openlit 1.34.17__tar.gz → 1.34.18__tar.gz

{openlit-1.34.17 → openlit-1.34.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.34.17
+Version: 1.34.18
 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-1.34.17 → openlit-1.34.18}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.34.17"
+version = "1.34.18"
 description = "OpenTelemetry-native Auto instrumentation library for monitoring LLM Applications and GPUs, facilitating the integration of observability into your GenAI-driven projects"
 authors = ["OpenLIT"]
 license = "Apache-2.0"

{openlit-1.34.17 → openlit-1.34.18}/src/openlit/instrumentation/cohere/__init__.py

@@ -1,74 +1,88 @@
-# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
 """Initializer of Auto Instrumentation of Cohere Functions"""
+
 from typing import Collection
 import importlib.metadata
 from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
 from wrapt import wrap_function_wrapper
 
-from openlit.instrumentation.cohere.cohere import chat, chat_stream, embed
-from openlit.instrumentation.cohere.async_cohere import async_chat, async_chat_stream, async_embed
-
+from openlit.instrumentation.cohere.cohere import (
+    chat,
+    chat_stream,
+    embed
+)
+from openlit.instrumentation.cohere.async_cohere import (
+    async_chat,
+    async_chat_stream,
+    async_embed
+)
 
 _instruments = ("cohere >= 5.14.0",)
 
 class CohereInstrumentor(BaseInstrumentor):
-    """An instrumentor for Cohere's client library."""
+    """
+    An instrumentor for Cohere client library.
+    """
 
     def instrumentation_dependencies(self) -> Collection[str]:
         return _instruments
 
     def _instrument(self, **kwargs):
-        application_name = kwargs.get("application_name")
-        environment = kwargs.get("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")
-        capture_message_content = kwargs.get("capture_message_content")
+        pricing_info = kwargs.get("pricing_info", {})
+        capture_message_content = kwargs.get("capture_message_content", False)
         disable_metrics = kwargs.get("disable_metrics")
         version = importlib.metadata.version("cohere")
 
-        # Sync Client
+        # sync chat completions
         wrap_function_wrapper(
-            "cohere.client_v2",  
-            "ClientV2.chat",  
+            "cohere.client_v2",
+            "ClientV2.chat",
             chat(version, environment, application_name,
-                 tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
+
+        # sync chat streaming
         wrap_function_wrapper(
-            "cohere.client_v2",  
-            "ClientV2.chat_stream",  
+            "cohere.client_v2",
+            "ClientV2.chat_stream",
             chat_stream(version, environment, application_name,
-                        tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
+
+        # sync embeddings
         wrap_function_wrapper(
-            "cohere.client_v2",  
-            "ClientV2.embed",  
+            "cohere.client_v2",
+            "ClientV2.embed",
             embed(version, environment, application_name,
                   tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
-        # Async Client
+        # async chat completions
         wrap_function_wrapper(
-            "cohere.client_v2",  
-            "AsyncClientV2.chat",  
+            "cohere.client_v2",
+            "AsyncClientV2.chat",
             async_chat(version, environment, application_name,
-                 tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
+        # async chat streaming
         wrap_function_wrapper(
-            "cohere.client_v2",  
-            "AsyncClientV2.chat_stream",  
+            "cohere.client_v2",
+            "AsyncClientV2.chat_stream",
             async_chat_stream(version, environment, application_name,
-                        tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
+        # async embeddings
         wrap_function_wrapper(
-            "cohere.client_v2",  
-            "AsyncClientV2.embed",  
+            "cohere.client_v2",
+            "AsyncClientV2.embed",
             async_embed(version, environment, application_name,
                   tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
-    @staticmethod
     def _uninstrument(self, **kwargs):
         pass

openlit-1.34.18/src/openlit/instrumentation/cohere/async_cohere.py

@@ -0,0 +1,201 @@
+"""
+Module for monitoring Cohere API calls (async version).
+"""
+
+import time
+from opentelemetry.trace import SpanKind
+from openlit.__helpers import (
+    handle_exception,
+    set_server_address_and_port,
+)
+from openlit.instrumentation.cohere.utils import (
+    process_chunk,
+    process_chat_response,
+    process_streaming_chat_response,
+    process_embedding_response,
+)
+from openlit.semcov import SemanticConvention
+
+def async_chat(version, environment, application_name,
+              tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for GenAI chat function call
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the GenAI chat function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = kwargs.get("model", "command-r-plus-08-2024")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+            start_time = time.time()
+            response = await wrapped(*args, **kwargs)
+            response = process_chat_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
+            )
+
+        return response
+
+    return wrapper
+
+def async_chat_stream(version, environment, application_name,
+                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for GenAI chat_stream function call
+    """
+
+    class TracedAsyncStream:
+        """
+        Wrapper for async streaming responses to collect telemetry.
+        """
+
+        def __init__(
+                self,
+                wrapped,
+                span,
+                span_name,
+                kwargs,
+                server_address,
+                server_port,
+                **args,
+            ):
+            self.__wrapped__ = wrapped
+            self._span = span
+            self._span_name = span_name
+            self._llmresponse = ""
+            self._response_id = ""
+            self._response_model = ""
+            self._finish_reason = ""
+            self._tools = None
+            self._tool_plan = ""
+            self._input_tokens = 0
+            self._output_tokens = 0
+
+            self._args = args
+            self._kwargs = kwargs
+            self._start_time = time.time()
+            self._end_time = None
+            self._timestamps = []
+            self._ttft = 0
+            self._tbt = 0
+            self._server_address = server_address
+            self._server_port = server_port
+
+        async def __aenter__(self):
+            await self.__wrapped__.__aenter__()
+            return self
+
+        async def __aexit__(self, exc_type, exc_value, traceback):
+            await self.__wrapped__.__aexit__(exc_type, exc_value, traceback)
+
+        def __aiter__(self):
+            return self
+
+        async def __getattr__(self, name):
+            """Delegate attribute access to the wrapped object."""
+            return getattr(await self.__wrapped__, name)
+
+        async def __anext__(self):
+            try:
+                chunk = await self.__wrapped__.__anext__()
+                process_chunk(self, chunk)
+                return chunk
+            except StopAsyncIteration:
+                try:
+                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                        process_streaming_chat_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
+                        )
+
+                except Exception as e:
+                    handle_exception(self._span, e)
+
+                raise
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the GenAI chat_stream function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = kwargs.get("model", "command-r-plus-08-2024")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        # Stream endpoint is always streaming
+        awaited_wrapped = await wrapped(*args, **kwargs)
+        span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
+
+        return TracedAsyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
+
+    return wrapper
+
+def async_embed(version, environment, application_name,
+               tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for GenAI embedding function call
+    """
+
+    async def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the GenAI embedding function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = kwargs.get("model", "embed-english-v3.0")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+            start_time = time.time()
+            response = await wrapped(*args, **kwargs)
+
+            try:
+                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)
+
+            return response
+
+    return wrapper

openlit-1.34.18/src/openlit/instrumentation/cohere/cohere.py

@@ -0,0 +1,201 @@
+"""
+Module for monitoring Cohere API calls.
+"""
+
+import time
+from opentelemetry.trace import SpanKind
+from openlit.__helpers import (
+    handle_exception,
+    set_server_address_and_port,
+)
+from openlit.instrumentation.cohere.utils import (
+    process_chunk,
+    process_chat_response,
+    process_streaming_chat_response,
+    process_embedding_response,
+)
+from openlit.semcov import SemanticConvention
+
+def chat(version, environment, application_name,
+    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for GenAI chat function call
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the GenAI chat function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = kwargs.get("model", "command-r-plus-08-2024")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+            start_time = time.time()
+            response = wrapped(*args, **kwargs)
+            response = process_chat_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
+            )
+
+        return response
+
+    return wrapper
+
+def chat_stream(version, environment, application_name,
+    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for GenAI chat_stream function call
+    """
+
+    class TracedSyncStream:
+        """
+        Wrapper for streaming responses to collect telemetry.
+        """
+
+        def __init__(
+                self,
+                wrapped,
+                span,
+                span_name,
+                kwargs,
+                server_address,
+                server_port,
+                **args,
+            ):
+            self.__wrapped__ = wrapped
+            self._span = span
+            self._span_name = span_name
+            self._llmresponse = ""
+            self._response_id = ""
+            self._response_model = ""
+            self._finish_reason = ""
+            self._tools = None
+            self._tool_plan = ""
+            self._input_tokens = 0
+            self._output_tokens = 0
+
+            self._args = args
+            self._kwargs = kwargs
+            self._start_time = time.time()
+            self._end_time = None
+            self._timestamps = []
+            self._ttft = 0
+            self._tbt = 0
+            self._server_address = server_address
+            self._server_port = server_port
+
+        def __enter__(self):
+            self.__wrapped__.__enter__()
+            return self
+
+        def __exit__(self, exc_type, exc_value, traceback):
+            self.__wrapped__.__exit__(exc_type, exc_value, traceback)
+
+        def __iter__(self):
+            return self
+
+        def __getattr__(self, name):
+            """Delegate attribute access to the wrapped object."""
+            return getattr(self.__wrapped__, name)
+
+        def __next__(self):
+            try:
+                chunk = self.__wrapped__.__next__()
+                process_chunk(self, chunk)
+                return chunk
+            except StopIteration:
+                try:
+                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                        process_streaming_chat_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
+                        )
+
+                except Exception as e:
+                    handle_exception(self._span, e)
+
+                raise
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the GenAI chat_stream function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = kwargs.get("model", "command-r-plus-08-2024")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        # Stream endpoint is always streaming
+        awaited_wrapped = wrapped(*args, **kwargs)
+        span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
+
+        return TracedSyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
+
+    return wrapper
+
+def embed(version, environment, application_name,
+    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+    """
+    Generates a telemetry wrapper for GenAI embedding function call
+    """
+
+    def wrapper(wrapped, instance, args, kwargs):
+        """
+        Wraps the GenAI embedding function call.
+        """
+
+        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        request_model = kwargs.get("model", "embed-english-v3.0")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+
+        with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+            start_time = time.time()
+            response = wrapped(*args, **kwargs)
+
+            try:
+                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)
+
+            return response
+
+    return wrapper