gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

downloading example repo for eval

Browse source
This commit is contained in:
Rita Aleksziev 2024-11-12 17:40:42 +01:00
parent 96358bba19
commit aa95aa21af
1 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
evals/eval_on_swe_bench.py → evals/deepeval_on_swe_bench.py
View file

@ -160,8 +160,8 @@ if __name__ == "__main__":
# run_cognify_base_rag_and_search() # run_cognify_base_rag_and_search()
# # Data preprocessing before setting the dataset test cases # # Data preprocessing before setting the dataset test cases
swe_dataset = load_swebench_dataset('princeton-nlp/SWE-bench_bm25_13K', split='test') swe_dataset = load_swebench_dataset('princeton-nlp/SWE-bench_bm25_13K', split='test')
test_dataset = convert_swe_to_deepeval_testcases(dataset.test_cases) test_dataset = convert_swe_to_deepeval_testcases(swe_dataset)
from deepeval.metrics import HallucinationMetric from deepeval.metrics import HallucinationMetric
metric = HallucinationMetric() metric = HallucinationMetric()
evalresult = dataset.evaluate([metric]) evalresult = test_dataset.evaluate([metric])
pass pass