openlit 1.33.15__tar.gz → 1.33.16__tar.gz

{openlit-1.33.15 → openlit-1.33.16}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.33.15
+Version: 1.33.16
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 License: Apache-2.0
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu

{openlit-1.33.15 → openlit-1.33.16}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.33.15"
+version = "1.33.16"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 license = "Apache-2.0"

{openlit-1.33.15 → openlit-1.33.16}/src/openlit/__init__.py

@@ -65,6 +65,7 @@ from openlit.instrumentation.controlflow import ControlFlowInstrumentor
 from openlit.instrumentation.crawl4ai import Crawl4AIInstrumentor
 from openlit.instrumentation.firecrawl import FireCrawlInstrumentor
 from openlit.instrumentation.letta import LettaInstrumentor
+from openlit.instrumentation.openai_agents import OpenAIAgentsInstrumentor
 from openlit.instrumentation.gpu import GPUInstrumentor
 import openlit.guard
 import openlit.evals
@@ -293,6 +294,7 @@ def init(
         "firecrawl": "firecrawl",
         "letta": "letta",
         "together": "together",
+        "openai-agents": "agents"
     }
 
     invalid_instrumentors = [
@@ -411,6 +413,7 @@ def init(
             "firecrawl": FireCrawlInstrumentor(),
             "letta": LettaInstrumentor(),
             "together": TogetherInstrumentor(),
+            "openai-agents": OpenAIAgentsInstrumentor(),
         }
 
         # Initialize and instrument only the enabled instrumentors

{openlit-1.33.15 → openlit-1.33.16}/src/openlit/instrumentation/openai/__init__.py

@@ -5,11 +5,11 @@ import importlib.metadata
 from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
 from wrapt import wrap_function_wrapper
 
-from openlit.instrumentation.openai.openai import chat_completions, embedding
+from openlit.instrumentation.openai.openai import chat_completions, embedding, responses
 from openlit.instrumentation.openai.openai import image_generate, image_variatons, audio_create
 from openlit.instrumentation.openai.async_openai import async_chat_completions, async_embedding
 from openlit.instrumentation.openai.async_openai import async_image_generate, async_image_variatons
-from openlit.instrumentation.openai.async_openai import async_audio_create
+from openlit.instrumentation.openai.async_openai import async_audio_create, async_responses
 
 _instruments = ("openai >= 1.1.1",)
 
@@ -45,6 +45,22 @@ class OpenAIInstrumentor(BaseInstrumentor):
                                metrics, disable_metrics),
         )
 
+        wrap_function_wrapper(
+            "openai.resources.responses.responses",  
+            "Responses.create",  
+            responses(version, environment, application_name,
+                         tracer, pricing_info, capture_message_content,
+                         metrics, disable_metrics),
+        )
+
+        wrap_function_wrapper(
+            "openai.resources.responses.responses",  
+            "AsyncResponses.create",  
+            async_responses(version, environment, application_name,
+                         tracer, pricing_info, capture_message_content,
+                         metrics, disable_metrics),
+        )
+
         wrap_function_wrapper(
             "openai.resources.images",  
             "Images.generate",  

{openlit-1.33.15 → openlit-1.33.16}/src/openlit/instrumentation/openai/async_openai.py

@@ -13,6 +13,8 @@ from openlit.__helpers import (
     get_image_model_cost,
     general_tokens,
     handle_exception,
+    extract_and_format_input,
+    concatenate_all_contents,
     response_as_dict,
     calculate_ttft,
     calculate_tbt,
@@ -24,6 +26,409 @@ from openlit.semcov import SemanticConvetion
 # Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
 
+def async_responses(version, environment, application_name,
+                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for chat completions 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 OpenAI API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of OpenAI usage.
+        capture_message_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat completions method to add telemetry.
+    """
+
+    class TracedAsyncStream:
+        """
+        Wrapper for streaming responses to collect metrics and trace data.
+        Wraps the response to collect message IDs and aggregated response.
+
+        This class implements the '__aiter__' and '__anext__' methods that
+        handle asynchronous streaming responses.
+
+        This class also implements '__aenter__' and '__aexit__' methods that
+        handle asynchronous context management protocol.
+        """
+        def __init__(
+                self,
+                wrapped,
+                span,
+                kwargs,
+                server_address,
+                server_port,
+                **args,
+            ):
+            self.__wrapped__ = wrapped
+            self._span = span
+            # Placeholder for aggregating streaming response
+            self._llmresponse = ""
+            self._response_id = ""
+            self._response_model = ""
+            self._finish_reason = ""
+            self._input_tokens = ""
+            self._output_tokens = ""
+
+            self._args = args
+            self._kwargs = kwargs
+            self._start_time = time.time()
+            self._end_time = None
+            self._timestamps = []
+            self._ttft = 0
+            self._tbt = 0
+            self._server_address = server_address
+            self._server_port = server_port
+
+        async def __aenter__(self):
+            await self.__wrapped__.__aenter__()
+            return self
+
+        async def __aexit__(self, exc_type, exc_value, traceback):
+            await self.__wrapped__.__aexit__(exc_type, exc_value, traceback)
+
+        def __aiter__(self):
+            return self
+
+        async def __getattr__(self, name):
+            """Delegate attribute access to the wrapped object."""
+            return getattr(await self.__wrapped__, name)
+
+        async def __anext__(self):
+            try:
+                chunk = await self.__wrapped__.__anext__()
+                end_time = time.time()
+                # Record the timestamp for the current chunk
+                self._timestamps.append(end_time)
+
+                if len(self._timestamps) == 1:
+                    # Calculate time to first chunk
+                    self._ttft = calculate_ttft(self._timestamps, self._start_time)
+
+                chunked = response_as_dict(chunk)
+                # Collect message IDs and aggregated response from events
+                if chunked.get('type') == "response.output_text.delta":
+                    self._llmresponse += chunked.get('delta')
+                if chunked.get('type') == "response.completed":
+                    self._response_id = chunked.get('response').get('id')
+                    self._response_model = chunked.get('response').get('model')
+                    self._finish_reason = chunked.get('response').get('status')
+                    self._input_tokens = chunked.get('response').get('usage').get('input_tokens')
+                    self._output_tokens = chunked.get('response').get('usage').get('output_tokens')
+                return chunk
+            except StopAsyncIteration:
+                # Handling exception ensure observability without disrupting operation
+                try:
+                    self._end_time = time.time()
+                    if len(self._timestamps) > 1:
+                        self._tbt = calculate_tbt(self._timestamps)
+
+                    try:
+                        formatted_messages = extract_and_format_input(self._kwargs.get('input', ''))
+                        prompt = concatenate_all_contents(formatted_messages)
+                    except:
+                        prompt = self._kwargs.get('input', '')
+
+                    request_model = self._kwargs.get("model", "gpt-4o")
+
+                    # Calculate cost of the operation
+                    cost = get_chat_model_cost(request_model,
+                                                pricing_info, self._input_tokens,
+                                                self._output_tokens)
+
+                    # Set Span attributes (OTel Semconv)
+                    self._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
+                                        SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_OPENAI)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                        request_model)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                        self._kwargs.get("seed", ""))
+                    self._span.set_attribute(SemanticConvetion.SERVER_PORT,
+                                        self._server_port)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        self._kwargs.get("max_output_tokens", -1))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_STOP_SEQUENCES,
+                                        self._kwargs.get("stop", []))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                        self._kwargs.get("temperature", 1.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        self._kwargs.get("top_p", 1.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                        [self._finish_reason])
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                        self._response_id)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
+                                        self._response_model)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
+                                        self._input_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
+                                        self._output_tokens)
+                    self._span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
+                                        self._server_address)
+                    if isinstance(self._llmresponse, str):
+                        self._span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                        "text")
+                    else:
+                        self._span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                        "json")
+
+                    # Set Span attributes (Extra)
+                    self._span.set_attribute(DEPLOYMENT_ENVIRONMENT,
+                                        environment)
+                    self._span.set_attribute(SERVICE_NAME,
+                                        application_name)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        self._kwargs.get("user", ""))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                        True)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                        self._input_tokens + self._output_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                        cost)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TBT,
+                                        self._tbt)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
+                                        self._ttft)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
+                                        version)
+
+                    if capture_message_content:
+                        self._span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
+                        self._span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: self._llmresponse,
+                            },
+                        )
+                    self._span.set_status(Status(StatusCode.OK))
+
+                    if disable_metrics is False:
+                        attributes = create_metrics_attributes(
+                            service_name=application_name,
+                            deployment_environment=environment,
+                            operation=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
+                            system=SemanticConvetion.GEN_AI_SYSTEM_OPENAI,
+                            request_model=request_model,
+                            server_address=self._server_address,
+                            server_port=self._server_port,
+                            response_model=self._response_model,
+                        )
+
+                        metrics["genai_client_usage_tokens"].record(
+                            self._input_tokens + self._output_tokens, attributes
+                        )
+                        metrics["genai_client_operation_duration"].record(
+                            self._end_time - self._start_time, attributes
+                        )
+                        metrics["genai_server_tbt"].record(
+                            self._tbt, attributes
+                        )
+                        metrics["genai_server_ttft"].record(
+                            self._ttft, attributes
+                        )
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_completion_tokens"].add(self._output_tokens, attributes)
+                        metrics["genai_prompt_tokens"].add(self._input_tokens, attributes)
+                        metrics["genai_cost"].record(cost, attributes)
+
+                except Exception as e:
+                    handle_exception(self._span, e)
+                    logger.error("Error in trace creation: %s", e)
+                finally:
+                    self._span.end()
+                raise
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 'chat.completions' 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.completions' method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the 'chat.completions' method.
+            kwargs: Keyword arguments for the 'chat.completions' method.
+
+        Returns:
+            The response from the original 'chat.completions' method.
+        """
+
+        # Check if streaming is enabled for the API call
+        streaming = kwargs.get("stream", False)
+        server_address, server_port = set_server_address_and_port(instance, "api.openai.com", 443)
+        request_model = kwargs.get("model", "gpt-4o")
+
+        span_name = f"{SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        # pylint: disable=no-else-return
+        if streaming:
+            # Special handling for streaming response to accommodate the nature of data flow
+            awaited_wrapped = await wrapped(*args, **kwargs)
+            span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
+
+            return TracedAsyncStream(awaited_wrapped, span, kwargs, server_address, server_port)
+
+        # Handling for non-streaming responses
+        else:
+            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()
+
+                response_dict = response_as_dict(response)
+
+                try:
+                    try:
+                        formatted_messages = extract_and_format_input(kwargs.get('input', ''))
+                        prompt = concatenate_all_contents(formatted_messages)
+                    except:
+                        prompt = kwargs.get('input', '')
+
+                    input_tokens = response_dict.get('usage').get('input_tokens')
+                    output_tokens = response_dict.get('usage').get('output_tokens')
+
+                    # Calculate cost of the operation
+                    cost = get_chat_model_cost(request_model,
+                                                pricing_info, input_tokens,
+                                                output_tokens)
+
+                    # Set base span attribues (OTel Semconv)
+                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
+                                        SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
+                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_OPENAI)
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                        request_model)
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                        kwargs.get("seed", ""))
+                    span.set_attribute(SemanticConvetion.SERVER_PORT,
+                                        server_port)
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        kwargs.get("max_output_tokens", -1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_STOP_SEQUENCES,
+                                        kwargs.get("stop", []))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                        str(response_dict.get("temperature", 1.0)))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        str(response_dict.get("top_p", 1.0)))
+                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                        response_dict.get("id"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
+                                        response_dict.get('model'))
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
+                                        input_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
+                                        output_tokens)
+                    span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
+                                        server_address)
+
+                    # Set base span attribues (Extras)
+                    span.set_attribute(DEPLOYMENT_ENVIRONMENT,
+                                        environment)
+                    span.set_attribute(SERVICE_NAME,
+                                        application_name)
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        kwargs.get("user", ""))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                        False)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                        input_tokens + output_tokens)
+                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                        cost)
+                    span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
+                                        end_time - start_time)
+                    span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
+                                        version)
+
+                    if capture_message_content:
+                        span.add_event(
+                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
+                            attributes={
+                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
+                            },
+                        )
+
+                    for i in range(kwargs.get('n',1)):
+                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                           [response_dict.get('status')])
+                        try:
+                            llm_response = str(response_dict.get('output')[i].get('content')[0].get('text',''))
+                        except:
+                            llm_response = ''
+
+                        if capture_message_content:
+                            span.add_event(
+                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
+                                attributes={
+                                    # pylint: disable=line-too-long
+                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llm_response,
+                                },
+                            )
+                        if kwargs.get('tools'):
+                            span.set_attribute(SemanticConvetion.GEN_AI_TOOL_CALLS,
+                                            str(response_dict.get('tools')))
+
+                        if isinstance(llm_response, str):
+                            span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                            "text")
+                        elif llm_response is not None:
+                            span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
+                                            "json")
+
+                    span.set_status(Status(StatusCode.OK))
+
+                    if disable_metrics is False:
+                        attributes = create_metrics_attributes(
+                            service_name=application_name,
+                            deployment_environment=environment,
+                            operation=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
+                            system=SemanticConvetion.GEN_AI_SYSTEM_OPENAI,
+                            request_model=request_model,
+                            server_address=server_address,
+                            server_port=server_port,
+                            response_model=response_dict.get('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
+
+                except Exception as e:
+                    handle_exception(span, e)
+                    logger.error("Error in trace creation: %s", e)
+
+                    # Return original response
+                    return response
+
+    return wrapper
+
 def async_chat_completions(version, environment, application_name,
                            tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """