feat: parameterize embedding service port and update configuration do…

Dockerfile

@@ -37,6 +37,7 @@ COPY --from=builder /usr/local/bin/warmup /usr/local/bin/warmup
 ARG EMBEDDING_MODELS=nomic,bge-small
 RUN EMBEDDING_MODELS="${EMBEDDING_MODELS}" EMBEDDING_POOL_SIZE=1 /usr/local/bin/warmup
 
-EXPOSE 3000
+ARG EMBEDDING_PORT=3000
+EXPOSE ${EMBEDDING_PORT}
 
 ENTRYPOINT ["/usr/local/bin/embedding"]

README.md

@@ -16,6 +16,17 @@ curl -X POST http://localhost:3000/embed \
   -d '{"texts":["hello world","another piece of text"]}'
 ```
 
+## Configuration
+
+Configured via environment variables (set them in `.env`):
+
+| Variable | Default | Description |
+| --- | --- | --- |
+| `EMBEDDING_PORT` | `3000` | Port the service listens on. |
+| `EMBEDDING_MODELS` | `nomic` | Comma-separated list of models to load. |
+| `EMBEDDING_CACHE_DIR` | _(default cache)_ | Directory for downloaded model files. |
+| `EMBEDDING_POOL_SIZE` | _(memory-derived)_ | Number of model instances per pool. |
+
 ## API
 
 ### `POST /embed`

docker-compose.yml

@@ -8,7 +8,7 @@ services:
     image: embedding:latest
     container_name: embedding
     ports:
-      - "3000:3000"
+      - "${EMBEDDING_PORT:-3000}:${EMBEDDING_PORT:-3000}"
     env_file:
       - .env
     volumes:

src/main.rs

@@ -82,7 +82,8 @@ async fn main() -> Result<(), Box<dyn std::error::Error + Send + Sync>> {
 
     let app = Router::new().route("/embed", post(embed)).with_state(state);
 
-    let addr = std::env::var("BIND_ADDR").unwrap_or_else(|_| "0.0.0.0:3000".to_string());
+    let port = std::env::var("EMBEDDING_PORT").unwrap_or_else(|_| "3000".to_string());
+    let addr = format!("0.0.0.0:{}", port);
     let listener = tokio::net::TcpListener::bind(&addr).await?;
     tracing::info!("listening on {}", addr);
     axum::serve(listener, app)