Spotlight on Two Aussie Start-Ups Building AI Services on MongoDB Atlas

Anoop Dhankhar
February 5, 2024 | Updated: February 22, 2024

Australian-based Eclipse AI and Pending AI are using the power of MongoDB Atlas to bring their AI ideas to life and blaze new trails in fields including pharmaceutical R&D and customer retention.

With the recent advancements in the fields of AI and generative AI, innovation has been unleashed to new heights. Many organisations are taking advantage of technologies such as Natural Language Processing (NLP), Large Language Models (LLMs), and more to create AI-driven products, services, and apps.

Amongst those that are blazing new trails in the AI space are two Australian start-ups: Pending AI, which is helping scientists and researchers in the pharmaceutical space improve early research & development stages, and Eclipse AI, a company that unifies and analyses omnichannel voice-of-customer data to give customers actionable intelligence to drive retention.

What they have in common is their choice to use MongoDB Atlas. This multi-cloud, developer data platform unifies operational, analytical, and generative AI data services to streamline building AI-enriched applications.

Here is how we are helping these two Australian start-ups create the next generation of AI products faster, with less complexity, and without breaking the bank.

Pending AI improves pharmaceutical R&D by leveraging next-generation technologies

Pending AI has developed a suite of artificial intelligence and quantum mechanics-based capabilities to solve critical problem statements within the earliest stages of pharmaceutical research and development.

The Pending AI platform is capable of dramatically improving the efficiency and effectiveness of the compound discovery pipeline, meaning stakeholders can obtain better, commercially viable scaffolds for further clinical development in a fraction of the time and cost.

Building its two artificial intelligence-based capabilities - Generative Molecule Designer and Retrosynthesis Engine - was a mammoth task.

The known number of pharmacologically relevant molecules in chemical space is exceptionally large, and there are over 50 million known chemical reactions and billions of molecular building blocks - expert scientists have to undergo cost- and time-inefficient trial-and-error processes to design desired molecules and identify optimal synthesis routes to them.

Pending AI needed a database that could handle a very large number of records, and be highly performant at that scale, as required by the vastness of chemical space.

A few databases were considered by Pending AI, but MongoDB kept standing out as a battle-tested, reliable, and easy-to-implement solution, enabling Pending AI’s team to build a highly performant deployment on MongoDB Atlas.

“As a startup, getting started with the community edition of MongoDB and being able to run a reliable cluster at scale was a huge benefit. Now that we’re starting to leverage the AWS infrastructure in our platform, MongoDB Atlas provides us with a fully managed solution at a low cost, and with a Private Endpoint between our AWS deployment and MongoDB cluster, we have kept latency to a minimum, and our data secure,” said Dr. David Almeida Cardoso, Vice President, Business Development at Pending AI.

Output of Pending AI's Generative Molecule Designer

Pending AI’s Generative Molecule Designer has been built as a machine learning model on MongoDB Atlas, trained to understand the language of pharmaceutical structures, which allows for automated production of novel compound scaffolds that can be focused and tailored to outputs of biological and/or structural studies.

The Retrosynthesis Engine is also built using a set of machine learning models and MongoDB Atlas, trained to understand chemical reactions, which allows for the prediction of multiple, valid synthetic routes within a matter of minutes.

“We’re also excited to explore the new Atlas Search index feature in MongoDB 7.0. We hope this will allow us to integrate some of the search functionality, which is currently complex to manage and maintain, directly into MongoDB, rather than relying on a separately maintained Elasticsearch cluster,” added Cardoso.

Being part of the MongoDB AI Innovator program also allowed Pending AI to explore leveraging cloud infrastructure to scale its platform and test newer versions of MongoDB quickly and easily.

Eclipse AI turns customer interaction insights into revenue

Eclipse AI is a SaaS platform that turns siloed customer interactions from different sources - these can be customer calls, emails, surveys, reviews, support tickets, and more - into insights that drive retention and revenue.

It was created to address the frustration of customer experience (CX) teams around the number of hours and man-weeks of effort needed to consolidate and analyse customer feedback data from different channels. Eclipse AI took on the challenge of solving this issue and worked hard to find a way to offer customers faster and more efficient ways to turn customer feedback into actionable insights.

The first problem was consolidating the voice-of-customer data which was so fragmented; the second was analysing that data and turning it into specific improvement actions to improve the customer experience and prevent customer churn.

Because MongoDB Atlas is a flexible document database that also can store and index vector embeddings for unstructured data, it was a perfect fit for Eclipse AI and enabled its small dev team to focus on building the product very efficiently and quickly, without being burdened with managing infrastructure.

MongoDB Atlas also comes with key features such as MongoDB Atlas Device SDKs (formerly Realm) and MongoDB Atlas Search that were instrumental in bringing Eclipse AI’s platform to life.

"For us, MongoDB is more than just a database, it is data-as-a-service. This is thanks to tools like Realm and Atlas Search that are seamlessly built into the platform. With minimum effort, we were able to add a relevance-based full-text search on top of our data. Without MongoDB Atlas we would not have been able to iterate quickly and ship new features fast,” commented Saad Irfani, co-founder of Eclipse AI.

“Best of all, horizontal scaling is a breeze with single-click sharding that doesn't require setting up config servers or routers, reducing costs along the way. The unified monitoring and performance advisor recommendations are just the cherry on top.”

Screenshot of the Eclipse AI - MongoDB dashboard. The dashboard shows 4 different charts, the first being for improvement suggestions with outputs of positive, neutral, and negative. The second chart graphs the positive vs negative feedback by date. The 3rd chart provides a start rating system on a scale of 1-5 for customer feedback. The final chart graphs users overall rating overtime.
Eclipse AI - MongoDB dashboard

G2 rated Eclipse AI as the #1 proactive customer retention platform globally for SMEs, a recognition that wouldn’t have been possible without the use of MongoDB Atlas.

Exploring your AI potential with MongoDB

MongoDB Atlas is built for AI. Why? Because MongoDB specialises in helping companies and their developer teams manage richly structured data that doesn't neatly fit into the rigid rows and columns of traditional relational databases, and turn that into meaningful and actionable insights that help operationalise AI.

More recently, we have added Vector Search - enabling developers to build intelligent applications powered by semantic search and generative AI over any type of data - and enhanced AWS CodeWhisperer coding assistant to our list of tools companies can use to further their AI exploration.

These are just a handful of examples of what is possible in the realm of AI today. Many of our customers around the world, from start-ups to large enterprises like banks and telcos are investing in MongoDB Atlas and capabilities such as Atlas Search, Vector Search, and more to create what the future of AI and generative AI will look like in the next decade.

If you want to learn more about how you can get started with your AI project, or take your AI capabilities to the next level, you can check out our MongoDB for Artificial Intelligence resources page for the latest best practices that get you started in turning your idea into an AI-driven reality.

← Previous

Building AI with MongoDB: How Patronus Automates LLM Evaluation to Boost Confidence in GenAI

It is hardly headline news that large language models can be unreliable. For some use cases, this can be inconvenient. For others — especially in regulated industries — the consequences are way more severe. Enter Patronus AI , the industry-first automated evaluation platform for LLMs. Founded by machine learning experts from Meta AI and Meta Reality Labs, Patronus AI is on a mission to boost enterprise confidence in gen AI-powered apps, leading the way in shaping a trustworthy AI landscape. Rebecca Qian, Patronus co-founder and CTO explains, “Our platform enables engineers to score and benchmark LLM performance on real-world scenarios, generate adversarial test cases, monitor hallucinations, and detect PII and other unexpected and unsafe behavior. Customers use Patronus AI to detect LLM mistakes at scale and deploy AI products safely and confidently.” In recently published and widely cited research based on the FinanceBench question answering (QA) evaluation suite , Patronus made a startling discovery. Researchers found that a range of widely used state-of-the-art LLMs frequently hallucinated, incorrectly answering or refusing to answer up to 81% of financial analysts’ questions! This error rate occurred despite the models’ context windows being augmented with context retrieved from an external vector store. While retrieval augmented generation (RAG) is a common way of feeding models with up-to-date, domain-specific context, a key question faced by app owners is how to test the reliability of model outputs in a scalable way. This is where Patronus comes in. The company has partnered with the leading technologies in the gen AI ecosystem — from model providers and frameworks to vector store and RAG solutions — to provide managed evaluation services, test suites, and adversarial data sets. “As we assessed the landscape to prioritize which partners to work with, we saw massive demand from our customers for MongoDB Atlas ," said Qian. “Through our Patronus RAG evaluation API, we help customers verify that their RAG systems built on top of MongoDB Atlas consistently deliver top-tier, dependable information." In its new 10-minute guide , Patronus takes developers through a workflow showcasing how to evaluate a MongoDB Atlas-based retrieval system. The guide focuses on evaluating hallucination and answers relevance against an SEC 10-K filing, simulating a financial analyst querying the document for analysis and insights. The workflow is built using: The LlamaIndex data framework to ingest and chunk the source pdf document Atlas Vector Search to store, index, and query the chunk’s metadata and embeddings Patronus to score the model responses The workflow is shown in the figure below. Equipped with the results of an analysis, there are a number of steps developers can take to improve the performance of a RAG system. These include exploring different indexes, modifying document chunking sizes, re-engineering prompts, and for the most domain-specific apps, fine-tuning the embedding model itself. Review the 10-minute guide for a more detailed explanation of each of these steps. As Qian goes on to say, “Regardless of which approach you take to debug and fix hallucinations, it’s always important to continuously test your RAG system to make sure performance improvements are maintained over time. Of course, you can use the Patronus API iteratively to confirm.” To learn more about LLM evaluation, reach out at contact@patronus.ai . Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Head over to our quick-start guide to get started with Atlas Vector Search today.

February 2, 2024
Next →

Hanabi Technologies Uses MongoDB to Power AI Assistant, Hana

For all the hype surrounding generative AI, cynics tend to view the few real-world implementations as little more than “fancy chatbots.” But for Abhinav Aggarwal, CEO of Hanabi Technologies, the idea of a generative AI-powered bot that is more than just an assistant was intriguing. “I’d been using ChatGPT since it launched,” said Aggarwal. “That got me thinking: How could we make a chatbot that was like a team member?” And with that concept, Hana was born. The problem with bots “Most generative AI chatbots do not act like people; they wait for a command and give a response,” said Aggarwal. “We wanted to create a human-like chatbot that would proactively help people based on what they wanted—automating reminders, for example, or fetching time zones from your calendar to correctly schedule meetings.” Hanabi’s flagship product, Hana, is an AI assistant designed to enhance team collaboration within Google Chat, working in concert with Google Workspace and its suite of products. “Our target customers are smaller companies of between 10 and 50 people. At this size you’re not going to build your own agent from scratch,” he said. Hana integrates with Google APIs to deliver a human-like assistant that chimes in with helpful interventions, such as automatically setting reminders and making sure meetings are booked in the right time zone for each participant. “Hana is designed to bring AI to smaller companies and help them collaborate in a space where they are already working—Google Workspace,” Aggarwal explained. The MongoDB Atlas solution For Hana to act like a member of the team, Hanabi needed to process massive amounts of data to support advanced features like retrieval-augmented generation (RAG) for better information retrieval across Google Docs and many other sources. And with a rapidly growing user base of over 600 organizations and 17,000+ installs, Hanabi also required a secure, scalable, and high-performing data storage solution. MongoDB Atlas provided a flexible document model, built-in vector database, and scalable cloud-based infrastructure, freeing Hanabi engineers to build new features for Hana rather than focusing on rote tasks like data extract, transform, and load processes or manual scaling and provisioning. Now, MongoDB Atlas handles a variety of responsibilities: Scalability and security: MongoDB Atlas’s auto-scaling and automatic backup features have enabled Hanabi to seamlessly grow its user base without the need for manual database management. RAG: MongoDB Atlas plays a critical role in Hana’s RAG functionality. The platform enables Hanabi to split Google Docs into small sections, create embeddings, and store these sections in Atlas’s vector database. Development Processes: According to Aggarwal, MongoDB’s flexibility in managing changing schemas has been essential to the company’s fast-paced development cycle. Data Visualization: Using MongoDB Atlas Charts has enabled Hanabi to create comprehensive dashboards for real-time data visualization. This has helped the team track usage, set reminders, and optimize performance without needing to build a manual dashboard. Impact and results With MongoDB Atlas, Hanabi can successfully scale Hana to meet the demands of its rapidly expanding user base. The integration is also enabling Hana to offer powerful features like automatic interactions with customers, advanced information retrieval from Google Docs, and manually added memory snippets, making it an essential tool for teams around the world. Next steps Hanabi plans to continue integrating more tools into Hana while expanding its reach to personal Gmail users. The company is also rolling out a new automatic-interaction feature, further enhancing Hana’s ability to proactively assist users without direct commands. MongoDB Atlas remains a key component of Hanabi’s stack, alongside Google Kubernetes Engine, NestJS, and LangChain, enabling Hanabi to focus on innovating to improve the customer experience. Tech Stack MongoDB Atlas Google Kubernetes Engine NestJS LangChain Are you building AI apps? Join the MongoDB AI Innovators Program today! Successful participants gain access to free MongoDB Atlas credits, technical enablement, and invaluable connections within the broader AI ecosystem. If your company is interested in being featured, we’d love to hear from you. Connect with us at ai_adopters@mongodb.com.

November 21, 2024