dify-docs/zh/develop-plugin/features-and-specs/advanced-development/reverse-invocation-node.mdx

---
dimensions:
  type:
    primary: implementation
    detail: advanced
  level: advanced
standard_title: Reverse Invocation Node
language: en
title: 节点
description: 本文档描述了插件如何在 Dify 平台内反向调用 Chatflow/Workflow 应用节点的功能。主要涵盖两个特定节点 ParameterExtractor 和 QuestionClassifier 的调用方法。文档详细介绍了调用这两个节点的入口、接口参数和示例代码。
---

<Note> ⚠️ 本文档由 AI 自动翻译。如有任何不准确之处，请参考[英文原版](/en/develop-plugin/features-and-specs/advanced-development/reverse-invocation-node)。</Note>

反向调用节点意味着插件可以访问 Dify Chatflow/工作流应用中某些节点的能力。

`Workflow` 中的 `ParameterExtractor` 和 `QuestionClassifier` 节点封装了复杂的提示词和代码逻辑，能够通过 LLM 完成难以用硬编码解决的任务。插件可以调用这两个节点。

### 调用参数提取器节点

#### **入口**

```python
    self.session.workflow_node.parameter_extractor
```

#### **接口**

```python
    def invoke(
        self,
        parameters: list[ParameterConfig],
        model: ModelConfig,
        query: str,
        instruction: str = "",
    ) -> NodeResponse
        pass
```

其中，`parameters` 是要提取的参数列表，`model` 符合 `LLMModelConfig` 规范，`query` 是用于参数提取的源文本，`instruction` 提供 LLM 可能需要的任何附加指令。关于 `NodeResponse` 的结构，请参阅此[文档](/zh/develop-plugin/features-and-specs/plugin-types/general-specifications.mdx#noderesponse)。

#### **使用场景**

要从对话中提取人名，可以参考以下代码：

```python
from collections.abc import Generator
from dify_plugin.entities.tool import ToolInvokeMessage
from dify_plugin import Tool
from dify_plugin.entities.workflow_node import ModelConfig, ParameterConfig, NodeResponse # Assuming NodeResponse is importable

class ParameterExtractorTool(Tool):
    def _invoke(
        self, tool_parameters: dict
    ) -> Generator[ToolInvokeMessage, None, None]:
        response: NodeResponse = self.session.workflow_node.parameter_extractor.invoke(
            parameters=[
                ParameterConfig(
                    name="name",
                    description="name of the person",
                    required=True,
                    type="string",
                )
            ],
            model=ModelConfig(
                provider="langgenius/openai/openai",
                name="gpt-4o-mini",
                completion_params={},
            ),
            query="My name is John Doe",
            instruction="Extract the name of the person",
        )

        # Assuming NodeResponse has an 'outputs' attribute which is a dictionary
        extracted_name = response.outputs.get("name", "Name not found") 
        yield self.create_text_message(extracted_name)
```

### 调用问题分类器节点

#### **入口**

```python
    self.session.workflow_node.question_classifier
```

#### **接口**

```python
    def invoke(
        self,
        classes: list[ClassConfig], # Assuming ClassConfig is defined/imported
        model: ModelConfig,
        query: str,
        instruction: str = "",
    ) -> NodeResponse:
        pass
```

接口参数与 `ParameterExtractor` 一致。最终结果存储在 `NodeResponse.outputs['class_name']` 中。

{/*
Contributing Section
DO NOT edit this section!
It will be automatically generated by the script.
*/}

---

[编辑此页面](https://github.com/langgenius/dify-docs/edit/main/en/develop-plugin/features-and-specs/advanced-development/reverse-invocation-node.mdx) | [报告问题](https://github.com/langgenius/dify-docs/issues/new?template=docs.yml)