docs(aigw): README and docker-compose updates for image generation (gpt-image-1-mini 1024x1024 low); align examples and services

Signed-off-by: Hrushikesh Patil <[email protected]>

Author: nutanix-Hrushikesh

cmd/aigw/README.md

@@ -80,11 +80,11 @@ Here are values we use for Ollama:
 
 4. **Create embeddings**:
 
-   The `create-embeddings` service uses `curl` to send an embeddings request
+   The `embeddings` service uses `curl` to send an embeddings request
    to the AI Gateway CLI (aigw) which routes it to Ollama.
 
    ```bash
-   docker compose run --rm create-embeddings
+   docker compose run --rm embeddings
    ```
 
 5. **Shutdown the example stack**:

cmd/aigw/docker-compose-otel.yaml

@@ -105,34 +105,16 @@ services:
       - OPENAI_BASE_URL=http://aigw:1975/v1
       - OPENAI_API_KEY=unused
 
-  # embeddings is the standard OpenAI client (`openai` in pip), instrumented
+  # create-embeddings is the standard OpenAI client (`openai` in pip), instrumented
   # with the following OpenTelemetry instrumentation libraries:
   # - openinference-instrumentation-openai (embeddings spans)
   # - opentelemetry-instrumentation-httpx (HTTP client spans and trace headers)
-  embeddings:
+  create-embeddings:
     build:
       context: ../../tests/internal/testopeninference
       dockerfile: Dockerfile.openai_client
       target: create-embeddings
-    container_name: embeddings
-    profiles: ["test"]
-    env_file:
-      - ../../.env.ollama
-      - .env.otel.${COMPOSE_PROFILES:-console}
-    environment:
-      - OPENAI_BASE_URL=http://aigw:1975/v1
-      - OPENAI_API_KEY=unused
-
-  # completion is the standard OpenAI client (`openai` in pip), instrumented
-  # with the following OpenTelemetry instrumentation libraries:
-  # - openinference-instrumentation-openai (completions spans)
-  # - opentelemetry-instrumentation-httpx (HTTP client spans and trace headers)
-  completion:
-    build:
-      context: ../../tests/internal/testopeninference
-      dockerfile: Dockerfile.openai_client
-      target: completion
-    container_name: completion
+    container_name: create-embeddings
     profiles: ["test"]
     env_file:
       - ../../.env.ollama