DeepEval plugin: what it installs and how to add it

The plugin helps evaluate LLM applications such as agents, RAG pipelines and chatbots. It supports metrics for areas including answer relevancy, hallucination and task completion, along with tracing for examining model calls, tool use, retrieval and other agent steps.

Use it when you need to test AI behaviour, create evaluation datasets, inspect traces or iterate on prompts, models and application architecture. DeepEval evaluations run locally, and the plugin can connect results with Confident AI reports.

What's inside

• 3 skills: deepeval-otel, deepeval-tracing and deepeval