openlit 1.33.8__py3-none-any.whl → 1.33.9__py3-none-any.whl

openlit/instrumentation/anthropic/async_anthropic.py

@@ -1,35 +1,267 @@
-# pylint: disable=duplicate-code, broad-exception-caught, too-many-statements, unused-argument, possibly-used-before-assignment
 """
 Module for monitoring Anthropic API calls.
 """
 
 import logging
+import time
 from opentelemetry.trace import SpanKind, Status, StatusCode
-from opentelemetry.sdk.resources import TELEMETRY_SDK_NAME
-from openlit.__helpers import get_chat_model_cost, handle_exception
+from opentelemetry.sdk.resources import SERVICE_NAME, TELEMETRY_SDK_NAME, DEPLOYMENT_ENVIRONMENT
+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.semcov import SemanticConvetion
 
 # Initialize logger for logging potential issues and operations
 logger = logging.getLogger(__name__)
 
-def async_messages(gen_ai_endpoint, version, environment, application_name,
-                   tracer, pricing_info, trace_content, metrics, disable_metrics):
+def async_messages(version, environment, application_name, tracer,
+             pricing_info, trace_content, metrics, disable_metrics):
     """
     Generates a telemetry wrapper for messages to collect metrics.
 
     Args:
-        gen_ai_endpoint: Endpoint identifier for logging and tracing.
         version: Version of the monitoring package.
         environment: Deployment environment (e.g., production, staging).
-        application_name: Name of the application using the OpenAI API.
+        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 OpenAI usage.
+        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.
     """
 
+    class TracedASyncStream:
+        """
+        Wrapper for streaming responses to collect metrics and trace data.
+        Wraps the 'anthropic.AsyncStream' 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.
+        """
+        def __init__(
+                self,
+                wrapped,
+                span,
+                kwargs,
+                server_address,
+                server_port,
+                **args,
+            ):
+            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._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__()
+                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')
+
+                return chunk
+            except StopAsyncIteration:
+                # 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,
+                            },
+                        )
+                    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
+
     async def wrapper(wrapped, instance, args, kwargs):
         """
         Wraps the 'messages' API call to add telemetry.
@@ -49,147 +281,27 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
 
         # 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")
+
+        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
-            async def stream_generator():
-                with tracer.start_as_current_span(gen_ai_endpoint, kind= SpanKind.CLIENT) as span:
-                    # Placeholder for aggregating streaming response
-                    llmresponse = ""
-
-                    # Loop through streaming events capturing relevant details
-                    async for event in await wrapped(*args, **kwargs):
-
-                        # Collect message IDs and input token from events
-                        if event.type == "message_start":
-                            response_id = event.message.id
-                            prompt_tokens = event.message.usage.input_tokens
-
-                        # Aggregate response content
-                        if event.type == "content_block_delta":
-                            llmresponse += event.delta.text
-
-                        # Collect output tokens and stop reason from events
-                        if event.type == "message_delta":
-                            completion_tokens = event.usage.output_tokens
-                            finish_reason = event.delta.stop_reason
-                        yield event
-
-                    # Handling exception ensure observability without disrupting operation
-                    try:
-                        # Format 'messages' into a single string
-                        message_prompt = kwargs.get("messages", "")
-                        formatted_messages = []
-                        for message in message_prompt:
-                            role = message["role"]
-                            content = message["content"]
-
-                            if isinstance(content, list):
-                                content_str = ", ".join(
-                                    # pylint: disable=line-too-long
-                                    f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
-                                    if "type" in item else f'text: {item["text"]}'
-                                    for item in content
-                                )
-                                formatted_messages.append(f"{role}: {content_str}")
-                            else:
-                                formatted_messages.append(f"{role}: {content}")
-                        prompt = "\n".join(formatted_messages)
-
-                        # Calculate cost of the operation
-                        cost = get_chat_model_cost(
-                            kwargs.get("model", "claude-3-sonnet-20240229"),
-                            pricing_info, prompt_tokens, completion_tokens
-                        )
+            awaited_wrapped = await wrapped(*args, **kwargs)
+            span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
 
-                        # Set Span attributes
-                        span.set_attribute(TELEMETRY_SDK_NAME, "openlit")
-                        span.set_attribute(SemanticConvetion.GEN_AI_SYSTEM,
-                                            SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC)
-                        span.set_attribute(SemanticConvetion.GEN_AI_TYPE,
-                                            SemanticConvetion.GEN_AI_TYPE_CHAT)
-                        span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                            gen_ai_endpoint)
-                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                            response_id)
-                        span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                            environment)
-                        span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                            application_name)
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                            kwargs.get("model", "claude-3-sonnet-20240229"))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MAX_TOKENS,
-                                            kwargs.get("max_tokens", -1))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_IS_STREAM,
-                                            True)
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TEMPERATURE,
-                                            kwargs.get("temperature", 1.0))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_P,
-                                            kwargs.get("top_p", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
-                                            kwargs.get("top_k", ""))
-                        span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_FINISH_REASON,
-                                            [finish_reason])
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                            prompt_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                            completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_TOTAL_TOKENS,
-                                            prompt_tokens + completion_tokens)
-                        span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COST,
-                                            cost)
-                        if trace_content:
-                            span.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: llmresponse,
-                                },
-                            )
-
-                        span.set_status(Status(StatusCode.OK))
-
-                        if disable_metrics is False:
-                            attributes = {
-                                TELEMETRY_SDK_NAME:
-                                    "openlit",
-                                SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                                    application_name,
-                                SemanticConvetion.GEN_AI_SYSTEM:
-                                    SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC,
-                                SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                    environment,
-                                SemanticConvetion.GEN_AI_TYPE:
-                                    SemanticConvetion.GEN_AI_TYPE_CHAT,
-                                SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                    kwargs.get("model", "claude-3-sonnet-20240229")
-                            }
-
-                            metrics["genai_requests"].add(1, attributes)
-                            metrics["genai_total_tokens"].add(
-                                prompt_tokens + completion_tokens, attributes
-                            )
-                            metrics["genai_completion_tokens"].add(completion_tokens, attributes)
-                            metrics["genai_prompt_tokens"].add(prompt_tokens, attributes)
-                            metrics["genai_cost"].record(cost, attributes)
-
-                    except Exception as e:
-                        handle_exception(span, e)
-                        logger.error("Error in trace creation: %s", e)
-
-            return stream_generator()
+            return TracedASyncStream(awaited_wrapped, span, kwargs, server_address, server_port)
 
         # Handling for non-streaming responses
         else:
-            with tracer.start_as_current_span(gen_ai_endpoint, kind=SpanKind.CLIENT) as span:
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+                start_time = time.time()
                 response = await 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", "")
@@ -200,7 +312,6 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
 
                         if isinstance(content, list):
                             content_str = ", ".join(
-                                # pylint: disable=line-too-long
                                 f'{item["type"]}: {item["text"] if "text" in item else item["image_url"]}'
                                 if "type" in item else f'text: {item["text"]}'
                                 for item in content
@@ -210,48 +321,71 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                             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(kwargs.get("model", "claude-3-sonnet-20240229"),
-                                                pricing_info, response.usage.input_tokens,
-                                                response.usage.output_tokens)
+                    cost = get_chat_model_cost(request_model,
+                                                pricing_info, input_tokens,
+                                                output_tokens)
 
-                    # Set Span attribues
+                    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_TYPE,
-                                        SemanticConvetion.GEN_AI_TYPE_CHAT)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENDPOINT,
-                                        gen_ai_endpoint)
-                    span.set_attribute(SemanticConvetion.GEN_AI_RESPONSE_ID,
-                                        response.id)
-                    span.set_attribute(SemanticConvetion.GEN_AI_ENVIRONMENT,
-                                        environment)
-                    span.set_attribute(SemanticConvetion.GEN_AI_APPLICATION_NAME,
-                                        application_name)
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_MODEL,
-                                        kwargs.get("model", "claude-3-sonnet-20240229"))
+                                        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_IS_STREAM,
-                                        False)
+                    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_P,
-                                        kwargs.get("top_p", ""))
                     span.set_attribute(SemanticConvetion.GEN_AI_REQUEST_TOP_K,
-                                        kwargs.get("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.stop_reason])
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_PROMPT_TOKENS,
-                                        response.usage.input_tokens)
-                    span.set_attribute(SemanticConvetion.GEN_AI_USAGE_COMPLETION_TOKENS,
-                                        response.usage.output_tokens)
+                                        [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,
-                                        response.usage.input_tokens +
-                                        response.usage.output_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,
@@ -262,37 +396,36 @@ def async_messages(gen_ai_endpoint, version, environment, application_name,
                         span.add_event(
                             name=SemanticConvetion.GEN_AI_CONTENT_COMPLETION_EVENT,
                             attributes={
-                                # pylint: disable=line-too-long
-                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: response.content[0].text if response.content else "",
+                                SemanticConvetion.GEN_AI_CONTENT_COMPLETION: llm_response,
                             },
                         )
 
                     span.set_status(Status(StatusCode.OK))
 
                     if disable_metrics is False:
-                        attributes = {
-                            TELEMETRY_SDK_NAME:
-                                "openlit",
-                            SemanticConvetion.GEN_AI_APPLICATION_NAME:
-                                application_name,
-                            SemanticConvetion.GEN_AI_SYSTEM:
-                                SemanticConvetion.GEN_AI_SYSTEM_ANTHROPIC,
-                            SemanticConvetion.GEN_AI_ENVIRONMENT:
-                                environment,
-                            SemanticConvetion.GEN_AI_TYPE:
-                                SemanticConvetion.GEN_AI_TYPE_CHAT,
-                            SemanticConvetion.GEN_AI_REQUEST_MODEL:
-                                kwargs.get("model", "claude-3-sonnet-20240229")
-                        }
+                        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_total_tokens"].add(
-                            response.usage.input_tokens +
-                            response.usage.output_tokens, attributes)
-                        metrics["genai_completion_tokens"].add(
-                            response.usage.output_tokens, attributes)
-                        metrics["genai_prompt_tokens"].add(
-                            response.usage.input_tokens, 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

openlit/instrumentation/assemblyai/__init__.py

@@ -34,7 +34,7 @@ class AssemblyAIInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "assemblyai.transcriber",
             "Transcriber.transcribe",
-            transcribe("assemblyai.transcribe", version, environment, application_name,
+            transcribe(version, environment, application_name,
                   tracer, pricing_info, trace_content, metrics, disable_metrics),
         )