Abstract
Prepare data for LLM applications with Data Prep Kit, an open-source toolkit for cleansing, transforming, and enriching unstructured data. This talk introduces the toolkit through practical examples and a demo, connecting data preparation to the needs of LLM and retrieval-augmented generation (RAG) applications.
Who it’s for
Developers and data practitioners working on LLM or RAG applications who want an introduction to preparing unstructured data with Data Prep Kit.
What you’ll learn
- Understand the role of data preparation in LLM and RAG applications.
- Explore cleansing, transformation, and enrichment of unstructured data.
- See how Data Prep Kit supports a practical data preparation workflow.
- Find code examples to continue exploring after the session.
Format / duration
- Format: Talk + demo.
- Duration: 90 mins to 120 mins, adaptable to event format
Resources
- Video: Session recording on Airmeet
- Slides: Not currently linked.
- Code: Code and examples