opro_demo/export-ollama-models.sh

#!/bin/bash

# Export Ollama models for offline deployment
# This script copies Ollama models from your local machine
# so they can be bundled into the Docker image
#
# Required models:
# - qwen3:14b (main chat model)
# - qwen3-embedding:4b (embedding model)

set -e

MODELS_DIR="ollama-models"
OLLAMA_MODELS_PATH="$HOME/.ollama"

echo "=========================================="
echo "Exporting Ollama models for offline deployment"
echo "=========================================="

# Check if Ollama is installed
if ! command -v ollama &> /dev/null; then
    echo "ERROR: Ollama is not installed or not in PATH"
    exit 1
fi

# Check if required models are available
echo ""
echo "Checking for required models..."
MISSING_MODELS=0

if ! ollama list | grep -q "qwen3:14b"; then
    echo "ERROR: qwen3:14b model not found!"
    echo "Please run: ollama pull qwen3:14b"
    MISSING_MODELS=1
fi

if ! ollama list | grep -q "qwen3-embedding:4b"; then
    echo "ERROR: qwen3-embedding:4b model not found!"
    echo "Please run: ollama pull qwen3-embedding:4b"
    MISSING_MODELS=1
fi

if [ $MISSING_MODELS -eq 1 ]; then
    echo ""
    echo "Please download the required models first:"
    echo "  ollama pull qwen3:14b"
    echo "  ollama pull qwen3-embedding:4b"
    exit 1
fi

echo "✓ All required models found"

# Check if Ollama directory exists
if [ ! -d "$OLLAMA_MODELS_PATH" ]; then
    echo "ERROR: Ollama directory not found at $OLLAMA_MODELS_PATH"
    exit 1
fi

# Create export directory structure
echo ""
echo "Creating export directory: $MODELS_DIR"
rm -rf "$MODELS_DIR"
mkdir -p "$MODELS_DIR/models/manifests/registry.ollama.ai/library"
mkdir -p "$MODELS_DIR/models/blobs"

echo ""
echo "Copying only required models (qwen3:14b and qwen3-embedding:4b)..."
echo "This may take several minutes (models are large)..."

# Function to get blob hashes from manifest
get_blobs_from_manifest() {
    local manifest_file=$1
    # Extract all sha256 hashes from the manifest JSON
    grep -oE 'sha256:[a-f0-9]{64}' "$manifest_file" 2>/dev/null | sed 's/sha256://' | sort -u
}

# Function to copy model files
copy_model() {
    local model_name=$1
    local model_tag=$2
    local manifest_dir="$OLLAMA_MODELS_PATH/models/manifests/registry.ollama.ai/library/$model_name"

    if [ ! -d "$manifest_dir" ]; then
        echo "ERROR: Model manifest not found: $manifest_dir"
        return 1
    fi

    echo "  Copying $model_name:$model_tag manifest..."
    mkdir -p "$MODELS_DIR/models/manifests/registry.ollama.ai/library/$model_name"

    # Copy the specific tag manifest
    if [ -f "$manifest_dir/$model_tag" ]; then
        cp "$manifest_dir/$model_tag" "$MODELS_DIR/models/manifests/registry.ollama.ai/library/$model_name/"

        # Get all blob hashes referenced in this manifest
        echo "  Finding blob files for $model_name:$model_tag..."
        local blob_hashes=$(get_blobs_from_manifest "$manifest_dir/$model_tag")
        local blob_count=0

        for blob_hash in $blob_hashes; do
            local blob_file="$OLLAMA_MODELS_PATH/models/blobs/sha256-$blob_hash"
            if [ -f "$blob_file" ]; then
                cp "$blob_file" "$MODELS_DIR/models/blobs/" 2>/dev/null
                blob_count=$((blob_count + 1))
            fi
        done

        echo "  ✓ $model_name:$model_tag copied ($blob_count blobs)"
    else
        echo "ERROR: Manifest file not found: $manifest_dir/$model_tag"
        return 1
    fi
}

# Copy required models with specific tags
copy_model "qwen3" "14b" || exit 1
copy_model "qwen3-embedding" "4b" || exit 1

echo ""
echo "=========================================="
echo "Models exported successfully!"
echo "=========================================="
echo ""
echo "Total size:"
du -sh "$MODELS_DIR"

echo ""
echo "Models included:"
if [ -d "$MODELS_DIR/models/manifests/registry.ollama.ai/library" ]; then
    ls -lh "$MODELS_DIR/models/manifests/registry.ollama.ai/library/"
fi

echo ""
echo "Blob files:"
if [ -d "$MODELS_DIR/models/blobs" ]; then
    echo "  Total blobs: $(ls -1 "$MODELS_DIR/models/blobs" | wc -l)"
    du -sh "$MODELS_DIR/models/blobs"
fi

echo ""
echo "=========================================="
echo "Summary"
echo "=========================================="
echo "✓ Only qwen3:14b and qwen3-embedding:4b were exported"
echo ""
echo "Models in your Ollama that were NOT copied:"
ollama list | grep -v "qwen3:14b" | grep -v "qwen3-embedding:4b" | tail -n +2 || echo "  (none)"
echo ""
echo "This keeps the Docker image size minimal!"

echo ""
echo "=========================================="
echo "Next steps:"
echo "=========================================="
echo "1. Build the all-in-one Docker image:"
echo "   ./build-allinone.sh"
echo ""
echo "2. Or manually:"
echo "   docker build -f Dockerfile.allinone -t system-prompt-optimizer:allinone ."
echo ""
echo "3. Export the image:"
echo "   docker save -o system-prompt-optimizer-allinone.tar system-prompt-optimizer:allinone"
echo ""
echo "4. Transfer to target server:"
echo "   scp system-prompt-optimizer-allinone.tar user@server:/path/"
echo ""
echo "Note: The final Docker image will be very large (10-20GB) due to the models."