Gllm Evals

This documentation covers the Gllm Evals library, which is part of the GLLM Monorepo.

API Reference

The following modules are available in this library:

• Constant: Constants for the gllm_evals package.
• Constants
• Dataset: Dataset module for loading and managing evaluation datasets.
• Evaluate: Evaluate Module.
• Evaluator: Evaluator module for orchestrating evaluation workflows.
• Experiment Tracker: Experiment tracker module for logging and tracking evaluation experiments.
• Judge: Judge module for multiple LLM evaluation and ensemble calculation.
• Metrics: Metrics module for evaluating AI model outputs.
• Prompts
• Runner: Runner module for executing batch evaluation workflows.
• Simple Runner: Runner class for evaluating datasets.
• Types: Types for the evaluator.
• Utils