ai-data-engineering

SKILL.md

Build data infrastructure for AI/ML systems including RAG pipelines, feature stores, and embedding generation. Provides architecture patterns, orchestration workflows, and evaluation metrics for production AI applications.

RAG pipelines have 5 distinct stages. Understanding this architecture is critical for production implementations.

Chunking is the most critical decision for RAG quality. Poor chunking breaks retrieval.

AI/ML 系統的數據管道、特徵存儲和嵌入生成。在構建 RAG 管道、ML 功能服務或數據轉換時使用。涵蓋特徵存儲（Feast、Tecton）、嵌入管道、分塊策略、編排（Dagster、Prefect、Airflow）、dbt 轉換、數據版本控制（LakeFS）​​​​和實驗跟踪（MLflow、W&B）。 來源：ancoleman/ai-design-components。

查看原文