Vector Search and Dedicated Search Nodes: Now in General Availability

Elliott Gluck
December 4, 2023 | Updated: May 2, 2024
#genAI#Vector Search

Update May 2, 2024: Search Nodes are now in general availability for Google Cloud and announcing preview for Microsoft Azure.

This post is also available in: Deutsch, Français, Español, Português, Italiano, 한국어, 简体中文.

Today we’re excited to take the next step in adding even more value to the Atlas platform with the general availability (GA) release of both Atlas Vector Search and Search Nodes.

Since announcing Atlas Vector Search and dedicated infrastructure with Search Nodes in public preview, we’ve seen continued excitement and demand for additional workloads using vector-optimized search nodes. This new level of scalability and performance ensures workload isolation and the ability to better optimize resources for vector search use cases.

Atlas Vector Search allows developers to build intelligent applications powered by semantic search and generative AI over any data type. Atlas Vector Search solves the challenge of providing relevant results even when users don’t know what they’re looking for and uses machine learning models to find results that are similar for almost any type of data. Within just five months of being announced in public preview, Atlas Vector Search has already received the highest developer net promoter score (NPS) — a measure of how likely someone is to recommend a solution to someone else — and is the second most widely used vector database, according to Retool’s State of AI report.

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

There are two key use cases for Atlas Vector Search to build next-gen applications:

  1. Semantic search: searching and finding relevant results from unstructured data, based on semantic similarity

  2. Retrieval augmented generation (RAG): augment the incredible reasoning capabilities of LLMs with feeds of your own, real-time data to create GenAI apps uniquely tailored to the demands of your business.

Atlas Vector Search unlocks the full potential of your data, no matter whether it’s structured or unstructured, taking advantage of the rise in popularity and usage of AI and LLMs to solve critical business challenges. This is possible due to Vector Search being part of the MongoDB Atlas developer data platform, which starts with our flexible document data model and unified API providing one consistent experience. To ensure you unlock the most value possible from Atlas Vector Search, we have cultivated a robust ecosystem of AI integrations, allowing developers to build with their favorite LLMs or frameworks.

Our ecosystem of AI integrations for Atlas Vector Search

To learn more about Atlas Vector Search, watch our short video or jump right into the tutorial.

Atlas Vector Search also takes advantage of our new Search Nodes dedicated architecture, enabling better optimization for the right level of resourcing for specific workload needs. Search Nodes provide dedicated infrastructure for Atlas Search and Vector Search workloads, allowing you to optimize compute resources and fully scale search needs independent of the database. Search Nodes provide better performance at scale, delivering workload isolation, higher availability, and the ability to better optimize resource usage. In some cases we’ve seen 60% faster query time for some users' workloads, leveraging concurrent querying in Search Nodes.

In addition to the compute-heavy search nodes we provided in the public preview, this GA release includes a memory-optimized, low CPU option that is optimal for Vector Search in production. This makes resource contention or the possibility of a resulting service interruption (due to your database and search sharing the same infrastructure previously) a thing of the past.

Coupled Architecture (left) compared with the decoupled Search Node architecture (right)

We see this as the next evolution of our architecture for both Atlas Search and Vector Search, furthering the value provided by the MongoDB developer data platform. At this time Search Nodes are currently available on AWS single-region clusters (with Google Cloud and Azure coming soon), as customers can continue using shared infrastructure for Google Cloud and Microsoft Azure.

Read our initial announcement blog post to view the steps of how to turn on Search Nodes today, or jump right into the tutorial.

Both of these features are available today for production usage. We can’t wait to see what you build, and please reach out to us with any questions.

← Previous

How Canara HSBC Life Insurance Optimized Costs and Claims Processing with MongoDB

Since 2008, Canara HSBC Life Insurance has focused relentlessly on bringing a fresh perspective to an industry known more for stability and conservatism rather than innovation. Since its inception in 2008 as a joint venture between Canara Bank and HSBC Insurance, Canara HSBC Life Insurance has strived to differentiate itself from the competition through enhanced customer interactions, launching cutting-edge digital products, and integrating digital services that cater to the evolving needs of customers. For the past six years Chief Operating Officer, Mr. Sachin Dutta, has been on a mission to bring this customer-first mindset to the digital products and touchpoints his team creates. Speaking at MongoDB’s annual .local developer conference in Delhi, Dutta outlined Canara HSBC Life Insurance’s ongoing digital transformation journey, and how his team's focus on customer success and business efficiency led them to work with MongoDB for improved efficiencies and results. “I truly value the partnership we have with MongoDB. We are building a future-ready organization, and this partnership clearly helps us achieve our aim of reaching the last mile possible in customer servicing. Mr. Sachin Dutta, Chief Operating Officer, Canara HSBC Modernizing the architecture and driving developer efficiency Canara HSBC’s digital transformation was centered on three technical pillars: the cloud, analytics, and mobility. The company focused on creating a more integrated organization and automating manual processes within the system. “We try to remove human intervention with a life insurance policy delivered in seconds and claims that are settled virtually in seconds,” Dutta says. To get there, Canara HSBC Life Insurance had to move on from its existing architecture, which required multifaceted changes and several new implementations: Monolithic applications made alterations a time-consuming process A reliance on rigid relational databases prolonged development timelines, forcing developers to spend time wrangling data when they could be building better products for customers. The fully on-premises system had supported the organization in the past but required future-proofing to support growth and deliver a better customer experience. Because of this valuable development time and money were spent managing, patching, and scaling databases, rather than getting new products into the hands of customers. These technical issues impacted the speed of business, particularly during month-end and year-end data processing, when the volumes were high. In addition, batch processing stood in the way of creating the real-time availability of information customers wanted. Dutta and his senior team also realized that their existing infrastructure would make it more challenging to find the right talent in the market, as the existing infrastructure was increasingly becoming outdated. Dutta realized early on that, in order for Canara HSBC to attract and retain the best and brightest developers, the insurer had to offer the chance to work with the latest technologies. Platforms like MongoDB would be integral to this effort. “I want to create an organization that is attracting talent and where people start to enjoy their work, and that benefit then gets passed on to the customers, ” Mr. Dutta says. Looking to overhaul its existing infrastructure, Canara HSBC Life Insurance wanted to move fast and hire the talent required to best serve its end customers. Dutta summarized the situation succinctly: "We found that some of those relational structures that had worked for us would not take us through the next 10 years.” Migrating to a secure, fully managed database platform After evaluating the solutions on the market, the team decided to transition from their existing on-premises relational databases, like IBM DB2, MySQL, and Postgres, to MongoDB Atlas . In the last six years of my work, I’m pleased to say that MongoDB has seamlessly integrated all the processes in the backend. We migrated from a completely legacy-based setup to the new fully managed MongoDB service to enhance IT productivity Mr. Sachin Dutta The first stage of the journey was moving from monolithic applications and relational databases to a microservices architecture. With its flexible schema and capabilities for redundancy, automation, and scalability, MongoDB served as the best partner to help facilitate the transition. Next, the team moved to modernize key parts of the business, such as underwriting, freeing their data to power more automation in straight-through processing (STP) of policies and faster claims processing. The adoption of a hybrid cloud model shifted Canara HSBC Life Insurance away from on-premises databases to MongoDB Atlas. As a fully managed cloud database, MongoDB Atlas solves issues related to scalability, database management, and overall reliability. MongoDB Atlas is also cloud agnostic, giving the insurance company an option to work with Azure, AWS, and Google Cloud. Mongo Atlas’ BI Connector bridged the gap between MongoDB and traditional BI tools. This seamless integration allowed Canara HSBC Life Insurance to deploy its preferred reporting tools and, when coupled with MongoDB Atlas’ real-time analytics capability, made batch processing a thing of the past. Halving delivery times and driving business efficiencies Moving to MongoDB Atlas has had a profound impact on the breadth of digital experiences Canara HSBC Life Insurance can offer customers and the speed at which new products can be developed. Something that used to take months, with the implementation of our new tools could be completed in a couple of weeks or days Mr. Sachin Dutta And it’s not only the customer experience and product delivery that has benefited from the partnership. Canara HSBC Life Insurance has also realized substantial efficiency gains and savings as a result of working with MongoDB. We are leveraging artificial intelligence as a core capability to predict human behavior and auto-underwrite policies wherein around half of the policies issued today are issued by the system Mr. Sachin Dutta Highlighted results include: Straight-through processing (STP) surged from 37% to an impressive 60%. This is set to increase further with AI/ML integrations and rule suggestions. Policy issuance turnaround time improved by 60%. Efficiency in operations led to a 20% cost-saving per policy issuance. Canara HSBC experienced 2x top-line growth due to seamless integration with analytical tools. Looking ahead, Canara HSBC Life Insurance has already outlined three key areas where the MongoDB partnership will grow. First, Dutta wants to take advantage of MongoDB Atlas’ flexible document data model to collect and organize data on customers from across the business, making MongoDB Atlas the sole database at Canara HSBC Life Insurance and creating a true customer 360 data layer to power sophisticated data analytics. In financial services, this capability is referred to as know your customer (KYC). “We want to build a data layer that provides a unique experience to the customer after getting to know them,” he says. “That’ll help the company generate better NPS scores and retain customers.” Second, the adoption and integration of AI and machine learning tools also factor heavily into future plans. MongoDB Atlas, with its flexible schema, compatibility with various machine learning platforms, and AI-specific features — such as Vector Search and storage — is a good fit for the company. In Dutta's words, "We are going to scale up and capture the GenAI space.” Last, Dutta wants to take advantage of the MongoDB Atlas SQL interface, connectors, and drivers to augment business intelligence for reporting and precise SQL-based report conversions. Learn More about how MongoDB Works with global Insurers

December 4, 2023
Next →

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 in July 2023. 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!

May 14, 2024