initial

2026-01-16 01:51:57 +00:00
commit 7d135569fe
10 changed files with 545 additions and 0 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -0,0 +1,32 @@
+# Dependencies
+node_modules/
+
+# Build outputs
+dist/
+dist_ts/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# OS
+.DS_Store
+Thumbs.db
+
+# Logs
+*.log
+npm-debug.log*
+
+# Environment
+.env
+.env.local
+.env.*.local
+
+# Test artifacts
+.nogit/
+coverage/
+
+# Docker
+*.tar
--- a/25
+++ b/25
@@ -0,0 +1,25 @@
+# MiniCPM-V 4.5 GPU Variant
+# Vision-Language Model with NVIDIA GPU support
+FROM ollama/ollama:latest
+
+LABEL maintainer="Task Venture Capital GmbH <hello@task.vc>"
+LABEL description="MiniCPM-V 4.5 Vision-Language Model - GPU optimized"
+LABEL org.opencontainers.image.source="https://code.foss.global/host.today/ht-docker-ai"
+
+# Environment configuration
+ENV MODEL_NAME="minicpm-v"
+ENV OLLAMA_HOST="0.0.0.0"
+ENV OLLAMA_ORIGINS="*"
+
+# Copy and setup entrypoint
+COPY image_support_files/docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+
+# Expose Ollama API port
+EXPOSE 11434
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:11434/api/tags || exit 1
+
+ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]
--- a/27
+++ b/27
@@ -0,0 +1,27 @@
+# MiniCPM-V 4.5 CPU Variant
+# Vision-Language Model optimized for CPU-only inference
+FROM ollama/ollama:latest
+
+LABEL maintainer="Task Venture Capital GmbH <hello@task.vc>"
+LABEL description="MiniCPM-V 4.5 Vision-Language Model - CPU optimized (GGUF)"
+LABEL org.opencontainers.image.source="https://code.foss.global/host.today/ht-docker-ai"
+
+# Environment configuration for CPU-only mode
+ENV MODEL_NAME="minicpm-v"
+ENV OLLAMA_HOST="0.0.0.0"
+ENV OLLAMA_ORIGINS="*"
+# Disable GPU usage for CPU-only variant
+ENV CUDA_VISIBLE_DEVICES=""
+
+# Copy and setup entrypoint
+COPY image_support_files/docker-entrypoint.sh /usr/local/bin/docker-entrypoint.sh
+RUN chmod +x /usr/local/bin/docker-entrypoint.sh
+
+# Expose Ollama API port
+EXPOSE 11434
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=120s --retries=3 \
+    CMD curl -f http://localhost:11434/api/tags || exit 1
+
+ENTRYPOINT ["/usr/local/bin/docker-entrypoint.sh"]
--- a/build-images.sh
+++ b/build-images.sh
@@ -0,0 +1,37 @@
+#!/bin/bash
+set -e
+
+# Configuration
+REGISTRY="code.foss.global"
+NAMESPACE="host.today"
+IMAGE_NAME="ht-docker-ai"
+
+# Colors for output
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+echo -e "${BLUE}Building ht-docker-ai images...${NC}"
+
+# Build GPU variant
+echo -e "${GREEN}Building MiniCPM-V 4.5 GPU variant...${NC}"
+docker build \
+    -f Dockerfile_minicpm45v \
+    -t ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:minicpm45v \
+    -t ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:minicpm45v-gpu \
+    -t ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:latest \
+    .
+
+# Build CPU variant
+echo -e "${GREEN}Building MiniCPM-V 4.5 CPU variant...${NC}"
+docker build \
+    -f Dockerfile_minicpm45v_cpu \
+    -t ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:minicpm45v-cpu \
+    .
+
+echo -e "${GREEN}All images built successfully!${NC}"
+echo ""
+echo "Available images:"
+echo "  - ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:minicpm45v (GPU)"
+echo "  - ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:minicpm45v-cpu (CPU)"
+echo "  - ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:latest (GPU)"
--- a/image_support_files/docker-entrypoint.sh
+++ b/image_support_files/docker-entrypoint.sh
@@ -0,0 +1,28 @@
+#!/bin/bash
+set -e
+
+# Default model to pull
+MODEL_NAME="${MODEL_NAME:-minicpm-v}"
+
+# Start Ollama server in background
+echo "Starting Ollama server..."
+ollama serve &
+
+# Wait for Ollama to be ready
+echo "Waiting for Ollama server to start..."
+sleep 5
+
+# Check if model is already pulled
+if ! ollama list | grep -q "${MODEL_NAME}"; then
+    echo "Pulling model: ${MODEL_NAME}..."
+    ollama pull "${MODEL_NAME}"
+    echo "Model ${MODEL_NAME} pulled successfully."
+else
+    echo "Model ${MODEL_NAME} already available."
+fi
+
+echo "Ollama server ready with ${MODEL_NAME}"
+echo "API available at http://0.0.0.0:11434"
+
+# Keep container running
+wait
--- a/npmextra.json
+++ b/npmextra.json
@@ -0,0 +1,25 @@
+{
+  "npmci": {
+    "npmGlobalTools": [],
+    "npmAccessLevel": "public"
+  },
+  "gitzone": {
+    "projectType": "docker",
+    "module": {
+      "githost": "code.foss.global",
+      "gitscope": "host.today",
+      "gitrepo": "ht-docker-ai",
+      "description": "Docker images for AI vision-language models including MiniCPM-V 4.5",
+      "npmPackagename": "@host.today/ht-docker-ai",
+      "license": "MIT",
+      "keywords": [
+        "docker",
+        "ai",
+        "vision-language",
+        "minicpm",
+        "ollama",
+        "multimodal"
+      ]
+    }
+  }
+}
--- a/package.json
+++ b/package.json
@@ -0,0 +1,27 @@
+{
+  "name": "@host.today/ht-docker-ai",
+  "version": "1.0.0",
+  "private": false,
+  "description": "Docker images for AI vision-language models including MiniCPM-V 4.5",
+  "main": "dist_ts/index.js",
+  "typings": "dist_ts/index.d.ts",
+  "author": "Task Venture Capital GmbH <hello@task.vc>",
+  "license": "MIT",
+  "scripts": {
+    "build": "./build-images.sh",
+    "test": "./test-images.sh"
+  },
+  "repository": {
+    "type": "git",
+    "url": "https://code.foss.global/host.today/ht-docker-ai.git"
+  },
+  "homepage": "https://code.foss.global/host.today/ht-docker-ai",
+  "keywords": [
+    "docker",
+    "ai",
+    "vision-language",
+    "minicpm",
+    "ollama",
+    "multimodal"
+  ]
+}
--- a/readme.hints.md
+++ b/readme.hints.md
@@ -0,0 +1,125 @@
+# Technical Notes - ht-docker-ai
+
+## Architecture
+
+This project uses **Ollama** as the runtime framework for serving AI models. This provides:
+
+- Automatic model download and caching
+- Unified REST API (compatible with OpenAI format)
+- Built-in quantization support
+- GPU/CPU auto-detection
+
+## Model Details
+
+### MiniCPM-V 4.5
+
+- **Source**: OpenBMB (https://github.com/OpenBMB/MiniCPM-V)
+- **Base Models**: Qwen3-8B + SigLIP2-400M
+- **Total Parameters**: 8B
+- **Ollama Model Name**: `minicpm-v`
+
+### VRAM Usage
+
+| Mode | VRAM Required |
+|------|---------------|
+| Full precision (bf16) | 18GB |
+| int4 quantized | 9GB |
+| GGUF (CPU) | 8GB RAM |
+
+## Container Startup Flow
+
+1. `docker-entrypoint.sh` starts Ollama server in background
+2. Waits for server to be ready
+3. Checks if model already exists in volume
+4. Pulls model if not present
+5. Keeps container running
+
+## Volume Persistence
+
+Mount `/root/.ollama` to persist downloaded models:
+
+```bash
+-v ollama-data:/root/.ollama
+```
+
+Without this volume, the model will be re-downloaded on each container start (~5GB download).
+
+## API Endpoints
+
+All endpoints follow the Ollama API specification:
+
+| Endpoint | Method | Description |
+|----------|--------|-------------|
+| `/api/tags` | GET | List available models |
+| `/api/generate` | POST | Generate completion |
+| `/api/chat` | POST | Chat completion |
+| `/api/pull` | POST | Pull a model |
+| `/api/show` | POST | Show model info |
+
+## GPU Detection
+
+The GPU variant uses Ollama's automatic GPU detection. For CPU-only mode, we set:
+
+```dockerfile
+ENV CUDA_VISIBLE_DEVICES=""
+```
+
+This forces Ollama to use CPU inference even if GPU is available.
+
+## Health Checks
+
+Both variants include Docker health checks:
+
+```dockerfile
+HEALTHCHECK --interval=30s --timeout=10s --start-period=60s --retries=3 \
+    CMD curl -f http://localhost:11434/api/tags || exit 1
+```
+
+CPU variant has longer `start-period` (120s) due to slower startup.
+
+## Adding New Models
+
+To add a new model variant:
+
+1. Create `Dockerfile_<modelname>`
+2. Set `MODEL_NAME` environment variable
+3. Update `build-images.sh` with new build target
+4. Add documentation to `readme.md`
+
+## Troubleshooting
+
+### Model download hangs
+
+Check container logs:
+```bash
+docker logs -f <container-name>
+```
+
+The model download is ~5GB and may take several minutes.
+
+### Out of memory
+
+- GPU: Use int4 quantized version or add more VRAM
+- CPU: Increase container memory limit: `--memory=16g`
+
+### API not responding
+
+1. Check if container is healthy: `docker ps`
+2. Check logs for errors: `docker logs <container>`
+3. Verify port mapping: `curl localhost:11434/api/tags`
+
+## CI/CD Integration
+
+Build and push using npmci:
+
+```bash
+npmci docker login
+npmci docker build
+npmci docker push code.foss.global
+```
+
+## Related Resources
+
+- [Ollama Documentation](https://ollama.ai/docs)
+- [MiniCPM-V GitHub](https://github.com/OpenBMB/MiniCPM-V)
+- [Ollama API Reference](https://github.com/ollama/ollama/blob/main/docs/api.md)
--- a/readme.md
+++ b/readme.md
@@ -0,0 +1,147 @@
+# @host.today/ht-docker-ai
+
+Docker images for AI vision-language models, starting with MiniCPM-V 4.5.
+
+## Overview
+
+This project provides ready-to-use Docker containers for running state-of-the-art AI vision-language models. Built on Ollama for simplified model management and a consistent REST API.
+
+## Available Images
+
+| Tag | Description | Requirements |
+|-----|-------------|--------------|
+| `minicpm45v` | MiniCPM-V 4.5 with GPU support | NVIDIA GPU, 9-18GB VRAM |
+| `minicpm45v-cpu` | MiniCPM-V 4.5 CPU-only | 8GB+ RAM |
+| `latest` | Alias for `minicpm45v` | NVIDIA GPU |
+
+## Quick Start
+
+### GPU (Recommended)
+
+```bash
+docker run -d \
+  --name minicpm \
+  --gpus all \
+  -p 11434:11434 \
+  -v ollama-data:/root/.ollama \
+  code.foss.global/host.today/ht-docker-ai:minicpm45v
+```
+
+### CPU Only
+
+```bash
+docker run -d \
+  --name minicpm \
+  -p 11434:11434 \
+  -v ollama-data:/root/.ollama \
+  code.foss.global/host.today/ht-docker-ai:minicpm45v-cpu
+```
+
+## API Usage
+
+The container exposes the Ollama API on port 11434.
+
+### List Available Models
+
+```bash
+curl http://localhost:11434/api/tags
+```
+
+### Generate Text from Image
+
+```bash
+curl http://localhost:11434/api/generate -d '{
+  "model": "minicpm-v",
+  "prompt": "What do you see in this image?",
+  "images": ["<base64-encoded-image>"]
+}'
+```
+
+### Chat with Vision
+
+```bash
+curl http://localhost:11434/api/chat -d '{
+  "model": "minicpm-v",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Describe this image in detail",
+      "images": ["<base64-encoded-image>"]
+    }
+  ]
+}'
+```
+
+## Environment Variables
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `MODEL_NAME` | `minicpm-v` | Model to pull on startup |
+| `OLLAMA_HOST` | `0.0.0.0` | Host address for API |
+| `OLLAMA_ORIGINS` | `*` | Allowed CORS origins |
+
+## Hardware Requirements
+
+### GPU Variant (`minicpm45v`)
+
+- NVIDIA GPU with CUDA support
+- Minimum 9GB VRAM (int4 quantized)
+- Recommended 18GB VRAM (full precision)
+- NVIDIA Container Toolkit installed
+
+### CPU Variant (`minicpm45v-cpu`)
+
+- Minimum 8GB RAM
+- Recommended 16GB+ RAM for better performance
+- No GPU required
+
+## Model Information
+
+**MiniCPM-V 4.5** is a GPT-4o level multimodal large language model developed by OpenBMB.
+
+- **Parameters**: 8B (Qwen3-8B + SigLIP2-400M)
+- **Capabilities**: Image understanding, OCR, multi-image analysis
+- **Languages**: 30+ languages including English, Chinese, French, Spanish
+
+## Docker Compose Example
+
+```yaml
+version: '3.8'
+services:
+  minicpm:
+    image: code.foss.global/host.today/ht-docker-ai:minicpm45v
+    container_name: minicpm
+    ports:
+      - "11434:11434"
+    volumes:
+      - ollama-data:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    restart: unless-stopped
+
+volumes:
+  ollama-data:
+```
+
+## Building Locally
+
+```bash
+# Clone the repository
+git clone https://code.foss.global/host.today/ht-docker-ai.git
+cd ht-docker-ai
+
+# Build all images
+./build-images.sh
+
+# Run tests
+./test-images.sh
+```
+
+## License
+
+MIT - Task Venture Capital GmbH
--- a/test-images.sh
+++ b/test-images.sh
@@ -0,0 +1,72 @@
+#!/bin/bash
+set -e
+
+# Configuration
+REGISTRY="code.foss.global"
+NAMESPACE="host.today"
+IMAGE_NAME="ht-docker-ai"
+TEST_PORT=11434
+
+# Colors for output
+GREEN='\033[0;32m'
+RED='\033[0;31m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+cleanup() {
+    echo -e "${BLUE}Cleaning up test containers...${NC}"
+    docker rm -f test-minicpm-gpu 2>/dev/null || true
+    docker rm -f test-minicpm-cpu 2>/dev/null || true
+}
+
+trap cleanup EXIT
+
+test_image() {
+    local tag=$1
+    local container_name=$2
+    local extra_args=$3
+
+    echo -e "${BLUE}Testing ${tag}...${NC}"
+
+    # Start container
+    docker run -d \
+        --name ${container_name} \
+        -p ${TEST_PORT}:11434 \
+        ${extra_args} \
+        ${REGISTRY}/${NAMESPACE}/${IMAGE_NAME}:${tag}
+
+    # Wait for startup
+    echo "Waiting for container to start..."
+    sleep 10
+
+    # Test API endpoint
+    echo "Testing API endpoint..."
+    if curl -s -f http://localhost:${TEST_PORT}/api/tags > /dev/null; then
+        echo -e "${GREEN}API endpoint responding!${NC}"
+    else
+        echo -e "${RED}API endpoint not responding!${NC}"
+        docker logs ${container_name}
+        return 1
+    fi
+
+    # Cleanup this container
+    docker rm -f ${container_name}
+
+    echo -e "${GREEN}${tag} test passed!${NC}"
+    echo ""
+}
+
+echo -e "${BLUE}=== Testing ht-docker-ai images ===${NC}"
+echo ""
+
+# Test CPU variant (doesn't require GPU)
+test_image "minicpm45v-cpu" "test-minicpm-cpu" ""
+
+# Test GPU variant only if NVIDIA runtime is available
+if docker info 2>/dev/null | grep -q "nvidia"; then
+    test_image "minicpm45v" "test-minicpm-gpu" "--gpus all"
+else
+    echo -e "${BLUE}Skipping GPU test (NVIDIA runtime not available)${NC}"
+fi
+
+echo -e "${GREEN}=== All tests passed! ===${NC}"