HyDE (Hypothetical Document Embeddings)

Appears in 2 tutorials

Generate a hypothetical answer, embed *it*, and search with that; the fake answer is often closer to real passages than the question.

As used in Retrieval-Augmented Generation (RAG) →

Generate a hypothetical answer, embed it, and search with that; the fake answer is often closer to real passages than the question.

As used in Vector Databases →

Embed a hypothetical LLM-written answer instead of the raw question to improve retrieval.