Evaluates whether the provided context is sufficient and relevant to answer the given input query. This evaluation is crucial for RAG systems to ensure that retrieved context pieces contain the necessary information to generate accurate responses.
Click here to learn how to setup evaluation using the Python SDK.Input:
string
- The context column provided to the modelstring
- The input column provided to the modelbool
- True/False (Whether to check the internet for relevant information)float
- Returns score between 0 and 1