Fix duplicate OPENSEARCH_PASSWORD and remove legacy docker-compose-cpu.yml

- Remove duplicate OPENSEARCH_PASSWORD in docker-compose.yml line 136
- Delete legacy docker-compose-cpu.yml file
- Update Makefile to use base docker-compose.yml for CPU mode
- Update Makefile to use docker-compose.yml + docker-compose.gpu.yml for GPU mode
- Update documentation to reflect new architecture
- Remove all references to docker-compose-cpu.yml from docs

Co-authored-by: phact <1313220+phact@users.noreply.github.com>

Makefile

@@ -55,7 +55,7 @@ help:
 # Development environments
 dev:
 	@echo "🚀 Starting OpenRAG with GPU support..."
-	docker compose up -d
+	docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
 	@echo "✅ Services started!"
 	@echo "   Backend: http://localhost:8000"
 	@echo "   Frontend: http://localhost:3000"
@@ -65,7 +65,7 @@ dev:
 
 dev-cpu:
 	@echo "🚀 Starting OpenRAG with CPU only..."
-	docker compose -f docker-compose-cpu.yml up -d
+	docker compose up -d
 	@echo "✅ Services started!"
 	@echo "   Backend: http://localhost:8000"
 	@echo "   Frontend: http://localhost:3000"
@@ -93,7 +93,7 @@ infra:
 
 infra-cpu:
 	@echo "🔧 Starting infrastructure services only..."
-	docker-compose -f docker-compose-cpu.yml up -d opensearch dashboards langflow
+	docker compose up -d opensearch dashboards langflow
 	@echo "✅ Infrastructure services started!"
 	@echo "   Langflow: http://localhost:7860"
 	@echo "   OpenSearch: http://localhost:9200"
@@ -103,14 +103,12 @@ infra-cpu:
 stop:
 	@echo "🛑 Stopping all containers..."
 	docker compose down
-	docker compose -f docker-compose-cpu.yml down 2>/dev/null || true
 
 restart: stop dev
 
 clean: stop
 	@echo "🧹 Cleaning up containers and volumes..."
 	docker compose down -v --remove-orphans
-	docker compose -f docker-compose-cpu.yml down -v --remove-orphans 2>/dev/null || true
 	docker system prune -f
 
 # Local development
@@ -210,13 +208,13 @@ test-ci:
 		chmod 644 keys/public_key.pem 2>/dev/null || true; \
 	fi; \
 	echo "Cleaning up old containers and volumes..."; \
-	docker compose -f docker-compose-cpu.yml down -v 2>/dev/null || true; \
+	docker compose down -v 2>/dev/null || true; \
 	echo "Pulling latest images..."; \
-	docker compose -f docker-compose-cpu.yml pull; \
+	docker compose pull; \
 	echo "Building OpenSearch image override..."; \
 	docker build --no-cache -t langflowai/openrag-opensearch:latest -f Dockerfile .; \
 	echo "Starting infra (OpenSearch + Dashboards + Langflow + Backend + Frontend) with CPU containers"; \
-	docker compose -f docker-compose-cpu.yml up -d opensearch dashboards langflow openrag-backend openrag-frontend; \
+	docker compose up -d opensearch dashboards langflow openrag-backend openrag-frontend; \
 	echo "Starting docling-serve..."; \
 	DOCLING_ENDPOINT=$$(uv run python scripts/docling_ctl.py start --port 5001 | grep "Endpoint:" | awk '{print $$2}'); \
 	echo "Docling-serve started at $$DOCLING_ENDPOINT"; \
@@ -288,7 +286,7 @@ test-ci:
 	echo ""; \
 	echo "Tearing down infra"; \
 	uv run python scripts/docling_ctl.py stop || true; \
-	docker compose -f docker-compose-cpu.yml down -v 2>/dev/null || true; \
+	docker compose down -v 2>/dev/null || true; \
 	exit $$TEST_RESULT
 
 # CI-friendly integration test target with local builds: builds all images, brings up infra, waits, runs tests, tears down
@@ -305,14 +303,14 @@ test-ci-local:
 		chmod 644 keys/public_key.pem 2>/dev/null || true; \
 	fi; \
 	echo "Cleaning up old containers and volumes..."; \
-	docker compose -f docker-compose-cpu.yml down -v 2>/dev/null || true; \
+	docker compose down -v 2>/dev/null || true; \
 	echo "Building all images locally..."; \
 	docker build -t langflowai/openrag-opensearch:latest -f Dockerfile .; \
 	docker build -t langflowai/openrag-backend:latest -f Dockerfile.backend .; \
 	docker build -t langflowai/openrag-frontend:latest -f Dockerfile.frontend .; \
 	docker build -t langflowai/openrag-langflow:latest -f Dockerfile.langflow .; \
 	echo "Starting infra (OpenSearch + Dashboards + Langflow + Backend + Frontend) with CPU containers"; \
-	docker compose -f docker-compose-cpu.yml up -d opensearch dashboards langflow openrag-backend openrag-frontend; \
+	docker compose up -d opensearch dashboards langflow openrag-backend openrag-frontend; \
 	echo "Starting docling-serve..."; \
 	DOCLING_ENDPOINT=$$(uv run python scripts/docling_ctl.py start --port 5001 | grep "Endpoint:" | awk '{print $$2}'); \
 	echo "Docling-serve started at $$DOCLING_ENDPOINT"; \
@@ -394,7 +392,7 @@ test-ci-local:
 	fi; \
 	echo "Tearing down infra"; \
 	uv run python scripts/docling_ctl.py stop || true; \
-	docker compose -f docker-compose-cpu.yml down -v 2>/dev/null || true; \
+	docker compose down -v 2>/dev/null || true; \
 	exit $$TEST_RESULT
 
 # SDK integration tests (requires running OpenRAG instance)

docker-compose-cpu.yml

@@ -1,143 +0,0 @@
-services:
-  opensearch:
-    image: langflowai/openrag-opensearch:${OPENRAG_VERSION:-latest}
-    #build:
-    #  context: .
-    #  dockerfile: Dockerfile
-    container_name: os
-    depends_on:
-      - openrag-backend
-    environment:
-      - discovery.type=single-node
-      - OPENSEARCH_INITIAL_ADMIN_PASSWORD=${OPENSEARCH_PASSWORD}
-    # Run security setup in background after OpenSearch starts
-    command: >
-      bash -c "
-        # Ensure data directory has correct permissions
-        sudo chown -R opensearch:opensearch /usr/share/opensearch/data || true
-        
-        # Start OpenSearch in background
-        /usr/share/opensearch/opensearch-docker-entrypoint.sh opensearch &
-
-        # Wait a bit for OpenSearch to start, then apply security config
-        sleep 10 && /usr/share/opensearch/setup-security.sh &
-
-        # Wait for background processes
-        wait
-      "
-    ports:
-      - "9200:9200"
-      - "9600:9600"
-    volumes:
-      - ${OPENSEARCH_DATA_PATH:-./opensearch-data}:/usr/share/opensearch/data:Z
-
-  dashboards:
-    image: opensearchproject/opensearch-dashboards:3.0.0
-    container_name: osdash
-    depends_on:
-      - opensearch
-    environment:
-      OPENSEARCH_HOSTS: '["https://opensearch:9200"]'
-      OPENSEARCH_USERNAME: "admin"
-      OPENSEARCH_PASSWORD: ${OPENSEARCH_PASSWORD}
-    ports:
-      - "5601:5601"
-
-  openrag-backend:
-    image: langflowai/openrag-backend:${OPENRAG_VERSION:-latest}
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile.backend
-    container_name: openrag-backend
-    depends_on:
-      - langflow
-    environment:
-      - OPENSEARCH_HOST=opensearch
-      - LANGFLOW_URL=http://langflow:7860
-      - LANGFLOW_PUBLIC_URL=${LANGFLOW_PUBLIC_URL}
-      - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
-      - LANGFLOW_SECRET_KEY=${LANGFLOW_SECRET_KEY}
-      - LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
-      - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
-      - LANGFLOW_CHAT_FLOW_ID=${LANGFLOW_CHAT_FLOW_ID}
-      - LANGFLOW_INGEST_FLOW_ID=${LANGFLOW_INGEST_FLOW_ID}
-      - LANGFLOW_URL_INGEST_FLOW_ID=${LANGFLOW_URL_INGEST_FLOW_ID}
-      - DISABLE_INGEST_WITH_LANGFLOW=${DISABLE_INGEST_WITH_LANGFLOW:-false}
-      - NUDGES_FLOW_ID=${NUDGES_FLOW_ID}
-      - OPENSEARCH_PORT=9200
-      - OPENSEARCH_USERNAME=admin
-      - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
-      - OPENAI_API_KEY=${OPENAI_API_KEY}
-      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
-      - WATSONX_API_KEY=${WATSONX_API_KEY}
-      - WATSONX_ENDPOINT=${WATSONX_ENDPOINT}
-      - WATSONX_PROJECT_ID=${WATSONX_PROJECT_ID}
-      - OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT}
-      - GOOGLE_OAUTH_CLIENT_ID=${GOOGLE_OAUTH_CLIENT_ID}
-      - GOOGLE_OAUTH_CLIENT_SECRET=${GOOGLE_OAUTH_CLIENT_SECRET}
-      - MICROSOFT_GRAPH_OAUTH_CLIENT_ID=${MICROSOFT_GRAPH_OAUTH_CLIENT_ID}
-      - MICROSOFT_GRAPH_OAUTH_CLIENT_SECRET=${MICROSOFT_GRAPH_OAUTH_CLIENT_SECRET}
-      - WEBHOOK_BASE_URL=${WEBHOOK_BASE_URL}
-      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
-      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
-    volumes:
-      - ./openrag-documents:/app/openrag-documents:Z
-      - ./keys:/app/keys:Z
-      - ./flows:/app/flows:U,z
-      - ./config:/app/config:Z
-
-  openrag-frontend:
-    image: langflowai/openrag-frontend:${OPENRAG_VERSION:-latest}
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile.frontend
-    container_name: openrag-frontend
-    depends_on:
-      - openrag-backend
-    environment:
-      - OPENRAG_BACKEND_HOST=openrag-backend
-    ports:
-      - "3000:3000"
-
-  langflow:
-    volumes:
-      - ./flows:/app/flows:U,z
-    image: langflowai/openrag-langflow:${LANGFLOW_VERSION:-latest}
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile.langflow
-    container_name: langflow
-    ports:
-      - "7860:7860"
-    environment:
-      - LANGFLOW_DEACTIVATE_TRACING=true
-      - OPENAI_API_KEY=${OPENAI_API_KEY}
-      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
-      - WATSONX_API_KEY=${WATSONX_API_KEY}
-      - WATSONX_ENDPOINT=${WATSONX_ENDPOINT}
-      - WATSONX_PROJECT_ID=${WATSONX_PROJECT_ID}
-      - OLLAMA_BASE_URL=${OLLAMA_ENDPOINT}
-      - LANGFLOW_LOAD_FLOWS_PATH=/app/flows
-      - LANGFLOW_SECRET_KEY=${LANGFLOW_SECRET_KEY}
-      - JWT=None  
-      - OWNER=None
-      - OWNER_NAME=None
-      - OWNER_EMAIL=None
-      - CONNECTOR_TYPE=system
-      - CONNECTOR_TYPE_URL=url
-      - OPENRAG-QUERY-FILTER="{}"
-      - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
-      - FILENAME=None
-      - MIMETYPE=None
-      - FILESIZE=0
-      - SELECTED_EMBEDDING_MODEL=${SELECTED_EMBEDDING_MODEL:-}
-      - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE,SELECTED_EMBEDDING_MODEL
-      - LANGFLOW_LOG_LEVEL=DEBUG
-      - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}
-      - LANGFLOW_SUPERUSER=${LANGFLOW_SUPERUSER}
-      - LANGFLOW_SUPERUSER_PASSWORD=${LANGFLOW_SUPERUSER_PASSWORD}
-      - LANGFLOW_NEW_USER_IS_ACTIVE=${LANGFLOW_NEW_USER_IS_ACTIVE}
-      - LANGFLOW_ENABLE_SUPERUSER_CLI=${LANGFLOW_ENABLE_SUPERUSER_CLI}
-      # - DEFAULT_FOLDER_NAME=OpenRAG
-      - HIDE_GETTING_STARTED_PROGRESS=true
-

docker-compose.yml

@@ -133,7 +133,6 @@ services:
       - MIMETYPE=None
       - FILESIZE=0
       - SELECTED_EMBEDDING_MODEL=${SELECTED_EMBEDDING_MODEL:-}
-      - OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
       - LANGFLOW_VARIABLES_TO_GET_FROM_ENVIRONMENT=JWT,OPENRAG-QUERY-FILTER,OPENSEARCH_PASSWORD,OWNER,OWNER_NAME,OWNER_EMAIL,CONNECTOR_TYPE,FILENAME,MIMETYPE,FILESIZE,SELECTED_EMBEDDING_MODEL,OPENAI_API_KEY,ANTHROPIC_API_KEY,WATSONX_API_KEY,WATSONX_ENDPOINT,WATSONX_PROJECT_ID,OLLAMA_BASE_URL
       - LANGFLOW_LOG_LEVEL=DEBUG
       - LANGFLOW_AUTO_LOGIN=${LANGFLOW_AUTO_LOGIN}

docs/docs/get-started/docker.mdx

@@ -114,29 +114,26 @@ The following variables are required or recommended:
    PID: 27746
    ```
 
-3. Deploy the OpenRAG containers locally using the appropriate Docker Compose file for your environment.
-Both files deploy the same services.
+3. Deploy the OpenRAG containers locally using the appropriate Docker Compose configuration for your environment.
 
-   * [`docker-compose.yml`](https://github.com/langflow-ai/openrag/blob/main/docker-compose.yml): If your host machine has an NVIDIA GPU with CUDA support and compatible NVIDIA drivers, you can use this file  to deploy OpenRAG with accelerated processing.
+   * **CPU-only deployment** (default): If your host machine doesn't have NVIDIA GPU support, use the base `docker-compose.yml` file.
 
       ```bash title="Docker"
-      docker compose build
       docker compose up -d
       ```
 
       ```bash title="Podman"
-      podman compose build
       podman compose up -d
       ```
 
-   * [`docker-compose-cpu.yml`](https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml): If your host machine doesn't have NVIDIA GPU support, use this file for a CPU-only OpenRAG deployment.
+   * **GPU-accelerated deployment**: If your host machine has an NVIDIA GPU with CUDA support and compatible NVIDIA drivers, use the base `docker-compose.yml` file with the `docker-compose.gpu.yml` override.
 
       ```bash title="Docker"
-      docker compose -f docker-compose-cpu.yml up -d
+      docker compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
       ```
 
       ```bash title="Podman"
-      podman compose -f docker-compose-cpu.yml up -d
+      podman compose -f docker-compose.yml -f docker-compose.gpu.yml up -d
       ```
 
 4. Wait for the OpenRAG containers to start, and then confirm that all containers are running:

docs/docs/support/troubleshoot.mdx

@@ -38,7 +38,7 @@ For more information about this variable and how this variable controls Langflow
 
 ## Container out of memory errors
 
-Increase Docker memory allocation or use [docker-compose-cpu.yml](https://github.com/langflow-ai/openrag/blob/main/docker-compose-cpu.yml) to deploy OpenRAG.
+Increase Docker memory allocation or use the CPU-only deployment (base `docker-compose.yml` without GPU override) to reduce memory usage.
 
 ## Memory issue with Podman on macOS