Revert testing changes from commit a40104e7

- Restore docker-compose.yml to use image instead of build with config.yaml
- Remove steps_to_repro.md (testing file)

docker-compose.yml

@@ -4,21 +4,21 @@ services:
       context: .
       args:
         target: runtime
-#    image: docker.litellm.ai/berriai/litellm:main-stable
-    volumes:
-      - ./config.yaml:/app/config.yaml # Mount your config file
-    command:
-      - "--config=/app/config.yaml"
+    image: docker.litellm.ai/berriai/litellm:main-stable
+    #########################################
+    ## Uncomment these lines to start proxy with a config.yaml file ##
+    # volumes:
+    #  - ./config.yaml:/app/config.yaml
+    # command:
+    #  - "--config=/app/config.yaml"
+    ##############################################
     ports:
-      - "4000:4000" # Main proxy port
-      - "4001:4001" # Separate health app port
+      - "4000:4000" # Map the container port to the host, change the host port if necessary
     environment:
       DATABASE_URL: "postgresql://llmproxy:dbpassword9090@db:5432/litellm"
       STORE_MODEL_IN_DB: "True" # allows adding models to proxy via UI
-      SEPARATE_HEALTH_APP: "1" # Enable separate health check app
-      SEPARATE_HEALTH_PORT: "4001" # Port for health app (default is 4001)
-    # env_file:
-    #   - .env # Optional: Load local .env file if it exists
+    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

steps_to_repro.md

@@ -1,17 +0,0 @@
-1. docker compose up
-2. Start the fake LLM provider and make sure the delay is set to 10sec
-3. Make the request, and wait 3 seconds:
-``` bash
-# Create the JSON file first
-@'
-{"model":"db-openai-endpoint","messages":[{"role":"user","content":"Say hello"}],"max_tokens":2000}
-'@ | Out-File -FilePath request.json -Encoding utf8
-
-# Then use it with curl
-curl.exe -X POST http://localhost:4000/v1/chat/completions -H "Content-Type: application/json" -d "@request.json"
-```
-4. On a different terminal run:
-```bash
-docker kill --signal=SIGTERM (docker ps --filter "name=litellm" --format "{{.Names}}" | Select-Object -First 1)
-```
-5. Check if the call gets terminated or if LiteLLM waits the 10 seconds.