aigw: move to ENV driven easy mode

inference-platforms/aigw/README.md

@@ -3,8 +3,10 @@
 This shows how to use [Envoy AI Gateway][docs] to proxy Ollama, accessible via an
 OpenAI compatible API.
 
-Envoy AI Gateway [YAML configuration](ai-gateway-local.yaml) is processed and run
-by `aigw`, which launches an Envoy proxy to handle requests. OpenTelemetry support
+Envoy AI Gateway is automatically configured by OpenAI and OpenTelemetry
+environment variables read by `aigw run`, such as `OPENAI_API_KEY`.
+
+`aigw run` launches an Envoy proxy to handle requests. OpenTelemetry support
 for GenAI metrics and traces is handled directly in the `aigw` (go) binary.
 
 OpenTelemetry traces produced by Envoy AI Gateway follow the [OpenInference specification][openinference].
@@ -32,7 +34,7 @@ Once Envoy AI Gateway is running, use [uv][uv] to make an OpenAI request via
 [chat.py](../chat.py):
 
 ```bash
-uv run --exact -q --env-file env.local ../chat.py
+OPENAI_BASE_URL=http://localhost:1975/v1 uv run --exact -q --env-file env.local ../chat.py
 ```
 
 ## Notes

inference-platforms/aigw/docker-compose.yml

@@ -21,12 +21,10 @@ services:
     env_file:
       - env.local
     environment:
-      - OPENAI_HOST=host.docker.internal
+      - OPENAI_BASE_URL=http://host.docker.internal:11434/v1
       - OTEL_EXPORTER_OTLP_ENDPOINT=http://host.docker.internal:4318
     ports:
       - "1975:1975"  # OpenAI compatible endpoint at /v1
     extra_hosts:  # localhost:host-gateway trick doesn't work with aigw
       - "host.docker.internal:host-gateway"
-    volumes:
-      - ./ai-gateway-local.yaml:/config.yaml:ro
     command: ["run", "/config.yaml"]

inference-platforms/aigw/env.local

@@ -1,4 +1,5 @@
-OPENAI_BASE_URL=http://localhost:1975/v1
+# Override default ENV variables for Ollama
+OPENAI_BASE_URL=http://localhost:11434/v1
 OPENAI_API_KEY=unused
 CHAT_MODEL=qwen3:0.6B