2025-10-14 21:29:42 +08:00
{
"id" : 25 ,
"title" : {
"en" : "Title Chunker" ,
2025-10-30 03:56:28 +01:00
"de" : "Titel basierte Segmentierung" ,
2025-10-14 21:29:42 +08:00
"zh" : "标题切片"
} ,
"description" : {
"en" : "This template slices the parsed file based on its title structure. It is ideal for documents with well-defined headings, such as product manuals, legal contracts, research reports, and academic papers." ,
2025-10-30 03:56:28 +01:00
"de" : "Diese Vorlage segmentiert die geparste Datei basierend auf ihrer Titelstruktur. Sie eignet sich ideal für Dokumente mit klar definierten Überschriften, wie Produkthandbücher, Verträge, Forschungsberichte und wissenschaftliche Arbeiten." ,
2025-10-14 21:29:42 +08:00
"zh" : "此模板将解析后的文件按标题结构进行切片，适用于具有清晰标题层级的文档类型，如产品手册、合同法规、研究报告和学术论文等。"
} ,
"canvas_type" : "Ingestion Pipeline" ,
"canvas_category" : "dataflow_canvas" ,
"dsl" : {
"components" : {
"File" : {
"obj" : {
"component_name" : "File" ,
"params" : { }
} ,
"downstream" : [
"Parser:HipSignsRhyme"
] ,
"upstream" : [ ]
} ,
"Parser:HipSignsRhyme" : {
"obj" : {
"component_name" : "Parser" ,
"params" : {
"outputs" : {
"html" : {
"type" : "string" ,
"value" : ""
} ,
"json" : {
"type" : "Array<object>" ,
"value" : [ ]
} ,
"markdown" : {
"type" : "string" ,
"value" : ""
} ,
"text" : {
"type" : "string" ,
"value" : ""
}
} ,
"setups" : {
"pdf" : {
"output_format" : "json" ,
"suffix" : [
"pdf"
] ,
"parse_method" : "DeepDOC"
} ,
"text&markdown" : {
"output_format" : "text" ,
"suffix" : [
"md" ,
"markdown" ,
"mdx" ,
"txt"
]
} ,
"word" : {
"output_format" : "json" ,
"suffix" : [
"doc" ,
"docx"
]
}
}
}
} ,
"downstream" : [
"HierarchicalMerger:BusyPoetsSearch"
] ,
"upstream" : [
"File"
]
} ,
"Tokenizer:NeatRadiosEnd" : {
"obj" : {
"component_name" : "Tokenizer" ,
"params" : {
"fields" : "text" ,
"filename_embd_weight" : 0.1 ,
"outputs" : { } ,
"search_method" : [
"embedding" ,
"full_text"
]
}
} ,
"downstream" : [ ] ,
"upstream" : [
"HierarchicalMerger:BusyPoetsSearch"
]
} ,
"HierarchicalMerger:BusyPoetsSearch" : {
"obj" : {
"component_name" : "HierarchicalMerger" ,
"params" : {
"hierarchy" : 3 ,
"levels" : [
[
"^#[^#]"
] ,
[
"^##[^#]"
] ,
[
"^###[^#]"
] ,
[
"^####[^#]"
]
] ,
"outputs" : {
"chunks" : {
"type" : "Array<Object>" ,
"value" : [ ]
}
}
}
} ,
"downstream" : [
"Tokenizer:NeatRadiosEnd"
] ,
"upstream" : [
"Parser:HipSignsRhyme"
]
}
} ,
"globals" : { } ,
"graph" : {
"nodes" : [
{
"data" : {
"label" : "File" ,
"name" : "File"
} ,
"id" : "File" ,
"measured" : {
"height" : 48 ,
"width" : 200
} ,
"position" : {
"x" : 50 ,
"y" : 200
} ,
"sourcePosition" : "left" ,
"targetPosition" : "right" ,
"type" : "beginNode"
} ,
{
"data" : {
"form" : {
"outputs" : {
"html" : {
"type" : "string" ,
"value" : ""
} ,
"json" : {
"type" : "Array<object>" ,
"value" : [ ]
} ,
"markdown" : {
"type" : "string" ,
"value" : ""
} ,
"text" : {
"type" : "string" ,
"value" : ""
}
} ,
"setups" : [
{
"fileFormat" : "pdf" ,
"output_format" : "json" ,
"parse_method" : "DeepDOC"
} ,
{
"fileFormat" : "text&markdown" ,
"output_format" : "text"
} ,
{
"fileFormat" : "word" ,
"output_format" : "json"
}
]
} ,
"label" : "Parser" ,
"name" : "Parser"
} ,
"dragging" : false ,
"id" : "Parser:HipSignsRhyme" ,
"measured" : {
"height" : 204 ,
"width" : 200
} ,
"position" : {
"x" : 316.99524094206413 ,
"y" : 195.39629819663406
} ,
"selected" : false ,
"sourcePosition" : "right" ,
"targetPosition" : "left" ,
"type" : "parserNode"
} ,
{
"data" : {
"form" : {
"fields" : "text" ,
"filename_embd_weight" : 0.1 ,
"outputs" : { } ,
"search_method" : [
"embedding" ,
"full_text"
]
} ,
"label" : "Tokenizer" ,
"name" : "Indexer"
} ,
"dragging" : false ,
"id" : "Tokenizer:NeatRadiosEnd" ,
"measured" : {
"height" : 120 ,
"width" : 200
} ,
"position" : {
"x" : 855.3572909622682 ,
"y" : 199.08562542263914
} ,
"selected" : false ,
"sourcePosition" : "right" ,
"targetPosition" : "left" ,
"type" : "tokenizerNode"
} ,
{
"data" : {
"form" : {
"hierarchy" : "3" ,
"levels" : [
{
"expressions" : [
{
"expression" : "^#[^#]"
}
]
} ,
{
"expressions" : [
{
"expression" : "^##[^#]"
}
]
} ,
{
"expressions" : [
{
"expression" : "^###[^#]"
}
]
} ,
{
"expressions" : [
{
"expression" : "^####[^#]"
}
]
}
] ,
"outputs" : {
"chunks" : {
"type" : "Array<Object>" ,
"value" : [ ]
}
}
} ,
"label" : "HierarchicalMerger" ,
"name" : "Title Chunker"
} ,
"dragging" : false ,
"id" : "HierarchicalMerger:BusyPoetsSearch" ,
"measured" : {
"height" : 80 ,
"width" : 200
} ,
"position" : {
"x" : 587.0312356829183 ,
"y" : 197.9169308584236
} ,
"selected" : false ,
"sourcePosition" : "right" ,
"targetPosition" : "left" ,
"type" : "splitterNode"
} ,
{
"data" : {
"form" : {
"text" : "It is ideal for documents with well-defined headings, such as product manuals, legal contracts, research reports, and academic papers."
} ,
"label" : "Note" ,
"name" : "Chunk by Title"
} ,
"dragHandle" : ".note-drag-handle" ,
"dragging" : false ,
"height" : 159 ,
"id" : "Note:KhakiBerriesPick" ,
"measured" : {
"height" : 159 ,
"width" : 323
} ,
"position" : {
"x" : 623.9675370532708 ,
"y" : 369.74281927307146
} ,
"resizing" : false ,
"selected" : false ,
"sourcePosition" : "right" ,
"targetPosition" : "left" ,
"type" : "noteNode" ,
"width" : 323
}
] ,
"edges" : [
{
"id" : "xy-edge__Filestart-Parser:HipSignsRhymeend" ,
"source" : "File" ,
"sourceHandle" : "start" ,
"target" : "Parser:HipSignsRhyme" ,
"targetHandle" : "end"
} ,
{
"id" : "xy-edge__Parser:HipSignsRhymestart-HierarchicalMerger:BusyPoetsSearchend" ,
"source" : "Parser:HipSignsRhyme" ,
"sourceHandle" : "start" ,
"target" : "HierarchicalMerger:BusyPoetsSearch" ,
"targetHandle" : "end" ,
"data" : {
"isHovered" : false
}
} ,
{
"data" : {
"isHovered" : false
} ,
"id" : "xy-edge__HierarchicalMerger:BusyPoetsSearchstart-Tokenizer:NeatRadiosEndend" ,
"markerEnd" : "logo" ,
"source" : "HierarchicalMerger:BusyPoetsSearch" ,
"sourceHandle" : "start" ,
"style" : {
"stroke" : "rgba(91, 93, 106, 1)" ,
"strokeWidth" : 1
} ,
"target" : "Tokenizer:NeatRadiosEnd" ,
"targetHandle" : "end" ,
"type" : "buttonEdge" ,
"zIndex" : 1001
}
]
} ,
"history" : [ ] ,
"messages" : [ ] ,
"path" : [ ] ,
"retrieval" : [ ]
} ,
"avatar" : " d a t a : i m a g e / p n g ; b a s e 64 , i V B O R w 0 K G g o A A A A N S U h E U g A A A D A A A A A w C A Y A A A B X A v m H A A A A C X B I W X M A A B Y l A A A W J Q F J U i T w A A A A A X N S R 0 I A r s 4 c 6 Q A A A A R n Q U 1 B A A C x j w v 8 Y Q U A A B M a S U R B V H g B b V p r j F 3 V d f 72 P u c + 5 s 7 L n h m / x / Z g C H W A F L d V K E q o g J Y 2 i k I J E U S B h i Z F I a V R K Z j + K F H a 1 G 7 a p B S 1 K l G p k h 99 E E U g y k M i K l F p F C U I y S 1 p S T F C Q L A D H m N j j z 3 j e c 99 n X P 27 r f W 3 u f O t Z O x r u / c c 8 / Z e z 2 + 9 a 3 H H o M L f v 7 s k j u u y / L i 4 w b m Z n 6 c 8 t 7 r d W M M n H O w 1 k K u y W f 56 f 9 d f u S e 8 r O 8 y / f y j F y X n / 7 f y + / l l S R J e N b y W W 5 p Z Q 2 + j O z v c b i W 1 A 67 w v 3 F w e l H p / v l 7e18 c O r 3 N r T Q O c C b 9 / c L V Q p c b l I U x f r D Z l 0 B 2 U f f R S l V Q p 5 z 5 y l X G q E n b F S g / 935 g s I n 4 b m o P C 8 i 4 T + q w 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
}
