Datasets

Datasets are the entrypoint to LLM evaluation. Datasets can consist of inputs (prompts), gold labels (correct answers) and additional metadata.

There are multiple ways to use datasets in Patronus:

• Upload datasets: You can upload your own datasets to start using them in evaluations. We support flexible schema mapping to accommodate all data schemas.
• Local datasets: Our experimentation framework supports ingesting data locally, directly from CSV or JSONL files.
• Patronus datasets: These are off-the-shelf datasets you can use in your application to get started covering general use cases such as toxic inputs.