h2oGPT integration

H2O Driverless AI features integration with h2oGPT that lets you optionally generate and view dataset or experiment results summaries using a GPT model. These options let you easily explain the results of complex experiments and datasets and help you share the insights and implications of your experiments and data in a more convenient manner.

Note: For information about H2O.ai’s enterprise generative AI solution, see the Enterprise h2oGPTe documentation and https://h2o.ai/platform/enterprise-h2ogpte/.

The following sections describe how to enable and use GPT-related options in H2O Driverless AI.

Description of relevant configuration options

The following are descriptions of the relevant configuration options when enabling h2oGPT integration.

  • enable_gpt: Specify whether to enable GPT functionality. By default, this option is set to False. (Note that if the openai_api_secret_key configuration option is provided, then the OpenAI API is used.)

  • h2ogpt_url: Specify your h2oGPT endpoint. Note that for some h2oGPT URLs, specifying an h2oGPT key with the h2ogpt_key configuration option is required to enable authorized access for GPT-related tasks. (Optional: OpenAI can also be used if you explicitly opt-in to set this configuration option to OpenAI’s API key with openai_api_secret_key.)

  • h2ogpt_key: Specify an h2oGPT key. For some h2oGPT URLs, specifying an h2oGPT key is required to enable authorized access for GPT-related tasks.

  • h2ogpt_model_name: Specify a model to use based on its name from the list provided by the h2oGPT client. If the provided name doesn’t match any model names in the list, the first model is chosen by default.

GPT summaries

The following subsections describe how to generate and view summaries for datasets and experiment results.

Summarize datasets

  1. Ensure that GPT functionality is enabled by setting enable_gpt=true.

  2. Ensure that the relevant configuration options have been set correctly. For more information, see Description of relevant configuration options.

  3. In the main navigation, click Datasets to go to the Datasets page.

  4. Click Click for Actions next to the dataset you want to generate a summary for.

  5. From the list of options, select Summarize.

Summarize experiment results

  1. Ensure that GPT functionality is enabled by setting enable_gpt=true.

  2. Ensure that the relevant configuration options have been set correctly. For more information, see Description of relevant configuration options.

  3. In the main navigation, click Experiments to go to the Experiments page.

  4. For the completed experiment that you want to generate a summary of, click Extra > Summarize in the list of experiment options.