Part 1: Your App is Taking Off, Now What? Understanding MongoDB Deployment Health.

Meghan Gill
September 29, 2014 | Updated: May 22, 2015
#Technical

Your app is on the front page of the app store. Hooray! Your service is suddenly flooded with new users and you have a problem that everyone envies: maintaining high performance while your app is under heavy load. Here’s what you need to think about to ensure deployment health.

1. Design Your Schema for Scale You may be surprised that the design of your schema will be a critical component of ensuring performance as your app grows. Your schema should be informed by your application’s use case and query patterns. A good schema will support your common app queries and updates, as well as allow you to create efficient indexes. In contrast, a poor schema can lead to storage fragmentation, make it difficult to efficiently query data and challenging to create indexes. Our rules of thumb blog post is a great resource when modeling your data, as is our Schema Design consultation package.

2. Optimize Your Indexes Many MongoDB users get great performance from a single replica set. Before throwing money at more expensive hardware or diving into sharding, make sure that you’ve got the right indexes in place and that you’ve tuned your queries. Our upcoming webinar on indexing strategies for scale will provide you with lots of useful tips and tricks on this topic.

3. Get the Right Hardware Does your working set fit in RAM? Are you relying on SSDs or HDDs? Are you prioritizing faster CPUs over more cores? Is your storage local or remote? Are you virtualizing or running on bare metal? The right hardware will optimize performance, while the wrong hardware can lead to problems down the line. This presentation on Hardware Provisioning from MongoDB World provides excellent advice using several real-world examples.

4. Look Inside with Monitoring Without visibility into your system, you can’t discover and diagnose issues. To optimize performance properly, first you need to identify what is actually slow! Using the monitoring functionality in MongoDB Management Service along with tools like mtools, mongostat and mongotop, you can visualize performance and identify bottlenecks. Taking it a step further, you can set up alerts in MMS to proactively inform you when key metrics are out of range.

5. Talk to an Expert You’re not the first to face these challenges. Thousands of organizations have built high performance, scalable applications on MongoDB. And we’ve helped most of them. So if you’re worried about performance and scalability, talk to an expert at MongoDB -- at no cost to you.

In our next blog post, we’ll explore methods for scaling out MongoDB.

← Previous

What We're Reading This Week

Here's what we're reading this week at MongoDB: Ashnik : “Performance degrades after migrating to MongoDB”. Really? Read this. Diginomica : MyDealerLot boosts dealership revenue opportunities with MongoDB DZone : Product Catalog with MongoDB, Part 1: Schema Design DZone : Product Catalog with MongoDB, Part 2: Product Search Forbes : Bypass The Cord, TV Viewing Shifts To The Small Screen Paul Done's Technical Blog : Tracking Versions in MongoDB VentureBeat : The 5 backend tools every game developer needs

September 27, 2014
Next →

Retrieval Augmented Generation for Claim Processing: Combining MongoDB Atlas Vector Search and Large Language Models

Following up on our previous blog, AI, Vectors, and the Future of Claims Processing: Why Insurance Needs to Understand The Power of Vector Databases , we’ll pick up the conversation right where we left it. We discussed extensively how Atlas Vector Search can benefit the claim process in insurance and briefly covered Retrieval Augmented Generation (RAG) and Large Language Models (LLMs). MongoDB.local NYC Join us in person on May 2, 2024 for our keynote address, announcements, and technical sessions to help you build and deploy mission-critical applications at scale. Use Code Web50 for 50% off your ticket! Learn More One of the biggest challenges for claim adjusters is pulling and aggregating information from disparate systems and diverse data formats. PDFs of policy guidelines might be stored in a content-sharing platform, customer information locked in a legacy CRM, and claim-related pictures and voice reports in yet another tool. All of this data is not just fragmented across siloed sources and hard to find but also in formats that have been historically nearly impossible to index with traditional methods. Over the years, insurance companies have accumulated terabytes of unstructured data in their data stores but have failed to capitalize on the possibility of accessing and leveraging it to uncover business insights, deliver better customer experiences, and streamline operations. Some of our customers even admit they’re not fully aware of all the data in their archives. There’s a tremendous opportunity to leverage this unstructured data to benefit the insurer and its customers. Our image search post covered part of the solution to these challenges, opening the door to working more easily with unstructured data. RAG takes it a step further, integrating Atlas Vector Search and LLMs, thus allowing insurers to go beyond the limitations of baseline foundational models, making them context-aware by feeding them proprietary data. Figure 1 shows how the interaction works in practice: through a chat prompt, we can ask questions to the system, and the LLM returns answers to the user and shows what references it used to retrieve the information contained in the response. Great! We’ve got a nice UI, but how can we build an RAG application? Let’s open the hood and see what’s in it! Figure 1: UI of the claim adjuster RAG-powered chatbot Architecture and flow Before we start building our application, we need to ensure that our data is easily accessible and in one secure place. Operational Data Layers (ODLs) are the recommended pattern for wrangling data to create single views. This post walks the reader through the process of modernizing insurance data models with Relational Migrator, helping insurers migrate off legacy systems to create ODLs. Once the data is organized in our MongoDB collections and ready to be consumed, we can start architecting our solution. Building upon the schema developed in the image search post , we augment our documents by adding a few fields that will allow adjusters to ask more complex questions about the data and solve harder business challenges, such as resolving a claim in a fraction of the time with increased accuracy. Figure 2 shows the resulting document with two highlighted fields, “claimDescription” and its vector representation, “claimDescriptionEmbedding” . We can now create a Vector Search index on this array, a key step to facilitate retrieving the information fed to the LLM. Figure 2: document schema of the claim collection, the highlighted fields are used to retrieve the data that will be passed as context to the LLM Having prepared our data, building the RAG interaction is straightforward; refer to this GitHub repository for the implementation details. Here, we’ll just discuss the high-level architecture and the data flow, as shown in Figure 3 below: The user enters the prompt, a question in natural language. The prompt is vectorized and sent to Atlas Vector Search; similar documents are retrieved. The prompt and the retrieved documents are passed to the LLM as context. The LLM produces an answer to the user (in natural language), considering the context and the prompt. Figure 3: RAG architecture and interaction flow It is important to note how the semantics of the question are preserved throughout the different steps. The reference to “adverse weather” related accidents in the prompt is captured and passed to Atlas Vector Search, which surfaces claim documents whose claim description relates to similar concepts (e.g., rain) without needing to mention them explicitly. Finally, the LLM consumes the relevant documents to produce a context-aware question referencing rain, hail, and fire, as we’d expect based on the user's initial question. So what? To sum it all up, what’s the benefit of combining Atlas Vector Search and LLMs in a Claim Processing RAG application? Speed and accuracy: Having the data centrally organized and ready to be consumed by LLMs, adjusters can find all the necessary information in a fraction of the time. Flexibility: LLMs can answer a wide spectrum of questions, meaning applications require less upfront system design. There is no need to build custom APIs for each piece of information you’re trying to retrieve; just ask the LLM to do it for you. Natural interaction: Applications can be interrogated in plain English without programming skills or system training. Data accessibility: Insurers can finally leverage and explore unstructured data that was previously hard to access. Not just claim processing The same data model and architecture can serve additional personas and use cases within the organization: Customer Service: Operators can quickly pull customer data and answer complex questions without navigating different systems. For example, “Summarize this customer's past interactions,” “What coverages does this customer have?” or “What coverages can I recommend to this customer?” Customer self-service: Simplify your members’ experience by enabling them to ask questions themselves. For example, “My apartment is flooded. Am I covered?” or “How long do windshield repairs take on average?” Underwriting: Underwriters can quickly aggregate and summarize information, providing quotes in a fraction of the time. For example, “Summarize this customer claim history.” “I Am renewing a customer policy. What are the customer's current coverages? Pull everything related to the policy entity/customer. I need to get baseline info. Find relevant underwriting guidelines.” If you would like to discover more about Converged AI and Application Data Stores with MongoDB, take a look at the following resources: RAG for claim processing GitHub repository From Relational Databases to AI: An Insurance Data Modernization Journey Modernize your insurance data models with MongoDB and Relational Migrator

April 18, 2024