openlit 1.32.12__py3-none-any.whl → 1.33.0__py3-none-any.whl

openlit/__init__.py

@@ -52,6 +52,7 @@ from openlit.instrumentation.milvus import MilvusInstrumentor
 from openlit.instrumentation.astra import AstraInstrumentor
 from openlit.instrumentation.transformers import TransformersInstrumentor
 from openlit.instrumentation.litellm import LiteLLMInstrumentor
+from openlit.instrumentation.together import TogetherInstrumentor
 from openlit.instrumentation.crewai import CrewAIInstrumentor
 from openlit.instrumentation.ag2 import AG2Instrumentor
 from openlit.instrumentation.multion import MultiOnInstrumentor
@@ -188,7 +189,6 @@ def instrument_if_available(
                 metrics_dict=config.metrics_dict,
                 disable_metrics=config.disable_metrics,
             )
-            logger.info("Instrumented %s", instrumentor_name)
         else:
             # pylint: disable=line-too-long
             logger.info("Library for %s (%s) not found. Skipping instrumentation", instrumentor_name, module_name)
@@ -264,6 +264,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
         "crawl4ai": "crawl4ai",
         "firecrawl": "firecrawl",
         "letta": "letta",
+        "together": "together",
     }
 
     invalid_instrumentors = [
@@ -360,6 +361,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
             "crawl4ai": Crawl4AIInstrumentor(),
             "firecrawl": FireCrawlInstrumentor(),
             "letta": LettaInstrumentor(),
+            "together": TogetherInstrumentor(),
         }
 
         # Initialize and instrument only the enabled instrumentors

openlit/instrumentation/together/__init__.py

@@ -0,0 +1,70 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of Together AI Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.together.together import (
+    completion, image_generate
+)
+from openlit.instrumentation.together.async_together import (
+    async_completion, async_image_generate
+)
+
+_instruments = ("together >= 1.3.5",)
+
+class TogetherInstrumentor(BaseInstrumentor):
+    """
+    An instrumentor for Together's 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")
+        tracer = kwargs.get("tracer")
+        metrics = kwargs.get("metrics_dict")
+        pricing_info = kwargs.get("pricing_info", {})
+        trace_content = kwargs.get("trace_content", False)
+        disable_metrics = kwargs.get("disable_metrics")
+        version = importlib.metadata.version("together")
+
+        # Chat completions
+        wrap_function_wrapper(
+            "together.resources.chat.completions",  
+            "ChatCompletions.create",  
+            completion("together.chat.completions", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # Image generate
+        wrap_function_wrapper(
+            "together.resources.images",  
+            "Images.generate",  
+            image_generate("together.image.generate", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # Chat completions
+        wrap_function_wrapper(
+            "together.resources.chat.completions",  
+            "AsyncChatCompletions.create",  
+            async_completion("together.chat.completions", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # Image generate
+        wrap_function_wrapper(
+            "together.resources.images",  
+            "AsyncImages.generate",  
+            async_image_generate("together.image.generate", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+    def _uninstrument(self, **kwargs):
+        # Proper uninstrumentation logic to revert patched methods
+        pass

openlit/instrumentation/together/async_together.py

@@ -0,0 +1,558 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, too-many-branches, too-many-instance-attributes
+"""
+Module for monitoring Together 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_image_model_cost,
+    handle_exception,
+    response_as_dict,
+)
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def async_completion(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 Together AI SDK.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Together AI usage.
+        trace_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.
+
+        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,
+                **args,
+            ):
+            self.__wrapped__ = wrapped
+            self._span = span
+            # Placeholder for aggregating streaming response
+            self._llmresponse = ""
+            self._response_id = ""
+            self._prompt_tokens = 0
+            self._completion_tokens = 0
+            self._total_tokens = 0
+
+            self._args = args
+            self._kwargs = kwargs
+
+        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__()
+                chunked = response_as_dict(chunk)
+                # Collect message IDs and aggregated response from events
+                if (len(chunked.get('choices')) > 0 and ('delta' in chunked.get('choices')[0] and
+                    'content' in chunked.get('choices')[0].get('delta'))):
+
+                    content = chunked.get('choices')[0].get('delta').get('content')
+                    if content:
+                        self._llmresponse += content
+                if chunked.get("usage"):
+                    self._prompt_tokens = chunked.get("usage").get("prompt_tokens")
+                    self._completion_tokens = chunked.get("usage").get("completion_tokens")
+                    self._total_tokens = chunked.get("usage").get("total_tokens")
+                self._response_id = chunked.get('id')
+                return chunk
+            except StopAsyncIteration:
+                # Handling exception ensure observability without disrupting operation
+                try:
+                    # Format 'messages' into a single string
+                    message_prompt = self._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 cost of the operation
+                    cost = get_chat_model_cost(self._kwargs.get(
+                                                "model",
+                                                "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                                ),
+                                                pricing_info, self._prompt_tokens,
+                                                self._completion_tokens)
+
+                    # Set Span attributes
+                    self._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_TOGETHER)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                        SemanticConvetion.GEN_AI_TYPE_CHAT)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                        gen_ai_endpoint)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                        self._response_id)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                        environment)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                        application_name)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                        self._kwargs.get(
+                                            "model",
+                                            "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                        ))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        self._kwargs.get("user", ""))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        self._kwargs.get("top_p", 1.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        self._kwargs.get("max_tokens", -1))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                        self._kwargs.get("temperature", 1.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                        self._kwargs.get("presence_penalty", 0.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
+                                        self._kwargs.get("frequency_penalty", 0.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                        self._kwargs.get("seed", ""))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                        True)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        self._prompt_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                        self._completion_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                        self._total_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                        cost)
+                    if trace_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 = {
+                            TELEMETRY_SDK_NAME:
+                                "openlit",
+                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                                application_name,
+                            SemanticConvetion.GEN_AI_SYSTEM:
+                                SemanticConvetion.GEN_AI_SYSTEM_TOGETHER,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                self._kwargs.get("model",
+                                "meta-llama/Llama-3.3-70B-Instruct-Turbo")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(
+                            self._total_tokens, attributes
+                        )
+                        metrics["genai_completion_tokens"].add(
+                            self._completion_tokens, attributes
+                        )
+                        metrics["genai_prompt_tokens"].add(
+                            self._prompt_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)
+
+        # 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(gen_ai_endpoint, kind=SpanKind.CLIENT)
+
+            return TracedAsyncStream(awaited_wrapped, span, kwargs)
+
+        # 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)
+
+                response_dict = response_as_dict(response)
+
+                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)
+
+                    # Set base span attribues
+                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_TOGETHER)
+                    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_dict.get("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,
+                                        kwargs.get("model",
+                                        "meta-llama/Llama-3.3-70B-Instruct-Turbo"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        kwargs.get("top_p", 1.0))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        kwargs.get("max_tokens", -1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        kwargs.get("user", ""))
+                    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(kwargs.get(
+                                                        "model",
+                                                        "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                                    ),
+                                                    pricing_info,
+                                                    response_dict.get('usage', {}).get('prompt_tokens', None),
+                                                    response_dict.get('usage', {}).get('completion_tokens', None))
+
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                           response_dict.get('usage', {}).get('prompt_tokens', None))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                           response_dict.get('usage', {}).get('completion_tokens', None))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                           response_dict.get('usage', {}).get('total_tokens', None))
+                        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_dict.get('choices', [])[0].get("message").get("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_dict.get('choices')[i].get("message").get("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(kwargs.get(
+                                                    "model",
+                                                    "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                                    ),
+                                                    pricing_info,
+                                                    response_dict.get('usage').get('prompt_tokens'),
+                                                    response_dict.get('usage').get('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_dict.get('usage').get('prompt_tokens'))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            response_dict.get('usage').get('completion_tokens'))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            response_dict.get('usage').get('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_TOGETHER,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                kwargs.get("model", "meta-llama/Llama-3.3-70B-Instruct-Turbo")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(
+                            response_dict.get('usage').get('total_tokens'), attributes)
+                        metrics["genai_completion_tokens"].add(
+                            response_dict.get('usage').get('completion_tokens'), attributes)
+                        metrics["genai_prompt_tokens"].add(
+                            response_dict.get('usage').get('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 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 Together API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Together 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
+                image_size = str(kwargs.get("width", 1024)) + "x" + str(kwargs.get("height", 1024))
+                cost_per_million = get_image_model_cost(kwargs.get(
+                                            "model", "black-forest-labs/FLUX.1-dev"
+                                            ),
+                                            pricing_info, "1000000",
+                                            kwargs.get("quality", "standard"))
+                pixels = kwargs.get("width", 1024) * kwargs.get("height", 1024)
+                cost = pixels / 1_000_000 * cost_per_million
+
+                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_TOGETHER)
+                    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.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,
+                                        kwargs.get("model", "black-forest-labs/FLUX.1-dev"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_SIZE,
+                                        image_size)
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_QUALITY,
+                                        kwargs.get("quality", "standard"))
+                    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_TOGETHER,
+                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                            environment,
+                        SemanticConvetion.GEN_AI_TYPE:
+                            SemanticConvetion.GEN_AI_TYPE_IMAGE,
+                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                            kwargs.get("model", "black-forest-labs/FLUX.1-dev")
+                    }
+
+                    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

openlit/instrumentation/together/together.py

@@ -0,0 +1,558 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, too-many-branches, too-many-instance-attributes
+"""
+Module for monitoring Together 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_image_model_cost,
+    handle_exception,
+    response_as_dict,
+)
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def completion(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 Together AI SDK.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Together AI usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat completions method to add telemetry.
+    """
+
+    class TracedSyncStream:
+        """
+        Wrapper for streaming responses to collect metrics and trace data.
+
+        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,
+                **args,
+            ):
+            self.__wrapped__ = wrapped
+            self._span = span
+            # Placeholder for aggregating streaming response
+            self._llmresponse = ""
+            self._response_id = ""
+            self._prompt_tokens = 0
+            self._completion_tokens = 0
+            self._total_tokens = 0
+
+            self._args = args
+            self._kwargs = kwargs
+
+        def __enter__(self):
+            self.__wrapped__.__enter__()
+            return self
+
+        def __exit__(self, exc_type, exc_value, traceback):
+            self.__wrapped__.__exit__(exc_type, exc_value, traceback)
+
+        def __iter__(self):
+            return self
+
+        def __getattr__(self, name):
+            """Delegate attribute access to the wrapped object."""
+            return getattr(self.__wrapped__, name)
+
+        def __next__(self):
+            try:
+                chunk = self.__wrapped__.__next__()
+                chunked = response_as_dict(chunk)
+                # Collect message IDs and aggregated response from events
+                if (len(chunked.get('choices')) > 0 and ('delta' in chunked.get('choices')[0] and
+                    'content' in chunked.get('choices')[0].get('delta'))):
+
+                    content = chunked.get('choices')[0].get('delta').get('content')
+                    if content:
+                        self._llmresponse += content
+                if chunked.get("usage"):
+                    self._prompt_tokens = chunked.get("usage").get("prompt_tokens")
+                    self._completion_tokens = chunked.get("usage").get("completion_tokens")
+                    self._total_tokens = chunked.get("usage").get("total_tokens")
+                self._response_id = chunked.get('id')
+                return chunk
+            except StopIteration:
+                # Handling exception ensure observability without disrupting operation
+                try:
+                    # Format 'messages' into a single string
+                    message_prompt = self._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 cost of the operation
+                    cost = get_chat_model_cost(self._kwargs.get(
+                                                    "model",
+                                                    "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                                ),
+                                                pricing_info, self._prompt_tokens,
+                                                self._completion_tokens)
+
+                    # Set Span attributes
+                    self._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_TOGETHER)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                        SemanticConvetion.GEN_AI_TYPE_CHAT)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                        gen_ai_endpoint)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                        self._response_id)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                        environment)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                        application_name)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                        self._kwargs.get(
+                                            "model",
+                                            "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                        ))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        self._kwargs.get("user", ""))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        self._kwargs.get("top_p", 1.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        self._kwargs.get("max_tokens", -1))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                        self._kwargs.get("temperature", 1.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                        self._kwargs.get("presence_penalty", 0.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
+                                        self._kwargs.get("frequency_penalty", 0.0))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                        self._kwargs.get("seed", ""))
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                        True)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                        self._prompt_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                        self._completion_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                        self._total_tokens)
+                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                        cost)
+                    if trace_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 = {
+                            TELEMETRY_SDK_NAME:
+                                "openlit",
+                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                                application_name,
+                            SemanticConvetion.GEN_AI_SYSTEM:
+                                SemanticConvetion.GEN_AI_SYSTEM_TOGETHER,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                self._kwargs.get("model",
+                                "meta-llama/Llama-3.3-70B-Instruct-Turbo")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(
+                            self._total_tokens, attributes
+                        )
+                        metrics["genai_completion_tokens"].add(
+                            self._completion_tokens, attributes
+                        )
+                        metrics["genai_prompt_tokens"].add(
+                            self._prompt_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
+
+    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
+            awaited_wrapped = wrapped(*args, **kwargs)
+            span = tracer.start_span(gen_ai_endpoint, kind=SpanKind.CLIENT)
+
+            return TracedSyncStream(awaited_wrapped, span, kwargs)
+
+        # 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)
+
+                response_dict = response_as_dict(response)
+
+                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)
+
+                    # Set base span attribues
+                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_TOGETHER)
+                    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_dict.get("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,
+                                        kwargs.get("model",
+                                        "meta-llama/Llama-3.3-70B-Instruct-Turbo"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        kwargs.get("top_p", 1.0))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        kwargs.get("max_tokens", -1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        kwargs.get("user", ""))
+                    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(kwargs.get(
+                                                        "model",
+                                                        "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                                    ),
+                                                    pricing_info,
+                                                    response_dict.get('usage', {}).get('prompt_tokens', None),
+                                                    response_dict.get('usage', {}).get('completion_tokens', None))
+
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                           response_dict.get('usage', {}).get('prompt_tokens', None))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                           response_dict.get('usage', {}).get('completion_tokens', None))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                           response_dict.get('usage', {}).get('total_tokens', None))
+                        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_dict.get('choices', [])[0].get("message").get("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_dict.get('choices')[i].get("message").get("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(kwargs.get(
+                                                    "model",
+                                                    "meta-llama/Llama-3.3-70B-Instruct-Turbo"
+                                                    ),
+                                                    pricing_info,
+                                                    response_dict.get('usage').get('prompt_tokens'),
+                                                    response_dict.get('usage').get('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_dict.get('usage').get('prompt_tokens'))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            response_dict.get('usage').get('completion_tokens'))
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            response_dict.get('usage').get('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_TOGETHER,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                kwargs.get("model", "meta-llama/Llama-3.3-70B-Instruct-Turbo")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(
+                            response_dict.get('usage').get('total_tokens'), attributes)
+                        metrics["genai_completion_tokens"].add(
+                            response_dict.get('usage').get('completion_tokens'), attributes)
+                        metrics["genai_prompt_tokens"].add(
+                            response_dict.get('usage').get('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 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 Together API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Together 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.
+    """
+
+    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 = 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
+                image_size = str(kwargs.get("width", 1024)) + "x" + str(kwargs.get("height", 1024))
+                cost_per_million = get_image_model_cost(kwargs.get(
+                                            "model", "black-forest-labs/FLUX.1-dev"
+                                            ),
+                                            pricing_info, "1000000",
+                                            kwargs.get("quality", "standard"))
+                pixels = kwargs.get("width", 1024) * kwargs.get("height", 1024)
+                cost = pixels / 1_000_000 * cost_per_million
+
+                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_TOGETHER)
+                    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.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,
+                                        kwargs.get("model", "black-forest-labs/FLUX.1-dev"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_SIZE,
+                                        image_size)
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IMAGE_QUALITY,
+                                        kwargs.get("quality", "standard"))
+                    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_TOGETHER,
+                        SemanticConvetion.GEN_AI_ENVIRONMENT:
+                            environment,
+                        SemanticConvetion.GEN_AI_TYPE:
+                            SemanticConvetion.GEN_AI_TYPE_IMAGE,
+                        SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                            kwargs.get("model", "black-forest-labs/FLUX.1-dev")
+                    }
+
+                    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

openlit/semcov/__init__.py

@@ -134,6 +134,7 @@ class SemanticConvetion:
     GEN_AI_SYSTEM_CRAWL4AI = "crawl4ai"
     GEN_AI_SYSTEM_FIRECRAWL = "firecrawl"
     GEN_AI_SYSTEM_LETTA = "letta"
+    GEN_AI_SYSTEM_TOGETHER = "together"
 
     # Vector DB
     DB_OPERATION_API_ENDPOINT = "db.operation.api_endpoint"

{openlit-1.32.12.dist-info → openlit-1.33.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.32.12
+Version: 1.33.0
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 Home-page: https://github.com/openlit/openlit/tree/main/openlit/python
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu
@@ -56,7 +56,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 
 ## ⚡ Features
 
-- 🔎 **Auto Instrumentation**: Works with 40+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
+- 🔎 **Auto Instrumentation**: Works with 50+ LLM providers, Agents, Vector databases, and GPUs with just one line of code.
 - 🔭 **OpenTelemetry-Native Observability SDKs**: Vendor-neutral SDKs that can send traces and metrics to your existing observability tool like Prometheus and Jaeger.
 - 💲 **Cost Tracking for Custom and Fine-Tuned Models**: Pass custom pricing files for accurate budgeting of custom and fine-tuned models.
 - 🚀 **Suppport for OpenLIT Features**: Includes suppprt for prompt management and secrets management features available in OpenLIT.
@@ -89,6 +89,7 @@ This project proudly follows and maintains the [Semantic Conventions](https://gi
 | [✅ xAI](https://docs.openlit.io/latest/integrations/xai)                            |                                                                          |                                                |               |
 | [✅ Prem AI](https://docs.openlit.io/latest/integrations/premai)                     |                                                                          |                                                |               |
 | [✅ Assembly AI](https://docs.openlit.io/latest/integrations/assemblyai)             |                                                                          |                                                |               |
+| [✅ Together](https://docs.openlit.io/latest/integrations/together)                  |                                                                          |                                                |               |
 
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)

{openlit-1.32.12.dist-info → openlit-1.33.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 openlit/__helpers.py,sha256=bqMxdNndLW5NGO2wwpAoHEOnAFr_mhnmVLua3ifpSEc,6427
-openlit/__init__.py,sha256=VBmUj1L-HKJnSIV6Ga1YHPgxdLZbNPj6T6DDIkdvzOM,21870
+openlit/__init__.py,sha256=CBo1-jSVFbyQ3dEeFog95Bhd8f2BZG8QoLsTtObfiks,21954
 openlit/evals/__init__.py,sha256=nJe99nuLo1b5rf7pt9U9BCdSDedzbVi2Fj96cgl7msM,380
 openlit/evals/all.py,sha256=oWrue3PotE-rB5WePG3MRYSA-ro6WivkclSHjYlAqGs,7154
 openlit/evals/bias_detection.py,sha256=mCdsfK7x1vX7S3psC3g641IMlZ-7df3h-V6eiICj5N8,8154
@@ -103,6 +103,9 @@ openlit/instrumentation/qdrant/qdrant.py,sha256=K0cvEUbNx0hnk8AbEheYPSHcCgjFC482
 openlit/instrumentation/reka/__init__.py,sha256=X0zZ8Q18Z_6pIpksa7pdWldK4SKZM7U24zNc2UeRXC8,1870
 openlit/instrumentation/reka/async_reka.py,sha256=PDodlH_XycevE3k8u0drP7bokKtPDUcDfzfWRz6Fzt4,7439
 openlit/instrumentation/reka/reka.py,sha256=CL9uNX_tYjw2eetTxLKRNRQJ-OgI_e5YRz9iu9f_gP4,7421
+openlit/instrumentation/together/__init__.py,sha256=pg3gNqT4HjL3E-QHvAkM0UNdF3obii0HHp2xRx32gRc,2713
+openlit/instrumentation/together/async_together.py,sha256=HUO3lCheCq1o9wRzuL11_osVr_5U3Q5VGACIGirmwgg,29120
+openlit/instrumentation/together/together.py,sha256=XVeZWo6MbWGpbI705fKjyhQMF6lOnpa-jaYlTowcxOs,29024
 openlit/instrumentation/transformers/__init__.py,sha256=4GBtjzcJU4XiPexIUYEqF3pNZMeQw4Gm5B-cyumaFjs,1468
 openlit/instrumentation/transformers/transformers.py,sha256=MWEVkxHRWTHrpD85I1leksDIVtBiTtR5fQCO3Z62qb4,7875
 openlit/instrumentation/vertexai/__init__.py,sha256=N3E9HtzefD-zC0fvmfGYiDmSqssoavp_i59wfuYLyMw,6079
@@ -112,8 +115,8 @@ openlit/instrumentation/vllm/__init__.py,sha256=OVWalQ1dXvip1DUsjUGaHX4J-2FrSp-T
 openlit/instrumentation/vllm/vllm.py,sha256=lDzM7F5pgxvh8nKL0dcKB4TD0Mc9wXOWeXOsOGN7Wd8,6527
 openlit/otel/metrics.py,sha256=y7SQDTyfLakMrz0V4DThN-WAeap7YZzyndeYGSP6nVg,4516
 openlit/otel/tracing.py,sha256=fG3vl-flSZ30whCi7rrG25PlkIhhr8PhnfJYCkZzCD0,3895
-openlit/semcov/__init__.py,sha256=F30Ki_08YjPrMe73kjp5sulC0qxHp9e-VExbzAOM1YI,10935
-openlit-1.32.12.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-openlit-1.32.12.dist-info/METADATA,sha256=hHrHGhViseJ9Cj6kyqrmMSIeudiOoQ93Mrbj_mnF8rQ,22735
-openlit-1.32.12.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-openlit-1.32.12.dist-info/RECORD,,
+openlit/semcov/__init__.py,sha256=_kxniPeCdAYC_ZK982gqDR6RwgFCIK8xUPCzotwtt0k,10975
+openlit-1.33.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.33.0.dist-info/METADATA,sha256=8_RfDUPjeQOBe32z7AQOZMKB6xDUmmpRNGxmescBQN4,22964
+openlit-1.33.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+openlit-1.33.0.dist-info/RECORD,,