pyrit.models.SeedPrompt

class SeedPrompt(value: str, value_sha256: str | None = None, data_type: ~typing.Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'error'] | None = None, id: ~uuid.UUID | None = <factory>, name: str | None = None, dataset_name: str | None = None, harm_categories: ~typing.Sequence[str] | None = <factory>, description: str | None = None, authors: ~typing.Sequence[str] | None = <factory>, groups: ~typing.Sequence[str] | None = <factory>, source: str | None = None, date_added: ~datetime.datetime | None = <factory>, added_by: str | None = None, metadata: ~typing.Dict[str, str | int] | None = <factory>, parameters: ~typing.Sequence[str] | None = <factory>, prompt_group_id: ~uuid.UUID | None = None, prompt_group_alias: str | None = None, sequence: int | None = 0)

Bases: YamlLoadable

Represents a seed prompt with various attributes and metadata.

__init__(value: str, value_sha256: str | None = None, data_type: ~typing.Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'error'] | None = None, id: ~uuid.UUID | None = <factory>, name: str | None = None, dataset_name: str | None = None, harm_categories: ~typing.Sequence[str] | None = <factory>, description: str | None = None, authors: ~typing.Sequence[str] | None = <factory>, groups: ~typing.Sequence[str] | None = <factory>, source: str | None = None, date_added: ~datetime.datetime | None = <factory>, added_by: str | None = None, metadata: ~typing.Dict[str, str | int] | None = <factory>, parameters: ~typing.Sequence[str] | None = <factory>, prompt_group_id: ~uuid.UUID | None = None, prompt_group_alias: str | None = None, sequence: int | None = 0) → None

Methods

__init__(value[, value_sha256, data_type, ...])
from_yaml_file(file)	Creates a new object from a YAML file.
from_yaml_with_required_parameters(...[, ...])	Load a SeedPrompt from a YAML file and validate that it contains specific parameters.
render_template_value(**kwargs)	Renders self.value as a template, applying provided parameters in kwargs
render_template_value_silent(**kwargs)	Renders self.value as a template, applying provided parameters in kwargs. For parameters in the template
set_encoding_metadata()	This method sets the encoding data for the prompt within metadata dictionary.
set_sha256_value_async()	This method computes the SHA256 hash value asynchronously.

Attributes

TEMPLATE_PATHS
added_by
data_type
dataset_name
description
name
prompt_group_alias
prompt_group_id
sequence
source
value_sha256
value
id
harm_categories
authors
groups
date_added
metadata
parameters

TEMPLATE_PATHS = {'datasets_path': PosixPath('/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/site-packages/pyrit/datasets'), 'db_data_path': PosixPath('/home/runner/.local/share/dbdata'), 'docs_code_path': PosixPath('/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/site-packages/doc/code'), 'log_path': PosixPath('/home/runner/.local/share/dbdata/logs.txt'), 'pyrit_home_path': PosixPath('/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/site-packages'), 'pyrit_path': PosixPath('/opt/hostedtoolcache/Python/3.11.13/x64/lib/python3.11/site-packages/pyrit')}

added_by: str | None = None

authors: Sequence[str] | None

data_type: Literal['text', 'image_path', 'audio_path', 'video_path', 'url', 'error'] | None = None

dataset_name: str | None = None

date_added: datetime | None

description: str | None = None

classmethod from_yaml_with_required_parameters(template_path: str | Path, required_parameters: list[str], error_message: str | None = None) → SeedPrompt

Load a SeedPrompt from a YAML file and validate that it contains specific parameters.

Parameters:

• template_path – Path to the YAML file containing the template.

• required_parameters – List of parameter names that must exist in the template.

• error_message – Custom error message if validation fails. If None, a default message is used.

Returns:

The loaded and validated seed prompt.

Return type:

SeedPrompt

Raises:

ValueError – If the template doesn’t contain all required parameters.

groups: Sequence[str] | None

harm_categories: Sequence[str] | None

id: UUID | None

metadata: Dict[str, str | int] | None

name: str | None = None

parameters: Sequence[str] | None

prompt_group_alias: str | None = None

prompt_group_id: UUID | None = None

render_template_value(**kwargs) → str

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

Parameters:

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

Returns:

A new prompt with the parameters applied.

Raises:

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

render_template_value_silent(**kwargs) → str

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

that are not provided as kwargs here, this function will leave them as is instead of raising an error.

Parameters:

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

Returns:

A new prompt with the parameters applied.

Raises:

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

sequence: int | None = 0

set_encoding_metadata()

This method sets the encoding data for the prompt within metadata dictionary. For images, this is just the file format. For audio and video, this also includes bitrate (kBits/s as int), samplerate (samples/second as int), bitdepth (as int), filesize (bytes as int), and duration (seconds as int) if the file type is supported by TinyTag. Example suppported file types include: MP3, MP4, M4A, and WAV.

async set_sha256_value_async()

This method computes the SHA256 hash value asynchronously. It should be called after prompt value is serialized to text, as file paths used in the value may have changed from local to memory storage paths.

Note, this method is async due to the blob retrieval. And because of that, we opted to take it out of main and setter functions. The disadvantage is that it must be explicitly called.

source: str | None = None

value: str

value_sha256: str | None = None