Carol Chen

Unlocking the full potential of AI starts with your data, but real-world documents come in countless formats and levels of complexity. This session will give you hands-on experience with Docling, an open-source Python library designed to convert complex documents into AI-ready formats.

Building production RAG pipelines starts with a problem most teams underestimate: getting clean, structured data out of real-world documents. PDFs lose table structure, figures get separated from captions, and multi-column layouts become unreadable. Before your PyTorch models even see your data,...

What’s powering the next generation of AI breakthroughs without relying on massive amounts of human-labeled data? Synthetic data generation has emerged as a transformative approach in enhancing Large Language Models (LLMs).