the-nexus/docs/DEEPSDIVE_QUICKSTART.md

Deep Dive Quick Start

Get your daily AI intelligence briefing running in 5 minutes.

Installation

# 1. Clone the-nexus repository
cd /opt
git clone http://143.198.27.163:3000/Timmy_Foundation/the-nexus.git
cd the-nexus

# 2. Install Python dependencies
pip install -r config/deepdive_requirements.txt

# 3. Install Piper TTS (Linux)
# Download model: https://github.com/rhasspy/piper/releases
mkdir -p /opt/piper/models
cd /opt/piper/models
wget https://huggingface.co/rhasspy/piper-voices/resolve/v1.0.0/en/en_US/lessac/medium/en_US-lessac-medium.onnx
wget https://huggingface.co/rhasspy/piper-voices/resolve/v1.0.0/en/en_US/lessac/medium/en_US-lessac-medium.onnx.json

# 4. Configure environment
cp config/deepdive.env.example /opt/deepdive/.env
nano /opt/deepdive/.env  # Edit with your API keys

# 5. Create data directories
mkdir -p /opt/deepdive/data/{cache,filtered,briefings,audio}

Run Manually (One-Time)

# Run full pipeline
./bin/deepdive_orchestrator.py --run-once

# Or run phases separately
./bin/deepdive_aggregator.py --output /opt/deepdive/data/raw_$(date +%Y-%m-%d).jsonl
./bin/deepdive_filter.py -i /opt/deepdive/data/raw_$(date +%Y-%m-%d).jsonl -o /opt/deepdive/data/filtered_$(date +%Y-%m-%d).jsonl
./bin/deepdive_synthesis.py -i /opt/deepdive/data/filtered_$(date +%Y-%m-%d).jsonl -o /opt/deepdive/data/briefings/briefing_$(date +%Y-%m-%d).md
./bin/deepdive_tts.py -i /opt/deepdive/data/briefings/briefing_$(date +%Y-%m-%d).md -o /opt/deepdive/data/audio/briefing_$(date +%Y-%m-%d).mp3
./bin/deepdive_delivery.py --audio /opt/deepdive/data/audio/briefing_$(date +%Y-%m-%d).mp3 --text /opt/deepdive/data/briefings/briefing_$(date +%Y-%m-%d).md

Schedule Daily (Cron)

# Edit crontab
crontab -e

# Add line for 6 AM daily
0 6 * * * cd /opt/the-nexus && /usr/bin/python3 ./bin/deepdive_orchestrator.py --run-once >> /opt/deepdive/logs/cron.log 2>&1

Telegram Bot Setup

1. Create bot via @BotFather
2. Get bot token, add to .env
3. Get your chat ID: Send /start to @userinfobot
4. Add to .env: TELEGRAM_CHAT_ID=your_id

Verifying Installation

# Test aggregation
./bin/deepdive_aggregator.py --test

# Test full pipeline (dry-run, no delivery)
./bin/deepdive_orchestrator.py --dry-run --verbose

# Check logs
tail -f /opt/deepdive/logs/deepdive.log

Customization

• Add sources: Edit config/deepdive_sources.yaml
• Adjust relevance: Edit config/deepdive_keywords.yaml
• Change schedule: Modify crontab or DEEPDIVE_SCHEDULE in .env
• Switch TTS: Change DEEPDIVE_TTS_PROVIDER in .env

Troubleshooting

Issue	Solution
No entries aggregated	Check feed URLs in sources.yaml
All filtered out	Lower min_relevance_score in keywords.yaml
TTS fails	Verify Piper model path in .env
Telegram fails	Check bot token and chat ID
LLM synthesis slow	Try smaller model or OpenRouter free tier

Architecture

See: docs/DEEPSDIVE_ARCHITECTURE.md

Issue

Tracked: the-nexus#830