Skip to main content

Sentry - Log LLM Exceptions

Sentry provides error monitoring for production. LiteLLM can add breadcrumbs and send exceptions to Sentry with this integration

Track exceptions for:

  • litellm.completion() - completion()for 100+ LLMs
  • litellm.acompletion() - async completion()
  • Streaming completion() & acompletion() calls

Usage

Set SENTRY_DSN & callback

import litellm, os
os.environ["SENTRY_DSN"] = "your-sentry-url"
litellm.failure_callback=["sentry"]

Sentry callback with completion

import litellm
from litellm import completion

litellm.input_callback=["sentry"] # adds sentry breadcrumbing
litellm.failure_callback=["sentry"] # [OPTIONAL] if you want litellm to capture -> send exception to sentry

import os
os.environ["SENTRY_DSN"] = "your-sentry-url"
os.environ["OPENAI_API_KEY"] = "your-openai-key"

# set bad key to trigger error
api_key="bad-key"
response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hey!"}], stream=True, api_key=api_key)

print(response)

Let us know if you need any additional options from Sentry.