@spec _bootstrap(
  SnakeBridge.Ref.t(),
  keyword()
) :: {:ok, term()} | {:error, Snakepit.Error.t()}

Python method BootstrapFewShot._bootstrap.

Parameters

• max_bootstraps (term() keyword-only default: None)

Returns

• term()

@spec _bootstrap_one_example(SnakeBridge.Ref.t(), term(), [term()], keyword()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

Python method BootstrapFewShot._bootstrap_one_example.

Parameters

• example (term())
• round_idx (term() default: 0)

Returns

• term()

@spec _prepare_predictor_mappings(
  SnakeBridge.Ref.t(),
  keyword()
) :: {:ok, term()} | {:error, Snakepit.Error.t()}

Python method BootstrapFewShot._prepare_predictor_mappings.

Returns

• term()

@spec _prepare_student_and_teacher(SnakeBridge.Ref.t(), term(), term(), keyword()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

Python method BootstrapFewShot._prepare_student_and_teacher.

Parameters

• student (term())
• teacher (term())

Returns

• term()

@spec _train(
  SnakeBridge.Ref.t(),
  keyword()
) :: {:ok, term()} | {:error, Snakepit.Error.t()}

Python method BootstrapFewShot._train.

Returns

• term()

@spec compile(SnakeBridge.Ref.t(), term(), keyword()) ::
  {:ok, term()} | {:error, Snakepit.Error.t()}

Optimize the student program.

Parameters

• student - The student program to optimize.
• trainset - The training set to use for optimization.
• teacher - The teacher program to use for optimization.
• valset - The validation set to use for optimization.

Returns

• term()

@spec get_params(
  SnakeBridge.Ref.t(),
  keyword()
) :: {:ok, %{optional(String.t()) => term()}} | {:error, Snakepit.Error.t()}

Get the parameters of the teleprompter.

Returns

• %{optional(String.t()) => term()}

@spec new(
  [term()],
  keyword()
) :: {:ok, SnakeBridge.Ref.t()} | {:error, Snakepit.Error.t()}

A Teleprompter class that composes a set of demos/examples to go into a predictor's prompt.

These demos come from a combination of labeled examples in the training set, and bootstrapped demos.

Each bootstrap round copies the LM with a new rollout_id at temperature=1.0 to bypass caches and gather diverse traces.

Parameters

• metric - A function that compares an expected value and predicted value, outputting the result of that comparison. (type: Callable)
• metric_threshold - If the metric yields a numerical value, then check it against this threshold when deciding whether or not to accept a bootstrap example. Defaults to None. (type: float())
• teacher_settings - Settings for the teacher model. Defaults to None. (type: map())
• max_bootstrapped_demos - Maximum number of bootstrapped demonstrations to include. Defaults to 4. (type: integer())
• max_labeled_demos - Maximum number of labeled demonstrations to include. Defaults to 16. (type: integer())
• max_rounds - Number of iterations to attempt generating the required bootstrap examples. If unsuccessful after max_rounds, the program ends. Defaults to 1. (type: integer())

• max_errors - Maximum number of errors until program ends. If None, inherits from dspy.settings.max_errors. (type: integer() | nil)