pengjunjie/ragflow
1
0
Fork 1
mirror of https://github.com/infiniflow/ragflow.git synced 2025-12-24 07:26:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Feat: add splitter (#10161)

Browse Source 
### What problem does this PR solve?


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

---------

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: Lynn <lynn_inf@hotmail.com>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: balibabu <cike8899@users.noreply.github.com>
Co-authored-by: 纷繁下的无奈 <zhileihuang@126.com>
Co-authored-by: huangzl <huangzl@shinemo.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: Wilmer <33392318@qq.com>
Co-authored-by: Adrian Weidig <adrianweidig@gmx.net>
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Yongteng Lei <yongtengrey@outlook.com>
Co-authored-by: Liu An <asiro@qq.com>
Co-authored-by: buua436 <66937541+buua436@users.noreply.github.com>
Co-authored-by: BadwomanCraZY <511528396@qq.com>
Co-authored-by: cucusenok <31804608+cucusenok@users.noreply.github.com>
Co-authored-by: Russell Valentine <russ@coldstonelabs.org>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Billy Bao <newyorkupperbay@gmail.com>
Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: TensorNull <129579691+TensorNull@users.noreply.github.com>
Co-authored-by: TensorNull <tensor.null@gmail.com>
This commit is contained in:
Kevin Hu
2025-09-19 10:15:19 +08:00
committed by GitHub
parent f9c7404bee
commit a1b947ffd6
81 changed files with 3083 additions and 799 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
rag/flow/tests/dsl_examples/general_pdf_all.json
View File

@ -44,20 +44,58 @@
"markdown"
],
"output_format": "json"
},
"text": {
"suffix": ["txt"],
"output_format": "json"
},
"image": {
"parse_method": "vlm",
"llm_id":"glm-4.5v",
"lang": "Chinese",
"suffix": [
"jpg",
"jpeg",
"png",
"gif"
],
"output_format": "text"
},
"audio": {
"suffix": [
"da",
"wave",
"wav",
"mp3",
"aac",
"flac",
"ogg",
"aiff",
"au",
"midi",
"wma",
"realaudio",
"vqf",
"oggvorbis",
"ape"
],
"lang": "Chinese",
"llm_id": "SenseVoiceSmall",
"output_format": "json"
}
}
}
}
},
"downstream": ["Chunker:0"],
"downstream": ["Splitter:0"],
"upstream": ["Begin"]
},
"Chunker:0": {
"Splitter:0": {
"obj": {
"component_name": "Chunker",
"component_name": "Splitter",
"params": {
"method": "general",
"auto_keywords": 5
"chunk_token_size": 512,
"delimiters": ["\n"],
"overlapped_percent": 0
}
},
"downstream": ["Tokenizer:0"],

84
rag/flow/tests/dsl_examples/hierarchical_merger.json Normal file
View File

@ -0,0 +1,84 @@
{
"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": []
}