Merge origin/main into gatekeeper/fix-1289-1

# Conflicts:
#	nodejs/lancedb/arrow.ts
#	nodejs/lancedb/embedding/registry.ts

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.37.1-beta.0"
+version = "0.38.0-beta.3"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -16,12 +16,12 @@ crate-type = ["cdylib"]
 async-trait.workspace = true
 arrow-ipc.workspace = true
 arrow-array.workspace = true
-arrow-buffer = "58.0.0"
+arrow-buffer.workspace = true
 half.workspace = true
 arrow-schema.workspace = true
 env_logger.workspace = true
 futures.workspace = true
-lancedb = { path = "../rust/lancedb", default-features = false }
+lancedb.workspace = true
 lance-namespace.workspace = true
 napi = { version = "3.8.3", default-features = false, features = [
     "napi9",
@@ -29,8 +29,8 @@ napi = { version = "3.8.3", default-features = false, features = [
     "chrono_date",
     "serde-json",
 ] }
-chrono = { version = "0.4", default-features = false, features = ["clock"] }
-serde_json = "1"
+chrono.workspace = true
+serde_json.workspace = true
 napi-derive = "3.5.2"
 # Prevent dynamic linking of lzma, which comes from datafusion
 lzma-sys = { version = "0.1", features = ["static"] }

nodejs/__test__/arrow.test.ts

@@ -6,7 +6,9 @@ import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";
 
 import {
+  Vector as CurrentVector,
   convertToTable,
+  tableFromIPC as currentTableFromIPC,
   fromBufferToRecordBatch,
   fromDataToBuffer,
   fromRecordBatchToBuffer,
@@ -19,6 +21,7 @@ import {
   FunctionOptions,
 } from "../lancedb/embedding/embedding_function";
 import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
+import { sanitizeTable } from "../lancedb/sanitize";
 
 // biome-ignore lint/suspicious/noExplicitAny: skip
 function sampleRecords(): Array<Record<string, any>> {
@@ -64,7 +67,11 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       tableFromIPC,
       DataType,
       Dictionary,
+      RecordBatch: ArrowRecordBatch,
+      Table: ArrowTable,
       Uint8: ArrowUint8,
+      makeData: arrowMakeData,
+      vectorFromArray,
       // biome-ignore lint/suspicious/noExplicitAny: <explanation>
     } = <any>arrow;
     type Schema = ApacheArrow["Schema"];
@@ -166,6 +173,36 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
     }
 
     describe("The function makeArrowTable", function () {
+      it("accepts snake_case embedding metadata like camelCase", function () {
+        const spellings = [
+          // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+          { source_column: "text", vector_column: "vector" },
+          { sourceColumn: "text", vectorColumn: "vector" },
+        ];
+        for (const columns of spellings) {
+          const schema = new Schema(
+            [
+              new Field("text", new Utf8(), false),
+              new Field(
+                "vector",
+                new FixedSizeList(3, new Field("item", new Float32(), true)),
+                false,
+              ),
+            ],
+            new Map([
+              [
+                "embedding_functions",
+                JSON.stringify([{ name: "mock", model: {}, ...columns }]),
+              ],
+            ]),
+          );
+          // The vector field is non-nullable and absent from the data; only a
+          // recognized embedding config makes that acceptable.
+          const table = makeArrowTable([{ text: "hello" }], { schema });
+          expect(table.numRows).toBe(1);
+        }
+      });
+
       it("will use data types from a provided schema instead of inference", async function () {
         const schema = new Schema([
           new Field("a", new Int32(), false),
@@ -1054,6 +1091,114 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
     });
 
     describe("when using two versions of arrow", function () {
+      it("preserves a dictionary shared by multiple fields", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const batch = new ArrowRecordBatch({
+          first: dictionaryVector.data[0],
+          second: dictionaryVector.data[0],
+        });
+        const table = new ArrowTable([batch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("first")!]).toEqual(values);
+        expect([...sanitized.getChild("second")!]).toEqual(values);
+        const firstType = sanitized.schema.fields[0].type as {
+          dictionary: unknown;
+        };
+        const secondType = sanitized.schema.fields[1].type as {
+          dictionary: unknown;
+        };
+        expect(secondType.dictionary).toBe(firstType.dictionary);
+        expect(sanitized.batches[0].data.children[1].dictionary).toBe(
+          sanitized.batches[0].data.children[0].dictionary,
+        );
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("first")!]).toEqual(values);
+        expect([...actual.getChild("second")!]).toEqual(values);
+      });
+
+      it("preserves shared dictionary data from another Arrow version", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const firstBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(0, 2).data[0],
+        });
+        const secondBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(2).data[0],
+        });
+        const table = new ArrowTable([firstBatch, secondBatch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("label")!]).toEqual(values);
+
+        const dictionaries = sanitized.batches.map(
+          (batch) => batch.data.children[0].dictionary,
+        );
+        expect(dictionaries[0]).toBeInstanceOf(CurrentVector);
+        expect(dictionaries[1]).toBe(dictionaries[0]);
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(values);
+      });
+
+      it("preserves shared chunks in growing dictionaries", async function () {
+        const type = new Dictionary(new Utf8(), new Int32(), 42, false);
+        const firstDictionary = vectorFromArray(["alpha", "beta"], new Utf8());
+        const secondDictionary = firstDictionary.concat(
+          vectorFromArray(["gamma"], new Utf8()),
+        );
+        const firstData = arrowMakeData({
+          type,
+          data: Int32Array.from([0, 1]),
+          dictionary: firstDictionary,
+        });
+        const secondData = arrowMakeData({
+          type,
+          data: Int32Array.from([2]),
+          dictionary: secondDictionary,
+        });
+        const table = new ArrowTable([
+          new ArrowRecordBatch({ label: firstData }),
+          new ArrowRecordBatch({ label: secondData }),
+        ]);
+
+        const sanitized = sanitizeTable(table);
+        const expected = ["alpha", "beta", "gamma"];
+        expect([...sanitized.getChild("label")!]).toEqual(expected);
+        const firstLocalDictionary =
+          sanitized.batches[0].data.children[0].dictionary!;
+        const secondLocalDictionary =
+          sanitized.batches[1].data.children[0].dictionary!;
+        expect(secondLocalDictionary.data[0]).toBe(
+          firstLocalDictionary.data[0],
+        );
+
+        const buf = await fromTableToBuffer(sanitized);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(expected);
+      });
+
+      it("can serialize list data from another Arrow version", async function () {
+        const values = [["anime", "action"], [], null];
+        const vector = vectorFromArray(
+          values,
+          new List(new Field("item", new Utf8(), true)),
+        );
+        const table = new ArrowTable({ tags: vector });
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        const actualTags = actual.getChild("tags");
+
+        expect(actualTags?.get(0)?.toJSON()).toEqual(values[0]);
+        expect(actualTags?.get(1)?.toJSON()).toEqual(values[1]);
+        expect(actualTags?.get(2)).toBeNull();
+      });
+
       it("can still import data", async function () {
         const schema = new arrow15.Schema([
           new arrow15.Field("id", new arrow15.Int32()),

nodejs/__test__/connection.test.ts

@@ -89,6 +89,16 @@ describe("given a connection", () => {
     await db.createTable("test4", [{ id: 1 }, { id: 2 }]);
   });
 
+  it("should return a completed job when dropping a local table", async () => {
+    await db.createTable("async-drop", [{ id: 1 }]);
+
+    const job = await db.dropTableAsync("async-drop");
+    expect(job.id).toBeNull();
+    await expect(job.status()).resolves.toBe("finished");
+    await job.wait();
+    await expect(db.tableNames()).resolves.toEqual([]);
+  });
+
   it("should fail if creating table twice, unless overwrite is true", async () => {
     let tbl = await db.createTable("test", [{ id: 1 }, { id: 2 }]);
     await expect(tbl.countRows()).resolves.toBe(2);

nodejs/__test__/registry.test.ts

@@ -106,6 +106,77 @@ describe.each([arrow15, arrow16, arrow17, arrow18])("Registry", (arrow) => {
       'Embedding function with alias "mock-embedding" already exists',
     );
   });
+  test("parseFunctions keeps entries sharing a function name", async () => {
+    class MockEmbeddingFunction extends EmbeddingFunction<string> {
+      ndims() {
+        return 3;
+      }
+      embeddingDataType() {
+        return new arrow.Float32() as apiArrow.Float;
+      }
+      async computeSourceEmbeddings(data: string[]) {
+        return data.map(() => [1, 2, 3]);
+      }
+    }
+    register("mock-embedding")(MockEmbeddingFunction);
+    const parsed = await getRegistry().parseFunctions(
+      new Map([
+        [
+          "embedding_functions",
+          JSON.stringify([
+            {
+              name: "mock-embedding",
+              sourceColumn: "text",
+              vectorColumn: "vector_a",
+              model: {},
+            },
+            {
+              name: "mock-embedding",
+              sourceColumn: "text",
+              vectorColumn: "vector_b",
+              model: {},
+            },
+          ]),
+        ],
+      ]),
+    );
+    expect([...parsed.values()].map((f) => f.vectorColumn)).toEqual([
+      "vector_a",
+      "vector_b",
+    ]);
+
+    // The Python bindings write snake_case keys.
+    const snake = await getRegistry().parseFunctions(
+      new Map([
+        [
+          "embedding_functions",
+          JSON.stringify([
+            {
+              name: "mock-embedding",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              source_column: "text",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              vector_column: "vector_a",
+              model: {},
+            },
+            {
+              name: "mock-embedding",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              source_column: "text",
+              // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+              vector_column: "vector_b",
+              model: {},
+            },
+          ]),
+        ],
+      ]),
+    );
+    expect([...snake.keys()]).toEqual(["vector_a", "vector_b"]);
+    expect([...snake.values()].map((f) => f.sourceColumn)).toEqual([
+      "text",
+      "text",
+    ]);
+  });
   test("schema should contain correct metadata", async () => {
     class MockEmbeddingFunction extends EmbeddingFunction<string> {
       constructor(args: FunctionOptions = {}) {

nodejs/__test__/table.test.ts

@@ -277,8 +277,16 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         },
         numIndices: 0,
         numRows: 3,
-        totalBytes: 44,
+        // Full on-disk size of the two data files, footers and metadata included.
+        totalBytes: 684,
       });
+
+      // Index files count toward totalBytes too (only deletion files and
+      // manifests are excluded).
+      await table.createIndex("id", { config: Index.btree() });
+      const statsWithIndex = await table.stats();
+      expect(statsWithIndex.numIndices).toBe(1);
+      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
     });
 
     it("should overwrite data if asked", async () => {
@@ -3332,3 +3340,120 @@ describe("LSM merge insert", () => {
     await expect(table.query().useLsm(true).toArray()).rejects.toThrow();
   });
 });
+
+describe("LSM convergence and stats", () => {
+  let tmpDir: tmp.DirResult;
+
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  async function lsmTable(conn: Connection): Promise<Table> {
+    const table = await conn.createEmptyTable(
+      "t",
+      new arrow.Schema([new arrow.Field("id", new arrow.Utf8(), false)]),
+    );
+    await table.setUnenforcedPrimaryKey("id");
+    await table.setLsmWriteSpec({ specType: "unsharded" });
+    return table;
+  }
+
+  // These four route through the server that owns the MemWAL, so a local table
+  // rejects them rather than answering. What is asserted here is that the
+  // bindings reach the core at all; the behavior against a real endpoint is
+  // covered by the mocked endpoint tests in rust/lancedb/src/remote/table.rs.
+  it("rejects flushLsm on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    await expect(table.flushLsm()).rejects.toThrow(/not supported/i);
+  });
+
+  it("rejects compactLsm on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    await expect(table.compactLsm()).rejects.toThrow(/not supported/i);
+  });
+
+  it("rejects getLsmStats on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    await expect(table.getLsmStats()).rejects.toThrow(/not supported/i);
+    await expect(table.getLsmStats(true)).rejects.toThrow(/not supported/i);
+  });
+
+  it("rejects checkpointLsm on a local table", async () => {
+    const conn = await connect(tmpDir.name);
+    const table = await lsmTable(conn);
+
+    // checkpointLsm seals first, so it surfaces flushLsm's rejection.
+    await expect(table.checkpointLsm()).rejects.toThrow(/not supported/i);
+  });
+});
+
+describe("computed columns", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("declares a column and fills it on refresh", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("computed", [{ x: 1 }, { x: 2 }]);
+
+    await table.addColumns({
+      computed: [{ name: "doubled", valueSql: "x * 2" }],
+    });
+    let rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled)).toEqual([null, null]);
+
+    const result = await table.refreshColumn("doubled");
+    expect(result.rowsFilled).toBe(2);
+
+    rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled).sort()).toEqual([2, 4]);
+  });
+
+  it("returns a job handle from refreshColumnAsync", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("computed_job", [{ x: 1 }, { x: 2 }]);
+
+    await table.addColumns({
+      computed: [{ name: "doubled", valueSql: "x * 2" }],
+    });
+
+    const job = await table.refreshColumnAsync("doubled");
+    expect(job.id).toBeNull();
+    await job.wait();
+    expect(await job.status()).toBe("finished");
+
+    const rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled).sort()).toEqual([2, 4]);
+
+    // Bad input rejects at the call, not through the job.
+    await expect(table.refreshColumnAsync("x")).rejects.toThrow(
+      "not a computed column",
+    );
+  });
+
+  it("fills rows added since the last refresh", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("computed_append", [{ x: 1 }]);
+
+    await table.addColumns({
+      computed: [{ name: "doubled", valueSql: "x * 2" }],
+    });
+    await table.refreshColumn("doubled");
+    await table.add([{ x: 5 }]);
+
+    const result = await table.refreshColumn("doubled");
+    expect(result.rowsFilled).toBe(1);
+
+    const rows = await table.query().toArray();
+    expect(rows.map((r) => r.doubled).sort()).toEqual([10, 2]);
+  });
+});

nodejs/lancedb/arrow.ts

@@ -48,8 +48,11 @@ import {
 } from "apache-arrow";
 import { Buffers } from "apache-arrow/data";
 import { type EmbeddingFunction } from "./embedding/embedding_function";
-import { parseEmbeddingFunctionMetadata } from "./embedding/metadata";
-import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
+import {
+  EmbeddingFunctionConfig,
+  getRegistry,
+  parseEmbeddingMetadata,
+} from "./embedding/registry";
 import {
   sanitizeField,
   sanitizeSchema,
@@ -934,7 +937,7 @@ async function applyEmbeddingsFromMetadata(
 
   for (const functionEntry of functions.values()) {
     const sourceColumn = columns[functionEntry.sourceColumn];
-    const destColumn = functionEntry.vectorColumn ?? "vector";
+    const destColumn = functionEntry.vectorColumn;
     if (sourceColumn === undefined) {
       throw new Error(
         `Cannot apply embedding function because the source column '${functionEntry.sourceColumn}' was not present in the data`,
@@ -1386,13 +1389,10 @@ function validateSchemaEmbeddings(
 
         // Check schema metadata for embedding functions
         if (schema.metadata.has("embedding_functions")) {
-          const embeddings = parseEmbeddingFunctionMetadata(schema.metadata);
-          if (
-            embeddings.find(
-              (embedding) =>
-                (embedding.vectorColumn ?? "vector") === field.name,
-            )
-          ) {
+          const entries = parseEmbeddingMetadata(
+            schema.metadata.get("embedding_functions")!,
+          );
+          if (entries.some((f) => f.vectorColumn === field.name)) {
             hasEmbeddingFunction = true;
           }
         }

nodejs/lancedb/connection.ts

@@ -327,6 +327,14 @@ export abstract class Connection {
    */
   abstract dropTable(name: string, namespacePath?: string[]): Promise<void>;
 
+  /**
+   * Start dropping a table and return its cleanup job.
+   *
+   * The table may become unavailable before its data files are removed. Wait
+   * on the returned job to know when cleanup has finished.
+   */
+  abstract dropTableAsync(name: string, namespacePath?: string[]): Promise<Job>;
+
   /**
    * Drop all tables in the database.
    * @param {string[]} namespacePath The namespace path to drop tables from (defaults to root namespace).
@@ -705,6 +713,10 @@ export class LocalConnection extends Connection {
     return this.inner.dropTable(name, namespacePath ?? []);
   }
 
+  async dropTableAsync(name: string, namespacePath?: string[]): Promise<Job> {
+    return this.inner.dropTableAsync(name, namespacePath ?? []);
+  }
+
   async dropAllTables(namespacePath?: string[]): Promise<void> {
     return this.inner.dropAllTables(namespacePath ?? []);
   }

nodejs/lancedb/embedding/metadata.ts

@@ -1,50 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import type { EmbeddingFunction } from "./embedding_function";
-
-interface SerializedEmbeddingFunction {
-  name: string;
-  model: EmbeddingFunction["TOptions"];
-  sourceColumn?: string;
-  vectorColumn?: string;
-  [key: string]: unknown;
-}
-
-export interface EmbeddingFunctionMetadata {
-  name: string;
-  model: EmbeddingFunction["TOptions"];
-  sourceColumn: string;
-  vectorColumn?: string;
-}
-
-export function parseEmbeddingFunctionMetadata(
-  metadata: Map<string, string>,
-): EmbeddingFunctionMetadata[] {
-  const serialized = metadata.get("embedding_functions");
-  if (serialized === undefined) {
-    return [];
-  }
-
-  return (JSON.parse(serialized) as SerializedEmbeddingFunction[]).map(
-    (functionMetadata) => {
-      const sourceColumn =
-        functionMetadata.sourceColumn ??
-        (functionMetadata["source_column"] as string | undefined);
-      if (sourceColumn === undefined) {
-        throw new Error(
-          "Embedding function metadata is missing a source column",
-        );
-      }
-
-      return {
-        name: functionMetadata.name,
-        model: functionMetadata.model,
-        sourceColumn,
-        vectorColumn:
-          functionMetadata.vectorColumn ??
-          (functionMetadata["vector_column"] as string | undefined),
-      };
-    },
-  );
-}

nodejs/lancedb/embedding/registry.ts

@@ -5,7 +5,6 @@ import {
   type EmbeddingFunction,
   type EmbeddingFunctionConstructor,
 } from "./embedding_function";
-import { parseEmbeddingFunctionMetadata } from "./metadata";
 import "reflect-metadata";
 
 export type CreateReturnType<T> = T extends { init: () => Promise<void> }
@@ -105,31 +104,29 @@ export class EmbeddingFunctionRegistry {
   async parseFunctions(
     this: EmbeddingFunctionRegistry,
     metadata: Map<string, string>,
-  ): Promise<Map<string, EmbeddingFunctionConfig>> {
-    const functions = parseEmbeddingFunctionMetadata(metadata);
-    if (functions.length === 0) {
+  ): Promise<Map<string, ResolvedEmbeddingFunctionConfig>> {
+    if (!metadata.has("embedding_functions")) {
       return new Map();
-    } else {
-      const items: [string, EmbeddingFunctionConfig][] = await Promise.all(
-        functions.map(async (f) => {
-          const fn = this.get(f.name);
-          if (!fn) {
-            throw new Error(`Function "${f.name}" not found in registry`);
-          }
-          const func = await this.get(f.name)!.create(f.model);
-          return [
-            f.vectorColumn ?? "vector",
-            {
-              sourceColumn: f.sourceColumn,
-              vectorColumn: f.vectorColumn,
-              function: func,
-            },
-          ];
-        }),
-      );
-
-      return new Map(items);
     }
+    const entries = parseEmbeddingMetadata(
+      metadata.get("embedding_functions")!,
+    );
+    const items = await Promise.all(
+      entries.map(async (f): Promise<ResolvedEmbeddingFunctionConfig> => {
+        const fn = this.get(f.name);
+        if (!fn) {
+          throw new Error(`Function "${f.name}" not found in registry`);
+        }
+        const func = await fn.create(f.model);
+        return {
+          sourceColumn: f.sourceColumn,
+          vectorColumn: f.vectorColumn,
+          function: func,
+        };
+      }),
+    );
+    // Keyed by output column: one function may serve several columns.
+    return new Map(items.map((config) => [config.vectorColumn, config]));
   }
   // biome-ignore lint/suspicious/noExplicitAny: <explanation>
   functionToMetadata(conf: EmbeddingFunctionConfig): Record<string, any> {
@@ -209,3 +206,52 @@ export interface EmbeddingFunctionConfig {
   vectorColumn?: string;
   function: EmbeddingFunction;
 }
+
+/** An [EmbeddingFunctionConfig] read back from table metadata, where the
+ * vector column is always recorded. */
+export type ResolvedEmbeddingFunctionConfig = EmbeddingFunctionConfig & {
+  vectorColumn: string;
+};
+
+/** One entry of the `embedding_functions` schema metadata, with the column
+ * keys normalized across the bindings' spellings. */
+export type EmbeddingMetadataEntry = {
+  name: string;
+  sourceColumn: string;
+  vectorColumn: string;
+  model: EmbeddingFunction["TOptions"];
+};
+
+/** The single parser for `embedding_functions` schema metadata: every reader
+ * goes through here, so the wire contract cannot fork between them. */
+export function parseEmbeddingMetadata(json: string): EmbeddingMetadataEntry[] {
+  // The wire format, honestly: the Python bindings write snake_case keys.
+  type Raw = {
+    name: string;
+    sourceColumn?: string;
+    // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+    source_column?: string;
+    vectorColumn?: string;
+    // biome-ignore lint/style/useNamingConvention: the Python wire spelling
+    vector_column?: string;
+    model: EmbeddingFunction["TOptions"];
+  };
+  const entries = <Raw[]>JSON.parse(json);
+  const seen = new Set<string>();
+  return entries.map((f) => {
+    const sourceColumn = f.sourceColumn ?? f.source_column;
+    const vectorColumn = f.vectorColumn ?? f.vector_column;
+    if (sourceColumn === undefined || vectorColumn === undefined) {
+      throw new Error(
+        `Embedding function "${f.name}" metadata names no source or vector column`,
+      );
+    }
+    if (seen.has(vectorColumn)) {
+      throw new Error(
+        `Multiple embedding configs claim vector column "${vectorColumn}"`,
+      );
+    }
+    seen.add(vectorColumn);
+    return { name: f.name, sourceColumn, vectorColumn, model: f.model };
+  });
+}

nodejs/lancedb/index.ts

@@ -50,6 +50,7 @@ export {
   MergeResult,
   AddResult,
   AddColumnsResult,
+  RefreshColumnResult,
   AlterColumnsResult,
   UpdateFieldMetadataResult,
   DeleteResult,
@@ -146,6 +147,10 @@ export {
   FtsToken,
   TokenizeTableOptions,
   LsmWriteSpec,
+  LsmStats,
+  BucketStats,
+  GenerationStats,
+  MemtableStats,
   ColumnAlteration,
   FieldMetadataUpdate,
 } from "./table";

nodejs/lancedb/sanitize.ts

@@ -9,7 +9,7 @@
 // comes from the exact same library instance.  This is not always the case
 // and so we must sanitize the input to ensure that it is compatible.
 
-import { BufferType, Data } from "apache-arrow";
+import { BufferType, Data, Vector } from "apache-arrow";
 import type { IntBitWidth, TKeys, TimeBitWidth } from "apache-arrow/type";
 import {
   Binary,
@@ -74,6 +74,20 @@ import {
   Utf8,
 } from "./arrow";
 
+type SanitizationContext = {
+  types: WeakMap<object, DataType>;
+  vectors: WeakMap<object, Vector>;
+  data: WeakMap<object, Data<DataType>>;
+};
+
+function createSanitizationContext(): SanitizationContext {
+  return {
+    types: new WeakMap(),
+    vectors: new WeakMap(),
+    data: new WeakMap(),
+  };
+}
+
 export function sanitizeMetadata(
   metadataLike?: unknown,
 ): Map<string, string> | undefined {
@@ -186,6 +200,13 @@ export function sanitizeInterval(typeLike: object) {
 }
 
 export function sanitizeList(typeLike: object) {
+  return sanitizeListWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeListWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
   if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
     throw Error(
       "Expected a List type to have an array-like `children` property",
@@ -194,19 +215,35 @@ export function sanitizeList(typeLike: object) {
   if (typeLike.children.length !== 1) {
     throw Error("Expected a List type to have exactly one child");
   }
-  return new List(sanitizeField(typeLike.children[0]));
+  return new List(sanitizeFieldWithContext(typeLike.children[0], context));
 }
 
 export function sanitizeStruct(typeLike: object) {
+  return sanitizeStructWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeStructWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
   if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
     throw Error(
       "Expected a Struct type to have an array-like `children` property",
     );
   }
-  return new Struct(typeLike.children.map((child) => sanitizeField(child)));
+  return new Struct(
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
+  );
 }
 
 export function sanitizeUnion(typeLike: object) {
+  return sanitizeUnionWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeUnionWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
   if (
     !("typeIds" in typeLike) ||
     !("mode" in typeLike) ||
@@ -226,7 +263,7 @@ export function sanitizeUnion(typeLike: object) {
     typeLike.mode,
     // biome-ignore lint/suspicious/noExplicitAny: skip
     typeLike.typeIds as any,
-    typeLike.children.map((child) => sanitizeField(child)),
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
   );
 }
 
@@ -234,6 +271,19 @@ export function sanitizeTypedUnion(
   typeLike: object,
   // eslint-disable-next-line @typescript-eslint/naming-convention
   UnionType: typeof DenseUnion | typeof SparseUnion,
+) {
+  return sanitizeTypedUnionWithContext(
+    typeLike,
+    UnionType,
+    createSanitizationContext(),
+  );
+}
+
+function sanitizeTypedUnionWithContext(
+  typeLike: object,
+  // eslint-disable-next-line @typescript-eslint/naming-convention
+  UnionType: typeof DenseUnion | typeof SparseUnion,
+  context: SanitizationContext,
 ) {
   if (!("typeIds" in typeLike)) {
     throw Error(
@@ -248,7 +298,7 @@ export function sanitizeTypedUnion(
 
   return new UnionType(
     typeLike.typeIds as Int32Array | number[],
-    typeLike.children.map((child) => sanitizeField(child)),
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
   );
 }
 
@@ -262,6 +312,16 @@ export function sanitizeFixedSizeBinary(typeLike: object) {
 }
 
 export function sanitizeFixedSizeList(typeLike: object) {
+  return sanitizeFixedSizeListWithContext(
+    typeLike,
+    createSanitizationContext(),
+  );
+}
+
+function sanitizeFixedSizeListWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
   if (!("listSize" in typeLike) || typeof typeLike.listSize !== "number") {
     throw Error("Expected a FixedSizeList type to have a `listSize` property");
   }
@@ -275,11 +335,18 @@ export function sanitizeFixedSizeList(typeLike: object) {
   }
   return new FixedSizeList(
     typeLike.listSize,
-    sanitizeField(typeLike.children[0]),
+    sanitizeFieldWithContext(typeLike.children[0], context),
   );
 }
 
 export function sanitizeMap(typeLike: object) {
+  return sanitizeMapWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeMapWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
   if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
     throw Error(
       "Expected a Map type to have an array-like `children` property",
@@ -292,7 +359,10 @@ export function sanitizeMap(typeLike: object) {
     throw Error("Expected a Map type to have exactly one child");
   }
 
-  return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted);
+  return new Map_(
+    sanitizeFieldWithContext(typeLike.children[0], context),
+    typeLike.keysSorted,
+  );
 }
 
 export function sanitizeDuration(typeLike: object) {
@@ -303,6 +373,13 @@ export function sanitizeDuration(typeLike: object) {
 }
 
 export function sanitizeDictionary(typeLike: object) {
+  return sanitizeDictionaryWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeDictionaryWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
   if (!("id" in typeLike) || typeof typeLike.id !== "number") {
     throw Error("Expected a Dictionary type to have an `id` property");
   }
@@ -316,8 +393,8 @@ export function sanitizeDictionary(typeLike: object) {
     throw Error("Expected a Dictionary type to have an `isOrdered` property");
   }
   return new Dictionary(
-    sanitizeType(typeLike.dictionary),
-    sanitizeType(typeLike.indices) as TKeys,
+    sanitizeTypeWithContext(typeLike.dictionary, context),
+    sanitizeTypeWithContext(typeLike.indices, context) as TKeys,
     typeLike.id,
     typeLike.isOrdered,
   );
@@ -325,12 +402,23 @@ export function sanitizeDictionary(typeLike: object) {
 
 // biome-ignore lint/suspicious/noExplicitAny: skip
 export function sanitizeType(typeLike: unknown): DataType<any> {
+  return sanitizeTypeWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeTypeWithContext(
+  typeLike: unknown,
+  context: SanitizationContext,
+): DataType {
   if (typeof typeLike === "string") {
     return dataTypeFromName(typeLike);
   }
   if (typeof typeLike !== "object" || typeLike === null) {
     throw Error("Expected a Type but object was null/undefined");
   }
+  const cached = context.types.get(typeLike);
+  if (cached !== undefined) {
+    return cached;
+  }
   if (
     !("typeId" in typeLike) ||
     !(
@@ -349,6 +437,16 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
     throw Error("Type's typeId property was not a function or number");
   }
 
+  const type = sanitizeTypeById(typeLike, typeId, context);
+  context.types.set(typeLike, type);
+  return type;
+}
+
+function sanitizeTypeById(
+  typeLike: object,
+  typeId: Type,
+  context: SanitizationContext,
+): DataType {
   switch (typeId) {
     case Type.NONE:
       throw Error("Received a Type with a typeId of NONE");
@@ -375,21 +473,21 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
     case Type.Interval:
       return sanitizeInterval(typeLike);
     case Type.List:
-      return sanitizeList(typeLike);
+      return sanitizeListWithContext(typeLike, context);
     case Type.Struct:
-      return sanitizeStruct(typeLike);
+      return sanitizeStructWithContext(typeLike, context);
     case Type.Union:
-      return sanitizeUnion(typeLike);
+      return sanitizeUnionWithContext(typeLike, context);
     case Type.FixedSizeBinary:
       return sanitizeFixedSizeBinary(typeLike);
     case Type.FixedSizeList:
-      return sanitizeFixedSizeList(typeLike);
+      return sanitizeFixedSizeListWithContext(typeLike, context);
     case Type.Map:
-      return sanitizeMap(typeLike);
+      return sanitizeMapWithContext(typeLike, context);
     case Type.Duration:
       return sanitizeDuration(typeLike);
     case Type.Dictionary:
-      return sanitizeDictionary(typeLike);
+      return sanitizeDictionaryWithContext(typeLike, context);
     case Type.Int8:
       return new Int8();
     case Type.Int16:
@@ -433,9 +531,9 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
     case Type.TimestampSecond:
       return sanitizeTypedTimestamp(typeLike, TimestampSecond);
     case Type.DenseUnion:
-      return sanitizeTypedUnion(typeLike, DenseUnion);
+      return sanitizeTypedUnionWithContext(typeLike, DenseUnion, context);
     case Type.SparseUnion:
-      return sanitizeTypedUnion(typeLike, SparseUnion);
+      return sanitizeTypedUnionWithContext(typeLike, SparseUnion, context);
     case Type.IntervalDayTime:
       return new IntervalDayTime();
     case Type.IntervalYearMonth:
@@ -454,6 +552,13 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
 }
 
 export function sanitizeField(fieldLike: unknown): Field {
+  return sanitizeFieldWithContext(fieldLike, createSanitizationContext());
+}
+
+function sanitizeFieldWithContext(
+  fieldLike: unknown,
+  context: SanitizationContext,
+): Field {
   if (fieldLike instanceof Field) {
     return fieldLike;
   }
@@ -471,7 +576,7 @@ export function sanitizeField(fieldLike: unknown): Field {
   }
   let type: DataType;
   try {
-    type = sanitizeType(fieldLike.type);
+    type = sanitizeTypeWithContext(fieldLike.type, context);
   } catch (error: unknown) {
     throw Error(
       `Unable to sanitize type for field: ${fieldLike.name} due to error: ${error}`,
@@ -501,6 +606,13 @@ export function sanitizeField(fieldLike: unknown): Field {
  * than lancedb is using.
  */
 export function sanitizeSchema(schemaLike: SchemaLike): Schema {
+  return sanitizeSchemaWithContext(schemaLike, createSanitizationContext());
+}
+
+function sanitizeSchemaWithContext(
+  schemaLike: SchemaLike,
+  context: SanitizationContext,
+): Schema {
   if (schemaLike instanceof Schema) {
     return schemaLike;
   }
@@ -522,7 +634,7 @@ export function sanitizeSchema(schemaLike: SchemaLike): Schema {
     );
   }
   const sanitizedFields = schemaLike.fields.map((field) =>
-    sanitizeField(field),
+    sanitizeFieldWithContext(field, context),
   );
   return new Schema(sanitizedFields, metadata);
 }
@@ -544,13 +656,18 @@ export function sanitizeTable(tableLike: TableLike): Table {
       "The table passed in does not appear to be a table (no 'columns' property)",
     );
   }
-  const schema = sanitizeSchema(tableLike.schema);
-
-  const batches = tableLike.batches.map(sanitizeRecordBatch);
+  const context = createSanitizationContext();
+  const schema = sanitizeSchemaWithContext(tableLike.schema, context);
+  const batches = tableLike.batches.map((batch) =>
+    sanitizeRecordBatch(batch, context),
+  );
   return new Table(schema, batches);
 }
 
-function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
+function sanitizeRecordBatch(
+  batchLike: RecordBatchLike,
+  context: SanitizationContext,
+): RecordBatch {
   if (batchLike instanceof RecordBatch) {
     return batchLike;
   }
@@ -567,19 +684,43 @@ function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
       "The record batch passed in does not appear to be a record batch (no 'data' property)",
     );
   }
-  const schema = sanitizeSchema(batchLike.schema);
-  const data = sanitizeData(batchLike.data);
+  const schema = sanitizeSchemaWithContext(batchLike.schema, context);
+  const data = sanitizeData(batchLike.data, context) as Data<Struct>;
   return new RecordBatch(schema, data);
 }
+
+type DictionaryVectorLike = {
+  data: readonly DataLike[];
+};
+
+type DictionaryDataLike = DataLike & {
+  dictionary?: DictionaryVectorLike;
+};
+
 function sanitizeData(
   dataLike: DataLike,
-  // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-): import("apache-arrow").Data<Struct<any>> {
+  context: SanitizationContext,
+): Data<DataType> {
   if (dataLike instanceof Data) {
     return dataLike;
   }
-  return new Data(
-    dataLike.type,
+  const cachedData = context.data.get(dataLike);
+  if (cachedData !== undefined) {
+    return cachedData;
+  }
+  const dictionaryLike = (dataLike as DictionaryDataLike).dictionary;
+  let dictionary: Vector | undefined;
+  if (dictionaryLike !== undefined) {
+    dictionary = context.vectors.get(dictionaryLike);
+    if (dictionary === undefined) {
+      dictionary = new Vector(
+        dictionaryLike.data.map((data) => sanitizeData(data, context)),
+      );
+      context.vectors.set(dictionaryLike, dictionary);
+    }
+  }
+  const data = new Data(
+    sanitizeTypeWithContext(dataLike.type, context),
     dataLike.offset,
     dataLike.length,
     dataLike.nullCount,
@@ -589,7 +730,11 @@ function sanitizeData(
       [BufferType.VALIDITY]: dataLike.nullBitmap,
       [BufferType.TYPE]: dataLike.typeIds,
     },
+    dataLike.children.map((child) => sanitizeData(child, context)),
+    dictionary,
   );
+  context.data.set(dataLike, data);
+  return data;
 }
 
 const constructorsByTypeName = {

nodejs/lancedb/table.ts

@@ -31,8 +31,10 @@ import {
   IndexConfig,
   IndexStatistics,
   Job,
+  LsmStats,
   Branches as NativeBranches,
   OptimizeStats,
+  RefreshColumnResult,
   TableStatistics,
   Tags,
   UpdateFieldMetadataResult,
@@ -49,6 +51,12 @@ import {
 import { sanitizeType } from "./sanitize";
 import { IntoSql, toSQL } from "./util";
 export { IndexConfig } from "./native";
+export {
+  BucketStats,
+  GenerationStats,
+  LsmStats,
+  MemtableStats,
+} from "./native";
 
 /**
  * Progress snapshot for a write operation, delivered to the `progress`
@@ -197,7 +205,11 @@ export interface LsmWriteSpec {
   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. */
+  /**
+   * Indexes the MemWAL keeps up to date. Omit to maintain every supported
+   * index, resolved on install — a snapshot, so indexes created later are not
+   * maintained. Pass `[]` for none.
+   */
   maintainedIndexes?: string[];
   /** Default `ShardWriter` configuration recorded in the MemWAL index. */
   writerConfigDefaults?: Record<string, string>;
@@ -521,18 +533,75 @@ export abstract class Table {
   abstract vectorSearch(vector: IntoVector | MultiVector): VectorQuery;
   /**
    * Add new columns with defined values.
+   *
+   * The `{ computed }` form stores the expression rather than evaluating it
+   * now: the column is committed with no values, and rows get them from
+   * {@link Table#refreshColumn}. Declaring one therefore costs the same on a
+   * large table as on an empty one.
+   *
+   * A refresh does not revisit rows it has already filled, so mutating an
+   * input leaves the value computed at fill time; recomputing means dropping
+   * the column and declaring it again. While a declaration reads a column,
+   * that column cannot be renamed, retyped or dropped.
+   *
+   * On LanceDB Cloud and Enterprise the expression is planned by the
+   * server, and the refresh runs as a server job -- see
+   * {@link Table#refreshColumnAsync}.
    * @param {AddColumnsSql[] | Field | Field[] | Schema} newColumnTransforms Either:
    *   - An array of objects with column names and SQL expressions to calculate values
    *   - A single Arrow Field defining one column with its data type (column will be initialized with null values)
    *   - An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
    *   - An Arrow Schema defining columns with their data types (columns will be initialized with null values)
+   *   - `{ computed }`, declaring columns defined by a SQL expression whose type and inputs are derived from it
    * @returns {Promise<AddColumnsResult>} A promise that resolves to an object
    * containing the new version number of the table after adding the columns.
+   * @example
+   * ```ts
+   * await table.addColumns({ computed: [{ name: "doubled", valueSql: "x * 2" }] });
+   * const { rowsFilled } = await table.refreshColumn("doubled");
+   * ```
    */
   abstract addColumns(
-    newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
+    newColumnTransforms:
+      | AddColumnsSql[]
+      | Field
+      | Field[]
+      | Schema
+      | { computed: AddColumnsSql[] },
   ): Promise<AddColumnsResult>;
 
+  /**
+   * Fill the rows of a computed column that hold no value yet.
+   *
+   * Rows appended since the last refresh are filled by the next one; rows
+   * already filled are left as they are, so the call is idempotent and does
+   * not observe a mutated input. Local tables only: a remote refresh runs
+   * as a server job, through {@link Table#refreshColumnAsync}.
+   * @param {string} column The name of the computed column to fill.
+   * @returns {Promise<RefreshColumnResult>} A promise that resolves to the
+   * number of rows filled and the new version number of the table.
+   */
+  abstract refreshColumn(column: string): Promise<RefreshColumnResult>;
+
+  /**
+   * Like {@link Table#refreshColumn}, but returns a handle to the refresh
+   * job instead of blocking until it completes.
+   *
+   * The job may already be complete when returned; callers must not assume
+   * the column is filled until {@link Job.wait} resolves. Invalid input --
+   * an unknown column, or one that is not computed -- rejects here rather
+   * than failing the job. On local tables the job runs in-process; on
+   * LanceDB Cloud and Enterprise it is the server's backfill job.
+   * @param {string} column The name of the computed column to fill.
+   * @example
+   * ```ts
+   * const job = await table.refreshColumnAsync("doubled");
+   * await job.wait();
+   * console.log(await job.status()); // "finished"
+   * ```
+   */
+  abstract refreshColumnAsync(column: string): Promise<Job>;
+
   /**
    * Alter the name or nullability of columns.
    * @param {ColumnAlteration[]} columnAlterations One or more alterations to
@@ -595,6 +664,11 @@ export abstract class Table {
    * 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.
+   *
+   * Omitting `maintainedIndexes` maintains every index on the table, resolved
+   * here, failing if one cannot be maintained — name them to install anyway.
+   * Naming them pins an exact set, and a still-building index is rejected
+   * rather than quietly omitted.
    * @param {LsmWriteSpec} spec The sharding spec to install.
    * @returns {Promise<void>}
    * @example
@@ -622,9 +696,10 @@ export abstract class Table {
    *
    * Resolves to `undefined` when the MemWAL LSM write path is not enabled (no
    * spec has been set, or it was removed with {@link Table#unsetLsmWriteSpec}).
-   * The returned spec — including its `maintainedIndexes` and
-   * `writerConfigDefaults` — mirrors what was passed to
-   * {@link Table#setLsmWriteSpec}.
+   * The returned spec mirrors what was passed to
+   * {@link Table#setLsmWriteSpec}, except that `maintainedIndexes` always
+   * reports the concrete list resolved when the spec was set — `undefined`
+   * never round-trips.
    * @returns {Promise<LsmWriteSpec | undefined>}
    */
   abstract getLsmWriteSpec(): Promise<LsmWriteSpec | undefined>;
@@ -638,6 +713,59 @@ export abstract class Table {
    * @returns {Promise<void>}
    */
   abstract closeLsmWriters(): Promise<void>;
+  /**
+   * Seal every bucket's active memtable into a new L0 generation.
+   *
+   * Returns once the seal is committed. Sealing an empty memtable is a no-op,
+   * so this is safe to call repeatedly.
+   * @returns {Promise<void>}
+   */
+  abstract flushLsm(): Promise<void>;
+  /**
+   * Trigger a background L0 → base compaction pass per bucket.
+   *
+   * Returns once the passes are *dispatched*, not once they finish — watch
+   * {@link Table#getLsmStats} for progress, or use
+   * {@link Table#checkpointLsm} to wait for convergence.
+   * @returns {Promise<void>}
+   */
+  abstract compactLsm(): Promise<void>;
+  /**
+   * Converge this table's LSM write path into its base table.
+   *
+   * Seals once, then triggers compaction and polls until the L0 that existed
+   * at the start is gone. The target set is fixed at the start, so
+   * generations created *during* the checkpoint are ignored — that is what
+   * lets it terminate under write load, and what makes it best-effort: it
+   * converges the fresh tier as of some instant. Idempotent, abandonable at
+   * any point, and safe to run on a cadence.
+   *
+   * There is no liveness bound — the compactor pool is shared across tables,
+   * so a checkpoint queued behind unrelated work looks exactly like one that
+   * is merging. The caller owns the deadline.
+   * @returns {Promise<void>}
+   * @example
+   * ```ts
+   * const before = await table.getLsmStats();
+   * await table.checkpointLsm();
+   * const after = await table.getLsmStats();
+   * ```
+   */
+  abstract checkpointLsm(): Promise<void>;
+  /**
+   * Read live per-bucket LSM state.
+   *
+   * Answers "how far behind is my fresh tier", "which bucket is hot", and
+   * "why is my fresh-tier vector search brute-force". Mutates no table state.
+   *
+   * Resolves to `undefined` only when the LSM write path is not enabled.
+   * @param {boolean} includeGenerationRows Also count rows per L0 generation.
+   *   Off by default because each count opens an uncached Lance dataset.
+   * @returns {Promise<LsmStats | undefined>}
+   */
+  abstract getLsmStats(
+    includeGenerationRows?: boolean,
+  ): Promise<LsmStats | undefined>;
   /** Retrieve the version of the table */
 
   abstract version(): Promise<number>;
@@ -1078,8 +1206,22 @@ export class LocalTable extends Table {
   // TODO: Support BatchUDF
 
   async addColumns(
-    newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
+    newColumnTransforms:
+      | AddColumnsSql[]
+      | Field
+      | Field[]
+      | Schema
+      | { computed: AddColumnsSql[] },
   ): Promise<AddColumnsResult> {
+    // Columns defined by an expression are declared, not materialized here.
+    if (
+      typeof newColumnTransforms === "object" &&
+      !Array.isArray(newColumnTransforms) &&
+      "computed" in newColumnTransforms
+    ) {
+      return await this.inner.addComputedColumns(newColumnTransforms.computed);
+    }
+
     // Handle single Field -> convert to array of Fields
     if (newColumnTransforms instanceof Field) {
       newColumnTransforms = [newColumnTransforms];
@@ -1114,6 +1256,14 @@ export class LocalTable extends Table {
     throw new Error("Invalid input type for addColumns");
   }
 
+  async refreshColumn(column: string): Promise<RefreshColumnResult> {
+    return await this.inner.refreshColumn(column);
+  }
+
+  async refreshColumnAsync(column: string): Promise<Job> {
+    return await this.inner.refreshColumnAsync(column);
+  }
+
   async alterColumns(
     columnAlterations: ColumnAlteration[],
   ): Promise<AlterColumnsResult> {
@@ -1176,6 +1326,24 @@ export class LocalTable extends Table {
     return await this.inner.closeLsmWriters();
   }
 
+  async flushLsm(): Promise<void> {
+    return await this.inner.flushLsm();
+  }
+
+  async compactLsm(): Promise<void> {
+    return await this.inner.compactLsm();
+  }
+
+  async checkpointLsm(): Promise<void> {
+    return await this.inner.checkpointLsm();
+  }
+
+  async getLsmStats(
+    includeGenerationRows: boolean = false,
+  ): Promise<LsmStats | undefined> {
+    return (await this.inner.getLsmStats(includeGenerationRows)) ?? undefined;
+  }
+
   async version(): Promise<number> {
     return await this.inner.version();
   }

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.37.1-beta.0",
+	"version": "0.38.0-beta.3",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/linux-arm64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.38.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

nodejs/npm/linux-arm64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.38.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.38.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.38.0-beta.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.37.1-beta.0",
+  "version": "0.38.0-beta.3",
   "os": [
     "win32"
   ],

nodejs/npm/win32-x64-msvc/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.37.1-beta.0",
+	"version": "0.38.0-beta.3",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.37.1-beta.0",
+  "version": "0.38.0-beta.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.37.1-beta.0",
+      "version": "0.38.0-beta.3",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.37.1-beta.0",
+  "version": "0.38.0-beta.3",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/connection.rs

@@ -334,6 +334,22 @@ impl Connection {
             .default_error()
     }
 
+    /// Start dropping a table and return its cleanup job.
+    #[napi(catch_unwind)]
+    pub async fn drop_table_async(
+        &self,
+        name: String,
+        namespace_path: Option<Vec<String>>,
+    ) -> napi::Result<crate::job::Job> {
+        let ns = namespace_path.unwrap_or_default();
+        let job = self
+            .get_inner()?
+            .drop_table_async(&name, &ns)
+            .await
+            .default_error()?;
+        Ok(crate::job::Job::new(job))
+    }
+
     #[napi(catch_unwind)]
     pub async fn drop_all_tables(&self, namespace_path: Option<Vec<String>>) -> napi::Result<()> {
         let ns = namespace_path.unwrap_or_default();

nodejs/src/table.rs

@@ -347,6 +347,40 @@ impl Table {
         Ok(res.into())
     }
 
+    #[napi(catch_unwind)]
+    pub async fn add_computed_columns(
+        &self,
+        columns: Vec<AddColumnsSql>,
+    ) -> napi::Result<AddColumnsResult> {
+        let table = self.inner_ref()?;
+        let mut builder = table.add_columns();
+        for column in columns {
+            builder = builder.computed(column.name, column.value_sql);
+        }
+        let res = builder.execute().await.default_error()?;
+        Ok(res.into())
+    }
+
+    #[napi(catch_unwind)]
+    pub async fn refresh_column(&self, column: String) -> napi::Result<RefreshColumnResult> {
+        let res = self
+            .inner_ref()?
+            .refresh_column(column)
+            .await
+            .default_error()?;
+        Ok(res.into())
+    }
+
+    #[napi(catch_unwind)]
+    pub async fn refresh_column_async(&self, column: String) -> napi::Result<crate::job::Job> {
+        let job = self
+            .inner_ref()?
+            .refresh_column_async(column)
+            .await
+            .default_error()?;
+        Ok(crate::job::Job::new(job))
+    }
+
     #[napi(catch_unwind)]
     pub async fn add_columns_with_schema(
         &self,
@@ -463,6 +497,34 @@ impl Table {
         self.inner_ref()?.close_lsm_writers().await.default_error()
     }
 
+    #[napi(catch_unwind)]
+    pub async fn flush_lsm(&self) -> napi::Result<()> {
+        self.inner_ref()?.flush_lsm().await.default_error()
+    }
+
+    #[napi(catch_unwind)]
+    pub async fn compact_lsm(&self) -> napi::Result<()> {
+        self.inner_ref()?.compact_lsm().await.default_error()
+    }
+
+    #[napi(catch_unwind)]
+    pub async fn checkpoint_lsm(&self) -> napi::Result<()> {
+        self.inner_ref()?.checkpoint_lsm().await.default_error()
+    }
+
+    #[napi(catch_unwind)]
+    pub async fn get_lsm_stats(
+        &self,
+        include_generation_rows: bool,
+    ) -> napi::Result<Option<LsmStats>> {
+        let stats = self
+            .inner_ref()?
+            .get_lsm_stats(include_generation_rows)
+            .await
+            .default_error()?;
+        Ok(stats.map(LsmStats::from))
+    }
+
     #[napi(catch_unwind)]
     pub async fn version(&self) -> napi::Result<i64> {
         self.inner_ref()?
@@ -772,7 +834,8 @@ pub struct LsmWriteSpec {
     pub column: Option<String>,
     /// Bucket variant: the number of buckets, in `[1, 1024]`.
     pub num_buckets: Option<u32>,
-    /// Names of indexes the MemWAL should keep up to date during writes.
+    /// Indexes the MemWAL keeps up to date. Omitted resolves every
+    /// maintainable index on install; an empty array means none.
     pub maintained_indexes: Option<Vec<String>>,
     /// Default `ShardWriter` configuration recorded in the MemWAL index.
     pub writer_config_defaults: Option<HashMap<String, String>>,
@@ -782,7 +845,6 @@ impl TryFrom<LsmWriteSpec> for lancedb::table::LsmWriteSpec {
     type Error = napi::Error;
 
     fn try_from(value: LsmWriteSpec) -> napi::Result<Self> {
-        let maintained = value.maintained_indexes.unwrap_or_default();
         let writer_config_defaults = value.writer_config_defaults.unwrap_or_default();
         let spec = match value.spec_type.as_str() {
             "bucket" => {
@@ -809,7 +871,7 @@ impl TryFrom<LsmWriteSpec> for lancedb::table::LsmWriteSpec {
             }
         };
         Ok(spec
-            .with_maintained_indexes(maintained)
+            .with_maintained_indexes(value.maintained_indexes)
             .with_writer_config_defaults(writer_config_defaults))
     }
 }
@@ -827,7 +889,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
                 spec_type: "bucket".to_string(),
                 column: Some(column),
                 num_buckets: Some(num_buckets),
-                maintained_indexes: Some(maintained_indexes),
+                maintained_indexes,
                 writer_config_defaults: Some(writer_config_defaults),
             },
             Native::Identity {
@@ -838,7 +900,7 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
                 spec_type: "identity".to_string(),
                 column: Some(column),
                 num_buckets: None,
-                maintained_indexes: Some(maintained_indexes),
+                maintained_indexes,
                 writer_config_defaults: Some(writer_config_defaults),
             },
             Native::Unsharded {
@@ -848,13 +910,136 @@ impl From<lancedb::table::LsmWriteSpec> for LsmWriteSpec {
                 spec_type: "unsharded".to_string(),
                 column: None,
                 num_buckets: None,
-                maintained_indexes: Some(maintained_indexes),
+                maintained_indexes,
                 writer_config_defaults: Some(writer_config_defaults),
             },
         }
     }
 }
 
+/// One flushed L0 generation.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct GenerationStats {
+    /// The generation number. Increases as memtables are sealed into L0.
+    pub generation: i64,
+    /// On-disk size of the generation.
+    pub bytes: i64,
+    /// Present only when `includeGenerationRows` was requested. Off by default
+    /// because each count opens an uncached Lance dataset.
+    pub rows: Option<i64>,
+}
+
+impl From<lancedb::table::GenerationStats> for GenerationStats {
+    fn from(g: lancedb::table::GenerationStats) -> Self {
+        Self {
+            generation: g.generation as i64,
+            bytes: g.bytes as i64,
+            rows: g.rows.map(|r| r as i64),
+        }
+    }
+}
+
+/// One in-memory memtable.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct MemtableStats {
+    /// The generation this memtable will become once sealed.
+    pub generation: i64,
+    /// Rows currently buffered.
+    pub rows: i64,
+    /// Estimated in-memory size.
+    pub bytes: i64,
+    /// Record batches currently buffered.
+    pub batches: i64,
+    /// Names of the indexes this memtable carries. An absent name is the whole
+    /// answer to "why is my fresh-tier search on that column brute-force".
+    pub indexes: Vec<String>,
+}
+
+impl From<lancedb::table::MemtableStats> for MemtableStats {
+    fn from(m: lancedb::table::MemtableStats) -> Self {
+        Self {
+            generation: m.generation as i64,
+            rows: m.rows as i64,
+            bytes: m.bytes as i64,
+            batches: m.batches as i64,
+            indexes: m.indexes,
+        }
+    }
+}
+
+/// Live state of one bucket. A table is N buckets on one node; flattening to a
+/// single number hides the one hot bucket that is usually why someone opened
+/// this endpoint.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct BucketStats {
+    /// The shard this bucket writes.
+    pub shard_id: String,
+    /// `"Active"` or `"Sealed"` (drop-table 2PC in flight).
+    pub status: String,
+    /// Epoch of the writer that currently owns the shard.
+    pub writer_epoch: i64,
+    /// Version of the shard manifest these numbers were read from.
+    pub manifest_version: i64,
+    /// The generation the active memtable will become.
+    pub current_generation: i64,
+    /// WAL position replay resumes from.
+    pub replay_after_wal_entry_position: i64,
+    /// Highest WAL position the writer has seen. The difference against
+    /// `replayAfterWalEntryPosition` is the WAL lag.
+    pub wal_entry_position_last_seen: i64,
+    /// Flushed L0 generations not yet merged into the base table.
+    pub generations: Vec<GenerationStats>,
+    /// Whether a pass owns this bucket's compaction latch right now. Says *a*
+    /// driver is running, not *whose*, and the latch is held from dispatch —
+    /// including while the pass queues for a pod-wide compactor permit. Read it
+    /// as "do not pile on", never as "mine is progressing".
+    pub compacting: bool,
+    /// Oldest first, active last. Absent for a `"Sealed"` bucket, whose
+    /// in-memory state is torn down.
+    pub memtables: Option<Vec<MemtableStats>>,
+}
+
+impl From<lancedb::table::BucketStats> for BucketStats {
+    fn from(b: lancedb::table::BucketStats) -> Self {
+        Self {
+            shard_id: b.shard_id,
+            status: b.status,
+            writer_epoch: b.writer_epoch as i64,
+            manifest_version: b.manifest_version as i64,
+            current_generation: b.current_generation as i64,
+            replay_after_wal_entry_position: b.replay_after_wal_entry_position as i64,
+            wal_entry_position_last_seen: b.wal_entry_position_last_seen as i64,
+            generations: b.generations.into_iter().map(Into::into).collect(),
+            compacting: b.compacting,
+            memtables: b
+                .memtables
+                .map(|ms| ms.into_iter().map(Into::into).collect()),
+        }
+    }
+}
+
+/// Live per-bucket LSM state, as returned by `Table#getLsmStats`.
+///
+/// Nothing here is derived: sums and differences (total L0 bytes, WAL lag) are
+/// the caller's to compute.
+#[napi(object)]
+#[derive(Clone, Debug)]
+pub struct LsmStats {
+    /// One entry per bucket backing this table.
+    pub buckets: Vec<BucketStats>,
+}
+
+impl From<lancedb::table::LsmStats> for LsmStats {
+    fn from(stats: lancedb::table::LsmStats) -> Self {
+        Self {
+            buckets: stats.buckets.into_iter().map(Into::into).collect(),
+        }
+    }
+}
+
 /// Statistics about a compaction operation.
 #[napi(object)]
 #[derive(Clone, Debug)]
@@ -1043,7 +1228,10 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {
 
 #[napi(object)]
 pub struct TableStatistics {
-    /// The total number of bytes in the table
+    /// The total size, in bytes, of the table's data files, index files, and
+    /// overlay files
+    ///
+    /// Read from the manifest, so this excludes deletion files and manifests.
     pub total_bytes: i64,
 
     /// The number of rows in the table
@@ -1193,6 +1381,21 @@ pub struct AddColumnsResult {
     pub version: i64,
 }
 
+#[napi(object)]
+pub struct RefreshColumnResult {
+    pub rows_filled: i64,
+    pub version: i64,
+}
+
+impl From<lancedb::table::RefreshColumnResult> for RefreshColumnResult {
+    fn from(value: lancedb::table::RefreshColumnResult) -> Self {
+        Self {
+            rows_filled: value.rows_filled as i64,
+            version: value.version as i64,
+        }
+    }
+}
+
 impl From<lancedb::table::AddColumnsResult> for AddColumnsResult {
     fn from(value: lancedb::table::AddColumnsResult) -> Self {
         Self {