Merge pull request #5059 from BerriAI/litelm_log_otel_args

OTEL - Log DB queries / functions on OTEL

litellm/_service_logger.py

@@ -97,6 +97,7 @@ class ServiceLogging(CustomLogger):
         parent_otel_span: Optional[Span] = None,
         start_time: Optional[Union[datetime, float]] = None,
         end_time: Optional[Union[float, datetime]] = None,
+        event_metadata: Optional[dict] = None,
     ):
         """
         - For counting if the redis, postgres call is unsuccessful
@@ -127,12 +128,16 @@ class ServiceLogging(CustomLogger):
 
         from litellm.proxy.proxy_server import open_telemetry_logger
 
-        if parent_otel_span is not None and open_telemetry_logger is not None:
+        if not isinstance(error, str):
+            error = str(error)
+        if open_telemetry_logger is not None:
             await open_telemetry_logger.async_service_failure_hook(
                 payload=payload,
                 parent_otel_span=parent_otel_span,
                 start_time=start_time,
                 end_time=end_time,
+                event_metadata=event_metadata,
+                error=error,
             )
 
     async def async_post_call_failure_hook(

litellm/integrations/opentelemetry.py

@@ -153,6 +153,11 @@ class OpenTelemetry(CustomLogger):
 
             if event_metadata:
                 for key, value in event_metadata.items():
+                    if isinstance(value, dict):
+                        try:
+                            value = str(value)
+                        except Exception:
+                            value = "litllm logging error - could_not_json_serialize"
                     service_logging_span.set_attribute(key, value)
             service_logging_span.set_status(Status(StatusCode.OK))
             service_logging_span.end(end_time=_end_time_ns)
@@ -160,9 +165,11 @@ class OpenTelemetry(CustomLogger):
     async def async_service_failure_hook(
         self,
         payload: ServiceLoggerPayload,
+        error: Optional[str] = "",
         parent_otel_span: Optional[Span] = None,
         start_time: Optional[Union[datetime, float]] = None,
         end_time: Optional[Union[float, datetime]] = None,
+        event_metadata: Optional[dict] = None,
     ):
         from datetime import datetime
 
@@ -193,6 +200,17 @@ class OpenTelemetry(CustomLogger):
             service_logging_span.set_attribute(
                 key="service", value=payload.service.value
             )
+            if error:
+                service_logging_span.set_attribute(key="error", value=error)
+            if event_metadata:
+                for key, value in event_metadata.items():
+                    if isinstance(value, dict):
+                        try:
+                            value = str(value)
+                        except Exception:
+                            value = "litllm logging error - could_not_json_serialize"
+                    service_logging_span.set_attribute(key, value)
+
             service_logging_span.set_status(Status(StatusCode.ERROR))
             service_logging_span.end(end_time=_end_time_ns)
 

litellm/proxy/proxy_config.yaml

@@ -26,18 +26,6 @@ model_list:
     model_info:
       mode: audio_speech
 
-# For /fine_tuning/jobs endpoints
-finetune_settings:
-  - custom_llm_provider: azure
-    api_base: https://exampleopenaiendpoint-production.up.railway.app
-    api_key: fake-key
-    api_version: "2023-03-15-preview"
-  - custom_llm_provider: openai
-    api_key: os.environ/OPENAI_API_KEY
-  - custom_llm_provider: "vertex_ai"
-    vertex_project: "adroit-crow-413218"
-    vertex_location: "us-central1"
-    vertex_credentials: "/Users/ishaanjaffer/Downloads/adroit-crow-413218-a956eef1a2a8.json"
 
 # for /files endpoints
 files_settings:
@@ -48,18 +36,11 @@ files_settings:
   - custom_llm_provider: openai
     api_key: os.environ/OPENAI_API_KEY
 
-default_vertex_config:
-  vertex_project: "adroit-crow-413218"
-  vertex_location: "us-central1"
-  vertex_credentials: "/Users/ishaanjaffer/Downloads/adroit-crow-413218-a956eef1a2a8.json"
-
 
 
 general_settings: 
   master_key: sk-1234
 
-  # Security controls
-  max_request_size_mb: 100
-  # google cloud run maximum repsonses size is 32MB
-  max_response_size_mb: 10
 
+litellm_settings:
+  callbacks: ["otel"] # 👈 KEY CHANGE

litellm/proxy/utils.py

@@ -128,6 +128,11 @@ def log_to_opentelemetry(func):
                     duration=0.0,
                     start_time=start_time,
                     end_time=end_time,
+                    event_metadata={
+                        "function_name": func.__name__,
+                        "function_kwargs": kwargs,
+                        "function_args": args,
+                    },
                 )
             elif (
                 # in litellm custom callbacks kwargs is passed as arg[0]
@@ -167,9 +172,15 @@ def log_to_opentelemetry(func):
                     error=e,
                     service=ServiceTypes.DB,
                     call_type=func.__name__,
+                    parent_otel_span=kwargs["parent_otel_span"],
                     duration=0.0,
                     start_time=start_time,
                     end_time=end_time,
+                    event_metadata={
+                        "function_name": func.__name__,
+                        "function_kwargs": kwargs,
+                        "function_args": args,
+                    },
                 )
             raise e