131 lines
3.6 KiB
Bash
Executable File
131 lines
3.6 KiB
Bash
Executable File
#!/bin/bash
|
|
# Mortdecai Gateway — fully automated setup
|
|
# Just run: ./setup.sh
|
|
# Everything downloads and configures automatically.
|
|
|
|
set -e
|
|
|
|
MODEL_URL="${MODEL_URL:-https://mortdec.ai/dl/m4gguf/mortdecai-0.4.0.gguf}"
|
|
MODEL_NAME="mortdecai:0.4.0"
|
|
|
|
echo "=== Mortdecai Gateway Setup ==="
|
|
echo ""
|
|
|
|
# Generate API key if not set
|
|
if [ ! -f .env ]; then
|
|
KEY="mk_$(openssl rand -hex 16)"
|
|
cat > .env << EOF
|
|
API_KEY=$KEY
|
|
GPU_TDP_WATTS=54
|
|
SYSTEM_OVERHEAD_WATTS=30
|
|
ELECTRICITY_RATE=0.15
|
|
SPENDING_CAP=10.00
|
|
EOF
|
|
echo "Generated API key: $KEY"
|
|
echo "Saved to .env"
|
|
else
|
|
echo ".env already exists"
|
|
KEY=$(grep API_KEY .env | cut -d= -f2)
|
|
fi
|
|
|
|
# Start containers
|
|
echo ""
|
|
echo "Starting containers..."
|
|
docker compose up -d
|
|
|
|
# Wait for Ollama to be ready
|
|
echo "Waiting for Ollama to start..."
|
|
for i in $(seq 1 60); do
|
|
if curl -s http://localhost:11434/api/tags > /dev/null 2>&1; then
|
|
echo "Ollama is ready"
|
|
break
|
|
fi
|
|
if [ $i -eq 60 ]; then
|
|
echo "ERROR: Ollama failed to start after 2 minutes"
|
|
echo "Check: docker logs mortdecai-ollama"
|
|
exit 1
|
|
fi
|
|
sleep 2
|
|
done
|
|
|
|
# Check if model already loaded
|
|
LOADED=$(curl -s http://localhost:11434/api/tags 2>/dev/null | python3 -c "import sys,json; print('yes' if any('$MODEL_NAME' in m['name'] for m in json.load(sys.stdin).get('models',[])) else 'no')" 2>/dev/null || echo "no")
|
|
|
|
if [ "$LOADED" = "yes" ]; then
|
|
echo "Model $MODEL_NAME already loaded"
|
|
else
|
|
# Download GGUF
|
|
mkdir -p models
|
|
GGUF_PATH="models/${MODEL_NAME}.gguf"
|
|
|
|
if [ ! -f "$GGUF_PATH" ]; then
|
|
echo ""
|
|
echo "Downloading model (~5.3 GB)..."
|
|
echo "Source: $MODEL_URL"
|
|
curl -L -o "$GGUF_PATH" "$MODEL_URL" --progress-bar
|
|
echo "Download complete"
|
|
else
|
|
echo "GGUF already downloaded"
|
|
fi
|
|
|
|
# Create Modelfile
|
|
cat > models/Modelfile << 'MEOF'
|
|
FROM /models/mortdecai:0.4.0.gguf
|
|
TEMPLATE """{{- if .Messages }}
|
|
{{- if or .System .Tools }}<|im_start|>system
|
|
{{- if .System }}
|
|
{{ .System }}
|
|
{{- end }}
|
|
<|im_end|>
|
|
{{ end }}
|
|
{{- range $m := .Messages }}
|
|
{{- if eq $m.Role "user" }}<|im_start|>user
|
|
{{ $m.Content }}<|im_end|>
|
|
{{- else if eq $m.Role "assistant" }}<|im_start|>assistant
|
|
{{ $m.Content }}<|im_end|>
|
|
{{- end }}
|
|
{{- end }}<|im_start|>assistant
|
|
{{ end }}"""
|
|
PARAMETER stop <|im_end|>
|
|
PARAMETER stop <|im_start|>
|
|
PARAMETER temperature 0.7
|
|
MEOF
|
|
|
|
echo "Loading model into Ollama..."
|
|
docker exec mortdecai-ollama ollama create "$MODEL_NAME" -f /models/Modelfile
|
|
echo "Model loaded as $MODEL_NAME"
|
|
fi
|
|
|
|
# Quick test
|
|
echo ""
|
|
echo "Running test inference..."
|
|
RESULT=$(curl -s http://localhost:8434/api/chat \
|
|
-H "Authorization: Bearer $KEY" \
|
|
-H "Content-Type: application/json" \
|
|
-d "{\"model\": \"$MODEL_NAME\", \"messages\": [{\"role\": \"user\", \"content\": \"say hello\"}], \"stream\": false}" 2>/dev/null)
|
|
|
|
if echo "$RESULT" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d['message']['content'][:80])" 2>/dev/null; then
|
|
echo "Test passed!"
|
|
else
|
|
echo "Test inference returned unexpected result (model may still be loading)"
|
|
echo "Try again in a minute: curl -s http://localhost:8434/health"
|
|
fi
|
|
|
|
echo ""
|
|
echo "========================================="
|
|
echo " Mortdecai Gateway is ready!"
|
|
echo "========================================="
|
|
echo ""
|
|
echo " Dashboard: http://localhost:8434/dashboard"
|
|
echo " Health: http://localhost:8434/health"
|
|
echo " API Key: $KEY"
|
|
echo ""
|
|
echo " Send this to Seth:"
|
|
echo " - Your public IP"
|
|
echo " - Port: 8434"
|
|
echo " - API Key: $KEY"
|
|
echo ""
|
|
echo " To stop: docker compose down"
|
|
echo " To start: docker compose up -d"
|
|
echo "========================================="
|