Python: Middleware

import asyncio
from rail_score_sdk import RAILMiddleware

async def my_llm(messages, **kwargs):
    # आपकी LLM call यहाँ — string return करती है
    return "The LLM generated this response."

async def main():
    mw = RAILMiddleware(
        api_key="YOUR_RAIL_API_KEY",
        generate_fn=my_llm,
        threshold=7.0,
        policy="block",
        eval_input=True,
        input_threshold=5.0,
    )

    result = await mw.run(
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "Explain quantum computing."},
        ]
    )
    print(f"Score: {result.score}, Met threshold: {result.threshold_met}")
    print(f"Content: {result.content}")

asyncio.run(main())

mw = RAILMiddleware(
    api_key="YOUR_RAIL_API_KEY",
    generate_fn=my_llm,
    # कोई threshold नहीं — हर response score होता है लेकिन block नहीं होता
)

result = await mw.run(messages=[...])
print(result.score)        # हमेशा मिलता है
print(result.threshold_met)  # None — कोई threshold set नहीं है

mw = RAILMiddleware(
    api_key="YOUR_RAIL_API_KEY",
    generate_fn=my_llm,
    threshold=7.0,
    policy="regenerate",
    max_iterations=3,
)

result = await mw.run(messages=[...])
print(result.content)           # सभी iterations में से best content
print(result.iterations_taken)  # 1 अगर original pass हो गया