The Quotient Python SDK ships with an asynchronous client for applications that already run an event loop. The API mirrors the synchronous surface but returns coroutines instead of concrete values.

​
Example Workflow

import asyncio

from quotientai import AsyncQuotientAI, DetectionType

async def main() -> None:
    quotient = AsyncQuotientAI(api_key="your-quotient-api-key")

    quotient.logger.init(
        app_name="async-support-bot",
        environment="dev",
        detections=[DetectionType.HALLUCINATION, DetectionType.DOCUMENT_RELEVANCY],
        detection_sample_rate=1.0,
    )

    log_id = await quotient.log(
        user_query="How do I cook a goose?",
        model_output="The capital of France is Paris.",
        documents=["Here is an excellent goose recipe..."],
    )

    logs = await quotient.logs.list()
    print("Created log:", log_id)
    print("Fetched", len(logs), "logs")

if __name__ == "__main__":
    asyncio.run(main())

​
Notes

  • Initialization remains synchronous; call it once during startup before issuing async logging calls.
  • The async client shares authentication and configuration options with the synchronous client.
  • When using frameworks such as FastAPI or LangChain that already use asyncio, prefer AsyncQuotientAI to avoid blocking the event loop.
Back: Retrieve Logs