Anthropic

This integration connects Sentry with the Anthropic Python SDK.

Once you've installed this SDK, you can use Sentry AI Agents Monitoring, a Sentry dashboard that helps you understand what's going on with your AI requests.

Sentry AI Monitoring will automatically collect information about prompts, tools, tokens, and models. Learn more about the AI Agents Dashboard.

Install

Install sentry-sdk from PyPI with the anthropic extra:

pip install "sentry-sdk[anthropic]"

Configure

If you have the anthropic package in your dependencies, the Anthropic integration will be enabled automatically when you initialize the Sentry SDK.

import sentry_sdk

sentry_sdk.init(
    dsn="https://examplePublicKey@o0.ingest.sentry.io/0",
    # Add data like request headers and IP for users, if applicable;
    # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
    send_default_pii=True,
    #  performance
    # Set traces_sample_rate to 1.0 to capture 100%
    # of transactions for tracing.
    traces_sample_rate=1.0,
    #  performance
    #  profiling
    # To collect profiles for all profile sessions,
    # set `profile_session_sample_rate` to 1.0.
    profile_session_sample_rate=1.0,
    # Profiles will be automatically collected while
    # there is an active span.
    profile_lifecycle="trace",
    #  profiling
    #  logs

    # Enable logs to be sent to Sentry
    _experiments={
        "enable_logs": True,
    },
    #  logs
)

Verify

Verify that the integration works by making a chat request to Anthropic.

import sentry_sdk
from anthropic import Anthropic

sentry_sdk.init(...)  # same as above

client = Anthropic(api_key="(your Anthropic key)")

def my_llm_stuff():
    with sentry_sdk.start_transaction(name="The result of the AI inference"):
        print(
            client.messages.create(
                model="claude-3-5-sonnet-20240620",
                max_tokens=1024,
                messages=[{"role": "user", "content": "say hello"}]
            )
            .content[0]
            .text
        )

After running this script, the resulting data should show up in the "AI Spans" tab on the "Explore" > "Traces" > "Trace" page on Sentry.io.

If you manually created an Invoke Agent Span (not done in the example above) the data will also show up in the AI Agents Dashboard.

It may take a couple of moments for the data to appear in sentry.io.

Behavior

• The Anthropic integration will connect Sentry with the supported Anthropic methods automatically.

• The supported function is currently messages.create (both sync and async).

• Sentry considers LLM inputs/outputs as PII (Personally identifiable information) and doesn't include PII data by default. If you want to include the data, set send_default_pii=True in the sentry_sdk.init() call. To explicitly exclude prompts and outputs despite send_default_pii=True, configure the integration with include_prompts=False as shown in the Options section below.

Options

By adding AnthropicIntegration to your sentry_sdk.init() call explicitly, you can set options for AnthropicIntegration to change its behavior:

import sentry_sdk
from sentry_sdk.integrations.anthropic import AnthropicIntegration

sentry_sdk.init(
    # ...
    # Add data like inputs and responses;
    # see https://docs.sentry.io/platforms/python/data-management/data-collected/ for more info
    send_default_pii=True,
    integrations=[
        AnthropicIntegration(
            include_prompts=False,  # LLM inputs/outputs will be not sent to Sentry, despite send_default_pii=True
        ),
    ],
)

You can pass the following keyword arguments to AnthropicIntegration():

• include_prompts:

  Whether LLM inputs and outputs should be sent to Sentry. Sentry considers this data personal identifiable data (PII) by default. If you want to include the data, set send_default_pii=True in the sentry_sdk.init() call. To explicitly exclude prompts and outputs despite send_default_pii=True, configure the integration with include_prompts=False.

  The default is True.

Supported Versions

• Anthropic: 0.16.0+
• Python: 3.8+