AI engineering glossary · RAG vector search
What is hyDE?
HyDE (also called Hypothetical document embeddings): Hypothetical Document Embeddings: a model first writes a plausible, possibly imperfect, answer to the question, and that text is embedded and used as the search query. Answer-like text tends to sit closer to real answer passages than a short question does.
HyDE: an example
For 'Why is my Wi-Fi slow at night?', the system generates a short paragraph about congestion and searches with its embedding.
Related terms
More RAG vector search terms
- Index refresh
- Ingestion pipeline
- Inverted index
- IVF
- Knowledge base
- Knowledge graph
- Late interaction
- Layout-aware parsing
Where you learn it
HyDE is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.