@55387.ai/uniapi-sdk

TypeScript SDK for One API - Unified AI client with OpenAI-compatible interface.

Installation

npm install @55387.ai/uniapi-sdk
# or
pnpm add @55387.ai/uniapi-sdk
# or
yarn add @55387.ai/uniapi-sdk

Quick Start

import { OneClient } from '@55387.ai/uniapi-sdk';

const client = new OneClient({
  apiKey: 'your-api-key',
  baseUrl: 'https://your-one-api-server.com', // or http://localhost:3000 for local
});

// Simple chat completion
const response = await client.chat.completions.create({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }],
});

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

API Reference

OneClient

The main client class for interacting with One API.

Constructor Options

interface OneClientOptions {
  apiKey: string;           // Your API key
  baseUrl?: string;         // API server URL (default: http://localhost:3000)
  timeout?: number;         // Request timeout in ms (default: 60000)
  maxRetries?: number;      // Max retry attempts (default: 3)
}

Chat Completions

Non-streaming

const response = await client.chat.completions.create({
  model: 'gpt-4',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' }
  ],
  temperature: 0.7,
  max_tokens: 1000,
});

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

Streaming

const stream = await client.chat.completions.create({
  model: 'claude-3-sonnet',
  messages: [{ role: 'user', content: 'Tell me a story' }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

Multimodal Support

Text and Images

import { imageUrl, imageBase64, text } from '@55387.ai/uniapi-sdk';

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{
    role: 'user',
    content: [
      text('What do you see in this image?'),
      imageUrl('https://example.com/image.jpg'),
    ],
  }],
});

Base64 Images

const response = await client.chat.completions.create({
  model: 'gemini-2.5-flash',
  messages: [{
    role: 'user',
    content: [
      text('Describe this image'),
      imageBase64(base64Data, 'image/png'),
    ],
  }],
});

Advanced Features

Thinking Mode (DeepSeek R1, Claude 3.7+)

const response = await client.chat.completions.create({
  model: 'claude-3-7-sonnet',
  messages: [{ role: 'user', content: 'Solve this complex math problem...' }],
  thinking: {
    type: 'enabled',
    budget_tokens: 2048
  }
});

// Access thinking process
console.log('Thinking:', response.choices[0].message.reasoning_content);
console.log('Answer:', response.choices[0].message.content);

Function Calling (Tool Use)

const tools = [{
  type: 'function',
  function: {
    name: 'get_weather',
    description: 'Get current weather information',
    parameters: {
      type: 'object',
      properties: {
        location: { type: 'string', description: 'City name' }
      },
      required: ['location']
    }
  }
}];

const response = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What\'s the weather in Beijing?' }],
  tools: tools,
});

// Check for tool calls
if (response.choices[0].message.tool_calls) {
  const toolCall = response.choices[0].message.tool_calls[0];
  console.log('Function:', toolCall.function.name);
  console.log('Args:', JSON.parse(toolCall.function.arguments));
}

Streaming Chat Helper

For easier streaming chat management:

const chat = client.createStreamingChat({
  model: 'gemini-1.5-pro',
  systemPrompt: 'You are a helpful assistant.',
});

await chat.send('Hello!', {
  onContent: (content) => process.stdout.write(content),
  onComplete: (fullContent) => console.log('\n--- Complete ---'),
  onError: (error) => console.error('Error:', error),
});

Error Handling

try {
  const response = await client.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: 'Hello!' }],
  });
} catch (error) {
  if (error.status === 401) {
    console.error('Invalid API key');
  } else if (error.status === 429) {
    console.error('Rate limit exceeded');
  } else {
    console.error('API error:', error.message);
  }
}

Supported Models

The SDK automatically routes to the appropriate provider based on model name:

| Provider | Model Prefixes | Example Models | |----------|----------------|----------------| | OpenAI | gpt-*, o1* | gpt-4, gpt-3.5-turbo | | Anthropic | claude-* | claude-3-sonnet, claude-3-haiku | | Google Gemini | gemini-* | gemini-1.5-pro, gemini-2.0-flash | | DeepSeek | deepseek-* | deepseek-chat, deepseek-reasoner | | 通义千问 | qwen* | qwen-turbo, qwen-max | | 智谱 GLM | glm-*, codegeex-* | glm-4, codegeex-2 | | Kimi | kimi-*, moonshot-* | kimi-latest |

TypeScript Support

The SDK is written in TypeScript and provides full type safety:

import type { ChatCompletionMessageParam, ChatCompletionCreateParams } from '@55387.ai/uniapi-sdk';

// All parameters are fully typed
const params: ChatCompletionCreateParams = {
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }],
  temperature: 0.7,
};

License

MIT