firefrost-gaming/skill-seekers-reference
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
642 Commits 1 Branch 0 Tags
2e30970dfbfeb4e06b2e3139f7ff1855c8a8ea0d
Commit Graph

3 Commits

Author SHA1 Message Date
yusyus
d19ad7d820 feat: video pipeline OCR quality fixes + two-pass AI enhancement 
- Skip OCR on WEBCAM/OTHER frames (eliminates ~64 junk results per video)
- Add _clean_ocr_line() to strip line numbers, IDE decorations, collapse markers
- Add _fix_intra_line_duplication() for multi-engine OCR overlap artifacts
- Add _is_likely_code() filter to prevent UI junk in reference code fences
- Add language detection to get_text_groups() via LanguageDetector
- Apply OCR cleaning in _assemble_structured_text() pipeline
- Add two-pass AI enhancement: Pass 1 cleans reference Code Timeline
  using transcript context, Pass 2 generates SKILL.md from cleaned refs
- Update video-tutorial.yaml prompts for pre-cleaned references
- Add 17 new tests (197 total video tests), 2540 tests passing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-01 21:48:21 +03:00
yusyus
cc9cc32417 feat: add skill-seekers video --setup for GPU auto-detection and dependency installation 
Auto-detects NVIDIA (CUDA), AMD (ROCm), or CPU-only GPU and installs the
correct PyTorch variant + easyocr + all visual extraction dependencies.
Removes easyocr from video-full pip extras to avoid pulling ~2GB of wrong
CUDA packages on non-NVIDIA systems.

New files:
- video_setup.py (835 lines): GPU detection, PyTorch install, ROCm config,
  venv checks, system dep validation, module selection, verification
- test_video_setup.py (60 tests): Full coverage of detection, install, verify

Updated docs: CHANGELOG, AGENTS.md, CLAUDE.md, README.md, CLI_REFERENCE,
FAQ, TROUBLESHOOTING, installation guide, video dependency plan

All 2523 tests passing (15 skipped).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-01 18:39:16 +03:00
YusufKaraaslanSpyke
62071c4aa9 feat: add video tutorial scraping pipeline with per-panel OCR and AI enhancement 
Add complete video tutorial extraction system that converts YouTube videos
and local video files into AI-consumable skills. The pipeline extracts
transcripts, performs visual OCR on code editor panels independently,
tracks code evolution across frames, and generates structured SKILL.md output.

Key features:
- Video metadata extraction (YouTube, local files, playlists)
- Multi-source transcript extraction (YouTube API, yt-dlp, Whisper fallback)
- Chapter-based and time-window segmentation
- Visual extraction: keyframe detection, frame classification, panel detection
- Per-panel sub-section OCR (each IDE panel OCR'd independently)
- Parallel OCR with ThreadPoolExecutor for multi-panel frames
- Narrow panel filtering (300px min width) to skip UI chrome
- Text block tracking with spatial panel position matching
- Code timeline with edit tracking across frames
- Audio-visual alignment (code + narrator pairs)
- Video-specific AI enhancement prompt for OCR denoising and code reconstruction
- video-tutorial.yaml workflow with 4 stages (OCR cleanup, language detection,
  tutorial synthesis, skill polish)
- CLI integration: skill-seekers video --url/--video-file/--playlist
- MCP tool: scrape_video for automation
- 161 tests passing

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-02-27 23:10:19 +03:00