外观
本页尚未翻译
本页内容仍为英文原文，源自官方文档 tutorials/agents/hyde。中文翻译正在分批进行中。
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.
说明
This example is a runnable notebook in the vectordb-recipes repository rather than a page here.