Open sahanHe opened 7 months ago
Description: As a part of the development of AI model, there should be a robust evaluation mechanism to test and benchmark each algorithm/prompt to find the best one.
As we are developing a language components, failures can be either data mapping failures or compilation failures. The Evaluation mechanism should be robust in all of these scenarios related to: https://github.com/ballerina-platform/ballerina-library/issues/5957
Evaluation framework implementation is completed and issue will be closed after adding to the ballerina platform
Description: As a part of the development of AI model, there should be a robust evaluation mechanism to test and benchmark each algorithm/prompt to find the best one.
As we are developing a language components, failures can be either data mapping failures or compilation failures. The Evaluation mechanism should be robust in all of these scenarios related to: https://github.com/ballerina-platform/ballerina-library/issues/5957