OpenAI codex API：使用 Python 快速入门

安装官方 SDK

使用官方 SDK 以确保与我们 openai 代理 API 的兼容性。此方法适用于任何支持 OpenAI 协议的标准库。

• 通过你首选的包管理器安装该包。
• 通过导入库来验证安装。

Copyfrom openai import OpenAI

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

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

设置您的基础 URL 和密钥

将您的客户端指向我们的 openai 网关端点以访问 uncensored AI 模型。将默认基础 URL 替换为我们的特定端点。

• 在环境变量中设置 API 密钥。
• 将基础 URL 配置为 https://api.openaicodexapi.com/v1.

此配置确保您的请求正确路由至我们的服务器，而无需修改现有的代码结构。

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

发送您的第一次请求

发送简单的文本补全以测试连接。使用模型 ID uncensored 用于请求。

• 定义消息内容。
• 执行请求。

Copyfrom openai import OpenAI

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

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

响应直接返回生成的文本。

启用流式传输和 JSON 模式

流式响应以降低延迟，或启用 JSON 模式以获取结构化数据。设置 stream=true 用于实时 token 交付。

• 使用 response_format for JSON 输出。
• 在代码中处理数据块。

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

流式传输有助于您快速显示部分结果。

处理工具和函数调用

在请求中定义工具以启用函数调用。指定工具定义并让模型决定何时使用它们。

• 定义函数模式。
• 解析响应中的工具调用。

Copyfrom openai import OpenAI

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

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

此功能允许与外部系统集成。

限制、错误和上下文窗口

监控使用情况以避免速率限制或错误。上下文窗口支持总共 100,000 个 token。

• 处理无效密钥的 401 错误。
• 处理余额不足的 402 错误。
• 处理 429 速率限制错误。

Copycurl https://api.openaicodexapi.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Explain how prepaid billing works for this API."}]
  }'

Copyfrom openai import OpenAI

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

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openaicodexapi.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)