# Portainer AI Templates

> **18 production-ready AI/ML Docker Compose stacks for Portainer** — filling the AI gap in the official v3 template library.

## Background

The official [Portainer v3 templates](https://raw.githubusercontent.com/portainer/templates/v3/templates.json) contain **71 templates** with **zero pure AI/ML deployments**. This repository provides a curated, Portainer-compatible template set covering the entire AI infrastructure stack.

See [docs/AI_GAP_ANALYSIS.md](docs/AI_GAP_ANALYSIS.md) for the full gap analysis.

## Quick Start

### Option A: Use as Custom Template URL in Portainer

1. In Portainer, go to **Settings → App Templates**
2. Set the URL to:
   ```
   https://git.oe74.net/adelorenzo/portainer_scripts/raw/branch/master/ai-templates/portainer-ai-templates.json
   ```
3. Click **Save** — AI templates now appear in your App Templates list

### Option B: Deploy Individual Stacks

Each stack has its own `docker-compose.yml` in `stacks/<name>/`:

```bash
cd stacks/ollama
docker compose up -d
```

## Template Catalog

### LLM Inference & Model Serving

| Template | Port | GPU | Description |
|---|---|---|---|
| **Ollama** | 11434 | Yes | Local LLM engine — Llama, Mistral, Qwen, Gemma, Phi |
| **Open WebUI + Ollama** | 3000 | Yes | ChatGPT-like UI bundled with Ollama backend |
| **LocalAI** | 8080 | Yes | Drop-in OpenAI API replacement |
| **vLLM** | 8000 | Yes | High-throughput serving with PagedAttention |
| **Text Gen WebUI** | 7860 | Yes | Comprehensive LLM interface (oobabooga) |
| **LiteLLM Proxy** | 4000 | No | Unified API gateway for 100+ LLM providers |

### Image & Video Generation

| Template | Port | GPU | Description |
|---|---|---|---|
| **ComfyUI** | 8188 | Yes | Node-based Stable Diffusion workflow engine |
| **Stable Diffusion WebUI** | 7860 | Yes | AUTOMATIC1111 interface for image generation |

### AI Agents & Workflows

| Template | Port | GPU | Description |
|---|---|---|---|
| **Langflow** | 7860 | No | Visual multi-agent and RAG pipeline builder |
| **Flowise** | 3000 | No | Drag-and-drop LLM chatflow builder |
| **n8n (AI-Enabled)** | 5678 | No | Workflow automation with AI agent nodes |

### Vector Databases

| Template | Port | GPU | Description |
|---|---|---|---|
| **Qdrant** | 6333 | No | High-performance vector similarity search |
| **ChromaDB** | 8000 | No | AI-native embedding database |
| **Weaviate** | 8080 | No | Vector DB with built-in vectorization modules |

### ML Operations

| Template | Port | GPU | Description |
|---|---|---|---|
| **MLflow** | 5000 | No | Experiment tracking and model registry |
| **Label Studio** | 8080 | No | Multi-type data labeling platform |
| **Jupyter (GPU/PyTorch)** | 8888 | Yes | GPU-accelerated notebooks |

### Speech & Audio

| Template | Port | GPU | Description |
|---|---|---|---|
| **Whisper ASR** | 9000 | Yes | Speech-to-text API server |

## GPU Requirements

Templates marked **GPU: Yes** require:
- NVIDIA GPU with CUDA support
- [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/install-guide.html) installed
- Docker configured with `nvidia` runtime

For AMD GPUs (ROCm), modify the `deploy.resources` section to use ROCm-compatible images and remove the NVIDIA device reservation.

## File Structure

```
ai-templates/
├── portainer-ai-templates.json    # Portainer v3 compatible template definition
├── README.md                      # This file
├── docs/
│   └── AI_GAP_ANALYSIS.md        # Analysis of official templates gap
└── stacks/
    ├── ollama/
    │   └── docker-compose.yml
    ├── open-webui/
    │   └── docker-compose.yml
    ├── localai/
    │   └── docker-compose.yml
    ├── vllm/
    │   └── docker-compose.yml
    ├── text-generation-webui/
    │   └── docker-compose.yml
    ├── litellm/
    │   └── docker-compose.yml
    ├── comfyui/
    │   └── docker-compose.yml
    ├── stable-diffusion-webui/
    │   └── docker-compose.yml
    ├── langflow/
    │   └── docker-compose.yml
    ├── flowise/
    │   └── docker-compose.yml
    ├── n8n-ai/
    │   └── docker-compose.yml
    ├── qdrant/
    │   └── docker-compose.yml
    ├── chromadb/
    │   └── docker-compose.yml
    ├── weaviate/
    │   └── docker-compose.yml
    ├── mlflow/
    │   └── docker-compose.yml
    ├── label-studio/
    │   └── docker-compose.yml
    ├── jupyter-gpu/
    │   └── docker-compose.yml
    └── whisper/
        └── docker-compose.yml
```

## License

These templates reference publicly available Docker images from their respective maintainers. Each tool has its own license — refer to the individual project documentation.

---

*Generated March 2026 — Portainer AI Templates by Adolfo De Lorenzo*