Oliver/ppt-tool
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
ppt-tool/backend/services
History
Vadym Samoilenko 8715fa8bd2 Replace docling+layoutparser+torch with PyMuPDF (~3.5GB → ~80MB) 
- docling removed: PDF now parsed by PyMuPDF (fitz), PPTX by python-pptx
- layoutparser removed: already optional with graceful fallback (returns [])
- torch/pytorch index removed: no longer needed by any dependency
- pymupdf added: ~20MB wheel, no ML deps, faster than docling for text extraction
- All existing DOCX parsing kept (python-docx, already working)
- extract_text_from_image_via_vision() unchanged (Gemini API)

Result: api/worker Docker image ~3-4GB lighter, no NVIDIA libs on CPU server

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-19 20:06:46 +00:00
..
__init__.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
access_service.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
ai_usage_service.py Phase 2: Admin panel, analytics, storage, template pipeline, multi-provider LLM 2026-02-26 23:39:34 +00:00
attachment_parser_service.py Phase 3: Content Pipeline — file parsing, content intelligence, slide mapping, native charts 2026-02-26 15:54:04 +00:00
audit_service.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
auth_service.py Implement critical security fixes and modern design system (Pre-launch P0 tasks) 2026-02-27 18:28:24 +00:00
brand_enforcement_service.py Phase 4: Generation Pipeline — brand enforcement, enhanced LLM calls, ARQ job queue 2026-02-26 16:15:25 +00:00
chart_data_extractor.py Phase 3: Content Pipeline — file parsing, content intelligence, slide mapping, native charts 2026-02-26 15:54:04 +00:00
concurrent_service.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
content_intelligence_service.py Phase 3: Content Pipeline — file parsing, content intelligence, slide mapping, native charts 2026-02-26 15:54:04 +00:00
database.py Fix RLS session variables syntax 2026-02-27 20:26:03 +00:00
docling_service.py Replace docling+layoutparser+torch with PyMuPDF (~3.5GB → ~80MB) 2026-03-19 20:06:46 +00:00
documents_loader.py Fix SSE crash + React layout error boundaries 2026-03-01 19:35:27 +00:00
html_to_text_runs_service.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
icon_finder_service.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
image_generation_service.py Fix image generation model and purge logic 2026-02-27 16:18:34 +00:00
layout_analysis_service.py Phase 4: Fix critical bugs, improve document parsing, add vision OCR 2026-02-27 14:07:00 +00:00
llm_client.py Phase 2: Admin panel, analytics, storage, template pipeline, multi-provider LLM 2026-02-26 23:39:34 +00:00
llm_service.py Implement critical security fixes and modern design system (Pre-launch P0 tasks) 2026-02-27 18:28:24 +00:00
llm_tool_calls_handler.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
master_deck_parser_service.py Phase 8: Data-driven slide architecture + template management overhaul 2026-03-01 20:05:25 +00:00
native_chart_service.py Phase 3: Content Pipeline — file parsing, content intelligence, slide mapping, native charts 2026-02-26 15:54:04 +00:00
pptx_presentation_creator.py Phase 3: Content Pipeline — file parsing, content intelligence, slide mapping, native charts 2026-02-26 15:54:04 +00:00
redis_service.py Phase 4: Generation Pipeline — brand enforcement, enhanced LLM calls, ARQ job queue 2026-02-26 16:15:25 +00:00
retention_service.py Phase 6: Export & Polish — brand export, client dashboard, retention, analytics 2026-02-26 16:41:58 +00:00
score_based_chunker.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00
settings_service.py Phase 3: Bug fixes, feature enhancements, and polish 2026-02-27 12:58:52 +00:00
slide_mapping_engine.py Phase 3: Content Pipeline — file parsing, content intelligence, slide mapping, native charts 2026-02-26 15:54:04 +00:00
temp_file_service.py Rebrand Presenton to Oliver DeckForge, pre-configure models, use NanoBanana Pro 2026-02-26 18:17:11 +00:00
template_codegen_service.py Add 3 sandbox features: diagrams, mermaid, and template code-gen 2026-03-19 18:47:31 +00:00
webhook_service.py Phase 1-2: Foundation + Admin Panel & Client Management 2026-02-26 15:37:17 +00:00