Dataiku Documentation
  • Academy
    • Join the Academy
      Benefit from guided learning opportunities →
      • Quick Starts
      • Learning Paths
      • Certifications
      • Academy Discussions
  • Community
      • Explore the Community
        Discover, share, and contribute →
      • Learn About Us
      • Ask A Question
      • What's New?
      • Discuss Dataiku
      • Using Dataiku
      • Setup And Configuration
      • General Discussion
      • Plugins & Extending Dataiku
      • Product Ideas
      • Programs
      • Frontrunner Awards
      • Dataiku Neurons
      • Community Resources
      • Community Feedback
      • User Research
  • Documentation
    • Reference Documentation
      Comprehensive specifications of Dataiku →
      • User's Guide
      • Specific Data Processing
      • Automation & Deployment
      • APIs
      • Installation & Administration
      • Other Topics
  • Knowledge
    • Knowledge Base
      Articles and tutorials on Dataiku features →
      • User Guide
      • Admin Guide
      • Dataiku Solutions
      • Dataiku Cloud
  • Developer
    • Developer Guide
      Tutorials and articles for developers and coder users →
      • Getting Started
      • Concepts and Examples
      • Tutorials
      • API Reference
  • User's Guide
  • DSS concepts
  • Connecting to data
  • Exploring data
  • The Flow
  • Data preparation
  • Visual recipes
  • Code recipes
  • Generative AI and LLM Mesh
  • AI Agents
  • Semantic Models
  • AI Assistants
    • Overview and setup
    • Flow Assistant
    • SQL Assistant
    • AI Search
      • Accessing AI Search
      • Searching for datasets & indexed tables
        • Refining a search
      • Interacting with results
    • OpenAI Codex AI coding agent
    • OpenCode AI coding agent
    • Github Copilot
    • Generate Metadata
    • Stories AI
    • AI Explain
    • Generate Steps
    • Dataiku AI Code Assistant
  • Charts
  • Schemas, storage types and meanings
  • Machine learning
  • MLOps
  • Interactive statistics
  • Code notebooks
  • Code Studios
  • Webapps
  • Collaboration
  • Dashboards
  • Workspaces
  • Stories
  • Data Catalog
  • Data Lineage
  • Dataiku Applications
  • Working with partitions
  • DSS and SQL
  • DSS and Python
  • DSS and R
  • DSS and Spark
  • Code environments
  • Specific Data Processing
  • Time Series
  • Geographic data
  • Graph
  • Text & Natural Language Processing
  • Images
  • Audio
  • Video
  • Automation & Deployment
  • Metrics, checks and Data Quality
  • Automation scenarios
  • Production deployments and bundles
  • API Node & API Deployer: Real-time APIs
  • AI Governance
  • Business Applications
  • Manufacturing Operations
  • APIs
  • Python APIs
  • R API
  • Public REST API
  • Additional APIs
  • Installation & Administration
  • Installing and setting up
  • Elastic AI computation
  • DSS in the cloud
  • DSS and Hadoop
  • Metastore catalog
  • Operating DSS
  • Security
  • User Isolation
  • Other topics
  • Plugins
  • Enterprise Asset Library
  • Streaming data
  • Formula language
  • Custom variables expansion
  • Sampling methods
  • Visualization themes
  • Accessibility
  • Troubleshooting
  • Release notes
  • Other Documentation
  • Third-party acknowledgements
Dataiku DSS
You are viewing the documentation for version 14 of DSS.
  • »
  • AI Assistants »
  • AI Search Open page in a new tab

AI Search¶

AI Search allows you to discover relevant datasets and indexed tables across the Data Catalog using natural language queries.

Accessing AI Search¶

You can access the AI Search interface from two main entry points:

  • From the Homepage: Navigate to Data Catalog > AI Search.

  • Within a Project: Navigate to Data Catalog > AI Search.

Searching for datasets & indexed tables¶

To begin a search, enter a natural language query describing the data you are looking for (e.g., “Find datasets related to financial records”).

The AI Search engine will:

  • Generate a global explanation of why the identified datasets and indexed tables are meaningful in the context of your query.

  • Display a list of up to 5 relevant datasets/indexed tables associated with your request.

Refining a search¶

You can refine your results by submitting follow-up questions or instructions. This allows you to keep the context of the previous questions without starting a new search (e.g., “Only show results as part of project X”, “Filter for datasets with the tag ‘finance’”).

The engine will then regenerate the global explanation and update the list of datasets to match your refined criteria.

Interacting with results¶

For each dataset and indexed table returned in the search results, you can open the right-hand panel to perform direct actions or use the buttons from the result tile:

  • Preview: View a sample of the dataset’s data.

  • Request share: Request access to the dataset if you do not already have the necessary permission.

  • Use: Use the dataset directly within a project.

Note

The explanations are AI-generated and, as such, are subject to errors.

Next Previous

© Copyright 2025, Dataiku

Built with Sphinx using a theme provided by Read the Docs.