GetGoAPI Logo
GetGoAPI
代码示例

gpt-3.5-turbo-16k 代码示例

完整的API调用示例，包含Python、Node.js、cURL多种语言。复制即用，快速集成。

1

基础对话

最简单的对话调用示例

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GETGOAPI_KEY",
    base_url="https://api.getgoapi.com/v1"
)

response = client.chat.completions.create(
    model="gpt-3.5-turbo-16k",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ]
)

print(response.choices[0].message.content)
Node.js
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_GETGOAPI_KEY',
  baseURL: 'https://api.getgoapi.com/v1'
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'gpt-3.5-turbo-16k',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'What is the capital of France?' }
    ]
  });

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

main();
cURL
curl https://api.getgoapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GETGOAPI_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-16k",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'
2

流式输出

实时流式获取AI响应

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GETGOAPI_KEY",
    base_url="https://api.getgoapi.com/v1"
)

stream = client.chat.completions.create(
    model="gpt-3.5-turbo-16k",
    messages=[{"role": "user", "content": "Write a short story"}],
    stream=True  # 开启流式输出
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end='')
Node.js
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_GETGOAPI_KEY',
  baseURL: 'https://api.getgoapi.com/v1'
});

async function main() {
  const stream = await client.chat.completions.create({
    model: 'gpt-3.5-turbo-16k',
    messages: [{ role: 'user', content: 'Write a short story' }],
    stream: true  // 开启流式输出
  });

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

main();
cURL
curl https://api.getgoapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GETGOAPI_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-16k",
    "messages": [{"role": "user", "content": "Write a short story"}],
    "stream": true
  }'
3

温度控制

调整输出的随机性

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GETGOAPI_KEY",
    base_url="https://api.getgoapi.com/v1"
)

# temperature=0: 确定性输出（适合编程、数学）
response_deterministic = client.chat.completions.create(
    model="gpt-3.5-turbo-16k",
    messages=[{"role": "user", "content": "Write a Python function to sort a list"}],
    temperature=0
)

# temperature=1: 创造性输出（适合写作、头脑风暴）
response_creative = client.chat.completions.create(
    model="gpt-3.5-turbo-16k",
    messages=[{"role": "user", "content": "Write a creative story"}],
    temperature=1
)
Node.js
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_GETGOAPI_KEY',
  baseURL: 'https://api.getgoapi.com/v1'
});

async function main() {
  // temperature=0: 确定性输出
  const deterministic = await client.chat.completions.create({
    model: 'gpt-3.5-turbo-16k',
    messages: [{ role: 'user', content: 'Write a Python function to sort a list' }],
    temperature: 0
  });

  // temperature=1: 创造性输出
  const creative = await client.chat.completions.create({
    model: 'gpt-3.5-turbo-16k',
    messages: [{ role: 'user', content: 'Write a creative story' }],
    temperature: 1
  });
}

main();
cURL
curl https://api.getgoapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GETGOAPI_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-16k",
    "messages": [{"role": "user", "content": "Write a Python function"}],
    "temperature": 0
  }'
4

限制输出长度

控制生成的token数量

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GETGOAPI_KEY",
    base_url="https://api.getgoapi.com/v1"
)

response = client.chat.completions.create(
    model="gpt-3.5-turbo-16k",
    messages=[{"role": "user", "content": "Explain quantum computing"}],
    max_tokens=100  # 限制输出100个tokens
)

print(response.choices[0].message.content)
print(f"Used tokens: {response.usage.total_tokens}")
Node.js
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_GETGOAPI_KEY',
  baseURL: 'https://api.getgoapi.com/v1'
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'gpt-3.5-turbo-16k',
    messages: [{ role: 'user', content: 'Explain quantum computing' }],
    max_tokens: 100  // 限制输出100个tokens
  });

  console.log(response.choices[0].message.content);
  console.log(`Used tokens: ${response.usage.total_tokens}`);
}

main();
cURL
curl https://api.getgoapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GETGOAPI_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-16k",
    "messages": [{"role": "user", "content": "Explain quantum computing"}],
    "max_tokens": 100
  }'
5

系统提示词

定制AI的行为和角色

Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GETGOAPI_KEY",
    base_url="https://api.getgoapi.com/v1"
)

response = client.chat.completions.create(
    model="gpt-3.5-turbo-16k",
    messages=[
        {
            "role": "system",
            "content": "You are a professional Python developer. Always provide code with comments and best practices."
        },
        {
            "role": "user",
            "content": "Write a function to calculate Fibonacci sequence"
        }
    ]
)

print(response.choices[0].message.content)
Node.js
import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_GETGOAPI_KEY',
  baseURL: 'https://api.getgoapi.com/v1'
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'gpt-3.5-turbo-16k',
    messages: [
      {
        role: 'system',
        content: 'You are a professional Python developer. Always provide code with comments.'
      },
      {
        role: 'user',
        content: 'Write a function to calculate Fibonacci sequence'
      }
    ]
  });

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

main();
cURL
curl https://api.getgoapi.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_GETGOAPI_KEY" \
  -d '{
    "model": "gpt-3.5-turbo-16k",
    "messages": [
      {
        "role": "system",
        "content": "You are a professional Python developer."
      },
      {
        "role": "user",
        "content": "Write a function to calculate Fibonacci sequence"
      }
    ]
  }'

最佳实践

妥善保管API Key

不要在代码中硬编码API Key，使用环境变量或密钥管理服务。

错误处理

始终添加try-catch处理API调用异常，提供友好的错误提示。

控制Token使用

使用max_tokens限制输出长度，避免不必要的费用。

优化提示词

清晰简洁的提示词可以获得更好的回答，并节省token。

需要更多帮助？

查看完整文档或联系技术支持团队

gpt-3.5-turbo-16k 代码示例 | Python/Node.js完整案例 | GetGoAPI