Generative AI for the enterprise

The Domino AI Hub is a collection of pre-built AI projects that help teams jumpstart GenAI development for use cases like RAG, fine-tuning, and more. Templates are fully customizable and shareable for promoting GenAI best practices and guardrails. AI Hub templates from Domino and partners like AWS, NVIDIA, Hugging Face, and others enable you to stay ahead of rapid generative AI innovations.

With a few clicks, spin up a complete Generative AI and Large Language Model development environment. Use tools like LangChain, popular frameworks, vector databases, and GPUs. Instantly and securely connect vector databases to support vector embeddings and techniques such as retrieval augmented generation (RAG). Provision scalable clusters — Ray, Dask, MPI, and Spark in a single click and automate hyperparameter tuning with RayTune.

Domino provides a secure, standard interface to LLMs while ensuring sensitive data is governed, eliminating prompt leakage, and logging all tuning activities for audibility. Compare LLM performance by submitting prompts to multiple services and comparing results. Protect API keys, control and secure your data with access controls, and manage costs for LLM services.

Quickly link to new generative AI services. Integrate and improve existing models using generative AI prompts. Safely compile corporate data into searchable vector databases. Employ Retrieval Augmented Generation (RAG), embed vector data for enhanced prompts and automate updates to vector embeddings via Domino jobs.

Use leading coding assistants like Jupyter AI and GitHub Copilot to automate coding, debug code, access foundation models, and more. Unlock the potential of generative AI in Jupyter notebooks. Easily create, troubleshoot, and summarize code while interacting with a user-friendly conversational assistant through a native chat UI. Seamlessly connect with popular LLMs, providers, or your models, ensuring reproducibility, customization, open-source transparency, and strict data privacy.

Fine-tune and deploy foundation models with Domino's AI Hub. Enjoy pre-built solutions and code assistants, and access scalable compute clusters with automated hyperparameter tuning for better efficiency and lower cost.

Domino can host your models - including LLMs - for inference. You can share your model as a web application or as a model API to help it connect with other systems. By automating infrastructure provisioning, Domino empowers practitioners to create and deploy models quickly without needing DevOps knowledge.

Easily add custom parameters, LLM evaluation frameworks, and guardrails to ensure responsible deployment of Generative AI. Use custom metrics from Domino to track and compare common metrics to ensure LLMs are well governed.

Domino Cost Center helps you control compute and storage costs with comprehensive cost analysis, spend tracking, project allocations, budgeting, and billing alerts. It also offers container cost optimization, workspace sizing, data storage limits, auto-shutdown, and auto-scaling to reduce spend. Scale with operational savings, efficiencies, and productivity gains while bending the Generative AI cost curve.