@amux.ai/adapter-google

Google Gemini adapter for Amux

Overview

Official Google Gemini adapter for Amux. Gemini API is OpenAI-compatible, so this adapter extends the OpenAI adapter with Gemini-specific configurations.

Installation

pnpm add @amux.ai/llm-bridge @amux.ai/adapter-google
# or
npm install @amux.ai/llm-bridge @amux.ai/adapter-google

Usage

As Inbound Adapter

import { createBridge } from '@amux.ai/llm-bridge'
import { geminiAdapter } from '@amux.ai/adapter-google'
import { openaiAdapter } from '@amux.ai/adapter-openai'

const bridge = createBridge({
  inbound: geminiAdapter,
  outbound: openaiAdapter,
  config: {
    apiKey: process.env.OPENAI_API_KEY
  }
})

As Outbound Adapter

import { createBridge } from '@amux.ai/llm-bridge'
import { openaiAdapter } from '@amux.ai/adapter-openai'
import { geminiAdapter } from '@amux.ai/adapter-google'

const bridge = createBridge({
  inbound: openaiAdapter,
  outbound: geminiAdapter,
  config: {
    apiKey: process.env.GOOGLE_API_KEY
  }
})

const response = await bridge.chat({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }]
})

Supported Features

• ✅ Chat completions
• ✅ Streaming
• ✅ Function/Tool calling
• ✅ Vision (image inputs)
• ✅ System prompts

Supported Models

• gemini-2.0-flash-exp
• gemini-exp-1206
• gemini-2.0-flash-thinking-exp-01-21
• gemini-1.5-pro
• gemini-1.5-flash

API Compatibility

Gemini API is OpenAI-compatible. For detailed API documentation, see Gemini API Documentation.

License

MIT © isboyjc

Links

• Documentation
• GitHub Repository
• Issue Tracker