Ask a question to get started
Enter to send•Shift+Enter new line
StringEvaluator()
RunEvaluator
BaseModel
Evaluate a run asynchronously.
The name evaluation, such as 'Accuracy' or 'Salience'.
'Accuracy'
'Salience'
The key in the run inputs to extract the input string.
The key in the run outputs to extra the prediction string.
The key in the example outputs the answer string.
Function that grades the run output against the example output.
Evaluate a single run.
Grades the run's string input, output, and optional answer.
.. deprecated:: 0.5.0
StringEvaluator is deprecated. Use openevals instead: https://github.com/langchain-ai/openevals
