ストリーミングレスポンス

curl https://as.apinoma.com/v1/chat/completions \
  -H "Authorization: Bearer $APINOMA_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "openai/gpt-4o",
    "messages": [{"role": "user", "content": "プログラミングについての詩を書いて"}],
    "stream": true
  }'

import anthropic
 
client = anthropic.Anthropic(
    base_url="https://as.apinoma.com/anthropic",
    api_key="<あなたの APINOMA_API_KEY>"
)
 
with client.messages.stream(
    model="anthropic/claude-sonnet-4.6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "プログラミングについての詩を書いて"}]
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)

stream = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "東京の今日の天気はどうですか？"}],
    tools=[{
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "指定した都市の天気を取得します",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {"type": "string", "description": "都市名"}
                },
                "required": ["city"]
            }
        }
    }],
    stream=True
)
 
for chunk in stream:
    delta = chunk.choices[0].delta
    if delta.tool_calls:
        # ツール呼び出しを処理
        print(f"ツール呼び出し: {delta.tool_calls[0].function}")
    elif delta.content:
        print(delta.content, end="", flush=True)

import time
 
def stream_with_retry(client, max_retries=3, **kwargs):
    for attempt in range(max_retries):
        try:
            stream = client.chat.completions.create(stream=True, **kwargs)
            for chunk in stream:
                yield chunk
            return  # 正常に完了
        except Exception as e:
            if attempt < max_retries - 1:
                wait = 2 ** attempt  # 指数バックオフ
                print(f"\n接続が中断されました。{wait}s 後に再試行します...")
                time.sleep(wait)
            else:
                raise e