Free Lesson
Modern Multi-Vector Code Search
60 min
Dec 11, 2025 1:00 PM
Virtual (Zoom)
In this video
What you'll learn
What makes semantic search work for code?
What's the technical difference between todays semantic search and a "standard" hybrid search + reranker from last year
What is "multi-vector" search and semantic chunking?
Learn the latest architectures and how a "single" vector per chunk is replaced with "multiple" for better search
Why wasn't multi-vector done before?
Learn the challenges of a multi-vector search and how extreme quantization with clustering is done to make it possible
Why this topic matters
Mixedbread showed in their launch how much faster/better semantic search could make Claude code. Cursor also just announced semantic embedding support, and other agents are soon to follow. I got better quality with 1/2 tokens and almost 2x faster with mixedbread search.
Learn what changed from the leading researchers in the space.
You'll learn from
.jpg&w=384&q=75)
Aamir Shakir
Founder of Mixedbread

Isaac Flath
Dev-efficiency and AI expert; Elite AI-Assisted Coding co-instructor
.png&w=1536&q=75)