Bump version: 0.22.0-beta.7 → 0.22.0-beta.8

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Added the ability to prewarm (load into memory) table indexes via new
methods in Python, Node.js, and Rust APIs, potentially reducing
cold-start query latency.
- **Bug Fixes**
- Ensured prewarming an index does not interfere with subsequent search
operations.
- **Tests**
- Introduced new test cases to verify full-text search index creation,
prewarming, and search functionalities in both Python and Node.js.
- **Chores**
  - Updated dependencies for improved compatibility and performance.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: Lu Qiu <luqiujob@gmail.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.19.0-beta.6"
+current_version = "0.19.0-beta.7"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

Cargo.lock

@@ -2721,8 +2721,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "rand 0.8.5",
 ]
@@ -3711,8 +3711,8 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -3738,6 +3738,7 @@ dependencies = [
  "deepsize",
  "futures",
  "half",
+ "humantime",
  "itertools 0.13.0",
  "lance-arrow",
  "lance-core",
@@ -3771,8 +3772,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3789,8 +3790,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3826,8 +3827,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3854,8 +3855,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3870,8 +3871,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrayref",
  "arrow",
@@ -3910,8 +3911,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -3945,8 +3946,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3999,8 +4000,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4038,8 +4039,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow-array",
  "arrow-ord",
@@ -4062,8 +4063,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4102,8 +4103,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "0.25.3"
+version = "0.26.0"
-source = "git+https://github.com/lancedb/lance?tag=v0.25.3-beta.4#236c8f986ab9e2d478d0754fab6e8d2643c31247"
+source = "git+https://github.com/lancedb/lance?tag=v0.26.0-beta.1#8e46047e2dcb171bec28e28b507a9b7858348773"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4114,7 +4115,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.19.0-beta.6"
+version = "0.19.0-beta.7"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4201,7 +4202,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-node"
-version = "0.19.0-beta.6"
+version = "0.19.0-beta.7"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4226,7 +4227,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.19.0-beta.6"
+version = "0.19.0-beta.7"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4244,7 +4245,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.22.0-beta.6"
+version = "0.22.0-beta.7"
 dependencies = [
  "arrow",
  "env_logger",

Cargo.toml

@@ -21,16 +21,16 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.25.3", "features" = [
+lance = { "version" = "=0.26.0", "features" = [
     "dynamodb",
-], tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+], tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-io = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-io = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-index = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-index = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-linalg = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-linalg = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-table = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-table = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-testing = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-testing = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-datafusion = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-datafusion = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
-lance-encoding = { version = "=0.25.3", tag = "v0.25.3-beta.4", git = "https://github.com/lancedb/lance" }
+lance-encoding = { version = "=0.26.0", tag = "v0.26.0-beta.1", git = "https://github.com/lancedb/lance" }
 # Note that this one does not include pyarrow
 arrow = { version = "54.1", optional = false }
 arrow-array = "54.1"

docs/README.md

@@ -2,7 +2,7 @@
 
 LanceDB docs are deployed to https://lancedb.github.io/lancedb/.
 
-Docs is built and deployed automatically by [Github Actions](.github/workflows/docs.yml)
+Docs is built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
 whenever a commit is pushed to the `main` branch. So it is possible for the docs to show
 unreleased features.
 

docs/src/guides/storage.md

@@ -342,7 +342,7 @@ For **read and write access**, LanceDB will need a policy such as:
             "Action": [
               "s3:PutObject",
               "s3:GetObject",
-              "s3:DeleteObject",
+              "s3:DeleteObject"
             ],
             "Resource": "arn:aws:s3:::<bucket>/<prefix>/*"
         },
@@ -374,7 +374,7 @@ For **read-only access**, LanceDB will need a policy such as:
         {
             "Effect": "Allow",
             "Action": [
-              "s3:GetObject",
+              "s3:GetObject"
             ],
             "Resource": "arn:aws:s3:::<bucket>/<prefix>/*"
         },

docs/src/js/classes/Table.md

@@ -454,6 +454,28 @@ Modeled after ``VACUUM`` in PostgreSQL.
 
 ***
 
+### prewarmIndex()
+
+```ts
+abstract prewarmIndex(name): Promise<void>
+```
+
+Prewarm an index in the table.
+
+#### Parameters
+
+* **name**: `string`
+    The name of the index.
+    This will load the index into memory.  This may reduce the cold-start time for
+    future queries.  If the index does not fit in the cache then this call may be
+    wasteful.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;
+
+***
+
 ### query()
 
 ```ts

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.19.0-beta.6</version>
+        <version>0.19.0-beta.7</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.19.0-beta.6</version>
+    <version>0.19.0-beta.7</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.19.0-beta.6",
+  "version": "0.19.0-beta.7",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.6",
+        "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.7",
-        "@lancedb/vectordb-darwin-x64": "0.19.0-beta.6",
+        "@lancedb/vectordb-darwin-x64": "0.19.0-beta.7",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.6",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.7",
-        "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.6",
+        "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.7",
-        "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.6"
+        "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.7"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -327,9 +327,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.0-beta.6.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.0-beta.7.tgz",
-      "integrity": "sha512-fujUe3Gt1n1vgxXMDaUatZEQICh9VAmj1CJK/gQCMZo9ky/MH1TnxP0nA6hN7fkRvl28C2Ms2adlTdlnTxLSlw==",
+      "integrity": "sha512-HpbVKw4Vs+mPv7uPwaK7ilJlGrGdjOrNlC2mSkMCj0OlEwGRVcEcrSyijI7LXQH7ybEgNnDhSds5TuzBV26SGg==",
       "cpu": [
         "arm64"
       ],
@@ -340,9 +340,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.0-beta.6.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.0-beta.7.tgz",
-      "integrity": "sha512-ZKUvPwKvnK5WfyCR3Asbm1XXXA5JWYfDVD2ovPU/mv/rqoroYEpxm7TH1OG8AQ8bvBmrCmPc0sPJP5kijd6BFg==",
+      "integrity": "sha512-x3X7nqIYVZtxaa0uZUk/M99vKvDinZ5G0+8k2NqZ696YXGWKGyRxR6k8ZzKYCoCTSuYXnBftgKoIlwJGtNt8Bw==",
       "cpu": [
         "x64"
       ],
@@ -353,9 +353,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.0-beta.6.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.0-beta.7.tgz",
-      "integrity": "sha512-m4DuGCEhEAy+EtamSBMF1ujiVkpJD3ybF/Yp1pYYo9FTFThczAeRiyUg7diRZYfahZExKsATj62PqHXNVo8x9A==",
+      "integrity": "sha512-Vwj0HI3+b4NgXKf+5+W/GfLBCGoQMBGM47vA/ts1dpe/PxraOQYPDv67I5kbXkCQKwhal7b0iZx/PbMu0JZPyw==",
       "cpu": [
         "arm64"
       ],
@@ -366,9 +366,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.0-beta.6.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.0-beta.7.tgz",
-      "integrity": "sha512-npUR23GZJDVfkPUPtaxLuYUeqyAQ/vcp4R7RjCSdBo+hJNiQAG4TX31YAE8OKnOGskEO7XJ3BgEAxM+upiNmnA==",
+      "integrity": "sha512-Dx2B6UWQei9D7Rt+MgHWqPTYtEK2w3EgsNb5ENEWUTZxH7lD/CV7Sw0JMK5LDG209fFcpXFerveF6J8ZC8uGBQ==",
       "cpu": [
         "x64"
       ],
@@ -379,9 +379,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.0-beta.6.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.0-beta.7.tgz",
-      "integrity": "sha512-Ebas+phT0D7NoB1e3lMZn5h7WVyT5pPIwO1Kk1cZ93V4zaxn2BQRwjLTLxJwR9G+emQoLv659Ze0NtnFuEbXaA==",
+      "integrity": "sha512-F5LZGa+gkUH1TgsWZWLLAMejwXFIWdash7+85ip4k2M0ThyqLF/dtlldOvteUEd5+flxihGjHg6TUtnSY8XBFA==",
       "cpu": [
         "x64"
       ],

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.19.0-beta.6",
+  "version": "0.19.0-beta.7",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -89,10 +89,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.19.0-beta.6",
+    "@lancedb/vectordb-darwin-x64": "0.19.0-beta.7",
-    "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.6",
+    "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.7",
-    "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.6",
+    "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.7",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.6",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.7",
-    "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.6"
+    "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.7"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.19.0-beta.6"
+version = "0.19.0-beta.7"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/__test__/table.test.ts

@@ -1312,6 +1312,28 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results2[0].text).toBe(data[1].text);
     });
 
+    test("prewarm full text search index", async () => {
+      const db = await connect(tmpDir.name);
+      const data = [
+        { text: ["lance database", "the", "search"], vector: [0.1, 0.2, 0.3] },
+        { text: ["lance database"], vector: [0.4, 0.5, 0.6] },
+        { text: ["lance", "search"], vector: [0.7, 0.8, 0.9] },
+        { text: ["database", "search"], vector: [1.0, 1.1, 1.2] },
+        { text: ["unrelated", "doc"], vector: [1.3, 1.4, 1.5] },
+      ];
+      const table = await db.createTable("test", data);
+      await table.createIndex("text", {
+        config: Index.fts(),
+      });
+
+      // For the moment, we just confirm we can call prewarmIndex without error
+      // and still search it afterwards
+      await table.prewarmIndex("text_idx");
+
+      const results = await table.search("lance").toArray();
+      expect(results.length).toBe(3);
+    });
+
     test("full text index on list", async () => {
       const db = await connect(tmpDir.name);
       const data = [

nodejs/lancedb/table.ts

@@ -235,6 +235,17 @@ export abstract class Table {
    */
   abstract dropIndex(name: string): Promise<void>;
 
+  /**
+   * Prewarm an index in the table.
+   *
+   * @param name The name of the index.
+   *
+   * This will load the index into memory.  This may reduce the cold-start time for
+   * future queries.  If the index does not fit in the cache then this call may be
+   * wasteful.
+   */
+  abstract prewarmIndex(name: string): Promise<void>;
+
   /**
    * Create a {@link Query} Builder.
    *
@@ -565,6 +576,10 @@ export class LocalTable extends Table {
     await this.inner.dropIndex(name);
   }
 
+  async prewarmIndex(name: string): Promise<void> {
+    await this.inner.prewarmIndex(name);
+  }
+
   query(): Query {
     return new Query(this.inner);
   }

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"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": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"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": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"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": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"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": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"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": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"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": "0.19.0-beta.6",
+  "version": "0.19.0-beta.7",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.19.0-beta.6",
+	"version": "0.19.0-beta.7",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.19.0-beta.6",
+  "version": "0.19.0-beta.7",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.19.0-beta.6",
+      "version": "0.19.0-beta.7",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.19.0-beta.6",
+  "version": "0.19.0-beta.7",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/query.rs

@@ -327,6 +327,7 @@ impl JsFullTextQuery {
     }
 
     #[napi(factory)]
+    #[allow(clippy::use_self)] // NAPI doesn't allow Self here but clippy reports it
     pub fn boost_query(
         positive: &JsFullTextQuery,
         negative: &JsFullTextQuery,
@@ -349,11 +350,8 @@ impl JsFullTextQuery {
         boosts: Option<Vec<f64>>,
     ) -> napi::Result<Self> {
         let q = match boosts {
-            Some(boosts) => MultiMatchQuery::try_new_with_boosts(
+            Some(boosts) => MultiMatchQuery::try_new(query, columns)
-                query,
+                .and_then(|q| q.try_with_boosts(boosts.into_iter().map(|v| v as f32).collect())),
-                columns,
-                boosts.into_iter().map(|v| v as f32).collect(),
-            ),
             None => MultiMatchQuery::try_new(query, columns),
         }
         .map_err(|e| {

nodejs/src/table.rs

@@ -132,6 +132,14 @@ impl Table {
             .default_error()
     }
 
+    #[napi(catch_unwind)]
+    pub async fn prewarm_index(&self, index_name: String) -> napi::Result<()> {
+        self.inner_ref()?
+            .prewarm_index(&index_name)
+            .await
+            .default_error()
+    }
+
     #[napi(catch_unwind)]
     pub async fn update(
         &self,

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.0-beta.7"
+current_version = "0.22.0-beta.8"
 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 = "0.22.0-beta.7"
+version = "0.22.0-beta.8"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -44,7 +44,7 @@ repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
 pylance = [
-    "pylance>=0.23.2",
+    "pylance>=0.25",
 ]
 tests = [
     "aiohttp",
@@ -58,7 +58,7 @@ tests = [
     "polars>=0.19, <=1.3.0",
     "tantivy",
     "pyarrow-stubs",
-    "pylance>=0.23.2",
+    "pylance>=0.25",
     "requests",
 ]
 dev = [

python/python/lancedb/table.py

@@ -1745,8 +1745,32 @@ class LanceTable(Table):
         )
 
     def drop_index(self, name: str) -> None:
+        """
+        Drops an index from the table
+
+        Parameters
+        ----------
+        name: str
+            The name of the index to drop
+        """
         return LOOP.run(self._table.drop_index(name))
 
+    def prewarm_index(self, name: str) -> None:
+        """
+        Prewarms an index in the table
+
+        This loads the entire index into memory
+
+        If the index does not fit into the available cache this call
+        may be wasteful
+
+        Parameters
+        ----------
+        name: str
+            The name of the index to prewarm
+        """
+        return LOOP.run(self._table.prewarm_index(name))
+
     def create_scalar_index(
         self,
         column: str,
@@ -3002,6 +3026,23 @@ class AsyncTable:
         """
         await self._inner.drop_index(name)
 
+    async def prewarm_index(self, name: str) -> None:
+        """
+        Prewarm an index in the table.
+
+        Parameters
+        ----------
+        name: str
+            The name of the index to prewarm
+
+        Notes
+        -----
+        This will load the index into memory.  This may reduce the cold-start time for
+        future queries.  If the index does not fit in the cache then this call may be
+        wasteful.
+        """
+        await self._inner.prewarm_index(name)
+
     async def add(
         self,
         data: DATA,

python/python/tests/test_index.py

@@ -8,7 +8,7 @@ import pyarrow as pa
 import pytest
 import pytest_asyncio
 from lancedb import AsyncConnection, AsyncTable, connect_async
-from lancedb.index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq
+from lancedb.index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq, FTS
 
 
 @pytest_asyncio.fixture
@@ -119,6 +119,18 @@ async def test_create_label_list_index(some_table: AsyncTable):
     assert str(indices) == '[Index(LabelList, columns=["tags"], name="tags_idx")]'
 
 
+@pytest.mark.asyncio
+async def test_full_text_search_index(some_table: AsyncTable):
+    await some_table.create_index("tags", config=FTS(with_position=False))
+    indices = await some_table.list_indices()
+    assert str(indices) == '[Index(FTS, columns=["tags"], name="tags_idx")]'
+
+    await some_table.prewarm_index("tags_idx")
+
+    res = await (await some_table.search("tag0")).to_arrow()
+    assert res.num_rows > 0
+
+
 @pytest.mark.asyncio
 async def test_create_vector_index(some_table: AsyncTable):
     # Can create

python/src/table.rs

@@ -204,6 +204,14 @@ impl Table {
         })
     }
 
+    pub fn prewarm_index(self_: PyRef<'_, Self>, index_name: String) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.prewarm_index(&index_name).await.infer_error()?;
+            Ok(())
+        })
+    }
+
     pub fn list_indices(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {

python/src/util.rs

@@ -163,8 +163,9 @@ pub fn parse_fts_query(query: &Bound<'_, PyDict>) -> PyResult<FtsQuery> {
                 .ok_or(PyValueError::new_err("boost not found"))?
                 .extract::<Vec<f32>>()?;
 
-            let query =
+            let query = MultiMatchQuery::try_new(query, columns)
-                MultiMatchQuery::try_new_with_boosts(query, columns, boost).map_err(|e| {
+                .and_then(|q| q.try_with_boosts(boost))
+                .map_err(|e| {
                     PyValueError::new_err(format!("Error creating MultiMatchQuery: {}", e))
                 })?;
             Ok(query.into())

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.19.0-beta.6"
+version = "0.19.0-beta.7"
 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 = "0.19.0-beta.6"
+version = "0.19.0-beta.7"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/remote/table.rs

@@ -1003,6 +1003,12 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         Ok(())
     }
 
+    async fn prewarm_index(&self, _index_name: &str) -> Result<()> {
+        Err(Error::NotSupported {
+            message: "prewarm_index is not yet supported on LanceDB cloud.".into(),
+        })
+    }
+
     async fn table_definition(&self) -> Result<TableDefinition> {
         Err(Error::NotSupported {
             message: "table_definition is not supported on LanceDB cloud.".into(),
@@ -1769,6 +1775,7 @@ mod tests {
                                 "boost": 1.0,
                                 "fuzziness": 0,
                                 "max_expansions": 50,
+                                "operator": "Or",
                             },
                         }
                     },

rust/lancedb/src/table.rs

@@ -455,6 +455,8 @@ pub trait BaseTable: std::fmt::Display + std::fmt::Debug + Send + Sync {
     async fn list_indices(&self) -> Result<Vec<IndexConfig>>;
     /// Drop an index from the table.
     async fn drop_index(&self, name: &str) -> Result<()>;
+    /// Prewarm an index in the table
+    async fn prewarm_index(&self, name: &str) -> Result<()>;
     /// Get statistics about the index.
     async fn index_stats(&self, index_name: &str) -> Result<Option<IndexStatistics>>;
     /// Merge insert new records into the table.
@@ -1086,6 +1088,22 @@ impl Table {
         self.inner.drop_index(name).await
     }
 
+    /// Prewarm an index in the table
+    ///
+    /// This is a hint to fully load the index into memory.  It can be used to
+    /// avoid cold starts
+    ///
+    /// It is generally wasteful to call this if the index does not fit into the
+    /// available cache.
+    ///
+    /// Note: This function is not yet supported on all indices, in which case it
+    /// may do nothing.
+    ///
+    /// Use [`Self::list_indices()`] to find the names of the indices.
+    pub async fn prewarm_index(&self, name: &str) -> Result<()> {
+        self.inner.prewarm_index(name).await
+    }
+
     // Take many execution plans and map them into a single plan that adds
     // a query_index column and unions them.
     pub(crate) fn multi_vector_plan(
@@ -2006,6 +2024,11 @@ impl BaseTable for NativeTable {
         Ok(())
     }
 
+    async fn prewarm_index(&self, index_name: &str) -> Result<()> {
+        let dataset = self.dataset.get().await?;
+        Ok(dataset.prewarm_index(index_name).await?)
+    }
+
     async fn update(&self, update: UpdateBuilder) -> Result<u64> {
         let dataset = self.dataset.get().await?.clone();
         let mut builder = LanceUpdateBuilder::new(Arc::new(dataset));
@@ -3455,6 +3478,9 @@ mod tests {
         assert_eq!(stats.num_unindexed_rows, 0);
         assert_eq!(stats.index_type, crate::index::IndexType::FTS);
         assert_eq!(stats.distance_type, None);
+
+        // Make sure we can call prewarm without error
+        table.prewarm_index("text_idx").await.unwrap();
     }
 
     #[tokio::test]
@@ -3550,7 +3576,7 @@ mod tests {
         let native_tbl = table.as_native().unwrap();
 
         let manifest = native_tbl.manifest().await.unwrap();
-        assert_eq!(manifest.config.len(), 0);
+        let base_config_len = manifest.config.len();
 
         native_tbl
             .update_config(vec![("test_key1".to_string(), "test_val1".to_string())])
@@ -3558,7 +3584,7 @@ mod tests {
             .unwrap();
 
         let manifest = native_tbl.manifest().await.unwrap();
-        assert_eq!(manifest.config.len(), 1);
+        assert_eq!(manifest.config.len(), 1 + base_config_len);
         assert_eq!(
             manifest.config.get("test_key1"),
             Some(&"test_val1".to_string())
@@ -3569,7 +3595,7 @@ mod tests {
             .await
             .unwrap();
         let manifest = native_tbl.manifest().await.unwrap();
-        assert_eq!(manifest.config.len(), 2);
+        assert_eq!(manifest.config.len(), 2 + base_config_len);
         assert_eq!(
             manifest.config.get("test_key1"),
             Some(&"test_val1".to_string())
@@ -3587,7 +3613,7 @@ mod tests {
             .await
             .unwrap();
         let manifest = native_tbl.manifest().await.unwrap();
-        assert_eq!(manifest.config.len(), 2);
+        assert_eq!(manifest.config.len(), 2 + base_config_len);
         assert_eq!(
             manifest.config.get("test_key1"),
             Some(&"test_val1".to_string())
@@ -3599,7 +3625,7 @@ mod tests {
 
         native_tbl.delete_config_keys(&["test_key1"]).await.unwrap();
         let manifest = native_tbl.manifest().await.unwrap();
-        assert_eq!(manifest.config.len(), 1);
+        assert_eq!(manifest.config.len(), 1 + base_config_len);
         assert_eq!(
             manifest.config.get("test_key2"),
             Some(&"test_val2_update".to_string())