Client-Side Load Balancing

from ironlabsai import IronlabsAI

client = IronlabsAI(
    reliability={
        "weights": {
            "openai/gpt-4o": 0.7,
            "anthropic/claude-3-5-haiku-20241022": 0.3
        },
        "max_retries": {
            "openai/gpt-4o": 2,
            "anthropic/claude-3-5-haiku-20241022": 1
        },
        "timeout": {
            "openai/gpt-4o": 5.0,
            "anthropic/claude-3-5-haiku-20241022": 5.0
        },
        "backoff": {
            "openai/gpt-4o": 2.0,
            "anthropic/claude-3-5-haiku-20241022": 1.0
        },
        "model_messages": {
            "openai/gpt-4o": [{"role": "user", "content": "Please provide a concise response."}],
            "anthropic/claude-3-5-haiku-20241022": [{"role": "user", "content": "Keep it short."}]
        }
    }
)

response = client.completions.create(
    messages=[{"role": "user", "content": "Write a haiku about the ocean."}]
)
print(response.choices[0].message.content)
print("Model used:", response.model)

from ironlabsai import IronlabsAI

client = IronlabsAI(
    reliability={
        "failover_chain": [
            {
                "model": "openai/gpt-4o",
                "max_retries": 2,
                "timeout": 5.0,
                "backoff": 1.0,
                "messages": [{"role": "user", "content": "Respond concisely."}]
            },
            {
                "model": "anthropic/claude-3-5-haiku-20241022",
                "max_retries": 1,
                "timeout": 5.0,
                "backoff": 2.0,
                "messages": [{"role": "user", "content": "Keep it brief."}]
            }
        ]
    }
)

response = client.completions.create(
    messages=[{"role": "user", "content": "Describe a sunset."}]
)
print(response.choices[0].message.content)
print("Model used:", response.model)