Type: nodetool.document.SplitHTML
Namespace: nodetool.document
Description
Split HTML content into semantic chunks based on HTML tags. html, text, semantic, tags, parsing
Properties
| Property | Type | Description | Default |
|---|---|---|---|
| document | document |
Document ID to associate with the HTML content | {'type': 'document', 'uri': '', 'asset_id': None, 'data': None} |
Outputs
| Output | Type | Description |
|---|---|---|
| text | str |
|
| source_id | str |
|
| start_index | int |
Metadata
Related Nodes
Browse other nodes in the nodetool.document namespace.