API Codex OpenAI: Quickstart dengan Python

Instal SDK Resmi

Gunakan SDK resmi untuk memastikan kompatibilitas dengan proxy API openai kami. Pendekatan ini berfungsi dengan pustaka standar apa pun yang mendukung protokol OpenAI.

• Instal paket melalui manajer paket pilihan Anda.
• Verifikasi instalasi dengan mengimpor library.

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);

Atur URL Dasar dan Kunci Anda

Arahkan klien Anda ke endpoint gerbang openai kami untuk mengakses model AI tanpa sensor. Ganti URL dasar default dengan endpoint khusus kami.

• Atur kunci API di variabel lingkungan Anda.
• Konfigurasikan URL dasar menjadi https://api.openaicodexapi.com/v1.

Konfigurasi ini memastikan permintaan Anda dialihkan dengan benar ke server kami tanpa memodifikasi struktur kode yang ada.

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."}]
  }'

Kirim Permintaan Pertama Anda

Kirim penyelesaian teks sederhana untuk menguji koneksi. Gunakan ID model uncensored untuk permintaan.

• Tentukan konten pesan.
• Eksekusi permintaan.

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);

Respons mengembalikan teks yang dihasilkan langsung.

Aktifkan Streaming dan Mode JSON

Stream respons untuk latensi lebih rendah atau aktifkan mode JSON untuk data terstruktur. Set stream=true untuk pengiriman token waktu nyata.

• Gunakan response_format untuk output JSON.
• Tangani chunk dalam kode Anda.

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."}]
  }'

Streaming membantu Anda menampilkan hasil parsial dengan cepat.

Tangani Alat dan Pemanggilan Fungsi

Tentukan alat dalam permintaan Anda untuk mengaktifkan pemanggilan fungsi. Tentukan definisi alat dan biarkan model memutuskan kapan harus menggunakannya.

• Tentukan skema fungsi.
• Parse panggilan alat dalam respons.

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);

Fitur ini memungkinkan integrasi dengan sistem eksternal.

Batas, Error, dan Jendela Konteks

Pantau penggunaan Anda untuk menghindari batas laju atau kesalahan. Jendela konteks mendukung 100.000 token total.

• Handle error 401 untuk kunci tidak valid.
• Tangani kesalahan 402 untuk kredit tidak cukup.
• Tangani kesalahan 429 untuk batas laju.

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)