### Docker Compose Up Output Example

Source: https://docs.dify.ai/zh/self-host/quick-start/docker-compose

This output shows the status of each container as it starts up. It includes network creation and individual service container status.

```text
[+] Running 13/13
✔ Network docker_ssrf_proxy_network  Created                                                                10.0s 
✔ Network docker_default             Created                                                                 0.1s 
✔ Container docker-sandbox-1         Started                                                                 0.3s 
✔ Container docker-db_postgres-1     Healthy                                                                 2.8s 
✔ Container docker-web-1             Started                                                                 0.3s 
✔ Container docker-redis-1           Started                                                                 0.3s 
✔ Container docker-ssrf_proxy-1      Started                                                                 0.4s 
✔ Container docker-weaviate-1        Started                                                                 0.3s 
✔ Container docker-worker_beat-1     Started                                                                 3.2s 
✔ Container docker-api-1             Started                                                                 3.2s 
✔ Container docker-worker-1          Started                                                                 3.2s 
✔ Container docker-plugin_daemon-1   Started                                                                 3.2s 
✔ Container docker-nginx-1           Started                                                                 3.4s 

```

--------------------------------

### Start the Web Service

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Launch the web service after building. This command starts the Next.js development server.

```bash
pnpm start
```

--------------------------------

### Example .env.local Configuration

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Create a .env.local file and populate it with these example environment variables. Adjust values according to your deployment needs, especially NEXT_PUBLIC_API_PREFIX and NEXT_PUBLIC_PUBLIC_API_PREFIX.

```dotenv
# For production release, change this to PRODUCTION
NEXT_PUBLIC_DEPLOY_ENV=DEVELOPMENT

# The deployment edition, SELF_HOSTED or CLOUD
NEXT_PUBLIC_EDITION=SELF_HOSTED

# The base URL of console application, refers to the Console base URL of WEB service if console domain is different from api or web app domain.
# example: http://cloud.dify.ai/console/api
NEXT_PUBLIC_API_PREFIX=http://localhost:5001/console/api

# The URL for Web APP, refers to the Web App base URL of WEB service if web app domain is different from console or api domain.
# example: http://udify.app/api
NEXT_PUBLIC_PUBLIC_API_PREFIX=http://localhost:5001/api

# When the frontend and backend run on different subdomains, set NEXT_PUBLIC_COOKIE_DOMAIN=1.
NEXT_PUBLIC_COOKIE_DOMAIN=

# SENTRY
NEXT_PUBLIC_SENTRY_DSN=
NEXT_PUBLIC_SENTRY_ORG=
NEXT_PUBLIC_SENTRY_PROJECT=
```

--------------------------------

### Install Web Service Dependencies

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Install all necessary project dependencies using PNPM. The --frozen-lockfile flag ensures that the exact versions specified in the lockfile are installed.

```bash
pnpm install --frozen-lockfile
```

--------------------------------

### Install Specific Dify Version with Git

Source: https://docs.dify.ai/zh/self-host/quick-start/faqs

Use the `--branch` flag with `git clone` to install a specific version of Dify. Ensure the rest of the setup follows the latest version's instructions.

```bash
git clone https://github.com/langgenius/dify.git --branch 0.15.3
```

--------------------------------

### Install Plugin Dependencies

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-md-exporter

Install the necessary Python dependencies for your plugin using the provided `requirements.txt` file.

```bash
pip install -r requirements.txt
```

--------------------------------

### Python FastAPI Code Example

Source: https://docs.dify.ai/zh/use-dify/workspace/api-extension/api-extension

A practical code example using Python's FastAPI framework to implement the API extension, including dependency installation, code structure, and service startup instructions.

```APIDOC
## Python FastAPI Code Example

This code example is based on the Python FastAPI framework.

### 1. Install Dependencies

```bash
pip install fastapi[all] uvicorn
```

### 2. Write Code According to API Specification

```python
from fastapi import FastAPI, Body, HTTPException, Header
from pydantic import BaseModel

app = FastAPI()


class InputData(BaseModel):
    point: str
    params: dict = {}


@app.post("/api/dify/receive")
async def dify_receive(data: InputData = Body(...), authorization: str = Header(None)):
    """
    Receive API query data from Dify.
    """
    expected_api_key = "123456"  # TODO Your API key of this API
    auth_scheme, _, api_key = authorization.partition(' ')

    if auth_scheme.lower() != "bearer" or api_key != expected_api_key:
        raise HTTPException(status_code=401, detail="Unauthorized")

    point = data.point

    # for debug
    print(f"point: {point}")

    if point == "ping":
        return {
            "result": "pong"
        }
    if point == "app.external_data_tool.query":
        return handle_app_external_data_tool_query(params=data.params)
    # elif point == "{point name}":
        # TODO other point implementation here

    raise HTTPException(status_code=400, detail="Not implemented")


def handle_app_external_data_tool_query(params: dict):
    app_id = params.get("app_id")
    tool_variable = params.get("tool_variable")
    inputs = params.get("inputs")
    query = params.get("query")

    # for debug
    print(f"app_id: {app_id}")
    print(f"tool_variable: {tool_variable}")
    print(f"inputs: {inputs}")
    print(f"query: {query}")

    # TODO your external data tool query implementation here, 
    #  return must be a dict with key "result", and the value is the query result
    if inputs.get("location") == "London":
        return {
            "result": "City: London\nTemperature: 10°C\nRealFeel®: 8°C\nAir Quality: Poor\nWind Direction: ENE\nWind "
                      "Speed: 8 km/h\nWind Gusts: 14 km/h\nPrecipitation: Light rain"
        }
    else:
        return {"result": "Unknown city"}
```

### 3. Start the API Service

The API service will run on port 8000 by default. The complete API address is `http://127.0.0.1:8000/api/dify/receive`. The configured API Key is `123456`.

```bash
uvicorn main:app --reload --host 0.0.0.0
```

### 4. Configure the API in Dify

Configure this API within Dify.

### 5. Select the API Extension in the App

Choose this API extension within your Dify App.

**App Debugging:**

When debugging an app, Dify will send requests to the configured API with the following example payload:

```json
{
    "point": "app.external_data_tool.query",
    "params": {
        "app_id": "61248ab4-1125-45be-ae32-0ce91334d021",
        "tool_variable": "weather_retrieve",
        "inputs": {
            "location": "London"
        },
        "query": "How's the weather today?"
    }
}
```

The API response will be:

```json
{
    "result": "City: London\nTemperature: 10°C\nRealFeel®: 8°C\nAir Quality: Poor\nWind Direction: ENE\nWind Speed: 8 km/h\nWind Gusts: 14 km/h\nPrecipitation: Light rain"
}
```
```

--------------------------------

### Navigate to Web Directory

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Change your current directory to the 'web' folder to proceed with the setup.

```bash
cd web
```

--------------------------------

### Copy Example .env File

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-md-exporter

Copy the example environment file to `.env` to configure your Dify debugging environment. Ensure you fill in your specific Dify environment details.

```bash
cp .env.example .env
```

--------------------------------

### Basic Plugin Manifest Example

Source: https://docs.dify.ai/zh/develop-plugin/features-and-specs/plugin-types/plugin-info-by-manifest

This is a fundamental example of a plugin's manifest file. It outlines essential plugin metadata and configurations.

```yaml
version: 0.0.1
type: "plugin"
author: "Yeuoly"
name: "neko"
label:
  en_US: "Neko"
created_at: "2024-07-12T08:03:44.658609186Z"
icon: "icon.svg"
resource:
  memory: 1048576
  permission:
    tool:
      enabled: true
    model:
      enabled: true
      llm: true
    endpoint:
      enabled: true
    app:
      enabled: true
    storage:
      enabled: true
      size: 1048576
plugins:
  endpoints:
    - "provider/neko.yaml"
meta:
  version: 0.0.1
  arch:
    - "amd64"
    - "arm64"
  runner:
    language: "python"
    version: "3.12"
    entrypoint: "main"
privacy: "./privacy.md"

```

--------------------------------

### Install API Service Dependencies with uv

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Install the required dependencies for the API service using `uv`. For macOS users, ensure `libmagic` is installed via Homebrew.

```bash
uv sync --dev
```

--------------------------------

### Install PNPM using npm

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Use this command to globally install PNPM if you have npm available.

```bash
npm i -g pnpm
```

--------------------------------

### Install FFmpeg on Ubuntu

Source: https://docs.dify.ai/zh/self-host/troubleshooting/integrations

Install FFmpeg on Ubuntu using apt-get. This is required for OpenAI Text-to-Speech (TTS) audio stream segmentation.

```bash
sudo apt-get update
sudo apt-get install ffmpeg
```

--------------------------------

### Create Custom Environment File

Source: https://docs.dify.ai/zh/self-host/quick-start/docker-compose

To configure specific settings, such as for vector stores like Milvus, copy the example environment file and rename it. This allows for customization without altering the original example file. Ensure you are in the `dify/docker` directory before running this command.

```bash
cd dify/docker
cp envs/vectorstores/milvus.env.example envs/vectorstores/milvus.env
```

--------------------------------

### Install Dify CLI on Mac

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-flomo-plugin

Use Homebrew to tap the Dify repository and install the CLI tool.

```bash
brew tap langgenius/dify
brew install dify
```

--------------------------------

### Install Dependencies for Schema Migration

Source: https://docs.dify.ai/zh/self-host/troubleshooting/weaviate-v4-migration

Installs the necessary Python packages (weaviate-client and requests) for the schema migration script. It's recommended to do this within a temporary virtual environment.

```bash
cd /path/to/dify
python3 -m venv weaviate_migration_env
source weaviate_migration_env/bin/activate
pip install weaviate-client requests
```

--------------------------------

### External Data Tool Example

Source: https://docs.dify.ai/zh/use-dify/workspace/api-extension/api-extension

This example demonstrates how to use the external data tool to fetch weather information for a specific region, which can then be used as context.

```APIDOC
## External Data Tool Example

This section provides an example for the external data tool, where the scenario is to get external weather information based on a region to serve as context.

### API Example

#### Endpoint
`POST https://fake-domain.com/api/dify/receive`

#### Headers
```
Content-Type: application/json
Authorization: Bearer 123456
```

#### Request Body
```json
{
    "point": "app.external_data_tool.query",
    "params": {
        "app_id": "61248ab4-1125-45be-ae32-0ce91334d021",
        "tool_variable": "weather_retrieve",
        "inputs": {
            "location": "London"
        },
        "query": "How's the weather today?"
    }
}
```

#### API Response
```json
{
    "result": "City: London\nTemperature: 10°C\nRealFeel®: 8°C\nAir Quality: Poor\nWind Direction: ENE\nWind Speed: 8 km/h\nWind Gusts: 14 km/h\nPrecipitation: Light rain"
}
```
```

--------------------------------

### Pull New Docker Images and Start Services

Source: https://docs.dify.ai/zh/self-host/platform-guides/dify-premium

Pull the latest Docker images for Dify and start the services using Docker Compose. This completes the upgrade process.

```bash
docker compose pull
docker compose -f docker-compose.yaml -f docker-compose.override.yaml up -d
```

--------------------------------

### Run FastAPI Application

Source: https://docs.dify.ai/zh/use-dify/workspace/api-extension/api-extension

Command to start the FastAPI development server using uvicorn, making the API accessible.

```bash
uvicorn main:app --reload --host 0.0.0.0
```

--------------------------------

### Start Dify Services with Docker Compose

Source: https://docs.dify.ai/zh/self-host/quick-start/docker-compose

Launch all Dify services, including core components and dependencies, in detached mode. Ensure you have Docker Compose version 2.24.0 or higher installed.

```bash
docker compose up -d
```

--------------------------------

### Prepare API Service Environment Variables

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Navigate to the 'api' directory and prepare the environment variables for the API service by copying the example file. Adjust `COOKIE_DOMAIN` if frontend and backend are on different subdomains.

```bash
cd api

cp .env.example .env
```

--------------------------------

### JavaScript with External Libraries (Lodash)

Source: https://docs.dify.ai/zh/use-dify/nodes/code

Example of using external JavaScript libraries like Lodash for utility functions. Ensure these libraries are available in your Dify installation's sandbox environment.

```javascript
// JavaScript: Import lodash, moment, etc.
const _ = require('lodash');

function main(data) {
    return { unique: _.uniq(data) };
}
```

--------------------------------

### Python with External Libraries (NumPy, Pandas)

Source: https://docs.dify.ai/zh/use-dify/nodes/code

Example of using external Python libraries like NumPy and Pandas for data manipulation. Ensure these libraries are available in your Dify installation's sandbox environment.

```python
# Python: Import numpy, pandas, requests, etc.
import numpy as np
import pandas as pd

def main(data: list) -> dict:
    df = pd.DataFrame(data)
    return {'mean': float(np.mean(df['values']))}
```

--------------------------------

### Initialize Bundle Plugin Project

Source: https://docs.dify.ai/zh/develop-plugin/features-and-specs/advanced-development/bundle

Run this command to create a new Bundle plugin project. Ensure you have the Dify plugin scaffold tool and Python 3.12 installed.

```bash
./dify-plugin-darwin-arm64 bundle init
```

```bash
dify bundle init
```

--------------------------------

### Structure Extraction Prompt for LLM Node

Source: https://docs.dify.ai/zh/use-dify/tutorials/article-reader

This prompt guides the LLM to parse article content, extract its structure, and summarize key information. It specifies the task, requirements, output format, and provides an example.

```text
阅读以下文章内容并执行任务
{{文档提取器结果的变量}}
# 任务

- **主要目标**：全面解析文章的结构。
- **目标**：详细说明文章每个部分的内容。
- **要求**：尽可能详细地分析。
- **限制**：无特别的格式限制，但需要保持解析的条理性和逻辑性。
- **预期输出**：文章结构的详细解析，包括每个部分的主要内容和作用。

# 推理顺序

- **推理部分**：通过仔细阅读文章，识别和解析其结构。
- **结论部分**：提供每个部分的具体内容和作用。

# 输出格式

- **解析格式**：每个部分应以标题形式列出，后跟对该部分内容的详细说明。
- **结构形式**：Markdown，以增强可读性。
- **具体说明**：每个部分的内容和作用，包括但不限于引言、正文、结论、引用等。

# 示例输出

## 示例文章解析

### 引言
- **内容**：介绍研究的背景、目的和重要性。
- **作用**：吸引读者的注意力，为文章内容提供上下文。

### 方法
- **内容**：描述研究的具体方法和步骤，包括实验设计、数据收集和分析技术。
- **作用**：使读者了解研究的科学性和可重复性。

### 结果
- **内容**：展示研究的主要发现和数据。
- **作用**：提供研究结论的证据基础。

### 讨论
- **内容**：解释结果的意义，对比其他研究，提出可能的改进方向。
- **作用**：帮助读者理解结果的广泛影响和未来研究的潜力。

### 结论
- **内容**：总结研究的主要发现和贡献。
- **作用**：强化文章的核心信息，提供明确的结论。

### 引用
- **内容**：列出文章中引用的所有文献。
- **作用**：提供进一步阅读的资源，确保学术诚信。

# 备注

- **边缘情况**：如果文章结构不典型（例如，缺少某些部分或有额外的部分），应在解析中明确指出这些特殊情况。
- **重要考虑事项**：解析时应关注文章的逻辑性和连贯性，确保每个部分的内容与文章的整体目标一致。
```

--------------------------------

### Reinstall Weaviate Client for Source Installation

Source: https://docs.dify.ai/zh/self-host/troubleshooting/weaviate-v4-migration

Commands to uninstall the old weaviate-client and install the specific v4 version for source code installations.

```bash
# 对于源码安装
pip uninstall weaviate-client
pip install weaviate-client==4.17.0
```

--------------------------------

### Create Plugin Entry Point

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-md-exporter

Set up the main entry point for the Dify plugin. This involves initializing `PluginRunner` with the created export tools.

```python
from dify_plugin import PluginRunner
from tools.word_export import WordExportTool
from tools.pdf_export import PDFExportTool

plugin = PluginRunner(
    tools=[
        WordExportTool(),
        PDFExportTool(),
    ],
    providers=[]  # No credential providers needed
)
```

--------------------------------

### Place Public Key for Verification

Source: https://docs.dify.ai/zh/develop-plugin/publishing/standards/third-party-signature-verification

Copy the public key file to a location accessible by the plugin daemon. This example places it in a 'public_keys' directory within the plugin daemon's volume.

```bash
mkdir docker/volumes/plugin_daemon/public_keys
cp your_key_pair.public.pem docker/volumes/plugin_daemon/public_keys
```

--------------------------------

### Build the Web Service

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Compile and build the web service for deployment using PNPM.

```bash
pnpm build
```

--------------------------------

### Verify Dify CLI Installation

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-flomo-plugin

Check the installed Dify CLI version.

```bash
dify version
```

--------------------------------

### Start Middleware Services with Docker Compose

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Use Docker Compose to launch the necessary middleware services for Dify, such as databases and other dependencies. Ensure to configure the `middleware.env` file if you are not using the default PostgreSQL and Weaviate configurations.

```bash
cd docker

cp envs/middleware.env.example middleware.env

# 如果不使用 PostgreSQL 和 Weaviate，请修改 middleware.env 中的 DB_TYPE 或 COMPOSE_PROFILES。
docker compose --env-file middleware.env -f docker-compose.middleware.yaml -p dify up -d
```

--------------------------------

### Install FastAPI Dependencies

Source: https://docs.dify.ai/zh/use-dify/workspace/api-extension/api-extension

Command to install the necessary Python packages for building a FastAPI application.

```bash
pip install fastapi[all] uvicorn
```

--------------------------------

### Initialize New Dify Plugin Project

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-flomo-plugin

Use the Dify CLI to create a new plugin project. Follow the prompts to name your plugin, select its type, and fill in required fields.

```bash
dify plugin init
```

--------------------------------

### Install Dify CLI on Linux

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-flomo-plugin

Download the appropriate Dify CLI binary from the GitHub releases page, make it executable, and move it to your system's PATH.

```bash
# Download appropriate version
chmod +x dify-plugin-linux-amd64
mv dify-plugin-linux-amd64 dify
sudo mv dify /usr/local/bin/
```

--------------------------------

### Initialize Agent Strategy Plugin

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/agent-strategy-plugin

Use the Dify CLI to create a new agent strategy plugin project. Follow the on-screen prompts to configure the plugin's name, author, description, language, and type.

```bash
dify plugin init
```

```bash
➜  Dify Plugins Developing dify plugin init
Edit profile of the plugin
Plugin name (press Enter to next step): # Enter the plugin name
Author (press Enter to next step): Author name # Enter the plugin author
Description (press Enter to next step): Description # Enter the plugin description
---
Select the language you want to use for plugin development, and press Enter to con
BTW, you need Python 3.12+ to develop the Plugin if you choose Python.
-> python # Select Python environment
  go (not supported yet)
---
Based on the ability you want to extend, we have divided the Plugin into four type

- Tool: It's a tool provider, but not only limited to tools, you can implement an
- Model: Just a model provider, extending others is not allowed.
- Extension: Other times, you may only need a simple http service to extend the fu
- Agent Strategy: Implement your own logics here, just by focusing on Agent itself

What's more, we have provided the template for you, you can choose one of them b
  tool
-> agent-strategy # Select Agent strategy template
  llm
  text-embedding
---
Configure the permissions of the plugin, use up and down to navigate, tab to sel
Backwards Invocation:
Tools:
    Enabled: [✔]  You can invoke tools inside Dify if it's enabled # Enabled by default
Models:
    Enabled: [✔]  You can invoke models inside Dify if it's enabled # Enabled by default
    LLM: [✔]  You can invoke LLM models inside Dify if it's enabled # Enabled by default
    Text Embedding: [✘]  You can invoke text embedding models inside Dify if it'
    Rerank: [✘]  You can invoke rerank models inside Dify if it's enabled
...
```

--------------------------------

### Install FFmpeg on CentOS

Source: https://docs.dify.ai/zh/self-host/troubleshooting/integrations

Install FFmpeg on CentOS. This is required for OpenAI Text-to-Speech (TTS) audio stream segmentation.

```bash
sudo yum install epel-release
sudo rpm -Uvh http://li.nux.ro/download/nux/dextop/el7/x86_64/nux-dextop-release-0-5.el7.nux.noarch.rpm
sudo yum update
sudo yum install ffmpeg ffmpeg-devel
```

--------------------------------

### Install FFmpeg on macOS

Source: https://docs.dify.ai/zh/self-host/troubleshooting/integrations

Install FFmpeg using Homebrew on macOS. This is required for OpenAI Text-to-Speech (TTS) audio stream segmentation.

```bash
brew install ffmpeg
```

--------------------------------

### Initialize New Dify Plugin Project

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/tool-plugin

Use the Dify plugin CLI tool to create a new Dify plugin project. Ensure the binary is accessible in your PATH or use its direct path.

```bash
./dify-plugin-darwin-arm64 plugin init
```

```bash
dify plugin init
```

--------------------------------

### Configure Remote Debugging

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/develop-a-slack-bot-plugin

This bash command configures the plugin for remote installation by setting environment variables for the installation method, URL, and key.

```bash
INSTALL_METHOD=remote
REMOTE_INSTALL_URL=debug.dify.ai:5003
REMOTE_INSTALL_KEY=********-****-****-****-************
```

--------------------------------

### Start API Service

Source: https://docs.dify.ai/zh/self-host/advanced-deployments/local-source-code

Launch the Dify API service in debug mode, accessible on all network interfaces. This command starts a development server.

```bash
uv run flask run --host 0.0.0.0 --port=5001 --debug
```

--------------------------------

### Package Bundle Project

Source: https://docs.dify.ai/zh/develop-plugin/features-and-specs/advanced-development/bundle

Execute this command to package your Bundle project into a .difybndl file. The output file will be created in the current directory.

```bash
dify-plugin bundle package ./bundle
```

--------------------------------

### Cron Expression Examples

Source: https://docs.dify.ai/zh/use-dify/nodes/trigger/schedule-trigger

See practical examples of Cron expressions for various scheduling requirements, from specific times on weekdays to monthly last days.

```text
工作日上午 9 点                
`0 9 * * MON-FRI` or `0 9 * * 1-5`

每周三下午 2:30               
`30 14 * * WED`                    

每周日凌晨 12 点               
`0 0 * * 0`                        

每周二每 2 小时一次              
`0 */2 * * 2`                      

每月第一天凌晨 12 点             
`0 0 1 * *`                        

1 月 1 日和 6 月 1 日的中午 12 点 
`0 12 1 JAN,JUN *`                 

每月最后一天下午 5 点             
`0 17 L * *`                       

每月最后一个星期五晚上 10 点         
`0 22 * * 5L`
```

--------------------------------

### 设置数据源插件 SDK 版本

Source: https://docs.dify.ai/zh/develop-plugin/dev-guides-and-walkthroughs/datasource-plugin

在 requirements.txt 文件中指定数据源插件开发所使用的 Dify 插件 SDK 版本范围。

```yaml
dify-plugin>=0.5.0,<0.6.0
```

--------------------------------

### Invoke Chat Application Example

Source: https://docs.dify.ai/zh/develop-plugin/features-and-specs/advanced-development/reverse-invocation-app

Example of how to invoke a chat-type application within an Endpoint and handle streaming responses. Ensure correct invocation of `self.session.app.chat.invoke`.

```python
import json
from typing import Mapping
from werkzeug import Request, Response
from dify_plugin import Endpoint

class Duck(Endpoint):
    def _invoke(self, r: Request, values: Mapping, settings: Mapping) -> Response:
        """
        Invokes the endpoint with the given request.
        """
        app_id = values["app_id"]

        def generator():
            # Note: The original example incorrectly called self.session.app.workflow.invoke
            # It should call self.session.app.chat.invoke for a chat app.
            # Assuming a chat app is intended here based on the section title.
            response = self.session.app.chat.invoke(
                app_id=app_id, 
                inputs={}, # Provide actual inputs as needed
                response_mode="streaming", 
                conversation_id="some-conversation-id", # Provide a conversation ID if needed
                files=[]
            )

            for data in response:
                yield f"{json.dumps(data)} <br>"

        return Response(generator(), status=200, content_type="text/html")
```