H2O.ai Blog

Supercharge Your Self-Hosted AI: OpenWebUI + h2oGPTe

Developers want more than a demo. You want control, flexibility, and power. That’s exactly what you get when you bring OpenWebUI — the open-source, customizable AI interface — together with h2oGPTe, H2O.ai’s enterprise-grade AI engine for Retrieval-Augmented Generation (RAG) and agentic reasoning. This isn’t just an integration. It’s a w...

H2O.ai Tops the General AI Assistant (GAIA) Test

We're proud to announce that our h2oGPTe Agent has once again claimed the #1 spot on the prestigious GAIA (General AI Assistants) benchmark with an impressive 75% accuracy rate – the first time a grade of C has been achieved on the GAIA test set. Previously H2O.ai was first to get a passing grade on the GAIA test. This achievement places...

H2O.ai Tops GAIA Leaderboard: A New Era of AI Agents

We're excited to announce that our h2oGPTe Agent has achieved the top position on the GAIA (General AI Assistants, https://arxiv.org/abs/2311.12983) benchmark leaderboard (https://huggingface.co/spaces/gaia-benchmark/leaderboard), with a remarkable score of 65% - significantly outperforming other major players in the field. This achieveme...

Agents | Building your first Agent step-by-step with h2oGPTe & LLM Chains

Model Selection | Routing you to the best LLM

Learn how h2oGPTe routes user queries to the best LLM based on preferences for latency, cost, or accuracy for chat and retrieval augmented generation. Welcome to Enterprise h2oGPTe, your Generative AI platform for interacting with a wide range of LLMs for chat, document question answering with Retrieval Augmented Generation, new content ...