cf21ba4516
Phase 1 (Foundation): - Project restructure (presenton-main → backend/ + frontend/) - Database schema (8 new models, Alembic config, seed script) - Auth (Azure AD SSO + dev bypass, JWT sessions, AuthMiddleware) - RBAC (access_service, rbac_middleware, admin routers) - Audit logging (fire-and-forget, AuditMiddleware, admin router) - i18n (react-i18next with 5 namespace files) Phase 2 (Admin Panel & Client Management): - Admin panel shell (sidebar layout, role guard, 12 pages) - Redux admin slice with 18 async thunks - User management (role changes, deactivation) - Client management (CRUD, brand config, team management) - Brand config editor (colors, fonts, logos, voice rules) - Master deck upload & parser (PPTX → HTML → React pipeline) - Audit log viewer with filters and CSV/JSON export Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
from docling.document_converter import (
|
|
DocumentConverter,
|
|
PdfFormatOption,
|
|
PowerpointFormatOption,
|
|
WordFormatOption,
|
|
)
|
|
from docling.datamodel.pipeline_options import PdfPipelineOptions
|
|
from docling.datamodel.base_models import InputFormat
|
|
|
|
|
|
class DoclingService:
|
|
def __init__(self):
|
|
self.pipeline_options = PdfPipelineOptions()
|
|
self.pipeline_options.do_ocr = False
|
|
|
|
self.converter = DocumentConverter(
|
|
allowed_formats=[InputFormat.PPTX, InputFormat.PDF, InputFormat.DOCX],
|
|
format_options={
|
|
InputFormat.DOCX: WordFormatOption(
|
|
pipeline_options=self.pipeline_options,
|
|
),
|
|
InputFormat.PPTX: PowerpointFormatOption(
|
|
pipeline_options=self.pipeline_options,
|
|
),
|
|
InputFormat.PDF: PdfFormatOption(
|
|
pipeline_options=self.pipeline_options,
|
|
),
|
|
},
|
|
)
|
|
|
|
def parse_to_markdown(self, file_path: str) -> str:
|
|
result = self.converter.convert(file_path)
|
|
return result.document.export_to_markdown()
|