HyDE: Hypothetical Document Embeddings for RAG
Vector search fails when a short question looks nothing like its answer. HyDE has an LLM draft a fake answer, embeds that, and retrieves against it instead.
Vector search fails when a short question looks nothing like its answer. HyDE has an LLM draft a fake answer, embeds that, and retrieves against it instead.
Chunking a document for RAG strips each piece of its context. Contextual retrieval adds an LLM-written note to every chunk before you index it.