Commit Graph

4 Commits

Author SHA1 Message Date
20210830cf Fix TTS: switch to 1.7B with ref_audio, speakable text on all lines
- Use 1.7B model (0.6B had tensor mismatch with cached prompts)
- Speak endpoint uses ref_audio directly (not cached pkl) as fallback
- Cache voice clone prompts in memory on startup
- Add SpeakableText component: 🔊 icon on each p and li element
- Remove old TTSReader sequential approach
- Add global exception handler to TTS server
- Fix profile localStorage caching
- inference_mode + bf16 optimization

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-13 12:14:06 +00:00
f9f710ec90 Add English level settings, improve content structuring and rendering
- Add english_level column to users table (CEFR with TOEIC mapping)
- Add UserController (GET/PATCH /api/users/me) and Settings page
- Enhance structuring prompts: sequential TOC, no summary sections,
  no content overlap, English expression extraction by CEFR level
- Remove sub-TOC analysis (caused content repetition), use simple
  per-section generation with truncation detection and continuation
- Fix CLOB truncation: explicit Clob-to-String conversion in repository
- Replace regex-based markdown rendering with react-markdown
- Add wallet renewal procedure to troubleshooting docs

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-12 23:48:38 +00:00
9abb770e37 Add knowledge structuring feature with incremental LLM processing
- Add structured_content column and STRUCTURING pipeline step
- Split LLM structuring into TOC + per-section calls to avoid token limit
- Save intermediate results to DB for real-time frontend polling (3s)
- Add manual "정리하기" button with async processing
- Fix browser login modal by customizing authentication entry point
- Fix standalone build symlinks for server.js and static files
- Add troubleshooting guide

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-09 19:43:21 +00:00
9929322de0 Implement all core features: Knowledge pipeline, RAG chat, Todos, Habits, Study Cards, Tags, Dashboard
- Google OAuth authentication with callback flow
- Knowledge ingest pipeline (TEXT/WEB/YOUTUBE → chunking → categorization → embedding)
- OCI GenAI integration (chat, embeddings) with multi-model support
- Semantic search via Oracle VECTOR_DISTANCE
- RAG-based AI chat with source attribution
- Todos with subtasks, filters, and priority levels
- Habits with daily check-in, streak tracking, and color customization
- Study Cards with SM-2 spaced repetition and LLM auto-generation
- Tags system with knowledge item mapping
- Dashboard with live data from all modules

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-30 21:43:51 +00:00