vrr/SurfSense
2
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2025-09-04 11:39:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

Refactor: Cleanup DOCLING PR

Browse source
This commit is contained in:
MSI\ModSetter 2025-07-21 06:12:11 -07:00
parent 641f784f77
commit 621590c049
5 changed files with 2331 additions and 2326 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
.gitignore vendored
View file

@ -1,5 +1,3 @@
.flashrank_cache* .flashrank_cache*
podcasts/ podcasts/
reports/
SURFSENSE_CRITICAL_FIXES_REPORT.md
.env .env

7
surfsense_backend/Dockerfile
View file

@ -11,10 +11,6 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
wget \ wget \
unzip \ unzip \
gnupg2 \ gnupg2 \
tesseract-ocr \
tesseract-ocr-eng \
libtesseract-dev \
libleptonica-dev \
&& rm -rf /var/lib/apt/lists/* && rm -rf /var/lib/apt/lists/*
# Update certificates and install SSL tools # Update certificates and install SSL tools
@ -60,9 +56,6 @@ COPY . .
ENV PYTHONPATH=/app ENV PYTHONPATH=/app
ENV UVICORN_LOOP=asyncio ENV UVICORN_LOOP=asyncio
# Set Tesseract data path
ENV TESSDATA_PREFIX=/usr/share/tesseract-ocr/5/tessdata/
# Run # Run
EXPOSE 8000 EXPOSE 8000
CMD ["python", "main.py"] CMD ["python", "main.py"]

1
surfsense_backend/pyproject.toml
View file

@ -30,7 +30,6 @@ dependencies = [
"slack-sdk>=3.34.0", "slack-sdk>=3.34.0",
"static-ffmpeg>=2.13", "static-ffmpeg>=2.13",
"tavily-python>=0.3.2", "tavily-python>=0.3.2",
"tesserocr>=2.8.0",
"unstructured-client>=0.30.0", "unstructured-client>=0.30.0",
"unstructured[all-docs]>=0.16.25", "unstructured[all-docs]>=0.16.25",
"uvicorn[standard]>=0.34.0", "uvicorn[standard]>=0.34.0",

4480
surfsense_backend/uv.lock generated
View file

File diff suppressed because it is too large Load diff

167
surfsense_web/app/dashboard/[search_space_id]/documents/upload/page.tsx
View file

@ -53,83 +53,98 @@ export default function FileUploader() {
}; };
// Conditionally set accepted file types based on ETL service // Conditionally set accepted file types based on ETL service
const acceptedFileTypes = process.env.NEXT_PUBLIC_ETL_SERVICE === 'LLAMACLOUD' const getAcceptedFileTypes = () => {
? { const etlService = process.env.NEXT_PUBLIC_ETL_SERVICE;
// LlamaCloud supported file types
'application/pdf': ['.pdf'], if (etlService === 'LLAMACLOUD') {
'application/msword': ['.doc'], return {
'application/vnd.openxmlformats-officedocument.wordprocessingml.document': ['.docx'], // LlamaCloud supported file types
'application/vnd.ms-word.document.macroEnabled.12': ['.docm'], 'application/pdf': ['.pdf'],
'application/msword-template': ['.dot'], 'application/msword': ['.doc'],
'application/vnd.ms-word.template.macroEnabled.12': ['.dotm'], 'application/vnd.openxmlformats-officedocument.wordprocessingml.document': ['.docx'],
'application/vnd.ms-powerpoint': ['.ppt'], 'application/vnd.ms-word.document.macroEnabled.12': ['.docm'],
'application/vnd.ms-powerpoint.template.macroEnabled.12': ['.pptm'], 'application/msword-template': ['.dot'],
'application/vnd.openxmlformats-officedocument.presentationml.presentation': ['.pptx'], 'application/vnd.ms-word.template.macroEnabled.12': ['.dotm'],
'application/vnd.ms-powerpoint.template': ['.pot'], 'application/vnd.ms-powerpoint': ['.ppt'],
'application/vnd.openxmlformats-officedocument.presentationml.template': ['.potx'], 'application/vnd.ms-powerpoint.template.macroEnabled.12': ['.pptm'],
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': ['.xlsx'], 'application/vnd.openxmlformats-officedocument.presentationml.presentation': ['.pptx'],
'application/vnd.ms-excel': ['.xls'], 'application/vnd.ms-powerpoint.template': ['.pot'],
'application/vnd.ms-excel.sheet.macroEnabled.12': ['.xlsm'], 'application/vnd.openxmlformats-officedocument.presentationml.template': ['.potx'],
'application/vnd.ms-excel.sheet.binary.macroEnabled.12': ['.xlsb'], 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': ['.xlsx'],
'application/vnd.ms-excel.workspace': ['.xlw'], 'application/vnd.ms-excel': ['.xls'],
'application/rtf': ['.rtf'], 'application/vnd.ms-excel.sheet.macroEnabled.12': ['.xlsm'],
'application/xml': ['.xml'], 'application/vnd.ms-excel.sheet.binary.macroEnabled.12': ['.xlsb'],
'application/epub+zip': ['.epub'], 'application/vnd.ms-excel.workspace': ['.xlw'],
'application/vnd.apple.keynote': ['.key'], 'application/rtf': ['.rtf'],
'application/vnd.apple.pages': ['.pages'], 'application/xml': ['.xml'],
'application/vnd.apple.numbers': ['.numbers'], 'application/epub+zip': ['.epub'],
'application/vnd.wordperfect': ['.wpd'], 'application/vnd.apple.keynote': ['.key'],
'application/vnd.oasis.opendocument.text': ['.odt'], 'application/vnd.apple.pages': ['.pages'],
'application/vnd.oasis.opendocument.presentation': ['.odp'], 'application/vnd.apple.numbers': ['.numbers'],
'application/vnd.oasis.opendocument.graphics': ['.odg'], 'application/vnd.wordperfect': ['.wpd'],
'application/vnd.oasis.opendocument.spreadsheet': ['.ods'], 'application/vnd.oasis.opendocument.text': ['.odt'],
'application/vnd.oasis.opendocument.formula': ['.fods'], 'application/vnd.oasis.opendocument.presentation': ['.odp'],
'text/csv': ['.csv'], 'application/vnd.oasis.opendocument.graphics': ['.odg'],
'text/tab-separated-values': ['.tsv'], 'application/vnd.oasis.opendocument.spreadsheet': ['.ods'],
'text/html': ['.html', '.htm', '.web'], 'application/vnd.oasis.opendocument.formula': ['.fods'],
'image/jpeg': ['.jpg', '.jpeg'], 'text/csv': ['.csv'],
'image/png': ['.png'], 'text/tab-separated-values': ['.tsv'],
'image/gif': ['.gif'], 'text/html': ['.html', '.htm', '.web'],
'image/bmp': ['.bmp'], 'image/jpeg': ['.jpg', '.jpeg'],
'image/svg+xml': ['.svg'], 'image/png': ['.png'],
'image/tiff': ['.tiff'], 'image/gif': ['.gif'],
'image/webp': ['.webp'], 'image/bmp': ['.bmp'],
'application/dbase': ['.dbf'], 'image/svg+xml': ['.svg'],
'application/vnd.lotus-1-2-3': ['.123'], 'image/tiff': ['.tiff'],
'text/x-web-markdown': ['.602', '.abw', '.cgm', '.cwk', '.hwp', '.lwp', '.mw', '.mcw', '.pbd', '.sda', '.sdd', '.sdp', '.sdw', '.sgl', '.sti', '.sxi', '.sxw', '.stw', '.sxg', '.uof', '.uop', '.uot', '.vor', '.wps', '.zabw'], 'image/webp': ['.webp'],
'text/x-spreadsheet': ['.dif', '.sylk', '.slk', '.prn', '.et', '.uos1', '.uos2', '.wk1', '.wk2', '.wk3', '.wk4', '.wks', '.wq1', '.wq2', '.wb1', '.wb2', '.wb3', '.qpw', '.xlr', '.eth'], 'application/dbase': ['.dbf'],
// Audio files (always supported) 'application/vnd.lotus-1-2-3': ['.123'],
...audioFileTypes, 'text/x-web-markdown': ['.602', '.abw', '.cgm', '.cwk', '.hwp', '.lwp', '.mw', '.mcw', '.pbd', '.sda', '.sdd', '.sdp', '.sdw', '.sgl', '.sti', '.sxi', '.sxw', '.stw', '.sxg', '.uof', '.uop', '.uot', '.vor', '.wps', '.zabw'],
'text/x-spreadsheet': ['.dif', '.sylk', '.slk', '.prn', '.et', '.uos1', '.uos2', '.wk1', '.wk2', '.wk3', '.wk4', '.wks', '.wq1', '.wq2', '.wb1', '.wb2', '.wb3', '.qpw', '.xlr', '.eth'],
// Audio files (always supported)
...audioFileTypes,
};
} else if (etlService === 'DOCLING') {
return {
// Docling supported file types (currently only PDF)
'application/pdf': ['.pdf'],
// Audio files (always supported)
...audioFileTypes,
};
} else {
return {
// Unstructured supported file types
'image/bmp': ['.bmp'],
'text/csv': ['.csv'],
'application/msword': ['.doc'],
'application/vnd.openxmlformats-officedocument.wordprocessingml.document': ['.docx'],
'message/rfc822': ['.eml'],
'application/epub+zip': ['.epub'],
'image/heic': ['.heic'],
'text/html': ['.html'],
'image/jpeg': ['.jpeg', '.jpg'],
'image/png': ['.png'],
'application/vnd.ms-outlook': ['.msg'],
'application/vnd.oasis.opendocument.text': ['.odt'],
'text/x-org': ['.org'],
'application/pkcs7-signature': ['.p7s'],
'application/pdf': ['.pdf'],
'application/vnd.ms-powerpoint': ['.ppt'],
'application/vnd.openxmlformats-officedocument.presentationml.presentation': ['.pptx'],
'text/x-rst': ['.rst'],
'application/rtf': ['.rtf'],
'image/tiff': ['.tiff'],
'text/tab-separated-values': ['.tsv'],
'application/vnd.ms-excel': ['.xls'],
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': ['.xlsx'],
'application/xml': ['.xml'],
// Audio files (always supported)
...audioFileTypes,
};
} }
: { };
// Unstructured supported file types
'image/bmp': ['.bmp'], const acceptedFileTypes = getAcceptedFileTypes();
'text/csv': ['.csv'],
'application/msword': ['.doc'],
'application/vnd.openxmlformats-officedocument.wordprocessingml.document': ['.docx'],
'message/rfc822': ['.eml'],
'application/epub+zip': ['.epub'],
'image/heic': ['.heic'],
'text/html': ['.html'],
'image/jpeg': ['.jpeg', '.jpg'],
'image/png': ['.png'],
'application/vnd.ms-outlook': ['.msg'],
'application/vnd.oasis.opendocument.text': ['.odt'],
'text/x-org': ['.org'],
'application/pkcs7-signature': ['.p7s'],
'application/pdf': ['.pdf'],
'application/vnd.ms-powerpoint': ['.ppt'],
'application/vnd.openxmlformats-officedocument.presentationml.presentation': ['.pptx'],
'text/x-rst': ['.rst'],
'application/rtf': ['.rtf'],
'image/tiff': ['.tiff'],
'text/tab-separated-values': ['.tsv'],
'application/vnd.ms-excel': ['.xls'],
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': ['.xlsx'],
'application/xml': ['.xml'],
// Audio files (always supported)
...audioFileTypes,
};
const supportedExtensions = Array.from(new Set(Object.values(acceptedFileTypes).flat())).sort() const supportedExtensions = Array.from(new Set(Object.values(acceptedFileTypes).flat())).sort()