/AWS1/CL_BDOLLMASAJUDGEEVALU00¶
The configuration for LLM-as-a-Judge evaluation that uses a language model to assess agent performance based on custom instructions and rating scales.
CONSTRUCTOR¶
IMPORTING¶
Required arguments:¶
iv_instructions TYPE /AWS1/BDOEVALUATORINSTRUCTIONS /AWS1/BDOEVALUATORINSTRUCTIONS¶
The evaluation instructions that guide the language model in assessing agent performance, including criteria and evaluation guidelines.
io_ratingscale TYPE REF TO /AWS1/CL_BDORATINGSCALE /AWS1/CL_BDORATINGSCALE¶
The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.
io_modelconfig TYPE REF TO /AWS1/CL_BDOEVALUATORMODELCFG /AWS1/CL_BDOEVALUATORMODELCFG¶
The model configuration that specifies which foundation model to use and how to configure it for evaluation.
Queryable Attributes¶
instructions¶
The evaluation instructions that guide the language model in assessing agent performance, including criteria and evaluation guidelines.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_INSTRUCTIONS() |
Getter for INSTRUCTIONS, with configurable default |
ASK_INSTRUCTIONS() |
Getter for INSTRUCTIONS w/ exceptions if field has no value |
HAS_INSTRUCTIONS() |
Determine if INSTRUCTIONS has a value |
ratingScale¶
The rating scale that defines how the evaluator should score agent performance, either numerical or categorical.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_RATINGSCALE() |
Getter for RATINGSCALE |
modelConfig¶
The model configuration that specifies which foundation model to use and how to configure it for evaluation.
Accessible with the following methods¶
| Method | Description |
|---|---|
GET_MODELCONFIG() |
Getter for MODELCONFIG |