You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[ ] I checked the documentation and related resources and couldn't find an answer to my question.
what is the difference between the retrieved contexts and reference contexts that extract from generate Synthetic test data?
The text was updated successfully, but these errors were encountered:
The difference between retrieved contexts and reference contexts in the context of generating synthetic test data is as follows:
Retrieved Contexts: These are the contexts that the system retrieves for a given query. They represent the information identified as relevant to the user's input query. In the SingleTurnSample class, this is represented by the attribute retrieved_contexts, which is a list of strings.
Reference Contexts: These are the contexts considered as the correct or expected ones for a given query. They serve as a benchmark or ground truth against which the retrieved contexts can be evaluated. In the SingleTurnSample class, this is represented by the attribute reference_contexts, which is also a list of strings.
The key difference lies in their roles: retrieved contexts are what the system actually retrieves, while reference contexts are what ideally should have been retrieved [1].
[ ] I checked the documentation and related resources and couldn't find an answer to my question.
what is the difference between the retrieved contexts and reference contexts that extract from generate Synthetic test data?
The text was updated successfully, but these errors were encountered: