openlit 1.34.29__py3-none-any.whl → 1.34.31__py3-none-any.whl

openlit/instrumentation/cohere/cohere.py

@@ -16,8 +16,17 @@ from openlit.instrumentation.cohere.utils import (
 )
 from openlit.semcov import SemanticConvention
 
-def chat(version, environment, application_name,
-    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+
+def chat(
+    version,
+    environment,
+    application_name,
+    tracer,
+    pricing_info,
+    capture_message_content,
+    metrics,
+    disable_metrics,
+):
     """
     Generates a telemetry wrapper for GenAI chat function call
     """
@@ -27,7 +36,9 @@ def chat(version, environment, application_name,
         Wraps the GenAI chat function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        server_address, server_port = set_server_address_and_port(
+            instance, "api.cohere.com", 443
+        )
         request_model = kwargs.get("model", "command-r-plus-08-2024")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
@@ -49,15 +60,24 @@ def chat(version, environment, application_name,
                 capture_message_content=capture_message_content,
                 disable_metrics=disable_metrics,
                 version=version,
-                **kwargs
+                **kwargs,
             )
 
         return response
 
     return wrapper
 
-def chat_stream(version, environment, application_name,
-    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+
+def chat_stream(
+    version,
+    environment,
+    application_name,
+    tracer,
+    pricing_info,
+    capture_message_content,
+    metrics,
+    disable_metrics,
+):
     """
     Generates a telemetry wrapper for GenAI chat_stream function call
     """
@@ -68,15 +88,15 @@ def chat_stream(version, environment, application_name,
         """
 
         def __init__(
-                self,
-                wrapped,
-                span,
-                span_name,
-                kwargs,
-                server_address,
-                server_port,
-                **args,
-            ):
+            self,
+            wrapped,
+            span,
+            span_name,
+            kwargs,
+            server_address,
+            server_port,
+            **args,
+        ):
             self.__wrapped__ = wrapped
             self._span = span
             self._span_name = span_name
@@ -120,7 +140,9 @@ def chat_stream(version, environment, application_name,
                 return chunk
             except StopIteration:
                 try:
-                    with tracer.start_as_current_span(self._span_name, kind= SpanKind.CLIENT) as self._span:
+                    with tracer.start_as_current_span(
+                        self._span_name, kind=SpanKind.CLIENT
+                    ) as self._span:
                         process_streaming_chat_response(
                             self,
                             pricing_info=pricing_info,
@@ -129,7 +151,7 @@ def chat_stream(version, environment, application_name,
                             metrics=metrics,
                             capture_message_content=capture_message_content,
                             disable_metrics=disable_metrics,
-                            version=version
+                            version=version,
                         )
 
                 except Exception as e:
@@ -142,7 +164,9 @@ def chat_stream(version, environment, application_name,
         Wraps the GenAI chat_stream function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        server_address, server_port = set_server_address_and_port(
+            instance, "api.cohere.com", 443
+        )
         request_model = kwargs.get("model", "command-r-plus-08-2024")
 
         span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT} {request_model}"
@@ -151,12 +175,23 @@ def chat_stream(version, environment, application_name,
         awaited_wrapped = wrapped(*args, **kwargs)
         span = tracer.start_span(span_name, kind=SpanKind.CLIENT)
 
-        return TracedSyncStream(awaited_wrapped, span, span_name, kwargs, server_address, server_port)
+        return TracedSyncStream(
+            awaited_wrapped, span, span_name, kwargs, server_address, server_port
+        )
 
     return wrapper
 
-def embed(version, environment, application_name,
-    tracer, pricing_info, capture_message_content, metrics, disable_metrics):
+
+def embed(
+    version,
+    environment,
+    application_name,
+    tracer,
+    pricing_info,
+    capture_message_content,
+    metrics,
+    disable_metrics,
+):
     """
     Generates a telemetry wrapper for GenAI embedding function call
     """
@@ -166,10 +201,14 @@ def embed(version, environment, application_name,
         Wraps the GenAI embedding function call.
         """
 
-        server_address, server_port = set_server_address_and_port(instance, "api.cohere.com", 443)
+        server_address, server_port = set_server_address_and_port(
+            instance, "api.cohere.com", 443
+        )
         request_model = kwargs.get("model", "embed-english-v3.0")
 
-        span_name = f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+        span_name = (
+            f"{SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING} {request_model}"
+        )
 
         with tracer.start_as_current_span(span_name, kind=SpanKind.CLIENT) as span:
             start_time = time.time()
@@ -190,7 +229,7 @@ def embed(version, environment, application_name,
                     capture_message_content=capture_message_content,
                     disable_metrics=disable_metrics,
                     version=version,
-                    **kwargs
+                    **kwargs,
                 )
 
             except Exception as e:

openlit/instrumentation/cohere/utils.py

@@ -1,6 +1,7 @@
 """
 Cohere OpenTelemetry instrumentation utility functions
 """
+
 import time
 
 from opentelemetry.trace import Status, StatusCode
@@ -17,6 +18,7 @@ from openlit.__helpers import (
 )
 from openlit.semcov import SemanticConvention
 
+
 def format_content(messages):
     """
     Process a list of messages to extract content.
@@ -35,8 +37,9 @@ def format_content(messages):
 
         if isinstance(content, list):
             content_str = ", ".join(
-                f'{item["type"]}: {item["text"] if "text" in item else item.get("image_url", "")}'
-                if "type" in item else f'text: {item.get("text", "")}'
+                f"{item['type']}: {item['text'] if 'text' in item else item.get('image_url', '')}"
+                if "type" in item
+                else f"text: {item.get('text', '')}"
                 for item in content
             )
             formatted_messages.append(f"{role}: {content_str}")
@@ -45,6 +48,7 @@ def format_content(messages):
 
     return "\n".join(formatted_messages)
 
+
 def process_chunk(scope, chunk):
     """
     Process a chunk of response data and update state.
@@ -65,13 +69,17 @@ def process_chunk(scope, chunk):
         scope._response_id = chunked.get("id")
 
     if chunked.get("type") == "content-delta":
-        content = chunked.get("delta", {}).get("message", {}).get("content", {}).get("text")
+        content = (
+            chunked.get("delta", {}).get("message", {}).get("content", {}).get("text")
+        )
         if content:
             scope._llmresponse += content
 
     # Handle tool plan deltas
     if chunked.get("type") == "tool-plan-delta":
-        tool_plan_text = chunked.get("delta", {}).get("message", {}).get("tool_plan", "")
+        tool_plan_text = (
+            chunked.get("delta", {}).get("message", {}).get("tool_plan", "")
+        )
         if tool_plan_text:
             if not hasattr(scope, "_tool_plan"):
                 scope._tool_plan = ""
@@ -94,8 +102,8 @@ def process_chunk(scope, chunk):
             "type": tool_call.get("type", "function"),
             "function": {
                 "name": tool_call.get("function", {}).get("name", ""),
-                "arguments": ""
-            }
+                "arguments": "",
+            },
         }
 
     # Handle tool call deltas (arguments)
@@ -103,7 +111,13 @@ def process_chunk(scope, chunk):
         if hasattr(scope, "_tools") and scope._tools:
             index = chunked.get("index", 0)
             if index < len(scope._tools):
-                arguments = chunked.get("delta", {}).get("message", {}).get("tool_calls", {}).get("function", {}).get("arguments", "")
+                arguments = (
+                    chunked.get("delta", {})
+                    .get("message", {})
+                    .get("tool_calls", {})
+                    .get("function", {})
+                    .get("arguments", "")
+                )
                 if arguments:
                     scope._tools[index]["function"]["arguments"] += arguments
 
@@ -115,8 +129,18 @@ def process_chunk(scope, chunk):
         scope._output_tokens = usage.get("output_tokens", 0)
         scope._end_time = time.time()
 
-def common_chat_logic(scope, pricing_info, environment, application_name, metrics,
-    capture_message_content, disable_metrics, version, is_stream):
+
+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
     """
@@ -127,58 +151,123 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
     prompt = format_content(scope._kwargs.get("messages", []))
     request_model = scope._kwargs.get("model", "command-r-plus-08-2024")
 
-    cost = get_chat_model_cost(request_model, pricing_info, scope._input_tokens, scope._output_tokens)
+    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_COHERE,
-        scope._server_address, scope._server_port, request_model, scope._response_model,
-        environment, application_name, is_stream, scope._tbt, scope._ttft, version)
+    common_span_attributes(
+        scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,
+        SemanticConvention.GEN_AI_SYSTEM_COHERE,
+        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_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_sequences", []))
-    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TEMPERATURE, scope._kwargs.get("temperature", 0.3))
-    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_K, scope._kwargs.get("k", 1.0))
-    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get("p", 1.0))
+    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_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_sequences", []),
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_REQUEST_TEMPERATURE,
+        scope._kwargs.get("temperature", 0.3),
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_REQUEST_TOP_K, scope._kwargs.get("k", 1.0)
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_REQUEST_TOP_P, scope._kwargs.get("p", 1.0)
+    )
 
     # 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_OUTPUT_TYPE, "text" if isinstance(scope._llmresponse, str) else "json")
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_RESPONSE_FINISH_REASON, [scope._finish_reason]
+    )
+    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_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 - optimized
     if scope._tools:
         tools = scope._tools if isinstance(scope._tools, list) else [scope._tools]
 
-        names, ids, args = zip(*[
-            (t.get("function", {}).get("name", ""),
-             str(t.get("id", "")),
-             str(t.get("function", {}).get("arguments", "")))
-            for t in tools if isinstance(t, dict) and t
-        ]) if tools else ([], [], [])
+        names, ids, args = (
+            zip(
+                *[
+                    (
+                        t.get("function", {}).get("name", ""),
+                        str(t.get("id", "")),
+                        str(t.get("function", {}).get("arguments", "")),
+                    )
+                    for t in tools
+                    if isinstance(t, dict) and t
+                ]
+            )
+            if tools
+            else ([], [], [])
+        )
 
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_NAME, ", ".join(filter(None, names)))
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_CALL_ID, ", ".join(filter(None, ids)))
-        scope._span.set_attribute(SemanticConvention.GEN_AI_TOOL_ARGS, ", ".join(filter(None, args)))
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_TOOL_NAME, ", ".join(filter(None, names))
+        )
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_TOOL_CALL_ID, ", ".join(filter(None, ids))
+        )
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_TOOL_ARGS, ", ".join(filter(None, args))
+        )
 
     # Span Attributes for Tool Plan (Cohere specific)
     if hasattr(scope, "_tool_plan") and scope._tool_plan:
-        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_REASONING, scope._tool_plan)
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_CONTENT_REASONING, scope._tool_plan
+        )
 
     # 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)
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_CONTENT_COMPLETION, scope._llmresponse
+        )
 
         # To be removed once the change to span_attributes (from span events) is complete
         scope._span.add_event(
@@ -198,23 +287,69 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
 
     # Metrics
     if not disable_metrics:
-        record_completion_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT, SemanticConvention.GEN_AI_SYSTEM_COHERE,
-            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)
+        record_completion_metrics(
+            metrics,
+            SemanticConvention.GEN_AI_OPERATION_TYPE_CHAT,
+            SemanticConvention.GEN_AI_SYSTEM_COHERE,
+            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=""):
+
+def process_streaming_chat_response(
+    scope,
+    pricing_info,
+    environment,
+    application_name,
+    metrics,
+    capture_message_content=False,
+    disable_metrics=False,
+    version="",
+):
     """
     Process streaming 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):
+    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
     """
@@ -235,8 +370,12 @@ def process_chat_response(response, request_model, pricing_info, server_port, se
         scope._llmresponse = ""
     scope._response_id = response_dict.get("id")
     scope._response_model = request_model
-    scope._input_tokens = response_dict.get("usage", {}).get("billed_units", {}).get("input_tokens", 0)
-    scope._output_tokens = response_dict.get("usage", {}).get("billed_units", {}).get("output_tokens", 0)
+    scope._input_tokens = (
+        response_dict.get("usage", {}).get("billed_units", {}).get("input_tokens", 0)
+    )
+    scope._output_tokens = (
+        response_dict.get("usage", {}).get("billed_units", {}).get("output_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
@@ -252,13 +391,31 @@ def process_chat_response(response, request_model, pricing_info, server_port, se
         scope._tools = None
         scope._tool_plan = ""
 
-    common_chat_logic(scope, pricing_info, environment, application_name, metrics,
-        capture_message_content, disable_metrics, version, is_stream=False)
+    common_chat_logic(
+        scope,
+        pricing_info,
+        environment,
+        application_name,
+        metrics,
+        capture_message_content,
+        disable_metrics,
+        version,
+        is_stream=False,
+    )
 
     return response
 
-def common_embedding_logic(scope, pricing_info, environment, application_name, metrics,
-    capture_message_content, disable_metrics, version):
+
+def common_embedding_logic(
+    scope,
+    pricing_info,
+    environment,
+    application_name,
+    metrics,
+    capture_message_content,
+    disable_metrics,
+    version,
+):
     """
     Process embedding request and generate Telemetry
     """
@@ -269,19 +426,39 @@ def common_embedding_logic(scope, pricing_info, environment, application_name, m
     cost = get_embed_model_cost(request_model, pricing_info, scope._input_tokens)
 
     # Common Span Attributes
-    common_span_attributes(scope,
-        SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_COHERE,
-        scope._server_address, scope._server_port, request_model, scope._response_model,
-        environment, application_name, False, 0, scope._ttft, version)
+    common_span_attributes(
+        scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING,
+        SemanticConvention.GEN_AI_SYSTEM_COHERE,
+        scope._server_address,
+        scope._server_port,
+        request_model,
+        scope._response_model,
+        environment,
+        application_name,
+        False,
+        0,
+        scope._ttft,
+        version,
+    )
 
     # Span Attributes for Request parameters
-    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_ENCODING_FORMATS, scope._kwargs.get("embedding_types", ["float"]))
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_REQUEST_ENCODING_FORMATS,
+        scope._kwargs.get("embedding_types", ["float"]),
+    )
 
     # 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_CLIENT_TOKEN_USAGE, scope._input_tokens)
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_USAGE_INPUT_TOKENS, scope._input_tokens
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE, scope._input_tokens
+    )
     scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_COST, cost)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_OUTPUT_TYPE, scope._response_type)
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_OUTPUT_TYPE, scope._response_type
+    )
 
     # Span Attributes for Content
     if capture_message_content:
@@ -299,13 +476,39 @@ def common_embedding_logic(scope, pricing_info, environment, application_name, m
 
     # Metrics
     if not disable_metrics:
-        record_embedding_metrics(metrics, SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING, SemanticConvention.GEN_AI_SYSTEM_COHERE,
-            scope._server_address, scope._server_port, request_model, scope._response_model, environment,
-            application_name, scope._start_time, scope._end_time, scope._input_tokens, cost)
+        record_embedding_metrics(
+            metrics,
+            SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING,
+            SemanticConvention.GEN_AI_SYSTEM_COHERE,
+            scope._server_address,
+            scope._server_port,
+            request_model,
+            scope._response_model,
+            environment,
+            application_name,
+            scope._start_time,
+            scope._end_time,
+            scope._input_tokens,
+            cost,
+        )
+
 
-def process_embedding_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):
+def process_embedding_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 embedding request and generate Telemetry
     """
@@ -317,14 +520,24 @@ def process_embedding_response(response, request_model, pricing_info, server_por
     scope._start_time = start_time
     scope._end_time = time.time()
     scope._span = span
-    scope._input_tokens = response_dict.get("meta", {}).get("billed_units", {}).get("input_tokens", 0)
+    scope._input_tokens = (
+        response_dict.get("meta", {}).get("billed_units", {}).get("input_tokens", 0)
+    )
     scope._response_model = request_model
     scope._response_type = response_dict.get("response_type", "")
     scope._ttft = scope._end_time - scope._start_time
     scope._server_address, scope._server_port = server_address, server_port
     scope._kwargs = kwargs
 
-    common_embedding_logic(scope, pricing_info, environment, application_name, metrics,
-        capture_message_content, disable_metrics, version)
+    common_embedding_logic(
+        scope,
+        pricing_info,
+        environment,
+        application_name,
+        metrics,
+        capture_message_content,
+        disable_metrics,
+        version,
+    )
 
     return response