defog-ai / sql-eval

Evaluate the accuracy of LLM generated outputs
Apache License 2.0
485 stars 52 forks source link

New nb for automated error analysis #133

Closed wendy-aw closed 2 months ago

wendy-aw commented 2 months ago

Added a new notebook for generating summaries of db exec errors and logical errors found in result files of a single train dataset. These summaries provide users with a better understanding of the areas in which the training dataset can be improved.