Bump version: 0.9.0 → 0.9.0-final.1

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.6.0"
+current_version = "0.5.2"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

Cargo.toml

@@ -20,18 +20,11 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-# lance = { "version" = "=0.13.0", "features" = ["dynamodb"] }
-# lance-index = { "version" = "=0.13.0" }
-# lance-linalg = { "version" = "=0.13.0" }
-# lance-testing = { "version" = "=0.13.0" }
-# lance-datafusion = { "version" = "=0.13.0" }
-
-lance = { path = "../lance/rust/lance" }
-lance-index = { path = "../lance/rust/lance-index" }
-lance-linalg= { path = "../lance/rust/lance-linalg" }
-lance-testing = { path = "../lance/rust/lance-testing" }
-lance-datafusion = { path = "../lance/rust/lance-datafusion" }
-
+lance = { "version" = "=0.13.0", "features" = ["dynamodb"] }
+lance-index = { "version" = "=0.13.0" }
+lance-linalg = { "version" = "=0.13.0" }
+lance-testing = { "version" = "=0.13.0" }
+lance-datafusion = { "version" = "=0.13.0" }
 # Note that this one does not include pyarrow
 arrow = { version = "51.0", optional = false }
 arrow-array = "51.0"

docs/src/guides/tables.md

@@ -116,21 +116,21 @@ This guide will show how to create tables, insert data into them, and update the
 
 ### From a Polars DataFrame
 
-LanceDB supports [Polars](https://pola.rs/), a modern, fast DataFrame library
-written in Rust. Just like in Pandas, the Polars integration is enabled by PyArrow
-under the hood. A deeper integration between LanceDB Tables and Polars DataFrames
-is on the way.
+    LanceDB supports [Polars](https://pola.rs/), a modern, fast DataFrame library
+    written in Rust. Just like in Pandas, the Polars integration is enabled by PyArrow
+    under the hood. A deeper integration between LanceDB Tables and Polars DataFrames
+    is on the way.
 
-```python
-import polars as pl
+    ```python
+    import polars as pl
 
-data = pl.DataFrame({
-    "vector": [[3.1, 4.1], [5.9, 26.5]],
-    "item": ["foo", "bar"],
-    "price": [10.0, 20.0]
-})
-table = db.create_table("pl_table", data=data)
-```
+    data = pl.DataFrame({
+        "vector": [[3.1, 4.1], [5.9, 26.5]],
+        "item": ["foo", "bar"],
+        "price": [10.0, 20.0]
+    })
+    table = db.create_table("pl_table", data=data)
+    ```
 
 ### From an Arrow Table
 === "Python"

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.6.0",
+  "version": "0.5.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.6.0",
+      "version": "0.5.2",
       "cpu": [
         "x64",
         "arm64"

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.6.0",
+  "version": "0.5.2",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

nodejs/__test__/table.test.ts

@@ -39,9 +39,7 @@ describe.each([arrow, arrowOld])("Given a table", (arrow: any) => {
   let tmpDir: tmp.DirResult;
   let table: Table;
 
-  const schema:
-    | import("apache-arrow").Schema
-    | import("apache-arrow-old").Schema = new arrow.Schema([
+  const schema = new arrow.Schema([
     new arrow.Field("id", new arrow.Float64(), true),
   ]);
 
@@ -317,7 +315,7 @@ describe("When creating an index", () => {
       .query()
       .limit(2)
       .nearestTo(queryVec)
-      .distanceType("dot")
+      .distanceType("DoT")
       .toArrow();
     expect(rst.numRows).toBe(2);
 

nodejs/lancedb/arrow.ts

@@ -15,7 +15,6 @@
 import {
   Table as ArrowTable,
   Binary,
-  BufferType,
   DataType,
   Field,
   FixedSizeBinary,
@@ -38,68 +37,14 @@ import {
   type makeTable,
   vectorFromArray,
 } from "apache-arrow";
-import { Buffers } from "apache-arrow/data";
 import { type EmbeddingFunction } from "./embedding/embedding_function";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
-import {
-  sanitizeField,
-  sanitizeSchema,
-  sanitizeTable,
-  sanitizeType,
-} from "./sanitize";
+import { sanitizeField, sanitizeSchema, sanitizeType } from "./sanitize";
 export * from "apache-arrow";
-export type SchemaLike =
-  | Schema
-  | {
-      fields: FieldLike[];
-      metadata: Map<string, string>;
-      get names(): unknown[];
-    };
-export type FieldLike =
-  | Field
-  | {
-      type: string;
-      name: string;
-      nullable?: boolean;
-      metadata?: Map<string, string>;
-    };
-
-export type DataLike =
-  // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-  | import("apache-arrow").Data<Struct<any>>
-  | {
-      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-      type: any;
-      length: number;
-      offset: number;
-      stride: number;
-      nullable: boolean;
-      children: DataLike[];
-      get nullCount(): number;
-      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-      values: Buffers<any>[BufferType.DATA];
-      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-      typeIds: Buffers<any>[BufferType.TYPE];
-      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-      nullBitmap: Buffers<any>[BufferType.VALIDITY];
-      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-      valueOffsets: Buffers<any>[BufferType.OFFSET];
-    };
-
-export type RecordBatchLike =
-  | RecordBatch
-  | {
-      schema: SchemaLike;
-      data: DataLike;
-    };
-
-export type TableLike =
-  | ArrowTable
-  | { schema: SchemaLike; batches: RecordBatchLike[] };
 
 export type IntoVector = Float32Array | Float64Array | number[];
 
-export function isArrowTable(value: object): value is TableLike {
+export function isArrowTable(value: object): value is ArrowTable {
   if (value instanceof ArrowTable) return true;
   return "schema" in value && "batches" in value;
 }
@@ -190,7 +135,7 @@ export function isFixedSizeList(value: unknown): value is FixedSizeList {
 }
 
 /** Data type accepted by NodeJS SDK */
-export type Data = Record<string, unknown>[] | TableLike;
+export type Data = Record<string, unknown>[] | ArrowTable;
 
 /*
  * Options to control how a column should be converted to a vector array
@@ -217,7 +162,7 @@ export class MakeArrowTableOptions {
    * The schema must be specified if there are no records (e.g. to make
    * an empty table)
    */
-  schema?: SchemaLike;
+  schema?: Schema;
 
   /*
    * Mapping from vector column name to expected type
@@ -365,7 +310,7 @@ export function makeArrowTable(
   if (opt.schema !== undefined && opt.schema !== null) {
     opt.schema = sanitizeSchema(opt.schema);
     opt.schema = validateSchemaEmbeddings(
-      opt.schema as Schema,
+      opt.schema,
       data,
       options?.embeddingFunction,
     );
@@ -449,7 +394,7 @@ export function makeArrowTable(
     // `new ArrowTable(schema, batches)` which does not do any schema inference
     const firstTable = new ArrowTable(columns);
     const batchesFixed = firstTable.batches.map(
-      (batch) => new RecordBatch(opt.schema as Schema, batch.data),
+      (batch) => new RecordBatch(opt.schema!, batch.data),
     );
     let schema: Schema;
     if (metadata !== undefined) {
@@ -462,9 +407,9 @@ export function makeArrowTable(
         }
       }
 
-      schema = new Schema(opt.schema.fields as Field[], schemaMetadata);
+      schema = new Schema(opt.schema.fields, schemaMetadata);
     } else {
-      schema = opt.schema as Schema;
+      schema = opt.schema;
     }
     return new ArrowTable(schema, batchesFixed);
   }
@@ -480,7 +425,7 @@ export function makeArrowTable(
  * Create an empty Arrow table with the provided schema
  */
 export function makeEmptyTable(
-  schema: SchemaLike,
+  schema: Schema,
   metadata?: Map<string, string>,
 ): ArrowTable {
   return makeArrowTable([], { schema }, metadata);
@@ -618,17 +563,18 @@ async function applyEmbeddingsFromMetadata(
 async function applyEmbeddings<T>(
   table: ArrowTable,
   embeddings?: EmbeddingFunctionConfig,
-  schema?: SchemaLike,
+  schema?: Schema,
 ): Promise<ArrowTable> {
-  if (schema !== undefined && schema !== null) {
-    schema = sanitizeSchema(schema);
-  }
   if (schema?.metadata.has("embedding_functions")) {
-    return applyEmbeddingsFromMetadata(table, schema! as Schema);
+    return applyEmbeddingsFromMetadata(table, schema!);
   } else if (embeddings == null || embeddings === undefined) {
     return table;
   }
 
+  if (schema !== undefined && schema !== null) {
+    schema = sanitizeSchema(schema);
+  }
+
   // Convert from ArrowTable to Record<String, Vector>
   const colEntries = [...Array(table.numCols).keys()].map((_, idx) => {
     const name = table.schema.fields[idx].name;
@@ -704,7 +650,7 @@ async function applyEmbeddings<T>(
         `When using embedding functions and specifying a schema the schema should include the embedding column but the column ${destColumn} was missing`,
       );
     }
-    return alignTable(newTable, schema as Schema);
+    return alignTable(newTable, schema);
   }
   return newTable;
 }
@@ -798,7 +744,7 @@ export async function fromRecordsToStreamBuffer(
 export async function fromTableToBuffer(
   table: ArrowTable,
   embeddings?: EmbeddingFunctionConfig,
-  schema?: SchemaLike,
+  schema?: Schema,
 ): Promise<Buffer> {
   if (schema !== undefined && schema !== null) {
     schema = sanitizeSchema(schema);
@@ -825,7 +771,7 @@ export async function fromDataToBuffer(
     schema = sanitizeSchema(schema);
   }
   if (isArrowTable(data)) {
-    return fromTableToBuffer(sanitizeTable(data), embeddings, schema);
+    return fromTableToBuffer(data, embeddings, schema);
   } else {
     const table = await convertToTable(data, embeddings, { schema });
     return fromTableToBuffer(table);
@@ -843,7 +789,7 @@ export async function fromDataToBuffer(
 export async function fromTableToStreamBuffer(
   table: ArrowTable,
   embeddings?: EmbeddingFunctionConfig,
-  schema?: SchemaLike,
+  schema?: Schema,
 ): Promise<Buffer> {
   const tableWithEmbeddings = await applyEmbeddings(table, embeddings, schema);
   const writer = RecordBatchStreamWriter.writeAll(tableWithEmbeddings);
@@ -908,6 +854,7 @@ function validateSchemaEmbeddings(
   for (let field of schema.fields) {
     if (isFixedSizeList(field.type)) {
       field = sanitizeField(field);
+
       if (data.length !== 0 && data?.[0]?.[field.name] === undefined) {
         if (schema.metadata.has("embedding_functions")) {
           const embeddings = JSON.parse(

nodejs/lancedb/connection.ts

@@ -12,7 +12,7 @@
 // See the License for the specific language governing permissions and
 // limitations under the License.
 
-import { Data, Schema, SchemaLike, TableLike } from "./arrow";
+import { Table as ArrowTable, Data, Schema } from "./arrow";
 import { fromTableToBuffer, makeEmptyTable } from "./arrow";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { Connection as LanceDbConnection } from "./native";
@@ -50,7 +50,7 @@ export interface CreateTableOptions {
    * The default is true while the new format is in beta
    */
   useLegacyFormat?: boolean;
-  schema?: SchemaLike;
+  schema?: Schema;
   embeddingFunction?: EmbeddingFunctionConfig;
 }
 
@@ -167,12 +167,12 @@ export abstract class Connection {
   /**
    * Creates a new Table and initialize it with new data.
    * @param {string} name - The name of the table.
-   * @param {Record<string, unknown>[] | TableLike} data - Non-empty Array of Records
+   * @param {Record<string, unknown>[] | ArrowTable} data - Non-empty Array of Records
    * to be inserted into the table
    */
   abstract createTable(
     name: string,
-    data: Record<string, unknown>[] | TableLike,
+    data: Record<string, unknown>[] | ArrowTable,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
 
@@ -183,7 +183,7 @@ export abstract class Connection {
    */
   abstract createEmptyTable(
     name: string,
-    schema: import("./arrow").SchemaLike,
+    schema: Schema,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
 
@@ -235,7 +235,7 @@ export class LocalConnection extends Connection {
     nameOrOptions:
       | string
       | ({ name: string; data: Data } & Partial<CreateTableOptions>),
-    data?: Record<string, unknown>[] | TableLike,
+    data?: Record<string, unknown>[] | ArrowTable,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
     if (typeof nameOrOptions !== "string" && "name" in nameOrOptions) {
@@ -259,7 +259,7 @@ export class LocalConnection extends Connection {
 
   async createEmptyTable(
     name: string,
-    schema: import("./arrow").SchemaLike,
+    schema: Schema,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
     let mode: string = options?.mode ?? "create";

nodejs/lancedb/query.ts

@@ -300,9 +300,7 @@ export class VectorQuery extends QueryBase<NativeVectorQuery, VectorQuery> {
    *
    * By default "l2" is used.
    */
-  distanceType(
-    distanceType: Required<IvfPqOptions>["distanceType"],
-  ): VectorQuery {
+  distanceType(distanceType: string): VectorQuery {
     this.inner.distanceType(distanceType);
     return this;
   }

nodejs/lancedb/remote/connection.ts

@@ -1,10 +1,5 @@
 import { Schema } from "apache-arrow";
-import {
-  Data,
-  SchemaLike,
-  fromTableToStreamBuffer,
-  makeEmptyTable,
-} from "../arrow";
+import { Data, fromTableToStreamBuffer, makeEmptyTable } from "../arrow";
 import {
   Connection,
   CreateTableOptions,
@@ -161,7 +156,7 @@ export class RemoteConnection extends Connection {
 
   async createEmptyTable(
     name: string,
-    schema: SchemaLike,
+    schema: Schema,
     options?: Partial<CreateTableOptions> | undefined,
   ): Promise<Table> {
     if (options?.mode) {

nodejs/lancedb/sanitize.ts

@@ -20,12 +20,10 @@
 // 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 type { IntBitWidth, TKeys, TimeBitWidth } from "apache-arrow/type";
 import {
   Binary,
   Bool,
-  DataLike,
   DataType,
   DateDay,
   DateMillisecond,
@@ -58,14 +56,9 @@ import {
   Map_,
   Null,
   type Precision,
-  RecordBatch,
-  RecordBatchLike,
   Schema,
-  SchemaLike,
   SparseUnion,
   Struct,
-  Table,
-  TableLike,
   Time,
   TimeMicrosecond,
   TimeMillisecond,
@@ -495,7 +488,7 @@ export function sanitizeField(fieldLike: unknown): Field {
  * instance because they might be using a different instance of apache-arrow
  * than lancedb is using.
  */
-export function sanitizeSchema(schemaLike: SchemaLike): Schema {
+export function sanitizeSchema(schemaLike: unknown): Schema {
   if (schemaLike instanceof Schema) {
     return schemaLike;
   }
@@ -521,68 +514,3 @@ export function sanitizeSchema(schemaLike: SchemaLike): Schema {
   );
   return new Schema(sanitizedFields, metadata);
 }
-
-export function sanitizeTable(tableLike: TableLike): Table {
-  if (tableLike instanceof Table) {
-    return tableLike;
-  }
-  if (typeof tableLike !== "object" || tableLike === null) {
-    throw Error("Expected a Table but object was null/undefined");
-  }
-  if (!("schema" in tableLike)) {
-    throw Error(
-      "The table passed in does not appear to be a table (no 'schema' property)",
-    );
-  }
-  if (!("batches" in tableLike)) {
-    throw Error(
-      "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);
-  return new Table(schema, batches);
-}
-
-function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
-  if (batchLike instanceof RecordBatch) {
-    return batchLike;
-  }
-  if (typeof batchLike !== "object" || batchLike === null) {
-    throw Error("Expected a RecordBatch but object was null/undefined");
-  }
-  if (!("schema" in batchLike)) {
-    throw Error(
-      "The record batch passed in does not appear to be a record batch (no 'schema' property)",
-    );
-  }
-  if (!("data" in batchLike)) {
-    throw Error(
-      "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);
-  return new RecordBatch(schema, data);
-}
-function sanitizeData(
-  dataLike: DataLike,
-  // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-): import("apache-arrow").Data<Struct<any>> {
-  if (dataLike instanceof Data) {
-    return dataLike;
-  }
-  return new Data(
-    dataLike.type,
-    dataLike.offset,
-    dataLike.length,
-    dataLike.nullCount,
-    {
-      [BufferType.OFFSET]: dataLike.valueOffsets,
-      [BufferType.DATA]: dataLike.values,
-      [BufferType.VALIDITY]: dataLike.nullBitmap,
-      [BufferType.TYPE]: dataLike.typeIds,
-    },
-  );
-}

nodejs/lancedb/table.ts

@@ -17,7 +17,6 @@ import {
   Data,
   IntoVector,
   Schema,
-  TableLike,
   fromDataToBuffer,
   fromTableToBuffer,
   fromTableToStreamBuffer,
@@ -39,8 +38,6 @@ import {
   Table as _NativeTable,
 } from "./native";
 import { Query, VectorQuery } from "./query";
-import { sanitizeTable } from "./sanitize";
-export { IndexConfig } from "./native";
 
 /**
  * Options for adding data to a table.
@@ -384,7 +381,8 @@ export abstract class Table {
   abstract indexStats(name: string): Promise<IndexStatistics | undefined>;
 
   static async parseTableData(
-    data: Record<string, unknown>[] | TableLike,
+    // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+    data: Record<string, unknown>[] | ArrowTable<any>,
     options?: Partial<CreateTableOptions>,
     streaming = false,
   ) {
@@ -397,9 +395,9 @@ export abstract class Table {
 
     let table: ArrowTable;
     if (isArrowTable(data)) {
-      table = sanitizeTable(data);
+      table = data;
     } else {
-      table = makeArrowTable(data as Record<string, unknown>[], options);
+      table = makeArrowTable(data, options);
     }
     if (streaming) {
       const buf = await fromTableToStreamBuffer(

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.6.0",
+	"version": "0.5.2",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.6.0",
+	"version": "0.5.2",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.6.0",
+	"version": "0.5.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.6.0",
+	"version": "0.5.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.6.0",
+	"version": "0.5.2",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -10,7 +10,7 @@
     "vector database",
     "ann"
   ],
-  "version": "0.6.0",
+  "version": "0.5.2",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.9.0"
+current_version = "0.9.0-final.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.9.0"
+version = "0.9.0-final.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/python/lancedb/__init__.py

@@ -35,6 +35,7 @@ def connect(
     host_override: Optional[str] = None,
     read_consistency_interval: Optional[timedelta] = None,
     request_thread_pool: Optional[Union[int, ThreadPoolExecutor]] = None,
+    storage_options: Optional[Dict[str, str]] = None,
     **kwargs,
 ) -> DBConnection:
     """Connect to a LanceDB database.
@@ -70,6 +71,9 @@ def connect(
         executor will be used for making requests. This is for LanceDB Cloud
         only and is only used when making batch requests (i.e., passing in
         multiple queries to the search method at once).
+    storage_options: dict, optional
+        Additional options for the storage backend. See available options at
+        https://lancedb.github.io/lancedb/guides/storage/
 
     Examples
     --------
@@ -105,12 +109,16 @@ def connect(
             region,
             host_override,
             request_thread_pool=request_thread_pool,
+            storage_options=storage_options,
             **kwargs,
         )
 
     if kwargs:
         raise ValueError(f"Unknown keyword arguments: {kwargs}")
-    return LanceDBConnection(uri, read_consistency_interval=read_consistency_interval)
+    return LanceDBConnection(
+        uri,
+        read_consistency_interval=read_consistency_interval,
+    )
 
 
 async def connect_async(

python/python/lancedb/remote/client.py

@@ -55,11 +55,13 @@ class RestfulLanceDBClient:
     region: str
     api_key: Credential
     host_override: Optional[str] = attrs.field(default=None)
+    db_prefix: Optional[str] = attrs.field(default=None)
 
     closed: bool = attrs.field(default=False, init=False)
 
     connection_timeout: float = attrs.field(default=120.0, kw_only=True)
     read_timeout: float = attrs.field(default=300.0, kw_only=True)
+    storage_options: Optional[Dict[str, str]] = attrs.field(default=None, kw_only=True)
 
     @functools.cached_property
     def session(self) -> requests.Session:
@@ -92,6 +94,18 @@ class RestfulLanceDBClient:
             headers["Host"] = f"{self.db_name}.{self.region}.api.lancedb.com"
         if self.host_override:
             headers["x-lancedb-database"] = self.db_name
+        if self.storage_options:
+            if self.storage_options.get("account_name") is not None:
+                headers["x-azure-storage-account-name"] = self.storage_options[
+                    "account_name"
+                ]
+            if self.storage_options.get("azure_storage_account_name") is not None:
+                headers["x-azure-storage-account-name"] = self.storage_options[
+                    "azure_storage_account_name"
+                ]
+        if self.db_prefix:
+            headers["x-lancedb-database-prefix"] = self.db_prefix
+
         return headers
 
     @staticmethod

python/python/lancedb/remote/db.py

@@ -15,7 +15,7 @@ import inspect
 import logging
 import uuid
 from concurrent.futures import ThreadPoolExecutor
-from typing import Iterable, List, Optional, Union
+from typing import Dict, Iterable, List, Optional, Union
 from urllib.parse import urlparse
 
 from cachetools import TTLCache
@@ -44,20 +44,25 @@ class RemoteDBConnection(DBConnection):
         request_thread_pool: Optional[ThreadPoolExecutor] = None,
         connection_timeout: float = 120.0,
         read_timeout: float = 300.0,
+        storage_options: Optional[Dict[str, str]] = None,
     ):
         """Connect to a remote LanceDB database."""
         parsed = urlparse(db_url)
         if parsed.scheme != "db":
             raise ValueError(f"Invalid scheme: {parsed.scheme}, only accepts db://")
         self.db_name = parsed.netloc
+        prefix = parsed.path.lstrip("/")
+        self.db_prefix = None if not prefix else prefix
         self.api_key = api_key
         self._client = RestfulLanceDBClient(
             self.db_name,
             region,
             api_key,
             host_override,
+            self.db_prefix,
             connection_timeout=connection_timeout,
             read_timeout=read_timeout,
+            storage_options=storage_options,
         )
         self._request_thread_pool = request_thread_pool
         self._table_cache = TTLCache(maxsize=10000, ttl=300)

python/python/tests/test_table.py

@@ -735,7 +735,7 @@ def test_create_scalar_index(db):
     indices = table.to_lance().list_indices()
     assert len(indices) == 1
     scalar_index = indices[0]
-    assert scalar_index["type"] == "Scalar"
+    assert scalar_index["type"] == "BTree"
 
     # Confirm that prefiltering still works with the scalar index column
     results = table.search().where("x = 'c'").to_arrow()

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.6.0"
+version = "0.5.2"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.6.0"
+version = "0.5.2"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/README.md

@@ -6,12 +6,3 @@
 LanceDB Rust SDK, a serverless vector database.
 
 Read more at: https://lancedb.com/
-
-> [!TIP]
-> A transitive dependency of `lancedb` is `lzma-sys`, which uses dynamic linking
-> by default. If you want to statically link `lzma-sys`, you should activate it's
-> `static` feature by adding the following to your dependencies:
->
-> ```toml
-> lzma-sys = { version = "*", features = ["static"] }
-> ```

rust/lancedb/src/table.rs

@@ -1889,7 +1889,6 @@ impl TableInternal for NativeTable {
                 }
                 columns.push(field.name.clone());
             }
-
             let index_type = if is_vector {
                 crate::index::IndexType::IvfPq
             } else {