Preprocessing Unstructured Data for LLMs and RAG Systems

In this 3-hour course, delve into the intricacies of preprocessing unstructured data for large language models (LLMs) and Retrieval-Augmented Generation (RAG) systems. Gain hands-on experience setting up environments, handling diverse document formats like PDFs and HTML, and building intelligent data pipelines by implementing advanced data extraction and normalization techniques.

What I will be able to do after this course

• Set up a development environment tailored for processing unstructured data.
• Apply preprocessing techniques to PDFs, HTML, and PPTX documents for AI pipelines.
• Normalize and chunk data for integration with LLMs and RAG systems.
• Extract metadata and analyze semantic features from documents.
• Build an end-to-end Retrieval-Augmented Generation system for enhanced data interaction.

Course Instructor(s)

Paulo Dichone is a seasoned instructor with expertise in machine learning and AI systems, who focuses on explaining complex concepts in an easy-to-understand manner. With exceptional teaching experience and a strong technical background, Paulo delivers practical insights, ensuring learners can directly apply new skills in real-world scenarios.

Who is it for?

This course is designed for AI developers, data scientists, and machine learning engineers aiming to enhance their expertise in preprocessing unstructured data. Learners should have basic Python programming knowledge, familiarity with APIs, and a foundational understanding of machine learning.