Natural Language Search on Semi-Structured Data

Lightning Lessons

Practical skills & tools to accelerate your career

Building AI-Native Products

Natural Language Search on Semi-Structured Data

Hosted by Jason Liu and Daniel Svonava

Wed, Jun 18, 2025

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

Learn directly from undefined

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

412 students

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

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

Wed, Jun 18, 2025

5:00 PM UTC (1 hour)

Virtual (Zoom)

Free to join

412 students

Invite your network

Go deeper with a course

Systematically Improving RAG Applications

Jason Liu

View syllabus

What you'll learn

Encoder Stacking Fundamentals

Students will learn how to combine encoders to build models that understand both text and metadata.

Real-World Implementation Strategies

Students will learn practical deployment techniques for encoder stacking in search and recommendation systems.

Metadata Integration Beyond Basics

Students will learn when to use encoder stacking over traditional metadata approaches.

Why this topic matters

Understanding encoder stacking transforms how AI systems process unified data. This skill helps engineers build smarter search and recommendation systems that truly grasp context. Mastering this technique enables professionals to create more accurate solutions—giving them a competitive edge in building next-generation information retrieval systems.

You'll learn from

Jason Liu

Consultant at the intersection of Informational 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.

Daniel Svonava

CEO at Superlinked

Daniel is the CEO & co-founder of Superlinked.com, an open source framework and ML infrastructure platform for building intelligent search, personalization and analytics experiences with vector embeddings that combine structured and unstructured data. Previously, Daniel was an ML Tech Lead at YouTube, where he built ads forecasting infrastructure that powered the buying flows of $10B/y-worth of ads.

Worked with