Discover data using semantic search

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

This document describes how to use project-based semantic search capabilities offered by Dataplex Search.

Semantic search, powered by Gemini, simplifies data discovery without the need for complex search syntax. It supports natural language queries, so you can search for resources using everyday language. This enhances accessibility for users with varying levels of technical expertise.

Similar to keyword search, semantic search emphasizes the discovery of resources by analyzing the metadata associated with the resources within an organization. Semantic search relies on technical metadata for data discovery. It also supports user-defined metadata, such as aspects. Semantic search focuses on enhancing recall rather than precision.

Note: You can use semantic search to search for resources only in projects where you have enabled semantic search. When you sign up for Preview, you need to specify the projects where you want to enable semantic search.

Sign up for Preview

To sign up for Preview, your Google account representative must submit a request by filling out the sign-up form. After you submit the form, the Dataplex team will contact you with next steps.

If semantic search introduces any challenges to your usage workloads or processes, provide feedback. You can send your questions and feedback to [e-mail].

Pricing

Semantic search in Dataplex is offered free of charge during Preview.

Limitations

• Only entries in the following regions are indexed. In other words, when you use semantic search, you see results only from the following regions in your projects:

  • Iowa (us-central1)
  • London (europe-west2)
  • US multi-region (us)
  • EU multi-region (eu)

• Semantic search in Dataplex is only available in the Google Cloud console.

• You can search for resources only in projects where you have enabled semantic search.

• Semantic search doesn't support time-based filters. For example, queries like Show all the tables created in the past month might not return precise results.

• Semantic search focuses only on discovering data. It doesn't address queries related to data exploration, such as Why is my sales volume down? or What are the outliers in my transactions?.

Required roles

When you search for resources in Dataplex using natural language, Dataplex automatically and seamlessly applies the same permissions you have for keyword search.

Search for resources using semantic search

1. In the Google Cloud console, go to the Dataplex Search page.

   Go to Search

2. To turn on semantic search, click the Query in natural language toggle.

3. In the search field, enter your query in natural language. The following are some sample queries:

   • Show me the datasets that contain taxi information
   • Find data on vaccine distribution across different countries
   • Get tables with historical temperature data for major US cities
   • Search for hurricane tracking and storm activity datasets
   • US population data by state

4. Review the search results.

5. Optional: To view the details of any entry in the search results, click the entry.

What's next

• Learn how to analyze with BigQuery data canvas.
• Learn how to search for resources in Dataplex using syntax and filters.