Overview
Datasets are collections of datapoints which represent input-output pairs for an LLM call.
Datasets are collections of datapoints which represent input-output pairs for an LLM call.
Datasets are pre-defined collections of input-output pairs that you can use within Humanloop to define fixed examples for your projects.
A datapoint consists of three things:
{{ variables }} you define in the prompt template.target with whatever fields are necessary to help you specify the intended behaviour. You can then use our evaluations feature to run the necessary code to compare the actual generated output with your target data to determine whether the result was as expected.
Datasets can be created via CSV upload, converting from existing Logs in your project, or by API requests.