@lancedb/lancedb 0.29.0 → 0.29.1-beta.0

package/dist/table.d.ts

@@ -61,6 +61,26 @@ export interface Version {
     timestamp: Date;
     metadata: Record<string, string>;
 }
+/**
+ * Specification selecting Lance's MemWAL LSM-style write path for
+ * `mergeInsert`.
+ *
+ * `specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
+ * `column` and `numBuckets` are required; for `"identity"`, `column` is
+ * required.
+ */
+export interface LsmWriteSpec {
+    /** One of `"bucket"`, `"identity"`, or `"unsharded"`. */
+    specType: "bucket" | "identity" | "unsharded";
+    /** Bucket and identity variants: the sharding column. */
+    column?: string;
+    /** Bucket variant: the number of buckets, in `[1, 1024]`. */
+    numBuckets?: number;
+    /** Names of indexes the MemWAL should keep up to date during writes. */
+    maintainedIndexes?: string[];
+    /** Default `ShardWriter` configuration recorded in the MemWAL index. */
+    writerConfigDefaults?: Record<string, string>;
+}
 /**
  * A Table is a collection of Records in a LanceDB Database.
  *
@@ -366,6 +386,54 @@ export declare abstract class Table {
      * containing the new version number of the table after dropping the columns.
      */
     abstract dropColumns(columnNames: string[]): Promise<DropColumnsResult>;
+    /**
+     * Set the unenforced primary key for this table to a single column.
+     *
+     * "Unenforced" means LanceDB does not check uniqueness on writes; the
+     * column is recorded in the schema as the primary key for use by features
+     * such as `merge_insert`. Only single-column primary keys are supported,
+     * and the key cannot be changed once set.
+     * @param {string | string[]} columns The primary key column. A one-element
+     * array is also accepted; passing more than one column is rejected.
+     * @returns {Promise<void>}
+     */
+    abstract setUnenforcedPrimaryKey(columns: string | string[]): Promise<void>;
+    /**
+     * Install an {@link LsmWriteSpec} on this table, selecting Lance's MemWAL
+     * LSM-style write path for future `mergeInsert` calls.
+     *
+     * `LsmWriteSpec` chooses one of three sharding strategies via `specType`:
+     *
+     * - `"bucket"` — hash-bucket writes by the single-column unenforced primary
+     *   key (`column` and `numBuckets` required).
+     * - `"identity"` — shard by the raw value of a scalar `column`.
+     * - `"unsharded"` — route every write to a single shard.
+     *
+     * All variants require the table to have an unenforced primary key
+     * ({@link Table#setUnenforcedPrimaryKey}); bucket sharding additionally
+     * requires it to be the single column being bucketed.
+     * @param {LsmWriteSpec} spec The sharding spec to install.
+     * @returns {Promise<void>}
+     * @example
+     * ```ts
+     * await table.setUnenforcedPrimaryKey("id");
+     * await table.setLsmWriteSpec({
+     *   specType: "bucket",
+     *   column: "id",
+     *   numBuckets: 16,
+     *   maintainedIndexes: ["id_idx"],
+     * });
+     * ```
+     */
+    abstract setLsmWriteSpec(spec: LsmWriteSpec): Promise<void>;
+    /**
+     * Remove the {@link LsmWriteSpec} from this table, reverting to the standard
+     * `mergeInsert` write path.
+     *
+     * Errors if no spec is currently set.
+     * @returns {Promise<void>}
+     */
+    abstract unsetLsmWriteSpec(): Promise<void>;
     /** Retrieve the version of the table */
     abstract version(): Promise<number>;
     /**
@@ -527,6 +595,9 @@ export declare class LocalTable extends Table {
     addColumns(newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema): Promise<AddColumnsResult>;
     alterColumns(columnAlterations: ColumnAlteration[]): Promise<AlterColumnsResult>;
     dropColumns(columnNames: string[]): Promise<DropColumnsResult>;
+    setUnenforcedPrimaryKey(columns: string | string[]): Promise<void>;
+    setLsmWriteSpec(spec: LsmWriteSpec): Promise<void>;
+    unsetLsmWriteSpec(): Promise<void>;
     version(): Promise<number>;
     checkout(version: number | string): Promise<void>;
     checkoutLatest(): Promise<void>;

package/dist/table.js

@@ -258,6 +258,16 @@ class LocalTable extends Table {
     async dropColumns(columnNames) {
         return await this.inner.dropColumns(columnNames);
     }
+    async setUnenforcedPrimaryKey(columns) {
+        const cols = typeof columns === "string" ? [columns] : columns;
+        return await this.inner.setUnenforcedPrimaryKey(cols);
+    }
+    async setLsmWriteSpec(spec) {
+        return await this.inner.setLsmWriteSpec(spec);
+    }
+    async unsetLsmWriteSpec() {
+        return await this.inner.unsetLsmWriteSpec();
+    }
     async version() {
         return await this.inner.version();
     }

package/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.29.0",
+  "version": "0.29.1-beta.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -38,15 +38,15 @@
     "url": "https://github.com/lancedb/lancedb"
   },
   "devDependencies": {
-    "@aws-sdk/client-dynamodb": "^3.33.0",
-    "@aws-sdk/client-kms": "^3.33.0",
-    "@aws-sdk/client-s3": "^3.33.0",
+    "@aws-sdk/client-dynamodb": "3.1003.0",
+    "@aws-sdk/client-kms": "3.1003.0",
+    "@aws-sdk/client-s3": "3.1003.0",
     "@biomejs/biome": "^1.7.3",
     "@jest/globals": "^29.7.0",
-    "@napi-rs/cli": "^3.5.1",
+    "@napi-rs/cli": "3.5.1",
     "@types/axios": "^0.14.0",
     "@types/jest": "^29.1.2",
-    "@types/node": "^22.7.4",
+    "@types/node": "22.7.4",
     "@types/tmp": "^0.2.6",
     "apache-arrow-15": "npm:apache-arrow@15.0.0",
     "apache-arrow-16": "npm:apache-arrow@16.0.0",
@@ -57,9 +57,9 @@
     "shx": "^0.3.4",
     "tmp": "^0.2.3",
     "ts-jest": "^29.1.2",
-    "typedoc": "^0.26.4",
-    "typedoc-plugin-markdown": "^4.2.1",
-    "typescript": "^5.5.4",
+    "typedoc": "0.26.4",
+    "typedoc-plugin-markdown": "4.2.1",
+    "typescript": "5.5.4",
     "typescript-eslint": "^7.1.0"
   },
   "ava": {
@@ -68,6 +68,7 @@
   "engines": {
     "node": ">= 18"
   },
+  "packageManager": "pnpm@11.1.1",
   "cpu": [
     "x64",
     "arm64"
@@ -80,10 +81,10 @@
   "scripts": {
     "artifacts": "napi artifacts",
     "build:debug": "napi build --platform --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir lancedb",
-    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
+    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/ && node -e \"require('fs').writeFileSync('dist/package.json', JSON.stringify({name:'@lancedb/lancedb',type:'commonjs'}))\"",
     "build:release": "napi build --platform --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir dist",
-    "build": "npm run build:debug && npm run tsc",
-    "build-release": "npm run build:release && npm run tsc",
+    "build": "pnpm build:debug && pnpm tsc",
+    "build-release": "pnpm build:release && pnpm tsc",
     "tsc": "tsc -b",
     "posttsc": "shx cp lancedb/native.d.ts dist/native.d.ts",
     "lint-ci": "biome ci .",
@@ -93,7 +94,7 @@
     "lint-fix": "biome check --write . && biome format --write .",
     "prepublishOnly": "napi prepublish -t npm",
     "test": "jest --verbose",
-    "integration": "S3_TEST=1 npm run test",
+    "integration": "S3_TEST=1 pnpm test",
     "universal": "napi universalize",
     "version": "napi version"
   },
@@ -101,13 +102,13 @@
     "reflect-metadata": "^0.2.2"
   },
   "optionalDependencies": {
-    "@lancedb/lancedb-darwin-arm64": "0.29.0",
-    "@lancedb/lancedb-linux-x64-gnu": "0.29.0",
-    "@lancedb/lancedb-linux-arm64-gnu": "0.29.0",
-    "@lancedb/lancedb-linux-x64-musl": "0.29.0",
-    "@lancedb/lancedb-linux-arm64-musl": "0.29.0",
-    "@lancedb/lancedb-win32-x64-msvc": "0.29.0",
-    "@lancedb/lancedb-win32-arm64-msvc": "0.29.0"
+    "@lancedb/lancedb-darwin-arm64": "0.29.1-beta.0",
+    "@lancedb/lancedb-linux-x64-gnu": "0.29.1-beta.0",
+    "@lancedb/lancedb-linux-arm64-gnu": "0.29.1-beta.0",
+    "@lancedb/lancedb-linux-x64-musl": "0.29.1-beta.0",
+    "@lancedb/lancedb-linux-arm64-musl": "0.29.1-beta.0",
+    "@lancedb/lancedb-win32-x64-msvc": "0.29.1-beta.0",
+    "@lancedb/lancedb-win32-arm64-msvc": "0.29.1-beta.0"
   },
   "peerDependencies": {
     "apache-arrow": ">=15.0.0 <=18.1.0"

package/pnpm-workspace.yaml

@@ -0,0 +1,18 @@
+# Flat node_modules layout. The @napi-rs/cli build step fails to locate
+# the cdylib artifact under pnpm's isolated layout; the hoisted linker
+# mirrors npm's structure and unblocks the native build.
+nodeLinker: hoisted
+
+# Block resolution of versions less than 24h old (Shai-Hulud window).
+# This is the pnpm 11 default but pinned here so it's visible to
+# reviewers and survives a future pnpm major flipping the default.
+minimumReleaseAge: 1440
+
+# Fail install if a transitive dep tries to run an unapproved script.
+strictDepBuilds: true
+
+allowBuilds:
+  '@biomejs/biome': true
+  onnxruntime-node: true
+  protobufjs: true
+  sharp: true