Domino fully supports generative AI workloads from pilot to production. Learn about Domino’s genAI capabilities and examples to get you started. Domino’s open and interoperable design ensures flexibility to meet the rapidly evolving demands of generative AI.
Domino offers several features specifically designed to streamline and manage generative AI projects.
-
Generative AI project templates accelerate project development by providing turnkey sample Projects directly in Domino, showcasing best practices for generative AI and classical machine learning.
-
Pinecone and Qdrant Vector database support enables managed access to high-dimension vectorized data for generative AI algorithms like Retrieval Augmented Generation (RAG).
-
AI Gateway provides users a safe and streamlined way to access external Large Language Models (LLMs) hosted by service providers like OpenAI, Anthropic, and more.
-
AI Code generation tools give you an on-demand AI coding assistant to help you analyze and develop code more efficiently.
-
Fine-tune foundation models using your datasets to bring context-specific knowledge to pre-trained models.
In addition to generative AI-specific features, Domino’s core platform features are already in place to respond to the challenges of genAI:
-
Domino’s data access layer lets data scientists access the vast quantities of disparate data required for generative AI from a central interface.
-
Model governance (Sentry) lets you register models and customize the model review and validation process with complete audit records and reproducibility to ensure responsible practices.
-
Compute scaling to train and deploy highly-compute intensive generative AI models.
-
Hybrid and multi-cloud support lets you run AI workloads in any cloud or on-prem environment to reduce costs, simplify scaling, and protect data.
-
Deploy and monitor models and apps including GenAI LLMs and apps, on-prem or in the cloud.
-
FinOps lets you monitor and reduce AI costs through budgeting, alerts, and efficient cost allocation.
Domino’s open and interoperable design means that it’s ready to handle any generative AI scenario. The following are some examples of generative AI projects from documentation and the AI Hub:
-
Enterprise Q&A applications with RAG (Retrieval Augmented Generation) using Pinecone database.
-
Summarize product feedback and respond with emails with LangChain and AWS Bedrock.
-
Build LLM chatbots with Streamlit and OpenAI.
Explore more generative AI projects in the AI Hub.