本页尚未翻译

本页内容仍为英文原文，源自官方文档 tutorials/agents/late-chunking。中文翻译正在分批进行中。

Late chunking

Retrieve whole documents first, chunk them afterwards.

Inverts the usual order: documents are retrieved first and chunked just before synthesis. Chunking late preserves context that pre-chunking discards, since a chunk is cut with knowledge of the query it is answering.

说明

This example is a runnable notebook in the vectordb-recipes repository rather than a page here.

Open in ColabRun it end to end in the browser.View on GitHubRead the source.