OpenAI
This integration connects Sentry with the OpenAI Python SDK. The integration has been confirmed to work with OpenAI 1.13.3.
Install sentry-sdk
from PyPI with the openai
extra:
pip install --upgrade 'sentry-sdk[openai]'
If you have the openai
package in your dependencies, the OpenAI integration will be enabled automatically when you initialize the Sentry SDK.
An additional dependency, tiktoken
, is required if you want to calculate token usage for streaming chat responses.
from openai import OpenAI
import sentry_sdk
sentry_sdk.init(
dsn="https://examplePublicKey@o0.ingest.sentry.io/0",
enable_tracing=True,
traces_sample_rate=1.0,
)
client = OpenAI()
Verify that the integration works by inducing an error. The error and performance transaction should appear in your Sentry project.
from openai import OpenAI
import sentry_sdk
sentry_sdk.init(...) # same as above
client = OpenAI(api_key="a bad API key")
with sentry_sdk.start_transaction(op="ai-inference", name="The result of the AI inference"):
response = (
client.chat.completions.create(
model="some-model", messages=[{"role": "system", "content": "hello"}]
)
.choices[0]
.message.content
)
print(response)
After running this script, a transaction will be created in the Performance section of sentry.io. Additionally, an error event (about the bad API key) will be sent to sentry.io and will be connected to the transaction.
It takes a couple of moments for the data to appear in sentry.io.
The OpenAI integration will connect Sentry with all supported OpenAI methods automatically.
All exceptions leading to an OpenAIException are reported.
The supported modules are currently
chat.completions.create
andembeddings.create
.Sentry is configured not to consider LLM and tokenizer inputs/outputs as PII. If you want to include them, set
send_default_pii=True
in thesentry_sdk.init()
call. To explicitly exclude prompts despitesend_default_pii=True
, configure the integration withinclude_prompts=False
like in the Options section.
By adding OpenAIIntegration
to your sentry_sdk.init()
call explicitly, you can set options for OpenAIIntegration
to change its behavior:
import sentry_sdk
from sentry_sdk.integrations.openai import OpenAIIntegration
sentry_sdk.init(
dsn="https://examplePublicKey@o0.ingest.sentry.io/0",
enable_tracing=True,
send_default_pii=True,
traces_sample_rate=1.0,
integrations = [
OpenAIIntegration(
include_prompts=False, # LLM/tokenizer inputs/outputs will be not sent to Sentry, despite send_default_pii=True
),
],
)
- OpenAI: 1.0+
- tiktoken: 0.6.0+
- Python: 3.9+
Our documentation is open source and available on GitHub. Your contributions are welcome, whether fixing a typo (drat!) or suggesting an update ("yeah, this would be better").
- Package:
- pypi:sentry-sdk
- Version:
- 1.45.0
- Repository:
- https://github.com/getsentry/sentry-python
- API Documentation:
- https://getsentry.github.io/sentry-python/