DeepEval

A Python library that adds LLM evaluation assertions directly into pytest test suites. Instead of a separate YAML config (like Promptfoo), you write eval checks as Python test functions using familiar pytest patterns.

Best suited for teams already using pytest who want to add LLM quality checks without adopting a new tool or workflow.

See also

• Promptfoo — alternative (YAML/CLI-first approach)
• Prompt Evaluation — the concepts these tools implement