Support custom OpenAI-compatible embedding server with OpenAI fallback

Adds EMBEDDING_SERVER_URL and EMBEDDING_MODEL_NAME env vars, mirroring
the existing LLAMA_SERVER_URL pattern for LLM configuration.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

docker-compose.yml

@@ -31,6 +31,8 @@ services:
       - BASE_URL=${BASE_URL}
       - OLLAMA_URL=${OLLAMA_URL:-http://localhost:11434}
       - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - EMBEDDING_SERVER_URL=${EMBEDDING_SERVER_URL}
+      - EMBEDDING_MODEL_NAME=${EMBEDDING_MODEL_NAME}
       - JWT_SECRET_KEY=${JWT_SECRET_KEY}
       - LLAMA_SERVER_URL=${LLAMA_SERVER_URL}
       - LLAMA_MODEL_NAME=${LLAMA_MODEL_NAME}