openlit 1.34.3__tar.gz → 1.34.4__tar.gz

{openlit-1.34.3 → openlit-1.34.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.34.3
+Version: 1.34.4
 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-1.34.3 → openlit-1.34.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.34.3"
+version = "1.34.4"
 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-1.34.4/src/openlit/instrumentation/ai21/__init__.py

@@ -0,0 +1,66 @@
+# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
+"""Initializer of Auto Instrumentation of AI21 Functions"""
+
+from typing import Collection
+import importlib.metadata
+from opentelemetry.instrumentation.instrumentor import BaseInstrumentor
+from wrapt import wrap_function_wrapper
+
+from openlit.instrumentation.ai21.ai21 import (
+    chat, chat_rag
+)
+from openlit.instrumentation.ai21.async_ai21 import (
+    async_chat, async_chat_rag
+)
+
+_instruments = ("ai21 >= 3.0.0",)
+
+class AI21Instrumentor(BaseInstrumentor):
+    """
+    An instrumentor for AI21 client library.
+    """
+
+    def instrumentation_dependencies(self) -> Collection[str]:
+        return _instruments
+
+    def _instrument(self, **kwargs):
+        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", False)
+        disable_metrics = kwargs.get("disable_metrics")
+        version = importlib.metadata.version("ai21")
+
+        #sync
+        wrap_function_wrapper(
+            "ai21.clients.studio.resources.chat.chat_completions",
+            "ChatCompletions.create",
+            chat(version, environment, application_name,
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+        )
+        wrap_function_wrapper(
+            "ai21.clients.studio.resources.studio_conversational_rag",
+            "StudioConversationalRag.create",
+            chat_rag(version, environment, application_name,
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+        )
+
+        #Async
+        wrap_function_wrapper(
+            "ai21.clients.studio.resources.chat.async_chat_completions",
+            "AsyncChatCompletions.create",
+            async_chat(version, environment, application_name,
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+        )
+        wrap_function_wrapper(
+            "ai21.clients.studio.resources.studio_conversational_rag",
+            "AsyncStudioConversationalRag.create",
+            async_chat_rag(version, environment, application_name,
+                  tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+        )
+
+    def _uninstrument(self, **kwargs):
+        # Proper uninstrumentation logic to revert patched methods
+        pass

{openlit-1.34.3 → openlit-1.34.4}/src/openlit/instrumentation/ai21/ai21.py

@@ -22,7 +22,7 @@ from openlit.semcov import SemanticConvention
 logger = logging.getLogger(__name__)
 
 def chat(version, environment, application_name,
-                     tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
+                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -46,9 +46,9 @@ def chat(version, environment, application_name,
             self._span = span
             self._span_name = span_name
             # Placeholder for aggregating streaming response
-            self._llmresponse = ''
-            self._response_id = ''
-            self._finish_reason = ''
+            self._llmresponse = ""
+            self._response_id = ""
+            self._finish_reason = ""
             self._input_tokens = 0
             self._output_tokens = 0
             self._choices = []
@@ -92,14 +92,13 @@ def chat(version, environment, application_name,
                             environment=environment,
                             application_name=application_name,
                             metrics=metrics,
-                            event_provider=event_provider,
                             capture_message_content=capture_message_content,
                             disable_metrics=disable_metrics,
                             version=version
                         )
                 except Exception as e:
                     handle_exception(self._span, e)
-                    logger.error('Error in trace creation: %s', e)
+                    logger.error("Error in trace creation: %s", e)
                 raise
 
     def wrapper(wrapped, instance, args, kwargs):
@@ -108,12 +107,12 @@ def chat(version, environment, application_name,
         """
 
         # Check if streaming is enabled for the API call
-        streaming = kwargs.get('stream', False)
+        streaming = kwargs.get("stream", False)
 
-        server_address, server_port = set_server_address_and_port(instance, 'api.ai21.com', 443)
-        request_model = kwargs.get('model', 'jamba-1.5-mini')
+        server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
+        request_model = kwargs.get("model", "jamba-1.5-mini")
 
-        span_name = f'{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}'
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
         # pylint: disable=no-else-return
         if streaming:
@@ -127,30 +126,34 @@ def chat(version, environment, application_name,
             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,
-                    event_provider=event_provider,
-                    start_time=start_time,
-                    span=span,
-                    capture_message_content=capture_message_content,
-                    disable_metrics=disable_metrics,
-                    version=version,
-                    **kwargs
-                )
 
-            return response
+                try:
+                    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
+                    )
+
+                except Exception as e:
+                    handle_exception(span, e)
+
+                return response
 
     return wrapper
 
 def chat_rag(version, environment, application_name,
-                tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
+                tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -160,32 +163,36 @@ def chat_rag(version, environment, application_name,
         Wraps the GenAI function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, 'api.ai21.com', 443)
-        request_model = kwargs.get('model', 'jamba-1.5-mini')
+        server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
+        request_model = kwargs.get("model", "jamba-1.5-mini")
 
-        span_name = f'{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}'
+        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_rag_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,
-                event_provider=event_provider,
-                start_time=start_time,
-                span=span,
-                capture_message_content=capture_message_content,
-                disable_metrics=disable_metrics,
-                version=version,
-                **kwargs
-            )
-
-        return response
+
+            try:
+                response = process_chat_rag_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-1.34.3 → openlit-1.34.4}/src/openlit/instrumentation/ai21/async_ai21.py

@@ -22,7 +22,7 @@ from openlit.semcov import SemanticConvention
 logger = logging.getLogger(__name__)
 
 def async_chat(version, environment, application_name,
-                     tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
+                     tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -46,9 +46,9 @@ def async_chat(version, environment, application_name,
             self._span = span
             self._span_name = span_name
             # Placeholder for aggregating streaming response
-            self._llmresponse = ''
-            self._response_id = ''
-            self._finish_reason = ''
+            self._llmresponse = ""
+            self._response_id = ""
+            self._finish_reason = ""
             self._input_tokens = 0
             self._output_tokens = 0
             self._choices = []
@@ -92,14 +92,13 @@ def async_chat(version, environment, application_name,
                             environment=environment,
                             application_name=application_name,
                             metrics=metrics,
-                            event_provider=event_provider,
                             capture_message_content=capture_message_content,
                             disable_metrics=disable_metrics,
                             version=version
                         )
                 except Exception as e:
                     handle_exception(self._span, e)
-                    logger.error('Error in trace creation: %s', e)
+
                 raise
 
     async def wrapper(wrapped, instance, args, kwargs):
@@ -108,12 +107,12 @@ def async_chat(version, environment, application_name,
         """
 
         # Check if streaming is enabled for the API call
-        streaming = kwargs.get('stream', False)
+        streaming = kwargs.get("stream", False)
 
-        server_address, server_port = set_server_address_and_port(instance, 'api.ai21.com', 443)
-        request_model = kwargs.get('model', 'jamba-1.5-mini')
+        server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
+        request_model = kwargs.get("model", "jamba-1.5-mini")
 
-        span_name = f'{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}'
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 
         # pylint: disable=no-else-return
         if streaming:
@@ -127,30 +126,34 @@ def async_chat(version, environment, application_name,
             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,
-                    event_provider=event_provider,
-                    start_time=start_time,
-                    span=span,
-                    capture_message_content=capture_message_content,
-                    disable_metrics=disable_metrics,
-                    version=version,
-                    **kwargs
-                )
 
-            return response
+                try:
+                    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
+                    )
+
+                except Exception as e:
+                    handle_exception(span, e)
+
+                return response
 
     return wrapper
 
 def async_chat_rag(version, environment, application_name,
-                tracer, event_provider, pricing_info, capture_message_content, metrics, disable_metrics):
+                tracer, pricing_info, capture_message_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for GenAI function call
     """
@@ -160,32 +163,36 @@ def async_chat_rag(version, environment, application_name,
         Wraps the GenAI function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, 'api.ai21.com', 443)
-        request_model = kwargs.get('model', 'jamba-1.5-mini')
+        server_address, server_port = set_server_address_and_port(instance, "api.ai21.com", 443)
+        request_model = kwargs.get("model", "jamba-1.5-mini")
 
-        span_name = f'{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}'
+        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_rag_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,
-                event_provider=event_provider,
-                start_time=start_time,
-                span=span,
-                capture_message_content=capture_message_content,
-                disable_metrics=disable_metrics,
-                version=version,
-                **kwargs
-            )
-
-        return response
+
+            try:
+                response = process_chat_rag_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