Building AI with MongoDB: Giving Your Apps a Voice

Mat Keep
November 8, 2023 | Updated: January 10, 2024
#genAI#Vector Search

In previous posts in this series, we covered how generative AI and MongoDB are being used to unlock value from data of any modality and in supercharging communications. Put those topics together, and we can start to harness the most powerful communications medium (arguably!) of them all: Voice.

Voice brings context, depth, and emotion in ways that text, images, and video alone simply cannot. Or as the ancient Chinese Proverb tells us, “The tongue can paint what the eyes can’t see.”

The rise of voice technology has been a transformative journey that spans over a century, from the earliest days of radio and telephone communication to the cutting-edge realm of generative AI. It began with the invention of the telephone in the late 19th century, enabling voice conversations across distances. The evolution continued with the advent of radio broadcasting, allowing mass communication through spoken word and music. As technology advanced, mobile communications emerged, making voice calls accessible anytime, anywhere.

Today, generative AI, powered by sophisticated machine learning (ML) models, has taken voice technology to unprecedented levels. The generation of human-like voices and text-to-speech capabilities are one example. Another is the ability to detect sentiment and create summaries from voice communications. These advances are revolutionizing how we interact with technology and information in the age of intelligent software.

In this post, we feature three companies that are harnessing the power of voice with generative AI to build completely new classes of user experiences:

  1. Xoltar uses voice along with vision to improve engagement and outcomes for patients through clinical treatment and recovery.

  2. Cognigy puts voice at the heart of its conversational AI platform, integrating with back-office CRM, ERP, and ticketing systems for some of the world’s largest manufacturing, travel, utility, and ecommerce companies.

  3. Artificial Nerds enables any company to enrich its customer service with voice bots and autonomous agents.

Let's learn more about the role voice plays in each of these very different applications.

Check out our AI resource page to learn more about building AI-powered apps with MongoDB.

GenAI companion for patient engagement and better clinical outcomes

XOLTAR is the first conversational AI platform designed for long-lasting patient engagement. XOLTAR’s hyper-personalized digital therapeutic app is led by Heather, XOLTAR’s live AI agent. Heather is able to conduct omni-channel interactions, including live video chats. The platform is able to use its multimodal architecture to better understand patients, get more data, increase engagement, create long-lasting relationships, and ultimately achieve real behavioral changes.

Figure 1:

About 50% of patients fail to stick to prescribed treatments. Through its app and platform, XOLTAR is working to change this, improving outcomes for both patients and practitioners. It provides physical and emotional well-being support through a course of treatment, adherence to medication regimes, monitoring post-treatment recovery, and collection of patient data from wearables for remote analysis and timely interventions.

Powering XOLTAR is a sophisticated array of state-of-the-art machine learning models working across multiple modalities — voice and text, as well as vision for visual perception of micro-expressions and non-verbal communication. Fine-tuned LLMs coupled with custom multilingual models for real-time automatic speech recognition and various transformers are trained and deployed to create a truthful, grounded, and aligned free-guided conversation.

XOLTAR’s models personalize each patient’s experience by retrieving data stored in MongoDB Atlas. Taking advantage of the flexible document model, XOLTAR developers store both structured data, such as patient details and sensor measurements from wearables, alongside unstructured data, such as video transcripts. This data provides both long-term memory for each patient as well as input for ongoing model training and tuning.

MongoDB also powers XOLTAR’S event-driven data pipelines. Follow-on actions generated from patient interactions are persisted in MongoDB, with Atlas Triggers notifying downstream consuming applications so they can react in real-time to new treatment recommendations and regimes.

Through its participation in the MongoDB AI Innovators program, XOLTAR’s development team receives access to free Atlas credits and expert technical support, helping them de-risk new feature development.

How Cognigy built a leading conversational AI solution

Cognigy delivers AI solutions that empower businesses to provide exceptional customer service that is instant, personalized, in any language, and on any channel. Its main product, Cognigy.AI, allows companies to create AI Agents, improving experiences through smart automation and natural language processing. This powerful solution is at the core of Cognigy's offerings, making it easy for businesses to develop and deploy intelligent voice and chatbots.

Developing a conversational AI system poses challenges for any company. These solutions must effectively interact with diverse systems like CRMs, ERPs, and ticketing systems. This is where Cognigy introduces the concept of a centralized platform. This platform allows you to construct and deploy agents through an intuitive low-code user interface.

Cognigy took a deliberate approach when constructing the platform, employing a composable architecture model, as depicted in Figure 1 below. To achieve this, it designed over 30 specialized microservices, adeptly orchestrated through Kubernetes. These microservices were strategically fortified with MongoDB's replica sets, spanning across three availability zones. In addition, sophisticated indexing and caching strategies were integrated to enhance query performance and expedite response times.

Figure 2: Congnigy's composable architecture model platform

MongoDB has been a driving force behind Cognigy's unprecedented flexibility and scalability and has been instrumental in bringing groundbreaking products like Cognigy.AI to life.

Check out the Cognigy case study to learn more about their architecture and how they use MongoDB.

The power of custom voice bots without the complexity of fine-tuning

Founded in 2017, Artificial Nerds assembled a group of creative, passionate, and "nerdy" technologists focused on unlocking the benefits of AI for all businesses. Its aim was to liberate teams from repetitive work, freeing them up to spend more time building closer relationships with their clients.

The result is a suite of AI-powered products that improve customer sales and service. These include multimodal bots for conversational AI via voice and chat along with intelligent hand-offs to human operators for live chat. These are all backed by no-code functions to integrate customer service actions with backend business processes and campaigns.

Originally the company’s ML engineers fine-tuned GPT and BERT language models to customize its products for each one of its clients. This was a time-consuming and complex process. The maturation of vector search and tooling to enable Retrieval-Augmented Generation (RAG) has radically simplified the workflow, allowing Artificial Nerds to grow its business faster.

Artificial Nerds started using MongoDB in 2019, taking advantage of its flexible schema to provide long-term memory and storage for richly structured conversation history, messages, and user data. When dealing with customers, it was important for users to be able to quickly browse and search this history. Adopting Atlas Search helped the company meet this need. With Atlas Search, developers were able to spin up a powerful full-text index right on top of their database collections to provide relevance-based search across their entire corpus of data. The integrated approach offered by MongoDB Atlas avoided the overhead of bolting on a separate search engine and creating an ETL mechanism to sync with the database. This eliminated the cognitive overhead of developing against, and operating, separate systems.

The release of Atlas Vector Search unlocks those same benefits for vector embeddings. The company has replaced its previously separate standalone vector database with the integrated MongoDB Atlas solution. Not only has this improved the productivity of its developers, but it has also improved the customer experience by reducing latency 4x.

Artificial Nerds is growing fast, with revenues expanding 8% every month. The company continues to push the boundaries of customer service by experimenting with new models including the Llama 2 LLM and multilingual sentence transformers hosted in Hugging Face. Being part of the MongoDB AI Innovators program helps Artificial Nerds stay abreast of all of the latest MongoDB product enhancements and provides the company with free Atlas credits to build new features.

Getting started

Check out our MongoDB for AI page to get access to all of the latest resources to help you build.

We see developers increasingly adopting state-of-the-art multimodal models and MongoDB Atlas Vector Search to work with data formats that have previously been accessible only to those organizations with access to the very deepest data science resources. Check out some examples from our previous Building AI with MongoDB blog post series here:

There is no better time to release your own inner voice and get building!

← Previous

Transforming Payments with Volante and MongoDB: A Modern Cloud Solution

In the ever-evolving world of banking and financial services, innovation and adaptability are key to success. Volante Technologies , a trusted cloud payments modernization partner to financial businesses worldwide, has been at the forefront of this transformation, empowering cloud-native payments solutions for over 125+ banks, financial institutions, and corporations across 35 countries to harness the power of digital payments and have the freedom to evolve and innovate at record speed. Volante's Payments as a Service and underlying low-code platform process millions of mission-critical transactions and trillions in value daily, so customers can focus on growing their business, not managing their technology. Real-time ready, API enabled, and ISO 20022 fluent, Volante’s solutions power four of the top five global corporate banks, two of the world’s largest card networks, and 66% of U.S. commercial deposits. In this customer story, we'll delve into how Volante, in partnership with MongoDB, has helped banks of all sizes modernize their payment systems, opening doors to new possibilities. The challenge Banks have long grappled with the constraints of monolithic infrastructure and legacy technologies that are a decade or more old and unable to handle the 24x7x365 digital demands of today's banking. In the fast-paced world of real-time payments – payments that clear and settle almost instantaneously using an underlying platform or network called payment rails – the need for speed and innovation is paramount. Corporate B2B banking, a lucrative revenue source, is also highly competitive. To win and retain customers, banks must offer improved and new payment services. Moreover, regulatory requirements demand that banks update their B2B payments systems to enable new payment rail standards such as FedNow and RTP as well as comply with new payment messaging standards like ISO20022 . The solution In response to these challenges, Volante Technologies, in partnership with MongoDB, introduced VolPay, a groundbreaking solution that redefined the way banks approach payments technology. This modern, cloud-native solution leverages MongoDB's cutting-edge technology to provide a modular, microservices API-based application. The benefits of this collaboration include: Modularity: Banks can now choose and integrate the services they need, making it a highly customizable solution. Innovative Tech Stack: By embracing modern technology, Volante's solution is resilient and able to meet the demands of today’s payments services and is future-proof as the landscape continues to evolve. Cloud Native: The solution is designed to operate in the cloud, enabling rapid deployment and scalability. Real-time: With real-time capabilities, banks can deliver 24x7x365 customer experiences that are critical in today's fast-paced digital world. Easy Integration and Extension: Volante's solution is easy to integrate with existing systems and extend as needed. Lower Total Cost of Ownership (TCO): The solution eliminates the need for costly "oil tanker" license upgrades, reducing both costs and implementation time. Global Connectivity: Banks can expand into new markets by connecting to over 100 global clearing and settlement schemes. MongoDB plays a crucial role in Volante's solution, providing a robust foundation for reading data, and ensuring high performance, scalability, and availability. The result MongoDB underpins the VolPay solution , a pioneering approach to payments technology. Unlike the monolithic systems of the past or generic middleware solutions, VolPay is an interoperable ecosystem of business services designed for payments innovation and transformation across the entire payments lifecycle including: Real-Time / Instant Payments, Global and Domestic Payments, ISO 20022 standardization, and more. Over 125+ global financial institutions take advantage of the cloud-native, API-ready solution. Built on a microservices architecture, VolPay is inherently real-time and ready to meet the demands of today's fast-paced payments environment. VolPay is available for deployment in various configurations across an organization’s modernization journey, from on-premise data centers to public cloud instances on major platforms like Microsoft Azure and AWS. Additionally, it is offered as a SaaS-managed service called " Payments-as-a-Service ." Customers looking to support their critical workloads in a self-managed environment can utilize MongoDB Enterprise Advanced , a comprehensive suite of products and services that put engineering teams in control of their self-managed MongoDB database, helping them drive security, performance, and operational efficiency. Those leveraging VolPay in the cloud can leverage the most advanced multi-cloud database service on the market – MongoDB Atlas – with unmatched data distribution and mobility, built-in automation for resource and workload optimization, and so much more. From on premises, to hybrid cloud and multi-cloud, MongoDB Enterprise Advanced and MongoDB Atlas deliver the scalability, high availability, and deployment flexibility today’s applications demand. In this transformative landscape, MongoDB plays a critical role as the archival (read) and transactional (write) database, ensuring performance, scalability, and high availability to meet the demanding transaction-per-second (tps) requirements of banks. In conclusion, the collaboration between Volante Technologies and MongoDB has ushered in a new era of payments technology, enabling banks to stay ahead of the curve and provide their customers with innovative, real-time payment experiences. This partnership has demonstrated that modern, cloud-native solutions can be implemented in a matter of months, offering a cost-effective and efficient alternative to the traditional, cumbersome systems that have held banks back for far too long. The future of payments is here, and it's being shaped by innovators like Volante and MongoDB. If you would like to learn more about why leading banks and payment providers choose Volante and MongoDB, take a look at the below resources: Volante Payments MongoDB for Payments Payments modernization – architectures shaping the future Volante Payments as a Service

November 8, 2023
Next →

The Developers' Developers: Two Australian Developers Share Their Connections to Customers

The world’s 28 million software developers are writing the foundations of our future, propelling innovation for their organizations through lines of code by creating game-changing new apps. Indeed, the US Bureau of Labor Statistics predicts that between 2022 and 2032, the number of software developers, quality assurance analysts, and testers will grow 24%, “much faster than the average for all occupations.” Fueling this innovative workforce is another group of developers, the people working behind the scenes to build the tools, technologies and platforms that other developers need to be successful: the developers’ developers. Many developers at MongoDB—which after all was built by developers for developers, and is beloved by enterprises and startups alike—fall into this camp. To learn more about what makes these developers tick, we talked with two Australia-based senior software engineers at MongoDB who love to code for their peers. For Lavender Chan and Angus Lee, there’s nothing like seeing the ripple effect of the code they have been working on and the impact it has on their customers. What’s more, the opportunity to be a “developer’s developer” has allowed Chan and Lee to find a space for deep technical work while thriving in an autonomous environment. At MongoDB we believe developers will build the future. First, can you share more about your roles and what you’re working on? Lavender Chan (LC): I work on the Relational Migrator tool, which allows developers to migrate SQL data onto MongoDB. I joined the company two and a half years ago, and have been part of the Sydney technology scene for the last 10 years. The appeal of joining MongoDB was that it’s a large global company, but in the engineering team you are able to have a big impact and a lot of autonomy. Relational Migrator was a greenfield project, and our team has been able to take the original product idea built out of the US and run with it. I’m a full stack developer and have touched on every feature of the tool. A lot of the engineers were able to contribute and work on new ideas. There’s also a strong emphasis on culture here which practically means a lot of the people I work with are excited to be here and passionate about their roles. Angus Lee (AL): I work in the MongoDB Charts team in Australia and think our team is a sweet spot for developers. I’ve interned for other tech companies and started my career at MongoDB. Since then I’ve been given responsibilities where I can create a lot of impact. My role at MongoDB in Sydney has also given me great opportunities to connect directly to the developers we are creating products for in a way that pushes my work to a higher level. Your roles are focused on products targeted to other developers. How does developing for developers affect your approach to your work? LC: In our roles we are creating directly for other developers, so the work that I am doing is deeply technical and specific. As Migrator is a newer product, we are able to interact directly with our customers—other developers—and often a lot of their questions are quite complex and specific, which means I go on a learning journey in debunking and fixing their problems. AL: We have a strong team culture in that as developers we want to be our own users. That means we want to use other MongoDB team products, and they use ours, so we can better identify pain points and issues for our customers. There’s a term that developers use called “dogfooding” that really sums up how we think on this, which basically means to use your own product. It means for me that I think about writing clean code to help any other developers extend on this, and how effective what I do will be for the user. What I’ve also learnt is how our product helps other products thrive. We should have done all the hard work to transform data and show it through data visualizsation tools so it’s easy for the customer. Can you tell us more about this connection to customers and how MongoDB empowers developers? LC: When Relational Migrator was released as a general product, I went to MongoDB World to work at the booth, and I talked to the developers and customers using the platform. As an engineer, it was an amazing experience and opportunity to see how it was being used and what else we could be doing. This connection of engineers with customers, as well as the ability to speak to them regularly in my role, is unique. In other companies I would need to go through support teams, to go through someone else just to push out a bug fix. Our team is very customer focused, so we can prioritizse features that our customers want. AL: One of the best moments for me at MongoDB was when I went to MongoDB World and I sat down with a customer to talk through a feature of Charts. It was a pivotal moment to see the improvements it makes for the businesses that use it, and the impact it generates for their customers beyond that. I could sit back and see the ripple effect of the code I’m writing. There is also a great feedback engine where our users can submit ideas and other users can vote for that feature. The product managers pick from these and push out features that are directly relevant to the developers using it. Where we really connect is in our aim to create an open forum for developers and customers to provide feedback and suggest ideas. Developers are problem solvers. As part of the MongoDB Love Your Developers campaign, we believe in championing the voice of developers and giving them the freedom to experiment and innovate. How do you see this in action? LC: In other places I was a small cog in a massive system. At MongoDB, I really have an impact, and can see directly how my work translates to our final product. In Sydney, we’re a satellite office, but it’s indicative of our company culture that there is huge trust placed in these teams. We’re given high impact projects and can run with them, which means I’ve been able to watch the Relational Migrator product go from a tiny product used by only a few customers, to one that is now generally available. Not many engineers get to work for a well-established,large company and still have the opportunity to work on and release products like a startup. There is a strong global interest in AI-driven innovations. How have your connections to customers led to innovations in this area? AL: We’ve been able to take an idea for a new AI feature, Natural Language Charts , and take it from concept to being released as a feature at MongoDB.local in London. We could see from our conversations with customers, as well as broader industry trends, that there was strong interest in new AI features so we were able to prioritizse it for Charts. We started with nothing and were given the freedom to research how this feature could work using AI, create a new proof of concept, and from there we were able to push it out into a feature which was a really proud moment. Having this agility and flexibility to prioritize something new is exactly what we want to provide to our customers. I never feel like I'm just churning out code. We are connected to the work and to our customers. MongoDB is built by developers, for developers. Become part of the team changing the way the world works with data!

May 9, 2024