datahub/docs/automations/ai-docs.md
Hyejin Yoon f986315582
doc: Acryl to DataHub, datahubproject.io to datahub.com (#13252)
Co-authored-by: Jay <159848059+jayacryl@users.noreply.github.com>
2025-04-28 10:34:33 -04:00

1.7 KiB

import FeatureAvailability from '@site/src/components/FeatureAvailability';

AI Documentation

:::info

This feature is currently in closed beta. Reach out to your DataHub Cloud representative to get access.

:::

With AI-powered documentation, you can automatically generate documentation for tables and columns.

Configuring

Ensure you have edit dataset description privileges.

Once permissions are obtained, no configuration is required - just hit "Generate" on any table or column in the UI.

How it works

Generating good documentation requires a holistic understanding of the data. Information we take into account includes, but is not limited to:

  • Dataset name and any existing documentation
  • Column name, type, description, and sample values
  • Lineage relationships to upstream and downstream assets
  • Metadata about other related assets

Data privacy: Your metadata is not sent to any third-party LLMs. We use AWS Bedrock internally, which means all metadata remains within the DataHub Cloud AWS account. We do not fine-tune on customer data.

Limitations

  • This feature is not available on tables with more than 100 columns. We are working on expanding this limit.
  • This feature is powered by an LLM, which can produce inaccurate results. While we've taken steps to reduce the likelihood of hallucinations, they can still occur.