اتصال کلاینت

export ANTHROPIC_BASE_URL="https://gateway.example.com"
export ANTHROPIC_AUTH_TOKEN="${HOOSHYAR_API_KEY}"

# Optional: pin every request from this shell to one route instead of
# letting the classifier choose per message.
# export ANTHROPIC_CUSTOM_HEADERS="x-task-type: <ROUTE_NAME>"

models:
  - name: Hooshyar
    provider: openai
    apiBase: https://gateway.example.com/v1
    apiKey: ${HOOSHYAR_API_KEY}
    model: auto
    roles:
      - chat
      - edit

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.example.com/v1",
    api_key=os.environ["HOOSHYAR_API_KEY"],
    max_retries=2,  # 3 tries in total, with backoff and jitter
)

resp = client.chat.completions.create(
    model="auto",  # a ROUTE name; use "auto" to let the classifier choose
    messages=[{"role": "user", "content": "Hello"}],
)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.example.com/v1",
  apiKey: process.env.HOOSHYAR_API_KEY!,
  maxRetries: 2, // 3 tries in total, with backoff and jitter
});

const resp = await client.chat.completions.create({
  model: "auto", // a ROUTE name; use "auto" to let the classifier choose
  messages: [{ role: "user", content: "Hello" }],
});

// Retry a refused or reset connection and a 502, 503 or 504. 3 tries,
// about 30 s at most. Every other status is the answer: return it.
const RETRY_STATUS = new Set([502, 503, 504]);
const BASE_DELAY_MS = [2_000, 8_000]; // before try 2, before try 3

export async function complete(body: object, sessionId: string): Promise<Response> {
  for (let attempt = 0; ; attempt++) {
    const last = attempt >= BASE_DELAY_MS.length;
    try {
      const res = await fetch("https://gateway.example.com/v1/chat/completions", {
        method: "POST",
        headers: {
          Authorization: `Bearer ${process.env.HOOSHYAR_API_KEY}`,
          "Content-Type": "application/json",
          "x-session-id": sessionId, // the same id on every try
        },
        body: JSON.stringify(body),
      });
      if (last || !RETRY_STATUS.has(res.status)) return res;
      await res.body?.cancel();
      await sleep(delayMs(attempt, res.headers.get("retry-after")));
    } catch (err) {
      if (last) throw err; // refused, reset, DNS: no answer at all
      await sleep(delayMs(attempt, null));
    }
  }
}

// Retry-After when the gateway sends one (max 15 s), else 50-100 % of the base.
function delayMs(attempt: number, retryAfter: string | null): number {
  const seconds = Number(retryAfter);
  if (seconds > 0) return Math.min(seconds, 15) * 1_000;
  const base = BASE_DELAY_MS[attempt]!;
  return base / 2 + Math.random() * (base / 2);
}

const sleep = (ms: number) => new Promise((resolve) => setTimeout(resolve, ms));

// One session per conversation. A stream that breaks after the first token
// is NOT retried: fetch returns at the headers, so the read error reaches you.
// Show the partial answer, or tell the user and start the turn again.
const res = await complete({ model: "auto", messages }, `chat-${chatId}`);

curl https://gateway.example.com/v1/chat/completions \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -H "Content-Type: application/json" \
  -H "x-task-type: auto" \
  -d '{"model":"auto","messages":[{"role":"user","content":"ping"}]}'

curl https://gateway.example.com/v1/images/generations \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","prompt":"a wide shot of a lighthouse at dusk","n":1}'

# Editing an existing image is multipart, and the model is a FORM FIELD —
# send it BEFORE the file part (see the note below).
curl https://gateway.example.com/v1/images/edits \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -F "model=<MODEL_ID>" \
  -F "prompt=make the sky clearer" \
  -F "image=@photo.png"

# Speech (text in, AUDIO BYTES out) — routed to the `tts` route,
# priced per character of input.
curl https://gateway.example.com/v1/audio/speech \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"model":"auto","input":"Hello from Hooshyar.","voice":"alloy"}' \
  --output speech.mp3

# Transcription (multipart) — name a concrete model, `model` first.
curl https://gateway.example.com/v1/audio/transcriptions \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -F "model=<MODEL_ID>" \
  -F "file=@meeting.m4a"

# 1. Upload the input file (one JSON request per line).
curl https://gateway.example.com/v1/files \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -F "purpose=batch" \
  -F "file=@requests.jsonl"

# 2. Submit the batch, naming the file id from step 1.
curl https://gateway.example.com/v1/batches \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"input_file_id":"file-…","endpoint":"/v1/chat/completions","completion_window":"24h"}'

# 3. Poll it. When the provider finishes, this is also what records the
#    cost — so polling your own batch is doing everyone a favour.
curl https://gateway.example.com/v1/batches/batch_… \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}"

curl https://gateway.example.com/v1/rerank \
  -H "Authorization: Bearer ${HOOSHYAR_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model":"auto",
    "query":"how do I rotate a client key",
    "documents":["key rotation guide","billing FAQ","routing overview"]
  }'