litellm-mirror/docs/my-website/docs/observability/sentry.md

Sentry Tutorial

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

This works on normal, async and streaming completion calls

usage

import litellm
from litellm import completion 
litellm.set_verbose = True

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_API_URL"] = "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.