"I don't use RAG, I just retrieve documents"

Hosted by Benjamin Clavié and Hamel Husain

Wed, Jun 25, 2025

12:30 AM UTC (30 minutes)

Virtual (Zoom)

Free to join

138 students

Invite your network

Go deeper with a course

AI Evals For Engineers & PMs
Hamel Husain and Shreya Shankar
View syllabus

What you'll learn

Understand The Limitations of vector search

Discover why RAG is more alive than ever, but simple cosine similarity is no longer enough.

Survey the many retrieval tools at your disposal

Find out about the many other tools that can be used to retrieve information.

Learn About The New Developments in Neural Retrieval

Vector search having limitations does not mean deep learning has hit a wall: let's learn about the exciting new stuff.

Why this topic matters

They say RAG is dead, but is it really? Its killer, “agentic search”, has become the hot new way to Retrieve relevant context. In this session, we’ll discuss the greatly exaggerated rumours of RAG’s demise. We will discuss (long-known) limitations of “vector search”, the vast array of existing tools, and, finally, new approaches researchers are uncovering for retrieval.

You'll learn from

Benjamin Clavié

R&D ML Engineer, currently working at Answer.AI

Benjamin is an R&D ML Engineer, currently working at Answer.AI. His interests are focused on NLP and, especially, Information Retrieval. He has been involved in multiple projects with a focus on broadening the access to state-of-the-art retrieval methods, such as RAGatouille and the rerankers library. Recently, Ben also co-led the ModernBERT project, which has modernized the widely used BERT backbone. Previously, Ben has worked at legaltech companies LexisNexis and Jus Mundi, and he’s currently interested in exploring the new possibilities that LLMs open up for retrieval.

Hamel Husain

ML Engineer with 20 years of experience

Hamel is a machine learning engineer with over 20 years of experience. He has worked with innovative companies such as Airbnb and GitHub, which included early LLM research used by OpenAI, for code understanding. He has also led and contributed to numerous popular open-source machine-learning tools. Hamel is currently an independent consultant helping companies build AI products.

Learn directly from Benjamin Clavié and Hamel Husain

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.