Add environment configuration and Docker Compose setup for Open WebUI and LiteLLM

containers/open-webui/.env.example

@@ -0,0 +1,14 @@
+# OPEN WEBUI
+OAUTH_CLIENT_ID=
+OAUTH_CLIENT_SECRET=
+AUDIO_STT_AZURE_API_KEY=
+AUDIO_TTS_API_KEY=
+
+# LITELLM
+LITELLM_MODE="PRODUCTION"
+LITELLM_MASTER_KEY=sk-<master_key>
+LITELLM_SALT_KEY=sk-<salt_key>
+AZURE_API_BASE_OPENAI=https://<resource-name>.openai.azure.com/
+AZURE_API_KEY_OPENAI=
+AZURE_API_BASE_AI=https://<resource-name>.services.ai.azure.com/models
+AZURE_API_KEY_AI=

containers/open-webui/docker-compose.yml

@@ -1,27 +1,85 @@
 services:
   openwebui:
     image: ghcr.io/open-webui/open-webui:main
+    container_name: open-webui
     ports:
-      - "4000:8080"
+      - "4080:8080"
     volumes:
       - open-webui:/app/backend/data
+    env_file:
+      - .env
     environment:
-      WEBUI_URL: https://ai.${DOMAIN}
       ENABLE_OPENAI_API: true
-      OPENAI_API_BASE_URL: http://open-webui.home:12345
+      OPENAI_API_BASE_URL: "http://litellm:4000"
       ENABLE_OLLAMA_API: false
+      ENABLE_IMAGE_GENERATION: true
+      IMAGE_SIZE: "1024x1024"
+      IMAGE_GENERATION_MODEL: "Dall-e 3"
       ENABLE_WEB_SEARCH: true
-      WEB_SEARCH_ENGINE: searxng
+      ENABLE_RAG_WEB_SEARCH: True
-      SEARXNG_QUERY_URL: https://search.${DOMAIN}/search?q=<query>
+      RAG_WEB_SEARCH_ENGINE: "searxng"
-      OAUTH_CLIENT_ID: ${OAUTH_CLIENT_ID}
+      RAG_WEB_SEARCH_RESULT_COUNT: 3
-      OAUTH_CLIENT_SECRET: ${OAUTH_CLIENT_SECRET}
+      RAG_WEB_SEARCH_CONCURRENT_REQUESTS: 10
-      OAUTH_PROVIDER_NAME: authentik
+      SEARXNG_QUERY_URL: "https://search.${DOMAIN}/search?q=<query>"
-      OPENID_PROVIDER_URL: https://auth.${DOMAIN}/application/o/openwebui/.well-known/openid-configuration
+      WEB_SEARCH_ENGINE: "searxng"
-      OPENID_REDIRECT_URI: https://ai.${DOMAIN}/oauth/oidc/callback
+      OAUTH_PROVIDER_NAME: "authentik"
+      OPENID_PROVIDER_URL: "https://auth.${DOMAIN}/application/o/openwebui/.well-known/openid-configuration"
+      OPENID_REDIRECT_URI: "https://ai.${DOMAIN}/oauth/oidc/callback"
       ENABLE_OAUTH_SIGNUP: true
       ENABLE_LOGIN_FORM: false
+      AUDIO_STT_ENGINE: "azure"
+      AUDIO_STT_AZURE_REGION: "swedencentral"
+      AUDIO_TTS_ENGINE: "azure"
+      AUDIO_TTS_AZURE_SPEECH_REGION: "swedencentral"
     labels:
       - "com.centurylinklabs.watchtower.enable=true"
 
+  litellm:
+    container_name: litellm
+    image: ghcr.io/berriai/litellm:main-stable
+    volumes:
+      - ./litellm-config.yaml:/app/config.yaml
+    command:
+      - "--config=/app/config.yaml"
+    ports:
+      - "4000:4000" # Map the container port to the host, change the host port if necessary
+    environment:
+      DATABASE_URL: "postgresql://llmproxy:Develop9090@db:5432/litellm"
+    env_file:
+      - .env # Load local .env file
+    depends_on:
+      - db # Indicates that this service depends on the 'db' service, ensuring 'db' starts first
+    healthcheck: # Defines the health check configuration for the container
+      test: [
+          "CMD",
+          "curl",
+          "-f",
+          "http://localhost:4000/health/liveliness || exit 1",
+        ] # Command to execute for health check
+      interval: 30s # Perform health check every 30 seconds
+      timeout: 10s # Health check command times out after 10 seconds
+      retries: 3 # Retry up to 3 times if health check fails
+      start_period: 40s # Wait 40 seconds after container start before beginning health checks
+    labels:
+      - "com.centurylinklabs.watchtower.enable=true"
+
+  db:
+    image: postgres:16
+    restart: always
+    container_name: litellm_db
+    environment:
+      POSTGRES_DB: litellm
+      POSTGRES_USER: llmproxy
+      POSTGRES_PASSWORD: Develop9090
+    volumes:
+      - postgres_data:/var/lib/postgresql/data # Persists Postgres data across container restarts
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -d litellm -U llmproxy"]
+      interval: 1s
+      timeout: 5s
+      retries: 10
+
 volumes:
   open-webui:
+  postgres_data:
+    name: litellm_postgres_data # Named volume for Postgres data persistence

containers/open-webui/litellm-config.yaml

@@ -0,0 +1,78 @@
+environment_variables: {}
+router_settings: {}
+
+general_settings:
+  proxy_batch_write_at: 60 # Batch write spend updates every 60s
+  proxy_batch_write_at: 60 # Batch write spend updates every 60s
+  database_connection_pool_limit: 10 # limit the number of database connections to = MAX Number of DB Connections/Number of instances of litellm proxy (Around 10-20 is good number)
+  # OPTIONAL Best Practices
+  disable_spend_logs: True # turn off writing each transaction to the db. We recommend doing this is you don't need to see Usage on the LiteLLM UI and are tracking metrics via Prometheus
+  disable_error_logs: True # turn off writing LLM Exceptions to DB
+  allow_requests_on_db_unavailable: True # Only USE when running LiteLLM on your VPC. Allow requests to still be processed even if the DB is unavailable. We recommend doing this if you're running LiteLLM on VPC that cannot be accessed from the public internet.
+  store_model_in_db: True
+
+litellm_settings:
+  request_timeout: 600    # raise Timeout error if call takes longer than 600 seconds. Default value is 6000seconds if not set
+  set_verbose: False      # Switch off Debug Logging, ensure your logs do not have any debugging on
+  json_logs: true         # Get debug logs in json format
+
+credential_list:
+  - credential_name: azure_openai_credential
+    credential_values:
+      api_base: os.environ/AZURE_API_BASE_OPENAI
+      api_key: os.environ/AZURE_API_KEY_OPENAI
+    credential_info:
+      description: Azure OpenAI credentials
+  - credential_name: azure_ai_credential
+    credential_values:
+      api_base: os.environ/AZURE_API_BASE_AI
+      api_key: os.environ/AZURE_API_KEY_AI
+    credential_info:
+      description: Azure AI credentials
+
+model_list:
+  - model_name: text-embedding-3-large
+    litellm_params:
+      model: azure/text-embedding-3-large
+      litellm_credential_name: azure_openai_credential
+  - model_name: text-embedding-3-small
+    litellm_params:
+      model: azure/text-embedding-3-small
+      litellm_credential_name: azure_openai_credential
+  - model_name: GPT-4.1
+    litellm_params:
+      model: azure/gpt-4.1
+      litellm_credential_name: azure_openai_credential
+  - model_name: GPT-4.1 Mini
+    litellm_params:
+      model: azure/gpt-4.1-mini
+      litellm_credential_name: azure_openai_credential
+  - model_name: GPT-3.5 Turbo
+    litellm_params:
+      model: azure/gpt-3.5-turbo
+      litellm_credential_name: azure_openai_credential
+  - model_name: GPT-4o
+    litellm_params:
+      model: azure/gpt-4o
+      litellm_credential_name: azure_openai_credential
+  - model_name: GPT-4o Mini
+    litellm_params:
+      model: azure/gpt-4o-mini
+      litellm_credential_name: azure_openai_credential
+  - model_name: o3 Mini
+    litellm_params:
+      model: azure/o3-mini
+      api_version: 2024-12-01-preview
+      litellm_credential_name: azure_openai_credential
+  - model_name: GPT-4o Audio
+    litellm_params:
+      model: azure/azure-openai-4o-audio
+      litellm_credential_name: azure_openai_credential
+  - model_name: Dall-e 3
+    litellm_params:
+      model: azure/dall-e-3
+      litellm_credential_name: azure_openai_credential
+  - model_name: DeepSeek-R1
+    litellm_params:
+      model: azure_ai/DeepSeek-R1
+      litellm_credential_name: azure_ai_credential