Regression testing and CI for models

Where it is assessed

4 assessed items, 0 done.

• AIE-102 M6.4 Evals in CI · tier 3
• AIE-102 M6.5 Break it on purpose · tier 1
• AIE-102 M6.6 Retention: regression and observability practice · tier 1
• AIE-102 M7.1c Evaluation report: publish · tier 3

Verified sources

• Designing Machine Learning Systems
• LLM Bootcamp - Spring 2023 · The Full Stack
• LLMOps (LLM Bootcamp) · The Full Stack
• confident-ai/deepeval
• EleutherAI/lm-evaluation-harness
• promptfoo/promptfoo
• How to Build and Evaluate AI systems in the Age of LLMs · DataTalksClub ⬛