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 Synthetic Generation

Notebook	Description
Tabular Fine Tuning with Differential Privacy	Generate secure, high-quality synthetic numeric, categorical, time-sequences, and text using Tabular Fine-Tuning and Differential Privacy tools.
Synthesizing Private Patient Data	Create privacy-safe synthetic patient data with Gretel, ensuring compliance, secure sharing, and actionable insights for AI and machine learning in healthcare.
Generate Differentially Private Synthetic Text	Safely leverage sensitive or proprietary text data for advanced language model training and fine-tuning
Detect and redact PII in free text	Ensure data quality and privacy by applying flexible de-identification and rule-based transformations to real and synthetic datasets.
Operationalize synthetic data generation	Create pipelines that connect to your data sources, automate, and operationalize synthetic data generation

Data Designer

Note: The Data Designer functionality demonstrated in this notebook is currently in Preview. To access these features, please join the waitlist.

Notebook	Description
Structured Outputs	Use structured outputs feature to generate synthetic data with complex, nested data structures, with support for both Pydantic and JSON schema definitions.
Synthesize Evaluation Sets	Synthetically generate a high-quality and diverse evaluation set for measuring the quality of your agent.
Multi-turn Chat	Create multi-turn user-assistant dialogues tailored for fine-tuning language models.
Sample-to-Dataset	Use the sample-to-dataset workflow to create diverse, large-scale synthetic datasets tailored to your needs with nothing but a few samples
Text-to-Code	Create a synthetic data generation pipeline for Python code examples.
Text-to-SQL	Create a synthetic data generation pipeline for natural language prompts and SQL code examples.
Question & Answer Generation	Synthetically generate and evaluate high-quality pairs from text and PDFs, and evaluate the quality and diversity of outputs.

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

Other

Notebook	Description
Generate and edit data from a prompt	Use Gretel's Navigator SDK to generate or edit tabular data from a user-provided prompt.
Time-series with DoppleGANger	Generate synthetic daily oil price data using the DoppelGANger GAN for time-series data.