The AI-Powered Super IC

RAG w/o APIs: When Function Calling Talks to Your Browser

Hosted by Jason Liu and Michael Struwig

Wed, Jun 4, 2025

6:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

86 students

Invite your network

Go deeper with a course

Systematically Improving RAG Applications
Jason Liu
View syllabus

What you'll learn

Browser-Centric RAG Implementation

Students will understand how to architect RAG systems with the browser as the primary retrieval engine.

Client-Side Function Execution

Students will learn to implement function calling patterns where LLMs return instructions executed locally by clients.

WYSIWYG Data Integration for LLMs

Students will discover techniques to leverage browser-accessible data sources for more responsive AI interactions.

Why this topic matters

Client-first RAG architecture lets browsers connect AI directly to user data, enabling faster development and more secure integrations. This approach streamlines prototyping and respects data boundaries—skills crucial for building modern AI applications that work seamlessly with existing systems.

You'll learn from

Jason Liu

Consultant at the intersection of Information Retrieval and AI

Jason has built search and recommendation systems for the past 6 years. He has consulted and advised a dozens startups in the last year to improve their RAG systems. He is the creator of the Instructor Python library.

Michael Struwig

Head of AI at OpenBB

worked with

OpenBB 🦋
Stitch Fix
Meta
University of Waterloo
New York University

Learn directly from Jason Liu and Michael Struwig

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

© 2025 Maven Learning, Inc.