context window. A PDF search application for this company would require 100,000 PDFs x 10 chunks = 1,000,000 embeddings. Benchmarked on Nomic’s AWS Sagemaker real-time inference offering on a single GPU ml.g5.xlarge instance, the total runtime is under 4 hours for a total of $15.60 per month. A similar performing embedding model, such as OpenAI’s text-embedding-3-small, costs $26.66 per month to generate the same number of embeddings. Once the embeddings are stored in MongoDB Atlas, it’s possible to create an Atlas Vector Search index to unlock their potential. Building a PDF search application at this point becomes straightforward. The query text is vectorized, and the embedding is fed to Atlas Vector Search to retrieve similar vectors. The result is a list of the most semantically similar sections of the PDF relevant to the original text. This is a significant leap forward compared to a simple “ctrl-f” search, as it captures meaning rather than just keyword matches. This process can be further improved by implementing a retrieval-augmented generation (RAG) pipeline, combining Atlas Vector Search and a large language model (LLMs). As shown in Figure 2, this approach allows users to ask questions in natural language about the content of the PDF. The relevant documents are then fed to the LLM as context, and the AI is able to provide structured answers by leveraging knowledge about the data. Figure 2: Retrieval Augmented Generation flow with Nomic In a nutshell, Nomic and MongoDB provide the building blocks for advanced RAG applications, equipping developers with a cost-effective and integrated toolset. Seamless integration, supercharged search: Nomic Embeddings in MongoDB Atlas MongoDB Atlas seamlessly ingests Nomic embeddings with its flexible document storage format. Depending on the application, embeddings and additional metadata can be neatly stored together or separately in MongoDB collections. MongoDB Atlas and Nomic Embed are both available as AWS Marketplace offerings for same-VPC deployments. MongoDB Atlas Stream Processing is a perfect fit for Nomic Embed’s high throughput capabilities. Incoming data streams are robustly processed and can be combined with MongoDB Database Triggers to generate embeddings for immediate downstream use. Given Nomic Embed’s lightweight nature and offline capabilities (via private or local deployments from open source), embeddings can be produced and ingested into MongoDB at extremely rapid transfer rates. MongoDB Atlas Vector Search delivers a fast and accessible method to leverage Nomic embeddings for semantic search . MongoDB Atlas Vector Search lets you combine these fast vector search queries with traditional database queries on various metadata, providing a flexible and powerful analytics tool for data insights, user recommendations, and more. Industry use cases PDFs are ubiquitous. In one way or another, every company in the world needs to extract and analyze PDF content to make business decisions or comply with regulations. Let’s have a look at some industry use cases: Financial services The financial services industry is constantly bombarded with essential updates, including market data, financial statements, and regulatory changes. Some of this information such as financial statements, annual reports, and regulatory filings, resides in PDF format. Efficient and reliable navigation through these documents is crucial for gaining a competitive edge in investment decision-making. For example, investors scrutinize key financial metrics such as revenue growth, profit margins, and cash flow trends extracted from income statements, balance sheets, and cash flow statements. They use this information to compare them between companies, gauging their strategic direction, risks, and competitive positioning before investing. However, accessing and extracting data from these PDFs can be a time-consuming challenge, hindering agility in the fast-paced financial landscape. Here, semantic search for financial PDFs offers a dramatic improvement in information discovery. By leveraging semantic search technology, which interprets the intent and contextual meaning behind a search query, FSI professionals can significantly enhance their ability to find relevant information. This applies equally to the broader financial industry, including areas like market analysis, performance evaluation, and many more. Retail In the retail industry, the challenge of processing hundreds of thousands of invoices from numerous suppliers annually is a common scenario. Most invoices are in PDF format, and the challenge arises from the combination of invoice volume and the variability in layouts and languages from one supplier to another. This makes manual processing impractical and error-prone. The question becomes: how can retailers automate this end-to-end process efficiently and accurately? The answer lies in solutions that utilize advanced technologies like AI and PDF search capabilities. By leveraging these solutions, retailers can automatically scan invoices, extract relevant data, and validate it against purchase orders and received goods. Moreover, these solutions offer the flexibility to adapt to different invoice layouts without the need for templates, ensuring scalability and efficiency gains. With increased automation rates and improved accuracy levels, retailers can shift focus from low-value manual tasks to more strategic initiatives, accelerating their digital transformation journey and unlocking significant cost savings along the way. Manufacturing & motion There are vast amounts of unstructured data contained in PDFs across the Manufacturing and Automotive industries, from machine instruction booklets to production or maintenance guidelines, Six Sigma best practices, production results, and team lead annotations. All this valuable data must be shared, read, and stored manually, introducing significant friction when it comes to leveraging its full potential. With MongoDB Atlas Vector Search, manufacturing companies have the opportunity to completely revive this data and make real use of it in their day-to-day operations, all while reducing the time spent managing these manuals and having everything ready to be accessed. It is as simple as vectorizing the documents, uploading them to MongoDB Atlas, and connecting a RAG-enabled application to this data source. With this, operators in a manufacturing plant can describe a problem to a smart interface and ask how to troubleshoot it. The interface will retrieve the specific parts of the manual that show how to address the issue. Moreover, it can also retrieve notes from previous operators, team leaders, or previous troubleshooting efforts, providing a very rich context and accelerating the problem-solving process. PDF RAG-enabled applications in manufacturing open up a wide range of operational improvements that directly benefit the company's bottom line. PDF search at scale In today’s data-driven world, extracting insights from unstructured data like PDFs is challenging. Traditional search methods fall short, but advancements in AI like, Nomic Embed, have revolutionized PDF search. By leveraging MongoDB with Nomic Embed, organizations gain a powerful and cost-effective AI-powered solution for large PDF collections. Nomic Embed’s extensive context, high throughput capabilities, and MongoDB’s seamless integration and powerful analytics enable efficient and reliable PDF search applications. This translates to enhanced data accessibility, faster decision-making, and improved operational efficiency. Don't waste time struggling with traditional PDF search! Apply for an innovation workshop to discuss what’s possible with our industry experts. If you would like to discover more about MongoDB and GenAI: Building a RAG LLM with Nomic Embed and MongoDB From Relational Databases to AI: An Insurance Data Modernization Journey
Building AI with MongoDB: Conversation Intelligence with Observe.AI
What's really happening in your business? The answer to that question lies in the millions of interactions between your customers and your brand. If you could listen in on every one of them, you'd know exactly what was up--and down. You’d also be able to continuously improve customer service by coaching agents when needed. However, the reality is that most companies have visibility in only 2% of their customer interactions. Observe.AI is here to change that. The company is focused on being the fastest way to boost contact center performance with live conversation intelligence. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Founded in 2017 and headquartered in California, Observe.AI has raised over $200m in funding. Its team of 250+ members serves more than 300 organizations across various industries. Leading companies like Accolade, Pearson, Public Storage, and 2U partner with Observe.AI to accelerate outcomes from the frontline to the rest of the business. The company has pioneered a 40 billion-parameter contact center large language model (LLM) and one of the industry’s most accurate Generative AI engines. Through these innovations, Observe.AI provides analysis and coaching to maximize the performance of its customers’ front-line support and sales teams. We sat down with Jithendra Vepa, Ph.D, Chief Scientist & India General Manager at Observe.AI to learn more about the AI stack powering the industry-first contact center LLM. Can you start by describing the AI/ML techniques, algorithms, or models you are using? “Our products employ a versatile range of AI and ML techniques, covering various domains. Within natural language processing (NLP), we rely on advanced algorithms and models such as transformers, including the likes of transformer-based in-house LLMs, for text classification, intent and entity recognition tasks, summarization, question-answering, and more. We embrace supervised, semi-supervised, and self-supervised learning approaches to enhance our models' accuracy and adaptability." "Additionally, our application extends its reach into speech processing, where we leverage state-of-the-art methods for tasks like automatic speech recognition and sentiment analysis. To ensure our language capabilities remain at the forefront, we integrate the latest Large Language Models (LLMs), ensuring that our application benefits from cutting-edge natural language understanding and generation capabilities. Our models are trained using contact center data to make them domain-specific and more accurate than generic models out there.” Can you share more on how you train and tune your models? “In the realm of model development and training, we leverage prominent frameworks like TensorFlow and PyTorch. These frameworks empower us to craft, fine-tune, and train intricate models, enabling us to continually improve their accuracy and efficiency." "In our natural language processing (NLP) tasks, prompt engineering and meticulous fine-tuning hold pivotal roles. We utilize advanced techniques like transfer learning and gradient-based optimization to craft specialized NLP models tailored to the nuances of our tasks." How do you operationalize and monitor these models? "To streamline our machine learning operations (MLOps) and ensure seamless scalability, we have incorporated essential tools such as Docker and Kubernetes. These facilitate efficient containerization and orchestration, enabling us to deploy, manage, and scale our models with ease, regardless of the complexity of our workloads." "To maintain a vigilant eye on the performance of our models in real-time, we have implemented robust monitoring and logging to continuously collect and analyze data on model performance, enabling us to detect anomalies, address issues promptly, and make data-driven decisions to enhance our application's overall efficiency and reliability.” The role of MongoDB in Observe.AI technology stack The MongoDB developer data platform gives the company’s developers and data scientists a unified solution to build smarter AI applications. Describing how they use MongoDB, Jithendra says “OBSERVE.AI processes and runs models on millions of support touchpoints daily to generate insights for our customers. Most of this rich, unstructured data is stored in MongoDB. We chose to build on MongoDB because it enables us to quickly innovate, scale to handle large and unpredictable workloads, and meet the security requirements of our largest enterprise customers.” Getting started Thanks so much to Jithendra for sharing details on the technology stack powering Observe.AI’s conversation intelligence and MongoDB’s role. To learn more about how MongoDB can help you build AI-enriched applications, take a look at the MongoDB for Artificial Intelligence page. Here, you will find tutorials, documentation, and whitepapers that will accelerate your journey to intelligent apps.
Building AI With MongoDB: Integrating Vector Search And Cohere to Build Frontier Enterprise Apps
Cohere is the leading enterprise AI platform, building large language models (LLMs) which help businesses unlock the potential of their data. Operating at the frontier of AI, Cohere’s models provide a more intuitive way for users to retrieve, summarize, and generate complex information. Cohere offers both text generation and embedding models to its customers. Enterprises running mission-critical AI workloads select Cohere because its models offer the best performance-cost tradeoff and can be deployed in production at scale. Cohere’s platform is cloud-agnostic. Their models are accessible through their own API as well as popular cloud managed services, and can be deployed on a virtual private cloud (VPC) or even on-prem to meet companies where their data is, offering the highest levels of flexibility and control. Cohere’s leading Embed 3 and Rerank 3 models can be used with MongoDB Atlas Vector Search to convert MongoDB data to vectors and build a state-of-the-art semantic search system. Search results also can be passed to Cohere’s Command R family of models for retrieval augmented generation (RAG) with citations. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. A new approach to vector embeddings It is in the realm of embedding where Cohere has made a host of recent advances. Described as “AI for language understanding,” Embed is Cohere’s leading text representation language model. Cohere offers both English and multilingual embedding models, and gives users the ability to specify the type of data they are computing an embedding for (e.g., search document, search query). The result is embeddings that improve the accuracy of search results for traditional enterprise search or retrieval-augmented generation. One challenge developers faced using Embed was that documents had to be passed one by one to the model endpoint, limiting throughput when dealing with larger data sets. To address that challenge and improve developer experience, Cohere has recently announced its new Embed Jobs endpoint . Now entire data sets can be passed in one operation to the model, and embedded outputs can be more easily ingested back into your storage systems. Additionally, with only a few lines of code, Rerank 3 can be added at the final stage of search systems to improve accuracy. It also works across 100+ languages and offers uniquely high accuracy on complex data such as JSON, code, and tabular structure. This is particularly useful for developers who rely on legacy dense retrieval systems. Demonstrating how developers can exploit this new endpoint, we have published the How to use Cohere embeddings and rerank modules with MongoDB Atlas tutorial . Readers will learn how to store, index, and search the embeddings from Cohere. They will also learn how to use the Cohere Rerank model to provide a powerful semantic boost to the quality of keyword and vector search results. Figure 1: Illustrating the embedding generation and search workflow shown in the tutorial Why MongoDB Atlas and Cohere? MongoDB Atlas provides a proven OLTP database handling high read and write throughput backed by transactional guarantees. Pairing these capabilities with Cohere’s batch embeddings is massively valuable to developers building sophisticated gen AI apps. Developers can be confident that Atlas Vector Search will handle high scale vector ingestion, making embeddings immediately available for accurate and reliable semantic search and RAG. Increasing the speed of experimentation, developers and data scientists can configure separate vector search indexes side by side to compare the performance of different parameters used in the creation of vector embeddings. In addition to batch embeddings, Atlas Triggers can also be used to embed new or updated source content in real time, as illustrated in the Cohere workflow shown in Figure 2. Figure 2: MongoDB Atlas Vector Search supports Cohere’s batch and real time workflows. (Image courtesy of Cohere) Supporting both batch and real-time embeddings from Cohere makes MongoDB Atlas well suited to highly dynamic gen AI-powered apps that need to be grounded in live, operational data. Developers can use MongoDB’s expressive query API to pre-filter query predicates against metadata, making it much faster to access and retrieve the more relevant vector embeddings. The unification and synchronization of source application data, metadata, and vector embeddings in a single platform, accessed by a single API, makes building gen AI apps faster, with lower cost and complexity. Those apps can be layered on top of the secure, resilient, and mature MongoDB Atlas developer data platform that is used today by over 45,000 customers spanning startups to enterprises and governments handling mission-critical workloads. What's next? To start your journey into gen AI and Atlas Vector Search, review our 10-minute Learning Byte . In the video, you’ll learn about use cases, benefits, and how to get started using Atlas Vector Search.