zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-08-01 13:33:48 +08:00
Code Issues Packages Projects Releases Wiki Activity

Support pipeline DSL modification through dataset configuration (backend) (#16991)

Browse Source 
…end)

### Summary

Support pipeline DSL modification through dataset configuration
(backend)

Key modification: knowledgebase.parser_config

---------

Co-authored-by: yzc <yuzhichang@gmail.com>
This commit is contained in:
qinling0210
2026-07-17 14:40:09 +08:00
committed by GitHub
parent b32d5fd86b
commit 995e405e8c
52 changed files with 4093 additions and 2819 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1464
agent/templates/advanced_ingestion_pipeline.json
View File

File diff suppressed because one or more lines are too long

920
agent/templates/chunk_summary.json
View File

File diff suppressed because one or more lines are too long

232
agent/templates/title_chunker.json
View File

@@ -88,123 +88,121 @@
"value": ""
}
},
"setups": {
"doc": {
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"doc"
]
},
"docx": {
"flatten_media_to_text": false,
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"docx"
],
"vlm": {}
},
"email": {
"fields": [
"from",
"to",
"cc",
"bcc",
"date",
"subject",
"body",
"attachments"
],
"output_format": "text",
"preprocess": "main_content",
"suffix": [
"eml",
"msg"
]
},
"html": {
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"htm",
"html"
]
},
"image": {
"output_format": "text",
"parse_method": "ocr",
"preprocess": "main_content",
"suffix": [
"jpg",
"jpeg",
"png",
"gif"
],
"system_prompt": ""
},
"markdown": {
"flatten_media_to_text": false,
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"md",
"markdown",
"mdx"
],
"vlm": {}
},
"pdf": {
"flatten_media_to_text": false,
"output_format": "json",
"parse_method": "DeepDOC",
"preprocess": "main_content",
"suffix": [
"pdf"
],
"vlm": {}
},
"slides": {
"output_format": "json",
"parse_method": "DeepDOC",
"preprocess": "main_content",
"suffix": [
"pptx",
"ppt"
]
},
"spreadsheet": {
"flatten_media_to_text": false,
"output_format": "html",
"parse_method": "DeepDOC",
"preprocess": "main_content",
"suffix": [
"xls",
"xlsx",
"csv"
],
"vlm": {}
},
"text&code": {
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"txt",
"py",
"js",
"java",
"c",
"cpp",
"h",
"php",
"go",
"ts",
"sh",
"cs",
"kt",
"sql"
]
}
"doc": {
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"doc"
]
},
"docx": {
"flatten_media_to_text": false,
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"docx"
],
"vlm": {}
},
"email": {
"fields": [
"from",
"to",
"cc",
"bcc",
"date",
"subject",
"body",
"attachments"
],
"output_format": "text",
"preprocess": "main_content",
"suffix": [
"eml",
"msg"
]
},
"html": {
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"htm",
"html"
]
},
"image": {
"output_format": "text",
"parse_method": "ocr",
"preprocess": "main_content",
"suffix": [
"jpg",
"jpeg",
"png",
"gif"
],
"system_prompt": ""
},
"markdown": {
"flatten_media_to_text": false,
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"md",
"markdown",
"mdx"
],
"vlm": {}
},
"pdf": {
"flatten_media_to_text": false,
"output_format": "json",
"parse_method": "DeepDOC",
"preprocess": "main_content",
"suffix": [
"pdf"
],
"vlm": {}
},
"slides": {
"output_format": "json",
"parse_method": "DeepDOC",
"preprocess": "main_content",
"suffix": [
"pptx",
"ppt"
]
},
"spreadsheet": {
"flatten_media_to_text": false,
"output_format": "html",
"parse_method": "DeepDOC",
"preprocess": "main_content",
"suffix": [
"xls",
"xlsx",
"csv"
],
"vlm": {}
},
"text&code": {
"output_format": "json",
"preprocess": "main_content",
"suffix": [
"txt",
"py",
"js",
"java",
"c",
"cpp",
"h",
"php",
"go",
"ts",
"sh",
"cs",
"kt",
"sql"
]
}
}
},