{ "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": "json" }, "text": { "suffix": ["txt"], "output_format": "json" } } } }, "downstream": ["Chunker:0"], "upstream": ["Begin"] }, "Chunker:0": { "obj": { "component_name": "Chunker", "params": { "method": "general", "auto_keywords": 5 } }, "downstream": ["Tokenizer:0"], "upstream": ["Parser:0"] }, "Tokenizer:0": { "obj": { "component_name": "Tokenizer", "params": { } }, "downstream": [], "upstream": ["Chunker:0"] } }, "path": [] }