version: "1.0.0"
name: "HTML Processor"
file_types: "html"
description: "A processor for HTML files"
configuration:
chunking_patterns:
name: "Chunking Patterns"
description: "A list of Patterns used to chunk files into logical pieces"
type: "chunking_patterns"
required: false
chunking_heading_level:
name: "Chunking Heading Level"
type: "integer"
description: "Maximum heading level to consider for chunking (1-6)"
required: false
default: 2
html_tags:
name: "HTML Tags"
type: "string"
description: "A comma-separated list of HTML tags"
required: true
default: "p, h1, h2, h3, h4, h5, h6, li, table, thead, tbody, tr, td"
html_end_tags:
name: "HTML End Tags"
type: "string"
description: "A comma-separated list of HTML end tags (where can the chunk end)"
required: true
default: "p, li, table"
html_included_elements:
name: "HTML Included Elements"
type: "string"
description: "A comma-separated list of elements to be included"
required: true
default: "article, main"
html_excluded_elements:
name: "HTML Excluded Elements"
type: "string"
description: "A comma-separated list of elements to be excluded"
required: false
default: "header, footer, nav, script"
html_excluded_classes:
name: "HTML Excluded Classes"
type: "string"
description: "A comma-separated list of classes to be excluded"
required: false
metadata:
author: "System"
date_added: "2023-01-01"
description: "A processor for HTML files"