secondbrain/deploy/install.sh
Atlas 84afdc1f56 SecondBrain v0.1 — local-first, privacy-scrubbing RAG memory
Generalized + redeployable: config via env, local Ollama embeddings, single
portable sqlite-vec db, hybrid dense+FTS5 recall, mandatory credential scrub.
2026-07-01 21:25:02 +02:00

40 lines
1.2 KiB
Bash
Executable file

#!/usr/bin/env bash
# SecondBrain — one-shot local install. Idempotent.
# curl -fsSL https://git.atlascorporation.nl/atlas/secondbrain/raw/branch/main/deploy/install.sh | bash
# or, from a clone: bash deploy/install.sh
set -euo pipefail
DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
cd "$DIR"
echo "==> python deps"
python3 -m venv .venv 2>/dev/null || true
. .venv/bin/activate
pip install -q --upgrade pip
pip install -q -r requirements.txt
echo "==> config"
[ -f .env ] || cp .env.example .env
echo " edit .env to point OLLAMA_URL / sources"
echo "==> ollama + embed model"
if command -v ollama >/dev/null 2>&1; then
ollama pull nomic-embed-text >/dev/null 2>&1 || true
else
echo " NOTE: ollama not found. Install from https://ollama.com and run: ollama pull nomic-embed-text"
fi
echo "==> init schema"
python3 brain.py init
cat <<'EOF'
SecondBrain installed. Next:
. .venv/bin/activate
python3 brain.py ingest-files /path/to/your/notes-or-code
python3 brain.py embed
python3 brain.py recall "your question" --hybrid
Continuous refresh (Linux): edit deploy/secondbrain-refresh.service paths, then
sudo cp deploy/secondbrain-refresh.* /etc/systemd/system/
sudo systemctl enable --now secondbrain-refresh.timer
EOF