Class: Langchain::Processors::Docx

Inherits:

Base

• Object
• Base
• Langchain::Processors::Docx

Defined in:

lib/langchain/processors/docx.rb

Constant Summary

EXTENSIONS =

[".docx"]

CONTENT_TYPES =

["application/vnd.openxmlformats-officedocument.wordprocessingml.document"]

Instance Method Summary

• #initialize ⇒ Docx constructor

  A new instance of Docx.

• #parse(data) ⇒ String

  Parse the document and return the text.

Methods included from DependencyHelper

#depends_on

Constructor Details

#initialize ⇒ Docx

Returns a new instance of Docx.

# File 'lib/langchain/processors/docx.rb', line 9

def initialize(*)
  depends_on "docx"
end

Instance Method Details

#parse(data) ⇒ String

Parse the document and return the text

Parameters:

• data (File)

Returns:

• (String)

# File 'lib/langchain/processors/docx.rb', line 16

def parse(data)
  ::Docx::Document
    .open(StringIO.new(data.read))
    .text
end