Add sentry sample rate (#10283)

* Add SENTRY_API_SAMPLE_RATE configuration option for Sentry SDK

* removed print line

* Update Sentry documentation with sample rate information

---------

Co-authored-by: Vinnie <vinnie@Vinnies-MacBook-Pro.local>

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

@@ -49,6 +49,18 @@ response = completion(model="gpt-3.5-turbo", messages=[{"role": "user", "content
 print(response)
 ```
 
+#### Sample Rate Options
+
+- **SENTRY_API_SAMPLE_RATE**: Controls what percentage of errors are sent to Sentry
+  - Value between 0 and 1 (default is 1.0 or 100% of errors)
+  - Example: 0.5 sends 50% of errors, 0.1 sends 10% of errors
+
+- **SENTRY_API_TRACE_RATE**: Controls what percentage of transactions are sampled for performance monitoring
+  - Value between 0 and 1 (default is 1.0 or 100% of transactions)
+  - Example: 0.5 traces 50% of transactions, 0.1 traces 10% of transactions
+
+These options are useful for high-volume applications where sampling a subset of errors and transactions provides sufficient visibility while managing costs.
+
 ## Redacting Messages, Response Content from Sentry Logging 
 
 Set `litellm.turn_off_message_logging=True` This will prevent the messages and responses from being logged to sentry, but request metadata will still be logged.

docs/my-website/docs/proxy/logging.md

@@ -2375,6 +2375,9 @@ pip install --upgrade sentry-sdk
 
 ```shell
 export SENTRY_DSN="your-sentry-dsn"
+# Optional: Configure Sentry sampling rates
+export SENTRY_API_SAMPLE_RATE="1.0"  # Controls what percentage of errors are sent (default: 1.0 = 100%)
+export SENTRY_API_TRACE_RATE="1.0"   # Controls what percentage of transactions are sampled for performance monitoring (default: 1.0 = 100%)
 ```
 
 ```yaml 

litellm/litellm_core_utils/litellm_logging.py

@@ -2691,9 +2691,15 @@ def set_callbacks(callback_list, function_id=None):  # noqa: PLR0915
                     if "SENTRY_API_TRACE_RATE" in os.environ
                     else "1.0"
                 )
+                sentry_sample_rate = (
+                    os.environ.get("SENTRY_API_SAMPLE_RATE")
+                    if "SENTRY_API_SAMPLE_RATE" in os.environ
+                    else "1.0"
+                )
                 sentry_sdk_instance.init(
                     dsn=os.environ.get("SENTRY_DSN"),
                     traces_sample_rate=float(sentry_trace_rate),  # type: ignore
+                    sample_rate=float(sentry_sample_rate),
                 )
                 capture_exception = sentry_sdk_instance.capture_exception
                 add_breadcrumb = sentry_sdk_instance.add_breadcrumb

tests/test_litellm/litellm_core_utils/test_litellm_logging.py

@@ -11,7 +11,7 @@ sys.path.insert(
 
 import time
 
-from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging
+from litellm.litellm_core_utils.litellm_logging import Logging as LitellmLogging, set_callbacks
 
 
 @pytest.fixture
@@ -34,6 +34,32 @@ def test_get_masked_api_base(logging_obj):
     assert type(masked_api_base) == str
 
 
+def test_sentry_sample_rate():
+    existing_sample_rate = os.getenv("SENTRY_API_SAMPLE_RATE")
+    try:
+        # test with default value by removing the environment variable
+        if existing_sample_rate:
+            del os.environ["SENTRY_API_SAMPLE_RATE"]
+
+        set_callbacks(["sentry"])
+        # Check if the default sample rate is set to 1.0
+        assert os.environ.get("SENTRY_API_SAMPLE_RATE") == "1.0"
+
+        # test with custom value
+        os.environ["SENTRY_API_SAMPLE_RATE"] = "0.5"
+
+        set_callbacks(["sentry"])
+        # Check if the custom sample rate is set correctly
+        assert os.environ.get("SENTRY_API_SAMPLE_RATE") == "0.5"
+    except Exception as e:
+        print(f"Error: {e}")
+    finally:
+        # Restore the original environment variable
+        if existing_sample_rate:
+            os.environ["SENTRY_API_SAMPLE_RATE"] = existing_sample_rate
+        else:
+            if "SENTRY_API_SAMPLE_RATE" in os.environ:
+                del os.environ["SENTRY_API_SAMPLE_RATE"]
 def test_use_custom_pricing_for_model():
     from litellm.litellm_core_utils.litellm_logging import use_custom_pricing_for_model