chore: add docker-compose for gpu setup

Signed-off-by: mudler <mudler@localai.io>

docker-compose.gpu.yaml

@@ -0,0 +1,74 @@
+services:
+  localai:
+    # See https://localai.io/basics/container/#standard-container-images for
+    # a list of available container images (or build your own with the provided Dockerfile)
+    # Available images with CUDA, ROCm, SYCL, Vulkan
+    # Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags
+    # Image list (dockerhub): https://hub.docker.com/r/localai/localai
+    image: localai/localai:latest-gpu-nvidia-cuda-12
+    command: 
+    - qwen_qwq-32b
+    - granite-embedding-107m-multilingual
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
+      interval: 10s
+      timeout: 20m
+      retries: 20
+    ports:
+    - 8081:8080
+    environment:
+      - DEBUG=true
+    volumes:
+      - ./volumes/models:/build/models:cached
+      - ./volumes/images:/tmp/generated/images
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+  ragserver:
+    image: quay.io/mudler/localrag
+    ports:
+      - 8080
+    environment:
+      - COLLECTION_DB_PATH=/db
+      - EMBEDDING_MODEL=granite-embedding-107m-multilingual
+      - FILE_ASSETS=/assets
+      - OPENAI_API_KEY=sk-1234567890
+      - OPENAI_BASE_URL=http://localai:8080
+    volumes:
+      - ./volumes/localrag/db:/db
+      - ./volumes/localrag/assets/:/assets
+
+  ragserver-healthcheck:
+    depends_on:
+      ragserver:
+        condition: service_started
+    image: busybox
+    command: ["sh", "-c", "until wget -q -O - http://ragserver:8080 > /dev/null 2>&1; do echo 'Waiting for ragserver...'; sleep 1; done; echo 'RagServer is up!'"]
+
+  localagent:
+    depends_on:
+      localai:
+        condition: service_healthy
+      ragserver-healthcheck:
+        condition: service_completed_successfully
+    build:
+      context: .
+      dockerfile: Dockerfile.webui
+    ports:
+      - 8080:3000
+    environment:
+      - LOCALAGENT_MODEL=arcee-agent
+      - LOCALAGENT_LLM_API_URL=http://localai:8080
+      - LOCALAGENT_API_KEY=sk-1234567890
+      - LOCALAGENT_LOCALRAG_URL=http://ragserver:8080
+      - LOCALAGENT_STATE_DIR=/pool
+      - LOCALAGENT_TIMEOUT=5m
+      - LOCALAGENT_ENABLE_CONVERSATIONS_LOGGING=false
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - ./volumes/localagent/:/pool

docker-compose.yaml

@@ -1,6 +1,6 @@
 services:
   localai:
-    # See https://localai.io/basics/getting_started/#container-images for
+    # See https://localai.io/basics/container/#standard-container-images for
     # a list of available container images (or build your own with the provided Dockerfile)
     # Available images with CUDA, ROCm, SYCL, Vulkan
     # Image list (quay.io): https://quay.io/repository/go-skynet/local-ai?tab=tags