Document Generator

ydata.synthesizers.text.model.document.DocumentFormat

Bases: Enum

Enum representing supported output formats for synthetic document generation.

Attributes:

Name	Type	Description
DOCX		Microsoft Word document format (docx)
PDF		Portable Document Format (pdf)
HTML		HyperText Markup Language format (html)

ydata.synthesizers.text.model.document.DocumentGenerator

Bases: BaseGenerator

A class for generating synthetic documents in various formats (DOCX, PDF, HTML) based on input specifications.

Features

• Support for multiple document formats (DOCX, PDF, HTML)
• Configurable LLM selection
• Template-based document generation
• Customizable document structure and styling
• Batch processing of multiple document specifications

Parameters:

Name	Type	Description	Default
api_key	str	API key for the LLM provider	required
provider	Union[LLMProvider, str]	The LLM provider to use	OPENAI
model_name	Optional[Union[OpenAIModel, AnthropicModel, str]]	Specific model to use	GPT_4
default_format	DocumentFormat	Default output format if not specified in request	required

generate(document_type=None, n_docs=1, audience=None, tone=None, purpose=None, region=None, language=None, length=None, topics=None, style_guide=None, output_dir=None, **kwargs)

Generate documents based on input specifications.

Parameters:

Name	Type	Description	Default
document_type	str	Type of document to generate	None
audience	str	Target audience for the document	None
tone	str	Desired tone of the document. Can be selected from the following limited list of values formal, casual, persuasive, empathetic, inspirational, enthusiastic, humorous, neutral.	None
purpose	str	Purpose of the document	None
region	str	Target region/locale	None
language	str	Language of the document	None
length	str	Desired length of the document	None
topics	str	Key points to cover	None
style_guide	str	Style guide to follow	None
output_dir	str	Directory to store generated documents	None
**kwargs		Additional arguments to pass to the generation process	{}

Raises:

Type	Description
ValueError	If input validation fails or document format is unsupported