Skip to main content

​
Modifying the Manifest File

The manifest.yaml file in the plugin directory declares the basic information about the plugin, which will be displayed in the LangBot UI or plugin marketplace interfaces. 
apiVersion: v1  # Do not modify
kind: Plugin  # Do not modify
metadata:
  author: RockChinQ  # Author, must match regex ^[a-zA-Z0-9_-]+$
  name: HelloPlugin  # Plugin name, used to distinguish plugins, must match regex ^[a-zA-Z0-9-]+$
  repository: 'https://github.com/langbot-app/HelloPlugin'  # Plugin repository URL
  version: 0.1.0  # Plugin version
  description:
    en_US: 'Hello LangBot Plugin'  # Plugin description, multilingual
    zh_Hans: 'Hello LangBot Plugin'
  label:
    en_US: HelloPlugin  # Plugin label, displayed in the interface, multilingual
    zh_Hans: HelloPlugin
  icon: assets/icon.svg  # Plugin icon, defaults to assets/icon.svg, can be replaced with various image formats
spec:
  config: []  # Plugin configuration item format
  components: {}  # Plugin component list, no need to modify manually
execution:
  python:
    path: main.py  # Do not modify
    attr: HelloPlugin  # Do not modify
Plugin multilingual support follows the RFC 4646 standard. Currently supported languages include:
  • en_US English
  • zh_Hans Simplified Chinese
  • zh_Hant Traditional Chinese
  • ja_JP Japanese

​
Plugin Configuration Item Format

In the manifest.yaml file, fields declared in spec.config will be rendered by LangBot as configuration item forms for users to fill out. Plugins can retrieve user-filled configuration items through APIs provided by the SDK (see later sections). For example: 
spec:
  config:
    - name: github_token  # Required; configuration item name, used for retrieval in the plugin
      type: string  # Required; configuration item type, supports string, integer, float, boolean, select, prompt-editor, llm-model-selector, bot-selector, etc.
      label:  # Required; configuration item display name, supports multilingual. Language codes follow RFC 4646 standard.
        en_US: Github Token
        zh_Hans: Github Token
      description:  # Configuration item description, supports multilingual. Optional.
        en_US: Image downloading requires a Github token
        zh_Hans: 如果不填的话，图片可能会下载失败
      default: ''  # Configuration item default value, optional.
      required: false  # Whether the configuration item is required, optional.
      show_if:  # Conditional rendering (shows when conditions are met), optional.
        field: mode
        operator: eq
        value: mode1
    - name: mode
      type: select
      ...
The supported types and fields for configuration items are as follows:

​
Conditional Rendering (show_if)

All types of configuration items support conditional rendering using the show_if field. You can decide whether the current field is rendered based on the value of another field in the same (or an associated) form. 
- name: advanced_setting
  type: string
  show_if:
    field: mode          # The name of the dependent field
    operator: eq         # The operator, supports 'eq' (equals), 'neq' (not equals), 'in' (in a list)
    value: advanced      # The value to check against
Note: Cross-form cascading relationships (e.g. creation_schema values reading from retrieval_schema values and vice versa in a Knowledge Engine) are supported in the latest LangBot frontend.

​
type: string

String type. 
- name: api_key
  type: string
  ...

​
type: array[string]

String array. 
- name: tags
  type: array[string]
  ...

​
type: integer

Integer type. 
- name: progress
  type: integer
  ...

​
type: float

Float type. 
- name: temperature
  type: float
  ...

​
type: boolean

Boolean type. 
- name: is_enabled
  type: boolean
  ...

​
type: select

Dropdown menu. Requires configuring options, which represents the dropdown menu options. 
- name: mode
  type: select
  options:  # Dropdown options, supports multilingual.
    - name: mode1  # Value
      label:  # Display name, supports multilingual.
        en_US: Mode 1
        zh_Hans: 模式 1
    - name: mode2
      label:  # Display name, supports multilingual.
        en_US: Mode 2
        zh_Hans: 模式 2
  ...

​
type: prompt-editor

Prompt editor. Displays a prompt editor from the pipeline configuration page, with the final result represented in OpenAI’s messages format. 
- name: prompt
  type: prompt-editor
  ...

​
type: text

Large text input. Rendered as a textarea in the frontend for user input, and passed to the plugin as a string. 
- name: prompt
  type: text
  ...

​
type: file

File upload. Supports file uploads up to 10MB, passed to the plugin in the format {"file_key": "xxxxx.xxx", "mimetype": "xxxxx"}. The plugin can use the get_config_file API to retrieve the file content. 
- name: config_file
  type: file
  accept: 'application/json'  # Optional, specify accepted file MIME types
  ...
Retrieving the file in the plugin: 
# Get file information from config
file_config = self.get_config()['config_file']
file_key = file_config['file_key']
mimetype = file_config['mimetype']

# Example output: {'file_input': {'file_key': 'plugin_config_d2234fd802054faf80babe0679a97fa9.json', 'mimetype': 'application/json'}}
print(file_config)

# Get file content
file_bytes = await self.get_config_file(file_key)
Common MIME type and file extension reference: MDN Documentation

​
type: array[file]

Multiple file upload. Similar to the file type, but supports uploading multiple files, passed to the plugin in the format [{"file_key": "xxxxx.xxx", "mimetype": "xxxxx"}]. 
- name: resource_files
  type: array[file]
  accept: 'image/*'  # Optional, specify accepted file MIME types
  ...
Retrieving files in the plugin: 
# Get file list from config
files_config = self.get_config()['resource_files']

for file_config in files_config:
    file_key = file_config['file_key']
    mimetype = file_config['mimetype']

    # Get file content
    file_bytes = await self.get_config_file(file_key)

​
type: llm-model-selector

LLM model selector. Displays an LLM model selector where you can choose configured LLM models, with the final result represented as the LLM model UUID. 
- name: model
  type: llm-model-selector
  ...

​
type: bot-selector

Bot selector. Displays a Bot selector where you can choose configured Bots, with the final result represented as the Bot UUID. 
- name: bot
  type: bot-selector
  ...
Using the Bot UUID in the plugin: 
# Get Bot UUID from config
bot_uuid = self.get_config()['bot']
print(bot_uuid)  # Output: '550e8400-e29b-41d4-a716-446655440000'

​
What’s Next

This tutorial will guide you through step-by-step completion of plugin functionality.
  • Adding Components: Plugin components are the core functional units of plugins. You can add components based on your needs.