Preprocessing Unstructured Data for LLMs and RAG Systems
Completed by Laurent Dellmann
August 7, 2025
5 hours (approximately)
Laurent Dellmann's account is verified. Coursera certifies their successful completion of Preprocessing Unstructured Data for LLMs and RAG Systems
What you will learn
Master techniques for preprocessing unstructured data for LLMs and RAG systems.
Extract and normalize data from complex document types like PDFs and HTML.
Implement semantic similarity and metadata extraction using vector databases.
Build a RAG system to dynamically interact with your preprocessed data.
Skills you will gain
- Category: Embeddings
- Category: Vector Databases
- Category: Vision Transformer (ViT)
- Category: LangChain
- Category: Retrieval-Augmented Generation
- Category: LLM Application
- Category: Data Quality
- Category: Application Frameworks

