relax half req

closes https://github.com/lancedb/lancedb/issues/1007

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.4.17
+current_version = 0.4.18
 commit = True
 message = Bump version: {current_version} → {new_version}
 tag = True

Cargo.toml

@@ -14,22 +14,22 @@ keywords = ["lancedb", "lance", "database", "vector", "search"]
 categories = ["database-implementations"]
 
 [workspace.dependencies]
-lance = { "version" = "=0.10.15", "features" = ["dynamodb"] }
-lance-index = { "version" = "=0.10.15" }
-lance-linalg = { "version" = "=0.10.15" }
-lance-testing = { "version" = "=0.10.15" }
+lance = { "version" = "=0.10.18", "features" = ["dynamodb"] }
+lance-index = { "version" = "=0.10.18" }
+lance-linalg = { "version" = "=0.10.18" }
+lance-testing = { "version" = "=0.10.18" }
 # Note that this one does not include pyarrow
-arrow = { version = "50.0", optional = false }
-arrow-array = "50.0"
-arrow-data = "50.0"
-arrow-ipc = "50.0"
-arrow-ord = "50.0"
-arrow-schema = "50.0"
-arrow-arith = "50.0"
-arrow-cast = "50.0"
+arrow = { version = "51.0", optional = false }
+arrow-array = "51.0"
+arrow-data = "51.0"
+arrow-ipc = "51.0"
+arrow-ord = "51.0"
+arrow-schema = "51.0"
+arrow-arith = "51.0"
+arrow-cast = "51.0"
 async-trait = "0"
 chrono = "0.4.35"
-half = { "version" = "=2.3.1", default-features = false, features = [
+half = { "version" = "2.4.1", default-features = false, features = [
     "num-traits",
 ] }
 futures = "0"

docs/src/embeddings/embedding_functions.md

@@ -46,7 +46,7 @@ For this purpose, LanceDB introduces an **embedding functions API**, that allow
 
     ```python
     class Pets(LanceModel):
-        vector: Vector(clip.ndims) = clip.VectorField()
+        vector: Vector(clip.ndims()) = clip.VectorField()
         image_uri: str = clip.SourceField()
     ```
 
@@ -149,7 +149,7 @@ You can also use the integration for adding utility operations in the schema. Fo
 
 ```python
 class Pets(LanceModel):
-    vector: Vector(clip.ndims) = clip.VectorField()
+    vector: Vector(clip.ndims()) = clip.VectorField()
     image_uri: str = clip.SourceField()
 
     @property
@@ -166,4 +166,4 @@ rs[2].image
 ![](../assets/dog_clip_output.png)
 
 Now that you have the basic idea about LanceDB embedding functions and the embedding function registry,
-let's dive deeper into defining your own [custom functions](./custom_embedding_function.md).
+let's dive deeper into defining your own [custom functions](./custom_embedding_function.md).

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.4.17",
+      "version": "0.4.18",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.4.17",
-        "@lancedb/vectordb-darwin-x64": "0.4.17",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.4.17",
-        "@lancedb/vectordb-linux-x64-gnu": "0.4.17",
-        "@lancedb/vectordb-win32-x64-msvc": "0.4.17"
+        "@lancedb/vectordb-darwin-arm64": "0.4.18",
+        "@lancedb/vectordb-darwin-x64": "0.4.18",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.4.18",
+        "@lancedb/vectordb-linux-x64-gnu": "0.4.18",
+        "@lancedb/vectordb-win32-x64-msvc": "0.4.18"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -333,6 +333,66 @@
         "@jridgewell/sourcemap-codec": "^1.4.10"
       }
     },
+    "node_modules/@lancedb/vectordb-darwin-arm64": {
+      "version": "0.4.18",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.4.18.tgz",
+      "integrity": "sha512-CzJbkBKz30U0ocFFhRLV3ZPRZh3MtAkOmFr76jxRWeXLPM/JcLvhGOAnW9h/XdTONidHOfHNZnUtrjeWDMCyig==",
+      "cpu": [
+        "arm64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-darwin-x64": {
+      "version": "0.4.18",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.4.18.tgz",
+      "integrity": "sha512-wyqpfdDBE5g+8SLN/6E/r37smt5i+4H3MVNZ2GZfvcMAd4xIZTwGAf5Mfx8j15t3mvKMiBEZPTvYQfFde2bQmA==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "darwin"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
+      "version": "0.4.18",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.4.18.tgz",
+      "integrity": "sha512-OfCjTrwfdmT9Qh5r92AUj7Wosvl8mSYADS6rp+ofNoht9nq1UqtlyrCot1RhuF5w6UW1aLCJXycXY0qHh1WUPw==",
+      "cpu": [
+        "arm64"
+      ],
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-linux-x64-gnu": {
+      "version": "0.4.18",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.4.18.tgz",
+      "integrity": "sha512-uJiCminsZQ6oUvVYEElgN+/Lqd9646cJUWCbfiFSnt10PCj/kFBXWjKEuCxfG/A0bp6DTm5mU5RYWDfY9v3T0Q==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "linux"
+      ]
+    },
+    "node_modules/@lancedb/vectordb-win32-x64-msvc": {
+      "version": "0.4.18",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.4.18.tgz",
+      "integrity": "sha512-T9//HlvtNDHEfbIjz0ExLQFbqKFHRdaKf3jpFECt5oJdU0VCXe5460DIMvp6w/SDf24pb1UvOjZnmPLvX4yPNg==",
+      "cpu": [
+        "x64"
+      ],
+      "optional": true,
+      "os": [
+        "win32"
+      ]
+    },
     "node_modules/@neon-rs/cli": {
       "version": "0.0.160",
       "resolved": "https://registry.npmjs.org/@neon-rs/cli/-/cli-0.0.160.tgz",

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "description": " Serverless, low-latency vector database for AI applications",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",
@@ -88,10 +88,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-arm64": "0.4.17",
-    "@lancedb/vectordb-darwin-x64": "0.4.17",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.4.17",
-    "@lancedb/vectordb-linux-x64-gnu": "0.4.17",
-    "@lancedb/vectordb-win32-x64-msvc": "0.4.17"
+    "@lancedb/vectordb-darwin-arm64": "0.4.18",
+    "@lancedb/vectordb-darwin-x64": "0.4.18",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.4.18",
+    "@lancedb/vectordb-linux-x64-gnu": "0.4.18",
+    "@lancedb/vectordb-win32-x64-msvc": "0.4.18"
   }
 }

node/src/remote/index.ts

@@ -140,6 +140,9 @@ export class RemoteConnection implements Connection {
       schema = nameOrOpts.schema
       embeddings = nameOrOpts.embeddingFunction
       tableName = nameOrOpts.name
+      if (data === undefined) {
+        data = nameOrOpts.data
+      }
     }
 
     let buffer: Buffer

nodejs/.gitignore

@@ -0,0 +1 @@
+yarn.lock

nodejs/lancedb/connection.ts

@@ -77,6 +77,18 @@ export interface OpenTableOptions {
    * The available options are described at https://lancedb.github.io/lancedb/guides/storage/
    */
   storageOptions?: Record<string, string>;
+  /**
+   * Set the size of the index cache, specified as a number of entries
+   *
+   * The exact meaning of an "entry" will depend on the type of index:
+   * - IVF: there is one entry for each IVF partition
+   * - BTREE: there is one entry for the entire index
+   *
+   * This cache applies to the entire opened table, across all indices.
+   * Setting this value higher will increase performance on larger datasets
+   * at the expense of more RAM
+   */
+  indexCacheSize?: number;
 }
 
 export interface TableNamesOptions {
@@ -160,6 +172,7 @@ export class Connection {
     const innerTable = await this.inner.openTable(
       name,
       cleanseStorageOptions(options?.storageOptions),
+      options?.indexCacheSize,
     );
     return new Table(innerTable);
   }

nodejs/lancedb/table.ts

@@ -169,17 +169,20 @@ export class Table {
    * // If the column has a vector (fixed size list) data type then
    * // an IvfPq vector index will be created.
    * const table = await conn.openTable("my_table");
-   * await table.createIndex(["vector"]);
+   * await table.createIndex("vector");
    * @example
    * // For advanced control over vector index creation you can specify
    * // the index type and options.
    * const table = await conn.openTable("my_table");
-   * await table.createIndex(["vector"], I)
-   *   .ivf_pq({ num_partitions: 128, num_sub_vectors: 16 })
-   *   .build();
+   * await table.createIndex("vector", {
+   *   config: lancedb.Index.ivfPq({
+   *     numPartitions: 128,
+   *     numSubVectors: 16,
+   *   }),
+   * });
    * @example
    * // Or create a Scalar index
-   * await table.createIndex("my_float_col").build();
+   * await table.createIndex("my_float_col");
    */
   async createIndex(column: string, options?: Partial<IndexOptions>) {
     // Bit of a hack to get around the fact that TS has no package-scope.
@@ -197,8 +200,7 @@ export class Table {
    * vector similarity, sorting, and more.
    *
    * Note: By default, all columns are returned.  For best performance, you should
-   * only fetch the columns you need.  See [`Query::select_with_projection`] for
-   * more details.
+   * only fetch the columns you need.
    *
    * When appropriate, various indices and statistics based pruning will be used to
    * accelerate the query.
@@ -206,10 +208,13 @@ export class Table {
    * // SQL-style filtering
    * //
    * // This query will return up to 1000 rows whose value in the `id` column
-   * // is greater than 5.  LanceDb supports a broad set of filtering functions.
-   * for await (const batch of table.query()
-   *                          .filter("id > 1").select(["id"]).limit(20)) {
-   *  console.log(batch);
+   * // is greater than 5. LanceDb supports a broad set of filtering functions.
+   * for await (const batch of table
+   *   .query()
+   *   .where("id > 1")
+   *   .select(["id"])
+   *   .limit(20)) {
+   *   console.log(batch);
    * }
    * @example
    * // Vector Similarity Search
@@ -218,13 +223,14 @@ export class Table {
    * // closest to the query vector [1.0, 2.0, 3.0].  If an index has been created
    * // on the "vector" column then this will perform an ANN search.
    * //
-   * // The `refine_factor` and `nprobes` methods are used to control the recall /
+   * // The `refineFactor` and `nprobes` methods are used to control the recall /
    * // latency tradeoff of the search.
-   * for await (const batch of table.query()
-   *                    .nearestTo([1, 2, 3])
-   *                    .refineFactor(5).nprobe(10)
-   *                    .limit(10)) {
-   *  console.log(batch);
+   * for await (const batch of table
+   *   .query()
+   *   .where("id > 1")
+   *   .select(["id"])
+   *   .limit(20)) {
+   *   console.log(batch);
    * }
    * @example
    * // Scan the full dataset
@@ -286,43 +292,45 @@ export class Table {
     await this.inner.dropColumns(columnNames);
   }
 
-  /**
-   * Retrieve the version of the table
-   *
-   * LanceDb supports versioning.  Every operation that modifies the table increases
-   * version.  As long as a version hasn't been deleted you can `[Self::checkout]` that
-   * version to view the data at that point.  In addition, you can `[Self::restore]` the
-   * version to replace the current table with a previous version.
-   */
+  /** Retrieve the version of the table */
   async version(): Promise<number> {
     return await this.inner.version();
   }
 
   /**
-   * Checks out a specific version of the Table
+   * Checks out a specific version of the table _This is an in-place operation._
    *
-   * Any read operation on the table will now access the data at the checked out version.
-   * As a consequence, calling this method will disable any read consistency interval
-   * that was previously set.
+   * This allows viewing previous versions of the table. If you wish to
+   * keep writing to the dataset starting from an old version, then use
+   * the `restore` function.
    *
-   * This is a read-only operation that turns the table into a sort of "view"
-   * or "detached head".  Other table instances will not be affected.  To make the change
-   * permanent you can use the `[Self::restore]` method.
+   * Calling this method will set the table into time-travel mode. If you
+   * wish to return to standard mode, call `checkoutLatest`.
+   * @param {number} version The version to checkout
+   * @example
+   * ```typescript
+   * import * as lancedb from "@lancedb/lancedb"
+   * const db = await lancedb.connect("./.lancedb");
+   * const table = await db.createTable("my_table", [
+   *   { vector: [1.1, 0.9], type: "vector" },
+   * ]);
    *
-   * Any operation that modifies the table will fail while the table is in a checked
-   * out state.
-   *
-   * To return the table to a normal state use `[Self::checkout_latest]`
+   * console.log(await table.version()); // 1
+   * console.log(table.display());
+   * await table.add([{ vector: [0.5, 0.2], type: "vector" }]);
+   * await table.checkout(1);
+   * console.log(await table.version()); // 2
+   * ```
    */
   async checkout(version: number): Promise<void> {
     await this.inner.checkout(version);
   }
 
   /**
-   * Ensures the table is pointing at the latest version
+   * Checkout the latest version of the table. _This is an in-place operation._
    *
-   * This can be used to manually update a table when the read_consistency_interval is None
-   * It can also be used to undo a `[Self::checkout]` operation
+   * The table will be set back into standard mode, and will track the latest
+   * version of the table.
    */
   async checkoutLatest(): Promise<void> {
     await this.inner.checkoutLatest();
@@ -344,9 +352,7 @@ export class Table {
     await this.inner.restore();
   }
 
-  /**
-   * List all indices that have been created with Self::create_index
-   */
+  /** List all indices that have been created with {@link Table.createIndex} */
   async listIndices(): Promise<IndexConfig[]> {
     return await this.inner.listIndices();
   }

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-darwin-arm64",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "os": [
     "darwin"
   ],

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-darwin-x64",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "os": [
     "darwin"
   ],

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

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-linux-arm64-gnu",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "os": [
     "linux"
   ],

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

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-linux-x64-gnu",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "os": [
     "linux"
   ],

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.4.16",
+  "version": "0.4.18",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.4.16",
+      "version": "0.4.18",
       "cpu": [
         "x64",
         "arm64"
@@ -45,13 +45,6 @@
       },
       "engines": {
         "node": ">= 18"
-      },
-      "optionalDependencies": {
-        "@lancedb/lancedb-darwin-arm64": "0.4.16",
-        "@lancedb/lancedb-darwin-x64": "0.4.16",
-        "@lancedb/lancedb-linux-arm64-gnu": "0.4.16",
-        "@lancedb/lancedb-linux-x64-gnu": "0.4.16",
-        "@lancedb/lancedb-win32-x64-msvc": "0.4.16"
       }
     },
     "node_modules/@75lb/deep-merge": {
@@ -2221,81 +2214,6 @@
         "@jridgewell/sourcemap-codec": "^1.4.14"
       }
     },
-    "node_modules/@lancedb/lancedb-darwin-arm64": {
-      "version": "0.4.16",
-      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-darwin-arm64/-/lancedb-darwin-arm64-0.4.16.tgz",
-      "integrity": "sha512-CV65ouIDQbBSNtdHbQSr2fqXflOuqud1cfweUS+EiK7eEOEYl7nO2oiFYO49Jy76MEwZxiP99hW825aCqIQJqg==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ],
-      "engines": {
-        "node": ">= 18"
-      }
-    },
-    "node_modules/@lancedb/lancedb-darwin-x64": {
-      "version": "0.4.16",
-      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-darwin-x64/-/lancedb-darwin-x64-0.4.16.tgz",
-      "integrity": "sha512-1CwIYCNdbFmV7fvqM+qUxbYgwxx0slcCV48PC/I19Ejitgtzw/NJiWDCvONhaLqG85lWNZm1xYceRpVv7b8seQ==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "darwin"
-      ],
-      "engines": {
-        "node": ">= 18"
-      }
-    },
-    "node_modules/@lancedb/lancedb-linux-arm64-gnu": {
-      "version": "0.4.16",
-      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-linux-arm64-gnu/-/lancedb-linux-arm64-gnu-0.4.16.tgz",
-      "integrity": "sha512-CzLEbzoHKS6jV0k52YnvsiVNx0VzLp1Vz/zmbHI6HmB/XbS67qDO93Jk71MDmXq3JDw0FKFCw9ghkg+6YWq7ZA==",
-      "cpu": [
-        "arm64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ],
-      "engines": {
-        "node": ">= 18"
-      }
-    },
-    "node_modules/@lancedb/lancedb-linux-x64-gnu": {
-      "version": "0.4.16",
-      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-linux-x64-gnu/-/lancedb-linux-x64-gnu-0.4.16.tgz",
-      "integrity": "sha512-nKChybybi8uA0AFRHBFm7Fz3VXcRm8riv5Gs7xQsrsCtYxxf4DT/0BfUvQ0xKbwNJa+fawHRxi9BOQewdj49fg==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "linux"
-      ],
-      "engines": {
-        "node": ">= 18"
-      }
-    },
-    "node_modules/@lancedb/lancedb-win32-x64-msvc": {
-      "version": "0.4.16",
-      "resolved": "https://registry.npmjs.org/@lancedb/lancedb-win32-x64-msvc/-/lancedb-win32-x64-msvc-0.4.16.tgz",
-      "integrity": "sha512-KMeBPMpv2g+ZMVsHVibed7BydrBlxje1qS0bZTDrLw9BtZOk6XH2lh1mCDnCJI6sbAscUKNA6fDCdquhQPHL7w==",
-      "cpu": [
-        "x64"
-      ],
-      "optional": true,
-      "os": [
-        "win32"
-      ],
-      "engines": {
-        "node": ">= 18"
-      }
-    },
     "node_modules/@napi-rs/cli": {
       "version": "2.18.0",
       "resolved": "https://registry.npmjs.org/@napi-rs/cli/-/cli-2.18.0.tgz",

nodejs/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.4.17",
+  "version": "0.4.18",
   "main": "./dist/index.js",
   "types": "./dist/index.d.ts",
   "napi": {
@@ -62,20 +62,14 @@
     "build-release": "npm run build:release && tsc -b && shx cp lancedb/native.d.ts dist/native.d.ts",
     "chkformat": "prettier . --check",
     "docs": "typedoc --plugin typedoc-plugin-markdown --out ../docs/src/js lancedb/index.ts",
-    "lint": "eslint lancedb && eslint __test__",
+    "lint": "eslint lancedb __test__",
+    "lint-fix": "eslint lancedb __test__ --fix",
     "prepublishOnly": "napi prepublish -t npm",
     "test": "npm run build && jest --verbose",
     "integration": "S3_TEST=1 npm run test",
     "universal": "napi universal",
     "version": "napi version"
   },
-  "optionalDependencies": {
-    "@lancedb/lancedb-darwin-arm64": "0.4.17",
-    "@lancedb/lancedb-darwin-x64": "0.4.17",
-    "@lancedb/lancedb-linux-arm64-gnu": "0.4.17",
-    "@lancedb/lancedb-linux-x64-gnu": "0.4.17",
-    "@lancedb/lancedb-win32-x64-msvc": "0.4.17"
-  },
   "dependencies": {
     "openai": "^4.29.2",
     "apache-arrow": "^15.0.0"

nodejs/src/connection.rs

@@ -176,6 +176,7 @@ impl Connection {
         &self,
         name: String,
         storage_options: Option<HashMap<String, String>>,
+        index_cache_size: Option<u32>,
     ) -> napi::Result<Table> {
         let mut builder = self.get_inner()?.open_table(&name);
         if let Some(storage_options) = storage_options {
@@ -183,6 +184,9 @@ impl Connection {
                 builder = builder.storage_option(key, value);
             }
         }
+        if let Some(index_cache_size) = index_cache_size {
+            builder = builder.index_cache_size(index_cache_size);
+        }
         let tbl = builder
             .execute()
             .await

python/.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.6.10
+current_version = 0.6.11
 commit = True
 message = [python] Bump version: {current_version} → {new_version}
 tag = True

python/Cargo.toml

@@ -14,7 +14,7 @@ name = "_lancedb"
 crate-type = ["cdylib"]
 
 [dependencies]
-arrow = { version = "50.0.0", features = ["pyarrow"] }
+arrow = { version = "51.0.0", features = ["pyarrow"] }
 lancedb = { path = "../rust/lancedb" }
 env_logger = "0.10"
 pyo3 = { version = "0.20", features = ["extension-module", "abi3-py38"] }

python/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "lancedb"
-version = "0.6.10"
+version = "0.6.11"
 dependencies = [
     "deprecation",
     "pylance==0.10.12",

python/python/lancedb/db.py

@@ -224,13 +224,23 @@ class DBConnection(EnforceOverrides):
     def __getitem__(self, name: str) -> LanceTable:
         return self.open_table(name)
 
-    def open_table(self, name: str) -> Table:
+    def open_table(self, name: str, *, index_cache_size: Optional[int] = None) -> Table:
         """Open a Lance Table in the database.
 
         Parameters
         ----------
         name: str
             The name of the table.
+        index_cache_size: int, default 256
+            Set the size of the index cache, specified as a number of entries
+
+            The exact meaning of an "entry" will depend on the type of index:
+            * IVF - there is one entry for each IVF partition
+            * BTREE - there is one entry for the entire index
+
+            This cache applies to the entire opened table, across all indices.
+            Setting this value higher will increase performance on larger datasets
+            at the expense of more RAM
 
         Returns
         -------
@@ -248,6 +258,18 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError
 
+    def rename_table(self, cur_name: str, new_name: str):
+        """Rename a table in the database.
+
+        Parameters
+        ----------
+        cur_name: str
+            The current name of the table.
+        new_name: str
+            The new name of the table.
+        """
+        raise NotImplementedError
+
     def drop_database(self):
         """
         Drop database
@@ -407,7 +429,9 @@ class LanceDBConnection(DBConnection):
         return tbl
 
     @override
-    def open_table(self, name: str) -> LanceTable:
+    def open_table(
+        self, name: str, *, index_cache_size: Optional[int] = None
+    ) -> LanceTable:
         """Open a table in the database.
 
         Parameters
@@ -419,7 +443,7 @@ class LanceDBConnection(DBConnection):
         -------
         A LanceTable object representing the table.
         """
-        return LanceTable.open(self, name)
+        return LanceTable.open(self, name, index_cache_size=index_cache_size)
 
     @override
     def drop_table(self, name: str, ignore_missing: bool = False):
@@ -751,7 +775,10 @@ class AsyncConnection(object):
         return AsyncTable(new_table)
 
     async def open_table(
-        self, name: str, storage_options: Optional[Dict[str, str]] = None
+        self,
+        name: str,
+        storage_options: Optional[Dict[str, str]] = None,
+        index_cache_size: Optional[int] = None,
     ) -> Table:
         """Open a Lance Table in the database.
 
@@ -764,12 +791,22 @@ class AsyncConnection(object):
             connection will be inherited by the table, but can be overridden here.
             See available options at
             https://lancedb.github.io/lancedb/guides/storage/
+        index_cache_size: int, default 256
+            Set the size of the index cache, specified as a number of entries
+
+            The exact meaning of an "entry" will depend on the type of index:
+            * IVF - there is one entry for each IVF partition
+            * BTREE - there is one entry for the entire index
+
+            This cache applies to the entire opened table, across all indices.
+            Setting this value higher will increase performance on larger datasets
+            at the expense of more RAM
 
         Returns
         -------
         A LanceTable object representing the table.
         """
-        table = await self._inner.open_table(name, storage_options)
+        table = await self._inner.open_table(name, storage_options, index_cache_size)
         return AsyncTable(table)
 
     async def drop_table(self, name: str):

python/python/lancedb/remote/db.py

@@ -94,7 +94,7 @@ class RemoteDBConnection(DBConnection):
                 yield item
 
     @override
-    def open_table(self, name: str) -> Table:
+    def open_table(self, name: str, *, index_cache_size: Optional[int] = None) -> Table:
         """Open a Lance Table in the database.
 
         Parameters
@@ -110,6 +110,12 @@ class RemoteDBConnection(DBConnection):
 
         self._client.mount_retry_adapter_for_table(name)
 
+        if index_cache_size is not None:
+            logging.info(
+                "index_cache_size is ignored in LanceDb Cloud"
+                " (there is no local cache to configure)"
+            )
+
         # check if table exists
         if self._table_cache.get(name) is None:
             self._client.post(f"/v1/table/{name}/describe/")
@@ -281,6 +287,24 @@ class RemoteDBConnection(DBConnection):
         )
         self._table_cache.pop(name)
 
+    @override
+    def rename_table(self, cur_name: str, new_name: str):
+        """Rename a table in the database.
+
+        Parameters
+        ----------
+        cur_name: str
+            The current name of the table.
+        new_name: str
+            The new name of the table.
+        """
+        self._client.post(
+            f"/v1/table/{cur_name}/rename/",
+            json={"new_table_name": new_name},
+        )
+        self._table_cache.pop(cur_name)
+        self._table_cache[new_name] = True
+
     async def close(self):
         """Close the connection to the database."""
         self._client.close()

python/python/lancedb/remote/table.py

@@ -72,7 +72,7 @@ class RemoteTable(Table):
         return resp
 
     def index_stats(self, index_uuid: str):
-        """List all the indices on the table"""
+        """List all the stats of a specified index"""
         resp = self._conn._client.post(
             f"/v1/table/{self._name}/index/{index_uuid}/stats/"
         )

python/python/lancedb/table.py

@@ -806,6 +806,7 @@ class _LanceLatestDatasetRef(_LanceDatasetRef):
     """Reference to the latest version of a LanceDataset."""
 
     uri: str
+    index_cache_size: Optional[int] = None
     read_consistency_interval: Optional[timedelta] = None
     last_consistency_check: Optional[float] = None
     _dataset: Optional[LanceDataset] = None
@@ -813,7 +814,9 @@ class _LanceLatestDatasetRef(_LanceDatasetRef):
     @property
     def dataset(self) -> LanceDataset:
         if not self._dataset:
-            self._dataset = lance.dataset(self.uri)
+            self._dataset = lance.dataset(
+                self.uri, index_cache_size=self.index_cache_size
+            )
             self.last_consistency_check = time.monotonic()
         elif self.read_consistency_interval is not None:
             now = time.monotonic()
@@ -842,12 +845,15 @@ class _LanceLatestDatasetRef(_LanceDatasetRef):
 class _LanceTimeTravelRef(_LanceDatasetRef):
     uri: str
     version: int
+    index_cache_size: Optional[int] = None
     _dataset: Optional[LanceDataset] = None
 
     @property
     def dataset(self) -> LanceDataset:
         if not self._dataset:
-            self._dataset = lance.dataset(self.uri, version=self.version)
+            self._dataset = lance.dataset(
+                self.uri, version=self.version, index_cache_size=self.index_cache_size
+            )
         return self._dataset
 
     @dataset.setter
@@ -884,6 +890,8 @@ class LanceTable(Table):
         connection: "LanceDBConnection",
         name: str,
         version: Optional[int] = None,
+        *,
+        index_cache_size: Optional[int] = None,
     ):
         self._conn = connection
         self.name = name
@@ -892,11 +900,13 @@ class LanceTable(Table):
             self._ref = _LanceTimeTravelRef(
                 uri=self._dataset_uri,
                 version=version,
+                index_cache_size=index_cache_size,
             )
         else:
             self._ref = _LanceLatestDatasetRef(
                 uri=self._dataset_uri,
                 read_consistency_interval=connection.read_consistency_interval,
+                index_cache_size=index_cache_size,
             )
 
     @classmethod

python/python/tests/test_db.py

@@ -368,6 +368,15 @@ async def test_create_exist_ok_async(tmp_path):
     #     await db.create_table("test", schema=bad_schema, exist_ok=True)
 
 
+def test_open_table_sync(tmp_path):
+    db = lancedb.connect(tmp_path)
+    db.create_table("test", data=[{"id": 0}])
+    assert db.open_table("test").count_rows() == 1
+    assert db.open_table("test", index_cache_size=0).count_rows() == 1
+    with pytest.raises(FileNotFoundError, match="does not exist"):
+        db.open_table("does_not_exist")
+
+
 @pytest.mark.asyncio
 async def test_open_table(tmp_path):
     db = await lancedb.connect_async(tmp_path)
@@ -397,6 +406,10 @@ async def test_open_table(tmp_path):
         }
     )
 
+    # No way to verify this yet, but at least make sure we
+    # can pass the parameter
+    await db.open_table("test", index_cache_size=0)
+
     with pytest.raises(ValueError, match="was not found"):
         await db.open_table("does_not_exist")
 

python/src/connection.rs

@@ -134,17 +134,21 @@ impl Connection {
         })
     }
 
-    #[pyo3(signature = (name, storage_options = None))]
+    #[pyo3(signature = (name, storage_options = None, index_cache_size = None))]
     pub fn open_table(
         self_: PyRef<'_, Self>,
         name: String,
         storage_options: Option<HashMap<String, String>>,
+        index_cache_size: Option<u32>,
     ) -> PyResult<&PyAny> {
         let inner = self_.get_inner()?.clone();
         let mut builder = inner.open_table(name);
         if let Some(storage_options) = storage_options {
             builder = builder.storage_options(storage_options);
         }
+        if let Some(index_cache_size) = index_cache_size {
+            builder = builder.index_cache_size(index_cache_size);
+        }
         future_into_py(self_.py(), async move {
             let table = builder.execute().await.infer_error()?;
             Ok(Table::new(table))

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.4.17"
+version = "0.4.18"
 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 = "0.4.17"
+version = "0.4.18"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -52,7 +52,7 @@ aws-sdk-kms = { version = "1.0" }
 aws-config = { version = "1.0" }
 
 [features]
-default = ["remote"]
+default = []
 remote = ["dep:reqwest"]
 fp16kernels = ["lance-linalg/fp16kernels"]
-s3-test = []
+s3-test = []

rust/lancedb/src/connection.rs

@@ -33,6 +33,9 @@ use crate::table::{NativeTable, WriteOptions};
 use crate::utils::validate_table_name;
 use crate::Table;
 
+#[cfg(feature = "remote")]
+use log::warn;
+
 pub const LANCE_FILE_EXTENSION: &str = "lance";
 
 pub type TableBuilderCallback = Box<dyn FnOnce(OpenTableBuilder) -> OpenTableBuilder + Send>;
@@ -579,6 +582,7 @@ impl ConnectBuilder {
         let api_key = self.api_key.ok_or_else(|| Error::InvalidInput {
             message: "An api_key is required when connecting to LanceDb Cloud".to_string(),
         })?;
+        warn!("The rust implementation of the remote client is not yet ready for use.");
         let internal = Arc::new(crate::remote::db::RemoteDatabase::try_new(
             &self.uri,
             &api_key,
@@ -909,12 +913,23 @@ impl ConnectionInternal for Database {
             }
         }
 
+        // Some ReadParams are exposed in the OpenTableBuilder, but we also
+        // let the user provide their own ReadParams.
+        //
+        // If we have a user provided ReadParams use that
+        // If we don't then start with the default ReadParams and customize it with
+        // the options from the OpenTableBuilder
+        let read_params = options.lance_read_params.unwrap_or_else(|| ReadParams {
+            index_cache_size: options.index_cache_size as usize,
+            ..Default::default()
+        });
+
         let native_table = Arc::new(
             NativeTable::open_with_params(
                 &table_uri,
                 &options.name,
                 self.store_wrapper.clone(),
-                options.lance_read_params,
+                Some(read_params),
                 self.read_consistency_interval,
             )
             .await?,
@@ -1032,7 +1047,6 @@ mod tests {
     }
 
     #[tokio::test]
-    #[ignore = "this can't pass due to https://github.com/lancedb/lancedb/issues/1019, enable it after the bug fixed"]
     async fn test_open_table() {
         let tmp_dir = tempdir().unwrap();
         let uri = tmp_dir.path().to_str().unwrap();

rust/lancedb/src/index/vector.rs

@@ -46,10 +46,18 @@ impl VectorIndex {
     }
 }
 
+#[derive(Debug, Deserialize)]
+pub struct VectorIndexMetadata {
+    pub metric_type: String,
+    pub index_type: String,
+}
+
 #[derive(Debug, Deserialize)]
 pub struct VectorIndexStatistics {
     pub num_indexed_rows: usize,
     pub num_unindexed_rows: usize,
+    pub index_type: String,
+    pub indices: Vec<VectorIndexMetadata>,
 }
 
 /// Builder for an IVF PQ index.

rust/lancedb/src/io/object_store.rs

@@ -350,8 +350,16 @@ mod test {
 
     #[tokio::test]
     async fn test_e2e() {
-        let dir1 = tempfile::tempdir().unwrap().into_path();
-        let dir2 = tempfile::tempdir().unwrap().into_path();
+        let dir1 = tempfile::tempdir()
+            .unwrap()
+            .into_path()
+            .canonicalize()
+            .unwrap();
+        let dir2 = tempfile::tempdir()
+            .unwrap()
+            .into_path()
+            .canonicalize()
+            .unwrap();
 
         let secondary_store = LocalFileSystem::new_with_prefix(dir2.to_str().unwrap()).unwrap();
         let object_store_wrapper = Arc::new(MirroringObjectStoreWrapper {

rust/lancedb/src/lib.rs

@@ -34,6 +34,16 @@
 //! cargo install lancedb
 //! ```
 //!
+//! ## Crate Features
+//!
+//! ### Experimental Features
+//!
+//! These features are not enabled by default.  They are experimental or in-development features that
+//! are not yet ready to be released.
+//!
+//! - `remote` - Enable remote client to connect to LanceDB cloud.  This is not yet fully implemented
+//!              and should not be enabled.
+//!
 //! ### Quick Start
 //!
 //! #### Connect to a database.

rust/lancedb/src/remote/db.rs

@@ -87,14 +87,16 @@ impl ConnectionInternal for RemoteDatabase {
             .await
             .unwrap()?;
 
-        self.client
-            .post(&format!("/v1/table/{}/create", options.name))
+        let rsp = self
+            .client
+            .post(&format!("/v1/table/{}/create/", options.name))
             .body(data_buffer)
             .header(CONTENT_TYPE, ARROW_STREAM_CONTENT_TYPE)
             // This is currently expected by LanceDb cloud but will be removed soon.
             .header("x-request-id", "na")
             .send()
             .await?;
+        self.client.check_response(rsp).await?;
 
         Ok(Table::new(Arc::new(RemoteTable::new(
             self.client.clone(),

rust/lancedb/src/table.rs

@@ -1061,6 +1061,26 @@ impl NativeTable {
         }
     }
 
+    pub async fn get_index_type(&self, index_uuid: &str) -> Result<Option<String>> {
+        match self.load_index_stats(index_uuid).await? {
+            Some(stats) => Ok(Some(stats.index_type)),
+            None => Ok(None),
+        }
+    }
+
+    pub async fn get_distance_type(&self, index_uuid: &str) -> Result<Option<String>> {
+        match self.load_index_stats(index_uuid).await? {
+            Some(stats) => Ok(Some(
+                stats
+                    .indices
+                    .iter()
+                    .map(|i| i.metric_type.clone())
+                    .collect(),
+            )),
+            None => Ok(None),
+        }
+    }
+
     pub async fn load_indices(&self) -> Result<Vec<VectorIndex>> {
         let dataset = self.dataset.get().await?;
         let (indices, mf) = futures::try_join!(dataset.load_indices(), dataset.latest_manifest())?;