Text embedding and vector-based search provide great capabilities for searches based on the meaning, or sentiment, of text rather than using keywords. These techniques are often used with great effect in retrieval augmented generation in LLM based “chat with your data” solutions.

Embedding and vector searches can be used in many other scenarios besides text. If you can embed data entities to a vector of numbers, you can use a vector search to find similar entities, and this includes images, faces, sounds, video and even music.

In this demo-intensive session Alan will explore the concepts of embedding and nearest-neighbor search. The analysis and embedding of data will be explained, along with techniques to vectorize text, images and music. Alan will show how text and image embedding can be leveraged, and then show similar techniques used to create a vector search using the beat signatures in electronic dance music. This can then be used to find melodically similar beat patterns in tracks, allowing code to mix them seamlessly, creating a stunning audio experience!

Well, that’s the theory, can this work in practice?

Join this session and learn about the power and versatility of embedding and vector-based searching.

Ya’ll ready for this?