Design-time planning
Advisors can help produce JSON plans, column tags, and realism reports that can be reviewed before generation.
from great_generator import generate_plan
plan = generate_plan(schema=schema, advisor="none")Advisor-reviewed planning
Optional AI advisor layer
The advisor layer is optional. The default generation path does not require model calls.
Great Generator creates synthetic data. It does not anonymize, mask, de-identify, or transform production records.
Deterministic generation
Generated data can consume saved plans so teams can review and reuse generation intent across tests and demos.
Boundary
Advisor support is not required for the base package and should not be treated as production-data anonymization or privacy transformation.
Related documentation
Keep exploring
Installation optionsInstall Great Generator for core Pandas workflows, Spark, Delta Lake, optional AI advisors, or the optional local MCP server.
Generate synthetic data from schemasCreate synthetic test data from schema strings, dictionaries, Pandas DataFrames, and Spark schemas using semantic field detection.
Query-aware synthetic dataGenerate synthetic data with required values, partition coverage, selectivity targets, and join coverage for SQL and data engineering tests.
Optional local MCP serverInstall the optional Great Generator MCP server so compatible AI assistants can call schema generation, DDL parsing, relational generation, coverage validation, and local export tools.
GitHub repositorySource code, issues, releases, and project history.
PyPI packageInstall Great Generator from Python Package Index.