The engine is modular, allowing different implementations of core components to be plugged in. It is designed to be easy to set up and use with major data warehouses, and it improves with usage. Users can connect to their data warehouses, add context about the data to the engine, and query the data in natural language. The engine supports connections to PostGres, BigQuery, Databricks, and Snowflake. The project is open-source and open to contributions.
Key takeaways:
- Dataherald is a natural language-to-SQL engine that allows users to query structured data in natural language.
- The engine is modular, allowing different implementations of core components to be plugged-in, and is designed to be easy to set up and use with major data warehouses.
- Users can connect to their data warehouses, add context about the data to the engine, and query the data in natural language.
- Dataherald is an open-source project and welcomes contributions in the form of new features, improved infrastructure, or better documentation.