openlit 1.34.8__py3-none-any.whl → 1.34.11__py3-none-any.whl

openlit/instrumentation/groq/utils.py

@@ -0,0 +1,199 @@
+"""
+Groq OpenTelemetry instrumentation utility functions
+"""
+import time
+
+from opentelemetry.trace import Status, StatusCode
+
+from openlit.__helpers import (
+    calculate_ttft,
+    response_as_dict,
+    calculate_tbt,
+    get_chat_model_cost,
+    common_span_attributes,
+    record_completion_metrics,
+)
+from openlit.semcov import SemanticConvention
+
+def format_content(messages):
+    """
+    Process a list of messages to extract content.
+    """
+
+    formatted_messages = []
+    for message in messages:
+        role = message["role"]
+        content = message["content"]
+
+        if isinstance(content, list):
+            content_str = ", ".join(
+                f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
+                if "type" in item else f'text: {item["text"]}'
+                for item in content
+            )
+            formatted_messages.append(f"{role}: {content_str}")
+        else:
+            formatted_messages.append(f"{role}: {content}")
+
+    return "\n".join(formatted_messages)
+
+def process_chunk(scope, chunk):
+    """
+    Process a chunk of response data and update state.
+    """
+
+    end_time = time.time()
+    # Record the timestamp for the current chunk
+    scope._timestamps.append(end_time)
+
+    if len(scope._timestamps) == 1:
+        # Calculate time to first chunk
+        scope._ttft = calculate_ttft(scope._timestamps, scope._start_time)
+
+    chunked = response_as_dict(chunk)
+
+    # Collect message IDs and aggregated response from events
+    if (len(chunked.get("choices", [])) > 0 and
+        "delta" in chunked.get("choices")[0] and
+        "content" in chunked.get("choices")[0].get("delta", {})):
+
+        content = chunked.get("choices")[0].get("delta").get("content")
+        if content:
+            scope._llmresponse += content
+
+    if chunked.get('x_groq') is not None:
+        if chunked.get('x_groq').get('usage') is not None:
+            scope._input_tokens = chunked.get('x_groq').get('usage').get('prompt_tokens')
+            scope._output_tokens = chunked.get('x_groq').get('usage').get('completion_tokens')
+            scope._response_id = chunked.get('x_groq').get('id')
+            scope._response_model = chunked.get('x_groq').get('model')
+            scope._finish_reason = chunked.get('choices', [{}])[0].get('finish_reason')
+            scope._system_fingerprint = chunked.get('x_groq').get('system_fingerprint')
+            scope._end_time = time.time()
+
+
+def common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version, is_stream):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    if len(scope._timestamps) > 1:
+        scope._tbt = calculate_tbt(scope._timestamps)
+
+    prompt = format_content(scope._kwargs.get("messages", []))
+    request_model = scope._kwargs.get("model", "mixtral-8x7b-32768")
+
+    cost = get_chat_model_cost(request_model, pricing_info, scope._input_tokens, scope._output_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_GROQ,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, is_stream, scope._tbt, scope._ttft, version)
+
+    # Span Attributes for Request parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SEED, scope._kwargs.get("seed", ""))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY, scope._kwargs.get("frequency_penalty", 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS, scope._kwargs.get("max_completion_tokens", -1))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY, scope._kwargs.get("presence_penalty", 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_STOP_SEQUENCES, scope._kwargs.get("stop", []))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, scope._kwargs.get("temperature", 1.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get("top_p", 1.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get("user", ""))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SERVICE_TIER, scope._kwargs.get("service_tier", "on_demand"))
+
+    # Span Attributes for Response parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_ID, scope._response_id)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason])
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_SYSTEM_FINGERPRINT, scope._system_fingerprint)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE, "text" if isinstance(scope._llmresponse, str) else "json")
+
+    # Span Attributes for Cost and Tokens
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, scope._output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, scope._input_tokens + scope._output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Tools
+    if scope._tools:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get("function", {}).get("name", ""))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get("id", "")))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get("function", {}).get("arguments", "")))
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, prompt)
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse)
+
+        # To be removed one the change to span_attributes (from span events) is complete
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
+            },
+        )
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_COMPLETION: scope._llmresponse,
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_completion_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_GROQ,
+            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
+            application_name, scope._start_time, scope._end_time, scope._input_tokens, scope._output_tokens,
+            cost, scope._tbt, scope._ttft)
+
+def process_streaming_chat_response(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content=False, disable_metrics=False, version=""):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=True)
+
+def process_chat_response(response, request_model, pricing_info, server_port, server_address,
+    environment, application_name, metrics, start_time, span, capture_message_content=False,
+    disable_metrics=False, version="1.0.0", **kwargs):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    # Create scope object
+    scope = type("GenericScope", (), {})()
+    response_dict = response_as_dict(response)
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._llmresponse = " ".join(
+        (choice.get("message", {}).get("content") or "")
+        for choice in response_dict.get("choices", [])
+    )
+    scope._response_id = response_dict.get("id")
+    scope._response_model = response_dict.get("model")
+    scope._input_tokens = response_dict.get("usage", {}).get("prompt_tokens", 0)
+    scope._output_tokens = response_dict.get("usage", {}).get("completion_tokens", 0)
+    scope._timestamps = []
+    scope._ttft, scope._tbt = scope._end_time - scope._start_time, 0
+    scope._server_address, scope._server_port = server_address, server_port
+    scope._kwargs = kwargs
+    scope._system_fingerprint = response_dict.get("system_fingerprint")
+    scope._finish_reason = str(response_dict.get("choices", [])[0].get("finish_reason", ""))
+
+    # Handle tool calls
+    if scope._kwargs.get("tools"):
+        scope._tools = response_dict.get("choices", [{}])[0].get("message", {}).get("tool_calls")
+    else:
+        scope._tools = None
+
+    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=False)
+
+    return response

openlit/instrumentation/ollama/__init__.py

@@ -41,7 +41,7 @@ def _dispatch_async(async_chat_wrap, async_emb_wrap):
 
 class OllamaInstrumentor(BaseInstrumentor):
     """
-    An instrumentor for Ollama's client library.
+    An instrumentor for Ollama client library.
     """
 
     def instrumentation_dependencies(self) -> Collection[str]:
@@ -51,7 +51,6 @@ class OllamaInstrumentor(BaseInstrumentor):
         application_name = kwargs.get("application_name", "default_application")
         environment = kwargs.get("environment", "default_environment")
         tracer = kwargs.get("tracer")
-        event_provider = kwargs.get("event_provider")
         metrics = kwargs.get("metrics_dict")
         pricing_info = kwargs.get("pricing_info", {})
         capture_message_content = kwargs.get("capture_message_content", False)
@@ -61,22 +60,22 @@ class OllamaInstrumentor(BaseInstrumentor):
         # Build wrapper factories for chat and embeddings
         sync_chat_wrap = chat(
             version, environment, application_name,
-            tracer, event_provider, pricing_info,
+            tracer, pricing_info,
             capture_message_content, metrics, disable_metrics
         )
         sync_emb_wrap = embeddings(
             version, environment, application_name,
-            tracer, event_provider, pricing_info,
+            tracer, pricing_info,
             capture_message_content, metrics, disable_metrics
         )
         async_chat_wrap = async_chat(
             version, environment, application_name,
-            tracer, event_provider, pricing_info,
+            tracer, pricing_info,
             capture_message_content, metrics, disable_metrics
         )
         async_emb_wrap = async_embeddings(
             version, environment, application_name,
-            tracer, event_provider, pricing_info,
+            tracer, pricing_info,
             capture_message_content, metrics, disable_metrics
         )
 

openlit/instrumentation/ollama/async_ollama.py

@@ -2,7 +2,6 @@
 Module for monitoring Ollama API calls.
 """
 
-import logging
 import time
 from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
@@ -17,12 +16,10 @@ from openlit.instrumentation.ollama.utils import (
 )
 from openlit.semcov import SemanticConvention
 
-logger = logging.getLogger(__name__)
-
 def async_chat(version, environment, application_name,
-            tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
+            tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for GenAI function call
+    Generates a telemetry wrapper for Ollama async chat function call
     """
 
     class TracedAsyncStream:
@@ -38,21 +35,21 @@ def async_chat(version, environment, application_name,
                 kwargs,
                 server_address,
                 server_port,
-                **args,
+                args,
             ):
             self.__wrapped__ = wrapped
             self._span = span
             self._llmresponse = ""
             self._response_model = ""
             self._finish_reason = ""
-            self._tool_calls = []
+            self._tools = []
             self._input_tokens = 0
             self._output_tokens = 0
-            self._response_role = ''
+            self._response_role = ""
             self._span_name = span_name
             self._args = args
             self._kwargs = kwargs
-            self._start_time = time.time()
+            self._start_time = time.monotonic()
             self._end_time = None
             self._timestamps = []
             self._ttft = 0
@@ -81,26 +78,25 @@ def async_chat(version, environment, application_name,
                 return chunk
             except StopAsyncIteration:
                 try:
-                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                    with tracer.start_as_current_span(self._span_name, kind=SpanKind.CLIENT) as self._span:
                         process_streaming_chat_response(
                             self,
                             pricing_info=pricing_info,
                             environment=environment,
                             application_name=application_name,
                             metrics=metrics,
-                            event_provider=event_provider,
                             capture_message_content=capture_message_content,
                             disable_metrics=disable_metrics,
                             version=version
                         )
                 except Exception as e:
                     handle_exception(self._span, e)
-                    logger.error("Error in trace creation: %s", e)
+
                 raise
 
     async def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the GenAI function call.
+        Wraps the Ollama async chat function call.
         """
 
         streaming = kwargs.get("stream", False)
@@ -111,26 +107,73 @@ def async_chat(version, environment, application_name,
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        # pylint: disable=no-else-return
         if streaming:
             awaited_wrapped = await wrapped(*args, **kwargs)
             span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
-            return TracedAsyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
+            return TracedAsyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port, args)
 
         else:
-            with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
-                start_time = time.time()
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+                start_time = time.monotonic()
+
+                try:
+                    response = await wrapped(*args, **kwargs)
+
+                    response = process_chat_response(
+                        response=response,
+                        gen_ai_endpoint="ollama.chat",
+                        pricing_info=pricing_info,
+                        server_port=server_port,
+                        server_address=server_address,
+                        environment=environment,
+                        application_name=application_name,
+                        metrics=metrics,
+                        start_time=start_time,
+                        span=span,
+                        capture_message_content=capture_message_content,
+                        disable_metrics=disable_metrics,
+                        version=version,
+                        **kwargs
+                    )
+
+                except Exception as e:
+                    handle_exception(span, e)
+
+            return response
+
+    return wrapper
+
+def async_embeddings(version, environment, application_name,
+              tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for Ollama async embeddings function call
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the Ollama async embeddings function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 11434)
+        request_model = kwargs.get("model")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+            start_time = time.monotonic()
+
+            try:
                 response = await wrapped(*args, **kwargs)
-                response = process_chat_response(
+
+                response = process_embedding_response(
                     response=response,
-                    request_model=request_model,
+                    gen_ai_endpoint="ollama.embeddings",
                     pricing_info=pricing_info,
                     server_port=server_port,
                     server_address=server_address,
                     environment=environment,
                     application_name=application_name,
                     metrics=metrics,
-                    event_provider=event_provider,
                     start_time=start_time,
                     span=span,
                     capture_message_content=capture_message_content,
@@ -139,47 +182,8 @@ def async_chat(version, environment, application_name,
                     **kwargs
                 )
 
-            return response
-
-    return wrapper
-
-def async_embeddings(version, environment, application_name,
-              tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for GenAI function call
-    """
-
-    async def wrapper(wrapped, instance, args, kwargs):
-        """
-        Wraps the GenAI function call.
-        """
-
-        server_address, server_port = set_server_address_and_port(instance, '127.0.0.1', 11434)
-        json_body = kwargs.get('json', {}) or {}
-        request_model = json_body.get('model') or kwargs.get('model')
-
-        span_name = f'{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}'
-
-        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
-            start_time = time.time()
-            response = await wrapped(*args, **kwargs)
-            response = process_embedding_response(
-                response=response,
-                request_model=request_model,
-                pricing_info=pricing_info,
-                server_port=server_port,
-                server_address=server_address,
-                environment=environment,
-                application_name=application_name,
-                metrics=metrics,
-                event_provider=event_provider,
-                start_time=start_time,
-                span=span,
-                capture_message_content=capture_message_content,
-                disable_metrics=disable_metrics,
-                version=version,
-                **kwargs
-            )
+            except Exception as e:
+                handle_exception(span, e)
 
         return response
 

openlit/instrumentation/ollama/ollama.py

@@ -2,7 +2,6 @@
 Module for monitoring Ollama API calls.
 """
 
-import logging
 import time
 from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
@@ -17,12 +16,10 @@ from openlit.instrumentation.ollama.utils import (
 )
 from openlit.semcov import SemanticConvention
 
-logger = logging.getLogger(__name__)
-
 def chat(version, environment, application_name,
-            tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
+            tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for GenAI function call
+    Generates a telemetry wrapper for Ollama chat function call
     """
 
     class TracedSyncStream:
@@ -38,21 +35,21 @@ def chat(version, environment, application_name,
                 kwargs,
                 server_address,
                 server_port,
-                **args,
+                args,
             ):
             self.__wrapped__ = wrapped
             self._span = span
             self._llmresponse = ""
             self._response_model = ""
             self._finish_reason = ""
-            self._tool_calls = []
+            self._tools = []
             self._input_tokens = 0
             self._output_tokens = 0
-            self._response_role = ''
+            self._response_role = ""
             self._span_name = span_name
             self._args = args
             self._kwargs = kwargs
-            self._start_time = time.time()
+            self._start_time = time.monotonic()
             self._end_time = None
             self._timestamps = []
             self._ttft = 0
@@ -81,26 +78,25 @@ def chat(version, environment, application_name,
                 return chunk
             except StopIteration:
                 try:
-                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                    with tracer.start_as_current_span(self._span_name, kind=SpanKind.CLIENT) as self._span:
                         process_streaming_chat_response(
                             self,
                             pricing_info=pricing_info,
                             environment=environment,
                             application_name=application_name,
                             metrics=metrics,
-                            event_provider=event_provider,
                             capture_message_content=capture_message_content,
                             disable_metrics=disable_metrics,
                             version=version
                         )
                 except Exception as e:
                     handle_exception(self._span, e)
-                    logger.error("Error in trace creation: %s", e)
+
                 raise
 
     def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the GenAI function call.
+        Wraps the Ollama chat function call.
         """
 
         streaming = kwargs.get("stream", False)
@@ -111,26 +107,73 @@ def chat(version, environment, application_name,
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        # pylint: disable=no-else-return
         if streaming:
             awaited_wrapped = wrapped(*args, **kwargs)
             span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
-            return TracedSyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
+            return TracedSyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port, args)
 
         else:
-            with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
-                start_time = time.time()
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+                start_time = time.monotonic()
+
+                try:
+                    response = wrapped(*args, **kwargs)
+
+                    response = process_chat_response(
+                        response=response,
+                        gen_ai_endpoint="ollama.chat",
+                        pricing_info=pricing_info,
+                        server_port=server_port,
+                        server_address=server_address,
+                        environment=environment,
+                        application_name=application_name,
+                        metrics=metrics,
+                        start_time=start_time,
+                        span=span,
+                        capture_message_content=capture_message_content,
+                        disable_metrics=disable_metrics,
+                        version=version,
+                        **kwargs
+                    )
+
+                except Exception as e:
+                    handle_exception(span, e)
+
+            return response
+
+    return wrapper
+
+def embeddings(version, environment, application_name,
+              tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for Ollama embeddings function call
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the Ollama embeddings function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 11434)
+        request_model = kwargs.get("model")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+            start_time = time.monotonic()
+
+            try:
                 response = wrapped(*args, **kwargs)
-                response = process_chat_response(
+
+                response = process_embedding_response(
                     response=response,
-                    request_model=request_model,
+                    gen_ai_endpoint="ollama.embeddings",
                     pricing_info=pricing_info,
                     server_port=server_port,
                     server_address=server_address,
                     environment=environment,
                     application_name=application_name,
                     metrics=metrics,
-                    event_provider=event_provider,
                     start_time=start_time,
                     span=span,
                     capture_message_content=capture_message_content,
@@ -139,47 +182,8 @@ def chat(version, environment, application_name,
                     **kwargs
                 )
 
-            return response
-
-    return wrapper
-
-def embeddings(version, environment, application_name,
-              tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for GenAI function call
-    """
-
-    def wrapper(wrapped, instance, args, kwargs):
-        """
-        Wraps the GenAI function call.
-        """
-
-        server_address, server_port = set_server_address_and_port(instance, '127.0.0.1', 11434)
-        json_body = kwargs.get('json', {}) or {}
-        request_model = json_body.get('model') or kwargs.get('model')
-
-        span_name = f'{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}'
-
-        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
-            start_time = time.time()
-            response = wrapped(*args, **kwargs)
-            response = process_embedding_response(
-                response=response,
-                request_model=request_model,
-                pricing_info=pricing_info,
-                server_port=server_port,
-                server_address=server_address,
-                environment=environment,
-                application_name=application_name,
-                metrics=metrics,
-                event_provider=event_provider,
-                start_time=start_time,
-                span=span,
-                capture_message_content=capture_message_content,
-                disable_metrics=disable_metrics,
-                version=version,
-                **kwargs
-            )
+            except Exception as e:
+                handle_exception(span, e)
 
         return response