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>

.env.example

@@ -19,6 +19,12 @@ BASE_URL=192.168.1.5:8000
 LLAMA_SERVER_URL=http://192.168.1.213:8080/v1
 LLAMA_MODEL_NAME=llama-3.1-8b-instruct
 
+# Embedding Server Configuration
+# If set, uses a custom OpenAI-compatible embedding server (e.g. llama-server)
+# Falls back to OpenAI embeddings if not set
+EMBEDDING_SERVER_URL=http://192.168.1.7:8086/v1
+EMBEDDING_MODEL_NAME=all-minilm
+
 # OpenAI Configuration
 OPENAI_API_KEY=your-openai-api-key