Fully automated setup: downloads GGUF, loads model, tests inference

Setup script now:
1. Generates API key
2. Starts Docker containers
3. Downloads GGUF from mortdec.ai automatically (~5.3GB)
4. Creates Ollama model with correct chat template
5. Runs test inference
6. Prints connection details for Seth

Matt just runs ./setup.sh — no manual file copying.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

docker-compose.yml

@@ -22,7 +22,7 @@ services:
       - "127.0.0.1:11434:11434"  # Only accessible to gateway, not exposed
     volumes:
       - ollama-data:/root/.ollama
-      - ./models:/models
+      - ./models:/models:ro
     devices:
       - /dev/kfd:/dev/kfd
       - /dev/dri:/dev/dri

setup.sh

@@ -1,10 +1,15 @@
 #!/bin/bash
-# Quick setup for Mortdecai Gateway
-# Run this after cloning the repo
+# 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-v4.gguf}"
+MODEL_NAME="mortdecai-v4"
+
 echo "=== Mortdecai Gateway Setup ==="
+echo ""
 
 # Generate API key if not set
 if [ ! -f .env ]; then
@@ -20,30 +25,52 @@ EOF
     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..."
-for i in $(seq 1 30); do
+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
 
-# Load the model if GGUF exists
-if ls models/*.gguf 1>/dev/null 2>&1; then
-    GGUF=$(ls models/*.gguf | head -1)
-    MODEL_NAME=$(basename "$GGUF" .gguf | tr '[:upper:]' '[:lower:]')
-    echo "Loading model from $GGUF..."
+# Check if model already loaded
+LOADED=$(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")
 
-    cat > /tmp/Modelfile << MEOF
-FROM /models/$(basename $GGUF)
+if [ "$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-v4.gguf
 TEMPLATE """{{- if .Messages }}
 {{- if or .System .Tools }}<|im_start|>system
 {{- if .System }}
@@ -51,11 +78,11 @@ TEMPLATE """{{- if .Messages }}
 {{- 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|>
+{{- 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 }}"""
@@ -64,22 +91,40 @@ PARAMETER stop <|im_start|>
 PARAMETER temperature 0.7
 MEOF
 
-    docker exec mortdecai-ollama ollama create mortdecai-v4 -f /tmp/Modelfile
-    echo "Model loaded as mortdecai-v4"
+    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 "No GGUF found in models/ — place your GGUF file there and run:"
-    echo "  docker exec mortdecai-ollama ollama create mortdecai-v4 -f Modelfile"
+    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 "=== Setup Complete ==="
-echo "Dashboard: http://localhost:8434/dashboard"
-echo "API Key: $(grep API_KEY .env | cut -d= -f2)"
+echo "========================================="
+echo "  Mortdecai Gateway is ready!"
+echo "========================================="
 echo ""
-echo "Test: curl -s http://localhost:8434/health"
+echo "  Dashboard:  http://localhost:8434/dashboard"
+echo "  Health:     http://localhost:8434/health"
+echo "  API Key:    $KEY"
 echo ""
-echo "To use from remote:"
-echo "  curl -X POST http://YOUR_IP:8434/api/chat \\"
-echo "    -H 'Authorization: Bearer YOUR_API_KEY' \\"
-echo "    -H 'Content-Type: application/json' \\"
-echo "    -d '{\"model\": \"mortdecai-v4\", \"messages\": [{\"role\": \"user\", \"content\": \"test\"}]}'"
+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 "========================================="