This example is a runnable notebook in the
vectordb-recipes repository rather than a page here.
Open in Colab
Run it end to end in the browser.
View on GitHub
Read the source.
RAG
HyDE: hypothetical document embeddings
Generate a hypothetical answer, then retrieve documents similar to it.
An LLM writes a hypothetical document answering the query, and that document,
not the query, is embedded and used for retrieval. It works because a
plausible answer sits nearer the real answers in embedding space than a question
does.
Was this page helpful?