dbt Semantic Layer and LLMs

Text-to-sql is a hard challenge to solve. However, when you can use the dbt Semantic Layer to write that SQL, the odds of getting accurate results increase significantly.

Comment

Inspiration

  • The outcome of an application like this aligns incredibly well with the mandate of most data teams I work with - empower stakeholders by providing them with the data they need, in a medium they can consume, all while considering aspects of trust, governance, and accuracy
  • The accuracy component is the very unique value proposition of an application like this relative to any other solution out there that purports to write SQL from a text prompt (check out some early benchmarks here). The reason for that is we’re not asking the LLM to write a SQL query, which is prone to hallucinating tables, columns, or just SQL that’s not valid. Instead, it generates a highly structured MetricFlow request. MetricFlow is the underlying piece of technology in the semantic layer that will translate that request to SQL based on the semantics you’ve defined in your dbt project.
  • If I’m being honest, it’s also an incredibly valuable tool to show our customers and prospects!

What it does

The application uses dbt Cloud’s Semantic Layer alongside Snowflake Cortex and Streamlit to power a natural language interface that enables users to retrieve data from their Snowflake platforms by simply asking questions like “What is total revenue by month in 2024?”.

How we built it

Diagram

Built With

Share this project:

Updates