fix _transform_usage_objects
This commit is contained in:
Ishaan Jaffer
parent
8a8c24e391
commit
b2df26d0be
@ -1462,6 +1462,51 @@ class Logging(LiteLLMLoggingBaseClass):
|
||||
)
|
||||
return logging_result
|
||||
|
||||
def _process_hidden_params_and_response_cost(
|
||||
self,
|
||||
logging_result,
|
||||
start_time,
|
||||
end_time,
|
||||
):
|
||||
hidden_params = getattr(logging_result, "_hidden_params", {})
|
||||
if hidden_params:
|
||||
if self.model_call_details.get("litellm_params") is not None:
|
||||
self.model_call_details["litellm_params"].setdefault("metadata", {})
|
||||
if self.model_call_details["litellm_params"]["metadata"] is None:
|
||||
self.model_call_details["litellm_params"]["metadata"] = {}
|
||||
self.model_call_details["litellm_params"]["metadata"]["hidden_params"] = getattr(logging_result, "_hidden_params", {}) # type: ignore
|
||||
|
||||
if "response_cost" in hidden_params:
|
||||
self.model_call_details["response_cost"] = hidden_params["response_cost"]
|
||||
else:
|
||||
self.model_call_details["response_cost"] = self._response_cost_calculator(result=logging_result)
|
||||
|
||||
self.model_call_details["standard_logging_object"] = get_standard_logging_object_payload(
|
||||
kwargs=self.model_call_details,
|
||||
init_response_obj=logging_result,
|
||||
start_time=start_time,
|
||||
end_time=end_time,
|
||||
logging_obj=self,
|
||||
status="success",
|
||||
standard_built_in_tools_params=self.standard_built_in_tools_params,
|
||||
)
|
||||
|
||||
def _transform_usage_objects(self, result):
|
||||
if isinstance(result, ResponsesAPIResponse):
|
||||
result = result.model_copy()
|
||||
transformed_usage = ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(result.usage)
|
||||
setattr(result, "usage", transformed_usage.model_dump() if hasattr(transformed_usage, "model_dump") else dict(transformed_usage))
|
||||
if (standard_logging_payload := self.model_call_details.get("standard_logging_object")) is not None:
|
||||
standard_logging_payload["response"] = result.model_dump() if hasattr(result, "model_dump") else dict(result)
|
||||
elif isinstance(result, TranscriptionResponse):
|
||||
from litellm.litellm_core_utils.llm_cost_calc.usage_object_transformation import (
|
||||
TranscriptionUsageObjectTransformation,
|
||||
)
|
||||
result = result.model_copy()
|
||||
transformed_usage = TranscriptionUsageObjectTransformation.transform_transcription_usage_object(result.usage) # type: ignore
|
||||
setattr(result, "usage", transformed_usage)
|
||||
return result
|
||||
|
||||
def _success_handler_helper_fn(
|
||||
self,
|
||||
result=None,
|
||||
@ -1477,143 +1522,40 @@ class Logging(LiteLLMLoggingBaseClass):
|
||||
end_time = datetime.datetime.now()
|
||||
if self.completion_start_time is None:
|
||||
self.completion_start_time = end_time
|
||||
self.model_call_details["completion_start_time"] = (
|
||||
self.completion_start_time
|
||||
)
|
||||
self.model_call_details["completion_start_time"] = self.completion_start_time
|
||||
|
||||
self.model_call_details["log_event_type"] = "successful_api_call"
|
||||
self.model_call_details["end_time"] = end_time
|
||||
self.model_call_details["cache_hit"] = cache_hit
|
||||
|
||||
if self.call_type == CallTypes.anthropic_messages.value:
|
||||
result = self._handle_anthropic_messages_response_logging(result=result)
|
||||
elif (
|
||||
self.call_type == CallTypes.generate_content.value
|
||||
or self.call_type == CallTypes.agenerate_content.value
|
||||
):
|
||||
result = self._handle_non_streaming_google_genai_generate_content_response_logging(
|
||||
result=result
|
||||
)
|
||||
## if model in model cost map - log the response cost
|
||||
## else set cost to None
|
||||
|
||||
elif self.call_type == CallTypes.generate_content.value or self.call_type == CallTypes.agenerate_content.value:
|
||||
result = self._handle_non_streaming_google_genai_generate_content_response_logging(result=result)
|
||||
|
||||
logging_result = self.normalize_logging_result(result=result)
|
||||
|
||||
if (
|
||||
standard_logging_object is None
|
||||
and result is not None
|
||||
and self.stream is not True
|
||||
):
|
||||
if self._is_recognized_call_type_for_logging(
|
||||
logging_result=logging_result
|
||||
):
|
||||
## HIDDEN PARAMS ##
|
||||
hidden_params = getattr(logging_result, "_hidden_params", {})
|
||||
if hidden_params:
|
||||
# add to metadata for logging
|
||||
if self.model_call_details.get("litellm_params") is not None:
|
||||
self.model_call_details["litellm_params"].setdefault(
|
||||
"metadata", {}
|
||||
)
|
||||
if (
|
||||
self.model_call_details["litellm_params"]["metadata"]
|
||||
is None
|
||||
):
|
||||
self.model_call_details["litellm_params"][
|
||||
"metadata"
|
||||
] = {}
|
||||
|
||||
self.model_call_details["litellm_params"]["metadata"][ # type: ignore
|
||||
"hidden_params"
|
||||
] = getattr(
|
||||
logging_result, "_hidden_params", {}
|
||||
)
|
||||
## RESPONSE COST - Only calculate if not in hidden_params ##
|
||||
if "response_cost" in hidden_params:
|
||||
self.model_call_details["response_cost"] = hidden_params[
|
||||
"response_cost"
|
||||
]
|
||||
else:
|
||||
self.model_call_details["response_cost"] = (
|
||||
self._response_cost_calculator(result=logging_result)
|
||||
)
|
||||
## STANDARDIZED LOGGING PAYLOAD
|
||||
|
||||
self.model_call_details["standard_logging_object"] = (
|
||||
get_standard_logging_object_payload(
|
||||
kwargs=self.model_call_details,
|
||||
init_response_obj=logging_result,
|
||||
start_time=start_time,
|
||||
end_time=end_time,
|
||||
logging_obj=self,
|
||||
status="success",
|
||||
standard_built_in_tools_params=self.standard_built_in_tools_params,
|
||||
)
|
||||
)
|
||||
if standard_logging_object is None and result is not None and self.stream is not True:
|
||||
if self._is_recognized_call_type_for_logging(logging_result=logging_result):
|
||||
self._process_hidden_params_and_response_cost(logging_result=logging_result, start_time=start_time, end_time=end_time)
|
||||
elif isinstance(result, dict) or isinstance(result, list):
|
||||
## STANDARDIZED LOGGING PAYLOAD
|
||||
self.model_call_details["standard_logging_object"] = (
|
||||
get_standard_logging_object_payload(
|
||||
kwargs=self.model_call_details,
|
||||
init_response_obj=result,
|
||||
start_time=start_time,
|
||||
end_time=end_time,
|
||||
logging_obj=self,
|
||||
status="success",
|
||||
standard_built_in_tools_params=self.standard_built_in_tools_params,
|
||||
)
|
||||
self.model_call_details["standard_logging_object"] = get_standard_logging_object_payload(
|
||||
kwargs=self.model_call_details,
|
||||
init_response_obj=result,
|
||||
start_time=start_time,
|
||||
end_time=end_time,
|
||||
logging_obj=self,
|
||||
status="success",
|
||||
standard_built_in_tools_params=self.standard_built_in_tools_params,
|
||||
)
|
||||
elif standard_logging_object is not None:
|
||||
self.model_call_details["standard_logging_object"] = (
|
||||
standard_logging_object
|
||||
)
|
||||
else: # streaming chunks + image gen.
|
||||
self.model_call_details["standard_logging_object"] = standard_logging_object
|
||||
else:
|
||||
self.model_call_details["response_cost"] = None
|
||||
|
||||
## RESPONSES API USAGE OBJECT TRANSFORMATION ##
|
||||
# MAP RESPONSES API USAGE OBJECT TO LITELLM USAGE OBJECT
|
||||
if isinstance(result, ResponsesAPIResponse):
|
||||
result = result.model_copy()
|
||||
transformed_usage = (
|
||||
ResponseAPILoggingUtils._transform_response_api_usage_to_chat_usage(
|
||||
result.usage
|
||||
)
|
||||
)
|
||||
# Set as dict instead of Usage object so model_dump() serializes it correctly
|
||||
setattr(
|
||||
result,
|
||||
"usage",
|
||||
(
|
||||
transformed_usage.model_dump()
|
||||
if hasattr(transformed_usage, "model_dump")
|
||||
else dict(transformed_usage)
|
||||
),
|
||||
)
|
||||
if (
|
||||
standard_logging_payload := self.model_call_details.get(
|
||||
"standard_logging_object"
|
||||
)
|
||||
) is not None:
|
||||
standard_logging_payload["response"] = (
|
||||
result.model_dump()
|
||||
if hasattr(result, "model_dump")
|
||||
else dict(result)
|
||||
)
|
||||
elif isinstance(result, TranscriptionResponse):
|
||||
from litellm.litellm_core_utils.llm_cost_calc.usage_object_transformation import (
|
||||
TranscriptionUsageObjectTransformation,
|
||||
)
|
||||
|
||||
result = result.model_copy()
|
||||
transformed_usage = TranscriptionUsageObjectTransformation.transform_transcription_usage_object(
|
||||
result.usage # type: ignore
|
||||
)
|
||||
setattr(result, "usage", transformed_usage)
|
||||
if (
|
||||
litellm.max_budget
|
||||
and self.stream is False
|
||||
and result is not None
|
||||
and isinstance(result, dict)
|
||||
and "content" in result
|
||||
):
|
||||
result = self._transform_usage_objects(result=result)
|
||||
|
||||
if litellm.max_budget and self.stream is False and result is not None and isinstance(result, dict) and "content" in result:
|
||||
time_diff = (end_time - start_time).total_seconds()
|
||||
float_diff = float(time_diff)
|
||||
litellm._current_cost += litellm.completion_cost(
|
||||
|
||||
Loading…
Reference in New Issue
Block a user