openlit 1.3.0__tar.gz → 1.4.0__tar.gz

{openlit-1.3.0 → openlit-1.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: openlit
-Version: 1.3.0
+Version: 1.4.0
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, 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
@@ -57,6 +57,7 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 - [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface)
 - [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock)
 - [✅ Vertex AI](https://docs.openlit.io/latest/integrations/vertexai)
+- [✅ Groq](https://docs.openlit.io/latest/integrations/groq)
 
 ### Vector DBs
 - [✅ ChromaDB](https://docs.openlit.io/latest/integrations/chromadb)

{openlit-1.3.0 → openlit-1.4.0}/README.md

@@ -32,6 +32,7 @@ This project adheres to the [Semantic Conventions](https://github.com/open-telem
 - [✅ HuggingFace Transformers](https://docs.openlit.io/latest/integrations/huggingface)
 - [✅ Amazon Bedrock](https://docs.openlit.io/latest/integrations/bedrock)
 - [✅ Vertex AI](https://docs.openlit.io/latest/integrations/vertexai)
+- [✅ Groq](https://docs.openlit.io/latest/integrations/groq)
 
 ### Vector DBs
 - [✅ ChromaDB](https://docs.openlit.io/latest/integrations/chromadb)

{openlit-1.3.0 → openlit-1.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.3.0"
+version = "1.4.0"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 repository = "https://github.com/openlit/openlit/tree/main/openlit/python"

{openlit-1.3.0 → openlit-1.4.0}/src/openlit/__init__.py

@@ -19,6 +19,7 @@ from openlit.instrumentation.cohere import CohereInstrumentor
 from openlit.instrumentation.mistral import MistralInstrumentor
 from openlit.instrumentation.bedrock import BedrockInstrumentor
 from openlit.instrumentation.vertexai import VertexAIInstrumentor
+from openlit.instrumentation.groq import GroqInstrumentor
 from openlit.instrumentation.langchain import LangChainInstrumentor
 from openlit.instrumentation.llamaindex import LlamaIndexInstrumentor
 from openlit.instrumentation.haystack import HaystackInstrumentor
@@ -151,6 +152,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
         "mistral": "mistralai",
         "bedrock": "boto3",
         "vertexai": "vertexai",
+        "groq": "groq",
         "langchain": "langchain",
         "llama_index": "llama_index",
         "haystack": "haystack",
@@ -201,6 +203,7 @@ def init(environment="default", application_name="default", tracer=None, otlp_en
             "mistral": MistralInstrumentor(),
             "bedrock": BedrockInstrumentor(),
             "vertexai": VertexAIInstrumentor(),
+            "groq": GroqInstrumentor(),
             "langchain": LangChainInstrumentor(),
             "llama_index": LlamaIndexInstrumentor(),
             "haystack": HaystackInstrumentor(),

openlit-1.4.0/src/openlit/instrumentation/groq/__init__.py

@@ -0,0 +1,50 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of Groq Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.groq.groq import chat
+from openlit.instrumentation.groq.async_groq import async_chat
+
+_instruments = ("groq >= 0.5.0",)
+
+class GroqInstrumentor(BaseInstrumentor):
+    """
+    An instrumentor for Groq'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("groq")
+
+        #sync
+        wrap_function_wrapper(
+            "groq.resources.chat.completions",  
+            "Completions.create",  
+            chat("groq.chat.completions", version, environment, application_name,
+                     tracer, pricing_info, trace_content, metrics, disable_metrics),
+        )
+
+        #async
+        wrap_function_wrapper(
+            "groq.resources.chat.completions",  
+            "AsyncCompletions.create",  
+            async_chat("groq.chat.completions", 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-1.4.0/src/openlit/instrumentation/groq/async_groq.py

@@ -0,0 +1,331 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, used-before-assignment, too-many-branches
+"""
+Module for monitoring Groq API calls.
+"""
+
+import logging
+from opentelemetry.trace import SpanKind, Status, StatusCode
+from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from openlit.__helpers import get_chat_model_cost, handle_exception
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def async_chat(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 Groq API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Groq usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat completions method to add telemetry.
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the 'chat.completions' API call to add telemetry.
+        
+        This collects metrics such as execution time, cost, and token usage, and handles errors
+        gracefully, adding details to the trace for observability.
+
+        Args:
+            wrapped: The original 'chat.completions' method to be wrapped.
+            instance: The instance of the class where the original method is defined.
+            args: Positional arguments for the 'chat.completions' method.
+            kwargs: Keyword arguments for the 'chat.completions' method.
+
+        Returns:
+            The response from the original 'chat.completions' method.
+        """
+
+        # Check if streaming is enabled for the API call
+        streaming = kwargs.get("stream", False)
+
+        # pylint: disable=no-else-return
+        if streaming:
+            # Special handling for streaming response to accommodate the nature of data flow
+            async def stream_generator():
+                with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+                    # Placeholder for aggregating streaming response
+                    llmresponse = ""
+
+                    # Loop through streaming events capturing relevant details
+                    async for chunk in await wrapped(*args, **kwargs):
+                        # Collect message IDs and aggregated response from events
+                        if len(chunk.choices) > 0:
+                            # pylint: disable=line-too-long
+                            if hasattr(chunk.choices[0], "delta") and hasattr(chunk.choices[0].delta, "content"):
+                                content = chunk.choices[0].delta.content
+                                if content:
+                                    llmresponse += content
+                            if chunk.x_groq is not None and chunk.x_groq.usage is not None:
+                                prompt_tokens = chunk.x_groq.usage.prompt_tokens
+                                completion_tokens = chunk.x_groq.usage.completion_tokens
+                                total_tokens = chunk.x_groq.usage.total_tokens
+                                response_id = chunk.x_groq.id
+                        yield chunk
+
+                    # Handling exception ensure observability without disrupting operation
+                    try:
+                        # Format 'messages' into a single string
+                        message_prompt = kwargs.get("messages", "")
+                        formatted_messages = []
+                        for message in message_prompt:
+                            role = message["role"]
+                            content = message["content"]
+
+                            if isinstance(content, list):
+                                content_str = ", ".join(
+                                    # pylint: disable=line-too-long
+                                    f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
+                                    if "type" in item else f'text: {item["text"]}'
+                                    for item in content
+                                )
+                                formatted_messages.append(f"{role}: {content_str}")
+                            else:
+                                formatted_messages.append(f"{role}: {content}")
+                        prompt = "\n".join(formatted_messages)
+
+                        # Calculate cost of the operation
+                        cost = get_chat_model_cost(kwargs.get("model", "gpt-3.5-turbo"),
+                                                    pricing_info, prompt_tokens,
+                                                    completion_tokens)
+
+                        # Set Span attributes
+                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                            SemanticConvetion.GEN_AI_SYSTEM_GROQ)
+                        span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                            SemanticConvetion.GEN_AI_TYPE_CHAT)
+                        span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                            gen_ai_endpoint)
+                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                            response_id)
+                        span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                            environment)
+                        span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                            application_name)
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                            kwargs.get("model", "gpt-3.5-turbo"))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                            kwargs.get("user", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                            kwargs.get("top_p", 1))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                            kwargs.get("max_tokens", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                            kwargs.get("temperature", 1))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                            kwargs.get("presence_penalty", 0))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
+                                            kwargs.get("frequency_penalty", 0))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                            kwargs.get("seed", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                            True)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            prompt_tokens + completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                            cost)
+                        if trace_content:
+                            span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                                prompt)
+                            span.set_attribute(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_GROQ,
+                                SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                    environment,
+                                SemanticConvetion.GEN_AI_TYPE:
+                                    SemanticConvetion.GEN_AI_TYPE_CHAT,
+                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                    kwargs.get("model", "gpt-3.5-turbo")
+                            }
+
+                            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)
+
+                    except Exception as e:
+                        handle_exception(span, e)
+                        logger.error("Error in trace creation: %s", e)
+
+            return stream_generator()
+
+        # Handling for non-streaming responses
+        else:
+            # pylint: disable=line-too-long
+            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+                response = await wrapped(*args, **kwargs)
+
+                try:
+                    # 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_GROQ)
+                    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.x_groq["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", "llama3-8b-8192"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        kwargs.get("top_p", 1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        kwargs.get("max_tokens", ""))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        kwargs.get("name", ""))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                        kwargs.get("temperature", 1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                        kwargs.get("presence_penalty", 0))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
+                                        kwargs.get("frequency_penalty", 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.set_attribute(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", "llama3-8b-8192"),
+                                                    pricing_info, response.usage.prompt_tokens,
+                                                    response.usage.completion_tokens)
+
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            response.usage.prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            response.usage.completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            response.usage.total_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                            response.choices[0].finish_reason)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                            cost)
+
+                        # Set span attributes for when n = 1 (default)
+                        if "n" not in kwargs or kwargs["n"] == 1:
+                            if trace_content:
+                                span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                                    response.choices[0].message.content)
+
+                        # Set span attributes for when n > 0
+                        else:
+                            i = 0
+                            while i < kwargs["n"] and trace_content is True:
+                                attribute_name = f"gen_ai.content.completion.{i}"
+                                span.set_attribute(attribute_name,
+                                                    response.choices[i].message.content)
+                                i += 1
+
+                            # Return original response
+                            return response
+
+                    # Set span attributes when tools is passed to the function call
+                    elif "tools" in kwargs:
+                        # Calculate cost of the operation
+                        cost = get_chat_model_cost(kwargs.get("model", "gpt-3.5-turbo"),
+                                                    pricing_info, response.usage.prompt_tokens,
+                                                    response.usage.completion_tokens)
+
+                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                            "Function called with tools")
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            response.usage.prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            response.usage.completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            response.usage.total_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                            cost)
+
+                    span.set_status(Status(StatusCode.OK))
+
+                    if disable_metrics is False:
+                        attributes = {
+                            TELEMETRY_SDK_NAME:
+                                "openlit",
+                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                                application_name,
+                            SemanticConvetion.GEN_AI_SYSTEM:
+                                SemanticConvetion.GEN_AI_SYSTEM_GROQ,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                kwargs.get("model", "gpt-3.5-turbo")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
+                        metrics["genai_completion_tokens"].add(response.usage.completion_tokens, attributes)
+                        metrics["genai_prompt_tokens"].add(response.usage.prompt_tokens, attributes)
+                        metrics["genai_cost"].record(cost, attributes)
+
+                    # Return original response
+                    return response
+
+                except Exception as e:
+                    handle_exception(span, e)
+                    logger.error("Error in trace creation: %s", e)
+
+                    # Return original response
+                    return response
+
+    return wrapper

openlit-1.4.0/src/openlit/instrumentation/groq/groq.py

@@ -0,0 +1,331 @@
+# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, used-before-assignment, too-many-branches
+"""
+Module for monitoring Groq API calls.
+"""
+
+import logging
+from opentelemetry.trace import SpanKind, Status, StatusCode
+from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
+from openlit.__helpers import get_chat_model_cost, handle_exception
+from openlit.semcov import SemanticConvetion
+
+# Initialize logger for logging potential issues and operations
+logger = logging.getLogger(__name__)
+
+def chat(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 Groq API.
+        tracer: OpenTelemetry tracer for creating spans.
+        pricing_info: Information used for calculating the cost of Groq usage.
+        trace_content: Flag indicating whether to trace the actual content.
+
+    Returns:
+        A function that wraps the chat completions method to add telemetry.
+    """
+
+    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
+            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
+                        if len(chunk.choices) > 0:
+                            # pylint: disable=line-too-long
+                            if hasattr(chunk.choices[0], "delta") and hasattr(chunk.choices[0].delta, "content"):
+                                content = chunk.choices[0].delta.content
+                                if content:
+                                    llmresponse += content
+                            if chunk.x_groq is not None and chunk.x_groq.usage is not None:
+                                prompt_tokens = chunk.x_groq.usage.prompt_tokens
+                                completion_tokens = chunk.x_groq.usage.completion_tokens
+                                total_tokens = chunk.x_groq.usage.total_tokens
+                                response_id = chunk.x_groq.id
+                        yield chunk
+
+                    # Handling exception ensure observability without disrupting operation
+                    try:
+                        # Format 'messages' into a single string
+                        message_prompt = kwargs.get("messages", "")
+                        formatted_messages = []
+                        for message in message_prompt:
+                            role = message["role"]
+                            content = message["content"]
+
+                            if isinstance(content, list):
+                                content_str = ", ".join(
+                                    # pylint: disable=line-too-long
+                                    f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
+                                    if "type" in item else f'text: {item["text"]}'
+                                    for item in content
+                                )
+                                formatted_messages.append(f"{role}: {content_str}")
+                            else:
+                                formatted_messages.append(f"{role}: {content}")
+                        prompt = "\n".join(formatted_messages)
+
+                        # Calculate cost of the operation
+                        cost = get_chat_model_cost(kwargs.get("model", "gpt-3.5-turbo"),
+                                                    pricing_info, prompt_tokens,
+                                                    completion_tokens)
+
+                        # Set Span attributes
+                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
+                                            SemanticConvetion.GEN_AI_SYSTEM_GROQ)
+                        span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
+                                            SemanticConvetion.GEN_AI_TYPE_CHAT)
+                        span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
+                                            gen_ai_endpoint)
+                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
+                                            response_id)
+                        span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
+                                            environment)
+                        span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
+                                            application_name)
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
+                                            kwargs.get("model", "gpt-3.5-turbo"))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                            kwargs.get("user", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                            kwargs.get("top_p", 1))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                            kwargs.get("max_tokens", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                            kwargs.get("temperature", 1))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                            kwargs.get("presence_penalty", 0))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
+                                            kwargs.get("frequency_penalty", 0))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_SEED,
+                                            kwargs.get("seed", ""))
+                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
+                                            True)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            prompt_tokens + completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                            cost)
+                        if trace_content:
+                            span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_PROMPT,
+                                                prompt)
+                            span.set_attribute(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_GROQ,
+                                SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                    environment,
+                                SemanticConvetion.GEN_AI_TYPE:
+                                    SemanticConvetion.GEN_AI_TYPE_CHAT,
+                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                    kwargs.get("model", "gpt-3.5-turbo")
+                            }
+
+                            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)
+
+                    except Exception as e:
+                        handle_exception(span, e)
+                        logger.error("Error in trace creation: %s", e)
+
+            return stream_generator()
+
+        # Handling for non-streaming responses
+        else:
+            # pylint: disable=line-too-long
+            with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
+                response = wrapped(*args, **kwargs)
+
+                try:
+                    # 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_GROQ)
+                    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.x_groq["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", "llama3-8b-8192"))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
+                                        kwargs.get("top_p", 1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
+                                        kwargs.get("max_tokens", ""))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_USER,
+                                        kwargs.get("name", ""))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
+                                        kwargs.get("temperature", 1))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_PRESENCE_PENALTY,
+                                        kwargs.get("presence_penalty", 0))
+                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_FREQUENCY_PENALTY,
+                                        kwargs.get("frequency_penalty", 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.set_attribute(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", "llama3-8b-8192"),
+                                                    pricing_info, response.usage.prompt_tokens,
+                                                    response.usage.completion_tokens)
+
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            response.usage.prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            response.usage.completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            response.usage.total_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
+                                            response.choices[0].finish_reason)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                            cost)
+
+                        # Set span attributes for when n = 1 (default)
+                        if "n" not in kwargs or kwargs["n"] == 1:
+                            if trace_content:
+                                span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                                    response.choices[0].message.content)
+
+                        # Set span attributes for when n > 0
+                        else:
+                            i = 0
+                            while i < kwargs["n"] and trace_content is True:
+                                attribute_name = f"gen_ai.content.completion.{i}"
+                                span.set_attribute(attribute_name,
+                                                    response.choices[i].message.content)
+                                i += 1
+
+                            # Return original response
+                            return response
+
+                    # Set span attributes when tools is passed to the function call
+                    elif "tools" in kwargs:
+                        # Calculate cost of the operation
+                        cost = get_chat_model_cost(kwargs.get("model", "gpt-3.5-turbo"),
+                                                    pricing_info, response.usage.prompt_tokens,
+                                                    response.usage.completion_tokens)
+
+                        span.set_attribute(SemanticConvetion.GEN_AI_CONTENT_COMPLETION,
+                                            "Function called with tools")
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
+                                            response.usage.prompt_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
+                                            response.usage.completion_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
+                                            response.usage.total_tokens)
+                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
+                                            cost)
+
+                    span.set_status(Status(StatusCode.OK))
+
+                    if disable_metrics is False:
+                        attributes = {
+                            TELEMETRY_SDK_NAME:
+                                "openlit",
+                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
+                                application_name,
+                            SemanticConvetion.GEN_AI_SYSTEM:
+                                SemanticConvetion.GEN_AI_SYSTEM_GROQ,
+                            SemanticConvetion.GEN_AI_ENVIRONMENT:
+                                environment,
+                            SemanticConvetion.GEN_AI_TYPE:
+                                SemanticConvetion.GEN_AI_TYPE_CHAT,
+                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
+                                kwargs.get("model", "gpt-3.5-turbo")
+                        }
+
+                        metrics["genai_requests"].add(1, attributes)
+                        metrics["genai_total_tokens"].add(response.usage.total_tokens, attributes)
+                        metrics["genai_completion_tokens"].add(response.usage.completion_tokens, attributes)
+                        metrics["genai_prompt_tokens"].add(response.usage.prompt_tokens, attributes)
+                        metrics["genai_cost"].record(cost, attributes)
+
+                    # Return original response
+                    return response
+
+                except Exception as e:
+                    handle_exception(span, e)
+                    logger.error("Error in trace creation: %s", e)
+
+                    # Return original response
+                    return response
+
+    return wrapper

{openlit-1.3.0 → openlit-1.4.0}/src/openlit/otel/tracing.py

@@ -40,6 +40,9 @@ def setup_tracing(application_name, environment, tracer, otlp_endpoint, otlp_hea
     global TRACER_SET
 
     try:
+        #Disable Haystack Auto Tracing
+        os.environ["HAYSTACK_AUTO_TRACE_ENABLED"] = "false"
+
         if not TRACER_SET:
             # Create a resource with the service name attribute.
             resource = Resource(attributes={

{openlit-1.3.0 → openlit-1.4.0}/src/openlit/semcov/__init__.py

@@ -87,6 +87,7 @@ class SemanticConvetion:
     GEN_AI_SYSTEM_MISTRAL = "mistral"
     GEN_AI_SYSTEM_BEDROCK = "bedrock"
     GEN_AI_SYSTEM_VERTEXAI = "vertexai"
+    GEN_AI_SYSTEM_GROQ = "groq"
     GEN_AI_SYSTEM_LANGCHAIN = "langchain"
     GEN_AI_SYSTEM_LLAMAINDEX = "llama_index"
     GEN_AI_SYSTEM_HAYSTACK = "haystack"