openlit 1.33.10__py3-none-any.whl → 1.33.12__py3-none-any.whl

openlit/instrumentation/anthropic/anthropic.py

@@ -4,54 +4,37 @@ Module for monitoring Anthropic 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 (
-    get_chat_model_cost,
     handle_exception,
-    response_as_dict,
-    calculate_ttft,
-    calculate_tbt,
-    create_metrics_attributes,
     set_server_address_and_port
 )
+from openlit.instrumentation.anthropic.utils import (
+    process_chunk,
+    process_chat_response,
+    process_streaming_chat_response,
+)
 from openlit.semcov import SemanticConvetion
 
 # Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
 
-def messages(version, environment, application_name, tracer,
-             pricing_info, trace_content, metrics, disable_metrics):
+def messages(version, environment, application_name, tracer, event_provider,
+             pricing_info, capture_message_content, metrics, disable_metrics):
     """
-    Generates a telemetry wrapper for messages 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 Anthropic API.
-        tracer: OpenTelemetry tracer for creating spans.
-        pricing_info: Information used for calculating the cost of Anthropic usage.
-        trace_content: Flag indicating whether to trace the actual content.
-
-    Returns:
-        A function that wraps the chat 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,
                 kwargs,
                 server_address,
                 server_port,
@@ -59,13 +42,18 @@ def messages(version, environment, application_name, tracer,
             ):
             self.__wrapped__ = wrapped
             self._span = span
-            # Placeholder for aggregating streaming response
-            self._llmresponse = ""
-            self._response_id = ""
-            self._response_model = ""
-            self._finish_reason = ""
-            self._input_tokens = ""
-            self._output_tokens = ""
+            self._span_name = span_name
+            self._llmresponse = ''
+            self._response_id = ''
+            self._response_model = ''
+            self._finish_reason = ''
+            self._input_tokens = ''
+            self._output_tokens = ''
+            self._tool_arguments = ''
+            self._tool_id = ''
+            self._tool_name = ''
+            self._tool_calls = None
+            self._response_role = ''
 
             self._args = args
             self._kwargs = kwargs
@@ -94,348 +82,68 @@ def messages(version, environment, application_name, tracer,
         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)
-
-                chunked = response_as_dict(chunk)
-
-                # Collect message IDs and input token from events
-                if chunked.get('type') == "message_start":
-                    self._response_id = chunked.get('message').get('id')
-                    self._input_tokens = chunked.get('message').get('usage').get('input_tokens')
-                    self._response_model = chunked.get('message').get('model')
-                # Collect message IDs and aggregated response from events
-                if chunked.get('type') == "content_block_delta":
-                    content = chunked.get('delta').get('text')
-                    if content:
-                        self._llmresponse += content
-                # Collect output tokens and stop reason from events
-                if chunked.get('type') == "message_delta":
-                    self._output_tokens = chunked.get('usage').get('output_tokens')
-                    self._finish_reason = chunked.get('delta').get('stop_reason')
-
+                process_chunk(self, chunk)
                 return chunk
             except StopIteration:
-                # Handling exception ensure observability without disrupting operation
                 try:
-                    self._end_time = time.time()
-                    if len(self._timestamps) > 1:
-                        self._tbt = calculate_tbt(self._timestamps)
-
-                    # Format 'messages' into a single string
-                    message_prompt = self._kwargs.get("messages", "")
-                    formatted_messages = []
-                    for message in message_prompt:
-                        role = message["role"]
-                        content = message["content"]
-
-                        if isinstance(content, list):
-                            content_str_list = []
-                            for item in content:
-                                if item["type"] == "text":
-                                    content_str_list.append(f'text: {item["text"]}')
-                                elif (item["type"] == "image_url" and
-                                      not item["image_url"]["url"].startswith("data:")):
-                                    content_str_list.append(f'image_url: {item["image_url"]["url"]}')
-                            content_str = ", ".join(content_str_list)
-                            formatted_messages.append(f"{role}: {content_str}")
-                        else:
-                            formatted_messages.append(f"{role}: {content}")
-                    prompt = "\n".join(formatted_messages)
-
-                    request_model = self._kwargs.get("model", "claude-3-5-sonnet-latest")
-
-                    # Calculate cost of the operation
-                    cost = get_chat_model_cost(request_model,
-                                                pricing_info, self._input_tokens,
-                                                self._output_tokens)
-
-                    # Set Span attributes (OTel Semconv)
-                    self._span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                        SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                        request_model)
-                    self._span.set_attribute(SemanticConvetion.SERVER_PORT,
-                                        self._server_port)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        self._kwargs.get("max_tokens", -1))
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_STOP_SEQUENCES,
-                                        self._kwargs.get("stop_sequences", []))
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        self._kwargs.get("temperature", 1.0))
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
-                                        self._kwargs.get("top_k", 1.0))
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        self._kwargs.get("top_p", 1.0))
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        [self._finish_reason])
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                        self._response_id)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
-                                        self._response_model)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                        self._input_tokens)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                        self._output_tokens)
-                    self._span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
-                                        self._server_address)
-                    if isinstance(self._llmresponse, str):
-                        self._span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
-                                        "text")
-                    else:
-                        self._span.set_attribute(SemanticConvetion.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(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                        True)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                        self._input_tokens + self._output_tokens)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                        cost)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TBT,
-                                        self._tbt)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
-                                        self._ttft)
-                    self._span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
-                                        version)
-                    if trace_content:
-                        self._span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
-                            },
-                        )
-                        self._span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: self._llmresponse,
-                            },
+                    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,
+                            event_provider=event_provider,
+                            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=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                            system=SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC,
-                            request_model=request_model,
-                            server_address=self._server_address,
-                            server_port=self._server_port,
-                            response_model=self._response_model,
-                        )
-
-                        metrics["genai_client_usage_tokens"].record(
-                            self._input_tokens + self._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(self._output_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(self._input_tokens, attributes)
-                        metrics["genai_cost"].record(cost, 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 'messages' 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 'messages' method to be wrapped.
-            instance: The instance of the class where the original method is defined.
-            args: Positional arguments for the 'messages' method.
-            kwargs: Keyword arguments for the 'messages' method.
-
-        Returns:
-            The response from the original 'messages' method.
+        Wraps the GenAI function call.
         """
 
-        # Check if streaming is enabled for the API call
-        streaming = kwargs.get("stream", False)
-        server_address, server_port = set_server_address_and_port(instance, "api.anthropic.com", 443)
-        request_model = kwargs.get("model", "claude-3-5-sonnet-latest")
+        streaming = kwargs.get('stream', False)
+        server_address, server_port = set_server_address_and_port(instance, 'api.anthropic.com', 443)
+        request_model = kwargs.get('model', 'claude-3-5-sonnet-latest')
 
-        span_name = f"{SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+        span_name = f'{SemanticConvetion.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)
+            return TracedSyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
 
-        # Handling for non-streaming responses
         else:
             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()
-
-                response_dict = response_as_dict(response)
-                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(
-                                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)
-
-                    input_tokens = response_dict.get('usage').get('input_tokens')
-                    output_tokens = response_dict.get('usage').get('output_tokens')
-
-                    # Calculate cost of the operation
-                    cost = get_chat_model_cost(request_model,
-                                                pricing_info, input_tokens,
-                                                output_tokens)
-
-                    llm_response = ""
-                    for i in range(len(response_dict.get('content'))):
-                        if response_dict.get('content')[i].get('type') == 'text':
-                            llm_response = response_dict.get('content')[i].get('text')
-
-                    # Set Span attributes (OTel Semconv)
-                    span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                    span.set_attribute(SemanticConvetion.GEN_AI_OPERATION,
-                                        SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT)
-                    span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                        SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                        request_model)
-                    span.set_attribute(SemanticConvetion.SERVER_PORT,
-                                        server_port)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                        kwargs.get("max_tokens", -1))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_STOP_SEQUENCES,
-                                        kwargs.get("stop_sequences", []))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                        kwargs.get("temperature", 1.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
-                                        kwargs.get("top_k", 1.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                        kwargs.get("top_p", 1.0))
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                        [response_dict.get('stop_reason')])
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                        response_dict.get('id'))
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_MODEL,
-                                        response_dict.get('model'))
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_INPUT_TOKENS,
-                                        input_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_OUTPUT_TOKENS,
-                                        output_tokens)
-                    span.set_attribute(SemanticConvetion.SERVER_ADDRESS,
-                                        server_address)
-
-                    span.set_attribute(SemanticConvetion.GEN_AI_OUTPUT_TYPE,
-                                        response_dict.get('content')[0].get('type'))
-
-                    # Set Span attributes (Extra)
-                    span.set_attribute(DEPLOYMENT_ENVIRONMENT,
-                                        environment)
-                    span.set_attribute(SERVICE_NAME,
-                                        application_name)
-                    span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                        False)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                        input_tokens + output_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                        cost)
-                    span.set_attribute(SemanticConvetion.GEN_AI_SERVER_TTFT,
-                                        end_time - start_time)
-                    span.set_attribute(SemanticConvetion.GEN_AI_SDK_VERSION,
-                                        version)
-
-                    if trace_content:
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_PROMPT_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_PROMPT: prompt,
-                            },
-                        )
-                        span.add_event(
-                            name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
-                            attributes={
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llm_response,
-                            },
-                        )
-
-                    span.set_status(Status(StatusCode.OK))
-
-                    if disable_metrics is False:
-                        attributes = create_metrics_attributes(
-                            service_name=application_name,
-                            deployment_environment=environment,
-                            operation=SemanticConvetion.GEN_AI_OPERATION_TYPE_CHAT,
-                            system=SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC,
-                            request_model=request_model,
-                            server_address=server_address,
-                            server_port=server_port,
-                            response_model=response_dict.get('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(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
+                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
 
     return wrapper