Skip to main content

Package to use llm monitoring via LightHouse service

Project description

lighthouse-monitoring

Python package with simple to use decorator for llm monitoring

pip install lighthouse-monitoring

Перед применением:

  1. Поднять основной сервис lighthouse-server
  2. Добавить в него анализаторы admin/add_analyzer/
  3. Создать продукт для конкретной модели admin/add_product/
  4. Для каждого анализатора добавить Vault vault/add/. Для каждого анализатора можно получить пример структуры его вольта vault/example/.
  5. Затем использовать декоратор из данной модели

Пример использования

from lighthouse-monitoring import LightHouseHandler

@LightHouseHandler(
    input_param_name="user_input",
    api_key="****",
    address="http://example.ru:8080",
)
async def llm_process(user_id: str, user_input: str) -> str:
    output = await model(user_input)
    return output

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lighthouse_monitoring-0.1.2.tar.gz (2.6 kB view hashes)

Uploaded Source

Built Distribution

lighthouse_monitoring-0.1.2-py3-none-any.whl (3.4 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page