openlit 1.34.30__py3-none-any.whl → 1.34.31__py3-none-any.whl

openlit/instrumentation/azure_ai_inference/utils.py

@@ -1,6 +1,7 @@
 """
 Azure AI Inference 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.
@@ -29,15 +31,17 @@ 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}')
+            formatted_messages.append(f"{role}: {content_str}")
         else:
-            formatted_messages.append(f'{role}: {content}')
+            formatted_messages.append(f"{role}: {content}")
+
+    return "\n".join(formatted_messages)
 
-    return '\n'.join(formatted_messages)
 
 def process_chunk(scope, chunk):
     """
@@ -92,25 +96,44 @@ def process_chunk(scope, chunk):
                     func = tool.get("function", {})
                     scope._tools[idx] = {
                         "id": tool["id"],
-                        "function": {"name": func.get("name", ""), "arguments": func.get("arguments", "")},
-                        "type": tool.get("type", "function")
+                        "function": {
+                            "name": func.get("name", ""),
+                            "arguments": func.get("arguments", ""),
+                        },
+                        "type": tool.get("type", "function"),
                     }
-                elif scope._tools[idx] and "function" in tool:  # Append args (id is None)
-                    scope._tools[idx]["function"]["arguments"] += tool["function"].get("arguments", "")
+                elif (
+                    scope._tools[idx] and "function" in tool
+                ):  # Append args (id is None)
+                    scope._tools[idx]["function"]["arguments"] += tool["function"].get(
+                        "arguments", ""
+                    )
 
     # Handle usage information (typically only in final chunk)
     if chunked.get("usage"):
         scope._input_tokens = chunked.get("usage").get("prompt_tokens", 0)
         scope._output_tokens = chunked.get("usage").get("completion_tokens", 0)
         # Handle reasoning tokens if present (optional) - check nested structure
-        completion_details = chunked.get("usage", {}).get("completion_tokens_details", {})
+        completion_details = chunked.get("usage", {}).get(
+            "completion_tokens_details", {}
+        )
         if "reasoning_tokens" in completion_details:
             scope._reasoning_tokens = completion_details.get("reasoning_tokens", 0)
         elif "reasoning_tokens" in chunked.get("usage", {}):
             scope._reasoning_tokens = chunked.get("usage").get("reasoning_tokens", 0)
 
-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
     """
@@ -121,65 +144,134 @@ def common_chat_logic(scope, pricing_info, environment, application_name, metric
     prompt = format_content(scope._kwargs.get("messages", []))
     request_model = scope._kwargs.get("model", "gpt-4o")
 
-    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_AZURE_AI_INFERENCE,
-        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_AZURE_AI_INFERENCE,
+        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_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", []))
-    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_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", [])
+    )
+    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)
+    )
 
     # 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_SERVICE_TIER, scope._response_service_tier)
-    scope._span.set_attribute(SemanticConvention.GEN_AI_RESPONSE_SYSTEM_FINGERPRINT, scope._response_service_tier)
-    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_RESPONSE_SERVICE_TIER, scope._response_service_tier
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_RESPONSE_SYSTEM_FINGERPRINT,
+        scope._response_service_tier,
+    )
+    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 Reasoning (if present)
     if hasattr(scope, "_reasoning_tokens") and scope._reasoning_tokens > 0:
-        scope._span.set_attribute(SemanticConvention.GEN_AI_USAGE_REASONING_TOKENS, scope._reasoning_tokens)
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_USAGE_REASONING_TOKENS, scope._reasoning_tokens
+        )
         # Update total token usage to include reasoning tokens
-        scope._span.set_attribute(SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE,
-                                scope._input_tokens + scope._output_tokens + scope._reasoning_tokens)
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_CLIENT_TOKEN_USAGE,
+            scope._input_tokens + scope._output_tokens + scope._reasoning_tokens,
+        )
 
     # 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 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
+        )
 
         # Add reasoning content if available
         if hasattr(scope, "_reasoning_content") and scope._reasoning_content:
-            scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_REASONING, scope._reasoning_content)
+            scope._span.set_attribute(
+                SemanticConvention.GEN_AI_CONTENT_REASONING, scope._reasoning_content
+            )
 
         # To be removed once the change to span_attributes (from span events) is complete
         scope._span.add_event(
@@ -199,23 +291,69 @@ 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_AZURE_AI_INFERENCE, 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_AZURE_AI_INFERENCE,
+            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)
+    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):
+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
     """
@@ -232,14 +370,20 @@ def process_chat_response(response, request_model, pricing_info, server_port, se
         for choice in response_dict.get("choices", [])
     )
     # Handle reasoning content from non-streaming response
-    reasoning_content = response_dict.get("choices", [{}])[0].get("message", {}).get("reasoning_content")
+    reasoning_content = (
+        response_dict.get("choices", [{}])[0]
+        .get("message", {})
+        .get("reasoning_content")
+    )
     if reasoning_content:
         scope._reasoning_content = reasoning_content
 
     scope._input_tokens = response_dict.get("usage", {}).get("prompt_tokens", 0)
     scope._output_tokens = response_dict.get("usage", {}).get("completion_tokens", 0)
     # Handle reasoning tokens if present (optional) - check nested structure
-    completion_details = response_dict.get("usage", {}).get("completion_tokens_details", {})
+    completion_details = response_dict.get("usage", {}).get(
+        "completion_tokens_details", {}
+    )
     if "reasoning_tokens" in completion_details:
         scope._reasoning_tokens = completion_details.get("reasoning_tokens", 0)
     elif "reasoning_tokens" in response_dict.get("usage", {}):
@@ -248,7 +392,9 @@ def process_chat_response(response, request_model, pricing_info, server_port, se
         scope._reasoning_tokens = 0
     scope._response_id = response_dict.get("id")
     scope._response_model = response_dict.get("model")
-    scope._finish_reason = str(response_dict.get("choices", [])[0].get("finish_reason", ""))
+    scope._finish_reason = str(
+        response_dict.get("choices", [])[0].get("finish_reason", "")
+    )
     scope._response_service_tier = str(response_dict.get("system_fingerprint", ""))
     scope._timestamps = []
     scope._ttft, scope._tbt = scope._end_time - scope._start_time, 0
@@ -257,17 +403,37 @@ def process_chat_response(response, request_model, pricing_info, server_port, se
 
     # Handle tool calls
     if scope._kwargs.get("tools"):
-        scope._tools = response_dict.get("choices", [{}])[0].get("message", {}).get("tool_calls")
+        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)
+    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
     """
@@ -277,29 +443,54 @@ 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_AZURE_AI_INFERENCE,
-        scope._server_address, scope._server_port, request_model, scope._response_model,
-        environment, application_name, False, 0, scope._end_time - scope._start_time, version)
+    common_span_attributes(
+        scope,
+        SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING,
+        SemanticConvention.GEN_AI_SYSTEM_AZURE_AI_INFERENCE,
+        scope._server_address,
+        scope._server_port,
+        request_model,
+        scope._response_model,
+        environment,
+        application_name,
+        False,
+        0,
+        scope._end_time - scope._start_time,
+        version,
+    )
 
     # Span Attributes for Request parameters
-    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_ENCODING_FORMATS, [scope._kwargs.get("encoding_format", "float")])
-    scope._span.set_attribute(SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get("user", ""))
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_REQUEST_ENCODING_FORMATS,
+        [scope._kwargs.get("encoding_format", "float")],
+    )
+    scope._span.set_attribute(
+        SemanticConvention.GEN_AI_REQUEST_USER, scope._kwargs.get("user", "")
+    )
 
     # 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)
 
     # Span Attributes for Content
     if capture_message_content:
-        scope._span.set_attribute(SemanticConvention.GEN_AI_CONTENT_PROMPT, str(scope._kwargs.get("input", "")))
+        scope._span.set_attribute(
+            SemanticConvention.GEN_AI_CONTENT_PROMPT,
+            str(scope._kwargs.get("input", "")),
+        )
 
         # To be removed once 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: str(scope._kwargs.get("input", "")),
+                SemanticConvention.GEN_AI_CONTENT_PROMPT: str(
+                    scope._kwargs.get("input", "")
+                ),
             },
         )
 
@@ -307,14 +498,39 @@ 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_AZURE_AI_INFERENCE, 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):
+        record_embedding_metrics(
+            metrics,
+            SemanticConvention.GEN_AI_OPERATION_TYPE_EMBEDDING,
+            SemanticConvention.GEN_AI_SYSTEM_AZURE_AI_INFERENCE,
+            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,
+):
     """
     Process embedding request and generate Telemetry
     """
@@ -331,7 +547,15 @@ def process_embedding_response(response, request_model, pricing_info, server_por
     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

openlit/instrumentation/bedrock/__init__.py

@@ -9,6 +9,7 @@ from openlit.instrumentation.bedrock.bedrock import converse, converse_stream
 
 _instruments = ("boto3 >= 1.34.138",)
 
+
 class BedrockInstrumentor(BaseInstrumentor):
     """
     An instrumentor for AWS Bedrock client library.
@@ -31,16 +32,32 @@ class BedrockInstrumentor(BaseInstrumentor):
         wrap_function_wrapper(
             "botocore.client",
             "ClientCreator.create_client",
-            converse(version, environment, application_name, tracer, pricing_info,
-                capture_message_content, metrics, disable_metrics),
+            converse(
+                version,
+                environment,
+                application_name,
+                tracer,
+                pricing_info,
+                capture_message_content,
+                metrics,
+                disable_metrics,
+            ),
         )
 
         # streaming
         wrap_function_wrapper(
             "botocore.client",
             "ClientCreator.create_client",
-            converse_stream(version, environment, application_name, tracer, pricing_info,
-                capture_message_content, metrics, disable_metrics),
+            converse_stream(
+                version,
+                environment,
+                application_name,
+                tracer,
+                pricing_info,
+                capture_message_content,
+                metrics,
+                disable_metrics,
+            ),
         )
 
     def _uninstrument(self, **kwargs):