joungmin 826961f2b9 fix: improve title, summary, and content formatting ...

- youtube.py: fetch real title via YouTube oEmbed API instead of falling back to video ID
- youtube.py: paragraphize transcript text by grouping sentences (4 per para)
- enricher.py: increase max_tokens 1024→2048 to prevent summary truncation
- web.py: restore paragraph breaks after HTML stripping

2026-02-28 09:39:05 +09:00

bot

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

core

fix: improve title, summary, and content formatting

2026-02-28 09:39:05 +09:00

daemon

feat: add English vocab extraction and Anki card registration

2026-02-28 08:39:58 +09:00

sql

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

.env.example

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

.gitignore

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

main.py

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

pyproject.toml

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

requirements.txt

feat: initial knowledge-inbox pipeline implementation

2026-02-28 08:16:11 +09:00

Description

Telegram 봇 + Oracle ADB 큐 + LLM 요약 + Obsidian 저장 파이프라인

70 KiB

Languages

Python 98.1%

PLSQL 1.9%