- Replace old implementation of PROCESSOR_TYPES and CATALOG_TYPES with the new cached approach

- Add an ordered_list dynamic field type (to be refined)
- Add tabulator javascript library to project

config/processors/globals/AUDIO_PROCESSOR/1.0.0.yaml

@@ -0,0 +1,9 @@
+version: "1.0.0"
+name: "AUDIO Processor"
+file_types: "mp3, mp4, ogg"
+description: "A Processor for audio files"
+configuration: {}
+metadata:
+  author: "System"
+  date_added: "2023-01-01"
+  description: "A Processor for audio files"

config/processors/globals/DOCX_PROCESSOR/1.0.0.yaml

@@ -0,0 +1,59 @@
+version: "1.0.0"
+name: "DOCX Processor"
+file_types: "docx"
+description: "A processor for DOCX 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
+  extract_comments:
+    name: "Extract Comments"
+    type: "boolean"
+    description: "Whether to include document comments in the markdown"
+    required: false
+    default: false
+  extract_headers_footers:
+    name: "Extract Headers/Footers"
+    type: "boolean"
+    description: "Whether to include headers and footers in the markdown"
+    required: false
+    default: false
+  preserve_formatting:
+    name: "Preserve Formatting"
+    type: "boolean"
+    description: "Whether to preserve bold, italic, and other text formatting"
+    required: false
+    default: true
+  list_style:
+    name: "List Style"
+    type: "enum"
+    description: "How to format lists in markdown"
+    required: false
+    default: "dash"
+    allowed_values: ["dash", "asterisk", "plus"]
+  image_handling:
+    name: "Image Handling"
+    type: "enum"
+    description: "How to handle embedded images"
+    required: false
+    default: "skip"
+    allowed_values: ["skip", "extract", "placeholder"]
+  table_alignment:
+    name: "Table Alignment"
+    type: "enum"
+    description: "How to align table contents"
+    required: false
+    default: "left"
+    allowed_values: ["left", "center", "preserve"]
+metadata:
+  author: "System"
+  date_added: "2023-01-01"
+  description: "A processor for DOCX files"

config/processors/globals/HTML_PROCESSOR/1.0.0.yaml

@@ -0,0 +1,49 @@
+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"

config/processors/globals/MARKDOWN_PROCESSOR/1.0.0.yaml

@@ -0,0 +1,20 @@
+version: "1.0.0"
+name: "Markdown Processor"
+file_types: "md"
+description: "A Processor for markdown 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
+metadata:
+  author: "System"
+  date_added: "2023-01-01"
+  description: "A Processor for markdown files"

config/processors/globals/PDF_PROCESSOR/1.0.0.yaml

@@ -0,0 +1,20 @@
+version: "1.0.0"
+name: "PDF Processor"
+file_types: "pdf"
+description: "A Processor for PDF 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
+metadata:
+  author: "System"
+  date_added: "2023-01-01"
+  description: "A Processor for PDF files"