www.mongodb.com
Open in
urlscan Pro
52.84.229.87
Public Scan
Submitted URL: https://salesloft.mongodb.com/t/109648/sc/0ac77819-d2af-40f1-aa8d-756cd4a5a3b8/NB2HI4DTHIXS653XO4XG233OM5XWIYROMNXW2L3CNRXWOL3...
Effective URL: https://www.mongodb.com/blog/post/building-ai-mongodb-conversation-intelligence-observe-ai
Submission: On June 04 via manual from SG — Scanned from SG
Effective URL: https://www.mongodb.com/blog/post/building-ai-mongodb-conversation-intelligence-observe-ai
Submission: On June 04 via manual from SG — Scanned from SG
Form analysis
1 forms found in the DOMGET https://www.mongodb.com/search
<form role="search" method="GET" action="https://www.mongodb.com/search" class="css-1c69emu">
<div class="css-87svlz">
<div class="css-36i4c2"><input type="text" placeholder="Search products, whitepapers, & more..." class="css-etrcff"></div>
<div class="css-v2nqhr">
<div class="css-aef77t"><button role="button" type="button" class="css-14k7wrz"><span data-testid="selected-value" class="css-6k4l2y">General Information</span>
<div class="css-109dpaz"><svg data-testid="icon" width="16" height="9" viewBox="0 0 16 9" fill="none" xmlns="http://www.w3.org/2000/svg" class="css-1yzkxhp">
<path d="M1.06689 0.799988L8.00023 7.73332L14.9336 0.799988" stroke-linecap="round" stroke-linejoin="round" class="css-1tlq8q9"></path>
</svg></div>
</button>
<div class="css-hn9qqo">
<ul data-testid="options" role="listbox" class="css-ac9zo2">
<li role="option" tabindex="0" class="css-11dtrvq">General Information</li>
<li role="option" tabindex="0" class="css-11dtrvq">Documentation</li>
<li role="option" tabindex="0" class="css-11dtrvq">Developer Articles & Topics</li>
<li role="option" tabindex="0" class="css-11dtrvq">Community Forums</li>
<li role="option" tabindex="0" class="css-11dtrvq">Blog</li>
<li role="option" tabindex="0" class="css-11dtrvq">University</li>
</ul>
</div>
</div><input type="hidden" id="addsearch" name="addsearch">
<div class="css-1myrko"><button type="submit" tabindex="0" class=" css-13l1z36" data-track="true"><img alt="search icon" src="https://webimages.mongodb.com/_com_assets/cms/krc3hljsdwdfd2w5d-web-actions-search.svg?auto=format%252Ccompress"
width="18" height="18" class="css-r9fohf"></button></div>
</div>
</div>
</form>
Text Content
Blog {Blog} Announced at MongoDB.local NYC 2024: A recap of all announcements and updates — Learn more > General Information * General Information * Documentation * Developer Articles & Topics * Community Forums * Blog * University * Products Platform AtlasBuild on a developer data platform Platform Services DatabaseDeploy a multi-cloud databaseSearchDeliver engaging search experiencesVector SearchDesign intelligent apps with GenAIStream ProcessingUnify data in motion and data at rest Tools CompassWork with MongoDB data in a GUIIntegrationsIntegrations with third-party servicesRelational MigratorMigrate to MongoDB with confidence Self Managed Enterprise AdvancedRun and manage MongoDB yourselfCommunity EditionDevelop locally with MongoDB Build with MongoDB Atlas Get started for free in minutes Sign Up Test Enterprise Advanced Develop with MongoDB on-premises Download Try Community Edition Explore the latest version of MongoDB Download * Resources Documentation Atlas DocumentationGet started using AtlasServer DocumentationLearn to use MongoDBStart With GuidesGet step-by-step guidance for key tasks Tools and ConnectorsLearn how to connect to MongoDBMongoDB DriversUse drivers and libraries for MongoDB AI Resources HubGet help building the next big thing in AI with MongoDBarrow-right Connect Developer CenterExplore a wide range of developer resourcesCommunityJoin a global community of developersCourses and CertificationLearn for free from MongoDBWebinars and EventsFind a webinar or event near you * Solutions Use cases Artificial IntelligenceEdge ComputingInternet of ThingsMobilePaymentsServerless Development Industries Financial ServicesTelecommunicationsHealthcareRetailPublic SectorManufacturing Solutions LibraryOrganized and tailored solutions to kick-start projectsarrow-right Developer Data Platform Accelerate innovation at scale Learn morearrow-right Startups and AI Innovators For world-changing ideas and AI pioneers Learn morearrow-right Customer Case Studies Hear directly from our users See Storiesarrow-right * Company CareersStart your next adventureBlogRead articles and announcementsNewsroomRead press releases and news stories PartnersLearn about our partner ecosystemLeadershipMeet our executive teamCompanyLearn more about who we are Contact Us Reach out to MongoDB Let’s chatarrow-right Investors Visit our investor portal Learn morearrow-right * Pricing SupportSign In Try Free menu-vertical Home News Applied QuickStart Updates Culture Events Artificial Intelligence Engineering Blog All BUILDING AI WITH MONGODB: CONVERSATION INTELLIGENCE WITH OBSERVE.AI Mat Keep April 29, 2024 | Updated: May 9, 2024 #genAI What's really happening in your business? The answer to that question lies in the millions of interactions between your customers and your brand. If you could listen in on every one of them, you'd know exactly what was up--and down. You’d also be able to continuously improve customer service by coaching agents when needed. However, the reality is that most companies have visibility in only 2% of their customer interactions. Observe.AI is here to change that. The company is focused on being the fastest way to boost contact center performance with live conversation intelligence. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Founded in 2017 and headquartered in California, Observe.AI has raised over $200m in funding. Its team of 250+ members serves more than 300 organizations across various industries. Leading companies like Accolade, Pearson, Public Storage, and 2U partner with Observe.AI to accelerate outcomes from the frontline to the rest of the business. The company has pioneered a 40 billion-parameter contact center large language model (LLM) and one of the industry’s most accurate Generative AI engines. Through these innovations, Observe.AI provides analysis and coaching to maximize the performance of its customers’ front-line support and sales teams. We sat down with Jithendra Vepa, Ph.D, Chief Scientist & India General Manager at Observe.AI to learn more about the AI stack powering the industry-first contact center LLM. CAN YOU START BY DESCRIBING THE AI/ML TECHNIQUES, ALGORITHMS, OR MODELS YOU ARE USING? “Our products employ a versatile range of AI and ML techniques, covering various domains. Within natural language processing (NLP), we rely on advanced algorithms and models such as transformers, including the likes of transformer-based in-house LLMs, for text classification, intent and entity recognition tasks, summarization, question-answering, and more. We embrace supervised, semi-supervised, and self-supervised learning approaches to enhance our models' accuracy and adaptability." "Additionally, our application extends its reach into speech processing, where we leverage state-of-the-art methods for tasks like automatic speech recognition and sentiment analysis. To ensure our language capabilities remain at the forefront, we integrate the latest Large Language Models (LLMs), ensuring that our application benefits from cutting-edge natural language understanding and generation capabilities. Our models are trained using contact center data to make them domain-specific and more accurate than generic models out there.” CAN YOU SHARE MORE ON HOW YOU TRAIN AND TUNE YOUR MODELS? “In the realm of model development and training, we leverage prominent frameworks like TensorFlow and PyTorch. These frameworks empower us to craft, fine-tune, and train intricate models, enabling us to continually improve their accuracy and efficiency." "In our natural language processing (NLP) tasks, prompt engineering and meticulous fine-tuning hold pivotal roles. We utilize advanced techniques like transfer learning and gradient-based optimization to craft specialized NLP models tailored to the nuances of our tasks." HOW DO YOU OPERATIONALIZE AND MONITOR THESE MODELS? "To streamline our machine learning operations (MLOps) and ensure seamless scalability, we have incorporated essential tools such as Docker and Kubernetes. These facilitate efficient containerization and orchestration, enabling us to deploy, manage, and scale our models with ease, regardless of the complexity of our workloads." "To maintain a vigilant eye on the performance of our models in real-time, we have implemented robust monitoring and logging to continuously collect and analyze data on model performance, enabling us to detect anomalies, address issues promptly, and make data-driven decisions to enhance our application's overall efficiency and reliability.” THE ROLE OF MONGODB IN OBSERVE.AI TECHNOLOGY STACK The MongoDB developer data platform gives the company’s developers and data scientists a unified solution to build smarter AI applications. Describing how they use MongoDB, Jithendra says “OBSERVE.AI processes and runs models on millions of support touchpoints daily to generate insights for our customers. Most of this rich, unstructured data is stored in MongoDB. We chose to build on MongoDB because it enables us to quickly innovate, scale to handle large and unpredictable workloads, and meet the security requirements of our largest enterprise customers.” GETTING STARTED Thanks so much to Jithendra for sharing details on the technology stack powering Observe.AI’s conversation intelligence and MongoDB’s role. To learn more about how MongoDB can help you build AI-enriched applications, take a look at the MongoDB for Artificial Intelligence page. Here, you will find tutorials, documentation, and whitepapers that will accelerate your journey to intelligent apps. ← Previous BUILDING AI WITH MONGODB: INTEGRATING VECTOR SEARCH AND COHERE TO BUILD FRONTIER ENTERPRISE APPS Cohere is the leading enterprise AI platform, building large language models (LLMs) which help businesses unlock the potential of their data. Operating at the frontier of AI, Cohere’s models provide a more intuitive way for users to retrieve, summarize, and generate complex information. Cohere offers both text generation and embedding models to its customers. Enterprises running mission-critical AI workloads select Cohere because its models offer the best performance-cost tradeoff and can be deployed in production at scale. Cohere’s platform is cloud-agnostic. Their models are accessible through their own API as well as popular cloud managed services, and can be deployed on a virtual private cloud (VPC) or even on-prem to meet companies where their data is, offering the highest levels of flexibility and control. Cohere’s leading Embed 3 and Rerank 3 models can be used with MongoDB Atlas Vector Search to convert MongoDB data to vectors and build a state-of-the-art semantic search system. Search results also can be passed to Cohere’s Command R family of models for retrieval augmented generation (RAG) with citations. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. A new approach to vector embeddings It is in the realm of embedding where Cohere has made a host of recent advances. Described as “AI for language understanding,” Embed is Cohere’s leading text representation language model. Cohere offers both English and multilingual embedding models, and gives users the ability to specify the type of data they are computing an embedding for (e.g., search document, search query). The result is embeddings that improve the accuracy of search results for traditional enterprise search or retrieval-augmented generation. One challenge developers faced using Embed was that documents had to be passed one by one to the model endpoint, limiting throughput when dealing with larger data sets. To address that challenge and improve developer experience, Cohere has recently announced its new Embed Jobs endpoint . Now entire data sets can be passed in one operation to the model, and embedded outputs can be more easily ingested back into your storage systems. Additionally, with only a few lines of code, Rerank 3 can be added at the final stage of search systems to improve accuracy. It also works across 100+ languages and offers uniquely high accuracy on complex data such as JSON, code, and tabular structure. This is particularly useful for developers who rely on legacy dense retrieval systems. Demonstrating how developers can exploit this new endpoint, we have published the How to use Cohere embeddings and rerank modules with MongoDB Atlas tutorial . Readers will learn how to store, index, and search the embeddings from Cohere. They will also learn how to use the Cohere Rerank model to provide a powerful semantic boost to the quality of keyword and vector search results. Figure 1: Illustrating the embedding generation and search workflow shown in the tutorial Why MongoDB Atlas and Cohere? MongoDB Atlas provides a proven OLTP database handling high read and write throughput backed by transactional guarantees. Pairing these capabilities with Cohere’s batch embeddings is massively valuable to developers building sophisticated gen AI apps. Developers can be confident that Atlas Vector Search will handle high scale vector ingestion, making embeddings immediately available for accurate and reliable semantic search and RAG. Increasing the speed of experimentation, developers and data scientists can configure separate vector search indexes side by side to compare the performance of different parameters used in the creation of vector embeddings. In addition to batch embeddings, Atlas Triggers can also be used to embed new or updated source content in real time, as illustrated in the Cohere workflow shown in Figure 2. Figure 2: MongoDB Atlas Vector Search supports Cohere’s batch and real time workflows. (Image courtesy of Cohere) Supporting both batch and real-time embeddings from Cohere makes MongoDB Atlas well suited to highly dynamic gen AI-powered apps that need to be grounded in live, operational data. Developers can use MongoDB’s expressive query API to pre-filter query predicates against metadata, making it much faster to access and retrieve the more relevant vector embeddings. The unification and synchronization of source application data, metadata, and vector embeddings in a single platform, accessed by a single API, makes building gen AI apps faster, with lower cost and complexity. Those apps can be layered on top of the secure, resilient, and mature MongoDB Atlas developer data platform that is used today by over 45,000 customers spanning startups to enterprises and governments handling mission-critical workloads. What's next? To start your journey into gen AI and Atlas Vector Search, review our 10-minute Learning Byte . In the video, you’ll learn about use cases, benefits, and how to get started using Atlas Vector Search. April 25, 2024 Next → MICROSERVICES: REALIZING THE BENEFITS WITHOUT THE COMPLEXITY The microservice architecture has emerged as the preferred, modern approach for developers to build and deploy applications on the cloud. It can help you deliver more reliable applications, and address the scale and latency concerns for System Reliability Engineers (SREs) and operations. But microservices aren't without their hangups. For developers, microservices can lead to additional complexity and cognitive overhead, such as cross-service coordination, shared states across multiple services, and coding and testing failure logic across disconnected services. While the monolith was suboptimal for compute and scale efficiencies, the programming model was simple. So the question is, can we get the best of both worlds? In addition, how do we make the individual services easier to build and adapt to changing requirements? Since, at their core, microservices provide access to and perform operations on data, how do we architect services so that developers can easily work with data? How can we make it easier for developers to add new types of data and data sources and perform a wide variety of data operations without the complexity of managing caches and using multiple query languages (SQL, full-text and vector search, time series, geospatial, etc.) The development complexity associated with microservice architectures occurs at two levels: service orchestration and service data management. The diagram below depicts this complexity. At the orchestration level, a typical application may support tens or hundreds of processes, and each may have thousands or millions of executions. To make this work, services are often connected by a patchwork of queues. Developers spend quite a bit of time tracking and managing all the various workflows. The sheer scale necessitates a central mechanism to manage concurrent tasks and sharded databases to manage the state of millions of concurrent workflow instances. To add more complexity, each microservice is deployed using a set of data platforms including RDBMS, caches, search engines, and vector and NoSQL databases. Developers must work with multiple query languages, write code to keep data in sync among these platforms and write code to deal with edge cases when invariably data or indexes are not in sync. Finally, developer productivity is inhibited by the brittleness of RDBMS, which lacks flexibility when trying to incorporate new or changing data types. As a result, microservice applications often end up with complex architectures that are difficult to develop against and maintain in terms of both the individual microservices and the service orchestration. Realizing the benefits without the complexity One approach to address these microservice challenges is to combine two technologies: Temporal and MongoDB. Both give you the benefits of microservices while simplifying the implementation of service orchestration. Together, they allow developers to build services that can easily handle a wide variety of data, eliminate the need to code for complex infrastructure and reduce the likelihood of failure. They simplify the data model and your code. In one real-world example, open-source indexing company Mixpeek leverages the combination of MongoDB and Temporal to provide a platform enabling organizations to easily incorporate multi-modal data sources in AI applications. Mixpeek’s CEO Ethan Steininger states, “Temporal’s durable execution guarantees and MongoDB's flexible data model are core components of Mixpeek’s multimodal data processing and storage. Combined, they enable our users to run high volume ML on commodity hardware without worrying about dropped jobs.” MongoDB and Temporal: Build like a monolith with durable microservices Both MongoDB and Temporal were built by developers, for developers. They both use a code-first approach to solving the complex infrastructure needs of our modern applications within our application code and empower developers to be more productive. They are part of an emerging development stack that greatly simplifies data and all the cross-functional coordination we need in our cloud applications. Ultimately, the combination of these two developer-focused platforms allows you to simplify design, development, and testing of microservice-based applications. With the document model of MongoDB, you model data as real world objects and not tables, rows, and columns. With Temporal, you design your end-to-end service flows as workflows as described by domain experts without having to explicitly identify every edge case and exception (Temporal handles those implicitly). Temporal and MongoDB provide the same benefits that, when combined, multiply in value. You become more agile, as not only can everyone understand your code better, but you are no longer challenged by the cognitive overload of trying to coordinate, comprehend, and test a web of disconnected and complex services. Together, they allow us to reliably orchestrate business processes within apps that are all speaking the language of the data itself. Combining Temporal and MongoDB results in the simplified architecture shown below. Temporal enables orchestration to be implemented at a higher level of abstraction, eliminating much of the event management and queuing complexity. MongoDB, in turn, provides a single integrated data platform with a unified query language thereby eliminating much of the data management complexity. Let’s examine MongoDB and Temporal in more depth to better understand their capabilities and why they facilitate the rapid development of microservices-based applications. MongoDB: Simplifying microservice data MongoDB's features align well with the principles of microservices architectures. It reduces the need for niche databases and the associated costs of deploying and maintaining a complicated sprawl of data technologies. More explicitly, MongoDB delivers key benefits for microservice development: Flexible schema, flexible services: Unlike relational databases with rigid schemas, MongoDB's document model allows microservices to easily evolve as data requirements change. Distributed scale for data-heavy, distributed services: MongoDB scales horizontally by adding more partitions to distribute the load. This aligns with the modular nature of microservices, where individual services can scale based on their specific needs. Unified query language reduces microservice sprawl: MongoDB supports a diverse set of data operations without requiring multiple data platforms (caches, vector, and text search engines, time series, geospatial, etc.) Operational efficiency: MongoDB Atlas, the cloud-based version of MongoDB, simplifies managing databases for microservices. It handles provisioning, backups, and patching, freeing developers to focus on core responsibilities. Integrated developer data platform: The integrated developer data platform delivers an intuitive set of tools to build services that support mobile clients, real-time analytics, data visualization, and historical analysis across many service databases. With MongoDB, development teams use one interface for all their services and run it anywhere, even across clouds. Also, it provides a data foundation for your microservices that is highly available, scalable, and secure. It greatly simplifies microservices development so that you can focus on your business problems and not data. Temporal: Don't coordinate services, orchestrate them Temporal delivers an open-source, durable execution solution that removes the complexity of building scalable distributed microservices. It presents a development abstraction that preserves the complete application state so that in the case of a host or software failure, it can seamlessly migrate execution to another machine. This means you can develop applications as if failures—like network outages or server crashes—do not exist. Temporal handles these issues, allowing you to focus on implementing business logic rather than coding complex failure detection and recovery routines. Here's how Temporal simplifies application development: Durable workflows: Temporal maintains the state and progress of a defined workflow across multiple services, even in the face of server crashes, network partitions, and other types of failures. This durability ensures that your application logic can resume where it left off, making your overall application more resilient. Simplifies failure handling: Temporal abstracts away the complex error handling and retry logic that developers typically have to implement in distributed systems. This abstraction allows developers to focus on business logic rather than the intricacies of ensuring their end-to-end services can handle failures gracefully. Scale: Temporal applications are inherently scalable and capable of handling billions of workflow executions. Long-running services: Temporal supports long-running operations, from seconds to years, with the same level of reliability and scalability. By providing a platform that handles the complexities of distributed systems, Temporal allows developers to concentrate on implementing business logic in their services. This focus can lead to faster development times and more reliable applications, as developers are not bogged down by the intricacies of state management, retries, and error handling. The next generation of microservices development is here Developers want to code. They want to solve business problems. They do not want to be bogged down by the complexity of infrastructure failures. They want to model their apps and data so that it is aligned with the real-world entities and domains they are solving for. Using MongoDB and Temporal together solves these complexities. Together, they simplify design, development, and testing of microservice-based applications so that you can focus on business problems and deliver more features faster. Getting started with Temporal and MongoDB Atlas We can help you design the best architecture for your organization’s needs. Feel free to connect with your MongoDB and Temporal account teams or contact us to schedule a collaborative session and explore how Temporal and MongoDB can optimize your AI development process. June 3, 2024 © 2024 MongoDB, Inc. About * Careers * Investor Relations * Legal Notices * Privacy Notices * Security Information * Trust Center Support * Contact Us * Customer Portal * Atlas Status * Customer Support Social * GitHub * Stack Overflow * LinkedIn * YouTube * X * Twitch * Facebook © 2024 MongoDB, Inc. PRIVACY PREFERENCE CENTER "Cookies" are small files that enable us to store information while you visit one of our websites. When you visit any website, it may store or retrieve information on your browser, mostly in the form of cookies. This information might be about you, your preferences or your device and is mostly used to make the site work as you expect it to. The information does not usually directly identify you, but it can give you a more personalized web experience. Because we respect your right to privacy, you can choose not to allow some types of cookies, but essential cookies are always enabled. Click on the different category headings to find out more and change our default settings. However, blocking some types of cookies may impact your experience of the site and the services we are able to offer. MongoDB Privacy Policy Allow All MANAGE CONSENT PREFERENCES STRICTLY NECESSARY COOKIES Always Active These cookies are necessary for the website to function and cannot be switched off in our systems. They are usually only set in response to actions made by you which amount to a request for services, such as setting your privacy preferences, logging in or filling in forms. You can set your browser to block or alert you about these cookies, but some parts of the site will not then work. These cookies do not store any personally identifiable information. PERFORMANCE COOKIES Performance Cookies These cookies allow us to count visits and traffic sources so we can measure and improve the performance of our site. They help us to know which pages are the most and least popular and see how visitors move around the site. All information these cookies collect is aggregated and therefore anonymous. If you do not allow these cookies we will not know when you have visited our site, and will not be able to monitor its performance. FUNCTIONAL COOKIES Functional Cookies These cookies enable the website to provide enhanced functionality and personalisation. They may be set by us or by third party providers whose services we have added to our pages. If you do not allow these cookies then some or all of these services may not function properly. TARGETING COOKIES Targeting Cookies These cookies may be set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant adverts on other sites. They do not store directly personal information, but are based on uniquely identifying your browser and internet device. If you do not allow these cookies, you will experience less targeted advertising. SOCIAL MEDIA COOKIES Social Media Cookies These cookies are set by a range of social media services that we have added to the site to enable you to share our content with your friends and networks. They are capable of tracking your browser across other sites and building up a profile of your interests. This may impact the content and messages you see on other websites you visit. If you do not allow these cookies you may not be able to use or see these sharing tools. Back Button COOKIE LIST Search Icon Filter Icon Clear checkbox label label Apply Cancel Consent Leg.Interest checkbox label label checkbox label label checkbox label label Confirm My Choices