Building AI with MongoDB: Accelerating App Development With the Codeium AI Toolkit

Mat Keep
February 21, 2024
#genAI

Of the many use cases set to be transformed by generative AI (gen AI), the bleeding edge of this revolution is underway with software development. Developers are using gen AI to improve productivity by writing higher-quality code faster. Tasks include autocompleting code, writing docs, generating tests, and answering natural language queries across a code base. How does this translate to adoption? A recent survey showed 44% of new code being committed was written by an AI code assistant.

Codeium is one of the leaders in the fast-growing AI code assistant space. Its AI toolkit is used by hundreds of thousands of developers for more than 70 languages across more than 40 IDEs including Visual Studio Code, the JetBrains suite, Eclipse, and Jupyter Notebooks. The company describes its toolkit as “the modern coding superpower,” reflected by its recent $65 million Series B funding round and five-star reviews across extension marketplaces.

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

As Anshul Ramachandran, Head of Enterprise & Partnerships at Codeium explains, “Codeium has been developed by a team of researchers and engineers to build on the industry-wide momentum around large language models, specifically for code. We realized that our specialized generative models, when deployed on our world-class optimized deep learning serving software, could provide users with top-quality AI-based products at the lowest possible costs (or ideally, free). The result of that realization is Codeium."

Codeium has recently trained its models on MongoDB code, libraries, and documentation. Now developers building apps with MongoDB can install the Codeium extension on the IDE of their choice and enjoy rapid code completion and codebase-aware chat and search. Developers can stay in the flow while they build, coding at the speed of thought, knowing that Codeium has ingested MongoDB best practices and documentation.

MongoDB is wildly popular across the developer community. This is because Atlas integrates the fully managed database services that provide a unified developer experience across transactional, analytical, and generative AI apps.

Anshul Ramachandran, Head of Enterprise & Partnerships, Codeium

Ramachandran, goes on to say, “MongoDB APIs are incredibly powerful, but due to the breadth and richness of the APIs, it is possible for developers to be spending more time than necessary looking through API documentation or using the APIs inefficiently for the task at hand. An AI assistant, if trained properly, can effectively assist the developer in retrieval and usage quality of these APIs. Unlike other AI code assistants, we at Codeium build our LLMs from scratch and own the underlying data layer. This means we accelerate and optimize the developer experience in unique and novel ways unmatched by others.”

Figure 1:  By simply typing statement names, the Codeium assistant will automatically provide code completion suggestions directly within your IDE.

In its announcement blog post and YouTube video, the Codeium team shows how to build an app in VSCode with MongoDB serving as the data layer. Developers can ask questions on how to read and write to the database, get code competition suggestions, explore specific functions and syntax, handle errors, and more. This was all done at no cost using the MongoDB Atlas free tier and Codeium 100% free, forever individual plan.

You can get started today by registering for MongoDB Atlas and then downloading the Codeium extension. If you are building your own AI app, sign up for the MongoDB AI Innovators Program. Successful applicants get access to free Atlas credits and technical enablement, as well as connections into the broader AI ecosystem.

← Previous

Aussie Fintech Monoova Leads the Way on “Multi” “Cloud” (Not “Multi-Cloud”), to Solve Data Security and Compliance Conundrums

Monoova is a fast-growing Australian Fintech scale-up providing real-time payment solutions to businesses. Having grown from 200,000 to 6 million business accounts in 5 years, Monoova has also created 13% of Australia’s PayID since the inception of NPP, and processed over $100 billion in payments. Dealing with critical financial information from hundreds of organisations in highly regulated industries means Monoova needs to put data security and compliance first. But this is easier said than done. Navigating an increasingly complex security and compliance landscape The increased reliance on the cloud, combined with more regulations requiring extra resilience capabilities, means that financial services organisations are facing increasingly complex data security and compliance challenges. APRA’s chair John Lonsdale recently warned the financial sector about cybersecurity non-compliance, mentioning CPS 230 as one of the upcoming regulations organisations should start preparing to comply with ahead of the July 2025 deadline. On November 3rd, 2023, Brad Jones, Assistant Governor of the Reserve Bank of Australia (RBA) gave a speech in which he listed the “Outside Operational Risk (Cloud Concentration Risk)” as one of the main threats to financial stability . “Multi” “cloud” or “multi-cloud”? A significant number of financial services institutions today aren’t using multi-cloud in a way that would make them resilient in the event of a data security or outage issue. Many say that they are using “multi-cloud” but what they are doing is hosting individual workloads and data sets in different clouds, which doesn’t provide full resilience and data security or meet requirements from regulating industry bodies and government. True multi-cloud resilience means having critical data hosted in different clouds at the same time. For Monoova’s CTO, Nicholas Tan, future-proofing compliance and data security lies in adopting a true multi-cloud approach, and this is exactly the path Monoova has taken by working with MongoDB Atlas. “Whether it’s in critical sectors like financial services or telecommunications, time and time again we see events such as outages seriously impact Australian organisations and their sometimes millions of users - the Optus outage from November 2023 is a perfect example," explains Nicholas Tan. “There are great operational risks of not having diversity in an organisations’ core infrastructure, and this is why building real resilience with a proper multi-cloud approach should be a no-brainer.” Working with MongoDB Atlas a game changer MongoDB Atlas, which is the operational database underpinning all of Monoova’s services, was chosen by Monoova to support extra scale requirements as it was - and still is fast growing, as well as empower developer productivity as the company needs to bring new products to market and innovate fast. Another key driver in working with MongoDB Atlas was the unique functionality that enables users to simply “turn a switch on” to automatically enable selected critical data and workloads to go multi-cloud, allowing data to be easily distributed across different clouds and providing resilience and protection for the workload. Tan and his team simply have to choose the UI to reconfigure their posture to be multi-cloud, which takes only a few minutes. Monoova’s MongoDB Atlas multi-cloud console According to Tan: “Our multi-cloud approach is pretty unique in the current Australian financial services landscape, and this is what has set Monoova to be one of the first Australian financial services organisations to align with the CPS230 framework, as well as at the forefront of ensuring compliance and resilience in an environment heavily reliant on third parties.” “Working with MongoDB has been a game changer because it means we were able to quickly scale up at a fraction of the manpower required; it saved us from recruiting a full team if we had had to do all that multi-cloud work in-house.” Learn more about MongoDB Atlas and our multi-cloud feature on our resources page .

February 20, 2024
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