Fouthantering

import openai
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1",
)

try:
    client.chat.completions.create(
        model="no-such-model",
        messages=[{"role": "user", "content": "Hello"}],
    )
except openai.APIStatusError as error:
    print(error.status_code)                           # 400
    print(error.type)                                  # invalid_request_error
    print(error.body["message"])                       # unknown model: no-such-model
    print(error.response.headers.get("x-request-id"))  # the id of this request

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.shannon-ai.com/v1",
});

try {
  await client.chat.completions.create({
    model: "no-such-model",
    messages: [{ role: "user", content: "Hello" }],
  });
} catch (error) {
  if (!(error instanceof OpenAI.APIError)) throw error;
  console.log(error.status);         // 400
  console.log(error.type);           // invalid_request_error
  console.log(error.error.message);  // unknown model: no-such-model
}

curl -i https://api.shannon-ai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "no-such-model",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import re
import time

import openai
from openai import OpenAI

# max_retries=0: this loop does the retrying, the SDK does not add its own.
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.shannon-ai.com/v1", max_retries=0)


def create_with_retry(attempts=5, **request):
    for attempt in range(attempts):
        try:
            return client.chat.completions.create(**request)
        except openai.RateLimitError as error:
            text = str(error)
            flood = re.search(r"Retry in (\d+)s", text)
            if flood:
                time.sleep(int(flood.group(1)))   # flood protection: wait out the minute
            elif "temporarily busy" in text:
                time.sleep(2 ** attempt)
            else:
                raise                             # balance: a wait of seconds does not help
        except (openai.InternalServerError, openai.APIConnectionError):
            time.sleep(2 ** attempt)              # 1, 2, 4, 8 seconds
    raise RuntimeError("the request failed after all attempts")


response = create_with_retry(
    model="shannon-3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

// maxRetries: 0 — this loop does the retrying, the SDK does not add its own.
const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://api.shannon-ai.com/v1", maxRetries: 0 });

const sleep = (seconds) => new Promise((resolve) => setTimeout(resolve, seconds * 1000));

async function createWithRetry(request, attempts = 5) {
  for (let attempt = 0; attempt < attempts; attempt++) {
    try {
      return await client.chat.completions.create(request);
    } catch (error) {
      const text = String(error.message);
      const flood = text.match(/Retry in (\d+)s/);
      if (error.status === 429 && flood) {
        await sleep(Number(flood[1]));            // flood protection: wait out the minute
      } else if (error.status === 429 && text.includes("temporarily busy")) {
        await sleep(2 ** attempt);
      } else if (error.status >= 500 || error instanceof OpenAI.APIConnectionError) {
        await sleep(2 ** attempt);                // 1, 2, 4, 8 seconds
      } else {
        throw error;                              // wrong request, wrong key or balance
      }
    }
  }
  throw new Error("the request failed after all attempts");
}

const response = await createWithRetry({
  model: "shannon-3",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);