Merge pull request #369 from outis1one/claude/gitea-standalone-setup-oxoi2e

ai-stack: offer an optional vision-capable Ollama model, including mo…

services/ai-stack.md

@@ -39,6 +39,26 @@ bash pull-models.sh    # pull Ollama models (run once after first install)
 ```
 Also a systemd unit: `sudo systemctl {start,stop,status} local-ai`
 
+## Vision models (image understanding)
+None of the tier-selected chat/code models above can read an image. `pull-models.sh`
+offers one optional vision model at the end — pick it there, or pull one manually
+any time:
+```bash
+docker exec ollama ollama pull moondream   # or llava:7b / qwen2.5vl:7b / llama3.2-vision:11b
+```
+| Model | Size | Notes |
+|-------|------|-------|
+| `moondream` | ~1.7 GB | By Moondream AI — tiny, built for CPU-only or weak/old-GPU hardware. Best default if you don't have a real GPU. |
+| `llava:7b` | ~4.7 GB | General-purpose vision, moderate resources. |
+| `qwen2.5vl:7b` | ~6 GB | Stronger accuracy, needs more RAM/VRAM. |
+| `llama3.2-vision:11b` | ~7.9 GB | Meta's vision model — heaviest of these four. |
+
+Point any OpenAI-compatible app's vision/image-import feature (e.g. Mealie's
+"import recipe from photo") at this stack's Ollama endpoint with the pulled
+model as `OPENAI_MODEL` — see Open WebUI → Settings → Connections for the
+exact local base URL, or `docker inspect ollama` for the container's address
+on `caddy_net`/the compose network.
+
 ## Cloud LLM providers (Open WebUI)
 Open WebUI uses an OpenAI-compatible connection list. The local RAG server is the
 first entry; any cloud providers added at install follow it. Two semicolon-separated

services/ai-stack.sh

@@ -34,6 +34,7 @@ install_ai-stack() {
         echo "[DRY-RUN] Would copy vendored source $SRC_DIR -> $AS_DIR"
         echo "[DRY-RUN] Would optionally collect cloud LLM provider keys (Groq/DeepInfra/OpenAI/OpenRouter)"
         echo "[DRY-RUN] Would run the app installer local-ai-setup.sh (Docker/NVIDIA toolkit, VRAM-aware models, generates compose/.env, starts stack, registers systemd 'local-ai')"
+        echo "[DRY-RUN] Would offer an optional vision-capable model to pull (moondream/llava/qwen2.5vl/llama3.2-vision) via the generated pull-models.sh"
         echo "[DRY-RUN] Would wire cloud providers into Open WebUI (OPENAI_API_BASE_URLS) preserving the local RAG connection"
         echo "[DRY-RUN] Would write gpu-mode.sh and optionally enable the GPU switcher (one small GPU shared by Ollama and InvokeAI/ComfyUI)"
         echo "[DRY-RUN] Would attach Open WebUI to caddy_net and configure Caddy (open-webui:8080, host port 3000)"

vendor/ai-stack/local-ai-setup.sh

@@ -860,6 +860,27 @@ echo "Reasoning model (DeepSeek-R1 14B — optional)..."
 read -rp "Pull DeepSeek-R1:14b for planning/reasoning? [y/N]: " DR
 [[ "\${DR,,}" == "y" ]] && docker exec ollama ollama pull deepseek-r1:14b
 
+echo ""
+echo "Vision model (optional — image understanding: Mealie's \"import recipe from"
+echo "photo\", attaching images in Open WebUI chat, etc.). None of the models"
+echo "above can read an image; pick one of these if you need that:"
+echo "  1) moondream            ~1.7 GB  Moondream AI — tiny, built for CPU-only/"
+echo "                                   weak or old GPU hardware. Recommended"
+echo "                                   default if you have no GPU or a low-VRAM one."
+echo "  2) llava:7b             ~4.7 GB  General-purpose vision, moderate resources."
+echo "  3) qwen2.5vl:7b         ~6 GB    Stronger accuracy, needs more RAM/VRAM."
+echo "  4) llama3.2-vision:11b  ~7.9 GB  Meta's vision model — heaviest of these four."
+read -rp "Pull a vision model? [1-4, blank to skip]: " VM
+case "\$VM" in
+    1) docker exec ollama ollama pull moondream ;;
+    2) docker exec ollama ollama pull llava:7b ;;
+    3) docker exec ollama ollama pull qwen2.5vl:7b ;;
+    4) docker exec ollama ollama pull llama3.2-vision:11b ;;
+    "") : ;;
+    *) echo "Unrecognized choice '\$VM' — skipping. Pull manually later with:"
+       echo "  docker exec ollama ollama pull <model>" ;;
+esac
+
 echo "" && docker exec ollama ollama list
 PULLSH
 chmod +x "$BASE/pull-models.sh"