Key Concepts

HoneyHive’s abstractions have been designed for maximal extensibility & reusability.

  1. Project: A project is a collection of data sources, models, and other resources. It is the top-level organizational unit in HoneyHive.

  2. Events: Events track the execution of different parts of your application along with related metadata, user feedback and so on.

  3. Sessions: A session is a collection of events that are related to a single user interaction with your application.

  4. Configuration: A configuration is the set of parameters that define the behavior of any component in your application - be that the model, a sub-component, or the application itself.

  5. Datapoint: A datapoint is a set of input-output pairs (along with any metadata) that are used for your models, retrievers and other components.

  6. Dataset: A dataset is a collection of datapoints that can be used in evaluation or fine-tuning or however you see fit.

  7. Evaluation Run: An evaluation run is a collection of sessions that track the execution of your application (or a part of it) against a dataset.

  8. Evaluator: An evaluator is a function (python or LLM) that’s run over your logs to evaluate the performance of your application.