Scores the linkage between input and output based on specified criteria. This evaluation ensures that the output is appropriately aligned with the input and context, adhering to the defined evaluation criteria. A high score indicates strong alignment between the input and output, while a low score suggests discrepancies or misalignment.
Click here to learn how to setup evaluation using the Python SDK.
Input Type | Parameter | Type | Description |
---|---|---|---|
Required Inputs | output | string | The output generated by the model. |
Optional Inputs | context | string | The context provided to the model. |
input | string | The input provided to the model. | |
Configuration Parameters | criteria | string | The evaluation criteria. |
check_internet | bool | Whether to check internet for evaluation based on the criteria. |
Output | Type | Description |
---|---|---|
Score | float | Returns a score between 0 and 1, where higher values indicate better alignment based on criteria. |