{ "components": { "File": { "obj":{ "component_name": "File", "params": { } }, "downstream": ["Parser:0"], "upstream": [] }, "Parser:0": { "obj": { "component_name": "Parser", "params": { "setups": { "pdf": { "parse_method": "deepdoc", "vlm_name": "", "lang": "Chinese", "suffix": [ "pdf" ], "output_format": "json" }, "spreadsheet": { "suffix": [ "xls", "xlsx", "csv" ], "output_format": "html" }, "word": { "suffix": [ "doc", "docx" ], "output_format": "json" }, "markdown": { "suffix": [ "md", "markdown" ], "output_format": "text" }, "text": { "suffix": ["txt"], "output_format": "json" } } } }, "downstream": ["Splitter:0"], "upstream": ["File"] }, "Splitter:0": { "obj": { "component_name": "Splitter", "params": { "chunk_token_size": 512, "delimiters": ["\r\n"], "overlapped_percent": 0 } }, "downstream": ["HierarchicalMerger:0"], "upstream": ["Parser:0"] }, "HierarchicalMerger:0": { "obj": { "component_name": "HierarchicalMerger", "params": { "levels": [["^#[^#]"], ["^##[^#]"], ["^###[^#]"], ["^####[^#]"]], "hierarchy": 2 } }, "downstream": [], "upstream": ["Splitter:0"] } }, "path": [] }