开始

安装

您可以使用我们的AI辅助设置来安装插件。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，请运行以下命令安装插件，并按照以下平台特定的说明进行操作:

bun add @capgo/capacitor-llm
bunx cap sync

导入

import { CapgoLLM } from '@capgo/capacitor-llm';

API概述

createChat

创建一个新聊天会话

import { CapgoLLM } from '@capgo/capacitor-llm';

await CapgoLLM.createChat();

sendMessage

在特定聊天会话中发送消息给AI

import { CapgoLLM } from '@capgo/capacitor-llm';

await CapgoLLM.sendMessage({} as { chatId: string; message: string });

getReadiness

获取LLM的就绪状态

import { CapgoLLM } from '@capgo/capacitor-llm';

await CapgoLLM.getReadiness();

setModel

设置模型配置

• iOS：使用“Apple Intelligence”作为系统模型的路径，或提供MediaPipe模型的路径
• Android：assets或files目录中的MediaPipe模型文件路径

import { CapgoLLM } from '@capgo/capacitor-llm';

await CapgoLLM.setModel({} as ModelOptions);

downloadModel

下载一个URL中的模型并将其保存到适当的位置

• iOS：将其下载到应用的文档目录
• Android：将其下载到应用的文件目录

import { CapgoLLM } from '@capgo/capacitor-llm';

await CapgoLLM.downloadModel({} as DownloadModelOptions);

类型参考

ModelOptions

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

下载模型的选项。

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

模型下载的结果。

export interface DownloadModelResult {
  /** Path where the model was saved */
  path: string;
  /** Path where the companion file was saved (if applicable) */
  companionPath?: string;
}

TextFromAiEvent

AI 完成事件的事件数据

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

AI完成事件

export interface AiFinishedEvent {
  /** The chat session ID that finished */
  chatId: string;
}

DownloadProgressEvent

下载进度事件的事件数据

export interface DownloadProgressEvent {
  /** Percentage of download completed (0-100) */
  progress: number;
  /** Total bytes to download */
  totalBytes?: number;
  /** Bytes downloaded so far */
  downloadedBytes?: number;
}

ReadinessChangeEvent

就绪状态变化事件的事件数据

export interface ReadinessChangeEvent {
  /** The readiness status */
  readiness: string;
}

真实来源

此页面由插件的源代码生成。重新同步公共__CAPGO_KEEP_0__时，源代码会从上游更新。 src/definitions.ts. Re-run the sync when the public API changes upstream.

section titled ‘Source Of Truth’

如果您正在使用 Getting Started 来规划仪表板和API操作，连接它与 使用 @capgo/capacitor-llm 为使用 @capgo/capacitor-llm 的本机能力 API 概述 为API 概述中的实现细节 介绍 为介绍中的实现细节 API 密钥 为API 密钥中的实现细节 设备 查看设备的实现细节。