聊天补全

聊天补全

聊天补全是与 AI 模型交互的主要 API。两个运行时均提供统一接口，适用于 35+ 提供商。

基本用法

Rust

let client = AiClient::from_model("openai/gpt-4o").await?;

let response = client.chat()
    .user("Hello, world!")
    .execute()
    .await?;

println!("{}", response.content);

Python

client = await AiClient.create("openai/gpt-4o")

response = await client.chat() \
    .user("Hello, world!") \
    .execute()

print(response.content)

消息

系统消息

设置模型行为：

// Rust
client.chat()
    .system("You are a helpful coding assistant. Always include code examples.")
    .user("Explain closures")
    .execute().await?;

# Python
await client.chat() \
    .system("You are a helpful coding assistant.") \
    .user("Explain closures") \
    .execute()

多轮对话

传入对话历史：

// Rust
use ai_lib::{Message, MessageRole};

let messages = vec![
    Message::system("You are a tutor."),
    Message::user("What is recursion?"),
    Message::assistant("Recursion is when a function calls itself..."),
    Message::user("Can you show an example?"),
];

client.chat().messages(messages).execute().await?;

# Python
from ai_lib_python import Message

messages = [
    Message.system("You are a tutor."),
    Message.user("What is recursion?"),
    Message.assistant("Recursion is when a function calls itself..."),
    Message.user("Can you show an example?"),
]

await client.chat().messages(messages).execute()

参数

Parameter	Type	Description
temperature	float	随机性（0.0 = 确定性，2.0 = 创造性）
max_tokens	int	最大响应长度
top_p	float	核采样（temperature 的替代）
stop	string[]	停止生成的序列

// Rust
client.chat()
    .user("Write a poem")
    .temperature(0.9)
    .max_tokens(200)
    .top_p(0.95)
    .execute().await?;

流式

如需实时输出，使用流式：

// Rust
let mut stream = client.chat()
    .user("Tell me a story")
    .stream()
    .execute_stream()
    .await?;

while let Some(event) = stream.next().await {
    if let StreamingEvent::ContentDelta { text, .. } = event? {
        print!("{text}");
        std::io::stdout().flush()?;
    }
}

# Python
async for event in client.chat() \
    .user("Tell me a story") \
    .stream():
    if event.is_content_delta:
        print(event.as_content_delta.text, end="", flush=True)

响应统计

用于成本管理的使用量跟踪：

// Rust
let (response, stats) = client.chat()
    .user("Hello")
    .execute_with_stats()
    .await?;

println!("Prompt tokens: {}", stats.prompt_tokens);
println!("Completion tokens: {}", stats.completion_tokens);
println!("Latency: {}ms", stats.latency_ms);

# Python
response, stats = await client.chat() \
    .user("Hello") \
    .execute_with_stats()

print(f"Tokens: {stats.total_tokens}")
print(f"Latency: {stats.latency_ms}ms")

提供商切换

相同代码适用于所有提供商：

// Just change the model identifier
let client = AiClient::from_model("anthropic/claude-3-5-sonnet").await?;
let client = AiClient::from_model("deepseek/deepseek-chat").await?;
let client = AiClient::from_model("gemini/gemini-2.0-flash").await?;

协议清单会自动处理端点 URL、认证、参数映射与流式格式差异。