feat: add 18 AI/ML Portainer templates with gap analysis

ai-templates/docs/AI_GAP_ANALYSIS.md

@@ -0,0 +1,70 @@
+# Portainer v3 Templates — AI Gap Analysis
+
+## Overview
+
+The official Portainer v3 templates (`templates.json`) contain **71 templates** across the following categories:
+
+| Category | Count | Examples |
+|---|---|---|
+| Database | 10 | MySQL, PostgreSQL, Mongo, Redis, CrateDB, Elasticsearch, CockroachDB, TimescaleDB |
+| Edge/IIoT | 14 | Softing EdgeConnectors, OPC Router, TOSIBOX, EMQX MQTT, Mosquitto, Node-RED, Litmus Edge |
+| Web/CMS | 8 | Nginx, Caddy, WordPress, Drupal, Joomla, Ghost, Plone |
+| DevOps/CI | 5 | Jenkins, GitLab CE, Dokku, Registry |
+| Monitoring | 4 | Grafana, Datadog, Sematext, Swarm Monitoring |
+| Messaging | 1 | RabbitMQ |
+| Storage | 3 | Minio, Scality S3, File Browser |
+| Serverless | 2 | OpenFaaS, IronFunctions |
+| Other | 6 | Ubuntu, NodeJS, Portainer Agent, OpenAMT, FDO, LiveSwitch |
+
+## AI Template Count: **0**
+
+There are **zero purely AI/ML-focused templates** in the current v3 template list.
+
+### Closest to AI
+
+- **Litmus Edge** (#70, #71) — Described as "enables industrial AI at scale" but is fundamentally an OT data platform / edge data collector, not an AI deployment.
+- **Elasticsearch** (#13) — Used in vector search / RAG pipelines but is a general-purpose search engine.
+
+### Gap
+
+The templates completely miss the fastest-growing Docker deployment category: AI inference, model serving, LLM tooling, vector databases, ML pipelines, AI-powered agents, and GPU-accelerated workloads.
+
+---
+
+## Recommended AI Template Additions
+
+This repository provides **18 production-ready AI Docker Compose stacks** for Portainer, organized into the following sub-categories:
+
+### LLM Inference & Model Serving
+1. **Ollama** — Local LLM inference engine (Llama, Mistral, Qwen, Gemma, etc.)
+2. **Open WebUI** — ChatGPT-like web interface for Ollama/OpenAI-compatible backends
+3. **LocalAI** — Drop-in OpenAI API replacement, runs models locally
+4. **vLLM** — High-throughput LLM serving with PagedAttention
+5. **Text Generation WebUI** — Comprehensive LLM interface (oobabooga)
+6. **LiteLLM** — Unified LLM API gateway / proxy
+
+### Image & Video Generation
+7. **ComfyUI** — Node-based Stable Diffusion workflow engine
+8. **Stable Diffusion WebUI** — AUTOMATIC1111 web interface for image generation
+
+### AI Agents & Workflows
+9. **Langflow** — Visual framework for building LLM-powered agents
+10. **Flowise** — Drag-and-drop LLM orchestration / chatflow builder
+11. **n8n AI** — Workflow automation with AI agent nodes
+
+### Vector Databases
+12. **Qdrant** — High-performance vector similarity search engine
+13. **ChromaDB** — AI-native open-source embedding database
+14. **Weaviate** — Vector database with built-in vectorization modules
+
+### ML Operations
+15. **MLflow** — ML experiment tracking, model registry, and serving
+16. **Label Studio** — Multi-type data labeling and annotation platform
+17. **Jupyter GPU** — GPU-accelerated Jupyter notebooks for ML development
+
+### Speech & Audio
+18. **Whisper** — OpenAI Whisper speech-to-text API server
+
+---
+
+*Generated: March 2026 — For use with Portainer Business Edition and Community Edition*