Mat Keep

169 results

Building AI with MongoDB: Conversation Intelligence with Observe.AI

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.

April 29, 2024

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. Head over to our quick-start guide to get started with Atlas Vector Search today.

April 25, 2024

Building AI With MongoDB: How DevRev is Redefining CRM for Product-Led Growth

OneCRM from DevRev is purpose-built for Software-as-a-Service (SaaS) companies. It brings together previously separate customer relationship management (CRM) suites for product management, support, and software development. Built on a foundation of customizable large language models (LLMs), data engineering, analytics, and MongoDB Atlas , it connects end users, sellers, support, product owners, and developers. OneCRM converges multiple discrete business apps and teams onto a common platform. As the company states on its website “Our mission is to connect makers (Dev) to customers (Rev) . When every employee adopts a “product-thinking” mindset, customer-centricity transcends from a department to become a culture.” DevRev was founded in October 2020 and raised over $85 million in seed funding from investors such as Khosla Ventures and Mayfield. At the time, this made it the largest seed in the history of Silicon Valley. The company is led by its co-founder and CEO, Dheeraj Pandey, who was previously the co-founder and CEO of Nutanix, and by Manoj Agarwal, DevRev's co-founder and former SVP of Engineering at Nutanix. DevRev is headquartered in Palo Alto and has offices in seven global locations. Check out our AI resource page to learn more about building AI-powered apps with MongoDB. CRM + AI: Digging into the stack DevRev’s Support and Product CRM serve over 4,500 customers: Support CRM brings support staff, product managers, and developers onto an AI-native platform to automate Level 1 (L1), assist L2, and elevate L3 to become true collaborators. Product CRM brings product planning, software work management, and product 360 together so product teams can assimilate the voice of the customer in real-time. Figure 1: DevRev’s real-time dashboards empower product teams to detect at-risk customers, monitor product health, track development velocity, and more. AI is central to both the Support and Product CRMs. The company’s engineers build and run their own neural networks, fine-tuned with application data managed by MongoDB Atlas. This data is also encoded by open-source embedding models where it is used alongside OpenAI models for customer support chatbots and question-answering tasks orchestrated by autonomous agents. MongoDB partner LangChain is used to call the models, while also providing a layer of abstraction that frees DevRev engineers to effortlessly switch between different generative AI models as needed. Data flows across DevRev’s distributed microservices estate and into its AI models are powered by MongoDB change streams . Downstream services are notified in real-time of any data changes using a fully reactive, event-driven architecture. MongoDB Atlas: AI-powered CRM on an agile and trusted data platform MongoDB is the primary database backing OneCRM, managing users, customer and product data, tickets, and more. DevRev selected MongoDB Atlas from the very outset of the company. The flexibility of its data model, freedom to run anywhere, reliability and compliance, and operational efficiency of the Atlas managed service all impact how quickly DevRev can build and ship high-quality features to its customers. The flexibility of the document data model enables DevRev’s engineers to handle the massive variety of data structures their microservices need to work with. Documents are large, and each can have many custom fields. To efficiently store, index, and query this data, developers use MongoDB’s Attribute pattern and have the flexibility to add, modify, and remove fields at any time. The freedom to run MongoDB anywhere helps the engineering team develop, test, and release faster. Developers can experiment locally, then move to integration testing, and then production — all running in different environments — without changing a single line of code. This is core to DevRev’s velocity in handling over 4,000 pull requests per month: Developers can experiment and test with MongoDB on local instances — for example adding indexes or evaluating new query operators, enabling them to catch issues earlier in the development cycle. Once unit tests are complete, developers can move to temporary instances in Docker containers for end-to-end integration testing. When ready, teams can deploy to production in MongoDB Atlas. The multi-cloud architecture of Atlas provides flexibility and choice that proprietary offerings from the hyperscalers can’t match. While DevRev today runs on AWS, in the early days of the company, they evaluated multiple cloud vendors. Knowing that MongoDB Atlas could run anywhere gave them the confidence to make a choice on the platform, knowing they would not be locked into that choice in the future. With MongoDB Atlas, our development velocity is 3-4x higher than if we used alternative databases. We can get our innovations to market faster, providing our customers with even more modern and useful CRM solutions. Anshu Avinash, Founding Engineer, DevRev The HashiCorp Terraform MongoDB Atlas Provider automates infrastructure deployments by making it easy to provision, manage, and control Atlas configurations as code. “The automation provided by Atlas and Terraform means we’ve avoided having to hire a dedicated infrastructure engineer for our database layer,” says Anshu. “This is a savings we can redirect into adding developers to work on customer-facing features.” Figure 2: The reactive, event-driven microservices architecture underpinning DevRev’s AI-powered CRM platform Anshu goes on to say, “We have a microservices architecture where each microservice manages its own database and collections. By using MongoDB Atlas, we have little to no management overhead. We never even look at minor version upgrades, which Atlas does for us in the background with zero downtime. Even the major version upgrades do not require any downtime, which is pretty unique for database systems.” Discussing scalability, Anshu says, “As the business has grown, we have been able to scale Atlas, again without downtime. We can move between instance and cluster sizes as our workloads expand, and with auto-storage scaling, we don’t need to worry about disks getting full.” DevRev manages critical customer data, and so relies on MongoDB Atlas’ native encryption and backup for data protection and regulatory compliance. The ability to provide multi-region databases in Atlas means global customers get further control over data residency, latency, and high availability requirements. Anshu goes on to say, “We also have the flexibility to use MongoDB’s native sharding to scale-out the workloads of our largest customers with complete tenant isolation.” DevRev is redefining the CRM market through AI, with MongoDB Atlas playing a critical role as the company’s data foundation. You can learn more about how innovators across the world are using MongoDB by reviewing our Building AI case studies . 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. Head over to our quick-start guide to get started with Atlas Vector Search today.

March 27, 2024

Fireworks AI and MongoDB: The Fastest AI Apps with the Best Models, Powered By Your Data

We’re happy to announce that Fireworks AI and MongoDB are now partnering to make innovating with generative AI faster, more efficient, and more secure. Fireworks AI was founded in late 2022 by industry veterans from Meta’s PyTorch team, where they focused on performance optimization, improving the developer experience, and running AI apps at scale. This post is also available in: Deutsch , Français , Español , Português , Italiano , 한국어 , 简体中文 . It’s this expertise that Fireworks AI brings to its production AI platform, curating and optimizing the industry's leading open models. Benchmarking by the company shows gen AI models running on Fireworks AI deliver up to 4x faster inference speeds than alternative platforms, with up to 8x higher throughput and scale. Models are one part of the application stack. But for developers to unlock the power of gen AI, they also need to bring enterprise data to those models. That’s why Fireworks AI has partnered with MongoDB, addressing one of the toughest challenges to adopting AI. With MongoDB Atlas , developers can securely unify operational data, unstructured data, and vector embeddings to safely build consistent, correct, and differentiated AI applications and experiences. Jointly, Fireworks AI and MongoDB provide a solution for developers who want to leverage highly curated and optimized open-source models, and combine these with their organization’s own proprietary data — and to do it all with unparalleled speed and security. Lightning-fast models from Fireworks AI: Enabling speed, efficiency, and value Developers can choose from many different models to build their gen AI-powered apps. Navigating the AI landscape to identify the most suitable models for specific tasks — and tuning them to achieve the best levels of price and performance — is complex and creates friction in building and running gen AI apps. This is one of the key pain points that Fireworks AI alleviates. With its lightning-fast inference platform, Fireworks AI curates, optimizes, and deploys 40+ different AI models. These optimizations can simultaneously result in significant cost savings , reduced latency , and improved throughput. Their platform delivers this via: Off-the-shelf models, optimized models, and add-ons: Fireworks AI provides a collection of top-quality text, embedding, and image foundation models . Developers can leverage these models or fine-tune and deploy their own, pairing them with their own proprietary data using MongoDB Atlas. Fine-tuning capabilities : To further improve model accuracy and speed, Fireworks AI also offers a fine-tuning service using its CLI to ingest JSON-formatted objects from databases such as MongoDB Atlas. Simple interfaces and APIs for development and production: The Fireworks AI playground allows developers to interact with models right in a browser. It can also be accessed programmatically via a convenient REST API. This is OpenAI API-compatible and thus interoperates with the broader LLM ecosystem. Cookbook: A simple and easy-to-use cookbook provides a comprehensive set of ready-to-use recipes that can be adapted for various use cases, including fine-tuning, generation, and evaluation. Fireworks AI and MongoDB: Setting the standard for AI with curated, optimized, and fast models With Fireworks AI and MongoDB Atlas, apps run in isolated environments ensuring uptime and privacy, protected by sophisticated security controls that meet the toughest regulatory standards: As one of the top open-source model API providers, Fireworks AI serves 66 billion tokens per day (and growing). With Atlas, you run your apps on a proven platform that serves tens of thousands of customers, from high-growth startups to the largest enterprises and governments. Together, the Fireworks AI and MongoDB joint solution enables: Retrieval-augmented generation (RAG) or Q&A from a vast pool of documents: Ingest a large number of documents to produce summaries and structured data that can then power conversational AI. Classification through semantic/similarity search: Classify and analyze concepts and emotions from sales calls, video conferences, and more to provide better intelligence and strategies. Or, organize and classify a product catalog using product images and text. Images to structured data extraction: Extract meaning from images to produce structured data that can be processed and searched in a range of vision apps — from stock photos, to fashion, to object detection, to medical diagnostics. Alert intelligence: Process large amounts of data in real-time to automatically detect and alert on instances of fraud, cybersecurity threats, and more. Figure 1: The Fireworks tutorial showcases how to bring your own data to LLMs with retrieval-augmented generation (RAG) and MongoDB Atlas Getting started with Fireworks AI and MongoDB Atlas To help you get started, review the Optimizing RAG with MongoDB Atlas and Fireworks AI tutorial, which shows you how to build a movie recommendation app and involves: MongoDB Atlas Database that indexes movies using embeddings. (Vector Store) A system for document embedding generation. We'll use the Fireworks embedding API to create embeddings from text data. (Vectorisation) MongoDB Atlas Vector Search responds to user queries by converting the query to an embedding, fetching the corresponding movies. (Retrieval Engine) The Mixtral model uses the Fireworks inference API to generate the recommendations. You can also use Llama, Gemma, and other great OSS models if you like. (LLM) Loading MongoDB Atlas Sample Mflix Dataset to generate embeddings (Dataset) We can also help you design the best architecture for your organization’s needs. Feel free to connect with your account team or contact us here to schedule a collaborative session and explore how Fireworks AI and MongoDB can optimize your AI development process. Head over to our quick-start guide to get started with Atlas Vector Search today.

March 26, 2024

Fireworks AI y MongoDB: las aplicaciones de IA más rápidas con los mejores modelos, impulsadas por sus datos

Nos complace anunciar que Fireworks AI y MongoDB ahora son socios para hacer que la innovación con IA Generativa sea más rápida, más eficiente y más segura. Fireworks AI fue fundada a finales de 2022 por veteranos de la industria del equipo PyTorch de Meta, donde se centraron en la optimización del rendimiento, la mejora de la experiencia del desarrollador y la ejecución de aplicaciones de IA a escala. Es esta la experiencia que Fireworks AI aporta a su plataforma de IA de producción, seleccionando y optimizando los modelos abiertos líderes de la industria. Las pruebas comparativas realizadas por la empresa demuestran que los modelos de IA Generativa que se ejecutan en Fireworks AI ofrecen velocidades de inferencia hasta 4 veces superiores a las de las plataformas alternativas, con un rendimiento y una escala hasta 8 veces superiores. Los modelos son una parte de la pila de aplicaciones. Pero para que los desarrolladores desbloqueen el poder de la IA Generativa, también deben incorporar datos empresariales a esos modelos. Es por eso que Fireworks AI se ha asociado con MongoDB, abordando uno de los desafíos más difíciles para la adopción de la IA. Con MongoDB Atlas , los desarrolladores pueden unificar de forma segura datos operativos, datos no estructurados e incrustaciones de vectores para crear de forma segura aplicaciones y experiencias de IA consistentes, correctas y diferenciadas. Conjuntamente, Fireworks AI y MongoDB proporcionan una solución para los desarrolladores que desean aprovechar modelos de código abierto altamente seleccionados y optimizados, y combinarlos con los datos patentados de su organización, y hacerlo todo con una velocidad y seguridad inigualables. Modelos ultrarrápidos de Fireworks AI: velocidad, eficacia y valor añadido Con su plataforma de inferencia ultrarrápida, Fireworks AI selecciona, optimiza e implementa más de 40 modelos diferentes de IA. Estas optimizaciones pueden suponer al mismo tiempo un importante ahorro de costos, una reducción de la latencia y una mejora del rendimiento. Su plataforma ofrece esto a través de: Modelos estándar, modelos optimizados y complementos: Fireworks AI proporciona una collection de modelos de texto, incrustación y base de imágenes de máxima calidad . Los desarrolladores pueden aprovechar estos modelos o afinar e implementar los suyos propios, emparejándolos con sus propios datos patentados mediante MongoDB Atlas. Capacidades de ajuste fino : Para mejorar aún más la precisión y velocidad del modelo, Fireworks AI también ofrece un servicio de ajuste fino utilizando su CLI para ingerir objetos con formato JSON de bases de datos como MongoDB Atlas. Interfaces y API simples para desarrollo y producción: El patio de juegos de Fireworks AI permite a los desarrolladores interactuar con modelos directamente en un navegador. También se puede acceder mediante programación a través de una conveniente REST API. Esto es compatible con la API de OpenAI y, por lo tanto, interopera con el ecosistema LLM más amplio. Manual: una guía simple y fácil de usar proporciona un conjunto completo de recetas listas para usar que se pueden adaptar para varios casos de uso, incluido el ajuste, la generación y la evaluación. Fireworks AI y MongoDB: cómo establecer el estándar para la IA con modelos seleccionados, optimizados y rápidos Con Fireworks AI y MongoDB Atlas, las aplicaciones se ejecutan en entornos aislados que garantizan el tiempo de actividad y la privacidad, protegidos por controles de seguridad sofisticados que cumplen con los estándares regulatorios más estrictos: Como uno de los principales proveedores de API de modelos de código abierto, Fireworks AI sirve a 66 mil millones de tokens por día (y sigue creciendo). Con Atlas, ejecuta sus aplicaciones en una plataforma probada que atiende a decenas de miles de clientes, desde startups de alto crecimiento hasta las empresas y gobiernos más grandes. Juntos, la solución conjunta de Fireworks AI y MongoDB permiten: Generación aumentada de recuperación (RAG) o preguntas y respuestas a partir de un amplio conjunto de documentos: procese una gran cantidad de documentos para producir resúmenes y datos estructurados que luego puedan impulsar la IA conversacional. Clasificación mediante búsqueda semántica/similar: clasifique y analice conceptos y emociones de llamadas de ventas, videoconferencias y mucho más para proporcionar mejor inteligencia y estrategias. O bien, organice y clasifique un catálogo de productos utilizando imágenes de productos y texto. Imágenes para extracción de datos estructurados: extraiga significado de las imágenes para producir datos estructurados que puedan procesarse y buscarse en una variedad de aplicaciones de visión, desde fotos de stock, moda, detección de objetos, hasta diagnósticos médicos. Inteligencia de alertas: procese grandes cantidades de datos en tiempo real para detectar y alertar automáticamente sobre instancias de fraude, amenazas de ciberseguridad y más. Figura 1: el tutorial de Fireworks muestra cómo llevar sus propios datos a los LLM con generación aumentada de recuperación (RAG) y MongoDB Atlas Primeros pasos con Fireworks AI y MongoDB Atlas Para ayudarte a comenzar, revisa la Optimización RAG con el tutorial de MongoDB Atlas y Fireworks AI , que te muestra cómo crear una aplicación de recomendación de películas e involucra la base de datos de MongoDB Atlas que indexa películas utilizando incrustaciones. (Almacén de vectores) Un sistema para la generación de incrustación de documentos. Usaremos la API de incrustación de Fireworks para crear incrustaciones a partir de datos de texto. (Vectorización) MongoDB Atlas Vector Search responde a las consultas de los usuarios convirtiendo la consulta en una incrustación y obteniendo las películas correspondientes. (Motor de recuperación) El modelo Mixtral utiliza la API de inferencia de Fireworks para generar las recomendaciones. También puede usar Llama, Gemma y otros excelentes modelos de OSS si lo desea. (LLM) Cargar el conjunto de datos Mflix de muestra de MongoDB Atlas para generar incrustaciones (conjunto de datos) También podemos ayudarle a diseñar la mejor arquitectura para las necesidades de su organización. No dude en comunicarse con su equipo de cuentas o póngase en contacto con nosotros aquí para programar una sesión de colaboración y explorar cómo Fireworks AI y MongoDB pueden optimizar su proceso de desarrollo de IA.

March 26, 2024

Fireworks AI et MongoDB : les applications d'IA les plus rapides avec les meilleurs modèles, alimentées par vos données

Nous sommes heureux d'annoncer que Fireworks AI et MongoDB s'associent désormais pour rendre l'innovation avec l'IA générative plus rapide, plus efficace et plus sûre. Fireworks AI a été fondée fin 2022 par des experts de l'équipe PyTorch de Meta, qui se sont concentrés sur l'optimisation des performances, l'amélioration de l'expérience des développeurs et l'exécution d'applications d'IA à grande échelle. C'est cette expertise que Fireworks AI apporte à sa plateforme d'IA de production, en conservant et en optimisant les principaux modèles ouverts du secteur. Les analyses comparatives réalisées par l'entreprise révèlent que les modèles d'IA générative fonctionnant sur Fireworks AI offrent des vitesses d'inférence jusqu'à quatre fois supérieures à celles des plateformes alternatives, avec un débit et une échelle jusqu'à huit fois plus élevés. Les modèles constituent une partie de la pile d'applications. Mais pour que les développeurs puissent exploiter la puissance de l'IA générique, ils doivent également intégrer les données de l'entreprise à ces modèles. C'est pourquoi Fireworks AI s'est associé à MongoDB pour relever l'un des plus grands défis de l'adoption de l'IA. Avec MongoDB Atlas , les développeurs peuvent unifier en toute sécurité les données opérationnelles, les données non structurées et les données vectorielles pour créer des applications et des expériences d'IA cohérentes, précises et différenciées. Ensemble, Fireworks AI et MongoDB offrent une solution aux développeurs qui souhaitent exploiter des modèles open source hautement spécialisés et optimisés, et les combiner avec les données propriétaires de leur organisation, le tout avec une rapidité et une sécurité inégalées. Modèles ultra-rapides de Fireworks AI : alliant rapidité, efficacité et valeur Grâce à sa plateforme d’inférence ultra-rapide, Fireworks AI organise, optimise et déploie plus de 40 modèles d’IA différents. Ces optimisations peuvent simultanément entraîner des économies de coûts significatives, une latence réduite et un débit amélioré. Leur plateforme offre cela via : Des modèles prêts à l'emploi, des modèles optimisés et des modules complémentaires : Fireworks AI propose une collection de modèles de qualité supérieure pour le texte, l'intégration et les fondations d'images . Les développeurs peuvent exploiter ces modèles ou affiner et déployer les leurs, en les associant à leurs propres données à l'aide de MongoDB Atlas. Des capacités d'affinage : pour améliorer encore la précision et la rapidité des modèles, Fireworks AI propose également un service d'affinage utilisant son CLI pour ingérer des objets au format JSON à partir de bases de données telles que MongoDB Atlas. Des interfaces et des API simples pour le développement et la production : Fireworks AI permet aux développeurs d'interagir avec les modèles directement dans un navigateur. Il est également accessible par programme via une API REST pratique. Elle est compatible avec l'API OpenAI et interagit donc avec l'écosystème LLM plus large. Un livre de cuisine : un livre de recettes simple et facile à utiliser fournit un ensemble complet de recettes prêtes à l'emploi qui peuvent être adaptées à différents cas d'utilisation, y compris l'affinage, la génération et l'évaluation. Fireworks AI et MongoDB : établir la norme pour l'IA avec des modèles organisés, optimisés et rapides Avec Fireworks AI et MongoDB Atlas, les applications s'exécutent dans des environnements isolés garantissant la disponibilité et la confidentialité, protégées par des contrôles de sécurité sophistiqués qui répondent aux normes réglementaires les plus strictes : Fireworks AI est l'un des principaux fournisseurs d'API de modèles open source et gère 66 milliards de jetons par jour (et ce chiffre ne cesse de croître). Avec Atlas, vous exécutez vos applications sur une plateforme éprouvée qui sert des dizaines de milliers de clients, des startups à forte croissance aux plus grandes entreprises et gouvernements. Ensemble, la solution conjointe Fireworks AI et MongoDB offre : Une génération augmentée de récupération (RAG) ou des questions-réponses à partir d'un vaste ensemble de documents : l'ingestion d'un grand nombre de documents permet de produire des résumés et des données structurées qui peuvent ensuite alimenter l'IA conversationnelle. Une classification grâce à la recherche sémantique/de similarité : classifie et analyse les concepts et les émotions issus des appels de vente, des vidéoconférences, etc. afin d'améliorer les informations et les stratégies. Ou encore, organise et classe un catalogue de produits à l'aide d'images et de textes. Une extraction de données structurées à partir d'images : extrait le sens des images pour produire des données structurées qui peuvent être traitées et recherchées dans une gamme d'applications visuelles. Des photos de stock à la mode, en passant par la détection d'objets et les diagnostics médicaux. Une alerte intelligente : traite de grandes quantités de données en temps réel pour détecter et alerter automatiquement les cas de fraude, les menaces de cybersécurité, etc. Figure 1 : le tutoriel Fireworks montre comment apporter vos propres données aux LLM avec la génération augmentée de récupération (RAG) et Atlas MongoDB. Prise en main de Fireworks AI et MongoDB Atlas Pour vous aider à vous lancer, découvrez le tutoriel Optimiser la RAG avec MongoDB Atlas et Fireworks AI , qui vous montre comment créer une application de recommandation de films et implique la base de données MongoDB Atlas qui indexe les films à l'aide d'intégrations. (Vector Store) Système de génération d'intégration de documents. Nous utiliserons l'API Fireworks pour créer des intégrations à partir de données textuelles. (Vectorisation) MongoDB Atlas Vector Search répond aux requêtes des utilisateurs en convertissant la requête en une image et en récupérant les films correspondants. (Moteur de récupération) Le modèle Mixtral utilise l'API d'inférence Fireworks pour générer les recommandations. Vous pouvez également utiliser Llama, Gemma et d'autres grands modèles OSS si vous le souhaitez. (LLM) Chargement de la base de données MongoDB Atlas Sample Mflix Dataset pour générer des intégrations (Dataset) Nous pouvons également vous aider à concevoir l'architecture la mieux adaptée aux besoins de votre organisation. N'hésitez pas à contacter votre équipe ou à nous contacter ici pour planifier une session de collaboration et découvrir comment Fireworks AI et MongoDB peuvent optimiser votre processus de développement de l'IA.

March 26, 2024

Fireworks AI e MongoDB: le app IA più veloci con i migliori modelli, alimentate dai tuoi dati

Siamo lieti di annunciare che Fireworks AI e MongoDB stanno ora diventando partner per rendere l'innovazione con l'IA generativa più veloce, più efficiente e più sicura. Fireworks AI è stata fondata alla fine del 2022 da veterani del settore provenienti dal team PyTorch di Meta, dove si sono concentrati sull'ottimizzazione delle prestazioni, sul miglioramento dell'esperienza degli sviluppatori e sull'esecuzione di applicazioni IA su larga scala. È questa competenza che Fireworks AI apporta alla sua piattaforma di produzione IA, curando e ottimizzando i principali modelli aperti del settore. Il benchmarking dell'azienda mostra che i modelli di IA generativa in esecuzione su Fireworks AI offrono velocità di inferenza fino a 4 volte maggiori rispetto alle piattaforme alternative, con throughput e scalabilità fino a 8 volte superiori. I modelli fanno parte dello stack dell'applicazione. Ma per sbloccare la potenza dell'IA generativa, gli sviluppatori devono anche portare i dati aziendali in quei modelli. Ecco perché Fireworks AI è diventato partner di MongoDB, affrontando una delle sfide più difficili per l'adozione dell'IA. Con MongoDB Atlas , gli sviluppatori possono unificare in sicurezza i dati operativi, i dati non strutturati e gli incorporamenti vettoriali, per creare in modo sicuro applicazioni ed esperienze IA coerenti, corrette e differenziate. Insieme, Fireworks AI e MongoDB offrono una soluzione per gli sviluppatori che desiderano sfruttare modelli open-source altamente curati e ottimizzati e combinarli con i dati proprietari della propria organizzazione, il tutto con una velocità e una sicurezza senza precedenti. Modelli velocissimi di Fireworks AI: velocità, efficienza e valore garantiti Grazie alla sua velocissima piattaforma di inferenza, Fireworks AI cura, ottimizza e distribuisce oltre 40 diversi modelli di IA. Queste ottimizzazioni possono portare contemporaneamente a notevoli risparmi sui costi, a una riduzione della latency e a un miglioramento del throughput. La loro piattaforma fornisce questo tramite: Modelli standard, modelli ottimizzati e componenti aggiuntivi: Fireworks AI fornisce una collection di modelli di testo, incorporamento e base di immagini di alta qualità . Gli sviluppatori possono sfruttare questi modelli o perfezionare e distribuire i propri, abbinandoli ai propri dati proprietari utilizzando MongoDB Atlas. Funzionalità di ottimizzazione : per migliorare ulteriormente la precisione e la velocità del modello, Fireworks AI offre anche un servizio di ottimizzazione utilizzando la sua CLI per acquisire oggetti in formato JSON da database come MongoDB Atlas. Interfacce e API semplici per lo sviluppo e la produzione: il playground Fireworks AI consente agli sviluppatori di interagire con i modelli direttamente in un browser. È anche possibile accedervi a livello di programmazione tramite una comoda REST API. Questo è compatibile con l'API OpenAI e quindi interagisce con l'ecosistema LLM più ampio. Cookbook: un cookbook semplice e facile da usare fornisce un set completo di ricette pronte all'uso che possono essere adattate a vari casi d'uso, tra cui la messa a punto, la generazione e la valutazione. Fireworks AI e MongoDB: definizione dello standard per l'IA con modelli curati, ottimizzati e veloci Con Fireworks AI e MongoDB Atlas, le app vengono eseguite in ambienti isolati garantendo tempi di attività e privacy, protetti da sofisticati controlli di sicurezza che soddisfano gli standard normativi più severi: Essendo uno dei principali fornitori di API di modelli open source, Fireworks AI serve 66 miliardi di token al giorno (e oltre). Con Atlas, esegui le tue app su una piattaforma collaudata che serve decine di migliaia di clienti, dalle startup in forte crescita alle più grandi aziende e governi. Insieme, la soluzione congiunta Fireworks AI e MongoDB consente: RAG o Q&A da un vasto bacino di documenti: ingerisci un gran numero di documenti per produrre sintesi e dati strutturati che possono poi alimentare l'IA conversazionale. Classificazione tramite ricerca semantica/somiglianza: classifica e analizza concetti ed emozioni provenienti da chiamate di vendita, videoconferenze e altro per fornire informazioni e strategie migliori. Oppure, organizza e classifica un catalogo di prodotti utilizzando immagini e testo. Estrazione da immagini a dati strutturati: estrai significato dalle immagini per produrre dati strutturati che possono essere elaborati e ricercati in una vasta gamma di app per la visione: dalle foto stock, alla moda, al rilevamento di oggetti, alla diagnostica medica. Intelligence sugli avvisi: elabora grandi quantità di dati in tempo reale per rilevare e avvisare automaticamente su casi di frode, minacce alla sicurezza informatica e altro ancora. Figura 1: Il tutorial di Fireworks mostra come trasferire i propri dati su LLM con retrieval-augmented generation (RAG) e MongoDB Atlas Introduzione a Fireworks AI e MongoDB Atlas Per aiutarti a iniziare, consulta il tutorial IA " Ottimizzazione RAG con MongoDB Atlas e Fireworks AI ", che mostra come creare un'app per consigliare film e prevede: MongoDB Atlas Database che indicizza i film utilizzando gli incorporamenti. (Archivio vettoriale) Un sistema per la generazione di incorporamenti di documenti. Utilizzeremo l'API di incorporamento di Fireworks per creare incorporamenti da dati di testo. (Vettorializzazione) MongoDB Atlas Vector Search risponde alle domande degli utenti convertendo la query in un incorporamento, recuperando i filmati corrispondenti. (Motore di recupero) Il modello Mixtral utilizza l'API di inferenza di Fireworks per generare i consigli. È possibile anche usare anche Llama, Gemma e altri fantastici modelli OSS. (LLM) Caricamento del set di dati Mflix di esempio di MongoDB Atlas per generare incorporamenti (set di dati) Possiamo anche aiutarti a progettare la migliore architettura per le esigenze della tua organizzazione. Mettiti in contatto con il team del tuo account o contattaci qui per programmare una sessione collaborativa ed esplorare come Fireworks AI e MongoDB possono ottimizzare il tuo processo di sviluppo dell'IA.

March 26, 2024

Fireworks AI e MongoDB: os aplicativos de IA mais rápidos com os melhores modelos, alimentados por seus dados

Temos o prazer de anunciar que o Fireworks AI e o MongoDB estão se unindo para tornar a inovação com IA generativa mais rápida, eficiente e segura. O Fireworks AI foi fundado no final de 2022 por veteranos do setor e integrantes da equipe PyTorch da Meta que se concentraram na otimização do desempenho, na melhoria da experiência do desenvolvedor e na execução de aplicativos de IA em grande escala. É essa experiência que o Fireworks AI traz para sua plataforma de IA de produção, selecionando e otimizando os principais modelos abertos do setor. O benchmarking da empresa mostra que os modelos de IA generativa executados no Fireworks AI operam com velocidades de inferência até 4 vezes mais rápidas do que as plataformas alternativas, com taxa de transferência e escala até 8 vezes maiores. Os modelos são uma parte da pilha de aplicação. No entanto, para que os desenvolvedores possam desbloquear o poder da IA generativa, eles também precisam trazer dados corporativos para esses modelos. É por isso que o Fireworks AI fez uma parceria com o MongoDB, abordando um dos desafios mais difíceis para a adoção da IA. Com o MongoDB Atlas , os desenvolvedores podem unificar com segurança dados operacionais, dados não estruturados e incorporações vetoriais para criar com segurança aplicações e experiências de IA consistentes, corretas e diferenciadas. Juntos, o Fireworks AI e o MongoDB oferecem uma solução para desenvolvedores que desejam aproveitar modelos de código aberto altamente selecionados e otimizados e combiná-los com os dados proprietários da própria organização – e fazer tudo isso com velocidade e segurança incomparáveis. Modelos ultrarrápidos do Fireworks AI: permitindo velocidade, eficiência e valor Com plataforma de inferência ultrarrápida, o Fireworks AI seleciona, otimiza e implanta mais de 40 modelos diferentes de IA. Essas otimizações podem resultar simultaneamente em economia significativa de custos, latência reduzida e taxa de transferência aprimorada. A plataforma oferece isso por meio de: Modelos prontos para uso, modelos otimizados e complementos: o Fireworks AI fornece uma coleção de modelos de base de texto, incorporação e imagem de alta qualidade . Os desenvolvedores podem aproveitar esses modelos ou ajustar e implantar os seus próprios, combinando-os com seus dados proprietários por meio do MongoDB Atlas. Recursos de ajuste fino : para melhorar ainda mais a precisão e a velocidade do modelo, o Fireworks AI também oferece um serviço de ajuste fino usando sua CLI para ingerir objetos formatados em JSON de bancos de dados como o MongoDB Atlas. Interfaces e API simples para desenvolvimento e produção: o playground do Fireworks AI permite que desenvolvedores interajam com modelos diretamente no navegador. Ele também pode ser acessado de forma programática por meio de uma REST API conveniente. Isso é compatível com a API OpenAI e, portanto, interopera com o ecossistema LLM mais amplo. Livro de receitas: um livro de receitas simples e fácil de usar que fornece um conjunto amplo de receitas prontas para uso que podem ser adaptadas para vários casos de uso, incluindo ajuste fino, geração e avaliação. Fireworks AI e MongoDB: definindo o padrão para IA com modelos selecionados, otimizados e rápidos Com o Fireworks AI e o MongoDB Atlas, os aplicativos são executados em ambientes isolados, garantindo tempo de atividade e privacidade, protegidos por controles de segurança sofisticados que atendem aos padrões regulatórios mais rígidos: Como um dos principais fornecedores de API de modelo de código aberto, o Fireworks AI fornece 66 bilhões de tokens por dia (e esse número só cresce). Com o Atlas, você executa seus aplicativos em uma plataforma comprovada que atende a dezenas de milhares de clientes, desde startups de alto crescimento até as maiores empresas e governos. Juntas, a solução conjunta do Fireworks AI e do MongoDB permite: RAG ou perguntas e respostas a partir de um vasto conjunto de documentos: ingerir inúmeros documentos para produzir resumos e dados estruturados que podem alimentar a IA conversacional. Classificação por meio de pesquisa semântica/similaridade: classifique e analise conceitos e emoções de chamadas de vendas, videoconferências e muito mais para garantir inteligência e estratégias melhores. Ou organize e classifique um catálogo de produtos usando imagens e texto do produto. Imagens para extração de dados estruturados: extraia o significado das imagens para produzir dados estruturados que possam ser processados e pesquisados em uma variedade de aplicativos de visão – de fotos de banco de imagens à moda, detecção de objetos e diagnósticos médicos. Inteligência de alerta: processe grandes quantidades de dados em tempo real para detectar e alertar automaticamente sobre casos de fraude, ameaças à segurança cibernética e muito mais. Figura 1: o tutorial do Fireworks mostra como trazer seus próprios dados para LLMs com o RAG e o MongoDB Atlas Introdução ao Fireworks AI e ao MongoDB Atlas Para ajudar você a começar, analise o tutorial Otimizando o RAG com o MongoDB Atlas e o Fireworks AI , que mostra como criar um aplicativo de recomendação de filmes e envolve Banco de dados MongoDB Atlas que indexa filmes usando incorporações. (Vector Store) Um sistema para geração de incorporação de documentos. Usaremos a API de incorporação do Fireworks para criar incorporações a partir de dados de texto. (Vetorização) O MongoDB Atlas Vector Search responde às consultas do usuário convertendo a consulta em uma incorporação, buscando os filmes correspondentes. (Mecanismo de recuperação) O modelo Mixtral usa a API de inferência do Fireworks para gerar as recomendações. Você também pode usar o Llama, o Gemma e outros modelos OSS excelentes, se desejar. (LLM) Carregando o conjunto de dados Mflix de amostra do MongoDB Atlas para gerar incorporações (conjunto de dados) Também podemos ajudar você a projetar a melhor arquitetura de acordo com necessidades da sua organização. Sinta-se à vontade para entrar em contato com a equipe responsável pela sua conta ou entre em contato com a gente por aqui para agendar uma sessão colaborativa e explorar como o Fireworks AI e o MongoDB podem otimizar seu processo de desenvolvimento de IA.

March 26, 2024

Fireworks AI 및 MongoDB: 데이터를 기반으로 하는 최고의 모델을 갖춘 가장 빠른 AI 앱

Fireworks AI 와 MongoDB가 더 빠르고, 더 효율적이고, 더 안전한 생성형 인공지능을 통한 혁신을 실현하기 위해 파트너십을 맺었음을 알려드립니다. Meta의 PyTorch 팀 출신의 업계 베테랑들이 2022년 말에 설립한 Fireworks AI는 성능 최적화, 개발자 경험 개선, 대규모 AI 앱 실행에 중점을 두고 있습니다. Fireworks AI는 이러한 전문성을 바탕으로 업계 최고의 개방형 모델을 큐레이팅하고 최적화하여 프로덕션 AI 플랫폼에 적용하고 있습니다. 이 회사의 벤치마킹에 따르면 Fireworks AI에서 실행되는 생성형 인공지능 모델은 다른 플랫폼에 비해 최고 4배 빠른 추론 속도와 최대 8배 더 높은 처리량과 확장성을 제공합니다. 모델은 애플리케이션 스택에 포함되어 있습니다. 그러나 생성형 인공지능의 성능을 활용하려면 개발자가 해당 모델에 엔터프라이즈 데이터를 가져와야 합니다. 바로 이것이 Fireworks AI가 MongoDB와 파트너십을 맺고 AI 도입의 가장 어려운 과제 중 하나를 해결한 이유입니다. 개발자는 MongoDB Atlas 를 통해 운영 데이터, 비정형 데이터, 벡터 임베딩을 안전하게 통합하여 일관되고 정확하며 차별화된 AI 애플리케이션과 경험을 안전하게 구축할 수 있습니다. Fireworks AI와 MongoDB는 고도로 선별되고 최적화된 오픈 소스 모델을 활용하고, 이를 조직의 독점 데이터와 결합하고자 하는 개발자를 위한 솔루션을 제공하며, 이 모든 작업을 탁월한 속도와 보안으로 수행할 수 있도록 공동으로 지원합니다. Fireworks AI의 초고속 모델: 속도, 효율성, 가치 실현 Fireworks AI는 초고속 추론 플랫폼을 통해 40개 이상의 다양한 AI 모델을 큐레이팅, 최적화 및 배포합니다. 이러한 최적화 덕에 상당한 비용 절감, 지연 시간 단축, 처리량 향상을 동시에 달성할 수 있습니다. 플랫폼이 이를 실현하는 방법은 다음과 같습니다. 기성 모델, 최적화된 모델 및 추가 기능: Fireworks AI는 최고 품질의 텍스트, 임베딩 및 이미지 기반 모델 컬렉션을 제공합니다 . 개발자는 이러한 모델을 활용하거나 자체 모델을 미세 조정하여 배포할 수 있으며, MongoDB Atlas를 사용해 자체 독점 데이터와 페어링할 수 있습니다. 미세 조정 기능 : Fireworks AI는 모델 정확도와 속도를 더욱 향상하기 위해 CLI를 사용하여 MongoDB Atlas와 같은 데이터베이스에서 JSON 형식의 개체를 수집하는 미세 조정 서비스도 제공합니다. 개발 및 제작을 위한 간단한 인터페이스와 API: 개발자는 Fireworks AI 플레이그라운드를 통해 브라우저에서 직접 모델과 상호 작용할 수 있습니다. 또는 편리한 REST API를 통해 프로그래밍 방식으로 액세스할 수도 있습니다. 이는 OpenAI API와 호환되므로 광범위한 LLM 에코시스템과 상호 운용됩니다. 쿡북: 간단하고 사용하기 쉬운 쿡북은 미세 조정, 생성, 평가 등 다양한 사용 사례에 바로 사용할 수 있는 포괄적인 레시피 세트를 제공합니다. Fireworks AI 및 MongoDB: 엄선되고 최적화된 빠른 모델로 AI의 표준을 정립합니다. Fireworks AI와 MongoDB Atlas를 사용하면 앱이 가장 엄격한 규제 표준을 충족하는 정교한 보안 제어로 보호되는 격리 환경에서 실행되므로 가동 시간과 개인정보 보호가 보장됩니다. 최고의 오픈소스 모델 API 제공업체 중 하나인 Fireworks AI는 하루에 660억 개의 토큰을 제공하며, 그 수는 계속 증가하고 있습니다. Atlas를 사용하면 고성장 스타트업부터 엔터프라이즈 및 정부 기관에 이르기까지 수만 명의 고객에게 서비스를 제공하는 검증된 플랫폼에서 앱을 실행할 수 있습니다. Fireworks AI와 MongoDB 공동 솔루션을 함께 사용하면 다음과 같은 이점을 얻을 수 있습니다. 방대한 문서 풀에서 검색 증강 생성(RAG) 또는 Q&A 수행: 대량의 문서를 수집하여 요약 및 구조화된 데이터를 생성한 다음 대화형 AI를 강화할 수 있습니다. 시맨틱/유사성 검색을 통한 분류: 영업 통화, 화상 회의 등에서 소개된 개념과 감정을 분류하고 분석하여 더 나은 인텔리전스와 전략을 제공할 수 있습니다. 또는 제품 이미지와 텍스트를 사용하여 제품 카탈로그를 구성하고 분류할 수 있습니다. 이미지에서 구조화된 데이터 추출: 이미지에서 의미를 추출하여 스톡 사진, 패션, 물체 감지, 의료 진단 등 다양한 비전 앱에서 처리 및 검색할 수 있는 구조화된 데이터를 생성합니다. 경고 인텔리전스: 대량의 데이터를 실시간으로 처리하여 사기, 사이버 보안 위협 등의 인스턴스를 자동으로 탐지하고 경고합니다. 그림 1: 검색 증강 생성(RAG) 및 MongoDB Atlas를 사용하여 자체 데이터를 거대 언어 모델로 가져오는 방법을 보여주는 Fireworks 튜토리얼. Fireworks AI 및 MongoDB Atlas 시작하기 임베딩을 사용하여 영화를 색인하는 MongoDB Atlas 데이터베이스와 영화 추천 앱을 구축하는 방법을 보여주는 MongoDB Atlas 및 Fireworks AI 튜토리얼을 통해 RAG 최적화를 검토하여 시작해 보세요. (벡터 저장소) 문서 임베딩 생성을 위한 시스템입니다. Fireworks 임베딩 API를 사용하여 텍스트 데이터에서 임베딩을 생성합니다. (벡터화) MongoDB Atlas Vector Search 는 쿼리를 임베딩으로 변환하여 해당 동영상을 가져오는 방식으로 사용자 쿼리에 응답합니다. (검색 엔진) Mixtral 모델은 Fireworks 추론 API를 사용하여 추천을 생성합니다. 원하는 경우 Llama, Gemma 및 다른 우수한 OSS 모델을 사용할 수도 있습니다. (LLM) MongoDB Atlas 샘플 Mflix 데이터 세트를 로드하여 임베딩 생성(데이터 세트) 또한 조직의 요구 사항에 가장 적합한 아키텍처를 설계할 수 있도록 도와드릴 수 있습니다. 언제든지 계정 팀에 문의하거나 여기를 클릭하여 공동 작업 세션을 예약하고, Fireworks AI와 MongoDB가 AI 개발 프로세스를 어떻게 최적화할 수 있는지 알아보세요 .

March 26, 2024

Fireworks AI 和 MongoDB：依托您的数据，借助优质模型，助力您开发高速 AI 应用

我们欣然宣布，MongoDB 与 Fireworks AI 正携手合作，让客户能够利用生成式人工智能 (AI)，更快速、更高效、更安全地开展创新活动。Fireworks AI 由 Meta 旗下 PyTorch 团队的行业资深人士于 2022 年底创立，他们在团队中主要负责优化性能、提升开发者体验以及大规模运行 AI 应用。 Fireworks AI 将这些专业知识运用于自己的生产 AI 平台，从而整理并优化了业界优质的开放模型。该公司进行了基准测试，结果表明，在 Fireworks AI 上运行的生成式 AI 模型的推断速度比其他同类平台快 4 倍，吞吐量和规模高出多达 8 倍。模型属于应用程序堆栈的一部分。然而，开发者要想发挥生成式人工智能的力量，还需要将企业数据引入这些模型中。这正是企业采用 AI 时所面临的一大棘手问题，也是 Fireworks AI 与 MongoDB 开展合作的原因。借助 MongoDB Atlas ，开发者可以安全地将运营数据、非结构化数据和向量嵌入进行统一，从而安全打造一致、正确和差异化的 AI 应用程序和体验。 Fireworks AI 和 MongoDB 强强联手，精心整理并优化了各种开源模型，为想要结合企业自身专有数据使用这些模型的开发者提供了解决方案，并且能够快速安全地实现这一切。 Fireworks AI 提供快如闪电的模型：将速度、效率和价值“一网打尽” Fireworks AI 凭借快如闪电的推断平台，整理、优化并部署了 40 多种不同的 AI 模型。这些优化措施可以同时节省大量成本、减少延迟、提高吞吐量。他们的平台通过以下方式实现这些效果：现成模型、优化模型和插件： Fireworks AI 提供一系列高质量的文本、嵌入和图像基础模型。开发者可以利用这些模型或者对其进行微调，然后部署自己的模型，再借助 MongoDB Atlas 将自己的专有数据引入模型。微调功能：为了进一步提高模型的准确性和速度，Fireworks AI 还提供了微调服务，该服务可利用命令行界面 (CLI) 从 MongoDB Atlas 等数据库中摄取采用 JSON 格式的对象。用于开发和生产的各种简易界面和 API： Fireworks AI Playground 可让开发者直接在浏览器中与模型进行交互，而且支持通过方便的 REST API 以编程方式进行访问。Fireworks AI Playground 与 OpenAI API 兼容，因此可以与更广泛的大型语言模型 (LLM) 生态系统进行互操作。使用指南：这份指南简单易用，提供了一套全面的即用型解决方案，可以满足包括微调、生成和评估在内的各种应用场景。 Fireworks AI 和 MongoDB：通过整理和优化快速的模型为 AI 设定标准借助 Fireworks AI 和 MongoDB Atlas，应用可在隔离的环境中运行，在符合最严格监管标准的复杂安全控制措施保护下，确保正常运行时间和数据的私密性：作为优秀的开源模型 API 提供商，Fireworks AI 每天提供 660 亿个词元（并且数量还在不断增长）。您可以在久经考验的 Atlas 平台上运行 App，该平台为数以万计的客户提供服务，其中不乏高增长的初创公司和规模庞大的企业和政府。 Fireworks AI 和 MongoDB 联合解决方案可以实现以下功能：基于大量文档进行检索增强生成 (RAG) 或问答 (Q&A)：摄入大量文档，生成摘要和结构化数据，从而为对话式 AI 提供支持。通过语义/相似性搜索进行分类：对来自销售电话、视频会议等事件中的概念和情绪进行分类和分析，以提供更好的情报和策略。或者，使用产品图片和文字对产品目录进行整理和分类。从图像中提取结构化数据：从图像中提取有意义的内容，生成可在库存照片、时尚、物体检测、医疗诊断应用等一系列视觉应用中处理和搜索的结构化数据。智能警报：实时处理大量数据，自动检测欺诈、网络安全威胁等活动并发出警报。图 1： Fireworks 教程展示了如何使用 RAG 和 MongoDB Atlas 将自己的数据引入 LLM 上手使用 Fireworks AI 和 MongoDB Atlas 为了帮助您上手使用 Fireworks AI 和 MongoDB Atlas，请查看《使用 MongoDB Atlas 和 Fireworks AI 优化 RAG 》的教程，该教程向您展示了如何构建电影推荐应用，其中涉及使用嵌入对电影进行索引的 MongoDB Atlas 数据库。（向量存储）文档嵌入生成系统。我们将使用 Fireworks 嵌入 API 从文本数据中创建嵌入。（向量化） MongoDB Atlas Vector Search 通过将查询转换为嵌入来获取对应的电影，进而响应用户查询。（检索引擎） Mixtral 模型使用 Fireworks 推断 API 来生成推荐建议。如果您愿意，您还可以使用 Llama、Gemma 和其他出色的开源软件 (OSS) 模型。(LLM) 加载 MongoDB Atlas 示例 Mflix 数据集以生成嵌入（数据集）我们还可以帮助您设计最符合贵组织需求的架构。请随时与您的客户团队联系，或在此联系我们为您安排一次协作会议，共同探讨 Fireworks AI 和 MongoDB 如何能够优化您的 AI 开发流程。

March 26, 2024

Fireworks AI und MongoDB: Die schnellsten KI-Apps mit den besten Modellen, angetrieben von Ihren Daten

Wir freuen uns, ankündigen zu können, dass Fireworks AI und MongoDB jetzt zusammenarbeiten, um Innovationen mit generativer KI schneller, effizienter und sicherer zu machen. Fireworks AI wurde Ende 2022 von Branchenexperten aus dem PyTorch-Team von Meta gegründet, wo sie sich auf die Optimierung der Leistung, die Verbesserung des Entwicklererlebnisses und den Betrieb von KI-Apps in großem Maßstab konzentrierten. Dieses Fachwissen bringt Fireworks AI in seine KI-Plattform für die Produktion ein und kuratiert und optimiert die führenden offenen Modelle der Branche. Benchmarking durch das Unternehmen zeigt, dass generative KI-Modelle, die auf Fireworks AI laufen, bis zu 4x schnellere Inferenzen liefern als alternative Plattformen, mit bis zu 8x höherem Durchsatz und Skalierung. Modelle sind ein Teil des Anwendungsstacks. Aber damit Entwickler die Möglichkeiten der generativen KI ausschöpfen können, müssen sie auch Unternehmensdaten in diese Modelle einbringen. Aus diesem Grund hat sich Fireworks AI mit MongoDB zusammengetan, um eine der größten Herausforderungen bei der Einführung von KI zu bewältigen. Mit MongoDB Atlas können Entwickler operative Daten, unstrukturierte Daten und Vektoreinbettungen sicher zusammenführen, um konsistente, korrekte und differenzierte KI-Anwendungen und -Erlebnisse zu erstellen. Gemeinsam bieten Fireworks AI und MongoDB eine Lösung für Entwickler, die hochgradig kuratierte und optimierte Open-Source-Modelle nutzen und diese mit den unternehmenseigenen Daten kombinieren möchten – und das alles mit unvergleichlicher Geschwindigkeit und Sicherheit. Blitzschnelle Modelle von Fireworks AI: Geschwindigkeit, Effizienz und Mehrwert Mit seiner blitzschnellen Inferenzplattform kuratiert, optimiert und verwendet Fireworks AI über 40 verschiedene KI-Modelle. Diese Optimierungen können gleichzeitig zu erheblichen Kosteneinsparungen, reduzierten Latenzen und verbessertem Durchsatz führen. Ihre Plattform stellt dies bereit über: Standardmodelle, optimierte Modelle und Add-Ons: Fireworks AI bietet eine Collection erstklassiger Text-, Einbettungs- und Bildgrundmodelle . Entwickler können diese Modelle nutzen oder ihre eigenen Modelle anpassen und einsetzen, indem sie sie mit ihren eigenen Daten über MongoDB Atlas verknüpfen. Fähigkeiten zur Feinabstimmung : Um die Modellgenauigkeit und -geschwindigkeit weiter zu verbessern, bietet Fireworks AI auch einen Feinabstimmungsdienst, der seine CLI nutzt, um JSON-formatierte Objekte aus Datenbanken wie MongoDB Atlas aufzunehmen. Einfache Schnittstellen und APIs für Entwicklung und Produktion: Der Fireworks AI-Spielplatz ermöglicht es Entwicklern, direkt im Browser mit Modellen zu interagieren. Der Zugriff kann auch programmatisch über eine praktische REST-API erfolgen. Dies ist OpenAI-API-kompatibel und interagiert somit mit der breiteren LLM-Umgebung. Kochbuch: Ein einfaches und benutzerfreundliches Kochbuch bietet einen umfassenden Satz gebrauchsfertiger Rezepte, die für verschiedene Anwendungsfälle angepasst werden können, einschließlich Feinabstimmung, Erstellung und Auswertung. Fireworks AI und MongoDB: Setzen Sie mit kuratierten, optimierten und schnellen Modellen den Standard für KI Mit Fireworks AI und MongoDB Atlas werden Apps in isolierten Umgebungen ausgeführt, die Betriebszeit und Datenschutz gewährleisten und durch ausgefeilte Sicherheitskontrollen geschützt sind, die den strengsten gesetzlichen Standards entsprechen: Als einer der führenden Anbieter von Open-Source-Modell-APIs bedient Fireworks AI 66 Milliarden Token pro Tag (Tendenz steigend). Mit Atlas betreiben Sie Ihre Apps auf einer bewährten Plattform, die Zehntausende von Kunden bedient, von wachstumsstarken Startups bis hin zu den größten Unternehmen und Regierungen. Zusammen ermöglicht die gemeinsame Lösung von Fireworks AI und MongoDB: Retrieval-augmented Generation (RAG) oder Q&A aus einem riesigen Pool von Dokumenten: Erfassen Sie eine große Anzahl von Dokumenten, um Zusammenfassungen und strukturierte Daten zu erstellen, die dann als Grundlage für KI dienen können. Klassifizierung durch semantische Suche/Ähnlichkeitssuche: Klassifizieren und analysieren Sie Konzepte und Emotionen aus Verkaufsgesprächen, Videokonferenzen und mehr, um bessere Informationen und Strategien zu erhalten. Oder organisieren und klassifizieren Sie einen Produktkatalog mit Produktbildern und Text. Extraktion von Bildern in strukturierte Daten: Extrahieren Sie Bedeutungen aus Bildern, um strukturierte Daten zu erzeugen, die in einer Reihe von Bildverarbeitungs-Apps verarbeitet und durchsucht werden können – von Bestandsfotos über Mode und Objekterkennung bis hin zu medizinischen Diagnosen. Intelligente Warnmeldungen: Verarbeiten Sie große Datenmengen in Echtzeit, um automatisch Betrugsfälle, Bedrohungen der Cybersicherheit und mehr zu erkennen und zu melden. Abbildung 1: Das Fireworks-Tutorial zeigt, wie Sie Ihre eigenen Daten mit Retrieval-Augmented Generation (RAG) und MongoDB Atlas in Large Language Models einbringen können Erste Schritte mit Fireworks AI und MongoDB Atlas Um Ihnen den Einstieg zu erleichtern, sehen Sie sich das Tutorial „ Optimizing RAG with MongoDB Atlas and Fireworks AI “ an, das Ihnen zeigt, wie Sie eine Filmempfehlungs-App erstellen und die MongoDB Atlas-Datenbank einbeziehen, die Filme mithilfe von Embeddings indiziert. (Vektorspeicher) Ein System zur Erzeugung von Dokumenteneinbettungen. Wir verwenden die Fireworks-Einbettungs-API, um Einbettungen aus Textdaten zu erstellen. (Vektorisierung) MongoDB Atlas Vector Search antwortet auf Benutzeranfragen, indem es die Anfrage in eine Einbettung umwandelt und die entsprechenden Filme abruft. (Retrieval Engine) Das Mixtral-Modell verwendet die Inferenz-API von Fireworks , um die Empfehlungen zu generieren. Sie können aber auch Llama, Gemma und andere großartige OSS-Modelle verwenden. (LLM) Laden des MongoDB Atlas-Beispieldatensatzes Mflix zur Erzeugung von Einbettungen (Datensatz) Wir können Ihnen auch dabei helfen, die beste Architektur für die Bedürfnisse Ihres Unternehmens zu entwerfen. Setzen Sie sich mit Ihrem Kundenteam in Verbindung oder kontaktieren Sie uns hier , um eine gemeinsame Sitzung zu vereinbaren und herauszufinden, wie Fireworks AI und MongoDB Ihren AI-Entwicklungsprozess optimieren können.

March 26, 2024

利用生成式人工智能和 MongoDB 应对网络安全的最大挑战

在不断变化的网络安全环境中，企业面临着众多挑战，需要利用尖端技术提供创新解决方案。最紧迫的问题之一是网络威胁日益复杂，包括恶意软件、勒索软件和网络钓鱼攻击，这些攻击越来越难以检测和缓解。此外，数字基础设施的快速扩张扩大了攻击面，使安全团队更难监控和保护每个入口和出口点。另一个重大挑战是缺少熟练的网络安全专业人员（据独立调查估计，全球缺口约为 400 万1），这使得许多组织容易受到攻击。这些挑战凸显了对先进技术的需求，这些技术可以增强人类保护数字资产和数据的努力。生成式AI有何帮助？生成式人工智能 ( gen AI ) 已成为应对这些网络安全挑战的强大工具。通过利用大型语言模型 ( LLM ) 在现有数据集的基础上生成新数据或模式，生成式人工智能可以在多个关键领域提供创新解决方案：强化威胁检测和响应生成式人工智能可用于模拟网络威胁，包括复杂的恶意软件和网络钓鱼攻击。这些模拟有助于训练机器学习模型，以更准确地检测新的和不断演变的威胁。此外，生成式人工智能可以帮助开发实时对威胁做出反应的自动响应系统。虽然这永远不会消除对人工监督的需求，但可以减少人工干预和劳累，从而更快地缓解攻击。例如，在适当的监督下，它可以自动为易受攻击的系统打补丁，或调整防火墙规则以阻止攻击载体。这种自动快速反应能力对于减少零日漏洞尤为重要，因为从发现漏洞到攻击者利用漏洞之间的窗口很短。从安全事件事后分析中汲取可操作的经验教训在网络安全事件发生后，进行彻底的事后分析对于了解事件的经过、原因以及今后如何防止类似事件的发生至关重要。在这一过程中，生成式人工智能可以综合和汇总多种来源的复杂数据（日志、网络流量和安全警报等），发挥关键作用。通过分析这些数据，生成式人工智能可以识别可能导致安全漏洞的模式和异常，从而提供由于信息量和复杂性而可能被人类分析师忽视的见解。此外，它还可以生成全面的报告，突出显示关键发现、诱发因素和潜在漏洞，从而简化事后分析过程。这种能力不仅能加快恢复和学习过程，还能使组织实施更有效的补救策略，最终加强其网络安全态势。生成用于深度模型训练的合成数据用于培训网络安全系统的真实数据短缺，这是一个重大障碍。生成式人工智能可以创建真实的合成数据集，反映真实的网络流量和用户行为，而不会暴露敏感信息。这种合成数据可用于训练检测系统，在不损害隐私或安全的情况下提高其准确性和有效性。自动检测网络钓鱼网络钓鱼仍然是最常见的攻击载体之一。生成式人工智能可以分析网络钓鱼电子邮件和网站中的模式，生成能够高精度预测和检测网络钓鱼尝试的模型。通过将这些模型集成到电子邮件系统和网络浏览器中，组织可以自动过滤掉网络钓鱼内容，保护用户免受潜在威胁。综合考虑：机遇与风险生成式人工智能有望实现复杂流程的自动化、加强威胁检测和响应、提供对网络威胁的更深入了解，从而改变网络安全实践。随着业界不断将生成式人工智能融入网络安全战略，我们必须对这项技术的道德使用和滥用潜力保持警惕。尽管如此，它在加强数字防御方面所带来的好处是毋庸置疑的，因此成为应对网络威胁的持久战中的宝贵资产。 MongoDB 如何提供帮助？有了 MongoDB，您的开发团队就能以任何规模更快地构建和部署强大、正确和差异化的实时网络防御系统。要了解 MongoDB 如何做到这一点，请考虑 AI 技术堆栈包含三层：底层计算 (GPU) 和 LLM 微调模型的工具以及用于上下文学习和对训练模型进行推理的工具人工智能应用程序和相关最终用户体验 MongoDB 在堆栈的第二层运行。它使客户能够将自己的专有数据带到任何计算基础设施上运行的任何 LLM，以构建生成式人工智能驱动的网络安全应用程序。为此，MongoDB 解决采用生成式人工智能保障网络安全时最棘手的问题。 MongoDB Atlas 将运营数据、非结构化数据和矢量数据安全地统一在一个完全托管的多云平台中，避免了在不同系统之间复制和同步数据的需要。 MongoDB 基于文档的架构还允许开发团队轻松地对应用程序数据和矢量嵌入之间的关系进行建模。这样就可以更深入、更快速地分析和见解与安全相关的数据。图 1：在统一的 API 和开发者数据平台中，MongoDB Atlas 汇集了构建现代网络安全应用程序所需的所有数据服务。 MongoDB 的开放式架构与丰富的 AI 开发者框架、LLM 和嵌入式提供商的生态系统相集成。这与我们业界领先的多云功能相结合，使您的开发团队能够灵活快速地行动，避免在这个快速发展的领域中被任何特定的云提供商或 AI 技术限制。请查看我们的 AI 资源页面，了解有关使用 MongoDB 构建 AI 驱动的应用的更多信息。将生成式人工智能和 MongoDB 应用于现实世界的网络安全应用威胁情报 ExTrac 利用 AI 驱动的分析技术和 MongoDB Atlas，通过分析数千个来源的数据来预测公共安全风险。该平台最初帮助西方政府预测冲突，现在正扩展到企业的声誉管理等方面。 MongoDB 的文档数据模型使 ExTrac 能够高效管理复杂数据，增强实时威胁识别。 Atlas Vector Search 有助于增强语言模型，并管理文本、图像和视频的矢量嵌入，从而加快功能开发。这种方法使 ExTrac 能够利用 MongoDB 的灵活性和强大功能，有效地为客户建立趋势模型、追踪不断变化的叙事和预测风险，从而处理任何形状和结构的数据。在 ExTrac 案例研究中了解更多信息。网络安全评估 VISO TRUST 利用 AI 简化对第三方网络风险的评估，使复杂的供应商安全信息能够快速获取，以便做出明智的决策。 VISO TRUST 的平台利用 Amazon Bedrock 和 MongoDB Atlas，实现了供应商安全尽职调查的自动化，大大减少了安全团队的工作量。其 AI 驱动的方法涉及人工智能，可对安全文档进行分类、检测组织并预测人工智能中的安全控制位置。 MongoDB Atlas 为密集检索系统提供文本嵌入，通过检索增强生成 ( RAG ) 提高 LLM 的准确性，提供即时、可操作的安全见解。通过创新地使用技术，VISO TRUST 能够提供快速、可扩展的网络风险评估，为 InstaCart 和 Upwork 等企业大大减少了工作量和时间。 MongoDB 灵活的文档数据库和 Atlas Vector Search 在管理和查询海量数据方面发挥了关键作用，支持 VISO TRUST 提供全面网络风险情报的使命。在 Viso Trust 案例研究中了解更多信息。开始使用的步骤由 LLM 驱动的生成式人工智能，辅以编码为矢量嵌入的操作数据，为网络安全领域带来了许多新的可能性。如果您想进一步了解这项技术及其可能性，请查看我们的 Atlas Vector Search Learning Byte 。在短短 10 分钟内，您将大致了解不同的使用案例以及如何开始。 1 1 Hill, M. （2023 年 4 月 10 日）。尽管进行了大规模的招聘活动，但网络安全劳动力缺口仍达 400 万。 CSO。

March 13, 2024