deechat-ai-chat

@ai-chat/core

A focused AI chat client for handling AI requests and tool calling in Node.js applications.

🎯 Core Purpose

@ai-chat is designed with a clear focus on core AI interaction:

• AI Request Processing - Send messages to AI providers and handle responses
• Tool Calling Coordination - Manage tool calls and results in AI conversations

This package does NOT handle:

• ❌ Conversation history management (use context-manager)
• ❌ Message persistence (use context-manager)
• ❌ Session state tracking (use context-manager)
• ❌ Token calculation and cost estimation (use dedicated token calculation packages)
• ❌ Specific tool implementations (use mcp-client or custom providers)

🚀 Quick Start

import { AIChat } from '@ai-chat/core'

// Create AI chat client
const aiChat = new AIChat({
  provider: 'openai',
  apiKey: process.env.OPENAI_API_KEY,
  model: 'gpt-4'
})

// Send messages (you manage the conversation history)
const messages = [
  { role: 'user', content: 'Hello!' }
]

const response = await aiChat.sendMessage(messages)
console.log(response.message.content)

📖 Core API

AIChat Class

class AIChat {
  constructor(config: AIChatConfig)
  
  // Send message and get complete response
  sendMessage(
    messages: Message[], 
    options?: ChatOptions
  ): Promise<ChatResponse>
  
  // Send message and get streaming response
  sendMessageStream(
    messages: Message[],
    options?: ChatOptions  
  ): AsyncIterable<ChatStreamChunk>
}

Configuration

interface AIChatConfig {
  provider: 'openai' | 'claude' | 'gemini' | string
  apiKey: string
  model?: string
  baseUrl?: string
  temperature?: number
  maxTokens?: number
}

Tool Integration

// Tools are provided as input, not discovered by this package
const response = await aiChat.sendMessage(messages, {
  tools: [
    {
      name: "search_files",
      description: "Search for files",
      parameters: { /* JSON Schema */ }
    }
  ],
  onToolCall: async (call) => {
    // Your tool execution logic here
    // This could call mcp-client, local functions, etc.
    return {
      toolCallId: call.id,
      result: await executeMyTool(call.name, call.arguments)
    }
  }
})

🌊 Streaming Example

const stream = aiChat.sendMessageStream(messages, {
  tools: myTools,
  onToolCall: handleToolCall
})

for await (const chunk of stream) {
  if (chunk.content) {
    process.stdout.write(chunk.content)
  }
  
  if (chunk.toolCalls) {
    console.log('AI wants to call tools:', chunk.toolCalls)
  }
  
  if (chunk.done) {
    console.log('\nResponse complete!')
    break
  }
}

🏗️ Architecture Integration

This package is designed to work alongside other focused packages:

// Example: Complete DeeChat integration
import { AIChat } from '@ai-chat/core'
import { ContextManager } from '@context-manager'  
import { MCPClient } from '@mcp-client'

// Each package handles its own responsibility
const aiChat = new AIChat(aiConfig)           // AI communication
const contextManager = new ContextManager()   // History & state
const mcpClient = new MCPClient()             // Tool implementation

// Compose them together
const sessionId = 'session-123'
const history = contextManager.getMessages(sessionId)

const response = await aiChat.sendMessage(
  [...history, { role: 'user', content: userInput }],
  {
    tools: await mcpClient.getTools(),
    onToolCall: (call) => mcpClient.executeTools(call)
  }
)

// Update context with response
contextManager.addMessage(sessionId, response.message)

🎯 Features

• Multiple AI Providers: OpenAI, Claude, Gemini support
• Streaming Responses: Real-time response streaming
• Tool Calling: Coordinate tool execution without managing tools
• TypeScript First: Full type safety and IntelliSense
• Lightweight: Focused scope, minimal dependencies
• Framework Agnostic: Works in any Node.js environment

📦 Installation

npm install @ai-chat/core

# Peer dependencies (install the providers you need)
npm install openai anthropic  # for AI providers

📚 Documentation

核心文档

• API 设计文档 - 详细的 API 设计和类型定义
• 产品需求文档 - 完整的产品需求和用户故事
• 架构设计 - 技术架构和设计决策

开发文档

• 开发指南 - 开发环境搭建和编码规范
• 测试指南 - 测试策略和测试用例编写
• 变更日志 - 版本变更记录

🤝 Contributing

We welcome contributions! Please see our Contributing Guide.

📄 License

MIT License - see LICENSE file for details.