import asyncio
from callm import process_requests, RateLimitConfig
from callm.providers import OpenAIProvider

# Configure your provider
provider = OpenAIProvider(
    api_key="sk-...",
    model="gpt-5-mini",
    request_url="https://api.openai.com/v1/responses",
)

# Your data processing requests
products = [
    {"id": 1, "description": "Nike Air Max 90 - Classic sneakers in white/black, size 10"},
    {"id": 2, "description": "Sony WH-1000XM5 Wireless Headphones - Noise cancelling, 30hr battery"},
    # ... thousands more
]

requests = [
    {
        "input": f"Extract brand, category, and key features from: {p['description']}",
        "metadata": {"product_id": p["id"]},
    }
    for p in products
]

async def main():
    results = await process_requests(
        provider=provider,
        requests=requests,
        rate_limit=RateLimitConfig(
            max_requests_per_minute=5_000,    # Stay under your tier limit
            max_tokens_per_minute=2_000_000,
        ),
    )

    print(f"Processed {results.stats.successful} requests in {results.stats.duration_seconds:.1f}s")
    print(f"Tokens used: {results.stats.total_input_tokens + results.stats.total_output_tokens:,}")

    # Access results
    for result in results.successes:
        print(f"Product {result.metadata['product_id']}: {result.response}")

asyncio.run(main())

# 1. List → Memory (small batches)
results = await process_requests(
    provider=provider,
    requests=my_list,
    rate_limit=rate_limit,
)
# Access: results.successes, results.failures

# 2. List → File (persist results)
results = await process_requests(
    provider=provider,
    requests=my_list,
    rate_limit=rate_limit,
    output_path="results.jsonl",
)

# 3. File → File (large batches, low memory)
results = await process_requests(
    provider=provider,
    requests="input.jsonl",
    rate_limit=rate_limit,
    output_path="results.jsonl",
)

# 4. File → Memory (reload saved requests)
results = await process_requests(
    provider=provider,
    requests="input.jsonl",
    rate_limit=rate_limit,
)

from callm import RateLimitConfig, RetryConfig

# Rate limiting (required)
rate_limit = RateLimitConfig(
    max_requests_per_minute=1000,
    max_tokens_per_minute=100_000,
)

# Retry behavior (optional, sensible defaults)
retry = RetryConfig(
    max_attempts=5,
    base_delay_seconds=0.5,
    max_delay_seconds=15.0,
    jitter=0.1,
)

results = await process_requests(
    provider=provider,
    requests=requests,
    rate_limit=rate_limit,
    retry=retry,
)