Files
ragflow/rag/flow/tests/dsl_examples/general_pdf_all.json
Lynn 41cdba19ba Feat: dataflow supports markdown (#10003)
### What problem does this PR solve?

Dataflow supports markdown.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2025-09-10 13:31:02 +08:00

79 lines
1.8 KiB
JSON

{
"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"
}
}
}
}
},
"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": []
}