tskwvr / auto_eval /cases /execution_stateful.yaml
TRaw's picture
Upload 297 files
3d3d712
version: 0.1
config_var: null
app_dir: ../project/
eval_query:
- user_query: show the column names of ../../../../sample_data/demo_data.csv
scoring_points:
- score_point: "The column names are TimeBucket and Count"
weight: 1
post_index: -1
- user_query: generate 10 random numbers
scoring_points:
- score_point: "Agent should generate 10 random numbers and reply to user"
weight: 1
post_index: -1
- user_query: get the mean value of 'Count' column in the loaded data
scoring_points:
- score_point: "The correct mean value is 78172.75"
weight: 1
post_index: -1