forked from phoenix-oss/llama-stack-mirror
[Evals API][3/n] scoring_functions / scoring meta-reference implementations (#296)
* wip * dataset validation * test_scoring * cleanup * clean up test * comments * error checking * dataset client * test client: * datasetio client * clean up * basic scoring function works * scorer wip * equality scorer * score batch impl * score batch * update scoring test * refactor * validate scorer input * address comments * add all rows scores to ScoringResult * bugfix * scoring function def rename
This commit is contained in:
parent
e70420a06e
commit
cb84034567
28 changed files with 904 additions and 51 deletions
6
llama_stack/providers/tests/datasetio/test_dataset.csv
Normal file
6
llama_stack/providers/tests/datasetio/test_dataset.csv
Normal file
|
@ -0,0 +1,6 @@
|
|||
input_query,generated_answer,expected_answer
|
||||
What is the capital of France?,London,Paris
|
||||
Who is the CEO of Meta?,Mark Zuckerberg,Mark Zuckerberg
|
||||
What is the largest planet in our solar system?,Jupiter,Jupiter
|
||||
What is the smallest country in the world?,China,Vatican City
|
||||
What is the currency of Japan?,Yen,Yen
|
|
Loading…
Add table
Add a link
Reference in a new issue