Improving retrievers by Reranking and embedding fine-tuning
Hosted by Jason Liu and Ayush Chaurasia
What you'll learn
Reranking Fundamentals
Master reranker architecture and implementation to effectively boost retrieval accuracy beyond embedding models alone.
Strategic Model Fine-tuning
Apply practical criteria for deciding when to fine-tune embeddings vs. implementing rerankers based on use case demands.
Performance Optimization
Evaluate deployment tradeoffs to select optimal reranking and embedding approaches for various hardware environments.
Why this topic matters
Mastering reranking and embedding fine-tuning helps you build retrieval systems that deliver genuinely relevant results, not just basic search. These skills let you optimize for accuracy, speed, and cost—making you valuable for developing production-ready AI applications that outperform competitors.
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.
Ayush Chaurasia
ML Engineer @ LanceDB
Worked with
Go deeper with a course
Keep exploring