ChatClient API

The ChatClient is the main entry point for interacting with LLM providers.

Constructor

new ChatClient(config: ChatConfig)

Parameters:

• config.provider: The LLM provider ('openai' | 'anthropic' | 'google' | 'ollama')
• config.model: The specific model to use (e.g., 'gpt-4o', 'claude-3-5-sonnet')
• config.apiKey?: API key (optional, falls back to environment variable)
• config.auth?: Authentication configuration (recommended over apiKey)
• config.baseUrl?: Custom base URL for API requests
• config.conversationId?: Optional conversation ID for tracking

Methods

chat(message, options?)

Send a chat message and get a response.

Parameters:

• message: string - The user message to send
• options?: ChatOptions - Optional chat configuration

Returns: Promise<ChatResponse>

const response = await client.chat('Hello!', { temperature: 0.7 });
console.log(response.content);

stream(message, options?)

Stream a chat response for real-time output.

Parameters:

• message: string
• options?: ChatOptions

Returns: AsyncIterator<StreamChunk>

for await (const chunk of client.stream('Tell me a story')) {
  process.stdout.write(chunk.content);
}

getHistory()

Retrieve the full conversation history for the current conversation.

Returns: Promise<Message[]>

clearHistory()

Clear the conversation history for the current conversation.

Returns: Promise<void>