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

Mat Keep and Angela Lee
March 26, 2024 | Updated: August 8, 2024
#genAI

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.

← Previous

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
Next →

MongoDB and Partners: Building the AI Future, Together

If you’re like me, over the past year you’ve closely watched AI’s developments—and the world’s reactions to them. From infectious excitement about AI’s capabilities, to impatience with its cost and return on investment, every day has been filled with AI twists and turns. It’s been quite the roller coaster. During the ride, from time to time I’ve wondered where AI falls on the Gartner hype cycle, which gives "a view of how a technology or application will evolve over time." Have we hit the "peak of inflated expectations" only to fall into the "trough of disillusionment?" Or is the hype cycle an imperfect guide, as The Economist argues? The reality is that it takes time for any new technology—even transformative ones like AI—to take hold. And every advance, no matter how big, has had its detractors. A famous example is that of Picasso (!), who in 1968 said, “Computers are useless. They can only give you answers.” (!!) For our part, MongoDB is convinced that AI is a once-in-a-generation technology that will enhance every future application—a belief that has been reinforced by the incredible work our partners have shared at MongoDB’s 2024 events. Speeding AI development MongoDB is committed to helping organizations of all sizes succeed with AI, and one way we’re doing that is by collaborating with the MongoDB partner ecosystem to create powerful, user-friendly AI development tools and solutions. For example, Fireworks.ai —which is a member of the MongoDB AI Applications Program ecosystem —created an inference solution that hosts gen AI models and supports containerized deployments. This tool makes it easier for developers to build and deploy powerful applications with a range of easy-to-use tools and customization options. They can choose to use state-of-the-art, open-source language, image, and multimodal foundation models off the shelf, or they can customize and fine-tune models to their needs. 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 so with unparalleled speed and security. “MongoDB is one of the most sophisticated database providers, and it’s very easy to use,” said Benny Chen , cofounder of Fireworks.ai. "We want developers to be able to use these tools, and we want to work with providers who enable and empower developers." Nomic , another MAAP ecosystem member, also enables developers with best-in-class solutions across the entire unstructured data workflow. Their Embed offering, available through the Nomic API , allows users to vectorize large-scale datasets for use in text, image, and multimodal retrieval applications, including retrieval-augmented generation (RAG), using only their web browser. The Nomic-MongoDB solution is a highly efficient, open-weight model that developers can use to visualize the unstructured datasets they store in MongoDB Atlas . These insights help users quickly discover trends and articulate data-driven value propositions. Nomic also supported the recently announced vector quantization in MongoDB Atlas Vector Search , which reduces vector sizes while preserving performance. Last—but hardly least!—there’s our new reference architecture with MAAP partners AWS and Anthropic. Announced at MongoDB.local London , the reference architecture supports building memory-enhanced AI agents, and is designed to streamline complex processes and develop smarter, more responsive applications. For more—including a link to the code on Github— check out the MongoDB Developer Center . Making AI work for anyone and everyone The companies MongoDB partners with aren’t just making gen AI easier for developers—they’re building tools for everyone. For example, Capgemini has invested $2 billion in gen AI and is training 100,000 of its employees in the technology. GenYoda, a solution that helps insurance professionals with their daily work, is a product of this investment. GenYoda leverages MongoDB Atlas Vector Search to analyze large amounts of customer data, like policy statements, premiums, claims history, and health information. Using GenYoda, insurance professionals can quickly analyze underwriters’ reports to make informed decisions, create longitudinal health summaries, and streamline customer interactions to improve contact center efficiency. GenYoda can ingest 100,000 documents in just a few hours and respond to users’ queries in two to three seconds—a metric on par with the most widely used gen AI models. And it produces results: in one example, by using Capgemini’s solution an insurer was able to increase productivity by 15%, add new reports 25% faster (thus speeding decision-making), and reduce the manual effort of searching PDFs, increasing efficiency by 10%. Building the future of AI together So, what’s next? Honestly, I’m as curious as you are. But I’m also incredibly excited. At MongoDB, we’re active participants in the AI revolution, working to embrace the possibilities that lie ahead. The future of gen AI is bright, and I can’t wait to see what we’ll build together. To learn more about how MongoDB can accelerate your AI journey, explore the MongoDB AI Applications Program .

November 4, 2024