DSPy: The framework for programming—not prompting—language models
Python
Update BootstrapFewShotWithRandomSearch.md
arnavsinghvi110c31cf835cdd
diff --git a/docs/api/optimizers/BootstrapFewShotWithRandomSearch.md b/docs/api/optimizers/BootstrapFewShotWithRandomSearch.mdindex 1a36af2a8..7b5897465 100644--- a/docs/api/optimizers/BootstrapFewShotWithRandomSearch.md+++ b/docs/api/optimizers/BootstrapFewShotWithRandomSearch.md@@ -10,15 +10,16 @@ The constructor initializes the `BootstrapFewShotWithRandomSearch` class and set```pythonclass BootstrapFewShotWithRandomSearch(BootstrapFewShot):- def __init__(self, metric, teacher_settings={}, max_bootstrapped_demos=4, max_labeled_demos=16, max_rounds=1, num_candidate_programs=16, num_threads=6):+ def __init__(self, metric, teacher_settings={}, max_bootstrapped_demos=4, max_labeled_demos=16, max_rounds=1, num_candidate_programs=16, num_threads=6, max_errors=10, stop_at_score=None, metric_threshold=None):self.metric = metricself.teacher_settings = teacher_settingsself.max_rounds = max_rounds-self.num_threads = num_threads-+ self.stop_at_score = stop_at_score+ self.metric_threshold = metric_thresholdself.min_num_samples = 1self.max_num_samples = max_bootstrapped_demos+ self.max_errors = max_errorsself.num_candidate_sets = num_candidate_programsself.max_num_traces = 1 + int(max_bootstrapped_demos / 2.0 * self.num_candidate_sets)@@ -32,12 +33,15 @@ class BootstrapFewShotWithRandomSearch(BootstrapFewShot):**Parameters:**- `metric` (_callable_, _optional_): Metric function to evaluate examples during bootstrapping. Defaults to `None`.-- `teacher_settings` (_dict_, _optional_): Settings for teacher predictor. Defaults to empty dictionary.+- `teacher_settings` (_dict_, _optional_): Settings for teacher predictor. Defaults to an empty dictionary.- `max_bootstrapped_demos` (_int_, _optional_): Maximum number of bootstrapped demonstrations per predictor. Defaults to 4.- `max_labeled_demos` (_int_, _optional_): Maximum number of labeled demonstrations per predictor. Defaults to 16.- `max_rounds` (_int_, _optional_): Maximum number of bootstrapping rounds. Defaults to 1.-- `num_candidate_programs` (_int_): Number of candidate programs to generate during random search.-- `num_threads` (_int_): Number of threads used for evaluation during random search.+- `num_candidate_programs` (_int_): Number of candidate programs to generate during random search. Defaults to 16.+- `num_threads` (_int_): Number of threads used for evaluation during random search. Defaults to 6.+- `max_errors` (_int_): Maximum errors permitted during evaluation. Halts run with the latest error message. Defaults to 10. Configure to 1 if no evaluation run error is desired.+- `stop_at_score` (_float_, _optional_): Score threshold for random search to stop early. Defaults to `None`.+- `metric_threshold` (_float_, _optional_): Score threshold for metric to determine successful example. Defaults to `None`.### Method@@ -56,4 +60,4 @@ teleprompter = BootstrapFewShotWithRandomSearch(teacher_settings=dict({'lm': tea# Compile!compiled_rag = teleprompter.compile(student=RAG(), trainset=trainset)-```\ No newline at end of file+```