openlit 1.19.0__py3-none-any.whl → 1.20.0__py3-none-any.whl

openlit/__init__.py

@@ -33,6 +33,7 @@ from openlit.instrumentation.ollama import OllamaInstrumentor
 from openlit.instrumentation.gpt4all import GPT4AllInstrumentor
 from openlit.instrumentation.elevenlabs import ElevenLabsInstrumentor
 from openlit.instrumentation.vllm import VLLMInstrumentor
+from openlit.instrumentation.google_ai_studio import GoogleAIStudioInstrumentor
 from openlit.instrumentation.langchain import LangChainInstrumentor
 from openlit.instrumentation.llamaindex import LlamaIndexInstrumentor
 from openlit.instrumentation.haystack import HaystackInstrumentor
@@ -196,6 +197,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
         "gpt4all": "gpt4all",
         "elevenlabs": "elevenlabs",
         "vllm": "vllm",
+        "google-ai-studio": "google.generativeai",
         "langchain": "langchain",
         "llama_index": "llama_index",
         "haystack": "haystack",
@@ -273,6 +275,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
             "gpt4all": GPT4AllInstrumentor(),
             "elevenlabs": ElevenLabsInstrumentor(),
             "vllm": VLLMInstrumentor(),
+            "google-ai-studio": GoogleAIStudioInstrumentor(),
             "langchain": LangChainInstrumentor(),
             "llama_index": LlamaIndexInstrumentor(),
             "haystack": HaystackInstrumentor(),

openlit/instrumentation/google_ai_studio/__init__.py

@@ -0,0 +1,56 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of Google AI Studio Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.google_ai_studio.google_ai_studio import (
+    generate
+)
+
+from openlit.instrumentation.google_ai_studio.async_google_ai_studio import (
+    async_generate
+)
+
+_instruments = ("google-generativeai >= 0.2.0",)
+
+class GoogleAIStudioInstrumentor(BaseInstrumentor):
+    """
+    An instrumentor for google-generativeai'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("ollama")
+
+        # sync generate
+        wrap_function_wrapper(
+            "google.generativeai.generative_models",
+            "GenerativeModel.generate_content",
+            generate("google_ai_studio.generate_content", version, environment, application_name,
+                  tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        # async generate
+        wrap_function_wrapper(
+            "google.generativeai.generative_models",
+            "GenerativeModel.generate_content_async",
+            async_generate("google_ai_studio.generate_content", 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/google_ai_studio/async_google_ai_studio.py

@@ -0,0 +1,259 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment, protected-access
+"""
+Module for monitoring Ollama API calls.
+"""
+
+import logging
+from opentelemetry.trace import SpanKind, Status, StatusCode
+from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from openlit.__helpers import (
+    handle_exception,
+    get_chat_model_cost,
+)
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def async_generate(gen_ai_endpoint, version, environment, application_name,
+                     tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for chat 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 Ollama API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Ollama usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat method to add telemetry.
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 'chat' API call to add telemetry.
+        
+        This collects metrics such as execution time, cost, and token usage, and handles errors
+        gracefully, adding details to the trace for observability.
+
+        Args:
+            wrapped: The original 'chat' method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the 'chat' method.
+            kwargs: Keyword arguments for the 'chat' method.
+
+        Returns:
+            The response from the original 'chat' method.
+        """
+        # pylint: disable=no-else-return
+        if kwargs.get('stream', False) is True:
+            # Special handling for streaming response to accommodate the nature of data flow
+            async def stream_generator():
+                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
+                        content = chunk.text
+                        if content:
+                            llmresponse += content
+
+                        input_tokens = chunk.usage_metadata.prompt_token_count
+                        output_tokens = chunk.usage_metadata.candidates_token_count
+                        yield chunk
+
+                    # Handling exception ensure observability without disrupting operation
+                    try:
+                        prompt = ""
+                        for arg in args:
+                            if isinstance(arg, str):
+                                prompt = f"{prompt}{arg}\n"
+                            elif isinstance(arg, list):
+                                for subarg in arg:
+                                    prompt = f"{prompt}{subarg}\n"
+                        if hasattr(instance, "_model_id"):
+                            model = instance._model_id
+                        if hasattr(instance, "_model_name"):
+                            model = instance._model_name.replace("publishers/google/models/", "")
+
+                        total_tokens = input_tokens + output_tokens
+                        # Calculate cost of the operation
+                        cost = get_chat_model_cost(kwargs.get("model", "gpt-3.5-turbo"),
+                                                    pricing_info, input_tokens,
+                                                    output_tokens)
+
+                        # Set Span attributes
+                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                            SemanticConvetion.GEN_AI_SYSTEM_GOOGLE_AI_STUDIO)
+                        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_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_IS_STREAM,
+                                            True)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            input_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            output_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            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: 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_GOOGLE_AI_STUDIO,
+                                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(
+                                total_tokens, attributes
+                            )
+                            metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                            metrics["genai_prompt_tokens"].add(input_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()
+        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:
+                    prompt = ""
+                    for arg in args:
+                        if isinstance(arg, str):
+                            prompt = f"{prompt}{arg}\n"
+                        elif isinstance(arg, list):
+                            for subarg in arg:
+                                prompt = f"{prompt}{subarg}\n"
+                    if hasattr(instance, "_model_id"):
+                        model = instance._model_id
+                    if hasattr(instance, "_model_name"):
+                        model = instance._model_name.replace("publishers/google/models/", "")
+
+                    # Set base span attribues
+                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_GOOGLE_AI_STUDIO)
+                    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_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_IS_STREAM,
+                                        False)
+
+                    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: response.text,
+                            },
+                        )
+
+                    prompt_tokens = response.usage_metadata.prompt_token_count
+                    completion_tokens = response.usage_metadata.candidates_token_count
+                    total_tokens = response.usage_metadata.total_token_count
+                    # Calculate cost of the operation
+                    cost = get_chat_model_cost(kwargs.get("model", "llama3"),
+                                                pricing_info, prompt_tokens, completion_tokens)
+
+                    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,
+                                        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_OLLAMA,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                kwargs.get("model", "llama3")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(total_tokens, attributes)
+                        metrics["genai_completion_tokens"].add(completion_tokens, attributes)
+                        metrics["genai_prompt_tokens"].add(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

openlit/instrumentation/google_ai_studio/google_ai_studio.py

@@ -0,0 +1,261 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment, protected-access
+"""
+Module for monitoring Ollama API calls.
+"""
+
+import logging
+from opentelemetry.trace import SpanKind, Status, StatusCode
+from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from openlit.__helpers import (
+    handle_exception,
+    get_chat_model_cost,
+)
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def generate(gen_ai_endpoint, version, environment, application_name,
+                     tracer, pricing_info, trace_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for chat 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 Ollama API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Ollama usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat method to add telemetry.
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 'chat' API call to add telemetry.
+        
+        This collects metrics such as execution time, cost, and token usage, and handles errors
+        gracefully, adding details to the trace for observability.
+
+        Args:
+            wrapped: The original 'chat' method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the 'chat' method.
+            kwargs: Keyword arguments for the 'chat' method.
+
+        Returns:
+            The response from the original 'chat' method.
+        """
+        # pylint: disable=no-else-return
+        if kwargs.get("stream", False) is True:
+            # Special handling for streaming response to accommodate the nature of data flow
+            def stream_generator():
+                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
+                    for chunk in wrapped(*args, **kwargs):
+                        # Collect message IDs and aggregated response from events
+                        content = chunk.text
+                        if content:
+                            llmresponse += content
+
+                        input_tokens = chunk.usage_metadata.prompt_token_count
+                        output_tokens = chunk.usage_metadata.candidates_token_count
+                        yield chunk
+
+                    # Handling exception ensure observability without disrupting operation
+                    try:
+                        prompt = ""
+                        for arg in args:
+                            if isinstance(arg, str):
+                                prompt = f"{prompt}{arg}\n"
+                            elif isinstance(arg, list):
+                                for subarg in arg:
+                                    prompt = f"{prompt}{subarg}\n"
+                        if hasattr(instance, "_model_id"):
+                            model = instance._model_id
+                        if hasattr(instance, "_model_name"):
+                            model = instance._model_name.replace("publishers/google/models/", "")
+
+                        total_tokens = input_tokens + output_tokens
+                        # Calculate cost of the operation
+                        cost = get_chat_model_cost(kwargs.get("model", "gpt-3.5-turbo"),
+                                                    pricing_info, input_tokens,
+                                                    output_tokens)
+
+                        # Set Span attributes
+                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                            SemanticConvetion.GEN_AI_SYSTEM_GOOGLE_AI_STUDIO)
+                        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_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_IS_STREAM,
+                                            True)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            input_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            output_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            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: 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_GOOGLE_AI_STUDIO,
+                                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(
+                                total_tokens, attributes
+                            )
+                            metrics["genai_completion_tokens"].add(output_tokens, attributes)
+                            metrics["genai_prompt_tokens"].add(input_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()
+        else:
+            # pylint: disable=line-too-long
+            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+                response = wrapped(*args, **kwargs)
+
+                # print(instance._system_instruction.__dict__["_pb"].parts[0].text)
+                try:
+                    prompt = ""
+                    for arg in args:
+                        if isinstance(arg, str):
+                            prompt = f"{prompt}{arg}\n"
+                        elif isinstance(arg, list):
+                            for subarg in arg:
+                                prompt = f"{prompt}{subarg}\n"
+
+                    if hasattr(instance, "_model_id"):
+                        model = instance._model_id
+                    if hasattr(instance, "_model_name"):
+                        model = instance._model_name.replace("publishers/google/models/", "")
+
+                    # Set base span attribues
+                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                        SemanticConvetion.GEN_AI_SYSTEM_GOOGLE_AI_STUDIO)
+                    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_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_IS_STREAM,
+                                        False)
+
+                    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: response.text,
+                            },
+                        )
+
+                    prompt_tokens = response.usage_metadata.prompt_token_count
+                    completion_tokens = response.usage_metadata.candidates_token_count
+                    total_tokens = response.usage_metadata.total_token_count
+                    # Calculate cost of the operation
+                    cost = get_chat_model_cost(kwargs.get("model", "llama3"),
+                                                pricing_info, prompt_tokens, completion_tokens)
+
+                    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,
+                                        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_OLLAMA,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                kwargs.get("model", "llama3")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(total_tokens, attributes)
+                        metrics["genai_completion_tokens"].add(completion_tokens, attributes)
+                        metrics["genai_prompt_tokens"].add(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

openlit/semcov/__init__.py

@@ -102,6 +102,7 @@ class SemanticConvetion:
     GEN_AI_SYSTEM_GPT4ALL = "gpt4all"
     GEN_AI_SYSTEM_ELEVENLABS = "elevenlabs"
     GEN_AI_SYSTEM_VLLM = "vLLM"
+    GEN_AI_SYSTEM_GOOGLE_AI_STUDIO = "google-ai-studio"
     GEN_AI_SYSTEM_LANGCHAIN = "langchain"
     GEN_AI_SYSTEM_LLAMAINDEX = "llama_index"
     GEN_AI_SYSTEM_HAYSTACK = "haystack"

{openlit-1.19.0.dist-info → openlit-1.20.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.19.0
+Version: 1.20.0
 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
@@ -60,7 +60,7 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 | [✅ Ollama](https://docs.openlit.io/latest/integrations/ollama)              | [✅ Pinecone](https://docs.openlit.io/latest/integrations/pinecone)       | [✅ LiteLLM](https://docs.openlit.io/latest/integrations/litellm)         |               |
 | [✅ Anthropic](https://docs.openlit.io/latest/integrations/anthropic)        | [✅ Qdrant](https://docs.openlit.io/latest/integrations/qdrant)           | [✅ LlamaIndex](https://docs.openlit.io/latest/integrations/llama-index)  |               |
 | [✅ GPT4All](https://docs.openlit.io/latest/integrations/gpt4all)            | [✅ Milvus](https://docs.openlit.io/latest/integrations/milvus)           | [✅ Haystack](https://docs.openlit.io/latest/integrations/haystack)       |               |
-| [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere)              |                                                                          | [✅ EmbedChain](https://docs.openlit.io/latest/integrations/embedchain)   |               |                                       
+| [✅ Cohere](https://docs.openlit.io/latest/integrations/cohere)              |                                          | [✅ EmbedChain](https://docs.openlit.io/latest/integrations/embedchain)   |               |                                       
 | [✅ Mistral](https://docs.openlit.io/latest/integrations/mistral)            |                                                                          | [✅ Guardrails](https://docs.openlit.io/latest/integrations/guardrails)   |               |
 | [✅ Azure OpenAI](https://docs.openlit.io/latest/integrations/azure-openai)  |                                                                          |                                       |               |
 | [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface) |                                                                          |                                        |               |
@@ -70,6 +70,7 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 | [✅ ElevenLabs](https://docs.openlit.io/latest/integrations/elevenlabs)      |                                                                          |                                       |               |
 | [✅ vLLM](https://docs.openlit.io/latest/integrations/vllm)                  |                                                                          |                                       |               |
 | [✅ OLA Krutrim](https://docs.openlit.io/latest/integrations/krutrim)                  |                                                                          |                                       |               |
+| [✅ Google AI Studio](https://docs.openlit.io/latest/integrations/google-ai-studio) |                                                                          |                                       |               |
 
 ## Supported Destinations
 - [✅ OpenTelemetry Collector](https://docs.openlit.io/latest/connections/otelcol)

{openlit-1.19.0.dist-info → openlit-1.20.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 openlit/__helpers.py,sha256=lrn4PBs9owDudiCY2NBoVbAi7AU_HtUpyOj0oqPBsPY,5545
-openlit/__init__.py,sha256=LfU5w-D62u5pY70DdNbv5_DGtqeL1Yb0TlY-l0NAn8I,15103
+openlit/__init__.py,sha256=fqeMFg76VYEX4VdxTn76Fh-0kbrN5_Sk8ahlm7Xlp9k,15296
 openlit/instrumentation/anthropic/__init__.py,sha256=oaU53BOPyfUKbEzYvLr1DPymDluurSnwo4Hernf2XdU,1955
 openlit/instrumentation/anthropic/anthropic.py,sha256=y7CEGhKOGHWt8G_5Phr4qPJTfPGRJIAr9Yk6nM3CcvM,16775
 openlit/instrumentation/anthropic/async_anthropic.py,sha256=Zz1KRKIG9wGn0quOoLvjORC-49IvHQpJ6GBdB-4PfCQ,16816
@@ -14,6 +14,9 @@ openlit/instrumentation/elevenlabs/async_elevenlabs.py,sha256=yMYACh95SFr5EYklKn
 openlit/instrumentation/elevenlabs/elevenlabs.py,sha256=mFnD7sgT47OxaXJz0Vc1nrNjXEpcGQDj5run3gA48Lw,6089
 openlit/instrumentation/embedchain/__init__.py,sha256=8TYk1OEbz46yF19dr-gB_x80VZMagU3kJ8-QihPXTeA,1929
 openlit/instrumentation/embedchain/embedchain.py,sha256=SLlr7qieT3kp4M6OYSRy8FaVCXQ2t3oPyIiE99ioNE4,7892
+openlit/instrumentation/google_ai_studio/__init__.py,sha256=vG4WzaavOiiwI3r5stDMotM5TSBxdcxQhC3W4XjJIG8,2146
+openlit/instrumentation/google_ai_studio/async_google_ai_studio.py,sha256=cEy5FNu92gvdmsKKVDrUcY5LpY4hHzWwJl9yezxN-Zo,13404
+openlit/instrumentation/google_ai_studio/google_ai_studio.py,sha256=mLABvD756GEgVfAjiYsfLYWATT1AxPuWDuElwpX4voo,13453
 openlit/instrumentation/gpt4all/__init__.py,sha256=-59CP2B3-HGZJ_vC-fI9Dt-0BuQXRhSCWCjnaGeU15Q,1802
 openlit/instrumentation/gpt4all/gpt4all.py,sha256=dbxqZeuTrv_y6wyDOIEmC8-Dc4iCGgLpj3l5JiodLMI,18787
 openlit/instrumentation/gpu/__init__.py,sha256=Dj2MLar0DB20-t6W3pfR-3jfR_mwg4SYwhzIrH_n9sU,5596
@@ -52,8 +55,8 @@ openlit/instrumentation/vllm/__init__.py,sha256=OVWalQ1dXvip1DUsjUGaHX4J-2FrSp-T
 openlit/instrumentation/vllm/vllm.py,sha256=lDzM7F5pgxvh8nKL0dcKB4TD0Mc9wXOWeXOsOGN7Wd8,6527
 openlit/otel/metrics.py,sha256=O7NoaDz0bY19mqpE4-0PcKwEe-B-iJFRgOCaanAuZAc,4291
 openlit/otel/tracing.py,sha256=vL1ifMbARPBpqK--yXYsCM6y5dSu5LFIKqkhZXtYmUc,3712
-openlit/semcov/__init__.py,sha256=EvoNOKtc7UKwLZ3Gp0-B1zwmeTcAIbx8O7wvAw8wXP4,7498
-openlit-1.19.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-openlit-1.19.0.dist-info/METADATA,sha256=7P2h2TmPkrD-DTeqa0qqaC_oiqp8LdcEZ-pjuVepCjY,14746
-openlit-1.19.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-openlit-1.19.0.dist-info/RECORD,,
+openlit/semcov/__init__.py,sha256=56daxsJtWFqp87TTT3R5OxSeMH7eOZqb4k-7AELirTI,7554
+openlit-1.20.0.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.20.0.dist-info/METADATA,sha256=DvK9Dt8ZvBBvdPc_Fdbi7HxkCu9Kp-Z4IkzCOuynkg4,14934
+openlit-1.20.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+openlit-1.20.0.dist-info/RECORD,,