#305 RAG 2.0 and The New Era of RAG Agents with Douwe Kiela, CEO at Contextual AI, Adjunct Professor at Stanford University, Inventor of RAG

22 snips

Jun 9, 2025

Douwe Kiela, CEO at Contextual AI and Stanford Adjunct Professor, delves into the evolution of Retrieval Augmented Generation (RAG). He debunks myths about RAG's decline, asserting its relevance in AI. The conversation highlights the integration of vector databases with large language models for high-stakes accuracy. Kiela also emphasizes the need for sophisticated RAG systems and the role of feedback loops in enhancing model performance. With AI agents on the rise, he explores their potential for dynamic reasoning, paving the way for innovative applications in various industries.

Ask episode

AI Snips

Chapters

Transcript

Episode notes

INSIGHT

RAG Is a Foundational Paradigm

Retrieval Augmented Generation (RAG) is a foundational paradigm that combines a generative AI model with retrieval from relevant data.
Despite claims, RAG is not dying; fine-tuning and long context windows complement rather than replace RAG.

INSIGHT

RAG 2.0: Integrated and State-of-the-Art

RAG 2.0 moves beyond simple coupling of parts to a fully state-of-the-art integrated system.
Its components are trained jointly for seamless interaction and improved performance.

ANECDOTE

Qualcomm’s Complex Use Case

Qualcomm's customer engineering team uses a RAG 2.0 system daily to answer complex questions.
This system handles specialist knowledge work that simple internal search cannot.

Get the Snipd Podcast app to discover more snips from this episode

Get the app

Retrieval Augmented Generation (RAG) continues to be a foundational approach in AI despite claims of its demise. While some marketing narratives suggest RAG is being replaced by fine-tuning or long context windows, these technologies are actually complementary rather than competitive. But how do you build a truly effective RAG system that delivers accurate results in high-stakes environments? What separates a basic RAG implementation from an enterprise-grade solution that can handle complex queries across disparate data sources? And with the rise of AI agents, how will RAG evolve to support more dynamic reasoning capabilities?

Douwe Kiela is the CEO and co-founder of Contextual AI, a company at the forefront of next-generation language model development. He also serves as an Adjunct Professor in Symbolic Systems at Stanford University, where he contributes to advancing the theoretical and practical understanding of AI systems.

Before founding Contextual AI, Douwe was the Head of Research at Hugging Face, where he led groundbreaking efforts in natural language processing and machine learning. Prior to that, he was a Research Scientist and Research Lead at Meta’s FAIR (Fundamental AI Research) team, where he played a pivotal role in developing Retrieval-Augmented Generation (RAG)—a paradigm-shifting innovation in AI that combines retrieval systems with generative models for more grounded and contextually aware responses.

In the episode, Richie and Douwe explore the misconceptions around the death of Retrieval Augmented Generation (RAG), the evolution to RAG 2.0, its applications in high-stakes industries, the importance of metadata and entitlements in data governance, the potential of agentic systems in enterprise settings, and much more.

Links Mentioned in the Show:

New to DataCamp?

Learn on the go using the DataCamp mobile app
Empower your business with world-class data and AI skills with DataCamp for business