Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 8 additions & 2 deletions docs-website/sidebars.js
Original file line number Diff line number Diff line change
Expand Up @@ -136,6 +136,12 @@ module.exports = {
type: "category",
collapsed: true,
items: [
{
label: "Ask DataHub",
type: "doc",
id: "docs/features/feature-guides/ask-datahub",
className: "saasOnly",
},
{
label: "Documentation Propagation",
type: "doc",
Expand Down Expand Up @@ -213,12 +219,12 @@ module.exports = {
],
},
{
label: "Custom Asset Summaries",
label: "Asset Summaries",
type: "doc",
id: "docs/features/feature-guides/custom-asset-summaries",
},
{
label: "Custom Home Page",
label: "Home Page",
type: "doc",
id: "docs/features/feature-guides/custom-home-page",
},
Expand Down
14 changes: 13 additions & 1 deletion docs/automations/ai-docs.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ With AI-powered documentation, you can automatically generate documentation for

## Prerequisites

As of DataHub Cloud v0.3.12, AI documentation is in public beta. Admins (or users with the "Manage Platform Settings" privilege) can enable it from settings.
As of DataHub Cloud v0.3.12, AI documentation is in **Public Beta**. Admins (or users with the "Manage Platform Settings" privilege) can enable it from settings.

<p align="center">
<img width="70%" src="https://raw.githubusercontent.com/datahub-project/static-assets/main/imgs/automation/saas/ai-docs/ai-docs-toggle.png"/>
Expand All @@ -28,6 +28,18 @@ All AI-generated documentation that has not been reviewed by a human will be mar
<img width="70%" src="https://raw.githubusercontent.com/datahub-project/static-assets/main/imgs/automation/saas/ai-docs/ai-docs-generation.gif"/>
</p>

### Customize Documentation Generation

As of v0.3.15, you can customize how documentation is generated by providing custom instructions that are passed to the underlying AI model when generating dcumentation for any Table or Column. This is useful if you want AI-generated documentation to follow specific guidelines or standards set by your organization.

To provide custom instructions for documentation generation, start by navigating to **Settings > AI**. Then simply provide custom instructions in the **AI Documentation > Instructions** input.

<p align="center">
<img width="70%" src="https://raw.githubusercontent.com/datahub-project/static-assets/main/imgs/saas/ai/add_custom_prompts_docs.png"/>
</p>

Note that after updating instructions, it may take up to 5 minutes for the new instructions to take effect.

## How it works

Generating good documentation requires a holistic understanding of the data. Information we take into account includes, but is not limited to:
Expand Down
14 changes: 13 additions & 1 deletion docs/automations/ai-term-suggestion.md
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@ This automation can:

- A business glossary with terms defined. Additional metadata, like documentation and existing term assignments, will improve the accuracy of our suggestions.

## Configuring
## Usage

1. **Navigate to Automations**: Click on 'Govern' > 'Automations' in the navigation bar.

Expand All @@ -52,6 +52,18 @@ This automation can:
<img width="70%" src="https://raw.githubusercontent.com/datahub-project/static-assets/main/imgs/automation/saas/ai-term-suggestion/term-proposals.png"/>
</p>

### Customize AI Classification Generation

As of v0.3.15, you can customize how classification recommendations are generated by providing custom instructions that are passed to the underlying AI model when generating classification decisions for any Table or Column. This is useful if you want AI-generated classification to follow specific guidelines or standards set by your organization.

To provide custom instructions for AI classification generation, simply provide them in the Custom Instruction input when creating the AI classification automation.

<p align="center">
<img width="70%" src="https://raw.githubusercontent.com/datahub-project/static-assets/main/imgs/saas/ai/add_custom_prompts_classification.png"/>
</p>

Note that after updating instructions, it may take up to 5 minutes for the new instructions to take effect.

## How it works

The automation will scan through all the datasets matched by the configured filters. For each one, it will generate suggestions.
Expand Down
127 changes: 127 additions & 0 deletions docs/features/feature-guides/ask-datahub.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,127 @@
import FeatureAvailability from '@site/src/components/FeatureAvailability';

# Ask DataHub

<FeatureAvailability saasOnly />

**Ask DataHub** is DataHub's conversational AI assistant that brings intelligent, context-aware help directly to where you work. Using Ask DataHub, you can ask questions about your organization's metadata and get instant, accurate answers about your data landscape.

## What Can Ask DataHub Do?

Ask DataHub empowers your organization to navigate & understand your entire data ecosystem with ease.

Key capabilities include:

### Natural Language Search

Search for data assets using plain English instead of memorizing exact table names or technical identifiers. Ask DataHub understands context and synonyms to help you find what you need.

### Find Trustworthy Data

Discover high-quality, reliable data assets based on usage patterns, documentation quality, ownership information, and data quality metrics. Ask DataHub helps you identify the most authoritative sources for your analysis.

### Impact Analysis

Quickly assess how changes to a data asset will ripple through your organization. Ask DataHub can trace lineage and identify all downstream dependencies, helping you make informed decisions before making changes.

### Understand Social and Organizational Context

Get insights into the human side of your data:

- **Ownership**: Find out who owns and maintains specific assets
- **Expertise**: Identify domain experts and frequent users
- **Collaboration**: Understand which teams work with particular datasets
- **History**: Learn about past usage patterns and organizational knowledge

### Assess Data Quality

Quickly understand the health and reliability of your data assets:

- View assertion results and data quality scores
- Understand freshness and validation status
- Identify potential issues before using data
- Get context on historical quality trends

### Write SQL Queries

Generate first-draft SQL queries to answer specific analytical questions, accelerating your data exploration and analysis workflows.

## Where You Can Use Ask DataHub

## Getting Started

To start using Ask DataHub:

1. **In Slack or Teams**: Simply mention @DataHub followed by your question in any channel or chat
2. **Enable the feature**: As of DataHub Cloud v0.3.13, Ask DataHub is in public beta and can be enabled in Settings → AI
3. **Start asking questions**: Try queries like:
- "What tables contain customer email data?"
- "Who owns the sales_facts table?"
- "What would break if I change the orders table schema?"
- "Find me the most reliable revenue datasets"
- "Show me tables with data quality issues"

### Slack

Ask DataHub is available in Slack by mentioning @DataHub in any channel. This brings DataHub's intelligence directly into your team conversations.

Learn more: [Ask DataHub in Slack](../../managed-datahub/slack/saas-slack-app.md#ask-datahub-in-slack)

### Microsoft Teams

Similarly, you can use Ask DataHub in Microsoft Teams by mentioning @DataHub in channels and chats.

Learn more: [Ask DataHub in Teams](../../managed-datahub/teams/saas-teams-app.md#ask-datahub-in-slack)

### DataHub UI

Ask DataHub is coming soon to the DataHub UI, providing seamless access to AI assistance while browsing your data catalog.

Ask DataHub is currently available in the DataHub UI as part of a private beta. If you're interested in enabling this feature, please reach out to your DataHub representative.

## Customize Ask DataHub

As of v0.3.15, you can customize how Ask DataHub responds to queries by configuring custom instructions. These are injected into AI context to tailor the AI assistant's behavior to match your organization's specific needs, terminology, and guidelines.

### Configuring Custom Instructions

To configure custom instructions:

1. Navigate to **Settings > AI** in your DataHub instance
2. Locate the **Ask DataHub** section
3. Enter your custom instructions in the **Instructions** field

That's it!

<p align="center">
<img width="70%" src="https://raw.githubusercontent.com/datahub-project/static-assets/main/imgs/saas/ai/add_custom_prompts_chat.png"/>
</p>

Custom base prompts can be used to:

- Define response style and tone
- Define organization specific terminology or terms
- Guide the model on how to navigate Glossary Terms, Tags, Domains, and properties.
- Guide the assistant toward specific of recommendations (e.g. helping differentiate production over staging assets)

### Default Organization View

By default, Ask DataHub applies your organization's default **Search View** (if one is set). This means the assistant will prioritize finding assets from a narrower set of assets, enabling it to separate the signal from the noise by default.

This ensures that Ask DataHub's responses are always relevant to your team's specific data landscape, without requiring additional filtering in your queries.

:::info Note
After updating custom prompts or organization view settings, it may take up to 5 minutes for changes to take effect.
:::

## How It Works

Ask DataHub leverages your complete metadata graph to provide intelligent, context-aware responses. The AI assistant considers:

- Asset names, descriptions, and documentation
- Lineage relationships (upstream and downstream)
- Ownership and domain information
- Usage patterns and popularity metrics
- Data quality and assertion results
- Tags, glossary terms, and classifications
- Schema information and sample values
20 changes: 10 additions & 10 deletions docs/features/feature-guides/custom-asset-summaries.md
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
---
title: Custom Asset Summaries
title: Asset Summaries
---

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

# Custom Asset Summaries
# Asset Summaries

<FeatureAvailability saasOnly />

DataHub's **Custom Asset Summaries** enable organizations to create tailored, curated discovery experiences for their most important logical assets by customizing the Summary tab view that users see when browsing Domains, Data Products, Glossary Terms, and Glossary Term Groups.
DataHub's **Asset Summaries** enable organizations to create tailored, curated discovery experiences for their most important logical assets by customizing the Summary tab view that users see when browsing Domains, Data Products, Glossary Terms, and Glossary Term Groups.

<p align="center">
<img
Expand All @@ -18,23 +18,23 @@ DataHub's **Custom Asset Summaries** enable organizations to create tailored, cu
</p>

:::info Supported Asset Types
Custom Asset Summaries are currently supported for **Domains, Data Products, Glossary Terms, and Glossary Term Groups only**. These logical asset types help organize and group your physical data assets within DataHub.
Asset Summaries are currently supported for **Domains, Data Products, Glossary Terms, and Glossary Term Groups only**. These logical asset types help organize and group your physical data assets within DataHub.
:::

## Why Use Custom Asset Summaries?
## Why Use Asset Summaries?

Custom Asset Summaries transform how your team discovers and navigates key organizational assets by enabling you to:
Asset Summaries transform how your team discovers and navigates key organizational assets by enabling you to:

- **Improve Asset Discoverability**: Highlight the most relevant information about your domains, data products, and glossary terms right on the Summary tab
- **Create Owner-Driven Experiences**: Asset owners can curate what information is most important for their users to see
- **Reduce Navigation Time**: Surface key details, documentation, and related assets without requiring users to click through multiple tabs
- **Standardize Asset Presentation**: Ensure consistent, professional presentation of your most important organizational constructs

Whether you're a domain owner wanting to highlight key data products, a data product manager showcasing important assets, or a data steward organizing glossary terms, Custom Asset Summaries put the most relevant information front and center.
Whether you're a domain owner wanting to highlight key data products, a data product manager showcasing important assets, or a data steward organizing glossary terms, Asset Summaries put the most relevant information front and center.

## What's Included

Custom Asset Summaries consist of three customizable sections that you can tailor to your asset's specific needs:
Asset Summaries consist of three customizable sections that you can tailor to your asset's specific needs:

### Summary Page Header

Expand Down Expand Up @@ -167,11 +167,11 @@ When customizing your Asset Summaries:

## Next Steps

Now that you understand Custom Asset Summaries:
Now that you understand Asset Summaries:

1. **Start with high-traffic assets**: Begin by customizing the Summary pages for your most frequently accessed domains and data products
2. **Gather feedback**: Ask users what information would be most helpful to see on Summary pages
3. **Iterate based on usage**: Monitor how users interact with your customized summaries and adjust accordingly
4. **Scale thoughtfully**: Apply learnings from your initial customizations to other assets in your organization

Custom Asset Summaries are designed to evolve with your organization's needs, providing the flexibility to create discovery experiences that truly serve your users while maintaining the structure that makes DataHub powerful.
Asset Summaries are designed to evolve with your organization's needs, providing the flexibility to create discovery experiences that truly serve your users while maintaining the structure that makes DataHub powerful.
16 changes: 8 additions & 8 deletions docs/features/feature-guides/custom-home-page.md
Original file line number Diff line number Diff line change
@@ -1,14 +1,14 @@
---
title: Custom Home Page
title: Home Page
---

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

# Custom Home Page
# Home Page

<FeatureAvailability saasOnly />

DataHub's **Custom Home Page** empowers organizations and individual users to create personalized, modular home page experiences that put the most relevant data assets and information front and center.
DataHub's **Home Page** empowers organizations and individual users to create personalized, modular home page experiences that put the most relevant data assets and information front and center.

<p align="center">
<img
Expand All @@ -17,20 +17,20 @@ DataHub's **Custom Home Page** empowers organizations and individual users to cr
alt="Default custom home page"/>
</p>

## Why Use the Custom Home Page?
## Why Use the Home Page?

The Custom Home Page transforms how your team interacts with DataHub by enabling you to:
The Home Page transforms how your team interacts with DataHub by enabling you to:

- **Reduce Time to Insight**: Surface the most critical data assets, domains, and resources directly on your home page for instant access
- **Personalize Your Workflow**: Create a home page experience tailored to your specific role, projects, and data needs
- **Improve Data Discoverability**: Highlight important collections, documentation, and quick links that help your team find what they need faster
- **Standardize Organization Views**: Administrators can create consistent default experiences while still allowing individual customization

Whether you're a data analyst who needs quick access to specific dashboards, a data engineer focused on particular domains, or an administrator wanting to promote data governance resources, the Custom Home Page adapts to your workflow.
Whether you're a data analyst who needs quick access to specific dashboards, a data engineer focused on particular domains, or an administrator wanting to promote data governance resources, the Home Page adapts to your workflow.

## What's Included

The Custom Home Page consists of **modules** that you can arrange in rows of up to 3 modules each. You can choose from:
The Home Page consists of **modules** that you can arrange in rows of up to 3 modules each. You can choose from:

### Default Modules

Expand Down Expand Up @@ -206,7 +206,7 @@ Now that you understand how to customize your home page experience:
3. **Gather feedback**: If you're an administrator, ask users what they'd find most valuable on the default home page
4. **Iterate over time**: Home page needs may change as your team and data landscape evolve

The Custom Home Page is designed to grow with your organization's needs, providing both the flexibility for individual workflows and the consistency that administrators need to promote important resources and best practices.
The Home Page is designed to grow with your organization's needs, providing both the flexibility for individual workflows and the consistency that administrators need to promote important resources and best practices.

## Relevant APIs

Expand Down
2 changes: 1 addition & 1 deletion docs/managed-datahub/slack/saas-slack-app.md
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ The integration enables your team to:
The Slack App makes data discovery easier and more accessible, by making DataHub available where you work.
Learn more about [how to set up the Slack app](./saas-slack-setup.md) or [how to troubleshoot issues](./saas-slack-troubleshoot.md).

## Ask DataHub
## Ask DataHub in Slack

**Ask DataHub** is DataHub's conversational AI assistant. In Slack, you can mention @DataHub in any channel to ask questions about your metadata.

Expand Down
Loading