Establish clean homelab infrastructure baseline

Reorganize the brownfield repository, remove retired and generated artifacts, harden ignore rules, and record the GitOps/IaC redesign.
2026-09-09 16:47:20 +00:00
commit 88a02ababa
418 changed files with 50579 additions and 0 deletions
@@ -0,0 +1,42 @@
+model_list:
+  - model_name: chatgpt/gpt-5.4
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.4
+  - model_name: chatgpt/gpt-5.4-pro
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.4-pro
+  - model_name: chatgpt/gpt-5.3-codex
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-codex
+  - model_name: chatgpt/gpt-5.3-codex-spark
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-codex-spark
+  - model_name: chatgpt/gpt-5.3-instant
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-instant
+  - model_name: chatgpt/gpt-5.3-chat-latest
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.3-chat-latest
+  - model_name: chatgpt/gpt-5.4-mini
+    model_info:
+      mode: responses
+    litellm_params:
+      model: chatgpt/gpt-5.4-mini
+  - model_name: hf/google/embeddinggemma-300m
+    model_info:
+      mode: embedding
+    litellm_params:
+      model: huggingface/google/embeddinggemma-300m
+      api_key: os.environ/HF_TOKEN
@@ -0,0 +1,65 @@
+services:
+  litellm:
+    build:
+      context: .
+      args:
+        target: runtime
+    image: docker.litellm.ai/berriai/litellm:dev
+    #########################################
+    ## Uncomment these lines to start proxy with a config.yaml file ##
+    volumes:
+      - ./config.yaml:/app/config.yaml
+      - ./auth.json:/root/.config/litellm/chatgpt/auth.json
+    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:${POSTGRES_PASSWORD}@db:5432/litellm"
+      STORE_MODEL_IN_DB: "True" # allows adding models to proxy via UI
+    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-SHELL
+        - python3 -c "import urllib.request; urllib.request.urlopen('http://localhost:4000/health/liveliness')"  # 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
+
+  db:
+    image: postgres:16
+    restart: always
+    container_name: litellm_db
+    environment:
+      POSTGRES_DB: litellm
+      POSTGRES_USER: llmproxy
+      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
+    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
+
+  prometheus:
+    image: prom/prometheus
+    volumes:
+      - prometheus_data:/prometheus
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+    command:
+      - "--config.file=/etc/prometheus/prometheus.yml"
+      - "--storage.tsdb.path=/prometheus"
+      - "--storage.tsdb.retention.time=15d"
+    restart: always
+
+volumes:
+  prometheus_data:
+    driver: local
+  postgres_data:
+    name: litellm_postgres_data # Named volume for Postgres data persistence
@@ -0,0 +1,8 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: "litellm"
+    static_configs:
+      - targets: ["litellm:4000"]