Get Started with Enterprise h2oGPTe for Free
- Generative AI
- Enterprise h2oGPTe
This lesson walks through getting started with the free public instance of Enterprise h2oGPTe. It covers signing in with a Google or GitHub account, and explains that the platform supports air-gapped, on-premises, or cloud VPC deployments for full control over data and prompts. It covers what the platform offers, including connecting any LLM or embedding model with Kubernetes scalability and guardrails, and customizing and deploying open source models as your own assistants. It also notes retrieval-augmented generation with citation support and intelligent model routing as core features.
Key takeaways
- How to sign in to the free public Enterprise h2oGPTe instance using a Google or GitHub account
- Why Enterprise h2oGPTe supports air-gapped, on-premises, or cloud VPC deployment for data control
- What intelligent model routing does: selecting the optimal model for each task automatically
- How retrieval-augmented generation with citation support helps trace an answer back to its source
Start owning your AI