Use Case Examples

Notebooks for common Gretel use cases.

Follow along with these use cases to familiarize yourself with core Gretel features. These examples provide a starting point for common use cases which you can modify to suit your specific needs.

To help decide which approach may be best for you, you can use this flow chart.

Safe Synthetics

Notebook	Description
Create GDPR-ready synthetic customer data	Develop privacy-protected synthetic versions of customer datasets containing personal identifiers. Transform sensitive fields and generate realistic synthetic data that maintains analytical utility while implementing GDPR privacy principles.
Synthesize HIPAA-protected healthcare data	Apply safeguards to healthcare datasets designed for HIPAA requirements while maintaining data utility for analysis and model training.
Redact & synthesize free text with maximum privacy	Use Transform and Text Fine-Tuning with Differential Privacy to protect your free text data.

Data Designer

Notebook	Description
Getting started with Data Designer	This comprehensive introduction to Gretel's Data Designer will walk you through the essential concepts and techniques you need to generate high-quality synthetic data for your projects. Whether you need test data for development, synthetic data for privacy protection, or training data for AI models, Data Designer provides a flexible and powerful solution.
Create Text to Code datasets	Create high-quality synthetic datasets that pair natural language instructions with corresponding code implementations. These instruction-code pairs are essential for training and fine-tuning coding assistants that can accurately translate user requests into executable code. This blueprint showcases how to create synthetic datasets for code generation in both Python and SQL contexts.
Create an evaluation dataset for your RAG application	Create tailored evaluation datasets for your Retrieval-Augmented Generation systems with Gretel Data Designer. This blueprint helps you generate domain-specific reference documents, queries, and ground truth answers that match your real-world use cases and evaluation needs
Use realistic personal details to add diversity to a dataset	Create datasets with realistic personal details. Gretel’s person sampler can generate demographically accurate data for US persons that can boost the quality and diversity of your datasets.
Create a multi-turn chat dataset to train a chatbot	Create multi-turn user-assistant dialogues tailored for fine-tuning language models.
Generate a dataset of realistic physicians notes	Use a combination of numerical samplers, personal details, and LLM generated data to create a physicians notes dataset.
Accelerate your development using the Magic library	Data Designer’s magic library can accelerate your development through LLM generated prompts, categories, or configs.

Partner Integrations

Notebook	Description	Partner
Fine-tuning for Function Calling	Use Gretel Navigator on Amazon Bedrock to create safe, scalable synthetic data for training AI to understand and execute tool commands.	AWS
Gretel Navigator on Azure AI	How to use Gretel Navigator on Azure AI Model-as-a-Service. Model card.	Azure
Fine-tuning Models for Healthcare	How to safely fine-tune LLMs on sensitive medical text for healthcare AI applications using Gretel and Amazon Bedrock	AWS
Privacy-First RAG Chatbot	Enhance finance chatbots with privacy-first synthetic data using Gretel and Databricks to boost performance while ensuring compliance with privacy regulations.	Databricks
RAG Model Evaluation	Create an end-to-end RAG chatbot and synthetic evals using Gretel and Azure AI Studio	Azure
Create private synthetic data in BigQuery	A practical guide to synthetic data generation with Gretel and Google BigQuery DataFrames	Google