Docker Hub catalogs

Table of contents

Docker Hub catalogs are your go-to collections of trusted, ready-to-use container images and resources, tailored to meet specific development needs. They make it easier to find high-quality, pre-verified content so you can quickly build, deploy, and manage your applications with confidence. Catalogs in Docker Hub:

  • Simplify content discovery: Organized and curated content makes it easy to discover tools and resources tailored to your specific domain or technology.
  • Reduce complexity: Trusted resources, vetted by Docker and its partners, ensure security, reliability, and adherence to best practices.
  • Accelerate development: Quickly integrate advanced capabilities into your applications without the hassle of extensive research or setup.

The generative AI catalog is the first catalog in Docker Hub, offering specialized content for AI development.

Generative AI catalog

The generative AI catalog makes it easy to explore and add AI capabilities to your applications. With trusted, ready-to-use content and comprehensive documentation, you can skip the hassle of sorting through countless tools and configurations. Instead, focus your time and energy on creating innovative AI-powered applications.

The generative AI catalog provides a wide range of trusted content, organized into key areas to support diverse AI development needs:

  • Demos: Ready-to-deploy examples showcasing generative AI capabilities. These demos provide a hands-on way to explore AI tools and frameworks, making it easier to understand how they can be integrated into real-world applications.
  • Models: Pre-trained AI models for tasks like text generation, Natural Language Processing (NLP), and conversational AI. These models provide a foundation for AI applications without requiring developers to train models from scratch.
  • Applications and end-to-end platforms: Comprehensive platforms and tools that simplify AI application development, including low-code solutions and frameworks for building multi-agent and Retrieval-Augmented Generation (RAG) applications.
  • Model deployment and serving: Tools and frameworks that enable developers to efficiently deploy and serve AI models in production environments. These resources include pre-configured stacks for GPUs and other specialized hardware, ensuring performance at scale.
  • Orchestration: Solutions for managing complex AI workflows, such as workflow engines, Large Language Model (LLM) application frameworks, and lifecycle management tools, to help streamline development and operations.
  • Machine learning frameworks: Popular frameworks like TensorFlow and PyTorch that provide the building blocks for creating, training, and fine-tuning machine learning models.
  • Databases: Databases optimized for AI workloads, including vector databases for similarity search, time-series databases for analytics, and NoSQL solutions for handling unstructured data.