pyapp_docling

README

Docling

Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.

https://github.com/docling-project/docling

Documentation

Index

• type Docling
  • func NewDocling(venv pyvenv_commons.IVenv) (instance *Docling)
  • func (instance *Docling) Environment() (response []string)
  • func (instance *Docling) InitializeAll() (response []string, err error)
  • func (instance *Docling) Install() (response string, err error)
  • func (instance *Docling) IsInstalled() (response bool)
  • func (instance *Docling) PrefetchAll() (response string, err error)
  • func (instance *Docling) To(source string, outFormat string, options ...string) (response string, err error)
  • func (instance *Docling) ToMarkdown(source string, options ...string) (response string, err error)

Types

type Docling

type Docling struct {
	// contains filtered or unexported fields
}

Docling represents an abstraction for managing the "Docling" application within a Python virtual environment. Convert for: docx | pptx | html | image | pdf | asciidoc | md | csv | xlsx | xml_uspto | xml_jats | json_docling To: md | json | html | text | doctags https://ds4sd.github.io/docling/reference/cli/

func NewDocling

func NewDocling(venv pyvenv_commons.IVenv) (instance *Docling)

NewDocling creates and initializes a new Docling instance with the provided Python virtual environment.

func (*Docling) Environment

func (instance *Docling) Environment() (response []string)

func (*Docling) InitializeAll

func (instance *Docling) InitializeAll() (response []string, err error)

InitializeAll initializes the Docling application by checking its installation and installing if necessary.

func (*Docling) Install

func (instance *Docling) Install() (response string, err error)

Install installs the "docling" package within the Python virtual environment using pip. Returns the response and error. https://ds4sd.github.io/docling/installation/

func (*Docling) IsInstalled

func (instance *Docling) IsInstalled() (response bool)

IsInstalled checks if the "docling" application is installed in the Python virtual environment.

func (*Docling) PrefetchAll

func (instance *Docling) PrefetchAll() (response string, err error)

PrefetchAll downloads all available models for the "Docling" application using the "docling-tools models download" command. Returns the command response or an error if the operation fails or the application is not installed. https://docling-project.github.io/docling/usage/#advanced-options

func (*Docling) To

func (instance *Docling) To(source string, outFormat string, options ...string) (response string, err error)

To converts a given source file to a specified output format using the "Docling" application. Returns the result or an error. Sample Usage: To("md", "--image-export-mode", "placeholder") // remove images

func (*Docling) ToMarkdown

func (instance *Docling) ToMarkdown(source string, options ...string) (response string, err error)

ToMarkdown converts a given source file into a Markdown file using the "Docling" application and returns the content. Returns an error if the source file doesn't exist or if the "Docling" application is not installed.