explodinggradients / ragas

Supercharge Your LLM Application Evaluations 🚀
https://docs.ragas.io
Apache License 2.0
7.3k stars 745 forks source link

failed to parse the output #1630

Open amin-kh96 opened 2 weeks ago

amin-kh96 commented 2 weeks ago

@shawnmittal @shahules786 @jannikmaierhoefer @jjmachan

In ragas version 0.1.6 how can I fix the error : Failed to parse output: Answer not found in new_ragas_dataset.. Returning None. Failed to parse output: Answer not found in new_ragas_dataset.. Returning None. Failed to parse output: Answer not found in new_ragas_dataset.. Returning None. Failed to parse output: Answer not found in new_ragas_dataset.. Returning None. Evaluating: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:01<00:00, 2.44it/s] c:\Users\Amin\git\ragas-prototype.venv\Lib\site-packages\ragas\evaluation.py:277: RuntimeWarning: Mean of empty slice value = np.nanmean(self.scores[cn]) RAGAS Evaluation Report: {'context_utilization': nan}

I checked and the answer exist in my dataset. i used this code also:

new_ragas_dataset = Dataset.from_list(new_ragas_dataset)