Skip to main content

​
Overview

switchAILocal is fully compatible with the OpenAI Node.js SDK. Point the SDK to your local switchAILocal instance to access all configured providers through one unified API.

​
Installation

Install the official OpenAI Node.js SDK: 
npm install openai
# or
yarn add openai
# or
pnpm add openai

​
Quick Start

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:18080/v1',
  apiKey: 'sk-test-123', // Must match a key in config.yaml
});

async function main() {
  // Auto-routing: switchAILocal picks the best available provider
  const completion = await client.chat.completions.create({
    model: 'gemini-2.5-pro',
    messages: [
      { role: 'user', content: 'What is the meaning of life?' }
    ],
  });

  console.log(completion.choices[0].message.content);
}

main();

​
Advanced Features

​
Multi-turn Conversations

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:18080/v1',
  apiKey: 'sk-test-123',
});

async function conversation() {
  const messages = [
    { role: 'system', content: 'You are a helpful coding assistant.' },
    { role: 'user', content: 'Write a JavaScript function to calculate factorial' }
  ];

  const response = await client.chat.completions.create({
    model: 'gemini-2.5-pro',
    messages,
  });

  // Add assistant response to conversation
  messages.push({
    role: 'assistant',
    content: response.choices[0].message.content
  });

  // Continue conversation
  messages.push({
    role: 'user',
    content: 'Now add TypeScript types'
  });

  const followUp = await client.chat.completions.create({
    model: 'gemini-2.5-pro',
    messages,
  });

  console.log(followUp.choices[0].message.content);
}

conversation();

​
Temperature and Parameters

const completion = await client.chat.completions.create({
  model: 'gemini-2.5-pro',
  messages: [{ role: 'user', content: 'Write a creative story' }],
  temperature: 0.9,      // Higher = more creative
  max_tokens: 1000,      // Limit response length
  top_p: 0.95,           // Nucleus sampling
});

​
CLI Attachments (Files & Folders)

Pass local files and folders to CLI providers: 
const completion = await client.chat.completions.create({
  model: 'geminicli:gemini-2.5-pro',
  messages: [{ role: 'user', content: 'Explain the logic in this file' }],
  extra_body: {
    cli: {
      attachments: [
        { type: 'file', path: '/path/to/script.js' },
        { type: 'folder', path: './src/internal' }
      ]
    }
  }
});

​
CLI Flags (Auto-approve, Sandbox)

const completion = await client.chat.completions.create({
  model: 'vibe:mistral-large',
  messages: [{ role: 'user', content: 'Update the version in package.json' }],
  extra_body: {
    cli: {
      flags: {
        auto_approve: true,  // Auto-approve actions
        sandbox: true        // Run in sandbox mode
      }
    }
  }
});

​
Session Management

const completion = await client.chat.completions.create({
  model: 'geminicli:gemini-2.5-pro',
  messages: [{ role: 'user', content: 'Continue our previous discussion' }],
  extra_body: {
    cli: {
      session_id: 'latest'  // Or use a custom session name
    }
  }
});

​
List Available Models

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:18080/v1',
  apiKey: 'sk-test-123',
});

async function listModels() {
  const models = await client.models.list();
  
  for (const model of models.data) {
    console.log(`${model.id} (${model.owned_by})`);
  }
}

listModels();

​
Error Handling

import OpenAI from 'openai';
import { APIConnectionError, APIError } from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:18080/v1',
  apiKey: 'sk-test-123',
});

async function handleErrors() {
  try {
    const completion = await client.chat.completions.create({
      model: 'gemini-2.5-pro',
      messages: [{ role: 'user', content: 'Hello!' }],
    });
    console.log(completion.choices[0].message.content);
  } catch (error) {
    if (error instanceof APIConnectionError) {
      console.error(`Connection error: ${error.message}`);
    } else if (error instanceof APIError) {
      console.error(`API error: ${error.status} - ${error.message}`);
    } else {
      console.error(`Unexpected error: ${error}`);
    }
  }
}

handleErrors();

​
TypeScript Support

The OpenAI SDK includes built-in TypeScript types: 
import OpenAI from 'openai';
import type { ChatCompletion, ChatCompletionMessageParam } from 'openai/resources/chat';

const client = new OpenAI({
  baseURL: 'http://localhost:18080/v1',
  apiKey: 'sk-test-123',
});

async function typedExample(): Promise<string> {
  const messages: ChatCompletionMessageParam[] = [
    { role: 'user', content: 'What is TypeScript?' }
  ];

  const completion: ChatCompletion = await client.chat.completions.create({
    model: 'gemini-2.5-pro',
    messages,
  });

  return completion.choices[0].message.content || '';
}

​
Provider Prefixes

PrefixProviderExample
geminicli:Google Gemini CLIgeminicli:gemini-2.5-pro
claudecli:Anthropic Claude CLIclaudecli:claude-sonnet-4
ollama:Ollama (local)ollama:llama3.2
lmstudio:LM Studio (local)lmstudio:mistral-7b
switchai:Traylinx switchAIswitchai:switchai-fast
gemini:Google AI Studiogemini:gemini-2.5-pro
claude:Anthropic APIclaude:claude-3-5-sonnet
openai:OpenAI APIopenai:gpt-4
Omit the prefix to let switchAILocal automatically route to the best available provider.

​
Environment Variables

import OpenAI from 'openai';

// Set environment variables before importing
process.env.OPENAI_BASE_URL = 'http://localhost:18080/v1';
process.env.OPENAI_API_KEY = 'sk-test-123';

// Client automatically uses environment variables
const client = new OpenAI();

async function main() {
  const completion = await client.chat.completions.create({
    model: 'gemini-2.5-pro',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
  
  console.log(completion.choices[0].message.content);
}

main();

​
Next Steps

Python SDK

Use switchAILocal with Python

Go SDK

Embed switchAILocal in Go applications

Examples

See more usage examples

API Reference

Complete API documentation