Add docs

.github/workflows/docs-ci.yml

@@ -0,0 +1,93 @@
+name: Docs CI
+
+on:
+  push:
+    branches: [main]
+    paths:
+      - "docs/**"
+  pull_request:
+    branches: [main]
+    paths:
+      - "docs/**"
+
+# Cancel in-progress runs for the same branch/PR to save resources
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  format:
+    name: Format Check
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: "22"
+      - name: Setup PNPM
+        uses: pnpm/action-setup@v4
+        with:
+          version: "10.11.0"
+          run_install: false
+      - name: Get pnpm store directory
+        id: pnpm-cache
+        shell: bash
+        run: |
+          echo "STORE_PATH=$(pnpm store path)" >> $GITHUB_OUTPUT
+      - name: Setup pnpm cache
+        uses: actions/cache@v4
+        with:
+          path: ${{ steps.pnpm-cache.outputs.STORE_PATH }}
+          key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/docs/pnpm-lock.yaml') }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-store-
+      - name: Install dependencies
+        working-directory: ./docs
+        run: pnpm install
+      - name: Check formatting
+        working-directory: ./docs
+        run: pnpm prettier --check . 
+
+  build:
+    name: Validate Build
+    runs-on: ubuntu-latest
+    needs: [format]
+    steps:
+      - uses: actions/checkout@v6
+      - name: Setup Node.js
+        uses: actions/setup-node@v6
+        with:
+          node-version: "22"
+      - name: Setup PNPM
+        uses: pnpm/action-setup@v4
+        with:
+          version: "10.11.0"
+          run_install: false
+      - name: Get pnpm store directory
+        id: pnpm-cache
+        shell: bash
+        run: |
+          echo "STORE_PATH=$(pnpm store path)" >> $GITHUB_OUTPUT
+      - name: Setup pnpm cache
+        uses: actions/cache@v4
+        with:
+          path: ${{ steps.pnpm-cache.outputs.STORE_PATH }}
+          key: ${{ runner.os }}-pnpm-store-${{ hashFiles('**/docs/pnpm-lock.yaml') }}
+          restore-keys: |
+            ${{ runner.os }}-pnpm-store-
+      - name: Install dependencies
+        working-directory: ./docs
+        run: pnpm install
+      - name: Validate build
+        working-directory: ./docs
+        run: pnpm build:dry-run
+
+  vale-lint:
+    name: Vale lint
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v6
+      - uses: errata-ai/vale-action@v2.1.1
+        with:
+          files: "docs/src/content/"

.vale.ini

@@ -0,0 +1,17 @@
+StylesPath = .github/styles
+
+MinAlertLevel = suggestion
+
+Packages = Google, write-good, MDX
+
+Vocab = embucket
+
+[*.{md,mdx}]
+BasedOnStyles = Vale, Google, write-good
+
+[formats]
+mdx = md
+
+[*.mdx]
+CommentDelimiters = {/*, */}
+TokenIgnores = (import\s+[^;]+;)

README.md

@@ -24,7 +24,18 @@ Embucket features:
 Start Embucket and run your first query in 30 seconds:
 
 ```bash
-docker run --name embucket --rm -p 3000:3000 embucket/embucket
+mkdir -p config
+cat > config/metastore.yaml <<'EOF'
+volumes:
+  - ident: embucket
+    type: memory
+    database: embucket
+EOF
+
+docker run --name embucket --rm -p 3000:3000 \
+  -v $PWD/config:/app/config \
+  embucket/embucket \
+  ./embucketd --metastore-config config/metastore.yaml
 ```
 
 Install and configure the Snowflake CLI against the local endpoint:
@@ -100,7 +111,6 @@ docker run --name embucket --rm -p 3000:3000 \
 
 ```bash
 ./embucketd \
-  --no-bootstrap \
   --metastore-config config/metastore.yaml
 ```
 

crates/embucket-lambda/Cargo.toml

@@ -45,7 +45,7 @@ default-binary = "bootstrap"
 [package.metadata.lambda.deploy]
 # Function name: Can be set via CARGO_LAMBDA_FUNCTION_NAME env var
 # If not set, falls back to binary name or pass as CLI argument
-memory = 3008
+memory = 1024
 timeout = 30
 tracing = "Active"
 # Note: include path is relative to workspace root
@@ -55,3 +55,6 @@ include = ["config"]
 [package.metadata.lambda.deploy.env]
 LOG_FORMAT = "json"
 METASTORE_CONFIG = "config/metastore.yaml"
+JWT_SECRET = "secret"
+QUERY_TIMEOUT_SECS = "29"
+MEM_POOL_SIZE_MB = "800"

crates/embucket-lambda/src/config.rs

@@ -14,7 +14,6 @@ pub struct EnvConfig {
     pub mem_enable_track_consumers_pool: Option<bool>,
     pub disk_pool_size_mb: Option<usize>,
     pub query_history_rows_limit: usize,
-    pub bootstrap_default_entities: bool,
     pub embucket_version: String,
     pub metastore_config: Option<PathBuf>,
     pub jwt_secret: Option<String>,
@@ -38,7 +37,6 @@ impl EnvConfig {
             disk_pool_size_mb: parse_env("DISK_POOL_SIZE_MB"),
             query_history_rows_limit: parse_env("QUERY_HISTORY_ROWS_LIMIT")
                 .unwrap_or(DEFAULT_QUERY_HISTORY_ROWS_LIMIT),
-            bootstrap_default_entities: !env_bool("NO_BOOTSTRAP"),
             embucket_version: env_or_default("EMBUCKET_VERSION", "0.1.0"),
             metastore_config: env::var("METASTORE_CONFIG").ok().map(PathBuf::from),
             jwt_secret: env::var("JWT_SECRET").ok(),
@@ -51,7 +49,6 @@ impl EnvConfig {
     pub fn execution_config(&self) -> ExecutionConfig {
         ExecutionConfig {
             embucket_version: self.embucket_version.clone(),
-            bootstrap_default_entities: self.bootstrap_default_entities,
             sql_parser_dialect: self.sql_parser_dialect.clone(),
             query_timeout_secs: self.query_timeout_secs,
             max_concurrency_level: self.max_concurrency_level,
@@ -70,12 +67,6 @@ fn env_or_default(name: &str, default: &str) -> String {
     env::var(name).unwrap_or_else(|_| default.to_string())
 }
 
-fn env_bool(name: &str) -> bool {
-    env::var(name)
-        .map(|value| matches!(value.to_lowercase().as_str(), "1" | "true" | "yes" | "on"))
-        .unwrap_or(false)
-}
-
 fn parse_mem_pool_type() -> Option<MemPoolType> {
     env::var("MEM_POOL_TYPE")
         .ok()

crates/embucket-lambda/src/main.rs

@@ -47,7 +47,6 @@ async fn main() -> Result<(), LambdaError> {
         mem_pool_type = ?env_config.mem_pool_type,
         mem_pool_size_mb = ?env_config.mem_pool_size_mb,
         disk_pool_size_mb = ?env_config.disk_pool_size_mb,
-        bootstrap_default_entities = env_config.bootstrap_default_entities,
         read_only = env_config.read_only,
         metastore_config = env_config.metastore_config.as_ref().map(|p| p.display().to_string()),
         "Loaded Lambda configuration"

crates/embucketd/src/cli.rs

@@ -6,14 +6,6 @@ use tracing_subscriber::filter::LevelFilter;
 #[derive(Parser)]
 #[command(version, about, long_about=None)]
 pub struct CliOpts {
-    #[arg(
-        long,
-        env = "NO_BOOTSTRAP",
-        default_value = "false",
-        help = "Disable bootstrap functionality"
-    )]
-    pub no_bootstrap: bool,
-
     #[arg(
         long,
         env = "METASTORE_CONFIG",

crates/embucketd/src/main.rs

@@ -129,14 +129,8 @@ async fn async_main(
             opts.auth_demo_password.clone().unwrap(),
         );
 
-    // Bootstrap the service if no flag is present (`--no-bootstrap`) with:
-    // 1. Creation of a default in-memory volume named `embucket`
-    // 2. Creation of a default database `embucket` in the volume `embucket`
-    // 3. Creation of a default schema `public` in the database `embucket`
-
     let execution_cfg = ExecutionConfig {
         embucket_version: "0.1.0".to_string(),
-        bootstrap_default_entities: !opts.no_bootstrap,
         sql_parser_dialect: opts.sql_parser_dialect.clone(),
         query_timeout_secs: opts.query_timeout_secs,
         max_concurrency_level: opts.max_concurrency_level,

crates/executor/src/error.rs

@@ -600,15 +600,6 @@ pub enum Error {
         location: Location,
     },
 
-    #[snafu(display("Failed to bootstrap {entity_type}: {source}"))]
-    Bootstrap {
-        entity_type: String,
-        #[snafu(source(from(catalog_metastore::error::Error, Box::new)))]
-        source: Box<catalog_metastore::error::Error>,
-        #[snafu(implicit)]
-        location: Location,
-    },
-
     #[snafu(display("Failed to get async result for query [{query_id}]: {error}"))]
     AsyncResultTaskJoin {
         #[snafu(source)]

crates/executor/src/service.rs

@@ -31,18 +31,13 @@ use crate::running_queries::RunningQueryId;
 use crate::session::{SESSION_INACTIVITY_EXPIRATION_SECONDS, to_unix};
 use crate::tracing::SpanTracer;
 use crate::utils::{Config, MemPoolType};
-use catalog::catalog_list::{DEFAULT_CATALOG, EmbucketCatalogList};
-use catalog_metastore::{
-    Database, InMemoryMetastore, Metastore, Schema, SchemaIdent, TableIdent as MetastoreTableIdent,
-    Volume, VolumeType,
-};
+use catalog::catalog_list::EmbucketCatalogList;
+use catalog_metastore::{InMemoryMetastore, Metastore, TableIdent as MetastoreTableIdent};
 use tokio::sync::RwLock;
 use tokio::time::Duration;
 use tracing::Instrument;
 use uuid::Uuid;
 
-const DEFAULT_SCHEMA: &str = "public";
-
 pub const TIMEOUT_SIGNAL_INTERVAL_SECONDS: u64 = 60;
 
 #[async_trait::async_trait]
@@ -159,11 +154,6 @@ impl CoreExecutionService {
         err
     )]
     pub async fn new(metastore: Arc<dyn Metastore>, config: Arc<Config>) -> Result<Self> {
-        if config.bootstrap_default_entities {
-            // do not fail on bootstrap errors
-            let _ = Self::bootstrap(metastore.clone()).await;
-        }
-
         Self::initialize_datafusion_tracer();
 
         let catalog_list = Self::catalog_list(metastore.clone(), &config).await?;
@@ -178,60 +168,6 @@ impl CoreExecutionService {
         })
     }
 
-    ///This function bootstraps the service if no flag is present (`--no-bootstrap`) with:
-    /// 1. Creation of a default in-memory volume named `embucket`
-    /// 2. Creation of a default database `embucket` in the volume `embucket`
-    /// 3. Creation of a default schema `public` in the database `embucket`
-    ///
-    /// Only traces the errors, doesn't panic.
-    #[tracing::instrument(
-        name = "CoreExecutionService::bootstrap",
-        level = "info",
-        skip(metastore),
-        err
-    )]
-    #[allow(clippy::cognitive_complexity)]
-    async fn bootstrap(metastore: Arc<dyn Metastore>) -> Result<()> {
-        let ident = DEFAULT_CATALOG.to_string();
-        metastore
-            .create_volume(&ident, Volume::new(ident.clone(), VolumeType::Memory))
-            .await
-            .context(ex_error::BootstrapSnafu {
-                entity_type: "volume",
-            })?;
-
-        metastore
-            .create_database(
-                &ident,
-                Database {
-                    ident: ident.clone(),
-                    properties: None,
-                    volume: ident.clone(),
-                    should_refresh: false,
-                },
-            )
-            .await
-            .context(ex_error::BootstrapSnafu {
-                entity_type: "database",
-            })?;
-
-        let schema_ident = SchemaIdent::new(ident.clone(), DEFAULT_SCHEMA.to_string());
-        metastore
-            .create_schema(
-                &schema_ident,
-                Schema {
-                    ident: schema_ident.clone(),
-                    properties: None,
-                },
-            )
-            .await
-            .context(ex_error::BootstrapSnafu {
-                entity_type: "schema",
-            })?;
-
-        Ok(())
-    }
-
     #[tracing::instrument(
         name = "CoreExecutionService::catalog_list",
         level = "debug",

crates/executor/src/utils.rs

@@ -34,8 +34,6 @@ pub static DEFAULT_QUERY_HISTORY_ROWS_LIMIT: usize = 50;
 #[derive(Clone, Debug)]
 pub struct Config {
     pub embucket_version: String,
-    /// If true, bootstrap default volume, database and schema
-    pub bootstrap_default_entities: bool,
     pub sql_parser_dialect: Option<String>,
     pub query_timeout_secs: u64,
     pub max_concurrency_level: usize,
@@ -60,7 +58,6 @@ impl Default for Config {
     fn default() -> Self {
         Self {
             embucket_version: "0.1.0".to_string(),
-            bootstrap_default_entities: true,
             sql_parser_dialect: None,
             query_timeout_secs: 1200, // 20 minutes
             max_concurrency_level: 100,
@@ -88,15 +85,6 @@ impl Config {
         self
     }
 
-    #[must_use]
-    pub const fn with_bootstrap_default_entities(
-        mut self,
-        bootstrap_default_entities: bool,
-    ) -> Self {
-        self.bootstrap_default_entities = bootstrap_default_entities;
-        self
-    }
-
     #[must_use]
     pub const fn with_query_history_rows_limit(mut self, limit: usize) -> Self {
         self.query_history_rows_limit = limit;

docs/.gitignore

@@ -0,0 +1,24 @@
+# Dependencies
+node_modules
+.pnpm-debug.log*
+
+# Build artifacts
+/dist
+/.astro
+
+# OS-specific
+.DS_Store
+*.swo
+*~
+*.swp
+
+# Logs
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+# Environment variables
+.env
+.env*.local