openlit 1.34.10__tar.gz → 1.34.11__tar.gz

{openlit-1.34.10 → openlit-1.34.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: openlit
-Version: 1.34.10
+Version: 1.34.11
 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-1.34.10 → openlit-1.34.11}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "openlit"
-version = "1.34.10"
+version = "1.34.11"
 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-1.34.10 → openlit-1.34.11}/src/openlit/__helpers.py

@@ -379,3 +379,26 @@ def record_completion_metrics(metrics, gen_ai_operation, gen_ai_system, server_a
     metrics["genai_completion_tokens"].add(output_tokens, attributes)
     metrics["genai_prompt_tokens"].add(input_tokens, attributes)
     metrics["genai_cost"].record(cost, attributes)
+
+def record_embedding_metrics(metrics, gen_ai_operation, gen_ai_system, server_address, server_port,
+    request_model, response_model, environment, application_name, start_time, end_time,
+    input_tokens, cost):
+    """
+    Record embedding-specific metrics for the operation.
+    """
+
+    attributes = create_metrics_attributes(
+        operation=gen_ai_operation,
+        system=gen_ai_system,
+        server_address=server_address,
+        server_port=server_port,
+        request_model=request_model,
+        response_model=response_model,
+        service_name=application_name,
+        deployment_environment=environment,
+    )
+    metrics["genai_client_usage_tokens"].record(input_tokens, attributes)
+    metrics["genai_client_operation_duration"].record(end_time - start_time, attributes)
+    metrics["genai_requests"].add(1, attributes)
+    metrics["genai_prompt_tokens"].add(input_tokens, attributes)
+    metrics["genai_cost"].record(cost, attributes)

{openlit-1.34.10 → openlit-1.34.11}/src/openlit/instrumentation/groq/__init__.py

@@ -1,4 +1,3 @@
-# pylint: disable=useless-return, bad-staticmethod-argument, disable=duplicate-code
 """Initializer of Auto Instrumentation of Groq Functions"""
 
 from typing import Collection
@@ -13,15 +12,15 @@ _instruments = ("groq >= 0.5.0",)
 
 class GroqInstrumentor(BaseInstrumentor):
     """
-    An instrumentor for Groq's client library.
+    An instrumentor for Groq client library.
     """
 
     def instrumentation_dependencies(self) -> Collection[str]:
         return _instruments
 
     def _instrument(self, **kwargs):
-        application_name = kwargs.get("application_name", "default_application")
-        environment = kwargs.get("environment", "default_environment")
+        application_name = kwargs.get("application_name", "default")
+        environment = kwargs.get("environment", "default")
         tracer = kwargs.get("tracer")
         metrics = kwargs.get("metrics_dict")
         pricing_info = kwargs.get("pricing_info", {})
@@ -29,22 +28,21 @@ class GroqInstrumentor(BaseInstrumentor):
         disable_metrics = kwargs.get("disable_metrics")
         version = importlib.metadata.version("groq")
 
-        #sync
+        # Chat completions
         wrap_function_wrapper(
             "groq.resources.chat.completions",  
             "Completions.create",  
             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 completions
         wrap_function_wrapper(
             "groq.resources.chat.completions",  
             "AsyncCompletions.create",  
             async_chat(version, environment, application_name,
-                            tracer, pricing_info, capture_message_content, metrics, disable_metrics),
+                      tracer, pricing_info, capture_message_content, metrics, disable_metrics),
         )
 
     def _uninstrument(self, **kwargs):
-        # Proper uninstrumentation logic to revert patched methods
         pass

openlit-1.34.11/src/openlit/instrumentation/groq/async_groq.py

@@ -0,0 +1,143 @@
+"""
+Module for monitoring Groq 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.groq.utils import (
+    process_chunk,
+    process_streaming_chat_response,
+    process_chat_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 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._system_fingerprint = ""
+            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 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.groq.com", 443)
+        request_model = kwargs.get("model", "mixtral-8x7b-32768")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        if streaming:
+            # Special handling for streaming response
+            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)
+        else:
+            # Handling for non-streaming responses
+            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_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

openlit-1.34.11/src/openlit/instrumentation/groq/groq.py

@@ -0,0 +1,143 @@
+"""
+Module for monitoring Groq API calls.
+"""
+
+import time
+from opentelemetry.trace import SpanKind
+from openlit.__helpers import (
+    handle_exception,
+    set_server_address_and_port
+)
+from openlit.instrumentation.groq.utils import (
+    process_chunk,
+    process_streaming_chat_response,
+    process_chat_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 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._system_fingerprint = ""
+            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 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.groq.com", 443)
+        request_model = kwargs.get("model", "mixtral-8x7b-32768")
+
+        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
+
+        if streaming:
+            # Special handling for streaming response
+            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)
+        else:
+            # Handling for non-streaming responses
+            with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
+                start_time = time.time()
+                response = wrapped(*args, **kwargs)
+
+                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

openlit-1.34.11/src/openlit/instrumentation/groq/utils.py

@@ -0,0 +1,199 @@
+"""
+Groq OpenTelemetry instrumentation utility functions
+"""
+import time
+
+from opentelemetry.trace import Status, StatusCode
+
+from openlit.__helpers import (
+    calculate_ttft,
+    response_as_dict,
+    calculate_tbt,
+    get_chat_model_cost,
+    common_span_attributes,
+    record_completion_metrics,
+)
+from openlit.semcov import SemanticConvention
+
+def format_content(messages):
+    """
+    Process a list of messages to extract content.
+    """
+
+    formatted_messages = []
+    for message in messages:
+        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}")
+
+    return "\n".join(formatted_messages)
+
+def process_chunk(scope, chunk):
+    """
+    Process a chunk of response data and update state.
+    """
+
+    end_time = time.time()
+    # Record the timestamp for the current chunk
+    scope._timestamps.append(end_time)
+
+    if len(scope._timestamps) == 1:
+        # Calculate time to first chunk
+        scope._ttft = calculate_ttft(scope._timestamps, scope._start_time)
+
+    chunked = response_as_dict(chunk)
+
+    # Collect message IDs and aggregated response from events
+    if (len(chunked.get("choices", [])) > 0 and
+        "delta" in chunked.get("choices")[0] and
+        "content" in chunked.get("choices")[0].get("delta", {})):
+
+        content = chunked.get("choices")[0].get("delta").get("content")
+        if content:
+            scope._llmresponse += content
+
+    if chunked.get('x_groq') is not None:
+        if chunked.get('x_groq').get('usage') is not None:
+            scope._input_tokens = chunked.get('x_groq').get('usage').get('prompt_tokens')
+            scope._output_tokens = chunked.get('x_groq').get('usage').get('completion_tokens')
+            scope._response_id = chunked.get('x_groq').get('id')
+            scope._response_model = chunked.get('x_groq').get('model')
+            scope._finish_reason = chunked.get('choices', [{}])[0].get('finish_reason')
+            scope._system_fingerprint = chunked.get('x_groq').get('system_fingerprint')
+            scope._end_time = time.time()
+
+
+def common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content, disable_metrics, version, is_stream):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    if len(scope._timestamps) > 1:
+        scope._tbt = calculate_tbt(scope._timestamps)
+
+    prompt = format_content(scope._kwargs.get("messages", []))
+    request_model = scope._kwargs.get("model", "mixtral-8x7b-32768")
+
+    cost = get_chat_model_cost(request_model, pricing_info, scope._input_tokens, scope._output_tokens)
+
+    # Common Span Attributes
+    common_span_attributes(scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_GROQ,
+        scope._server_address, scope._server_port, request_model, scope._response_model,
+        environment, application_name, is_stream, scope._tbt, scope._ttft, version)
+
+    # Span Attributes for Request parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SEED, scope._kwargs.get("seed", ""))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_FREQUENCY_PENALTY, scope._kwargs.get("frequency_penalty", 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_MAX_TOKENS, scope._kwargs.get("max_completion_tokens", -1))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_PRESENCE_PENALTY, scope._kwargs.get("presence_penalty", 0.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_STOP_SEQUENCES, scope._kwargs.get("stop", []))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, scope._kwargs.get("temperature", 1.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get("top_p", 1.0))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get("user", ""))
+    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_SERVICE_TIER, scope._kwargs.get("service_tier", "on_demand"))
+
+    # Span Attributes for Response parameters
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_ID, scope._response_id)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason])
+    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_SYSTEM_FINGERPRINT, scope._system_fingerprint)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE, "text" if isinstance(scope._llmresponse, str) else "json")
+
+    # Span Attributes for Cost and Tokens
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_OUTPUT_TOKENS, scope._output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, scope._input_tokens + scope._output_tokens)
+    scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
+
+    # Span Attributes for Tools
+    if scope._tools:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get("function", {}).get("name", ""))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get("id", "")))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get("function", {}).get("arguments", "")))
+
+    # Span Attributes for Content
+    if capture_message_content:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, prompt)
+        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse)
+
+        # To be removed one the change to span_attributes (from span events) is complete
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_PROMPT_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: prompt,
+            },
+        )
+        scope._span.add_event(
+            name=SemanticConvention.GEN_AI_CONTENT_COMPLETION_EVENT,
+            attributes={
+                SemanticConvention.GEN_AI_CONTENT_COMPLETION: scope._llmresponse,
+            },
+        )
+
+    scope._span.set_status(Status(StatusCode.OK))
+
+    # Metrics
+    if not disable_metrics:
+        record_completion_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_GROQ,
+            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
+            application_name, scope._start_time, scope._end_time, scope._input_tokens, scope._output_tokens,
+            cost, scope._tbt, scope._ttft)
+
+def process_streaming_chat_response(scope, pricing_info, environment, application_name, metrics,
+    capture_message_content=False, disable_metrics=False, version=""):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=True)
+
+def process_chat_response(response, request_model, pricing_info, server_port, server_address,
+    environment, application_name, metrics, start_time, span, capture_message_content=False,
+    disable_metrics=False, version="1.0.0", **kwargs):
+    """
+    Process chat request and generate Telemetry
+    """
+
+    # Create scope object
+    scope = type("GenericScope", (), {})()
+    response_dict = response_as_dict(response)
+
+    scope._start_time = start_time
+    scope._end_time = time.time()
+    scope._span = span
+    scope._llmresponse = " ".join(
+        (choice.get("message", {}).get("content") or "")
+        for choice in response_dict.get("choices", [])
+    )
+    scope._response_id = response_dict.get("id")
+    scope._response_model = response_dict.get("model")
+    scope._input_tokens = response_dict.get("usage", {}).get("prompt_tokens", 0)
+    scope._output_tokens = response_dict.get("usage", {}).get("completion_tokens", 0)
+    scope._timestamps = []
+    scope._ttft, scope._tbt = scope._end_time - scope._start_time, 0
+    scope._server_address, scope._server_port = server_address, server_port
+    scope._kwargs = kwargs
+    scope._system_fingerprint = response_dict.get("system_fingerprint")
+    scope._finish_reason = str(response_dict.get("choices", [])[0].get("finish_reason", ""))
+
+    # Handle tool calls
+    if scope._kwargs.get("tools"):
+        scope._tools = response_dict.get("choices", [{}])[0].get("message", {}).get("tool_calls")
+    else:
+        scope._tools = None
+
+    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
+        capture_message_content, disable_metrics, version, is_stream=False)
+
+    return response

{openlit-1.34.10 → openlit-1.34.11}/src/openlit/instrumentation/ollama/async_ollama.py

@@ -42,7 +42,7 @@ def async_chat(version, environment, application_name,
             self._llmresponse = ""
             self._response_model = ""
             self._finish_reason = ""
-            self._tool_calls = []
+            self._tools = []
             self._input_tokens = 0
             self._output_tokens = 0
             self._response_role = ""
@@ -102,7 +102,8 @@ def async_chat(version, environment, application_name,
         streaming = kwargs.get("stream", False)
 
         server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 11434)
-        request_model = kwargs.get("model")
+        json_body = kwargs.get("json", {}) or {}
+        request_model = json_body.get("model") or kwargs.get("model")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 

{openlit-1.34.10 → openlit-1.34.11}/src/openlit/instrumentation/ollama/ollama.py

@@ -42,7 +42,7 @@ def chat(version, environment, application_name,
             self._llmresponse = ""
             self._response_model = ""
             self._finish_reason = ""
-            self._tool_calls = []
+            self._tools = []
             self._input_tokens = 0
             self._output_tokens = 0
             self._response_role = ""
@@ -102,7 +102,8 @@ def chat(version, environment, application_name,
         streaming = kwargs.get("stream", False)
 
         server_address, server_port = set_server_address_and_port(instance, "127.0.0.1", 11434)
-        request_model = kwargs.get("model")
+        json_body = kwargs.get("json", {}) or {}
+        request_model = json_body.get("model") or kwargs.get("model")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
 

{openlit-1.34.10 → openlit-1.34.11}/src/openlit/instrumentation/ollama/utils.py

@@ -57,7 +57,7 @@ def process_chunk(self, chunk):
     self._llmresponse += chunked.get("message", {}).get("content", "")
 
     if chunked.get("message", {}).get("tool_calls"):
-        self._tool_calls = chunked["message"]["tool_calls"]
+        self._tools = chunked["message"]["tool_calls"]
 
     if chunked.get("eval_count"):
         self._response_role = chunked.get("message", {}).get("role", "")
@@ -138,10 +138,10 @@ def common_chat_logic(scope, gen_ai_endpoint, pricing_info, environment, applica
     scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
 
     # Span Attributes for Tools
-    if hasattr(scope, "_tool_calls") and scope._tool_calls:
-        tool_call = scope._tool_calls[0]
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, tool_call.get("function", {}).get("name", ""))
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(tool_call.get("function", {}).get("arguments", "")))
+    if scope._tools is not None:
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, scope._tools.get("function","")).get("name","")
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, str(scope._tools.get("id","")))
+        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, str(scope._tools.get("function","").get("arguments","")))
 
     # Span Attributes for Content
     if capture_message_content:
@@ -244,7 +244,11 @@ def process_chat_response(response, gen_ai_endpoint, pricing_info, server_port,
     scope._tbt = 0
     scope._server_address, scope._server_port = server_address, server_port
     scope._kwargs = kwargs
-    scope._tool_calls = response_dict.get("message", {}).get("tool_calls", [])
+
+    if scope._kwargs.get("tools"):
+        scope._tools = response_dict.get("choices")[0].get("message").get("tool_calls")
+    else:
+        scope._tools = None
 
     common_chat_logic(scope, gen_ai_endpoint, pricing_info, environment, application_name, metrics,
         capture_message_content, disable_metrics, version)