openlit 1.33.7__py3-none-any.whl → 1.33.9__py3-none-any.whl

openlit/instrumentation/openai/async_azure_openai.py

@@ -1,900 +0,0 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, too-many-branches
-"""
-Module for monitoring Azure OpenAI API calls.
-"""
-
-import logging
-from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
-from openlit.__helpers import get_chat_model_cost, get_embed_model_cost
-from openlit.__helpers import get_image_model_cost, openai_tokens, handle_exception
-from openlit.semcov import SemanticConvetion
-
-# Initialize logger for logging potential issues and operations
-logger = logging.getLogger(__name__)
-
-def azure_async_chat_completions(gen_ai_endpoint, version, environment, application_name,
-                                 tracer, pricing_info, trace_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for chat completions to collect metrics.
-
-    Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
-        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.
-        trace_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the chat completions method to add telemetry.
-    """
-
-    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)
-
-        # pylint: disable=no-else-return
-        if streaming:
-            # Special handling for streaming response to accommodate the nature of data flow
-            async def stream_generator():
-                # pylint: disable=line-too-long
-                with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                    # Placeholder for aggregating streaming response
-                    llmresponse = ""
-
-                    # Loop through streaming events capturing relevant details
-                    async for chunk in await wrapped(*args, **kwargs):
-                        # Collect message IDs and aggregated response from events
-                        if len(chunk.choices) > 0:
-                            # pylint: disable=line-too-long
-                            if hasattr(chunk.choices[0], "delta") and hasattr(chunk.choices[0].delta, "content"):
-                                content = chunk.choices[0].delta.content
-                                if content:
-                                    llmresponse += content
-                        yield chunk
-                        response_id = chunk.id
-                        model = "azure_" + chunk.model
-
-                    # Handling exception ensure observability without disrupting operation
-                    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(
-                                    # pylint: disable=line-too-long
-                                    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)
-
-                        # Calculate tokens using input prompt and aggregated response
-                        prompt_tokens = openai_tokens(prompt,
-                                                        kwargs.get("model", "gpt-3.5-turbo"))
-                        completion_tokens = openai_tokens(llmresponse,
-                                                            kwargs.get("model", "gpt-3.5-turbo"))
-
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(model, pricing_info,
-                                                    prompt_tokens, completion_tokens)
-
-                        # Set Span attributes
-                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                            SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI)
-                        span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                            SemanticConvetion.GEN_AI_TYPE_CHAT)
-                        span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                            gen_ai_endpoint)
-                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                            response_id)
-                        span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                            environment)
-                        span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                            application_name)
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                            model)
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
-                                            kwargs.get("user", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
-                                            kwargs.get("tool_choice", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
-                                            kwargs.get("seed", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                            True)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            prompt_tokens + completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-                        if trace_content:
-                            span.add_event(
-                                name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                                attributes={
-                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
-                                },
-                            )
-                            span.add_event(
-                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                                attributes={
-                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
-                                },
-                            )
-
-                        span.set_status(Status(StatusCode.OK))
-
-                        if disable_metrics is False:
-                            attributes = {
-                                TELEMETRY_SDK_NAME:
-                                    "openlit",
-                                SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                                    application_name,
-                                SemanticConvetion.GEN_AI_SYSTEM:
-                                    SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI,
-                                SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                    environment,
-                                SemanticConvetion.GEN_AI_TYPE:
-                                    SemanticConvetion.GEN_AI_TYPE_CHAT,
-                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                    model
-                            }
-
-                            metrics["genai_requests"].add(1, attributes)
-                            metrics["genai_total_tokens"].add(prompt_tokens + completion_tokens, attributes)
-                            metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                            metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                            metrics["genai_cost"].record(cost, attributes)
-
-                    except Exception as e:
-                        handle_exception(span, e)
-                        logger.error("Error in trace creation: %s", e)
-
-            return stream_generator()
-
-        # Handling for non-streaming responses
-        else:
-            # pylint: disable=line-too-long
-            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                response = await wrapped(*args, **kwargs)
-
-                try:
-                    # Find base model from response
-                    model = "azure_" + response.model
-
-                    # 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(
-                                # pylint: disable=line-too-long
-                                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)
-
-                    # Set base span attribues
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI)
-                    span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                        SemanticConvetion.GEN_AI_TYPE_CHAT)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                        gen_ai_endpoint)
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                        response.id)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                        environment)
-                    span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                        application_name)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                        model)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
-                                        kwargs.get("user", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
-                                        kwargs.get("tool_choice", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
-                                        kwargs.get("seed", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                        False)
-                    if trace_content:
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
-                            },
-                        )
-
-                    # Set span attributes when tools is not passed to the function call
-                    if "tools" not in kwargs:
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(model, pricing_info,
-                                                    response.usage.prompt_tokens,
-                                                    response.usage.completion_tokens)
-
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            response.usage.prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            response.usage.completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            response.usage.total_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                            [response.choices[0].finish_reason])
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-
-                        # Set span attributes for when n = 1 (default)
-                        if "n" not in kwargs or kwargs["n"] == 1:
-                            if trace_content:
-                                span.add_event(
-                                    name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                                    attributes={
-                                        SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.choices[0].message.content,
-                                    },
-                                )
-
-                        # Set span attributes for when n > 0
-                        else:
-                            i = 0
-                            while i < kwargs["n"] and trace_content is True:
-                                attribute_name = f"gen_ai.content.completion.{i}"
-                                span.add_event(
-                                    name=attribute_name,
-                                    attributes={
-                                        SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.choices[i].message.content,
-                                    },
-                                )
-                                i += 1
-
-                            # Return original response
-                            return response
-
-                    # Set span attributes when tools is passed to the function call
-                    elif "tools" in kwargs:
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(model, pricing_info,
-                                                    response.usage.prompt_tokens,
-                                                    response.usage.completion_tokens)
-
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION:  "Function called with tools",
-                            },
-                        )
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            response.usage.prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            response.usage.completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            response.usage.total_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-
-                    span.set_status(Status(StatusCode.OK))
-
-                    if disable_metrics is False:
-                        attributes = {
-                            TELEMETRY_SDK_NAME:
-                                "openlit",
-                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                                application_name,
-                            SemanticConvetion.GEN_AI_SYSTEM:
-                                SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI,
-                            SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                environment,
-                            SemanticConvetion.GEN_AI_TYPE:
-                                SemanticConvetion.GEN_AI_TYPE_CHAT,
-                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                model
-                        }
-
-                        metrics["genai_requests"].add(1, attributes)
-                        metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
-                        metrics["genai_completion_tokens"].add(response.usage.completion_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(response.usage.prompt_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 azure_async_completions(gen_ai_endpoint, version, environment, application_name,
-                            tracer, pricing_info, trace_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for completions to collect metrics.
-
-    Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
-        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.
-        trace_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the chat completions method to add telemetry.
-    """
-
-    async def wrapper(wrapped, instance, args, kwargs):
-        """
-        Wraps the '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 'completions' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'completions' method.
-            kwargs: Keyword arguments for the '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)
-
-        # pylint: disable=no-else-return
-        if streaming:
-            # Special handling for streaming response to accommodate the nature of data flow
-            async def stream_generator():
-                # pylint: disable=line-too-long
-                with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                    # Placeholder for aggregating streaming response
-                    llmresponse = ""
-
-                    # Loop through streaming events capturing relevant details
-                    async for chunk in await wrapped(*args, **kwargs):
-                        # Collect message IDs and aggregated response from events
-                        if len(chunk.choices) > 0:
-                            if hasattr(chunk.choices[0], "text"):
-                                content = chunk.choices[0].text
-                                if content:
-                                    llmresponse += content
-                        yield chunk
-                        response_id = chunk.id
-                        model = "azure_" + chunk.model
-
-                    # Handling exception ensure observability without disrupting operation
-                    try:
-                        prompt = kwargs.get("prompt", "")
-
-                        # Calculate tokens using input prompt and aggregated response
-                        prompt_tokens = openai_tokens(prompt,
-                                                        "gpt-3.5-turbo")
-                        completion_tokens = openai_tokens(llmresponse,
-                                                            "gpt-3.5-turbo")
-
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(model, pricing_info,
-                                                    prompt_tokens, completion_tokens)
-
-                        # Set Span attributes
-                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                            SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI)
-                        span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                            SemanticConvetion.GEN_AI_TYPE_CHAT)
-                        span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                            gen_ai_endpoint)
-                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                            response_id)
-                        span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                            environment)
-                        span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                            application_name)
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                            model)
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
-                                            kwargs.get("user", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
-                                            kwargs.get("tool_choice", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                            kwargs.get("presence_penalty", 0.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                            kwargs.get("frequency_penalty", 0.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
-                                            kwargs.get("seed", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                            True)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            prompt_tokens + completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-                        if trace_content:
-                            span.add_event(
-                                name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                                attributes={
-                                    SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
-                                },
-                            )
-                            span.add_event(
-                                name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                                attributes={
-                                    SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llmresponse,
-                                },
-                            )
-
-                        span.set_status(Status(StatusCode.OK))
-
-                        if disable_metrics is False:
-                            attributes = {
-                                TELEMETRY_SDK_NAME:
-                                    "openlit",
-                                SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                                    application_name,
-                                SemanticConvetion.GEN_AI_SYSTEM:
-                                    SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI,
-                                SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                    environment,
-                                SemanticConvetion.GEN_AI_TYPE:
-                                    SemanticConvetion.GEN_AI_TYPE_CHAT,
-                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                    model
-                            }
-
-                            metrics["genai_requests"].add(1, attributes)
-                            metrics["genai_total_tokens"].add(prompt_tokens + completion_tokens, attributes)
-                            metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                            metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                            metrics["genai_cost"].record(cost, attributes)
-
-                    except Exception as e:
-                        handle_exception(span, e)
-                        logger.error("Error in trace creation: %s", e)
-
-            return stream_generator()
-
-        # Handling for non-streaming responses
-        else:
-            # pylint: disable=line-too-long
-            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                response = wrapped(*args, **kwargs)
-
-                try:
-                    # Find base model from response
-                    model = "azure_" + response.model
-
-                    # Set base span attribues
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI)
-                    span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                        SemanticConvetion.GEN_AI_TYPE_CHAT)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                        gen_ai_endpoint)
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                        response.id)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                        environment)
-                    span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                        application_name)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                        model)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
-                                        kwargs.get("user", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOOL_CHOICE,
-                                        kwargs.get("tool_choice", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("frequency_penalty", 0.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
-                                        kwargs.get("seed", ""))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                        False)
-                    if trace_content:
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("prompt", ""),
-                            },
-                        )
-
-                    # Set span attributes when tools is not passed to the function call
-                    if "tools" not in kwargs:
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(model, pricing_info,
-                                                    response.usage.prompt_tokens,
-                                                    response.usage.completion_tokens)
-
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            response.usage.prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            response.usage.completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            response.usage.total_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                            [response.choices[0].finish_reason])
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-
-                        # Set span attributes for when n = 1 (default)
-                        if "n" not in kwargs or kwargs["n"] == 1:
-                            if trace_content:
-                                span.add_event(
-                                    name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                                    attributes={
-                                        SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.choices[0].text,
-                                    },
-                                )
-
-                        # Set span attributes for when n > 0
-                        else:
-                            i = 0
-                            while i < kwargs["n"] and trace_content is True:
-                                attribute_name = f"gen_ai.content.completion.{i}"
-                                span.add_event(
-                                    name=attribute_name,
-                                    attributes={
-                                        SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.choices[i].text,
-                                    },
-                                )
-                                i += 1
-                            return response
-
-                    # Set span attributes when tools is passed to the function call
-                    elif "tools" in kwargs:
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(model, pricing_info,
-                                                    response.usage.prompt_tokens,
-                                                    response.usage.completion_tokens)
-
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: "Function called with tools",
-                            },
-                        )
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            response.usage.prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            response.usage.completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            response.usage.total_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-
-                    span.set_status(Status(StatusCode.OK))
-
-                    if disable_metrics is False:
-                        attributes = {
-                            TELEMETRY_SDK_NAME:
-                                "openlit",
-                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                                application_name,
-                            SemanticConvetion.GEN_AI_SYSTEM:
-                                SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI,
-                            SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                environment,
-                            SemanticConvetion.GEN_AI_TYPE:
-                                SemanticConvetion.GEN_AI_TYPE_CHAT,
-                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                model
-                        }
-
-                        metrics["genai_requests"].add(1, attributes)
-                        metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
-                        metrics["genai_completion_tokens"].add(response.usage.completion_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(response.usage.prompt_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 azure_async_embedding(gen_ai_endpoint, version, environment, application_name,
-                          tracer, pricing_info, trace_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for embeddings to collect metrics.
-    
-    Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
-        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.
-        trace_content: Flag indicating whether to trace the actual content.
-    
-    Returns:
-        A function that wraps the embeddings method to add telemetry.
-    """
-
-    async def wrapper(wrapped, instance, args, kwargs):
-        """
-        Wraps the 'embeddings' 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 'embeddings' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'embeddings' method.
-            kwargs: Keyword arguments for the 'embeddings' method.
-
-        Returns:
-            The response from the original 'embeddings' method.
-        """
-
-        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-            response = await wrapped(*args, **kwargs)
-
-            try:
-                # Calculate cost of the operation
-                cost = get_embed_model_cost("azure_" + response.model,
-                                            pricing_info, response.usage.prompt_tokens)
-
-                # Set Span attributes
-                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                    SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI)
-                span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                    SemanticConvetion.GEN_AI_TYPE_EMBEDDING)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                    gen_ai_endpoint)
-                span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                    environment)
-                span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                    application_name)
-                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                    "azure_" + response.model)
-                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_EMBEDDING_FORMAT,
-                                    kwargs.get("encoding_format", "float"))
-                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_EMBEDDING_DIMENSION,
-                                    kwargs.get("dimensions", ""))
-                span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
-                                    kwargs.get("user", ""))
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                    response.usage.prompt_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    response.usage.total_tokens)
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST, cost)
-                if trace_content:
-                    span.add_event(
-                        name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                        attributes={
-                            SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("input", ""),
-                        },
-                    )
-
-                span.set_status(Status(StatusCode.OK))
-
-                if disable_metrics is False:
-                    attributes = {
-                        TELEMETRY_SDK_NAME:
-                            "openlit",
-                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                            application_name,
-                        SemanticConvetion.GEN_AI_SYSTEM:
-                            SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
-                            environment,
-                        SemanticConvetion.GEN_AI_TYPE:
-                            SemanticConvetion.GEN_AI_TYPE_EMBEDDING,
-                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                            "azure_" + response.model
-                    }
-
-                    metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
-                    metrics["genai_prompt_tokens"].add(response.usage.prompt_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 azure_async_image_generate(gen_ai_endpoint, version, environment, application_name,
-                               tracer, pricing_info, trace_content, metrics, disable_metrics):
-    """
-    Generates a telemetry wrapper for image generation to collect metrics.
-    
-    Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
-        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 image generation.
-        trace_content: Flag indicating whether to trace the input prompt and generated images.
-    
-    Returns:
-        A function that wraps the image generation method to add telemetry.
-    """
-
-    async def wrapper(wrapped, instance, args, kwargs):
-        """
-        Wraps the 'images.generate' API call to add telemetry.
-
-        This collects metrics such as execution time, cost, and handles errors
-        gracefully, adding details to the trace for observability.
-
-        Args:
-            wrapped: The original 'images.generate' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'images.generate' method.
-            kwargs: Keyword arguments for the 'images.generate' method.
-
-        Returns:
-            The response from the original 'images.generate' method.
-        """
-
-        with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-            response = await wrapped(*args, **kwargs)
-            images_count = 0
-
-            try:
-                # Find Image format
-                if "response_format" in kwargs and kwargs["response_format"] == "b64_json":
-                    image = "b64_json"
-                else:
-                    image = "url"
-
-                # Calculate cost of the operation
-                cost = get_image_model_cost("azure_" + kwargs.get("model", "dall-e-3"),
-                                            pricing_info, kwargs.get("size", "1024x1024"),
-                                            kwargs.get("quality", "standard"))
-
-                for items in response.data:
-                    # Set Span attributes
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI)
-                    span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                        SemanticConvetion.GEN_AI_TYPE_IMAGE)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                        gen_ai_endpoint)
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                        response.created)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                        environment)
-                    span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                        application_name)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                        "azure_" + kwargs.get("model", "dall-e-3"))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_SIZE,
-                                        kwargs.get("size", "1024x1024"))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_QUALITY,
-                                        kwargs.get("quality", "standard"))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_STYLE,
-                                        kwargs.get("style", "vivid"))
-                    span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_REVISED_PROMPT,
-                                        items.revised_prompt if response.revised_prompt else "")
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
-                                        kwargs.get("user", ""))
-                    if trace_content:
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: kwargs.get("prompt", ""),
-                            },
-                        )
-                        attribute_name = f"gen_ai.response.image.{images_count}"
-                        span.add_event(
-                            name=attribute_name,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: getattr(items, image),
-                            },
-                        )
-
-                    images_count+=1
-
-                span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                    len(response.data) * cost)
-                span.set_status(Status(StatusCode.OK))
-
-                if disable_metrics is False:
-                    attributes = {
-                        TELEMETRY_SDK_NAME:
-                            "openlit",
-                        SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                            application_name,
-                        SemanticConvetion.GEN_AI_SYSTEM:
-                            SemanticConvetion.GEN_AI_SYSTEM_AZURE_OPENAI,
-                        SemanticConvetion.GEN_AI_ENVIRONMENT:
-                            environment,
-                        SemanticConvetion.GEN_AI_TYPE:
-                            SemanticConvetion.GEN_AI_TYPE_IMAGE,
-                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                            "azure_" + kwargs.get("model", "dall-e-3")
-                    }
-
-                    metrics["genai_requests"].add(1, 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