Package com.logicaldoc.ai.tools

Class ParagraphsPreparer

java.lang.Object

com.logicaldoc.ai.tools.ParagraphsPreparer

public class ParagraphsPreparer
extends Object

Generates a file with a specified amount of paragraphs, taken from a list of sample documents. Useful for preparing contents to train embedder models. It accepts 3 arguments:

1. samples folder path (it must contains .txt files and subfolders)
2. output file path
3. number of paragraphs in the output

Since:

9.2.2

Author:

Giuseppe Desiato - LogicalDOC

Constructor Summary

Constructors

Constructor	Description
ParagraphsPreparer(File samplesFolder, File output, long totalParagraphs)

Method Summary

Modifier and Type	Method	Description
void	generate()
File	getOutput()
static void	main(String[] args)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

ParagraphsPreparer

public ParagraphsPreparer(File samplesFolder,
 File output,
 long totalParagraphs)

Method Details

main

public static void main(String[] args)

generate

public void generate()

getOutput

public File getOutput()