openlit 1.34.7__py3-none-any.whl → 1.34.8__py3-none-any.whl

openlit/instrumentation/gpt4all/__init__.py

@@ -1,4 +1,3 @@
-# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
 """Initializer of Auto Instrumentation of GPT4All Functions"""
 
 from typing import Collection
@@ -14,15 +13,15 @@ _instruments = ("gpt4all >= 2.6.0",)
 
 class GPT4AllInstrumentor(BaseInstrumentor):
     """
-    An instrumentor for GPT4All's client library.
+    An instrumentor for GPT4All 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")
+        application_name = kwargs.get("application_name", "default")
+        environment = kwargs.get("environment", "default")
         tracer = kwargs.get("tracer")
         metrics = kwargs.get("metrics_dict")
         pricing_info = kwargs.get("pricing_info", {})
@@ -46,7 +45,5 @@ class GPT4AllInstrumentor(BaseInstrumentor):
                   tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
-
     def _uninstrument(self, **kwargs):
-        # Proper uninstrumentation logic to revert patched methods
         pass

openlit/instrumentation/gpt4all/gpt4all.py

@@ -2,66 +2,47 @@
 Module for monitoring GPT4All API calls.
 """
 
-import logging
 import time
-from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+from opentelemetry.trace import SpanKind
 from openlit.__helpers import (
     handle_exception,
-    general_tokens,
-    create_metrics_attributes,
-    set_server_address_and_port,
-    calculate_tbt,
-    calculate_ttft
+    set_server_address_and_port
+)
+from openlit.instrumentation.gpt4all.utils import (
+    process_generate_response,
+    process_chunk,
+    process_streaming_generate_response,
+    process_embedding_response
 )
 from openlit.semcov import SemanticConvention
 
-# Initialize logger for logging potential issues and operations
-logger = logging.getLogger(__name__)
-
 def generate(version, environment, application_name,
-                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for chat completions to collect metrics.
-
-    Args:
-        version: Version of the monitoring package.
-        environment: Deployment environment (e.g., production, staging).
-        application_name: Name of the application using the GPT4All API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating GPT4All usage.
-        capture_message_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the chat completions method to add telemetry.
+    Generates a telemetry wrapper for GenAI function call
     """
 
     class TracedSyncStream:
         """
-        Wrapper for streaming responses to collect metrics and trace data.
-        Wraps the response to collect message IDs and aggregated response.
-
-        This class implements the '__aiter__' and '__anext__' methods that
-        handle asynchronous streaming responses.
-
-        This class also implements '__aenter__' and '__aexit__' methods that
-        handle asynchronous context management protocol.
+        Wrapper for streaming responses to collect telemetry.
         """
+
         def __init__(
                 self,
                 wrapped,
                 span,
+                span_name,
+                args,
                 kwargs,
                 server_address,
                 server_port,
                 request_model,
-                **args,
             ):
             self.__wrapped__ = wrapped
             self._span = span
-            # Placeholder for aggregating streaming response
+            self._span_name = span_name
             self._llmresponse = ""
-
+            self._request_model = request_model
             self._args = args
             self._kwargs = kwargs
             self._start_time = time.time()
@@ -71,7 +52,7 @@ def generate(version, environment, application_name,
             self._tbt = 0
             self._server_address = server_address
             self._server_port = server_port
-            self._request_model = request_model
+            self._tools = None
 
         def __enter__(self):
             self.__wrapped__.__enter__()
@@ -90,408 +71,119 @@ def generate(version, environment, application_name,
         def __next__(self):
             try:
                 chunk = self.__wrapped__.__next__()
-                end_time = time.time()
-                # Record the timestamp for the current chunk
-                self._timestamps.append(end_time)
-
-                if len(self._timestamps) == 1:
-                    # Calculate time to first chunk
-                    self._ttft = calculate_ttft(self._timestamps, self._start_time)
-
-                self._llmresponse += chunk
+                process_chunk(self, chunk)
                 return chunk
             except StopIteration:
-                # Handling exception ensure LLM observability without disrupting operation
                 try:
-                    self._end_time = time.time()
-
-                    if len(self._timestamps) > 1:
-                        self._tbt = calculate_tbt(self._timestamps)
-
-                    prompt = self._kwargs.get("prompt") or self._args[0] or ""
-
-                    # Calculate tokens using input prompt and aggregated response
-                    input_tokens = general_tokens(prompt)
-                    output_tokens = general_tokens(self._llmresponse)
-
-                    # Set Span attributes (OTel Semconv)
-                    self._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    self._span.set_attribute(SemanticConvention.GEN_AI_OPERATION,
-                                        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_SYSTEM,
-                                        SemanticConvention.GEN_AI_SYSTEM_GPT4ALL)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL,
-                                        self._request_model)
-                    self._span.set_attribute(SemanticConvention.SERVER_PORT,
-                                        self._server_port)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        self._kwargs.get("repeat_penalty", 1.18))
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS,
-                                        self._kwargs.get("max_tokens", 200))
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        self._kwargs.get("presence_penalty", 0.0))
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE,
-                                        self._kwargs.get("temp", 0.7))
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P,
-                                        self._kwargs.get("top_p", 0.4))
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_K,
-                                        self._kwargs.get("top_k", 40))
-                    self._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL,
-                                        self._request_model)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS,
-                                        input_tokens)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                        output_tokens)
-                    self._span.set_attribute(SemanticConvention.SERVER_ADDRESS,
-                                        self._server_address)
-                    if isinstance(self._llmresponse, str):
-                        self._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE,
-                                        "text")
-                    else:
-                        self._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE,
-                                        "json")
-
-                    # Set Span attributes (Extra)
-                    self._span.set_attribute(DEPLOYMENT_ENVIRONMENT,
-                                        environment)
-                    self._span.set_attribute(SERVICE_NAME,
-                                        application_name)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM,
-                                        True)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_USAGE_TOTAL_TOKENS,
-                                        input_tokens + output_tokens)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT,
-                                        self._tbt)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT,
-                                        self._ttft)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION,
-                                        version)
-                    self._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST,
-                                        0)
-                    if capture_message_content:
-                        self._span.add_event(
-                            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
-                            },
-                        )
-                        self._span.add_event(
-                            name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvention.GEN_AI_CONTENT_COMPLETION: self._llmresponse,
-                            },
+                    with tracer.start_as_current_span(self._span_name, kind=SpanKind.CLIENT) as self._span:
+                        process_streaming_generate_response(
+                            self,
+                            pricing_info=pricing_info,
+                            environment=environment,
+                            application_name=application_name,
+                            metrics=metrics,
+                            capture_message_content=capture_message_content,
+                            disable_metrics=disable_metrics,
+                            version=version
                         )
 
-                    self._span.set_status(Status(StatusCode.OK))
-
-                    if disable_metrics is False:
-                        attributes = create_metrics_attributes(
-                            service_name=application_name,
-                            deployment_environment=environment,
-                            operation=SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,
-                            system=SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
-                            request_model=self._request_model,
-                            server_address=self._server_address,
-                            server_port=self._server_port,
-                            response_model=self._request_model,
-                        )
-
-                        metrics["genai_client_usage_tokens"].record(
-                            input_tokens + output_tokens, attributes
-                        )
-                        metrics["genai_client_operation_duration"].record(
-                            self._end_time - self._start_time, attributes
-                        )
-                        metrics["genai_server_tbt"].record(
-                            self._tbt, attributes
-                        )
-                        metrics["genai_server_ttft"].record(
-                            self._ttft, attributes
-                        )
-                        metrics["genai_requests"].add(1, attributes)
-                        metrics["genai_completion_tokens"].add(output_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(input_tokens, attributes)
-                        metrics["genai_cost"].record(0, 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, 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.
+        Wraps the GenAI function call.
         """
 
         # Check if streaming is enabled for the API call
         streaming = kwargs.get("streaming", False)
 
-        server_address, server_port = set_server_address_and_port(instance, "localhost", 80)
-        request_model = str(instance.model.model_path).rsplit('/', maxsplit=1)[-1] or "orca-mini-3b-gguf2-q4_0.gguf"
+        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 80)
+        request_model = str(instance.model.model_path).rsplit("/", maxsplit=1)[-1] or "orca-mini-3b-gguf2-q4_0.gguf"
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
-        # pylint: disable=no-else-return
         if streaming:
             # Special handling for streaming response to accommodate the nature of data flow
             awaited_wrapped = wrapped(*args, **kwargs)
             span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
-
-            return TracedSyncStream(awaited_wrapped, span, kwargs, server_address, server_port, request_model)
+            return TracedSyncStream(awaited_wrapped, span, span_name, args, kwargs, server_address, server_port, request_model)
 
         # Handling for non-streaming responses
         else:
-            with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
                 start_time = time.time()
                 response = wrapped(*args, **kwargs)
-                end_time = time.time()
 
                 try:
-                    prompt = kwargs.get("prompt") or args[0] or ""
-
-                    # Calculate tokens using input prompt and aggregated response
-                    input_tokens = general_tokens(str(prompt))
-                    output_tokens = general_tokens(str(response))
-
-                    # Set Span attributes (OTel Semconv)
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvention.GEN_AI_OPERATION,
-                                        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT)
-                    span.set_attribute(SemanticConvention.GEN_AI_SYSTEM,
-                                        SemanticConvention.GEN_AI_SYSTEM_GPT4ALL)
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL,
-                                        request_model)
-                    span.set_attribute(SemanticConvention.SERVER_PORT,
-                                        server_port)
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY,
-                                        kwargs.get("repeat_penalty", 1.18))
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", 200))
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY,
-                                        kwargs.get("presence_penalty", 0.0))
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temp", 0.7))
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 0.4))
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_K,
-                                        kwargs.get("top_k", 40))
-                    span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL,
-                                        request_model)
-                    span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS,
-                                        input_tokens)
-                    span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                        output_tokens)
-                    span.set_attribute(SemanticConvention.SERVER_ADDRESS,
-                                        server_address)
-                    if isinstance(response, str):
-                        span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE,
-                                        "text")
-                    else:
-                        span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE,
-                                        "json")
-
-                    # Set Span attributes (Extra)
-                    span.set_attribute(DEPLOYMENT_ENVIRONMENT,
-                                        environment)
-                    span.set_attribute(SERVICE_NAME,
-                                        application_name)
-                    span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM,
-                                        False)
-                    span.set_attribute(SemanticConvention.GEN_AI_USAGE_TOTAL_TOKENS,
-                                        input_tokens + output_tokens)
-                    span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT,
-                                        end_time - start_time)
-                    span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION,
-                                        version)
-                    span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST,
-                                        0)
-                    if capture_message_content:
-                        span.add_event(
-                            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
-                            },
-                        )
-                        span.add_event(
-                            name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvention.GEN_AI_CONTENT_COMPLETION: response,
-                            },
-                        )
-
-                    span.set_status(Status(StatusCode.OK))
-
-                    if disable_metrics is False:
-                        attributes = create_metrics_attributes(
-                            service_name=application_name,
-                            deployment_environment=environment,
-                            operation=SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,
-                            system=SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
-                            request_model=request_model,
-                            server_address=server_address,
-                            server_port=server_port,
-                            response_model=request_model,
-                        )
-
-                        metrics["genai_client_usage_tokens"].record(
-                            input_tokens + output_tokens, attributes
-                        )
-                        metrics["genai_client_operation_duration"].record(
-                            end_time - start_time, attributes
-                        )
-                        metrics["genai_server_ttft"].record(
-                            end_time - start_time, attributes
-                        )
-                        metrics["genai_requests"].add(1, attributes)
-                        metrics["genai_completion_tokens"].add(output_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(input_tokens, attributes)
-                        metrics["genai_cost"].record(0, attributes)
-
-                    # Return original response
-                    return response
+                    response = process_generate_response(
+                        response=response,
+                        request_model=request_model,
+                        pricing_info=pricing_info,
+                        server_port=server_port,
+                        server_address=server_address,
+                        environment=environment,
+                        application_name=application_name,
+                        metrics=metrics,
+                        start_time=start_time,
+                        span=span,
+                        args=args,
+                        kwargs=kwargs,
+                        capture_message_content=capture_message_content,
+                        disable_metrics=disable_metrics,
+                        version=version
+                    )
 
                 except Exception as e:
                     handle_exception(span, e)
-                    logger.error("Error in trace creation: %s", e)
 
-                    # Return original response
-                    return response
+                return response
 
     return wrapper
 
 def embed(version, environment, application_name,
-              tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for embeddings to collect metrics.
-    
-    Args:
-        version: Version of the monitoring package.
-        environment: Deployment environment (e.g., production, staging).
-        application_name: Name of the application using the GPT4All API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating GPT4All usage.
-        capture_message_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the embeddings method to add telemetry.
+    Generates a telemetry wrapper for GenAI function call
     """
 
     def wrapper(wrapped, instance, args, kwargs):
         """
-        Wraps the 'embeddings' API call to add telemetry.
-
-        This collects metrics such as execution time, and token usage, and handles errors
-        gracefully, adding details to the trace for observability.
-
-        Args:
-            wrapped: The original 'embeddings' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'embeddings' method.
-            kwargs: Keyword arguments for the 'embeddings' method.
-
-        Returns:
-            The response from the original 'embeddings' method.
+        Wraps the GenAI function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, "localhost", 80)
-
-        # pylint: disable=line-too-long
-        request_model = str(instance.gpt4all.model.model_path).rsplit('/', maxsplit=1)[-1] or "all-MiniLM-L6-v2.gguf2.f16.gguf"
+        server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 80)
+        request_model = str(instance.gpt4all.model.model_path).rsplit("/", maxsplit=1)[-1] or "all-MiniLM-L6-v2.gguf2.f16.gguf"
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
 
-        with tracer.start_as_current_span(span_name, kind= SpanKind.CLIENT) as span:
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
             start_time = time.time()
             response = wrapped(*args, **kwargs)
-            end_time = time.time()
 
             try:
-                prompt = kwargs.get("prompt") or args[0] or ""
-                input_tokens = general_tokens(prompt)
-
-                # Set Span attributes (OTel Semconv)
-                span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                span.set_attribute(SemanticConvention.GEN_AI_OPERATION,
-                                    SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING)
-                span.set_attribute(SemanticConvention.GEN_AI_SYSTEM,
-                                    SemanticConvention.GEN_AI_SYSTEM_GPT4ALL)
-                span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL,
-                                    request_model)
-                span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL,
-                                    request_model)
-                span.set_attribute(SemanticConvention.SERVER_ADDRESS,
-                                    server_address)
-                span.set_attribute(SemanticConvention.SERVER_PORT,
-                                    server_port)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS,
-                                    input_tokens)
-
-                # Set Span attributes (Extras)
-                span.set_attribute(DEPLOYMENT_ENVIRONMENT,
-                                    environment)
-                span.set_attribute(SERVICE_NAME,
-                                    application_name)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_TOTAL_TOKENS,
-                                    input_tokens)
-                span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION,
-                                    version)
-                span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST,
-                                    0)
-
-                if capture_message_content:
-                    span.add_event(
-                        name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
-                        attributes={
-                            SemanticConvention.GEN_AI_CONTENT_PROMPT: str(kwargs.get("input", "")),
-                        },
-                    )
-
-                span.set_status(Status(StatusCode.OK))
-
-                if disable_metrics is False:
-                    attributes = create_metrics_attributes(
-                        service_name=application_name,
-                        deployment_environment=environment,
-                        operation=SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING,
-                        system=SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
-                        request_model=request_model,
-                        server_address=server_address,
-                        server_port=server_port,
-                        response_model=request_model,
-                    )
-                    metrics["genai_client_usage_tokens"].record(
-                            input_tokens, attributes
-                        )
-                    metrics["genai_client_operation_duration"].record(
-                        end_time - start_time, attributes
-                    )
-                    metrics["genai_requests"].add(1, attributes)
-                    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
-                    metrics["genai_cost"].record(0, attributes)
-
-
-                # Return original response
-                return response
+                response = process_embedding_response(
+                    response=response,
+                    request_model=request_model,
+                    pricing_info=pricing_info,
+                    server_port=server_port,
+                    server_address=server_address,
+                    environment=environment,
+                    application_name=application_name,
+                    metrics=metrics,
+                    start_time=start_time,
+                    span=span,
+                    capture_message_content=capture_message_content,
+                    disable_metrics=disable_metrics,
+                    version=version,
+                    **kwargs
+                )
 
             except Exception as e:
                 handle_exception(span, e)
-                logger.error("Error in trace creation: %s", e)
 
-                # Return original response
-                return response
+            return response
 
     return wrapper

openlit/instrumentation/gpt4all/utils.py

@@ -0,0 +1,281 @@
+"""
+GPT4All OpenTelemetry instrumentation utility functions
+"""
+import time
+
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+from opentelemetry.trace import Status, StatusCode
+
+from openlit.__helpers import (
+    calculate_ttft,
+    calculate_tbt,
+    general_tokens,
+    create_metrics_attributes,
+    get_chat_model_cost,
+    get_embed_model_cost,
+)
+from openlit.semcov import SemanticConvention
+
+def format_content(prompt):
+    """
+    Process a prompt to extract content.
+    """
+    return str(prompt) if prompt else ""
+
+def process_chunk(scope, chunk):
+    """
+    Process a chunk of response data and update state.
+    """
+
+    end_time = time.time()
+    # Record the timestamp for the current chunk
+    scope._timestamps.append(end_time)
+
+    if len(scope._timestamps) == 1:
+        # Calculate time to first chunk
+        scope._ttft = calculate_ttft(scope._timestamps, scope._start_time)
+
+    scope._llmresponse += chunk
+    scope._end_time = time.time()
+
+def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, is_stream, tbt, ttft, version):
+    """
+    Set common span attributes for both generate and embed operations.
+    """
+
+    scope._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OPERATION, gen_ai_operation)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SYSTEM, gen_ai_system)
+    scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, server_address)
+    scope._span.set_attribute(SemanticConvention.SERVER_PORT, server_port)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, response_model)
+    scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
+    scope._span.set_attribute(SERVICE_NAME, application_name)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM, is_stream)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, tbt)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, ttft)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
+
+def record_completion_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, start_time, end_time,
+    input_tokens, output_tokens, cost, tbt=None, ttft=None):
+    """
+    Record completion-specific metrics for the operation.
+    """
+
+    attributes = create_metrics_attributes(
+        operation=gen_ai_operation,
+        system=gen_ai_system,
+        server_address=server_address,
+        server_port=server_port,
+        request_model=request_model,
+        response_model=response_model,
+        service_name=application_name,
+        deployment_environment=environment,
+    )
+    metrics["genai_client_operation_duration"].record(end_time - start_time, attributes)
+    metrics["genai_requests"].add(1, attributes)
+    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+    metrics["genai_completion_tokens"].add(output_tokens, attributes)
+    metrics["genai_client_usage_tokens"].record(input_tokens + output_tokens, attributes)
+    metrics["genai_cost"].record(cost, attributes)
+    if tbt is not None:
+        metrics["genai_server_tbt"].record(tbt, attributes)
+    if ttft is not None:
+        metrics["genai_server_ttft"].record(ttft, attributes)
+
+def record_embedding_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, start_time, end_time,
+    input_tokens, cost):
+    """
+    Record embedding-specific metrics for the operation.
+    """
+
+    attributes = create_metrics_attributes(
+        operation=gen_ai_operation,
+        system=gen_ai_system,
+        server_address=server_address,
+        server_port=server_port,
+        request_model=request_model,
+        response_model=response_model,
+        service_name=application_name,
+        deployment_environment=environment,
+    )
+    metrics["genai_client_usage_tokens"].record(input_tokens, attributes)
+    metrics["genai_client_operation_duration"].record(end_time - start_time, attributes)
+    metrics["genai_requests"].add(1, attributes)
+    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+    metrics["genai_cost"].record(cost, attributes)
+
+def common_generate_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version, is_stream):
+    """
+    Process generate request and generate Telemetry
+    """
+
+    if len(scope._timestamps) > 1:
+        scope._tbt = calculate_tbt(scope._timestamps)
+
+    prompt = format_content(scope._kwargs.get("prompt") or (scope._args[0] if scope._args else "") or "")
+    request_model = scope._request_model
+
+    # Calculate tokens using input prompt and aggregated response
+    input_tokens = general_tokens(prompt)
+    output_tokens = general_tokens(scope._llmresponse)
+
+    cost = get_chat_model_cost(request_model, pricing_info, input_tokens, output_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
+        scope._server_address, scope._server_port, request_model, request_model,
+        environment, application_name, is_stream, scope._tbt, scope._ttft, version)
+
+    # Span Attributes for Request parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY, scope._kwargs.get("repeat_penalty", 1.18))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS, scope._kwargs.get("max_tokens", 200))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY, scope._kwargs.get("presence_penalty", 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, scope._kwargs.get("temp", 0.7))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get("top_p", 0.4))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_K, scope._kwargs.get("top_k", 40))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE, "text" if isinstance(scope._llmresponse, str) else "json")
+
+    # Span Attributes for Cost and Tokens
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, input_tokens + output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Tools
+    if scope._tools:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get("function","")).get("name","")
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get("id","")))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get("function","").get("arguments","")))
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, prompt)
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse)
+
+        # To be removed one the change to span_attributes (from span events) is complete
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
+            },
+        )
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_COMPLETION: scope._llmresponse,
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_completion_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
+            scope._server_address, scope._server_port, request_model, request_model, environment,
+            application_name, scope._start_time, scope._end_time, input_tokens, output_tokens,
+            cost, scope._tbt, scope._ttft)
+
+def common_embedding_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version):
+    """
+    Process embedding request and generate Telemetry
+    """
+
+    prompt = format_content(scope._kwargs.get("text") or "")
+    request_model = scope._request_model
+
+    input_tokens = general_tokens(prompt)
+
+    cost = get_embed_model_cost(request_model, pricing_info, input_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
+        scope._server_address, scope._server_port, request_model, request_model,
+        environment, application_name, False, scope._tbt, scope._ttft, version)
+
+    # Embedding-specific span attributes
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: str(scope._kwargs.get("input", "")),
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_embedding_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_GPT4ALL,
+            scope._server_address, scope._server_port, request_model, request_model, environment,
+            application_name, scope._start_time, scope._end_time, input_tokens, cost)
+
+def process_streaming_generate_response(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content=False, disable_metrics=False, version=""):
+    """
+    Process generate request and generate Telemetry
+    """
+    common_generate_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=True)
+
+def process_generate_response(response, request_model, pricing_info, server_port, server_address,
+    environment, application_name, metrics, start_time, span, args, kwargs, capture_message_content=False,
+    disable_metrics=False, version="1.0.0"):
+    """
+    Process generate request and generate Telemetry
+    """
+
+    scope = type("GenericScope", (), {})()
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._llmresponse = str(response)
+    scope._request_model = request_model
+    scope._timestamps = []
+    scope._ttft, scope._tbt = scope._end_time - scope._start_time, 0
+    scope._server_address, scope._server_port = server_address, server_port
+    scope._kwargs = kwargs
+    scope._args = args
+    scope._tools = None
+
+    common_generate_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=False)
+
+    return response
+
+def process_embedding_response(response, request_model, pricing_info, server_port, server_address,
+    environment, application_name, metrics, start_time, span, capture_message_content=False,
+    disable_metrics=False, version="1.0.0", **kwargs):
+    """
+    Process embedding request and generate Telemetry
+    """
+
+    scope = type("GenericScope", (), {})()
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._request_model = request_model
+    scope._timestamps = []
+    scope._ttft, scope._tbt = scope._end_time - scope._start_time, 0
+    scope._server_address, scope._server_port = server_address, server_port
+    scope._kwargs = kwargs
+
+    common_embedding_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version)
+
+    return response

openlit/instrumentation/premai/__init__.py

@@ -20,8 +20,8 @@ class PremAIInstrumentor(BaseInstrumentor):
         return _instruments
 
     def _instrument(self, **kwargs):
-        application_name = kwargs.get("application_name", "default_application")
-        environment = kwargs.get("environment", "default_environment")
+        application_name = kwargs.get("application_name", "default")
+        environment = kwargs.get("environment", "default")
         tracer = kwargs.get("tracer")
         metrics = kwargs.get("metrics_dict")
         pricing_info = kwargs.get("pricing_info", {})

openlit/instrumentation/premai/utils.py

@@ -64,6 +64,7 @@ def process_chunk(scope, chunk):
         scope._finish_reason = chunked.get("choices")[0].get("finish_reason")
         scope._response_id = chunked.get("id")
         scope._response_model = chunked.get("model")
+        scope._end_time = time.time()
 
 def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_address, server_port,
     request_model, response_model, environment, application_name, is_stream, tbt, ttft, version):
@@ -77,12 +78,12 @@ def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_addres
     scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, server_address)
     scope._span.set_attribute(SemanticConvention.SERVER_PORT, server_port)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, response_model)
     scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
     scope._span.set_attribute(SERVICE_NAME, application_name)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM, is_stream)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, scope._tbt)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, scope._ttft)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, tbt)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, ttft)
     scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
 
 def record_completion_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,

openlit/instrumentation/reka/utils.py

@@ -48,12 +48,12 @@ def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_addres
     scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, server_address)
     scope._span.set_attribute(SemanticConvention.SERVER_PORT, server_port)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, response_model)
     scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
     scope._span.set_attribute(SERVICE_NAME, application_name)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM, is_stream)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, scope._tbt)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, scope._ttft)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, tbt)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, ttft)
     scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
 
 def record_common_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,

openlit/instrumentation/together/utils.py

@@ -80,12 +80,12 @@ def common_span_attributes(scope, gen_ai_operation, gen_ai_system, server_addres
     scope._span.set_attribute(SemanticConvention.SERVER_ADDRESS, server_address)
     scope._span.set_attribute(SemanticConvention.SERVER_PORT, server_port)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MODEL, request_model)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, scope._response_model)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_MODEL, response_model)
     scope._span.set_attribute(DEPLOYMENT_ENVIRONMENT, environment)
     scope._span.set_attribute(SERVICE_NAME, application_name)
     scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_IS_STREAM, is_stream)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, scope._tbt)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, scope._ttft)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TBT, tbt)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_SERVER_TTFT, ttft)
     scope._span.set_attribute(SemanticConvention.GEN_AI_SDK_VERSION, version)
 
 def record_common_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,

{openlit-1.34.7.dist-info → openlit-1.34.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.34.7
+Version: 1.34.8
 Summary: OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects
 License: Apache-2.0
 Keywords: OpenTelemetry,otel,otlp,llm,tracing,openai,anthropic,claude,cohere,llm monitoring,observability,monitoring,gpt,Generative AI,chatGPT,gpu

{openlit-1.34.7.dist-info → openlit-1.34.8.dist-info}/RECORD

@@ -60,8 +60,9 @@ openlit/instrumentation/google_ai_studio/__init__.py,sha256=VLNOlaTFzjOpuUzloynv
 openlit/instrumentation/google_ai_studio/async_google_ai_studio.py,sha256=UL5AdTwkzdTKUomTfETMgYjUl00qL7BB8U0izuXfKFo,5527
 openlit/instrumentation/google_ai_studio/google_ai_studio.py,sha256=nanOoXz-1uJtdh39aD438_yMk0no3AM7VVNKzDganHo,5429
 openlit/instrumentation/google_ai_studio/utils.py,sha256=-X5sHk216ajJrl4cP35f5vT8YAZaIE4yLKI7nWEKHkQ,11140
-openlit/instrumentation/gpt4all/__init__.py,sha256=cO8mi3hhPDXcNwb9AwQ3-wQ_ydnOeBRwb0cptlQmAM4,1805
-openlit/instrumentation/gpt4all/gpt4all.py,sha256=EYp0njZ1kF56rTAjYZVtufA5W4xTWGzSIntjJ4MEfl4,24185
+openlit/instrumentation/gpt4all/__init__.py,sha256=kXciJbQMZYnTeAYLCjriVYXV7XzUUQrwEZPmyv1WXxI,1627
+openlit/instrumentation/gpt4all/gpt4all.py,sha256=6VkJbaPIDv5sbFXFiadH4IB0KljljnOZ1HaGAPuyp_E,6704
+openlit/instrumentation/gpt4all/utils.py,sha256=VQaQAdAFLQp_5IOC8ioC6GUIpJ-iztJWfTSNRmazxag,12485
 openlit/instrumentation/gpu/__init__.py,sha256=QQCFVEbRfdeTjmdFe-UeEiy19vEEWSIBpj2B1wYGhUs,11036
 openlit/instrumentation/groq/__init__.py,sha256=RszPvlPMD1j_uRu9MweyO_F_BRIqEExuB6sVQB2py4o,1901
 openlit/instrumentation/groq/async_groq.py,sha256=BDiGSS1C5uradPLDyfPCqyLWw7f5Emwe4KA1Zd7nXU8,24770
@@ -104,9 +105,9 @@ openlit/instrumentation/phidata/__init__.py,sha256=tqls5-UI6FzbjxYgq_qqAfALhWJm8
 openlit/instrumentation/phidata/phidata.py,sha256=ohrxs6i0Oik75P2BrjNGbK71tdZg94ZMmaXixrXwV5M,4834
 openlit/instrumentation/pinecone/__init__.py,sha256=0guSEPmObaZiOF8yHExpOGY-qW_egHXfZGog3rKGi8M,2596
 openlit/instrumentation/pinecone/pinecone.py,sha256=7hVUlC0HOj0yQyvLasfdb6kS46hRJQdoSRzZQ4ixIkk,8850
-openlit/instrumentation/premai/__init__.py,sha256=S3Q-Pa58jkJ1dKzPqKC8Q_phwFcGR0OuEP29vUmQ7TI,1752
+openlit/instrumentation/premai/__init__.py,sha256=3YlqyV-eNA_4aVUHDVUQUvGJRW8iVVcRtREw91yhbyw,1728
 openlit/instrumentation/premai/premai.py,sha256=rWRqfoIZUbTz-M7zgC2Z92gTVv9fCj1Z4iJcsG86YeI,6438
-openlit/instrumentation/premai/utils.py,sha256=ENZby0YET1U7kgNQeyHUTgK0rKIuhOcwau9R4Bbn-l0,14925
+openlit/instrumentation/premai/utils.py,sha256=v2DWazztCuwDMFW1IaWbWlyPLsBq9_2vTyU8zIle-ns,14942
 openlit/instrumentation/pydantic_ai/__init__.py,sha256=mq52QanFI4xDx6JK-qW5yzhFPXwznJqIYsuxRoBA2Xg,2023
 openlit/instrumentation/pydantic_ai/pydantic_ai.py,sha256=2F2hrowGqcPjTDLG9IeLY8OO-lXZKhLSU93XtZ3tt5A,1868
 openlit/instrumentation/pydantic_ai/utils.py,sha256=b0TqhSDnRqkPdM_qsOgMuXT3lwTvHzMYpaBv2qibiVo,4307
@@ -116,11 +117,11 @@ openlit/instrumentation/qdrant/qdrant.py,sha256=pafjlAzMPzYLRYFfTtWXsLKYVQls-grk
 openlit/instrumentation/reka/__init__.py,sha256=wI5KUYyTAD8ni4E98uziy9WPqoQqlzybDXanFOqDan0,1720
 openlit/instrumentation/reka/async_reka.py,sha256=CZk5rr7njThDkmrauRAJmNtMBgsLarTbQ54raPQb92A,1909
 openlit/instrumentation/reka/reka.py,sha256=wou7vVdN_1Y5UZd4tpkLpTPAtgmAl6gmh_onLn4k4GE,1908
-openlit/instrumentation/reka/utils.py,sha256=_2o4TcVgVhQNkI8_M9FCLMsEx5KCXxNw0wnUpGFTtiY,9232
+openlit/instrumentation/reka/utils.py,sha256=SmwP52XBcDkgLJrozHvNSqJQMSX_vQcmjpidavjNyq0,9211
 openlit/instrumentation/together/__init__.py,sha256=0UmUqQtppyK3oopb4lTjX2LITgVCR8VtH46IAV1rpA8,2484
 openlit/instrumentation/together/async_together.py,sha256=0-h5fKw6rIwN_fvWVpGuvVqizIuM9xFCzz8Z4oGgOj0,6822
 openlit/instrumentation/together/together.py,sha256=nY6mzHmHgoMbbnB_9eL0EBQjP0ltJVdkQj4pbamHAj0,6723
-openlit/instrumentation/together/utils.py,sha256=nIAxxbY5eTSB4yb90NdXwqim0W4ybfipQaerW_cyQEM,14389
+openlit/instrumentation/together/utils.py,sha256=n7r_pM_sqFnJEAkL7OhPydr0Uct0A74vXdcYELdbeW0,14368
 openlit/instrumentation/transformers/__init__.py,sha256=9Ubss5nlumcypxprxff8Fv3sst7II27SsvCzqkBX9Kg,1457
 openlit/instrumentation/transformers/transformers.py,sha256=y--t7PXhUfPC81w-aEE7qowMah3os9gnKBQ5bN4QLGc,1980
 openlit/instrumentation/transformers/utils.py,sha256=3f-ewpUpduaBrTVIFJKaabACjz-6Vf8K7NEU0EzQ4Nk,8042
@@ -134,7 +135,7 @@ openlit/otel/events.py,sha256=VrMjTpvnLtYRBHCiFwJojTQqqNpRCxoD4yJYeQrtPsk,3560
 openlit/otel/metrics.py,sha256=GM2PDloBGRhBTkHHkYaqmOwIAQkY124ZhW4sEqW1Fgk,7086
 openlit/otel/tracing.py,sha256=tjV2bEbEDPUB1Z46gE-UsJsb04sRdFrfbhIDkxViZc0,3103
 openlit/semcov/__init__.py,sha256=ptyo37PY-FHDx_PShEvbdns71cD4YvvXw15bCRXKCKM,13461
-openlit-1.34.7.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-openlit-1.34.7.dist-info/METADATA,sha256=Hhv4r0ePRYKY1nHeIImBPWZ6sN4o_CeT4CySPB8kw6g,23469
-openlit-1.34.7.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
-openlit-1.34.7.dist-info/RECORD,,
+openlit-1.34.8.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+openlit-1.34.8.dist-info/METADATA,sha256=eAza_iFpQukjA6yYb6qqkLQ9aTms9b7jFjx_5r6sz3U,23469
+openlit-1.34.8.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+openlit-1.34.8.dist-info/RECORD,,