Langflow 简单使用

2025年8月18日3

AI 生成的摘要

安装和运行Langflow的步骤如下： 1. 使用命令 `pip install langflow -U` 安装Langflow。 2. 运行命令 `langflow run --env-file .env` 启动应用。 `.env` 文件的配置内容包括： - `LANGFLOW_AUTO_LOGIN=False` - `LANGFLOW_SUPERUSER=admin` - `LANGFLOW_SUPERUSER_PASSWORD=password` - `LANGFLOW_SECRET_KEY=secret_key` - `LANGFLOW_NEW_USER_IS_ACTIVE=False` - `LANGFLOW_CONFIG_DIR=./config` 自定义Python代码组件示例： ```python from langflow.field_typing import Data from langflow.custom import Component from langflow.io import MessageTextInput, Output from langflow.schema import Data class CustomComponent(Component): display_name = "ParseChatResponse" description = "用作创建自定义组件的模板。" documentation: str = "https://dmentx.github.io/law-langflow/components-custom-components" icon = "custom_components" name = "CustomComponent" inputs = [ MessageTextInput(name="input_value", display_name="输入值", value="Hello, World!"), ] outputs = [ Output(display_name="输出", name="output", method="build_output"), ] def build_output(self) -> Data: data = Data(text=self.input_value, character="vtuber") self.status = data return data ``` 此组件接收输入并生成输出。

安装#

uv pip install langflow -U

运行#

uv run langflow run --env-file .env

.env 配置

LANGFLOW_AUTO_LOGIN=False
LANGFLOW_SUPERUSER=admin
LANGFLOW_SUPERUSER_PASSWORD=password
LANGFLOW_SECRET_KEY=secret_key
LANGFLOW_NEW_USER_IS_ACTIVE=False
LANGFLOW_CONFIG_DIR=./config

自定义 python 代码组件#

# from langflow.field_typing import Data
from langflow.custom import Component
from langflow.io import MessageTextInput, Output
from langflow.schema import Data


class CustomComponent(Component):
    display_name = "ParseChatResponse"
    description = "Use as a template to create your own component."
    documentation: str = "https://dmentx.github.io/law-langflow/components-custom-components"
    icon = "custom_components"
    name = "CustomComponent"

    inputs = [
        MessageTextInput(name="input_value", display_name="Input Value", value="Hello, World!"),
    ]

    outputs = [
        Output(display_name="Output", name="output", method="build_output"),
    ]

    def build_output(self) -> Data:
        data = Data(text=self.input_value, character="vtuber")
        self.status = data
        return data