Building AI with MongoDB: Accelerating App Development With the Codeium AI Toolkit
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.
Together AI: Advancing the Frontier of AI With Open Source Embeddings, Inference, and MongoDB Atlas
Founded in San Francisco in 2022, Together AI is on a mission to create the fastest cloud platform for building and running generative AI (gen AI). The company has so far raised over $120 million, counting Nvidia, Kleiner Perkins, Lux, and NEA as investors. Ce Zhang, Founder & CTO at Together AI says, “Together AI is a research-driven artificial intelligence company. We contribute leading open-source research, models, and datasets to advance the frontier of AI. Our cloud services empower developers and researchers at organizations of all sizes to train, fine-tune, and deploy generative AI models. We believe open and transparent AI systems will drive innovation and create the best outcomes for society." Check out our AI resource page to learn more about building AI-powered apps with MongoDB. The company has recently introduced its Together Embeddings endpoint — a new service for developers building a variety of applications, including one that is top of mind for nearly all gen AI-powered apps: retrieval-augmented generation (RAG) . With the RAG pattern, developers can feed gen AI models with their own up-to-date, domain-specific data. The results are more reliable gen AI outputs that are customized for the business along with reduced risks of hallucinations. The Together Embeddings endpoint offers access to eight leading open-source embedding models at up to 12x cheaper price than proprietary alternatives. The list of the models includes top models from the MTEB leaderboard (Massive Text Embedding Benchmark), such as UAE-Large-v1 and BGE models, and state-of-the-art long context retrieval models. Together Embeddings also offers integrations to MongoDB Atlas , LangChain, and LlamaIndex for RAG. To demonstrate this integration, the engineering team at Together AI created a tutorial for developers exploring how to build a RAG application with MongoDB Atlas. This tutorial shows how to use Together Embeddings and Together Inference to generate embeddings and language responses. Atlas Vector Search is used to store and index embeddings and then perform semantic search to retrieve relevant data examples for natural language queries against a sample Airbnb listing dataset. With this RAG pattern, the gen AI model can recommend properties that meet the user’s criteria while adhering to factual information. We prioritized integrating with MongoDB because of its relevance and importance in the AI stack. Vipul Ved Prakash, Founder & CEO at Together AI “Bringing together live application data synchronized right alongside vector embeddings in a single platform, MongoDB Atlas helps developers reduce complexity and cost, and bring cutting-edge apps to market faster,” says Prakash. “This is one example, and we are looking forward to seeing many amazing applications that will be built using Together AI and MongoDB’s Atlas Vector Search.” To learn more about its RAG integrations, take a look at Together AI’s documentation . To get started with MongoDB and Together AI, register for MongoDB Atlas and read the tutorial . If your team is building AI apps, sign up for the AI Innovators Program . Successful companies get access to free Atlas credits and technical enablement, as well as connections into the broader AI ecosystem.
Building AI with MongoDB: Putting Jina AI’s Breakthrough Open Source Embedding Model To Work
Founded in 2020 and based in Berlin, Germany, Jina AI has swiftly risen as a leader in multimodal AI, focusing on prompt engineering and embedding models. With its commitment to open-source and open research, Jina AI is bridging the gap between advanced AI theory and the real world AI-powered applications being built by developers and data scientists. Over 400,000 users are registered to use the Jina AI platform. Dr. Han Xiao, Founder and CEO at Jina AI, describes the company’s mission: “We envision paving the way towards the future of AI as a multimodal reality. We recognize that the existing machine learning and software ecosystems face challenges in handling multimodal AI. As a response, we're committed to developing pioneering tools and platforms that assist businesses and developers in navigating these complexities. Our vision is to play a crucial role in helping the world harness the vast potential of multimodal AI and truly revolutionize the way we interpret and interact with information." Jina AI’s work in embedding models has caught significant industry interest. As many developers now know, embeddings are essential to generative AI (gen AI). Embedding models are sophisticated algorithms that transform and embed data of any structure into multi-dimensional numerical encodings called vectors. These vectors give data semantic meaning by capturing its patterns and relationships. This means we can analyze and search for unstructured data in the same way we’ve always been able to with structured business data. Considering that over 80% of the data we create every day is unstructured, we start to appreciate how transformational embeddings — when combined with a powerful solution such as MongoDB Atlas Vector Search — are for gen AI. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Jina AI's jina-embeddings-v2 is the first open-source 8K text embedding model. Its 8K token length provides deeper context comprehension, significantly enhancing accuracy and relevance for tasks like retrieval-augmented generation (RAG) and semantic search . Jina AI’s embeddings offer enhanced data indexing and search capabilities, along with bilingual support. The embedding models are focused on singular languages and language pairs, ensuring state-of-the-art performance on language-specific benchmarks. Currently, Jina Embeddings v2 includes bilingual German-English and Chinese-English models, with other bilingual models in the works. Jina AI’s embedding models excel in classification, reranking, retrieval, and summarization, making them suitable for diverse applications, especially those that are cross-lingual. Recent examples from multinational enterprise customers include the automation of sales sequences, skills matching in HR applications, and payment reconciliation with fraud detection. Figure 1: Jina AI’s world-class embedding models improve search and RAG systems. In our recently published Jina Embeddings v2 and MongoDB Atlas article we show developers how to get started in bringing vector embeddings into their apps. The article covers: Creating a MongoDB Atlas instance and loading it with your data. (The article uses a sample Airbnb reviews data set.) Creating embeddings for the data set using the Jina Embeddings API. Storing and indexing the embeddings with Atlas Vector Search. Implementing semantic search using the embeddings. Dr. Xiao says, “Our Embedding API is natively integrated with key technologies within the gen AI developer stack including MongoDB Atlas, LangChain, LlamaIndex, Dify, and Haystack. MongoDB Atlas unifies application data and vector embeddings in a single platform, keeping both fully synced. Atlas Triggers keeps embeddings fresh by calling our Embeddings API whenever data is inserted or updated in the database. This integrated approach makes developers more productive as they build new, cutting-edge AI-powered apps for the business.” To get started with MongoDB and Jina AI, register for MongoDB Atlas and read the tutorial . If your team is building its AI apps, sign up for the AI Innovators Program . Successful companies get access to free Atlas credits and technical enablement, as well as connections into the broader AI ecosystem.
Building AI with MongoDB: Navigating the Path From Predictive to Generative AI
It should come as no surprise that the organizations unlocking the largest benefits from generative AI (gen AI) today have already been using predictive AI (a.k.a. classic, traditional, or analytical AI). McKinsey made this same observation back in June 2023 with its “Economic Potential of Generative AI 1 ” research. There would seem to be several reasons for this: An internal culture that is willing to experiment and explore what AI can do Access to skills — though we must emphasize that gen AI is way more reliant on developers than the data scientists driving predictive AI Availability of clean and curated data from across the organization that is ready to be fed into genAI models This doesn’t mean to say that only those teams with prior experience in predictive AI stand to benefit from gen AI. If you take a look at examples from our Building AI case study series , you’ll see many organizations with different AI maturity levels tapping MongoDB for gen AI innovation today. In this latest edition of the Building AI series, we feature two companies that, having built predictive AI apps, are now navigating the path to generative AI: MyGamePlan helps professional football players and coaches improve team performance. Ferret.ai helps businesses and consumers build trust by running background checks using public domain data. In both cases, Predictive AI is central to data-driven decision-making. And now both are exploring gen AI to extend their services with new products that further deepen user engagement. The common factor for both? Their use of MongoDB Atlas and its flexibility for any AI use case. Let's dig in. MyGamePlan: Elevating the performance of professional football players with AI-driven insights The use of data and analytics to improve the performance of professional athletes isn’t new. Typically, solutions are highly complex, relying on the integration of multiple data providers, resulting in high costs and slow time-to-insight. MyGamePlan is working to change that for professional football clubs and their players. (For the benefit of my U.S. colleagues, where you see “football” read “soccer.”) MyGamePlan is used by staff and players at successful teams across Europe, including Bayer Leverkusen (current number one in the German Bundesliga), AFC Sunderland in the English Championship, CD Castellón (current number one in the third division of Spain), and Slask Wroclaw (the current number one in the Polish Ekstraklasa). I met with Dries Deprest, CTO and co-founder at MyGamePlan who explains, “We redefine football analysis with cutting-edge analytics, AI, and a user-friendly platform that seamlessly integrates data from match events, player tracking, and video sources. Our platform automates workflows, allowing coaches and players to formulate tactics for each game, empower player development, and drive strategic excellence for the team's success.” At the core of the MyGamePlay platform are custom, Python-based predictive AI models hosted in Amazon Sagemaker. The models analyze passages of gameplay to score the performance of individual players and their impact on the game. Performance and contribution can be tracked over time and used to compare with players on opposing teams to help formulate matchday tactics. Data is key to making the models and predictions accurate. The company uses MongoDB Atlas as its database, storing: Metadata for each game, including matches, teams, and players. Event data from each game such as passes, tackles, fouls, and shots. Tracking telemetry that captures the position of each player on the field every 100ms. This data is pulled from MongoDB into Python DataFrames where it is used alongside third-party data streams to train the company’s ML models. Inferences generated from specific sequences of gameplay are stored back in MongoDB Atlas for downstream analysis by coaches and players. Figure 1: With MyGamePlans web and mobile apps, coaching staff, and players can instantly assess gameplay and shape tactics. On selecting MongoDB, Deprest says, We are continuously enriching data with AI models and using it for insights and analytics. MongoDB is a great fit for this use case. “We chose MongoDB when we started our development two years ago. Our data has complex multi-way relationships, mapping games to players to events and tracking. The best way to represent this data is with nested elements in rich document data structures. It's way more efficient for my developers to work with and for the app to process. Trying to model these relationships with foreign keys and then joining normalized tables in relational databases would be slow and inefficient.” In terms of development, Deprest says, “We use the PyMongo driver to integrate MongoDB with our Python ML data pipelines in Sagemaker and the MongoDB Node.js driver for our React-based, client-facing web and mobile apps.” Deprest goes on to say, "There are two key factors that differentiate MongoDB from NoSQL databases we also considered: the incredible level of developer adoption it has, meaning my team was immediately familiar and productive with it. And we can build in-app analytics directly on top of our live data, without the time and expense of having to move it out into some data warehouse or data lake. With MongoDB’s aggregation pipelines , we can process and analyze data with powerful roll-ups, transformations, and window functions to slice and dice data any way our users need it." Moving beyond predictive AI, the MyGamePlan team is now evaluating how gen AI can further improve user experience. Deprest says, "We have so much rich data and analytics in our platform, and we want to make it even easier for players and coaches to extract insights from it. We are experimenting with natural language processing via chat and question-answering interfaces on top of the data. Gen AI makes it easy for users to visualize and summarize the data. We are currently evaluating OpenAI’s ChatGPT LLM coupled with sophisticated approaches to prompt engineering, orchestration via Langchain, and retrieval augmented generation (RAG) using LlamaIndex and MongoDB Atlas Vector Search ." As our source data is in the MongoDB Atlas database already, unifying it with vector storage and search is a very productive and elegant solution for my developers. Dries Deprest, CTO and Co-founder, MyGamePlan By building on MongoDB Atlas, MyGamePlan’s team can use the breadth of functionality provided by a developer data platform to support almost any application and AI needs in the future. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Ferret.ai: Building trust with relationship intelligence powered by AI and MongoDB Atlas while cutting costs by 30% Across the physical and digital world, we are all constantly building relationships with others. Those relationships can be established through peer-to-peer transactions across online marketplaces, between tradespeople and professionals with their prospective clients, between investors and founders, or in creating new personal connections. All of those relationships rely on trust to work, but building it is hard. Ferret.ai was founded to remove the guesswork from building that trust. Ferret is an AI platform architected from the ground up to empower companies and individuals with real-time, unbiased intelligence to identify risks and embrace opportunities. Leveraging cutting-edge predictive and generative AI, hundreds of thousands of global data sources, and billions of public documents, Ferret.ai provides curated relationship intelligence and monitoring — once only available to the financial industry — making transparency the new norm. Al Basseri, CTO at Ferret tells us how it works: "We ingest information about individuals from public sources. This includes social networks, trading records, court documents, news archives, corporate ownership, and registered business interests. This data is streamed through Kafka pipelines into our Anyscale/Ray MLops platform where we apply natural language processing through our spaCy extraction and machine learning models. All metadata from our data sources — that's close to three billion documents — along with inferences from our models are stored in MongoDB Atlas . The data in Atlas is consumed by our web and mobile customer apps and by our corporate customers through our upcoming APIs." Figure 2: Artificial intelligence + real-time data = Relationship Intelligence from Ferret.ai. Moving beyond predictive AI, the company’s developers are now exploring opportunities to use gen AI in the Ferret platform. "We have a close relationship with the data science team at Nvidia,” says Basseri. “We see the opportunity to summarize the data sources and analysis we provide to help our clients better understand and engage with their contacts. Through our experimentation, the Mistral model with its mixture-of-experts ensemble seems to give us better results with less resource overhead than some of the larger and more generic large language models." As well as managing the data from Ferret’s predictive and gen AI models, customer data and contact lists are also stored in MongoDB Atlas. Through Ferret’s continuous monitoring and scoring of public record sources, any change in an individual's status is immediately detected. As Basseri explains, " MongoDB Atlas Triggers watch for updates to a score and instantly send an alert to consuming apps so our customers get real-time visibility into their relationship networks. It's all fully event-driven and reactive, so my developers just set it and forget it." Basseri also described the other advantages MongoDB provides his developers: Through Atlas, it’s available as a fully managed service with best practices baked in. That frees his developers and data scientists from the responsibilities of running a database so they can focus their efforts on app and AI innovation MongoDB Atlas is mature, having seen it scale in many other high-growth companies The availability of engineers who know MongoDB is important as the team rapidly expands Beyond the database, Ferret is extending its use of the MongoDB Atlas platform into text search. As the company moves into Google Cloud, it is migrating from its existing Amazon OpenSearch service to Atlas Search . Discussing the drivers for the migration, Basseri says, "Unifying both databases and search behind a single API reduces cognitive load for my developers, so they are more productive and build features faster. We eliminate all of the hassle of syncing data between database and search. Again, this frees up engineering cycles. It also means our users get a better experience because previous latency bottlenecks are gone — so as they search across contacts and content on our platform, they get the freshest results, not stale and outdated data." By migrating from OpenSearch to Atlas Search, we also save money and get more freedom. We will reduce our total cloud costs by 30% per month just by eliminating unnecessary data duplication between the database and the search engine. And with Atlas being multi-cloud, we get the optionality to move across cloud providers as and when we need to. Al Basseri, CTO at Ferret.ai Once the migration is complete, Basseri and the team will begin development with Atlas Vector Search as they continue to build out the gen AI side of the Ferret platform. What's next? No matter where you are in your AI journey, MongoDB can help. You can get started with your AI-powered apps by registering for MongoDB Atlas and exploring the tutorials available in our AI resources center . Our teams are always ready to come and explore the art of the possible with you. 1 https://www.mckinsey.com/capabilities/mckinsey-digital/our-insights/the-economic-potential-of-generative-ai-the-next-productivity-frontier
Announcing MongoDB as a Founding Member of the NIST AI Safety Institute Consortium
The U.S. Department of Commerce’s National Institute of Standards and Technology (NIST) is establishing the U.S. Artificial Intelligence Safety Institute Consortium (AISIC) to support the development and deployment of safe and trustworthy AI. Alongside MongoDB from the technology sector, the Consortium includes Amazon.com, AMD, Anthropic, Apple, Cohere, GitHub, Google, Hugging Face, Inflection AI, Intel, Meta, Microsoft, Nvidia, OpenAI, and Salesforce. In total, the Consortium brings together over 200 AI creators and users, academics, government and industry researchers, and civil society organizations. Together the members are focused on the R&D necessary to enable safe, trustworthy AI systems and underpin future standards and policies. You can see the complete list of current Consortium members on the NIST website . The Consortium will collaborate to develop science-based and empirically backed guidelines and standards for AI measurement and policy, laying the foundation for AI safety across the world. This will help prepare the U.S. to address the capabilities of the next generation of AI models or systems, from frontier models to new applications and approaches, with appropriate risk management strategies. Secretary of U.S. Department of Commerce Gina Raimondo said, “The U.S. government has a significant role to play in setting the standards and developing the tools we need to mitigate the risks and harness the immense potential of artificial intelligence. President Biden directed us to pull every lever to accomplish two key goals: set safety standards and protect our innovation ecosystem. That’s precisely what the U.S. AI Safety Institute Consortium is set up to help us do. Through President Biden’s landmark Executive Order, we will ensure America is at the front of the pack—and by working with this group of leaders from industry, civil society, and academia, together we can confront these challenges to develop the measurements and standards we need to maintain America’s competitive edge and develop AI responsibly.” MongoDB’s contributions to the Consortium Capitalizing on the experience gained working with startups, enterprises, and governments building and deploying AI-powered applications , MongoDB will contribute its expertise and resources across multiple fields including: Multi-cloud, globally distributed databases along with vector search and retrieval technology such as MongoDB Atlas Vector Search that power AI apps at scale. Developer experience engineering gained from building applications that integrate with the ecosystem of AI models and frameworks across all of the most popular programming languages. Data governance and cybersecurity technologies such as its groundbreaking to Queryable Encryption protect data and preserve privacy. “We believe that technology driven by software and data makes the world a better place, and we see our customers building modern applications achieving that every day,” said Lena Smart, Chief Information Security Officer at MongoDB . “New technology like generative AI can have an immense benefit to society, but we must ensure AI systems are built and deployed using standards that help ensure they operate safely and without harm across populations. By supporting the U.S. Artificial Intelligence Safety Institute Consortium as a founding member, MongoDB’s goal is to use scientific rigor, our industry expertise, and a human-centered approach to guide organizations on safely testing and deploying trustworthy AI systems without stifling innovation.” In addition to involvement in the AISIC, the MongoDB Atlas for Government program enables U.S. government departments to accelerate their time-to-mission with a database designed for developer productivity and broad workload support. MongoDB Atlas provides government-grade security running in a FedRAMP Moderate Authorized, dedicated environment. NIST’s role in setting technology standards As a part of the U.S. Department of Commerce, NIST plays a pivotal role in developing technology, metrics, and standards aimed at enhancing economic security and improving the quality of life for U.S. citizens. Through its rigorous research and development activities, NIST provides critical guidance and support for industries and science, ensuring the reliability and accuracy of measurements and standards essential for innovation and competitiveness in the global marketplace. Note that NIST does not evaluate commercial products under this Consortium and does not endorse any product or service used. Additional information on this Consortium can be found at: https://www.federalregister.gov/documents/2023/11/02/2023-24216/artificial-intelligence-safety-institute-consortium
DocsGPT: Migrating One of the Industry’s Most Popular Open Source AI Assistants to Atlas Vector Search
Since its founding in 2019, Arc53 has focused on building predictive AI/ML solutions for its clients, with use cases ranging from recommendation engines to fraud detection. But it was with OpenAI’s launch of ChatGPT in November 2022 that the company saw AI rapidly take a new direction. As Arc53 co-founder Alex Tushynski explains, “It was no surprise to see generative AI suddenly capture market attention. Suddenly developers and data teams were being challenged to bring their companies’ own proprietary data to gen AI models, in what we now call retrieval-augmented generation (RAG) . But this involved them building new skills and disciplines. It wasn’t easy as they had to stitch together all of their different databases, data lakes, file systems, and search engines, and then figure out how to feed data from those systems into their shiny new vector stores. Then they had to orchestrate all of these components to build a complete solution. We identified an opportunity to abstract this complexity away from them. So DocsGPT was born.” DocsGPT is an open-source documentation assistant that makes it easy for developers to build conversational user experiences with natural language processing (NLP) directly on top of their data. That can be a chatbot on a company website for customer support or as an interface into internal data repositories to help boost employee productivity. Developers simply connect their data sources to DocsGPT to experiment with different embedding and large language models to optimize for their specific use case. LLM options currently include ChatGPT 3.5 and 4, along with DocsGPT-7B, based on Mistral. In addition to the choice of models, developers can choose where they deploy DocsGPT. They can download the open source code to run in their own environment or consume DocsGPT as a managed service from Arc53. Figure 1: DocsGPT tech stack The freedom developers enjoy with DocsGPT is reflected in its levels of adoption. Since its release last year, the project has accumulated close to 14,000 GitHub stars and built a vibrant community with over 100 independent contributors. Tushynski says, “DocsGPT counts the UK government’s Department of Work and Pensions, pharmaceutical industry solution provider NoDeviation, and nearly 20,000 other users.” Tushynski and team selected MongoDB Atlas as the database for the DocsGPT managed service. “We’ve used MongoDB in many of our prior predictive AI projects. Its flexibility to store data of any structure, scale to huge data sets, and ease of use for both developers and data scientists means we can deliver richer AI-driven solutions faster. Using it to underpin DocsGPT was an obvious choice. As developers connect their documentation to DocsGPT, MongoDB stores all of the metadata, along with chat history and user account information.” Migrating from Elasticsearch to MongoDB Atlas Vector Search With the release of Atlas Vector Search , the DocsGPT team is now migrating its vector database from Elasticsearch into MongoDB Atlas. Tushynski says, “MongoDB is a proven OLTP database handling high read and write throughput with transactional guarantees. Bringing these capabilities to vector search and real-time gen AI apps is massively valuable. Atlas is able to handle highly dynamic workloads with rapidly changing embeddings in ways Elasticsearch cannot. The latency Elasticsearch exhibits as it merges updates into existing indexes means the app is often retrieving stale data, impacting the quality and reliability of model outputs.” Tushynski goes on to say, “We’ve experimented with a number of standalone vector databases. There are some good technologies there, but again, they don’t meet our needs when working with highly dynamic genAI apps. We often see users wanting to change embedding models as their apps evolve — a process that means re-encoding the data and updating the vector search index. For example, we’ve migrated our own default embedding models from OpenAI to multiple open-source models hosted on Hugging Face and now to BGE. MongoDB’s OLTP foundations make this a fast, simple, and hassle-free process.” The unification and synchronization of source 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. Alex Tushynski, co-founder, Arc53 Tushynski discusses the importance of embedding models in his blog post, Amplify DocsGPT with optimal embeddings . The post includes an example of how one customer was able to improve measured user experience by 50% simply by updating their embedding model. Figure 2: Demonstrating the impact of vector embedding choices “One of the standout features of MongoDB Atlas in this context is its adeptness in handling multiple embeddings. The ability to link various embeddings directly with one or more LLMs without the necessity for separate collections or tables is a powerful feature," Tushynski says. "This approach not only streamlines the data architecture but also eliminates the need for data duplication, a common challenge in traditional database setups. By facilitating the storage and management of multiple embeddings, it allows for a more seamless and flexible interaction between different LLMs and their respective embeddings.” Being part of AI Innovators program , the DocsGPT engineering team gets free Atlas credits as well as access to technical expertise to help support their migration. The AI Innovators program is open to any startup that is building AI with MongoDB. Check out our AI resource page to learn more about building AI-powered apps with MongoDB.
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 email@example.com . Check out our AI resource page to learn more about building AI-powered apps with MongoDB.
Building AI With MongoDB: How Gradient Accelerator Blocks Take You From Zero To AI in Seconds
Founded by the former leaders of AI teams at Google, Netflix, and Splunk, Gradient enables businesses to create high-performing, cost-effective custom AI applications. Gradient provides a platform for businesses to build, customize, and deploy bespoke AI solutions — starting with the fastest way to develop AI through the use of its Accelerator Blocks. Gradient’s Accelerator Blocks are comprehensive, fully managed building blocks designed for AI use cases — reducing developer workload and helping businesses achieve their goals in a fraction of the time. Each block can be used as is (e.g. entity extraction, document summarization, etc.) or combined to create more robust and intricate solutions (e.g. investment co-pilots, customer chatbots, etc.) that are low-code, use best-of-breed technologies, and provide state-of-the-art performance. Gradient’s newest Accelerator Block focuses on enhancing the performance and accuracy of a model through retrieval augmented generation (RAG). The Accelerator Block uses Gradient’s state-of-the-art LLMs and embeddings, MongoDB Atlas Vector Search for storing, indexing, and retrieving high-dimensional vector data, and LlamaIndex for data integration. Together, Atlas Vector Search and LlamaIndex feed foundation models with up-to-date, proprietary enterprise data in real-time. Gradient designed the Accelerator Block for RAG to improve development velocity up to 10x by removing the need for infrastructure, setup, or in-depth knowledge around retrieval architectures. It also incorporates best practices in document chunking, re-rankers, and advanced retrieval strategies. As Tiffany Peng, VP of Engineering from Gradient explains, “Users who are looking to build custom AI applications can leverage Gradient’s Accelerator Block for RAG to set up RAG in seconds. Users just have to upload their data into our UI and Gradient will take care of the rest. That way users can leverage all of the benefits of RAG, without having to write any code or worry about the setup.” Peng goes on to say: “With MongoDB, developers can store data of any structure and then expose that data to OLTP, text search, and vector search processing using a single query API and driver. With this unification, developers have all of the core data services they need to build AI-powered apps that rely on working with live, operational data. For example, querying across keyword and vector search applications can filter on metadata and fuse result sets to quickly identify and return the exact context the model needs to generate grounded, accurate outputs. It is really hard to do this with other systems. That is because developers have to deal with the complexity of bolting on a standalone vector database to a separate OLTP database and search engine, and then keep all those separate systems in sync.” Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Providing further customization and an industry edge With Gradient’s platform, businesses can further build, customize, and deploy AI as they see fit — in addition to the benefits that stem from the use of Gradient’s Accelerator Blocks. Gradient partners with key vendors and communities in the AI ecosystem to provide developers and businesses with best-of-breed technologies. This includes Llama-2 and Mistral LLMs — with additional options coming — alongside the BGE embedding model and the Langchain, LlamaIndex, and Haystack frameworks. MongoDB Atlas is included as a core part of the stack available in the Gradient platform. While any business can leverage its platform, Gradient’s domain-specific models in financial services and healthcare provide a unique advantage for businesses within those industries. For example in financial services, typical use cases for Gradient’s models include risk management, KYC, anti-money laundering (AML), and robo-advisers, along with forecasting and analysis. In healthcare, Gradient use cases include pre-screening and post-visit summaries, clinical research, billing, and benefits, along with claims auditing. What is common to both finance and healthcare is that these two industries are subject to comprehensive regulations where user privacy is key. By building on Gradient and its state-of-the-art open-source large language models (LLMs) and embedding models, enterprises maintain full ownership of their data and AI systems. Developers can train, tune, and deploy their models in private environments running on Gradient’s AI cloud, which the company claims delivers up to 7x higher performance than base foundation models at 10x lower cost than the hyperscale cloud providers. To keep up with the latest announcements from Gradient, follow the company on Twitter/X or LinkedIn . You can learn more about MongoDB Atlas Vector Search from our 10-minute learning byte .
Building AI with MongoDB: How Devnagri Brings the Internet to 1.3 Billion People with Machine Translations
It was while on a trip to Japan that Himanshu Sharma — later to become CEO of Devnagri — made an observation that drew parallels with his native India. Despite the majority of Japan’s population not speaking English, they were still well served by an internet that was largely based on the English language. Key to doing this was translation, and specifically the early days of automated machine translation. And so the idea to found Devnagri , India’s first AI-powered translation platform, was born. “In India, 90% of the population are not fluent in English. That is close to 1.3 billion people . We wanted to bridge this gap to make it easy for non-English speakers to access the internet in their native languages. There are more than 22 Indian languages in use, but they represent just 0.1% of data on the internet,” says Sharma. “We want to give people the same access to knowledge and education in their native languages so that they can be part of the digital ecosystem. We wanted to help businesses and the government reach real people who were not online because of the language barrier.” Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Figure 1: Devnagri’s real time translation engine helps over 100 Indian brands connect with their customers over digital channels for the first time Building India’s first machine translation platform Sharma and his team at Devnagri have developed an AI-powered translation platform that can accept multiple file formats from different industry domains. Conceptually it is similar to Google Translate. Rather than a general consumer tool, it focuses on the four key industries that together make the largest impact on the everyday lives of Indian citizens: e-learning, banking, e-commerce, and media publishing. Devnagri provides API access to its platform and a plug-and-play solution for dynamically translating applications and websites. As Sharma explains, “Our platform is built on our own custom transformer model based on the MarianNMT neural machine translation framework. We train on corpuses of content in documents, chunking them into sentences and storing them in MongoDB Atlas . We use in-context learning for training, which is further augmented with reinforcement learning from human feedback (RLHF) to further tune for precise accuracy.” Sharma goes on to say, “We run on Google Vertex AI, which handles our MLops pipeline across both model training as well as inferencing. We use Google Tensor Processing Units (TPUs) to host our models so we can translate content — such as web pages, PDFs, documentation, web and mobile apps, images, and more — for users on the fly in real-time.” While the custom transformer-based models have served the company well, recent advancements in off-the-shelf models is leading Devnagri’s engineers to switch. They are evaluating a move to OpenAI GPT-4 and the Llama-2-7b foundation models, fine-tuned with the past four years of machine translation data captured by Devnagri. Why MongoDB? Flexibility and performance MongoDB is used as the database platform for Devnagri’s machine translation models. For each sentence chunk, MongoDB stores the source English language version, the machine translation, and if applicable, the human-verified sentence translation. As Sharma explains, “We use the sentences stored in MongoDB to train our models and support real-time inference. The flexibility of its document data model made MongoDB an ideal fit to store the diversity of structured and unstructured content and features our ML models translate.” We also exploit MongoDB’s scalable distributed architecture. This allows our models to parallelize read and write requests across multiple nodes in the cloud, dramatically improving training and inference throughput. We get faster time to market with higher quality results by using MongoDB. Himanshu Sharma, Devnagri co-founder and CEO What's next? Today Devnagri serves over 100 brands and several government agencies in India. The company has also joined MongoDB’s AI Innovators Program . The program provides its data science team with access to free Atlas credits to support further machine translation experiments and development, along with access to technical guidance and best practices. If you are building AI-powered apps, the best way to get started is to sign up for an account on MongoDB Atlas. From there, you can create a free MongoDB instance with the Atlas database and Atlas Vector Search , load your own data or our sample data sets, and explore what’s possible within the platform.
Building AI With MongoDB: Boosting Productivity and Efficiency with Assistants and Agents
Among generative AI’s (genAI) many predicted benefits, its potential in unlocking new levels of employee productivity and operational efficiency are frequently cited. Over the course of our “Building AI with MongoDB” blog post series, we’ve featured multiple examples of genAI being used to automate repetitive tasks with virtual assistants and intelligent agents. From conversational AI with natural language processing (NLP) to research and analysis, examples from previous posts include: Ada : automating customer service for the likes of Meta, Shopify, and Verizon Eni : supporting its geologists’ research on the company’s path to net zero ExTrac : sifting through online chatter to track emerging threats to public safety Inovaare : transforming complex healthcare compliance processes Zelta : analyzing real-time customer feedback to prioritize product development In today’s roundup of AI builders, I’ll cover three more organizations that are applying genAI-powered assistants and agents. You’ll see how they are freeing staff to focus on more strategic and productive tasks while simplifying previously complex and expensive business processes. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. WINN.AI: The virtual assistant tackling sales admin overhead Salespeople typically spend over 25% of their time on administrative busywork — costing organizations time, money, and opportunity. WINN.AI is working to change that so that sales teams can better invest their working hours in serving customers. At the heart of WINN.AI is an AI-powered real-time sales assistant that joins virtual meetings to detect, interpret, and respond to customer questions. By comprehending the context of a conversation, it can immediately surface relevant information to the salesperson, for example retrieving appropriate customer references or competitive information. It can provide prompts from a sales playbook, and also make sure meetings stay on track and on time. At the end of the meeting, WINN.AI extracts and summarizes relevant information from the conversation and updates the CRM system with follow-on actions. Discussing its AI technology stack, Orr Mendelson, Ph.D., the head of R&D at WINN.AI says: “We started out building and training our own custom NLP algorithms and later switched to GPT 3.5 and 4 for entity extraction and summarization. We orchestrate all of the models with massive automation, reporting, and monitoring mechanisms. This is developed by our engineering teams and assures high-quality AI products across our services and users. We have a dedicated team of AI engineers and prompt engineers that develop and monitor each prompt and response so we are continuously tuning and optimizing app capabilities.” In the ever-changing AI tech market, MongoDB is our stable anchor … my developers are free to create with AI while being able to sleep at night Orr Mendelson, head of R&D at WINN.AI Describing its use of MongoDB Atlas, Mendelson says: “MongoDB stores everything in the WINN.AI platform. The primary driver for selecting MongoDB was its flexibility in being able to store, index, and query data of any shape or structure. The database fluidly adapts to our application’s data objects, which gives us a more agile approach than traditional relational databases.” Mendelson adds, “MongoDB is familiar to our developers so we don’t need any DBA or external experts to maintain and run it safely. We can invest those savings back into building great AI-powered products. MongoDB Atlas provides the managed services we need to run, scale, secure, and back up our data." WINN.AI is part of the MongoDB AI Innovators program , benefiting from access to free Atlas credits and technical expertise. Take a look at the full interview with Mendleson to learn more about WINN.AI and its AI developments. One AI: Providing AI-as-a-Service to deliver solutions in days rather than months The mission at One AI is to bring AI to everyday life by converting natural language into structured, actionable data. It provides seamless integration into products and services, and uses generative AI to redefine human-machine interactions. One AI curates and hones leading AI capabilities from across the ecosystem, and packages them as easy-to-use APIs. It’s a simple but highly effective concept that empowers businesses to deploy tailored AI solutions in days rather than weeks or months. “One AI was founded with the goal of democratizing and delivering AI as a service for companies,” explains Amit Ben, CEO and founder at One AI. “Our customers are product and services companies that plug One AI into the heart and core value of their products,” says Ben. “They are spread across use cases in multiple domains, from analyzing financial documents to AI-automated video editing.” Figure 1: The One AI APIs let developers analyze, process, and transform language input in their code. No training data or NLP/ML knowledge are required. One AI works with over 20 different AI/ML models. Having a flexible data infrastructure was key to help harness the latest innovations in data science, as Ben explains: “The MongoDB document model really allows us to spread our wings and freely explore new capabilities for the AI, such as new predictions, new insights, and new output data points.” Ben adds, “With any other platform, we would have to constantly go back to the underlying infrastructure and maintain it. Now, we can add, expand, and explore new capabilities on a continuous basis.” The company also benefits from the regular new releases from MongoDB, such as Atlas Vector Search , which Ben sees as a highly valuable addition to the platform’s toolkit. Ben explains: “The ability to have that vectorized language representation in the same database as other representations, which you can then access via a single query interface, solves a core problem for us as an API company." To learn more, watch the interview with Amit Ben. 4149.AI: Maximizing team productivity with a hypertasking AI-powered teammate 4149.AI helps teams get more work done by providing them with their very own AI-powered teammate. During the company’s private beta program, the autonomous AI agent has been used by close to 1,000 teams to help them track goals and priorities. It does this by building an understanding of team dynamics and unblocking key tasks. It participates in slack threads, joins meetings, transcribes calls, generates summaries from reports and whitepapers, responds to emails, updates issue trackers, and more. 4149.AI uses a custom-built AI-agent framework leveraging a combination of embedding models and LLMs from OpenAI and AI21 Labs, with text generation and entity extraction managed by Langchain. The models process project documentation and team interactions, persisting summaries and associated vector embeddings into Atlas Vector Search . There is even a no-code way for people to customize and expand the functionality of their AI teammate. Over time, the accumulated context generated for each team means more and more tasks can be offloaded to their AI-powered co-worker. The engineers at 4149.AI evaluated multiple vector stores before deciding on Atlas Vector Search. The ability to store summaries and chat history alongside vector embeddings in the same database accelerates developer velocity and the release of new features. It also simplifies the technology stack by eliminating unnecessary data movement. Hybrid search is another major benefit provided by the Atlas platform. The ability to pre-filter data with keyword-based Atlas Search before semantically searching vectors helps retrieve relevant information to users faster. Looking forward 4149.AI has an aggressive roadmap for its products as it starts to more fully exploit the chain-of-thought and multimodal capabilities provided by the most advanced language models. This will enable the AI co-worker to handle more creative tasks requiring deep reasoning such as conducting market research, monitoring the competitive landscape, and helping identify new candidates for job vacancies. The goal for these AI teammates is for them to eventually be able to take the initiative in what to do next rather than rely on someone to manually assign them a task. Being part of MongoDB’s AI Innovators program puts 4149.AI on a path to success with access to technical support and free Atlas credits, helping them quickly experiment using the native AI capabilities available in the MongoDB developer data platform. Getting started These are just a few examples of the capabilities of genAI-powered assistants and agents. Check out our library of AI case studies to see the range of applications developers are building with MongoDB. Our 10-minute learning byte is a great way to learn what you can do with Atlas Vector Search, how it’s different from other forms of search, and what you’ll need to get started using it.
Building AI With MongoDB: Optimizing the Product Lifecycle with Real-Time Customer Data
Over the course of our Building AI with MongoDB blog post series, we’ve seen many organizations using AI to shape product development and support. Examples we’ve profiled so far include: Ventecon’s co-pilot helping product managers generate and refine specifications for new products Cognigy’s conversational AI solutions empowering businesses to provide instant and personalized customer service in any language and for any channel Kovai’s AI assistant helping users quickly discover information from product documentation and knowledge bases In this roundup of the latest AI builders, I’ll focus on three more companies innovating across the product lifecycle. We’ll start with Zelta, which helps teams prioritize product roadmaps using live customer insights and sentiment. Then I'll move on to Crewmate, which connects products to engaged communities of users. We’ll wrap with Ada, which helps product companies like Meta and Verizon better support their customers through AI-driven automation. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. Zelta.AI : Prioritizing product roadmaps with data-driven customer analytics Today's digital economy means customer feedback streams into the enterprise from a multitude of physical and digital touchpoints. For product managers, it can seem an impossible task to synthesize this feedback into themes and priorities that underpin a coherent development plan everyone in the business commits to. This is the problem Zelta.ai was founded to address. Zelta uses generative AI to communicate insights on top of customer pain points found in companies’ most valuable asset: qualitative sources of customer feedback such as call transcripts and tickets, pulling directly from platforms like Gong, Zoom, Fireflies, Zendesk, Jira, Intercom, among others. Zelta leverages LLMs to process unstructured data and returns actionable insights for product teams The company’s engineering team uses a combination of fine-tuned OpenAI GPT-4, Cohere, and Anthropic models to extract, classify, and encode source data into trends and sentiment around specific topics and features. MongoDB Atlas is used as the data storage layer for source metadata and model outputs. “The flexibility MongoDB provides us has been unbelievable,” says Mick Cunningham, CTO and Co-Founder at Zelta AI. “My development team can constantly experiment with new features, just adding fields and evolving the data model as needed without any of the expensive schema migration pains imposed by relational databases.” Cunningham goes on to say, “We also make heavy use of the MongoDB aggregation pipeline for application-driven intelligence . Without having to ETL data out of MongoDB, we can analyze data in place to provide customers with real-time dashboards and reporting of trends in product feedback. This helps them make product decisions faster, making our service more valuable to them.” Looking forward, Zelta plans on creating its own custom models, and MongoDB will prove invaluable as a source of labeled data for supervised model training. Zelta is a member of the MongoDB AI Innovators program , taking advantage of free Atlas credits, access to technical support, and exposure to the wider MongoDB community. Crewmate : Helping brands connect with their communities In the digital economy, brands can spend millions of dollars growing online communities populated with highly engaged users of their products and services. However many of the tools used for building communities are third-party solutions that abstract away a brand’s visibility into user engagement. This is an issue Crewmate is working to address. Crewmate is a no-code builder for embedded AI-powered communities. The company’s builder provides customizable communities for brands to deploy directly onto their websites. Crewmate is already used today across companies in consumer packaged goods (CPG), B2B SaaS, gaming, Web3, and more. Crewmate starts by scraping a brand's website, along with open job postings and customer data from CRM systems. Scraped data is stored in its MongoDB Atlas database running on Google Cloud. An Atlas Trigger then calls OpenAI’s ada-002 embedding model, storing and indexing the vectorized encodings into Atlas Vector Search . An event-driven pipeline keeps the embeddings fresh by firing the Atlas Trigger as soon as new website data is inserted into the MongoDB database. Using context-aware semantic search powered by Atlas Vector Search, users hitting and browsing the community pages on a brand’s website are automatically served relevant content. This includes posts from social media feeds, forum discussions, job postings, special offers, and more. “I’ve used MongoDB in past projects and knew that its flexible document schema would allow me to store data of any structure. This is particularly important when ingesting many different types of data from my clients’ websites,” says Raj Thaker, CTO and Co-Founder of Crewmate. “The introduction of Atlas Vector Search and the Building Generative AI Applications tutorial gave me a fast, ready-made blueprint that brings together a database for source data, vector search for AI-powered semantic search, and reactive, real-time data pipelines to keep everything updated, all in a single platform with a single copy of the data and a unified developer API. This keeps my engineering team productive and my tech stack streamlined. Atlas also provides integrations with the fast-evolving AI ecosystem. So while today I’m using OpenAI models, I have the flexibility to easily integrate with other models, such as Llama, in the future.” Thaker goes on to say, “One of Crewmate’s major value creations is the insights brands can extract. Using the powerful and expressive MongoDB Query API I can process, aggregate, and analyze user engagement data so that brands can track community outreach efforts and conversions. They can generate this intelligence directly from their app data stored in MongoDB, avoiding the need to ETL it out into a separate data warehouse or data lake." Like Zelta, Crewmate is also part of MongoDB’s AI Innovators program . Ada : Revolutionizing customer service with AI-powered automations built on MongoDB Atlas Founded in 2016, Ada has become a leader in automating complex service interactions across any channel and modality. The company has raised close to $200 million, has 300 employees, and counts Meta, Verizon, and AT&T among its 300 customers. Mike Gozzo, Ada’s Chief Product and Technology Officer was interviewed at a recent MongoDB developer conference where he discussed the evolution of AI for customer service and the role MongoDB plays in Ada’s AI stack. Gozzo makes the point that while bots for customer service aren’t new, the huge advancements in transformer models and LLMs coupled with reinforcement learning from human feedback (RLHF) have made these assistants far more capable. Rather than just search for information, they can use advanced reasoning to solve customer problems. Asked why Ada selected MongoDB Atlas to underpin all its products, Gozzo says, “Having the flexibility and ability to just pivot on a dime was really important. We saw that as we advanced the company and brought in new channels and new modalities, having one data store that can be easily extended without crazy migrations and that would really support our needs was absolutely clear from MongoDB. We’ve always stayed the path with Atlas because the performance is there, the support from the team is great, and we believe in having less dependency on one central cloud vendor that MongoDB allows.” Gozzo goes on to say, “Using MongoDB means we’re not limited in how we source data if we want to build something new. We can query unstructured data and use it to train other models. We use generative AI effortlessly throughout our product stack to automate queries and provide support that goes beyond just answering multi-step queries. With MongoDB, we’re able to ship new products in just a few months.” Going forward, Ada is starting to use MongoDB Change Streams to build a distributed event processing system that powers bots and analytics. It is also exploring Queryable Encryption , which helps advance AI training while keeping conversations private. As discussed in his Voice of the Customer interview with Amazon Web Services (AWS), Gozzo talks about how velocity drives all product development at Ada. Velocity is measured both in terms of how quickly the company can ship products and features, and how quickly they can learn and iterate. Running MongoDB Atlas on AWS alongside serverless Lambda functions and LLMs through Amazon Bedrock means Ada delivers its applications scalably with repeatability and high performance. Getting started Check out our library of AI case studies to see the range of applications developers are building with MongoDB. Our 3-minute explainer video on Atlas Vector Search is a great way to assess what’s possible as you start on your journey to AI-powered apps.
Atlas Vector Search obtient le NPS le plus élevé pour les développeurs dans le cadre de l'enquête Retool State of AI 2023
Retool vient de publier son tout premier rapport sur l'IA et il vaut le détour . Inspirée de son célèbre rapport State of Internal Tools, l'enquête sur l'état de l'IA a examiné plus de 1 500 spécialistes de la technologie issus de divers secteurs d'activité : ingénieurs logiciels, dirigeants, chefs de produit, concepteurs, etc. Son objectif est de comprendre comment ils exploitent l'intelligence artificielle (IA). Dans le cadre de cette enquête, Retool s'est penché sur les outils les plus populaires, y compris les bases de données vectorielles les plus utilisées avec l'IA. Elle a révélé que MongoDB Atlas Vector Search a obtenu le Net Promoter Score (NPS) le plus élevé et est la deuxième base de données vectorielle la plus utilisée, cinq mois seulement après son lancement. Elle devance ainsi des solutions concurrentes qui existent depuis des années. Dans cet article, nous examinerons l'essor phénoménal des bases de données vectorielles et comment les développeurs utilisent des solutions telles qu'Atlas Vector Search pour créer des applications alimentées par l'IA. Nous aborderons également d'autres points clés du rapport Retool. Consultez notre page de ressources sur l'IA pour en savoir plus sur la création d'applications alimentées par l'IA avec MongoDB. Adoption des bases de données vectorielles : en plein essor (enfin presque…) De la curiosité mathématique à la superpuissance à l'origine de l’IA générative et les LLM, les vector embeddings et les bases de données qui les gèrent ont parcouru un long chemin en très peu de temps. Découvrez les tendances des modèles de base de données de DB-Engines au cours des 12 derniers mois et vous verrez que les bases de données vectorielles dépassent de loin toutes les autres en termes de popularité. Il suffit de regarder la trajectoire «de la ligne rose « vers le haut et vers la droite » dans le graphique ci-dessous. Capture d'écran avec l'aimable autorisation de DB-Engines, 8 novembre 2023 Mais pourquoi les bases de données vectorielles sont-elles devenues si populaires ? Ils constituent un élément clé d'un nouveau modèle architectural appelé « génération augmentée de récupération » ( RAG ). Il s'agit d'un puissent mélange qui combine les capacités de raisonnement des LLM préformés et polyvalents et les alimente en données spécifiques à l'entreprise en temps réel. Il en résulte des applications alimentées par l'IA qui apportent des solutions uniques à l'entreprise, qu'il s'agisse de créer de nouveaux produits, de repenser l'expérience client ou d'optimiser la productivité et l'efficacité. Les vector embeddings sont essentielles pour exploiter tout le potentiel de la RAG. Leurs modèles encodent les données d'entreprise, qu'il s'agisse de texte, de code, de vidéo, d'images, de flux audio ou de tableaux, comme les vecteurs. Ces derniers sont ensuite stockés, indexés et interrogés dans une base de données vectorielle ou un moteur de recherche vectorielle, fournissant les données d'entrée pertinentes en tant que contexte au LLM sélectionné. Il en résulte des applications d'IA fondées sur des données d'entreprise et des connaissances pertinentes pour l'activité, précises, fiables et à jour. Comme le montre l'enquête Retool, le paysage des bases de données vectorielles reste encore à exploiter. À l'heure actuelle, moins de 20 % des personnes interrogées les utilisent, mais avec la tendance croissante à la personnalisation des modèles et l’infrastructure d’IA, elles devraient être de plus en plus plébiscitées. Pourquoi les développeurs adoptent-ils Atlas Vector Search ? L'enquête de Retool présente d'excellentes bases de données vectorielles qui ont ouvert la voie au cours des deux dernières années, en particulier dans les applications nécessitant une recherche sémantique contextuelle. Pensez aux catalogues de produits ou à la découverte de contenu. Cependant, le défi auquel les développeurs sont confrontés lorsqu'ils utilisent ces bases de données vectorielles est qu'ils doivent les intégrer avec d'autres bases de données dans la pile technologique de leur application. Chaque couche de base de données supplémentaire de la pile technologique des applications renforce la complexité, la latence et les frais généraux. Cela signifie qu'ils doivent se procurer une autre base de données, l'assimiler, l'intégrer (pour le développement, les tests et la production), la sécuriser et la certifier, la faire évoluer, la surveiller et la sauvegarder, tout en synchronisant les données entre ces multiples systèmes. MongoDB adopte une approche différente qui contourne ces problèmes : Les développeurs stockent et recherchent des vector embeddings natives dans le même système que celui qu'ils utilisent comme base de données opérationnelle. Grâce à l'architecture distribuée de MongoDB, ils peuvent isoler ces différentes charges de travail tout en synchronisant les données. Search Nodes fournissent un calcul dédié et une isolation de la charge de travail, un aspect essentiel pour les charges de travail de recherche vectorielle à forte intensité de mémoire. Ce processus permet ainsi d'améliorer les performances et la disponibilité. Contrairement aux autres base de données, grâce au schéma de documents flexible et dynamique de MongoDB, les développeurs peuvent modéliser et faire évoluer les relations entre les vecteurs, les métadonnées et les données d'application. Ils peuvent traiter et filtrer les données vectorielles et opérationnelles en fonction des besoins de l'application avec une API de requête expressive et des pilotes qui prennent en charge tous les langages de programmation les plus courants. L'utilisation de la plateforme de données de développement MongoDB Atlas entièrement gérée permet aux développeurs d'obtenir le répartir, la sécurité et la performance que les utilisateurs de leurs applications attendent. Que signifie cette approche unifiée pour les développeurs ? Les cycles de développement plus rapides et les applications plus performantes offrent une latence plus faible avec des données plus pertinentes, le tout associé à des frais généraux et des coûts opérationnels réduits. Ces résultats se traduisent par le NPS de MongoDB, le meilleur de sa catégorie. Atlas Vector Search est robuste, rentable et incroyablement rapide ! Saravana Kumar, CEO, Kovai parle du développement de l'assistant d'intelligence artificielle de son entreprise Consultez notre série d'articles Concevoir l'IA avec MongoDB (rendez-vous dans la section « Démarrer » pour lire les articles précédemment publiés). Ici, Atlas Vector Search est utilisé pour les applications alimentées par l'IA conversationnelle avec des chatbots et des voicebots, des co-pilotes, des informations sur les menaces et la cybersécurité, la gestion des contrats, les foires aux questions, la conformité et les assistants de traitement, la découverte et la monétisation des contenus, etc. MongoDB stockait déjà des métadonnées relatives aux artefacts de notre système. Avec l'introduction d'Atlas Vector Search, nous disposons désormais d'une base de données complète de métadonnées vectorielles qui a été testée pendant plus de dix ans et qui répond à nos besoins considérables en termes de récupération. Il n'est pas nécessaire de déployer une nouvelle base de données que nous devrions gérer et apprendre. Nos vecteurs et les métadonnées de nos artefacts peuvent être stockés les uns à côté des autres. Pierce Lamb, ingénieur logiciel senior de l'équipe Data and Machine Learning chez VISO TRUST Que nous apprend le rapport Retool concernant l'IA ? Au-delà de la découverte des bases de données vectorielles les plus populaires, l'enquête aborde différents aspects du secteur. Elle commence par explorer les perceptions de l'IA par les personnes interrogées (sans surprise, les dirigeants sont plus optimistes que les collaborateurs). Il explore ensuite les priorités en matière d'investissement, l'impact de l'IA sur les perspectives d'emploi futures et la manière dont elle affectera probablement les développeurs et les compétences dont ils auront besoin à l'avenir. L'enquête examine ensuite le niveau d'adoption et de maturité de l'IA. Plus de 75 % des répondants déclarent que leur entreprise commence à exploiter l'IA. Environ la moitié d'entre eux déclarent que ces projets n'en sont qu'à leurs prémices et ciblent principalement une utilisation interne. Elle se penche ensuite sur la nature de ces applications sur leur utilité au sein de l'entreprise. Elle constate que presque tout le monde utilise l'IA au travail, que ce soit autorisé ou non, puis identifie les principaux problèmes. Sans surprise, la précision des modèles, la sécurité et les hallucinations figurent en tête de liste. L'enquête se termine par l'examen des principaux modèles utilisés. Là encore, il n'est pas surprenant de constater que les offres d'Open AI sont en tête, mais cela indique également une intention croissante d'utiliser des modèles open source ainsi que des outils et infrastructures d'IA pour la personnalisation à l'avenir. Pour en savoir plus sur cette enquête, lisez le rapport . Démarrer avec Atlas Vector Search Vous souhaitez découvrir notre offre Vector Search ? Rendez-vous sur notre page produit Atlas Vector Search . Vous y trouverez des liens vers des tutoriels, de la documentation et des intégrations clés de l'écosystème d'IA afin de vous commencer à créer vos propres applications alimentées par l'IA . Si vous souhaitez en savoir plus sur les possibilités de haut niveau de la recherche vectorielle, téléchargez notre livre blanc sur l'intégration de l'IA générative . Consultez notre présentation « Créer votre feuille de route IA pour 2024 » pour en savoir plus sur les différents cas d'utilisation de l'IA et comment les entreprises les prennent en charge !