openlit 1.34.5__py3-none-any.whl → 1.34.7__py3-none-any.whl

openlit/instrumentation/premai/utils.py

@@ -0,0 +1,325 @@
+"""
+PremAI OpenTelemetry instrumentation utility functions
+"""
+import time
+
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+from opentelemetry.trace import Status, StatusCode
+
+from openlit.__helpers import (
+    response_as_dict,
+    calculate_ttft,
+    calculate_tbt,
+    get_chat_model_cost,
+    get_embed_model_cost,
+    general_tokens,
+    create_metrics_attributes,
+)
+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 chunked.choices:
+        first_choice = chunked.get("choices")[0]
+
+        if first_choice.get("delta").get("content"):
+            scope._llmresponse += first_choice.get("delta").get("content")
+
+    if chunked.get("choices")[0].get("finish_reason"):
+        scope._finish_reason = chunked.get("choices")[0].get("finish_reason")
+        scope._response_id = chunked.get("id")
+        scope._response_model = chunked.get("model")
+
+def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, is_stream, tbt, ttft, version):
+    """
+    Set common span attributes for both chat and RAG operations.
+    """
+
+    scope._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OPERATION, gen_ai_operation)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SYSTEM, gen_ai_system)
+    scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, server_address)
+    scope._span.set_attribute(SemanticConvention.SERVER_PORT, server_port)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model)
+    scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
+    scope._span.set_attribute(SERVICE_NAME, application_name)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM, is_stream)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, scope._tbt)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, scope._ttft)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
+
+def record_completion_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, start_time, end_time,
+    input_tokens, output_tokens, cost, tbt=None, ttft=None):
+    """
+    Record completion-specific metrics for the operation.
+    """
+
+    attributes = create_metrics_attributes(
+        operation=gen_ai_operation,
+        system=gen_ai_system,
+        server_address=server_address,
+        server_port=server_port,
+        request_model=request_model,
+        response_model=response_model,
+        service_name=application_name,
+        deployment_environment=environment,
+    )
+    metrics["genai_client_operation_duration"].record(end_time - start_time, attributes)
+    metrics["genai_requests"].add(1, attributes)
+    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+    metrics["genai_completion_tokens"].add(output_tokens, attributes)
+    metrics["genai_client_usage_tokens"].record(input_tokens + output_tokens, attributes)
+    metrics["genai_cost"].record(cost, attributes)
+    if tbt is not None:
+        metrics["genai_server_tbt"].record(tbt, attributes)
+    if ttft is not None:
+        metrics["genai_server_ttft"].record(ttft, attributes)
+
+def record_embedding_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, start_time, end_time,
+    input_tokens, cost):
+    """
+    Record embedding-specific metrics for the operation.
+    """
+
+    attributes = create_metrics_attributes(
+        operation=gen_ai_operation,
+        system=gen_ai_system,
+        server_address=server_address,
+        server_port=server_port,
+        request_model=request_model,
+        response_model=response_model,
+        service_name=application_name,
+        deployment_environment=environment,
+    )
+    metrics["genai_client_usage_tokens"].record(input_tokens, attributes)
+    metrics["genai_client_operation_duration"].record(end_time - start_time, attributes)
+    metrics["genai_requests"].add(1, attributes)
+    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+    metrics["genai_cost"].record(cost, attributes)
+
+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", "llama3.2-3b")
+
+    # Calculate tokens using input prompt and aggregated response
+    if is_stream:
+        input_tokens = general_tokens(prompt)
+        output_tokens = general_tokens(scope._llmresponse)
+    else:
+        input_tokens = scope._input_tokens
+        output_tokens = scope._output_tokens
+
+    cost = get_chat_model_cost(request_model, pricing_info, input_tokens, output_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,SemanticConvention.GEN_AI_SYSTEM_PREMAI,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, is_stream, scope._tbt, scope._ttft, version)
+
+    # Span Attributes for Response parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason])
+    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_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_RESPONSE_ID, scope._response_id)
+    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, input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, input_tokens + 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_PREMAI,
+            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
+            application_name, scope._start_time, scope._end_time, input_tokens, output_tokens,
+            cost, scope._tbt, scope._ttft)
+
+def common_embedding_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version):
+    """
+    Process embedding request and generate Telemetry
+    """
+
+    request_model = scope._kwargs.get("model", "text-embedding-ada-002")
+
+    cost = get_embed_model_cost(request_model, pricing_info, scope._input_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_PREMAI,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, False, scope._tbt, scope._ttft, version)
+
+    # Embedding-specific span attributes
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_ENCODING_FORMATS, [scope._kwargs.get("encoding_format", "float")])
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get("user", ""))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: str(scope._kwargs.get("input", "")),
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_embedding_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_PREMAI,
+            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
+            application_name, scope._start_time, scope._end_time, scope._input_tokens, cost)
+
+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
+    """
+
+    scope = type("GenericScope", (), {})()
+    response_dict = response_as_dict(response)
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._llmresponse = str(response_dict.get("choices")[0].get("message").get("content"))
+    scope._response_id = response_dict.get("additional_properties", {}).get("id")
+    scope._response_model = response_dict.get("model")
+    scope._input_tokens = response_dict.get("usage").get("prompt_tokens")
+    scope._output_tokens = response_dict.get("usage").get("completion_tokens")
+    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._finish_reason = str(response_dict.get("choices")[0].get("finish_reason"))
+
+    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
+
+def process_embedding_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 embedding request and generate Telemetry
+    """
+
+    scope = type("GenericScope", (), {})()
+    response_dict = response_as_dict(response)
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._response_model = response_dict.get("model")
+    scope._input_tokens = response_dict.get("usage").get("prompt_tokens")
+    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
+
+    common_embedding_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version)
+
+    return response

openlit/instrumentation/reka/__init__.py

@@ -1,4 +1,3 @@
-# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
 """Initializer of Auto Instrumentation of Reka Functions"""
 
 from typing import Collection
@@ -17,15 +16,15 @@ _instruments = ("reka-api >= 3.2.0",)
 
 class RekaInstrumentor(BaseInstrumentor):
     """
-    An instrumentor for Reka's client library.
+    An instrumentor for Reka client library.
     """
 
     def instrumentation_dependencies(self) -> Collection[str]:
         return _instruments
 
     def _instrument(self, **kwargs):
-        application_name = kwargs.get("application_name", "default_application")
-        environment = kwargs.get("environment", "default_environment")
+        application_name = kwargs.get("application_name", "default")
+        environment = kwargs.get("environment", "default")
         tracer = kwargs.get("tracer")
         metrics = kwargs.get("metrics_dict")
         pricing_info = kwargs.get("pricing_info", {})
@@ -33,7 +32,7 @@ class RekaInstrumentor(BaseInstrumentor):
         disable_metrics = kwargs.get("disable_metrics")
         version = importlib.metadata.version("reka-api")
 
-        # sync chat
+        # Chat completions
         wrap_function_wrapper(
             "reka.chat.client",
             "ChatClient.create",
@@ -41,7 +40,7 @@ class RekaInstrumentor(BaseInstrumentor):
                   tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
-        # async chat
+        # Chat completions
         wrap_function_wrapper(
             "reka.chat.client",
             "AsyncChatClient.create",
@@ -50,5 +49,4 @@ class RekaInstrumentor(BaseInstrumentor):
         )
 
     def _uninstrument(self, **kwargs):
-        # Proper uninstrumentation logic to revert patched methods
         pass

openlit/instrumentation/reka/async_reka.py

@@ -2,53 +2,26 @@
 Module for monitoring Reka API calls.
 """
 
-import logging
 import time
-from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
-    get_chat_model_cost,
     handle_exception,
-    create_metrics_attributes,
     set_server_address_and_port
 )
+from openlit.instrumentation.reka.utils import (
+    process_chat_response
+)
 from openlit.semcov import SemanticConvention
 
-# Initialize logger for logging potential issues and operations
-logger = logging.getLogger(__name__)
-
 def async_chat(version, environment, application_name,
-                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for chat to collect metrics.
-
-    Args:
-        version: Version of the monitoring package.
-        environment: Deployment environment (e.g., production, staging).
-        application_name: Name of the application using the Reka API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating the cost of Reka usage.
-        capture_message_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the chat method to add telemetry.
+    Generates a telemetry wrapper for GenAI function call
     """
 
     async def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the 'chat' API call to add telemetry.
-        
-        This collects metrics such as execution time, cost, and token usage, and handles errors
-        gracefully, adding details to the trace for observability.
-
-        Args:
-            wrapped: The original 'chat' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'chat' method.
-            kwargs: Keyword arguments for the 'chat' method.
-
-        Returns:
-            The response from the original 'chat' method.
+        Wraps the GenAI function call.
         """
 
         server_address, server_port = set_server_address_and_port(instance, "api.reka.ai", 443)
@@ -56,142 +29,31 @@ def async_chat(version, environment, application_name,
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
             start_time = time.time()
             response = await wrapped(*args, **kwargs)
-            end_time = time.time()
 
             try:
-                # Format 'messages' into a single string
-                message_prompt = kwargs.get("messages", "")
-                formatted_messages = []
-                for message in message_prompt:
-                    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}")
-                prompt = "\n".join(formatted_messages)
-
-                input_tokens = response.usage.input_tokens
-                output_tokens = response.usage.output_tokens
-
-                # Calculate cost of the operation
-                cost = get_chat_model_cost(request_model,
-                                            pricing_info, input_tokens, output_tokens)
-
-                # Set Span attributes (OTel Semconv)
-                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                span.set_attribute(SemanticConvention.GEN_AI_OPERATION,
-                                    SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT)
-                span.set_attribute(SemanticConvention.GEN_AI_SYSTEM,
-                                    SemanticConvention.GEN_AI_SYSTEM_REKAAI)
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL,
-                                    request_model)
-                span.set_attribute(SemanticConvention.SERVER_PORT,
-                                    server_port)
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SEED,
-                                    kwargs.get("seed", ""))
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS,
-                                    kwargs.get("max_tokens", -1))
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_STOP_SEQUENCES,
-                                    kwargs.get("stop", []))
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                    kwargs.get("presence_penalty", 0.0))
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE,
-                                    kwargs.get("temperature", 0.4))
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_K,
-                                    kwargs.get("top_k", 1.0))
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P,
-                                    kwargs.get("top_p", 1.0))
-                span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON,
-                                    [response.responses[0].finish_reason])
-                span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_ID,
-                                    response.id)
-                span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL,
-                                    response.model)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS,
-                                    input_tokens)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                    output_tokens)
-                span.set_attribute(SemanticConvention.SERVER_ADDRESS,
-                                    server_address)
-                span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE,
-                                    'text')
-
-                # Set Span attributes (Extra)
-                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
-                                    environment)
-                span.set_attribute(SERVICE_NAME,
-                                    application_name)
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM,
-                                    False)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    input_tokens + output_tokens)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST,
-                                    cost)
-                span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT,
-                                    end_time - start_time)
-                span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION,
-                                    version)
-
-                if capture_message_content:
-                    span.add_event(
-                        name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
-                        attributes={
-                            SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
-                        },
-                    )
-                    span.add_event(
-                        name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
-                        attributes={
-                            SemanticConvention.GEN_AI_CONTENT_COMPLETION: response.responses[0].message.content,
-                        },
-                    )
-
-                span.set_status(Status(StatusCode.OK))
-
-                if disable_metrics is False:
-                    attributes = create_metrics_attributes(
-                        service_name=application_name,
-                        deployment_environment=environment,
-                        operation=SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,
-                        system=SemanticConvention.GEN_AI_SYSTEM_REKAAI,
-                        request_model=request_model,
-                        server_address=server_address,
-                        server_port=server_port,
-                        response_model=response.model,
-                    )
-
-                    metrics["genai_client_usage_tokens"].record(
-                        input_tokens + output_tokens, attributes
-                    )
-                    metrics["genai_client_operation_duration"].record(
-                        end_time - start_time, attributes
-                    )
-                    metrics["genai_server_ttft"].record(
-                        end_time - start_time, attributes
-                    )
-                    metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_completion_tokens"].add(output_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
-                    metrics["genai_cost"].record(cost, attributes)
-
-                # Return original response
-                return response
+                response = process_chat_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,
+                    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)
-                logger.error("Error in trace creation: %s", e)
 
-                # Return original response
-                return response
+            return response
 
     return wrapper