A key challenge when working with AI models is to ensure that the information generated by the model is relevant, timely and context-sensitive. Retrieval-Augmented Generation (RAG) is a technique to achieve this, where generative AI models are linked with additional relevant data sources to improve the accuracy of answers generated by the model. To address this challenge, Dagger for Data Pipelines can help build a consistent and reliable pipeline that delivers data to RAG models. Dagger Functions encapsulate all the workflows that make up a data pipeline, ensuring consistency across operating systems and environments. The framework includes tools such as LlamaIndex, which provides an easy-to-use example of how to link generative AI models with additional relevant data sources. Using Dagger ensures that your data pipeline always works consistently, benefits from caching, and accelerates pipeline runs significantly. Benefits include interacting with multiple tools and processes using containers and clean Python code, exposing a clean API to different pipeline functions, benefiting from tooling and best practices, and running the same way every time unaffected by environment differences or operating system variability.