autointent.generation.utterances.IncrementalUtteranceEvolver#
- class autointent.generation.utterances.IncrementalUtteranceEvolver(generator, prompt_makers, seed=0, async_mode=False, search_space=None)#
Bases:
autointent.generation.utterances._evolution.evolver.UtteranceEvolverIncremental evolutionary strategy to augmenting utterances.
This method adds LLM-generated training samples until the quality of linear classification on resulting dataset stops rising.
- Parameters:
generator (autointent.generation.Generator) – Generator instance for generating utterances.
prompt_makers (collections.abc.Sequence[autointent.generation.chat_templates.EvolutionChatTemplate]) – List of prompt makers for generating prompts.
seed (int) – Random seed for reproducibility.
async_mode (bool) – Whether to use asynchronous mode for generation.
search_space (str | None) – Search space for the pipeline optimizer.
- search_space#
- augment(dataset, split_name=Split.TRAIN, n_evolutions=1, update_split=True, batch_size=4, sequential=False)#
Add LLM-generated samples to some split of dataset.
- Parameters:
dataset (autointent.Dataset) – Dataset object.
split_name (str) – Dataset split (default is TRAIN).
n_evolutions (int) – Number of evolutions to perform.
update_split (bool) – Whether to update the dataset split with the new samples.
batch_size (int) – Batch size for augmentation.
sequential (bool) – Whether to perform augmentations sequentially.
- Return type: