OpenAI codex API：使用 Python 快速入門

安裝官方 SDK

使用官方 SDK 以確保與我們 openai 代理 API 的兼容性。此方法適用於任何支持 OpenAI 協議的標準庫。

• 透過您偏好的套件管理器安裝套件。
• 透過匯入程式庫來驗證安裝。

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);

設置您的 Base URL 和密鑰

將您的客戶端指向我們的 OpenAI 閘道器端點以存取無審查的 AI 模型。將預設的基礎 URL 替換為我們的特定端點。

• 在您的環境變數中設定 API 金鑰。
• 將基礎 URL 配置為 https://api.openaicodexapi.com/v1.

此設定確保您的請求正確路由至我們的伺服器，且無需修改現有的程式碼結構。

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."}]
  }'

發送您的第一個請求

發送簡單的文本完成請求以測試連線。使用模型 ID uncensored 用於請求。

• 定義訊息內容。
• 執行請求。

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);

回應直接返回生成的文字。

啟用串流與 JSON 模式

串流回應以降低延遲，或啟用 JSON 模式以獲取結構化資料。設定 stream=true 用於即時 token 交付。

• 使用 response_format for JSON 輸出。
• 在程式碼中處理區塊。

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."}]
  }'

串流有助於您快速顯示部分結果。

處理工具與函式呼叫

在請求中定義工具以啟用函式呼叫。指定工具定義並讓模型決定何時使用它們。

• 定義函式架構。
• 從回應中解析工具呼叫。

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);

此功能允許與外部系統整合。

限制、錯誤與上下文視窗

監控您的使用情況以避免速率限制或錯誤。上下文視窗支援總計 100,000 個 token。

• 處理無效金鑰的 401 錯誤。
• 處理餘額不足的 402 錯誤。
• 處理速率限制的 429 錯誤。

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)