Cost Metric¶
- pydantic model ibm_watsonx_gov.metrics.cost.cost_metric.CostMetric¶
Bases:
GenAIMetricDefines the Cost metric class.
The Cost metric keep track of LLM usage cost for provided token count.
Examples
- Create Cost metric with default parameters and compute using metrics evaluator.
metric = CostMetric() result = MetricsEvaluator().evaluate(data={"model": "...", "input_tokens": "...", "output_tokens": "..."}, metrics=[metric])
Show JSON schema
{ "title": "CostMetric", "description": "Defines the Cost metric class.\n\nThe Cost metric keep track of LLM usage cost for provided token count.\n\nExamples:\n 1. Create Cost metric with default parameters and compute using metrics evaluator.\n .. code-block:: python\n\n metric = CostMetric()\n result = MetricsEvaluator().evaluate(data={\"model\": \"...\", \"input_tokens\": \"...\", \"output_tokens\": \"...\"},\n metrics=[metric])", "type": "object", "properties": { "name": { "const": "cost", "default": "cost", "description": "The cost metric name.", "title": "name", "type": "string" }, "display_name": { "const": "Cost", "default": "Cost", "description": "The cost metric display name.", "title": "Display Name", "type": "string" }, "type_": { "default": "ootb", "description": "The type of the metric. Indicates whether the metric is ootb or custom.", "examples": [ "ootb", "custom" ], "title": "Metric type", "type": "string" }, "value_type": { "default": "numeric", "description": "The type of the metric value. Indicates whether the metric value is numeric or categorical.", "examples": [ "numeric", "categorical" ], "title": "Metric value type", "type": "string" }, "thresholds": { "default": [], "description": "The list of thresholds", "items": { "$ref": "#/$defs/MetricThreshold" }, "title": "Thresholds", "type": "array" }, "tasks": { "default": [ "question_answering", "classification", "summarization", "generation", "extraction", "retrieval_augmented_generation" ], "description": "The list of supported tasks.", "items": { "$ref": "#/$defs/TaskType" }, "title": "Tasks", "type": "array" }, "group": { "$ref": "#/$defs/MetricGroup", "default": "usage", "description": "The metric group.", "title": "Group" }, "is_reference_free": { "default": true, "description": "Decides whether this metric needs a reference for computation", "title": "Is Reference Free", "type": "boolean" }, "method": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The method used to compute the metric.", "title": "Method" }, "metric_dependencies": { "default": [], "description": "Metrics that needs to be evaluated first", "items": { "$ref": "#/$defs/GenAIMetric" }, "title": "Metric Dependencies", "type": "array" }, "applies_to": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "message", "description": "The tag to indicate for which the metric is applied to. Used for agentic application metric computation.", "examples": [ "message", "conversation", "sub_agent" ], "title": "Applies to" }, "target_component": { "anyOf": [ { "$ref": "#/$defs/TargetComponent" }, { "type": "null" } ], "default": null, "description": "The specific application component (node) where this metric is computed. Used for agentic application metric computation.", "examples": [ "Retrieval Node", "Context Node", "Generation Node" ], "title": "Target Component" }, "mapping": { "anyOf": [ { "$ref": "#/$defs/Mapping" }, { "type": "null" } ], "default": null, "description": "The data mapping details for the metric which are used to read the values needed to compute the metric.", "examples": { "items": [ { "attribute_name": "traceloop.entity.input", "column_name": null, "json_path": "$.inputs.input_text", "lookup_child_spans": false, "name": "input_text", "span_name": "LangGraph.workflow", "type": "input" }, { "attribute_name": "traceloop.entity.output", "column_name": null, "json_path": "$.outputs.generated_text", "lookup_child_spans": false, "name": "generated_text", "span_name": "LangGraph.workflow", "type": "output" } ], "source": "trace" }, "title": "Mapping" } }, "$defs": { "GenAIMetric": { "description": "Defines the Generative AI metric interface", "properties": { "name": { "description": "The name of the metric.", "examples": [ "answer_relevance", "context_relevance" ], "title": "Metric Name", "type": "string" }, "display_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The display name of the metric.", "examples": [ "Answer Relevance", "Context Relevance" ], "title": "Metric display name" }, "type_": { "default": "ootb", "description": "The type of the metric. Indicates whether the metric is ootb or custom.", "examples": [ "ootb", "custom" ], "title": "Metric type", "type": "string" }, "value_type": { "default": "numeric", "description": "The type of the metric value. Indicates whether the metric value is numeric or categorical.", "examples": [ "numeric", "categorical" ], "title": "Metric value type", "type": "string" }, "thresholds": { "default": [], "description": "The list of thresholds", "items": { "$ref": "#/$defs/MetricThreshold" }, "title": "Thresholds", "type": "array" }, "tasks": { "default": [], "description": "The task types this metric is associated with.", "items": { "$ref": "#/$defs/TaskType" }, "title": "Tasks", "type": "array" }, "group": { "anyOf": [ { "$ref": "#/$defs/MetricGroup" }, { "type": "null" } ], "default": null, "description": "The metric group this metric belongs to." }, "is_reference_free": { "default": true, "description": "Decides whether this metric needs a reference for computation", "title": "Is Reference Free", "type": "boolean" }, "method": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The method used to compute the metric.", "title": "Method" }, "metric_dependencies": { "default": [], "description": "Metrics that needs to be evaluated first", "items": { "$ref": "#/$defs/GenAIMetric" }, "title": "Metric Dependencies", "type": "array" }, "applies_to": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": "message", "description": "The tag to indicate for which the metric is applied to. Used for agentic application metric computation.", "examples": [ "message", "conversation", "sub_agent" ], "title": "Applies to" }, "target_component": { "anyOf": [ { "$ref": "#/$defs/TargetComponent" }, { "type": "null" } ], "default": null, "description": "The specific application component (node) where this metric is computed. Used for agentic application metric computation.", "examples": [ "Retrieval Node", "Context Node", "Generation Node" ], "title": "Target Component" }, "mapping": { "anyOf": [ { "$ref": "#/$defs/Mapping" }, { "type": "null" } ], "default": null, "description": "The data mapping details for the metric which are used to read the values needed to compute the metric.", "examples": { "items": [ { "attribute_name": "traceloop.entity.input", "column_name": null, "json_path": "$.inputs.input_text", "lookup_child_spans": false, "name": "input_text", "span_name": "LangGraph.workflow", "type": "input" }, { "attribute_name": "traceloop.entity.output", "column_name": null, "json_path": "$.outputs.generated_text", "lookup_child_spans": false, "name": "generated_text", "span_name": "LangGraph.workflow", "type": "output" } ], "source": "trace" }, "title": "Mapping" } }, "required": [ "name" ], "title": "GenAIMetric", "type": "object" }, "Mapping": { "description": "Defines the field mapping details to be used for computing a metric.", "properties": { "source": { "default": "trace", "description": "The source type of the data. Use trace if the data should be read from span in trace. Use tabular if the data is passed as a dataframe.", "enum": [ "trace", "tabular" ], "examples": [ "trace", "tabular" ], "title": "Source", "type": "string" }, "items": { "description": "The list of mapping items for the field. They are used to read the data from trace or tabular data for computing the metric.", "items": { "$ref": "#/$defs/MappingItem" }, "title": "Mapping Items", "type": "array" } }, "required": [ "items" ], "title": "Mapping", "type": "object" }, "MappingItem": { "description": "The mapping details to be used for reading the values from the data.", "properties": { "name": { "description": "The name of the item.", "examples": [ "input_text", "generated_text", "context", "ground_truth" ], "title": "Name", "type": "string" }, "type": { "description": "The type of the item.", "enum": [ "input", "output", "reference", "context", "tool_call", "start_time", "end_time", "input_token_count", "output_token_count", "model_usage_details", "status", "user_id", "target_component", "available_tools" ], "examples": [ "input" ], "title": "Type", "type": "string" }, "column_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The column name in the tabular data to be used for reading the field value. Applicable for tabular source.", "title": "Column Name" }, "span_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The span name in the trace data to be used for reading the field value. Applicable for trace source.", "title": "Span Name" }, "attribute_name": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The attribute name in the trace to be used for reading the field value. Applicable for trace source.", "title": "Attribute Name" }, "json_path": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The json path to be used for reading the field value from the attribute value. Applicable for trace source. If not provided, the span attribute value is read as the field value.", "title": "Json Path" }, "lookup_child_spans": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "default": false, "description": "The flag to indicate if all the child spans should be searched for the attribute value. Applicable for trace source.", "title": "Look up child spans" } }, "required": [ "name", "type" ], "title": "MappingItem", "type": "object" }, "MetricGroup": { "enum": [ "retrieval_quality", "answer_quality", "content_safety", "performance", "usage", "message_completion", "tool_call_quality", "readability", "custom" ], "title": "MetricGroup", "type": "string" }, "MetricThreshold": { "description": "The class that defines the threshold for a metric.", "properties": { "type": { "description": "Threshold type. One of 'lower_limit', 'upper_limit'", "enum": [ "lower_limit", "upper_limit" ], "title": "Type", "type": "string" }, "value": { "default": 0, "description": "The value of metric threshold", "title": "Threshold value", "type": "number" } }, "required": [ "type" ], "title": "MetricThreshold", "type": "object" }, "TargetComponent": { "properties": { "type": { "description": "How the component is referenced. By `string` for directly providing the node names or by `mapping` for reading it from span attributes", "enum": [ "string", "mapping" ], "examples": [ "string", "mapping" ], "title": "Type", "type": "string" }, "value": { "anyOf": [ { "type": "string" }, { "$ref": "#/$defs/MappingItem" } ], "description": "The component\u2019s value, either a node name represented as a string, or a MappingItem containing span and attribute details.", "title": "Value" } }, "required": [ "type", "value" ], "title": "TargetComponent", "type": "object" }, "TaskType": { "description": "Supported task types for generative AI models", "enum": [ "question_answering", "classification", "summarization", "generation", "extraction", "retrieval_augmented_generation" ], "title": "TaskType", "type": "string" } } }
- Fields:
group (Annotated[ibm_watsonx_gov.entities.enums.MetricGroup, FieldInfo(annotation=NoneType, required=False, default=
- Validators:
- field display_name: Annotated[Literal['Cost'], FieldInfo(annotation=NoneType, required=False, default='Cost', title='Display Name', description='The cost metric display name.', frozen=True)] = 'Cost'¶
The cost metric display name.
- Validated by:
- field name: Annotated[Literal['cost'], FieldInfo(annotation=NoneType, required=False, default='cost', title='name', description='The cost metric name.', frozen=True)] = 'cost'¶
The cost metric name.
- Validated by:
- field tasks: Annotated[list[TaskType], FieldInfo(annotation=NoneType, required=False, default=['question_answering', 'classification', 'summarization', 'generation', 'extraction', 'retrieval_augmented_generation'], title='Tasks', description='The list of supported tasks.', frozen=True)] = ['question_answering', 'classification', 'summarization', 'generation', 'extraction', 'retrieval_augmented_generation']¶
The list of supported tasks.
- Validated by:
- evaluate(data: DataFrame, configuration: GenAIConfiguration | AgenticAIConfiguration, **kwargs) list[AggregateMetricResult]¶
- model_post_init(context: Any, /) None¶
We need to both initialize private attributes and call the user-defined model_post_init method.
- pydantic model ibm_watsonx_gov.metrics.cost.cost_metric.CostResult¶
Bases:
RecordMetricResultShow JSON schema
{ "title": "CostResult", "type": "object", "properties": { "name": { "default": "cost", "title": "Name", "type": "string" }, "display_name": { "default": "Cost", "title": "Display Name", "type": "string" }, "value_type": { "default": "numeric", "description": "The type of the metric value. Indicates whether the metric value is numeric or categorical.", "examples": [ "numeric", "categorical" ], "title": "Metric value type", "type": "string" }, "method": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The method used to compute this metric result.", "examples": [ "token_recall" ], "title": "Method" }, "provider": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The provider used to compute this metric result.", "title": "Provider" }, "value": { "anyOf": [ { "type": "number" }, { "type": "string" }, { "type": "boolean" }, { "additionalProperties": { "type": "integer" }, "type": "object" }, { "type": "null" } ], "default": null, "description": "The metric value.", "title": "Value" }, "label": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The string equivalent of the metric value. This is used for metrics with categorical value type.", "title": "Label" }, "errors": { "anyOf": [ { "items": { "$ref": "#/$defs/Error" }, "type": "array" }, { "type": "null" } ], "default": null, "description": "The list of error messages", "title": "Errors" }, "additional_info": { "anyOf": [ { "type": "object" }, { "type": "null" } ], "default": null, "description": "The additional information about the metric result.", "title": "Additional Info" }, "explanation": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The explanation about the metric result.", "title": "Explanation" }, "group": { "anyOf": [ { "$ref": "#/$defs/MetricGroup" }, { "type": "null" } ], "default": null, "description": "The metric group", "title": "Group" }, "thresholds": { "default": [], "description": "The metric thresholds", "items": { "$ref": "#/$defs/MetricThreshold" }, "title": "Thresholds", "type": "array" }, "category_classification": { "additionalProperties": { "items": { "type": "string" }, "type": "array" }, "default": {}, "description": "The category classification of the metrics values.", "title": "Category Classification", "type": "object" }, "evidences": { "anyOf": [ { "items": {}, "type": "array" }, { "type": "null" } ], "default": null, "description": "The evidences for the metric result.", "title": "Evidences" }, "record_id": { "description": "The record identifier.", "examples": [ "record1" ], "title": "Record Id", "type": "string" }, "record_timestamp": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "default": null, "description": "The record timestamp.", "examples": [ "2025-01-01T00:00:00.000000Z" ], "title": "Record Timestamp" } }, "$defs": { "Error": { "properties": { "code": { "description": "The error code", "title": "Code", "type": "string" }, "message_en": { "description": "The error message in English.", "title": "Message En", "type": "string" }, "parameters": { "default": [], "description": "The list of parameters to construct the message in a different locale.", "items": {}, "title": "Parameters", "type": "array" } }, "required": [ "code", "message_en" ], "title": "Error", "type": "object" }, "MetricGroup": { "enum": [ "retrieval_quality", "answer_quality", "content_safety", "performance", "usage", "message_completion", "tool_call_quality", "readability", "custom" ], "title": "MetricGroup", "type": "string" }, "MetricThreshold": { "description": "The class that defines the threshold for a metric.", "properties": { "type": { "description": "Threshold type. One of 'lower_limit', 'upper_limit'", "enum": [ "lower_limit", "upper_limit" ], "title": "Type", "type": "string" }, "value": { "default": 0, "description": "The value of metric threshold", "title": "Threshold value", "type": "number" } }, "required": [ "type" ], "title": "MetricThreshold", "type": "object" } }, "required": [ "record_id" ] }
- Config:
arbitrary_types_allowed: bool = True
use_enum_values: bool = True
- Fields:
- field display_name: str = 'Cost'¶
- field name: str = 'cost'¶