Completions 文本补全

根据提示词生成文本补全。

参考文档: https://platform.openai.com/docs/api-reference/completions/create

请求

POST /v1/completions

认证

使用 Bearer Token 认证，格式: Authorization: Bearer sk-xxxxxx

请求体 (application/json)

参数	类型	必填	说明
model	string	是	模型 ID
prompt	string/array	是	生成补全的提示词
max_tokens	integer	否	最大生成 token 数
temperature	number	否	采样温度
top_p	number	否	核采样参数
n	integer	否	生成补全数量
stream	boolean	否	是否流式响应
stop	string/array	否	停止序列
suffix	string	否	补全后追加的后缀
echo	boolean	否	是否回显提示词
presence_penalty	number	否	存在惩罚
frequency_penalty	number	否	频率惩罚
logit_bias	object	否	token 偏置
user	string	否	用户标识

请求示例

cURL

curl -X POST "https://your-api-base/v1/completions" \
  -H "Authorization: Bearer sk-xxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Say this is a test",
    "max_tokens": 7,
    "temperature": 0
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxxxx",
    base_url="https://your-api-base/v1"
)

response = client.completions.create(
    model="gpt-3.5-turbo-instruct",
    prompt="Say this is a test",
    max_tokens=7,
    temperature=0
)

print(response.choices[0].text)

响应

200 成功响应

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1677858242,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "text": "\n\nThis is a test!",
      "index": 0,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}