feat(ai): introduce dedicated AI roles and wiring; clean up legacy AI stack

• Add svc-ai category under roles and load it in constructor stage

• Create new 'svc-ai-ollama' role (vars, tasks, compose, meta, README) and dedicated network

• Refactor former AI stack into separate app roles: web-app-flowise and web-app-openwebui

• Add web-app-minio role; adjust config (no central DB), meta (fa-database, run_after), compose networks include, volume key

• Provide user-focused READMEs for Flowise, OpenWebUI, MinIO, Ollama

• Networks: add subnets for web-app-openwebui, web-app-flowise, web-app-minio; rename web-app-ai → svc-ai-ollama

• Ports: rename ai_* keys to web-app-openwebui / web-app-flowise; keep minio_api/minio_console

• Add group_vars/all/17_ai.yml (OLLAMA_BASE_LOCAL_URL, OLLAMA_LOCAL_ENABLED)

• Replace hardcoded include paths with path_join in multiple roles (svc-db-postgres, sys-service, sys-stk-front-proxy, sys-stk-full-stateful, sys-svc-webserver, web-svc-cdn, web-app-keycloak)

• Remove obsolete web-app-ai templates/vars/env; split Flowise into its own role

• Minor config cleanups (CSP flags to {}, central_database=false)

https://chatgpt.com/share/68d15cb8-cf18-800f-b853-78962f751f81

roles/web-app-flowise/templates/docker-compose.yml.j2

@@ -0,0 +1,48 @@
+{% include 'roles/docker-compose/templates/base.yml.j2' %}
+  litellm:
+{% include 'roles/docker-container/templates/base.yml.j2' %}
+    image: {{ FLOWISE_LITELLM_IMAGE }}:{{ FLOWISE_LITELLM_VERSION }}
+    container_name: {{ FLOWISE_LITELLM_CONTAINER }}
+    depends_on:
+      - ollama
+    expose:
+      - {{ FLOWISE_LITELLM_PORT }}
+    volumes:
+      - {{ FLOWISE_LITELLM_CONFIG_PATH_HOST }}:{{ FLOWISE_LITELLM_CONFIG_PATH_DOCKER }}:ro
+    command: >
+      --host 0.0.0.0
+      --port {{ FLOWISE_LITELLM_PORT }}
+      --config {{ FLOWISE_LITELLM_CONFIG_PATH_DOCKER }}
+{% include 'roles/docker-container/templates/networks.yml.j2' %}
+
+  qdrant:
+{% include 'roles/docker-container/templates/base.yml.j2' %}
+    image: {{ FLOWISE_QDRANT_IMAGE }}:{{ FLOWISE_QDRANT_VERSION }}
+    container_name: {{ FLOWISE_QDRANT_CONTAINER }}
+    ports:
+      - {{ FLOWISE_QDRANT_HTTP_PORT }}
+      - {{ FLOWISE_QDRANT_GRPC_PORT }}
+    volumes:
+      - qdrant_data:/qdrant/storage
+{% include 'roles/docker-container/templates/networks.yml.j2' %}
+
+  flowise:
+{% include 'roles/docker-container/templates/base.yml.j2' %}
+    image: {{ FLOWISE_IMAGE }}:{{ FLOWISE_VERSION }}
+    container_name: {{ FLOWISE_CONTAINER }}
+    depends_on: 
+      - qdrant
+      - litellm
+    ports:
+      - "127.0.0.1:{{ FLOWISE_PORT_PUBLIC }}:{{ FLOWISE_PORT_INTERNAL }}"
+    volumes:
+      - flowise_data:/root/.flowise
+{% include 'roles/docker-container/templates/networks.yml.j2' %}
+
+{% include 'roles/docker-compose/templates/networks.yml.j2' %}
+
+{% include 'roles/docker-compose/templates/volumes.yml.j2' %}
+  qdrant_data:
+    name: {{ FLOWISE_QDRANT_VOLUME }}
+  flowise_data:
+    name: {{ FLOWISE_VOLUME }}

roles/web-app-flowise/templates/env.j2

@@ -0,0 +1,15 @@
+# LiteLLM
+LITELLM_MASTER_KEY=dummy-key
+LITELLM_CONFIG=/etc/litellm/config.yaml
+
+# Flowise
+PORT={{ FLOWISE_PORT_INTERNAL }}
+FLOWISE_USERNAME=admin
+FLOWISE_PASSWORD=admin
+DATABASE_PATH=/root/.flowise
+FLOWISE_FILE_STORAGE_PATH=/root/.flowise/storage
+
+# Qdrant + LiteLLM/Ollama:
+QDRANT_URL={{ FLOWISE_QDRANT_INTERNAL_URL }}
+OPENAI_API_BASE={{ FLOWISE_LITELLM_INTERNAL_URL }}/v1
+OPENAI_API_KEY=dummy-key

roles/web-app-flowise/templates/litellm.config.yaml.j2

@@ -0,0 +1,15 @@
+model_list:
+  - model_name: ollama/llama3
+    litellm_params:
+      model: ollama/llama3
+      api_base: {{ OLLAMA_BASE_LOCAL_URL }}
+      rpm: 1000
+  - model_name: ollama/nomic-embed-text
+    litellm_params:
+      model: ollama/nomic-embed-text
+      api_base: {{ OLLAMA_BASE_LOCAL_URL }}
+      rpm: 1000
+
+litellm_settings:
+  drop_params: true
+  set_verbose: true