RetrievalOptimization

Retrieval Optimization: From Tokenization to Vector Quantization

Dear learner,

We're excited to introduce Retrieval Optimization: From Tokenization to Vector Quantization, a short course made in collaboration with Qdrant, and taught by Kacper Łukawski, its Developer Relations Lead.

In this course, you'll learn about tokenization and vector search optimization for large-scale customer-facing RAG applications. You'll learn about the technical details of how vector search works and how to optimize it for better performance.

By the end of this course, you'll have a solid understanding of how tokenization is done and how to optimize vector search in your RAG systems.

Here's what you'll learn, in detail:

• Understand the internal workings of embedding models and how your text turns into vectors.
• Explore how different tokenization techniques like Byte-Pair Encoding, WordPiece, and Unigram, work and affect search relevance.
• Learn how to measure the quality of your search across several quality metrics.
• Understand how the main parameters in HNSW, a graph-based algorithm, affect the relevance and speed of vector search and how to optimally adjust these parameters.
• Experiment with the three major quantization methods –product, scalar, and binary – and learn how they impact memory requirements, search quality, and speed.

Join in and take your RAG applications to the next level!

Details

• Learn how tokenization works in large language and embedding models and how the tokenizer can affect the quality of your search.

• Explore how different tokenization techniques including Byte-Pair Encoding, WordPiece, and Unigram are trained and work.

• Understand how to measure the quality of your retrieval and how to optimize your search by adjusting HNSW parameters and vector quantizations.

Lesson	Video	Code
Introduction	video
Embedding models	video	code
Role of the tokenizers	video	code
Practical implications of the tokenization	video	code
Measuring Search Relevance	video	code
Optimizing HNSW search	video	code
Vector quantization	video	code
Conclusion	video
Appendix - Tips and Help		code