开始
复制一个包含安装步骤和此插件的完整Markdown指南的设置提示。
Set up this Capacitor plugin in the project.
Use the package manager already used by the project.
Install these package(s): `@capgo/capacitor-llm`
Run the required Capacitor sync/update step after installation.
Read this markdown guide for the full setup steps: https://raw.githubusercontent.com/Cap-go/website/refs/heads/main/apps/docs/src/content/docs/docs/plugins/llm/getting-started.mdx
Use that guide for platform-specific steps, native file edits, permissions, config changes, imports, and usage setup.
If that guide references other docs pages, read them too.
安装
标题为“安装”您可以使用我们的 AI 助手设置来安装插件。使用以下命令将 Capgo 技能添加到您的 AI 工具中:
npx skills add https://github.com/Cap-go/capgo-skills --skill capacitor-plugins然后使用以下提示:
Use the `capacitor-plugins` skill from `Cap-go/capgo-skills` to install the `@capgo/capacitor-llm` plugin in my project.如果您更喜欢手动设置,请按照以下命令安装插件并遵循以下平台特定的说明:
bun add @capgo/capacitor-llmbunx cap sync导入
导入import { CapgoLLM } from '@capgo/capacitor-llm';API概述
API概述createChat
创建会话创建会话
import { CapgoLLM } from '@capgo/capacitor-llm';
const result = await CapgoLLM.createChat();console.log(result);sendMessage
创建会话发送消息
import { CapgoLLM } from '@capgo/capacitor-llm';
await CapgoLLM.sendMessage({ chatId: 'chat-id-123', message: 'Hello from Capacitor',});getReadiness
获取准备状态获取LLM的就绪状态
import { CapgoLLM } from '@capgo/capacitor-llm';
const result = await CapgoLLM.getReadiness();console.log(result);setModel
标题:"setModel"设置模型配置
- iOS:使用"Apple Intelligence"作为系统模型路径,或者提供MediaPipe模型路径
- Android:assets或files目录下的MediaPipe模型文件路径
import { CapgoLLM } from '@capgo/capacitor-llm';
await CapgoLLM.setModel({ path: 'path/to/file', modelType: 'task',});downloadModel
标题:"downloadModel"从URL下载模型并将其保存到适当位置
- iOS:下载到应用的文档目录
- Android:下载到应用的文件目录
import { CapgoLLM } from '@capgo/capacitor-llm';
const result = await CapgoLLM.downloadModel({ url: 'https://example.com' });console.log(result);类型参考
类型参考ModelOptions
模型选项模型配置选项
export interface ModelOptions { /** Model path or "Apple Intelligence" for iOS system model */ path: string; /** Model file type/extension (e.g., "task", "bin", "litertlm"). If not provided, will be extracted from path. */ modelType?: string; /** Maximum number of tokens the model handles */ maxTokens?: number; /** Number of tokens the model considers at each step */ topk?: number; /** Amount of randomness in generation (0.0-1.0) */ temperature?: number; /** Random seed for generation */ randomSeed?: number;}DownloadModelOptions
下载模型选项下载模型结果
export interface DownloadModelOptions { /** URL of the model file to download */ url: string; /** Optional: URL of companion file (e.g., .litertlm for Android) */ companionUrl?: string; /** Optional: Custom filename (defaults to filename from URL) */ filename?: string;}DownloadModelResult
下载模型结果从AI事件中获取文本
export interface DownloadModelResult { /** Path where the model was saved */ path: string; /** Path where the companion file was saved (if applicable) */ companionPath?: string;}TextFromAiEvent
模型下载结果AI事件数据
export interface TextFromAiEvent { /** The text content from AI - this is an incremental chunk, not the full text */ text: string; /** The chat session ID */ chatId: string; /** Whether this is a complete chunk (true) or partial streaming data (false) */ isChunk?: boolean;}AiFinishedEvent
AiFinishedEventAI完成事件数据
export interface AiFinishedEvent { /** The chat session ID that finished */ chatId: string;}DownloadProgressEvent
DownloadProgressEvent下载进度事件数据
export interface DownloadProgressEvent { /** Percentage of download completed (0-100) */ progress: number; /** Total bytes to download */ totalBytes?: number; /** Bytes downloaded so far */ downloadedBytes?: number;}ReadinessChangeEvent
ReadinessChangeEvent就绪状态变化事件数据
export interface ReadinessChangeEvent { /** The readiness status */ readiness: string;}真实数据来源
Section titled “源头真相”本页面由插件生成 src/definitions.ts. 当公共 API 上游更改时,请重新运行同步
继续从 Getting Started
Section titled “继续从 Getting Started”如果您正在使用 开始使用 来规划仪表板和 API 操作,请将其连接到 使用 @capgo/capacitor-llm 使用 @capgo/capacitor-llm API 简介 API Overview 简介 为简介中的实现细节 API 键 为API 键中的实现细节,并 设备 为设备的实现细节。