摘要链节点#
¥Summarization Chain node
使用摘要链节点汇总多个文档。
¥Use the Summarization Chain node to summarize multiple documents.
本页提供摘要链节点的参数以及更多资源的链接。
¥On this page, you'll find the node parameters for the Summarization Chain node, and links to more resources.
节点参数#
¥Node parameters
在“要汇总的数据”中选择要汇总的数据类型。你选择的数据类型决定了其他节点参数。
¥Choose the type of data you need to summarize in Data to Summarize. The data type you choose determines the other node parameters.
- 使用节点输入(JSON)和节点输入(二进制):汇总来自工作流的节点数据。
¥Use Node Input (JSON) and Use Node Input (Binary): summarize the data coming into the node from the workflow.
-
你可以配置分块策略:选择用于定义数据块大小的策略。
¥You can configure the Chunking Strategy: choose what strategy to use to define the data chunk sizes.
- 如果选择“简单(定义如下)”,则可以设置“每块字符数”和“块重叠(字符)”。
¥If you choose Simple (Define Below) you can then set Characters Per Chunk and Chunk Overlap (Characters).
- 如果需要连接提供更多配置选项的拆分器子节点,请选择“高级”。
¥Choose Advanced if you want to connect a splitter sub-node that provides more configuration options.
-
使用文档加载器:汇总文档加载器子节点提供的数据。
¥Use Document Loader: summarize data provided by a document loader sub-node.
节点选项#
¥Node Options
你可以配置摘要方法和提示。选择“添加选项”>“汇总方法和提示”。
¥You can configure the summarization method and prompts. Select Add Option > Summarization Method and Prompts.
汇总方法中的选项:
¥Options in Summarization Method:
- MapReduce:这是推荐选项。在 LangChain 文档中了解更多关于 MapReduce 的信息。
¥Map Reduce: this is the recommended option. Learn more about Map Reduce in the LangChain documentation.
- 优化:在 LangChain 文档中了解更多关于 优化搜索 的信息。
¥Refine: learn more about Refine in the LangChain documentation.
- 内容:在 LangChain 文档中了解更多关于 其他 的信息。
¥Stuff: learn more about Stuff in the LangChain documentation.
你可以自定义“单个摘要提示”和“最终合并提示”。节点中包含示例。你必须包含 "{text}" 占位符。
¥You can customize the Individual Summary Prompts and the Final Prompt to Combine. There are examples in the node. You must include the "{text}" placeholder.
模板和示例#
¥Templates and examples
相关资源#
¥Related resources
有关服务的更多信息,请参阅 LangChain 的摘要文档。
¥Refer to LangChain's documentation on summarization for more information about the service.
View n8n's Advanced AI documentation.