perf: feature-gate smart deps, drop ONNX/qdrant from backend binary

wiring `smart` feature gates fastembed+qdrant; bootstrap no longer
links ONNX Runtime (~300 MiB RSS savings). prod compose stripped
to backend-only (no worker/qdrant).
This commit is contained in:
2026-08-08 15:23:39 +02:00
parent 425376874c
commit c7e1a867ed
5 changed files with 39 additions and 70 deletions

View File

@@ -9,58 +9,18 @@ services:
- HOST=0.0.0.0
- PORT=3000
- ALLOW_REGISTRATION=false
- NATS_URL=nats://k_nats:4222
- QDRANT_URL=http://qdrant:6334
- QDRANT_COLLECTION=notes
# SPA is bundled in the image at /app/frontend/dist (set in Dockerfile)
# Override here only if you move the dist elsewhere:
# - SPA_DIR=/app/frontend/dist
volumes:
- ./data:/app/data
networks:
- traefik
- shared-services
- internal
labels:
- "traefik.enable=true"
- "traefik.docker.network=traefik"
# Both the app domain and the API subdomain point to the same service.
# The backend serves /api/v1/* and falls back to the SPA for everything else.
- "traefik.http.routers.knotes.rule=Host(`knotes.gabrielkaszewski.dev`) || Host(`api.knotes.gabrielkaszewski.dev`)"
- "traefik.http.routers.knotes.entrypoints=websecure"
- "traefik.http.routers.knotes.tls.certresolver=letsencrypt"
- "traefik.http.services.knotes.loadbalancer.server.port=3000"
worker:
image: registry.gabrielkaszewski.dev/k-notes:latest
command: ["./worker"]
environment:
- DATABASE_URL=sqlite:///app/data/notes.db
- NATS_URL=nats://k_nats:4222
- QDRANT_URL=http://qdrant:6334
- ENABLE_EMBEDDINGS=true
depends_on:
- backend
- qdrant
volumes:
- ./data:/app/data
networks:
- internal
- shared-services
qdrant:
image: qdrant/qdrant:latest
container_name: k_notes_qdrant
volumes:
- ./data/qdrant_storage:/qdrant/storage:z
restart: unless-stopped
networks:
- internal
networks:
traefik:
external: true
shared-services:
external: true
internal:
driver: bridge

View File

@@ -3,6 +3,10 @@ name = "wiring"
version = "0.1.0"
edition = "2024"
[features]
default = []
smart = ["dep:fastembed-adapter", "dep:qdrant-adapter"]
[dependencies]
# domain + application
domain = { workspace = true }
@@ -13,8 +17,8 @@ sqlite = { workspace = true }
auth = { workspace = true }
event-publisher-memory = { workspace = true }
nats = { workspace = true }
fastembed-adapter = { workspace = true }
qdrant-adapter = { workspace = true }
fastembed-adapter = { workspace = true, optional = true }
qdrant-adapter = { workspace = true, optional = true }
# utilities
tokio = { workspace = true }

View File

@@ -12,7 +12,9 @@ use domain::{
type OptEmbedding = Option<Arc<dyn EmbeddingGenerator>>;
type OptVectorStore = Option<Arc<dyn VectorStore>>;
use event_publisher_memory::MemoryEventBus;
#[cfg(feature = "smart")]
use fastembed_adapter::{FastEmbedConfig, FastEmbedGenerator};
#[cfg(feature = "smart")]
use qdrant_adapter::{QdrantConfig, QdrantVectorStore};
use sqlite::{
db::{connect, run_migrations},
@@ -61,34 +63,38 @@ pub async fn build_context(cfg: &WiringConfig) -> anyhow::Result<AppContext> {
(bus.publisher(), bus.consumer())
};
// ── Smart features ────────────────────────────────────────────────────────
// EmbeddingGenerator: only load the fastembed model in the worker.
// The backend only needs VectorStore (for querying related notes).
// Loading the model in both processes wastes ~150 MB per process.
let embedding: OptEmbedding = if cfg.enable_embeddings && cfg.qdrant_url.is_some() {
tracing::info!("loading fastembed embedding model");
let embedder = FastEmbedGenerator::new(FastEmbedConfig::default())
.map_err(|e| anyhow::anyhow!("fastembed init failed: {e}"))?;
Some(Arc::new(embedder) as Arc<dyn EmbeddingGenerator>)
} else {
None
// ── Smart features (behind "smart" feature flag) ────────────────────────
#[cfg(feature = "smart")]
let (embedding, vector_store): (OptEmbedding, OptVectorStore) = {
let emb: OptEmbedding = if cfg.enable_embeddings && cfg.qdrant_url.is_some() {
tracing::info!("loading fastembed embedding model");
let embedder = FastEmbedGenerator::new(FastEmbedConfig::default())
.map_err(|e| anyhow::anyhow!("fastembed init failed: {e}"))?;
Some(Arc::new(embedder) as Arc<dyn EmbeddingGenerator>)
} else {
None
};
let vs: OptVectorStore = if let Some(ref url) = cfg.qdrant_url {
tracing::info!("connecting to qdrant at {url}");
let qdrant = QdrantVectorStore::new(QdrantConfig {
url: url.clone(),
collection: cfg.qdrant_collection.clone(),
vector_size: cfg.qdrant_vector_size,
})
.map_err(|e| anyhow::anyhow!("qdrant client init failed: {e}"))?;
qdrant.init(cfg.qdrant_vector_size).await?;
tracing::info!(collection = %cfg.qdrant_collection, "qdrant collection ready");
Some(Arc::new(qdrant) as Arc<dyn VectorStore>)
} else {
None
};
(emb, vs)
};
let vector_store: OptVectorStore = if let Some(ref url) = cfg.qdrant_url {
tracing::info!("connecting to qdrant at {url}");
let qdrant = QdrantVectorStore::new(QdrantConfig {
url: url.clone(),
collection: cfg.qdrant_collection.clone(),
vector_size: cfg.qdrant_vector_size,
})
.map_err(|e| anyhow::anyhow!("qdrant client init failed: {e}"))?;
qdrant.init(cfg.qdrant_vector_size).await?;
tracing::info!(collection = %cfg.qdrant_collection, "qdrant collection ready");
Some(Arc::new(qdrant) as Arc<dyn VectorStore>)
} else {
tracing::info!("no QDRANT_URL — smart features disabled");
None
};
#[cfg(not(feature = "smart"))]
let (embedding, vector_store): (OptEmbedding, OptVectorStore) = (None, None);
Ok(AppContext {
repos,

View File

@@ -10,7 +10,7 @@ path = "src/main.rs"
[dependencies]
domain = { workspace = true }
application = { workspace = true }
wiring = { workspace = true }
wiring = { workspace = true, features = ["smart"] }
async-trait = { workspace = true }
dotenvy = "0.15"
tokio = { workspace = true }

View File

@@ -1 +0,0 @@
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="35.93" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 228"><path fill="#00D8FF" d="M210.483 73.824a171.49 171.49 0 0 0-8.24-2.597c.465-1.9.893-3.777 1.273-5.621c6.238-30.281 2.16-54.676-11.769-62.708c-13.355-7.7-35.196.329-57.254 19.526a171.23 171.23 0 0 0-6.375 5.848a155.866 155.866 0 0 0-4.241-3.917C100.759 3.829 77.587-4.822 63.673 3.233C50.33 10.957 46.379 33.89 51.995 62.588a170.974 170.974 0 0 0 1.892 8.48c-3.28.932-6.445 1.924-9.474 2.98C17.309 83.498 0 98.307 0 113.668c0 15.865 18.582 31.778 46.812 41.427a145.52 145.52 0 0 0 6.921 2.165a167.467 167.467 0 0 0-2.01 9.138c-5.354 28.2-1.173 50.591 12.134 58.266c13.744 7.926 36.812-.22 59.273-19.855a145.567 145.567 0 0 0 5.342-4.923a168.064 168.064 0 0 0 6.92 6.314c21.758 18.722 43.246 26.282 56.54 18.586c13.731-7.949 18.194-32.003 12.4-61.268a145.016 145.016 0 0 0-1.535-6.842c1.62-.48 3.21-.974 4.76-1.488c29.348-9.723 48.443-25.443 48.443-41.52c0-15.417-17.868-30.326-45.517-39.844Zm-6.365 70.984c-1.4.463-2.836.91-4.3 1.345c-3.24-10.257-7.612-21.163-12.963-32.432c5.106-11 9.31-21.767 12.459-31.957c2.619.758 5.16 1.557 7.61 2.4c23.69 8.156 38.14 20.213 38.14 29.504c0 9.896-15.606 22.743-40.946 31.14Zm-10.514 20.834c2.562 12.94 2.927 24.64 1.23 33.787c-1.524 8.219-4.59 13.698-8.382 15.893c-8.067 4.67-25.32-1.4-43.927-17.412a156.726 156.726 0 0 1-6.437-5.87c7.214-7.889 14.423-17.06 21.459-27.246c12.376-1.098 24.068-2.894 34.671-5.345a134.17 134.17 0 0 1 1.386 6.193ZM87.276 214.515c-7.882 2.783-14.16 2.863-17.955.675c-8.075-4.657-11.432-22.636-6.853-46.752a156.923 156.923 0 0 1 1.869-8.499c10.486 2.32 22.093 3.988 34.498 4.994c7.084 9.967 14.501 19.128 21.976 27.15a134.668 134.668 0 0 1-4.877 4.492c-9.933 8.682-19.886 14.842-28.658 17.94ZM50.35 144.747c-12.483-4.267-22.792-9.812-29.858-15.863c-6.35-5.437-9.555-10.836-9.555-15.216c0-9.322 13.897-21.212 37.076-29.293c2.813-.98 5.757-1.905 8.812-2.773c3.204 10.42 7.406 21.315 12.477 32.332c-5.137 11.18-9.399 22.249-12.634 32.792a134.718 134.718 0 0 1-6.318-1.979Zm12.378-84.26c-4.811-24.587-1.616-43.134 6.425-47.789c8.564-4.958 27.502 2.111 47.463 19.835a144.318 144.318 0 0 1 3.841 3.545c-7.438 7.987-14.787 17.08-21.808 26.988c-12.04 1.116-23.565 2.908-34.161 5.309a160.342 160.342 0 0 1-1.76-7.887Zm110.427 27.268a347.8 347.8 0 0 0-7.785-12.803c8.168 1.033 15.994 2.404 23.343 4.08c-2.206 7.072-4.956 14.465-8.193 22.045a381.151 381.151 0 0 0-7.365-13.322Zm-45.032-43.861c5.044 5.465 10.096 11.566 15.065 18.186a322.04 322.04 0 0 0-30.257-.006c4.974-6.559 10.069-12.652 15.192-18.18ZM82.802 87.83a323.167 323.167 0 0 0-7.227 13.238c-3.184-7.553-5.909-14.98-8.134-22.152c7.304-1.634 15.093-2.97 23.209-3.984a321.524 321.524 0 0 0-7.848 12.897Zm8.081 65.352c-8.385-.936-16.291-2.203-23.593-3.793c2.26-7.3 5.045-14.885 8.298-22.6a321.187 321.187 0 0 0 7.257 13.246c2.594 4.48 5.28 8.868 8.038 13.147Zm37.542 31.03c-5.184-5.592-10.354-11.779-15.403-18.433c4.902.192 9.899.29 14.978.29c5.218 0 10.376-.117 15.453-.343c-4.985 6.774-10.018 12.97-15.028 18.486Zm52.198-57.817c3.422 7.8 6.306 15.345 8.596 22.52c-7.422 1.694-15.436 3.058-23.88 4.071a382.417 382.417 0 0 0 7.859-13.026a347.403 347.403 0 0 0 7.425-13.565Zm-16.898 8.101a358.557 358.557 0 0 1-12.281 19.815a329.4 329.4 0 0 1-23.444.823c-7.967 0-15.716-.248-23.178-.732a310.202 310.202 0 0 1-12.513-19.846h.001a307.41 307.41 0 0 1-10.923-20.627a310.278 310.278 0 0 1 10.89-20.637l-.001.001a307.318 307.318 0 0 1 12.413-19.761c7.613-.576 15.42-.876 23.31-.876H128c7.926 0 15.743.303 23.354.883a329.357 329.357 0 0 1 12.335 19.695a358.489 358.489 0 0 1 11.036 20.54a329.472 329.472 0 0 1-11 20.722Zm22.56-122.124c8.572 4.944 11.906 24.881 6.52 51.026c-.344 1.668-.73 3.367-1.15 5.09c-10.622-2.452-22.155-4.275-34.23-5.408c-7.034-10.017-14.323-19.124-21.64-27.008a160.789 160.789 0 0 1 5.888-5.4c18.9-16.447 36.564-22.941 44.612-18.3ZM128 90.808c12.625 0 22.86 10.235 22.86 22.86s-10.235 22.86-22.86 22.86s-22.86-10.235-22.86-22.86s10.235-22.86 22.86-22.86Z"></path></svg>

Before

Width:  |  Height:  |  Size: 4.0 KiB