Updated May 8, 2024

h2oGPT is a suite of components designed to facilitate the deployment and utilization of large language models (LLMs), specifically leveraging the power of the GPT architecture. The components included in the suite are a large language model, an embedding model, a database for document embeddings, and a graphical user interface. h2oGPT enables users to harness the capabilities of advanced language models for a variety of applications, from text generation to sentiment analysis. It maintains control over your data and ensures privacy while still having access to powerful language processing capabilities. This product offers commercially usable code, data, and models. It supports several types of documents including plain text (.txt), comma-separated values (.csv), Word (.docx and .doc), PDF, Markdown (.md), HTML, EPUB, and email files (.eml and .msg).

You can deploy h2oGPT in your Nebius AI Managed Service for Kubernetes clusters using this Marketplace product.

Deployment instructions

Before installing this product:

  1. Create a Kubernetes cluster and a node group in it.
  2. Install kubectl and configure it to work with the created cluster.
  3. If you want to use h2oGPT with GPUs and have them in your node group, install the NVIDIA® GPU Operator on the cluster.

To install the product:

  1. Click the button in this card to go to the cluster selection form.

  2. Select your cluster and click Continue.

  3. Configure the application:

    • Namespace: Select a namespace or create one.
    • Application name: Enter an application name.
    • Persistent volume size in Gb: Enter the size of a persistent volume that h2oGPT will create for cache and other files.
  4. Click Install.

  5. Wait for the application to change its status to Deployed.

  6. To check that h2oGPT is working, access its UI:

    1. Set up port forwarding:

      kubectl -n <namespace> port-forward \
        service/h2ogpt-web 8080:80
    2. Go to http://localhost:8080/ in your web browser.

Billing type
Kubernetes® Application
LLM apps framework
Use cases
  • Text generation for chatbots, virtual assistants, and content creation.

  • Sentiment analysis and opinion mining for social media monitoring and customer feedback analysis.

  • Text summarization and document clustering for information retrieval and organization.

  • Question answering systems for knowledge management and customer support automation.

  • Natural language understanding for contextual understanding and semantic analysis.

  • Dialog systems for interactive user experiences and conversational interfaces.

  • Text classification and categorization for content moderation and information filtering.

  • Language modeling for text completion and predictive typing applications.

  • Speech recognition and transcription for audio-to-text conversion and voice-enabled applications.

Technical support

Nebius AI does not provide technical support for the product. If you have any issues, please refer to the developer’s information resources.

Product composition
Helm chartVersion
Docker imageVersion
By using this product you agree to the Nebius AI Marketplace Terms of Service and the terms and conditions of the following software: Apache 2.0
Billing type
Kubernetes® Application
LLM apps framework