检索器
¥Retrievers
retriever 是一个接口，用于根据非结构化查询返回文档。它比向量存储更通用。检索器不需要能够存储文档，只需返回（或检索）文档即可。
¥A retriever is an interface that returns documents given an unstructured query. It is more general than a vector store. A retriever does not need to be able to store documents, only to return (or retrieve) them.
检索器接受字符串查询作为输入并返回文档列表。
¥Retrievers accept a string query as input and return a list of Documents.
有关如何使用提示模板的详细信息，请参阅 相关操作指南。
¥For specifics on how to use retrievers, see the relevant how-to guides here.
请注意，所有 向量存储 都可以是 转换为检索器。有关可用的向量存储检索器，请参阅向量存储 集成文档。
¥Note that all vector stores can be cast to retrievers. Refer to the vector store integration docs for available vector store retrievers.
如果你想编写自己的检索器，请参阅 此操作指南。如果你想贡献集成，请参阅 贡献集成。
¥If you'd like to write your own retriever, see this how-to. If you'd like to contribute an integration, see Contributing integrations.
所有检索器
¥All retrievers
| Name | Description |
|---|---|
| ArxivRetriever | arxivretriever} |
| Azion EdgeSQL | 概述 |
| Chaindesk Retriever | chaindesk-retriever} |
| Dria Retriever | dria-retriever} |
| HyDE 检索器 | hyde-retriever} |
| Metal Retriever | metal-retriever} |
| Supabase 混合搜索 | supabase-hybrid-search} |
| 时间加权检索器 | time-weighted-retriever} |
| Vespa Retriever | vespa-retriever} |
| Zep 云检索器 | zep-cloud-retriever} |
| Zep 开源检索器 | zep-open-source-retriever} |