Vector Podcast Trey Grainger - Wormhole Vectors
11 snips
Nov 7, 2025 
Trey Grainger, lead author of "AI Powered Search" and founder of Search Kernel, dives into the cutting-edge concept of Wormhole Vectors. He explains how these vectors interconnect various types of data spaces, enhancing hybrid search capabilities. Trey simplifies complex ideas, detailing behavioral embeddings derived from user interactions and the roles of semantic knowledge graphs. He shares practical applications and innovative methods to combine dense and sparse vectors, all while emphasizing the transformative potential of wormholes in search technology.
AI Snips
Chapters
Books
Transcript
Episode notes
Wormhole Vectors Enable Cross‑Space Hops
- Wormhole vectors map a document set from one vector space into a query vector for another space, enabling traversal between spaces.
- You can hop back and forth to collect documents and exploit different signal types (lexical, semantic, behavioral).
Create Sparse→Dense Wormholes By Pooling
- To go from sparse to dense, run a keyword search, take the top-K documents and average their embeddings.
- Use the pooled embedding as a dense-space query to find semantically related items lacking the keywords.
Translate Dense Results Into Lexical Queries
- To go from dense to sparse, derive a lexical query via a semantic knowledge graph traversal over the matched document set.
- Use the inverted/forward index relationships to produce readable term queries representing that dense region.
