fix: make Rust ML Docker build include ONNX runtime assets

- Add 'download-binaries' feature to ort crate in Cargo.toml to ensure ONNX Runtime binaries are downloaded during build
- Update .dockerignore to allow Machine_Learning/model/model.onnx through build context while still excluding other generated model artifacts (saved_model, tfjs_model, tflite)
- Dockerfile can now successfully copy model.onnx at runtime

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

apps/ml-service/Cargo.toml

@@ -8,7 +8,7 @@ anyhow = "1.0"
 axum = { version = "0.7", features = ["multipart"] }
 image = "0.25"
 ndarray = "0.15"
-ort = "2.0.0-rc.10"
+ort = { version = "2.0.0-rc.10", features = ["download-binaries"] }
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
 tokio = { version = "1.0", features = ["macros", "rt-multi-thread", "net"] }