Evaluations

Run code and LLM evaluations to measure performance

Run online evals in the Arize UI	Guide
Run offline evals in code	Colab Link
Evaluate code functionality	Colab Link
Evaluate hallucination	Colab Link
Evlauate human ground truth vs. AI	Colab Link
Evaluate Q&A correctness	Colab Link
Evaluate RAG	Colab Link
Evaluate reference links	Colab Link
Evaluate relevance	Colab Link
Evaluate SQL correctness	Colab Link
Evaluate tool calling	Colab Link
Evaluate toxicity	Colab Link
Evaluate user frustration	Colab Link
Handle errors with evals	Colab Link