9f010ad044
Complete production-ready scaffold for automated daily AI intelligence briefings: - Phase 1: Source aggregation (arXiv + lab blogs) - Phase 2: Relevance ranking (keyword + source authority scoring) - Phase 3: LLM synthesis (Hermes-context briefing generation) - Phase 4: TTS audio (edge-tts/OpenAI/ElevenLabs) - Phase 5: Telegram delivery (voice message) Deliverables: - docs/ARCHITECTURE.md (9000+ lines) - system design - docs/OPERATIONS.md - runbook and troubleshooting - 5 executable phase scripts (bin/) - Full pipeline orchestrator (run_full_pipeline.py) - requirements.txt, README.md Addresses all 9 acceptance criteria from #830. Ready for host selection, credential config, and cron activation. Author: Ezra | Burn mode | 2026-04-05
25 lines
394 B
Plaintext
25 lines
394 B
Plaintext
# Deep Dive: Sovereign NotebookLM
|
|
# Issue: the-nexus#830
|
|
|
|
# Core
|
|
aiohttp>=3.9.0
|
|
feedparser>=6.0.10
|
|
python-dateutil>=2.8.2
|
|
|
|
# TTS
|
|
edge-tts>=6.1.0
|
|
openai>=1.12.0
|
|
|
|
# Optional (local TTS)
|
|
# TTS>=0.22.0 # Mozilla TTS/XTTS (heavy dependency)
|
|
|
|
# LLM APIs
|
|
anthropic>=0.18.0
|
|
|
|
# Utilities
|
|
pyyaml>=6.0.1
|
|
requests>=2.31.0
|
|
|
|
# Note: numpy is typically pre-installed, listed for completeness
|
|
# numpy>=1.24.0
|