ragflow/agent/templates/title_chunker.json

{
    "id": 25,
    "title": {
        "en": "Title Chunker",
        "de": "Titel basierte Segmentierung",
        "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.",
        "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.",
        "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": "data:image/png;base64,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"
}