Labels

• async

  Async/await patterns
• bug

  Unexpected behavior or incorrect evaluation results
• chore

  Maintenance tasks, tooling, and dependencies
• cli

  CLI commands
• core

  Fundamental architecture and base classes
• dataset

  Synthetic data generation and test set management
• docs

  Technical documentation, examples, and docstrings
• evaluator

  Evaluator implementation
• feat

  New functionality or capability
• infra

  CI/CD pipelines, Docker, and PyPI publishing
• judge

  LLM judge implementation
• pytest

  RagaliQ pytest plugin and integration logic
• refactor

  Code improvement without changing behavior
• report

  Output formatting: HTML, JSON, and terminal visuals
• research

  Exploring new RAG evaluation papers or methods
• testing

  Testing infrastructure