Bump version: 0.20.1-beta.1 → 0.20.1-beta.2

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

## Summary by CodeRabbit

- **Chores**
- Updated the release workflow to explicitly check out the main branch
during the publishing process.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.20.1-beta.0"
+current_version = "0.20.1-beta.2"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/npm-publish.yml

@@ -541,6 +541,8 @@ jobs:
         run: npm deprecate vectordb "Use @lancedb/lancedb instead."
       - name: Checkout
         uses: actions/checkout@v4
+        with:
+          ref: main
       - name: Update package-lock.json
         run: |
           git config user.name 'Lance Release'

Cargo.toml

@@ -21,14 +21,14 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.29.1", "features" = ["dynamodb"], tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance = { "version" = "=0.30.0", "features" = ["dynamodb"], tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-io = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-io = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-index = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-index = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-linalg = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-linalg = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-table = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-table = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-testing = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-testing = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-datafusion = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-datafusion = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
-lance-encoding = { version = "=0.29.1", tag = "v0.29.1-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-encoding = { version = "=0.30.0", tag = "v0.30.0-beta.1", git="https://github.com/lancedb/lance.git" }
 # Note that this one does not include pyarrow
 arrow = { version = "55.1", optional = false }
 arrow-array = "55.1"

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.20.1-beta.0</version>
+        <version>0.20.1-beta.2</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.20.1-beta.0</version>
+    <version>0.20.1-beta.2</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.20.1-beta.0",
+  "version": "0.20.1-beta.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.20.1-beta.0",
+        "@lancedb/vectordb-darwin-arm64": "0.20.1-beta.1",
-        "@lancedb/vectordb-darwin-x64": "0.20.1-beta.0",
+        "@lancedb/vectordb-darwin-x64": "0.20.1-beta.1",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.20.1-beta.0",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.20.1-beta.1",
-        "@lancedb/vectordb-linux-x64-gnu": "0.20.1-beta.0",
+        "@lancedb/vectordb-linux-x64-gnu": "0.20.1-beta.1",
-        "@lancedb/vectordb-win32-x64-msvc": "0.20.1-beta.0"
+        "@lancedb/vectordb-win32-x64-msvc": "0.20.1-beta.1"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -327,9 +327,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.20.1-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.20.1-beta.1.tgz",
-      "integrity": "sha512-EZl1nvF/2MbLkB8DkNPg+9SpYWpqnNR9kY5a1JWtNWQWw735oT2VPnH3B2htDKU42gJ/9DJGBdEvIJwzeHT85w==",
+      "integrity": "sha512-DPD8gwFQz5aENYYbTFS/l3YX/rqzS6Kj2B4IZERccVFULQsdR5YwtaAfFwTMp7NSnsjWKwJAknohiMZlJr4njQ==",
       "cpu": [
         "arm64"
       ],
@@ -339,9 +339,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.20.1-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.20.1-beta.1.tgz",
-      "integrity": "sha512-1ZkMcsXsysLRohAeHGpbytVHUp4yEU89A34rrh48vcQUNvYtqxbAw+TLjAbN0vvNvOZOI4DRllxSL1O+Dbybbg==",
+      "integrity": "sha512-lTPtlRSTC08UgQW5Bv8WYhdbogAgUJ+9ejg+UE+fwP9gEsgEKXL/SHBm+9gmAlTo7LbrxJjg0CtCde/mW68UTw==",
       "cpu": [
         "x64"
       ],
@@ -351,9 +351,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.20.1-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.20.1-beta.1.tgz",
-      "integrity": "sha512-CxjSGaLJNRYxljdrC8MSirnHu73jctv3S3Q90CbsWMsij9za87zvnrjoiRIn7kv7UNS4ArwS9yyH6gNorCBf6Q==",
+      "integrity": "sha512-w/3O9FvwQiGegYsM21yZ0FezfOFVsW7HttYwwPzZMZaCpK3/i+LvZVSqwO4qXHHJBtHgKevonINyvVlg5487aQ==",
       "cpu": [
         "arm64"
       ],
@@ -363,9 +363,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.20.1-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.20.1-beta.1.tgz",
-      "integrity": "sha512-WI2XWYYO5ygL0Az7SlX98VpNqrz8hKuTK/xC/PoM99s1xnfcCukM28DaDGZJpXOGnLbVnexcO2RW4daJ2xDPaQ==",
+      "integrity": "sha512-rq7Q6Lq9kJmBcgwplYQVJmRbyeP+xPVmXyyQfAO3IjekqeSsyjj1HoCZYqZIfBZyN5ELiSvIJB0731aKf9pr1A==",
       "cpu": [
         "x64"
       ],
@@ -375,9 +375,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.20.1-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.20.1-beta.1.tgz",
-      "integrity": "sha512-Mxd7V3Y8whEBoQFQZhZGFQi0avq8ujHRI2c0LhjhYTdwGylrBS3bfGD+/nbDGhAjp7dp5U8P4kiBi30QNwoedA==",
+      "integrity": "sha512-kHra0SEXeMKdgqi5h0igsqHcBr73hKBhEVJBa8VTv1DUv6Jvazwl4B4ueqllcyD4k3vvOTb2XzZomm7dhQ9QnA==",
       "cpu": [
         "x64"
       ],

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.20.1-beta.0",
+  "version": "0.20.1-beta.2",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -89,10 +89,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.20.1-beta.0",
+    "@lancedb/vectordb-darwin-x64": "0.20.1-beta.2",
-    "@lancedb/vectordb-darwin-arm64": "0.20.1-beta.0",
+    "@lancedb/vectordb-darwin-arm64": "0.20.1-beta.2",
-    "@lancedb/vectordb-linux-x64-gnu": "0.20.1-beta.0",
+    "@lancedb/vectordb-linux-x64-gnu": "0.20.1-beta.2",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.20.1-beta.0",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.20.1-beta.2",
-    "@lancedb/vectordb-win32-x64-msvc": "0.20.1-beta.0"
+    "@lancedb/vectordb-win32-x64-msvc": "0.20.1-beta.2"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.20.1-beta.0"
+version = "0.20.1-beta.2"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/__test__/arrow.test.ts

@@ -592,14 +592,14 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         ).rejects.toThrow("column vector was missing");
       });
 
-      it("will provide a nice error if run twice", async function () {
+      it("will skip embedding application if already applied", async function () {
         const records = sampleRecords();
         const table = await convertToTable(records, dummyEmbeddingConfig);
 
         // fromTableToBuffer will try and apply the embeddings again
-        await expect(
+        // but should skip since the column already has non-null values
-          fromTableToBuffer(table, dummyEmbeddingConfig),
+        const result = await fromTableToBuffer(table, dummyEmbeddingConfig);
-        ).rejects.toThrow("already existed");
+        expect(result.byteLength).toBeGreaterThan(0);
       });
     });
 

nodejs/lancedb/arrow.ts

@@ -417,7 +417,9 @@ function inferSchema(
         } else {
           const inferredType = inferType(value, path, opts);
           if (inferredType === undefined) {
-            throw new Error(`Failed to infer data type for field ${path.join(".")} at row ${rowI}. \
+            throw new Error(`Failed to infer data type for field ${path.join(
+              ".",
+            )} at row ${rowI}. \
                              Consider providing an explicit schema.`);
           }
           pathTree.set(path, inferredType);
@@ -799,11 +801,17 @@ async function applyEmbeddingsFromMetadata(
         `Cannot apply embedding function because the source column '${functionEntry.sourceColumn}' was not present in the data`,
       );
     }
+
+    // Check if destination column exists and handle accordingly
     if (columns[destColumn] !== undefined) {
-      throw new Error(
+      const existingColumn = columns[destColumn];
-        `Attempt to apply embeddings to table failed because column ${destColumn} already existed`,
+      // If the column exists but is all null, we can fill it with embeddings
-      );
+      if (existingColumn.nullCount !== existingColumn.length) {
+        // Column has non-null values, skip embedding application
+        continue;
+      }
     }
+
     if (table.batches.length > 1) {
       throw new Error(
         "Internal error: `makeArrowTable` unexpectedly created a table with more than one batch",
@@ -903,11 +911,23 @@ async function applyEmbeddings<T>(
       );
     }
   } else {
+    // Check if destination column exists and handle accordingly
     if (Object.prototype.hasOwnProperty.call(newColumns, destColumn)) {
-      throw new Error(
+      const existingColumn = newColumns[destColumn];
-        `Attempt to apply embeddings to table failed because column ${destColumn} already existed`,
+      // If the column exists but is all null, we can fill it with embeddings
-      );
+      if (existingColumn.nullCount !== existingColumn.length) {
+        // Column has non-null values, skip embedding application and return table as-is
+        let newTable = new ArrowTable(newColumns);
+        if (schema != null) {
+          newTable = alignTable(newTable, schema as Schema);
+        }
+        return new ArrowTable(
+          new Schema(newTable.schema.fields, schemaMetadata),
+          newTable.batches,
+        );
+      }
     }
+
     if (table.batches.length > 1) {
       throw new Error(
         "Internal error: `makeArrowTable` unexpectedly created a table with more than one batch",

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.20.1-beta.0",
+	"version": "0.20.1-beta.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": "0.20.1-beta.0",
+	"version": "0.20.1-beta.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": "0.20.1-beta.0",
+	"version": "0.20.1-beta.2",
 	"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": "0.20.1-beta.0",
+	"version": "0.20.1-beta.2",
 	"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": "0.20.1-beta.0",
+	"version": "0.20.1-beta.2",
 	"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": "0.20.1-beta.0",
+	"version": "0.20.1-beta.2",
 	"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": "0.20.1-beta.0",
+  "version": "0.20.1-beta.2",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.20.1-beta.0",
+	"version": "0.20.1-beta.2",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.20.1-beta.0",
+  "version": "0.20.1-beta.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.20.1-beta.0",
+      "version": "0.20.1-beta.1",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.20.1-beta.0",
+  "version": "0.20.1-beta.2",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.23.1-beta.1"
+current_version = "0.23.1-beta.2"
 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 = "0.23.1-beta.1"
+version = "0.23.1-beta.2"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.20.1-beta.0"
+version = "0.20.1-beta.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 = "0.20.1-beta.0"
+version = "0.20.1-beta.2"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true