pyrit.models.SeedPromptDataset

class SeedPromptDataset(*, prompts: Sequence[Dict[str, Any]] | Sequence[SeedPrompt] = None, data_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'error'] | None = 'text', name: str | None = None, dataset_name: str | None = None, harm_categories: Sequence[str] | None = None, description: str | None = None, authors: Sequence[str] | None = None, groups: Sequence[str] | None = None, source: str | None = None, date_added: datetime | None = None, added_by: str | None = None)

Bases: YamlLoadable

SeedPromptDataset manages seed prompts plus optional top-level defaults. Prompts are stored as a Sequence[SeedPrompt], so references to prompt properties are straightforward (e.g. ds.prompts[0].value).

__init__(*, prompts: Sequence[Dict[str, Any]] | Sequence[SeedPrompt] = None, data_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'error'] | None = 'text', name: str | None = None, dataset_name: str | None = None, harm_categories: Sequence[str] | None = None, description: str | None = None, authors: Sequence[str] | None = None, groups: Sequence[str] | None = None, source: str | None = None, date_added: datetime | None = None, added_by: str | None = None)

Initialize the dataset. Typically, you’ll call from_dict or from_yaml_file so that top-level defaults are merged into each prompt. If you’re passing prompts directly, they can be either a list of SeedPrompt objects or prompt dictionaries (which then get converted to SeedPrompt objects).

Methods

__init__(*[, prompts, data_type, name, ...])	Initialize the dataset.
from_dict(data)	Builds a SeedPromptDataset by merging top-level defaults into each item in 'prompts'.
from_yaml_file(file)	Creates a new object from a YAML file.
get_values([first, last])	Extracts and returns a list of prompt values from the dataset.
group_seed_prompts_by_prompt_group_id(...)	Groups the given list of SeedPrompts by their prompt_group_id and creates SeedPromptGroup instances.
render_template_value(**kwargs)	Renders self.value as a template, applying provided parameters in kwargs

Attributes

data_type
name
dataset_name
harm_categories
description
authors
groups
source
date_added
added_by
prompts

added_by: str | None

authors: Sequence[str] | None

data_type: str | None

dataset_name: str | None

date_added: datetime | None

description: str | None

classmethod from_dict(data: Dict[str, Any]) → SeedPromptDataset

Builds a SeedPromptDataset by merging top-level defaults into each item in ‘prompts’.

get_values(first: Annotated[int, Gt(gt=0)] | None = None, last: Annotated[int, Gt(gt=0)] | None = None) → Sequence[str]

Extracts and returns a list of prompt values from the dataset. By default, returns all of them.

Parameters:

• first (Optional[int]) – If provided, values from the first N prompts are included.

• last (Optional[int]) – If provided, values from the last N prompts are included.

Returns:

A list of prompt values.

Return type:

Sequence[str]

static group_seed_prompts_by_prompt_group_id(seed_prompts: Sequence[SeedPrompt]) → Sequence[SeedPromptGroup]

Groups the given list of SeedPrompts by their prompt_group_id and creates SeedPromptGroup instances.

Parameters:

seed_prompts – A list of SeedPrompt objects.

Returns:

A list of SeedPromptGroup objects, with prompts grouped by prompt_group_id.

groups: Sequence[str] | None

harm_categories: Sequence[str] | None

name: str | None

prompts: Sequence[SeedPrompt]

render_template_value(**kwargs)

Renders self.value as a template, applying provided parameters in kwargs

Parameters:

kwargs – Key-value pairs to replace in the SeedPromptDataset value.

Returns:

None

Raises:

ValueError – If parameters are missing or invalid in the template.

source: str | None