容器化 Langflow 应用程序

在可视化编辑器中设计流程只是构建使用 Langflow 的应用程序的第一步。

一旦您有了一个功能性的流程，您就可以在更大的应用程序中使用该流程，例如网站或移动应用。 由于 Langflow 既是 IDE 又是运行时，您可以使用 Langflow 在本地构建和测试流程，然后在生产环境中打包和提供流程。

本指南介绍了使用 Langflow 进行应用程序开发，从项目设置到打包和部署。 本文档不介绍如何编写完整的应用程序；它只描述如何在更大的应用程序上下文中包含 Langflow。

项目结构

以下示例描述了最小化 Langflow 应用程序的项目目录结构：

_10

LANGFLOW-APPLICATION/

_10

├── docker.env

_10

├── Dockerfile

_10

├── flows/

_10

│ ├── flow1.json

_10

│ └── flow2.json

_10

├── langflow-config-dir/

_10

├── README.md

此项目目录包含以下内容：

• docker.env：此文件作为 .env 文件复制到 Docker 镜像的容器根目录中。
• Dockerfile：此文件控制您的 Langflow 镜像的构建方式。
• /flows：此文件夹保存您要托管的流程，即您的应用程序使用的流程。
• /langflow-config-dir：此文件夹在 Dockerfile 中被引用作为 Langflow 部署的配置文件、数据库和日志的位置。
• README.md：这是您的应用程序文档的典型 README 文件。

这是 Langflow 应用程序项目目录的最小化示例。 您的应用程序可能有额外的文件和文件夹，例如用于自定义组件的 /components 文件夹，或用于额外依赖项的 pyproject.toml 文件。

包管理

基础 Langflow Docker 镜像包含 Langflow 核心依赖项，因为它使用 langflowai/langflow:latest 作为父镜像。

如果您的应用程序需要额外的依赖项，请为额外的依赖项创建一个 pyproject.toml 文件。 有关更多信息，请参阅安装自定义依赖项。

要将具有额外依赖项的应用程序部署到 Docker，您必须将 pyproject.toml 和 uv.lock 文件复制到 Docker 镜像。 为此，请将以下内容添加到您的 Langflow 应用程序的 Dockerfile 中：

_10

COPY pyproject.toml uv.lock /app/

环境变量

docker.env 文件是加载到 Docker 镜像中的 .env 文件。 它包含控制 Langflow 行为的环境变量，例如身份验证、数据库存储、API 密钥和服务器配置。 例如：

_10

LANGFLOW_AUTO_LOGIN=true

_10

LANGFLOW_SAVE_DB_IN_CONFIG_DIR=true

_10

LANGFLOW_BASE_URL=http://0.0.0.0:7860

_10

OPENAI_API_KEY=sk-...

您包含的具体值取决于您的应用程序需求以及您希望如何配置 Langflow。 有关更多信息，请参阅 Langflow 环境变量和全局变量。

您也可以在 Dockerfile 中设置环境变量。 但是，如果您在 docker.env 和 Dockerfile 中都设置了环境变量，Langflow 会使用 docker.env 中设置的值。

密钥

为了简化，Langflow 文档中的示例可能会直接引用 API 密钥和其他敏感值。 在您自己的应用程序中，您应始终遵循管理密钥的行业最佳实践，例如使用环境变量或密钥管理工具。

有关生成身份验证密钥和在 Langflow 中管理密钥的信息，请参阅身份验证。

存储

默认情况下，Langflow 使用 SQLite 数据库进行存储。 如果您更喜欢使用 PostgreSQL，请参阅配置外部 PostgreSQL 数据库。

有关存储（包括缓存和内存）的更多信息，请参阅内存管理选项。

流程

您的本地 Langflow 实例可能有用于不同应用程序的多个流程。 当您将 Langflow 打包为应用程序的依赖项时，您只想包含您的应用程序使用的流程。

1. 导出流程，这些流程与您的应用程序相关。

   如果您有链式流程（触发其他流程的流程），请确保您导出 所有 必要的流程。

2. 将导出的 Langflow JSON 文件添加到项目目录中的 /flows 文件夹。

组件

您在 Langflow 可视化编辑器中看到的核心组件和包会自动包含在基础 Langflow Docker 镜像中。

如果您为应用程序创建了任何自定义组件，您必须在项目目录中包含这些组件：

1. 在项目目录中创建一个 /components 文件夹。
2. 将自定义组件文件添加到 /components 文件夹。
3. 在 docker.env 中指定 /components 的路径。

Langflow Dockerfile

The Dockerfile determines how your Langflow image is built, including the dependencies, flows, components, and configuration files.

At minimum, you need to specify the base Langflow image, create the necessary folders in the container, copy folders and files to the container, and provide a startup command.

_29

# Use the latest version of the base Langflow image

_29

FROM langflowai/langflow:latest

_29

_29

# Create folders and set the working directory in the container

_29

RUN mkdir /app/flows

_29

RUN mkdir /app/langflow-config-dir

_29

WORKDIR /app

_29

_29

# Copy flows, langflow-config-dir, and docker.env to the container

_29

COPY flows /app/flows

_29

COPY langflow-config-dir /app/langflow-config-dir

_29

COPY docker.env /app/.env

_29

_29

# Optional: Copy custom components to the container

_29

COPY components /app/components

_29

_29

# Optional: Use custom dependencies

_29

COPY pyproject.toml uv.lock /app/

_29

_29

# Set environment variables if not set in docker.env

_29

ENV PYTHONPATH=/app

_29

ENV LANGFLOW_LOAD_FLOWS_PATH=/app/flows

_29

ENV LANGFLOW_CONFIG_DIR=/app/langflow-config-dir

_29

ENV LANGFLOW_COMPONENTS_PATH=/app/components

_29

ENV LANGFLOW_LOG_ENV=container

_29

_29

# Command to run the Langflow server on port 7860

_29

EXPOSE 7860

_29

CMD ["langflow", "run", "--backend-only", "--env-file","/app/.env","--host", "0.0.0.0", "--port", "7860"]

The environment variables set directly in this Dockerfile specify resource paths for Langflow. If these variables are also set in docker.env, the values in docker.env override the values set in the Dockerfile.

In this example, ENV LANGFLOW_LOG_ENV=container sets the logging behavior for serialized JSON to stdout to track the application's behavior in a containerized environment. For more information, see Logging.

Backend-only mode

The --backend-only flag in CMD starts Langflow in backend-only mode, which provides programmatic access only. This is recommended when running Langflow as a dependency of an application where you don't need access to the Langflow UI.

If you want to serve the visual editor and the Langflow backend, omit --backend-only.

For more information, see Deploy Langflow on Docker.

Test your Langflow Docker image

Build and run your Langflow Docker image to test it.

This example runs the container locally. For information about publishing your image on Docker Hub and running a Langflow container remotely, see Deploy to Docker Hub and Kubernetes.

1. Build the Docker image:

   
   

   _10

   docker build -t langflow-pokedex:1.2.0 .

   
   

2. Run the Docker container to start your Langflow server:

   
   

   _10

   docker run -p 7860:7860 langflow-pokedex:1.2.0

   
   

3. To confirm that the container is serving your flows as expected, use the Langflow API to run a flow:

   1. Open one of the JSON files in your application's /flows folder, and then find the flow's id in the additional metadata and project information.

      There are many id values; make sure you get the ID for the entire flow, not the ID for an individual component. If your flow is complex, try searching for the flow's name, which is typically near the flow's id.

      
      

      _10

      "name": "Basic Prompting",

      _10

      "description": "Perform basic prompting with an OpenAI model.",

      _10

      "id": "e4167236-938f-4aca-845b-21de3f399858",

      
      

   2. Send a POST request to the /v1/run/$FLOW_ID endpoint using the flow ID from the previous step .

      The following example runs a simple LLM chat flow that responds to a chat input string. If necessary, modify the payload for your flow. For example, if your flow doesn't have a Chat input component, you must modify the payload to provide the expected input for your flow.

      
      

      _10

      curl --request POST \

      _10

      --url 'http://localhost:7860/api/v1/run/e4167236-938f-4aca-845b-21de3f399858?stream=true' \

      _10

      --header 'Content-Type: application/json' \

      _10

      --data '{

      _10

      "input_value": "Tell me about Charizard.",

      _10

      "output_type": "chat",

      _10

      "input_type": "chat",

      _10

      "session_id": "charizard_test_request"

      _10

      }'

      
      
      About this example

      This command runs the Pokédex template flow. It provides chat input about a specific Pokémon, uses an optional custom session_id, and enables response streaming with ?stream=true.

      The default session ID is the flow ID. Custom session IDs can help isolate unique conversation threads to keep the LLM's context clean, and they can help identify specific conversations in flow logs to make debugging easier.

      This command uses response streaming because the Pokédex flow can return a large amount of text. To use batching, set ?stream=false.

   3. Verify that the request succeeds and the response is valid, depending on the specific flow you ran.

      This confirms that your Langflow Docker image is correctly configured and this flow is accessible through the Langflow API server that is hosted on the container. When you build and test your entire application stack, your front-end application can use Langflow API requests to trigger the flows served by your Langflow container in the same way you manually tested the flow in the previous step.

      This example triggered a flow by sending chat input to the /v1/run/$FLOW_ID endpoint. For more examples of flow triggers, see Trigger flows with webhooks and the tutorial to Create a chatbot that can ingest files.

Deploy to Docker Hub and Kubernetes

When you're ready to share your application with the world, you need to serve Langflow in a production environment. For more information about deploying Langflow, see the following:

• Learn about Langflow deployments
• Deploy Langflow on Docker
• Deploy your application to Kubernetes