Bump version: 0.25.2-beta.1 → 0.25.2-beta.2

Example failure:
https://github.com/lancedb/lancedb/actions/runs/18237024283/job/51932651993

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.2-beta.0"
+current_version = "0.22.2-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/actions/create-failure-issue/action.yml

@@ -0,0 +1,45 @@
+name: Create Failure Issue
+description: Creates a GitHub issue if any jobs in the workflow failed
+
+inputs:
+  job-results:
+    description: 'JSON string of job results from needs context'
+    required: true
+  workflow-name:
+    description: 'Name of the workflow'
+    required: true
+
+runs:
+  using: composite
+  steps:
+    - name: Check for failures and create issue
+      shell: bash
+      env:
+        JOB_RESULTS: ${{ inputs.job-results }}
+        WORKFLOW_NAME: ${{ inputs.workflow-name }}
+        RUN_URL: ${{ github.server_url }}/${{ github.repository }}/actions/runs/${{ github.run_id }}
+        GH_TOKEN: ${{ github.token }}
+      run: |
+        # Check if any job failed
+        if echo "$JOB_RESULTS" | jq -e 'to_entries | any(.value.result == "failure")' > /dev/null; then
+          echo "Detected job failures, creating issue..."
+
+          # Extract failed job names
+          FAILED_JOBS=$(echo "$JOB_RESULTS" | jq -r 'to_entries | map(select(.value.result == "failure")) | map(.key) | join(", ")')
+
+          # Create issue with workflow name, failed jobs, and run URL
+          gh issue create \
+            --title "$WORKFLOW_NAME Failed ($FAILED_JOBS)" \
+            --body "The workflow **$WORKFLOW_NAME** failed during execution.
+
+        **Failed jobs:** $FAILED_JOBS
+
+        **Run URL:** $RUN_URL
+
+        Please investigate the failed jobs and address any issues." \
+            --label "ci"
+
+          echo "Issue created successfully"
+        else
+          echo "No job failures detected, skipping issue creation"
+        fi

.github/workflows/cargo-publish.yml

@@ -38,3 +38,17 @@ jobs:
       - name: Publish the package
         run: |
           cargo publish -p lancedb --all-features --token ${{ steps.auth.outputs.token }}
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [build]
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/docs.yml

@@ -58,7 +58,7 @@ jobs:
           cache: 'npm'
           cache-dependency-path: docs/package-lock.json
       - name: Install node dependencies
-        working-directory: node
+        working-directory: nodejs
         run: |
           sudo apt update
           sudo apt install -y protobuf-compiler libssl-dev

.github/workflows/java-publish.yml

@@ -43,7 +43,6 @@ jobs:
       - uses: Swatinem/rust-cache@v2
       - uses: actions-rust-lang/setup-rust-toolchain@v1
         with:
-          toolchain: "1.81.0"
           cache-workspaces: "./java/core/lancedb-jni"
           # Disable full debug symbol generation to speed up CI build and keep memory down
           # "1" means line tables only, which is useful for panic tracebacks.
@@ -112,3 +111,17 @@ jobs:
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [linux-arm64, linux-x86, macos-arm64]
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/nodejs.yml

@@ -6,6 +6,7 @@ on:
       - main
   pull_request:
     paths:
+      - Cargo.toml
       - nodejs/**
       - .github/workflows/nodejs.yml
       - docker-compose.yml

.github/workflows/npm-publish.yml

@@ -365,3 +365,17 @@ jobs:
             ARGS="$ARGS --tag preview"
           fi
           npm publish $ARGS
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [build-lancedb, test-lancedb, publish]
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    permissions:
+      contents: read
+      issues: write
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/pypi-publish.yml

@@ -173,3 +173,17 @@ jobs:
           generate_release_notes: false
           name: Python LanceDB v${{ steps.extract_version.outputs.version }}
           body: ${{ steps.python_release_notes.outputs.changelog }}
+  report-failure:
+    name: Report Workflow Failure
+    runs-on: ubuntu-latest
+    needs: [linux, mac, windows]
+    permissions:
+      contents: read
+      issues: write
+    if: always() && (github.event_name == 'release' || github.event_name == 'workflow_dispatch')
+    steps:
+      - uses: actions/checkout@v4
+      - uses: ./.github/actions/create-failure-issue
+        with:
+          job-results: ${{ toJSON(needs) }}
+          workflow-name: ${{ github.workflow }}

.github/workflows/python.yml

@@ -6,6 +6,7 @@ on:
       - main
   pull_request:
     paths:
+      - Cargo.toml
       - python/**
       - .github/workflows/python.yml
 

.github/workflows/rust.yml

@@ -125,6 +125,9 @@ jobs:
       - name: Run examples
         run: cargo run --example simple --locked
       - name: Run remote tests
+        # Running this requires access to secrets, so skip if this is
+        # a PR from a fork.
+        if: github.event_name != 'pull_request' || !github.event.pull_request.head.repo.fork
         run: make -C ./lancedb remote-tests
 
   macos:

Cargo.toml

@@ -15,15 +15,15 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.37.0", default-features = false, "features" = ["dynamodb"], "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-io = { "version" = "=0.37.0", default-features = false, "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-index = { "version" = "=0.37.0", "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-linalg = { "version" = "=0.37.0", "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-table = { "version" = "=0.37.0", "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-testing = { "version" = "=0.37.0", "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-datafusion = { "version" = "=0.37.0", "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-encoding = { "version" = "=0.37.0", "tag" = "v0.37.1-beta.1", "git" = "https://github.com/lancedb/lance.git" }
-lance-namespace = "0.0.15"
+lance = { "version" = "=0.38.0", default-features = false, "features" = ["dynamodb"] }
+lance-io = { "version" = "=0.38.0", default-features = false }
+lance-index = "=0.38.0"
+lance-linalg = "=0.38.0"
+lance-table = "=0.38.0"
+lance-testing = "=0.38.0"
+lance-datafusion = "=0.38.0"
+lance-encoding = "=0.38.0"
+lance-namespace = "0.0.16"
 # Note that this one does not include pyarrow
 arrow = { version = "55.1", optional = false }
 arrow-array = "55.1"
@@ -31,7 +31,6 @@ arrow-data = "55.1"
 arrow-ipc = "55.1"
 arrow-ord = "55.1"
 arrow-schema = "55.1"
-arrow-arith = "55.1"
 arrow-cast = "55.1"
 async-trait = "0"
 datafusion = { version = "49.0", default-features = false }
@@ -52,7 +51,6 @@ pin-project = "1.0.7"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-rand = "0.9"
 regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
@@ -60,7 +58,17 @@ crunchy = "0.2.4"
 # Temporary pins to work around downstream issues
 # https://github.com/apache/arrow-rs/commit/2fddf85afcd20110ce783ed5b4cdeb82293da30b
 chrono = "=0.4.41"
-# https://github.com/RustCrypto/formats/issues/1684
-base64ct = "=1.6.0"
 # Workaround for: https://github.com/Lokathor/bytemuck/issues/306
 bytemuck_derive = ">=1.8.1, <1.9.0"
+
+# This is only needed when we reference preview releases of lance
+# [patch.crates-io]
+# # Force to use the same lance version as the rest of the project to avoid duplicate dependencies
+# lance = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-io = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-index = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-linalg = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-table = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-testing = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-datafusion = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }
+# lance-encoding = { "version" = "=0.38.0", "tag" = "v0.38.0", "git" = "https://github.com/lancedb/lance.git" }

ci/run_with_test_connection.sh

@@ -16,29 +16,46 @@ check_command_exists() {
 }
 
 if [[ ! -e ./lancedb ]]; then
-    ARCH="x64"
-    if [[ $OSTYPE == 'darwin'* ]]; then
-        UNAME=$(uname -m)
-        if [[ $UNAME == 'arm64' ]]; then
-            ARCH='arm64'
-        fi
-        OSTYPE="macos"
-    elif [[ $OSTYPE == 'linux'* ]]; then
-        if [[ $UNAME == 'aarch64' ]]; then
-            ARCH='arm64'
-        fi
-        OSTYPE="linux"
+    if [[ -v SOPHON_READ_TOKEN ]]; then
+        INPUT="lancedb-linux-x64"
+        gh release \
+            --repo lancedb/lancedb \
+            download ci-support-binaries \
+            --pattern "${INPUT}" \
+            || die "failed to fetch cli."
+        check_command_exists openssl
+        openssl enc -aes-256-cbc \
+            -d -pbkdf2 \
+            -pass "env:SOPHON_READ_TOKEN" \
+            -in "${INPUT}" \
+            -out ./lancedb-linux-x64.tar.gz \
+            || die "openssl failed"
+        TARGET="${INPUT}.tar.gz"
     else
-        die "unknown OSTYPE: $OSTYPE"
-    fi
+        ARCH="x64"
+        if [[ $OSTYPE == 'darwin'* ]]; then
+            UNAME=$(uname -m)
+            if [[ $UNAME == 'arm64' ]]; then
+                ARCH='arm64'
+            fi
+            OSTYPE="macos"
+        elif [[ $OSTYPE == 'linux'* ]]; then
+            if [[ $UNAME == 'aarch64' ]]; then
+                ARCH='arm64'
+            fi
+            OSTYPE="linux"
+        else
+            die "unknown OSTYPE: $OSTYPE"
+        fi
 
-    check_command_exists gh
-    TARGET="lancedb-${OSTYPE}-${ARCH}.tar.gz"
-    gh release \
-        --repo lancedb/sophon \
-        download lancedb-cli-v0.0.3 \
-        --pattern "${TARGET}" \
-        || die "failed to fetch cli."
+        check_command_exists gh
+        TARGET="lancedb-${OSTYPE}-${ARCH}.tar.gz"
+        gh release \
+            --repo lancedb/sophon \
+            download lancedb-cli-v0.0.3 \
+            --pattern "${TARGET}" \
+            || die "failed to fetch cli."
+    fi
 
     check_command_exists tar
     tar xvf "${TARGET}" || die "tar failed."

ci/set_lance_version.py

@@ -117,7 +117,7 @@ def update_cargo_toml(line_updater):
     lance_line = ""
     is_parsing_lance_line = False
     for line in lines:
-        if line.startswith("lance"):
+        if line.startswith("lance") and not line.startswith("lance-namespace"):
             # Check if this is a single-line or multi-line entry
             # Single-line entries either:
             # 1. End with } (complete inline table)

docs/src/js/classes/MergeInsertBuilder.md

@@ -52,6 +52,30 @@ the merge result
 
 ***
 
+### useIndex()
+
+```ts
+useIndex(useIndex): MergeInsertBuilder
+```
+
+Controls whether to use indexes for the merge operation.
+
+When set to `true` (the default), the operation will use an index if available
+on the join key for improved performance. When set to `false`, it forces a full
+table scan even if an index exists. This can be useful for benchmarking or when
+the query optimizer chooses a suboptimal path.
+
+#### Parameters
+
+* **useIndex**: `boolean`
+    Whether to use indices for the merge operation. Defaults to `true`.
+
+#### Returns
+
+[`MergeInsertBuilder`](MergeInsertBuilder.md)
+
+***
+
 ### whenMatchedUpdateAll()
 
 ```ts

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.2-beta.0</version>
+        <version>0.22.2-beta.1</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/lance-namespace/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.2-beta.0</version>
+        <version>0.22.2-beta.1</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.22.2-beta.0</version>
+    <version>0.22.2-beta.1</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.22.2-beta.0"
+version = "0.22.2-beta.1"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/__test__/table.test.ts

@@ -211,8 +211,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       },
     );
 
-    // TODO: https://github.com/lancedb/lancedb/issues/1832
-    it.skip("should be able to omit nullable fields", async () => {
+    it("should be able to omit nullable fields", async () => {
       const db = await connect(tmpDir.name);
       const schema = new arrow.Schema([
         new arrow.Field(
@@ -236,23 +235,36 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await table.add([data3]);
 
       let res = await table.query().limit(10).toArray();
-      const resVector = res.map((r) => r.get("vector").toArray());
+      const resVector = res.map((r) =>
+        r.vector ? Array.from(r.vector) : null,
+      );
       expect(resVector).toEqual([null, data2.vector, data3.vector]);
-      const resItem = res.map((r) => r.get("item").toArray());
+      const resItem = res.map((r) => r.item);
       expect(resItem).toEqual(["foo", null, "bar"]);
-      const resPrice = res.map((r) => r.get("price").toArray());
+      const resPrice = res.map((r) => r.price);
       expect(resPrice).toEqual([10.0, 2.0, 3.0]);
 
       const data4 = { item: "foo" };
       // We can't omit a column if it's not nullable
-      await expect(table.add([data4])).rejects.toThrow("Invalid user input");
+      await expect(table.add([data4])).rejects.toThrow(
+        "Append with different schema",
+      );
 
       // But we can alter columns to make them nullable
       await table.alterColumns([{ path: "price", nullable: true }]);
       await table.add([data4]);
 
-      res = (await table.query().limit(10).toArray()).map((r) => r.toJSON());
-      expect(res).toEqual([data1, data2, data3, data4]);
+      res = (await table.query().limit(10).toArray()).map((r) => ({
+        ...r.toJSON(),
+        vector: r.vector ? Array.from(r.vector) : null,
+      }));
+      // Rust fills missing nullable fields with null
+      expect(res).toEqual([
+        { ...data1, vector: null },
+        { ...data2, item: null },
+        data3,
+        { ...data4, price: null, vector: null },
+      ]);
     });
 
     it("should be able to insert nullable data for non-nullable fields", async () => {
@@ -330,6 +342,43 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       const table = await db.createTable("my_table", data);
       expect(await table.countRows()).toEqual(2);
     });
+
+    it("should allow undefined and omitted nullable vector fields", async () => {
+      // Test for the bug: can't pass undefined or omit vector column
+      const db = await connect("memory://");
+      const schema = new arrow.Schema([
+        new arrow.Field("id", new arrow.Int32(), true),
+        new arrow.Field(
+          "vector",
+          new arrow.FixedSizeList(
+            32,
+            new arrow.Field("item", new arrow.Float32(), true),
+          ),
+          true, // nullable = true
+        ),
+      ]);
+      const table = await db.createEmptyTable("test_table", schema);
+
+      // Should not throw error for undefined value
+      await table.add([{ id: 0, vector: undefined }]);
+
+      // Should not throw error for omitted field
+      await table.add([{ id: 1 }]);
+
+      // Should still work for null
+      await table.add([{ id: 2, vector: null }]);
+
+      // Should still work for actual vector
+      const testVector = new Array(32).fill(0.5);
+      await table.add([{ id: 3, vector: testVector }]);
+      expect(await table.countRows()).toEqual(4);
+
+      const res = await table.query().limit(10).toArray();
+      const resVector = res.map((r) =>
+        r.vector ? Array.from(r.vector) : null,
+      );
+      expect(resVector).toEqual([null, null, null, testVector]);
+    });
   },
 );
 
@@ -1454,7 +1503,9 @@ describe("when optimizing a dataset", () => {
 
   it("delete unverified", async () => {
     const version = await table.version();
-    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${version - 1}.manifest`;
+    const versionFile = `${tmpDir.name}/${table.name}.lance/_versions/${
+      version - 1
+    }.manifest`;
     fs.rmSync(versionFile);
 
     let stats = await table.optimize({ deleteUnverified: false });

nodejs/lancedb/arrow.ts

@@ -1285,19 +1285,36 @@ function validateSchemaEmbeddings(
     if (isFixedSizeList(field.type)) {
       field = sanitizeField(field);
       if (data.length !== 0 && data?.[0]?.[field.name] === undefined) {
+        // Check if there's an embedding function registered for this field
+        let hasEmbeddingFunction = false;
+
+        // Check schema metadata for embedding functions
         if (schema.metadata.has("embedding_functions")) {
           const embeddings = JSON.parse(
             schema.metadata.get("embedding_functions")!,
           );
-          if (
-            // biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
-            embeddings.find((f: any) => f["vectorColumn"] === field.name) ===
-            undefined
-          ) {
+          // biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
+          if (embeddings.find((f: any) => f["vectorColumn"] === field.name)) {
+            hasEmbeddingFunction = true;
+          }
+        }
+
+        // Check passed embedding function parameter
+        if (embeddings && embeddings.vectorColumn === field.name) {
+          hasEmbeddingFunction = true;
+        }
+
+        // If the field is nullable AND there's no embedding function, allow undefined/omitted values
+        if (field.nullable && !hasEmbeddingFunction) {
+          fields.push(field);
+        } else {
+          // Either not nullable OR has embedding function - require explicit values
+          if (hasEmbeddingFunction) {
+            // Don't add to missingEmbeddingFields since this is expected to be filled by embedding function
+            fields.push(field);
+          } else {
             missingEmbeddingFields.push(field);
           }
-        } else {
-          missingEmbeddingFields.push(field);
         }
       } else {
         fields.push(field);

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"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": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"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": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"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": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"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": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"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": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"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": "0.22.2-beta.0",
+  "version": "0.22.2-beta.1",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.22.2-beta.0",
+	"version": "0.22.2-beta.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.22.2-beta.0",
+  "version": "0.22.2-beta.1",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.22.2-beta.0",
+      "version": "0.22.2-beta.1",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.22.2-beta.0",
+  "version": "0.22.2-beta.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.25.2-beta.0"
+current_version = "0.25.2-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 = "0.25.2-beta.0"
+version = "0.25.2-beta.2"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -10,7 +10,7 @@ dependencies = [
     "pyarrow>=16",
     "pydantic>=1.10",
     "tqdm>=4.27.0",
-    "lance-namespace==0.0.6"
+    "lance-namespace>=0.0.16"
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.22.2-beta.0"
+version = "0.22.2-beta.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/data/inspect.rs

@@ -52,13 +52,13 @@ pub fn infer_vector_columns(
     for field in reader.schema().fields() {
         match field.data_type() {
             DataType::FixedSizeList(sub_field, _) if sub_field.data_type().is_floating() => {
-                columns.push(field.name().to_string());
+                columns.push(field.name().clone());
             }
             DataType::List(sub_field) if sub_field.data_type().is_floating() && !strict => {
-                columns_to_infer.insert(field.name().to_string(), None);
+                columns_to_infer.insert(field.name().clone(), None);
             }
             DataType::LargeList(sub_field) if sub_field.data_type().is_floating() && !strict => {
-                columns_to_infer.insert(field.name().to_string(), None);
+                columns_to_infer.insert(field.name().clone(), None);
             }
             _ => {}
         }

rust/lancedb/src/database/listing.rs

@@ -718,9 +718,9 @@ impl Database for ListingDatabase {
             .map_err(|e| Error::Lance { source: e })?;
 
         let version_ref = match (request.source_version, request.source_tag) {
-            (Some(v), None) => Ok(Ref::Version(v)),
+            (Some(v), None) => Ok(Ref::Version(None, Some(v))),
             (None, Some(tag)) => Ok(Ref::Tag(tag)),
-            (None, None) => Ok(Ref::Version(source_dataset.version().version)),
+            (None, None) => Ok(Ref::Version(None, Some(source_dataset.version().version))),
             _ => Err(Error::InvalidInput {
                 message: "Cannot specify both source_version and source_tag".to_string(),
             }),

rust/lancedb/src/remote/db.rs

@@ -647,7 +647,7 @@ impl From<StorageOptions> for RemoteOptions {
         let mut filtered = HashMap::new();
         for opt in supported_opts {
             if let Some(v) = options.0.get(opt) {
-                filtered.insert(opt.to_string(), v.to_string());
+                filtered.insert(opt.to_string(), v.clone());
             }
         }
         Self::new(filtered)

rust/lancedb/src/table.rs

@@ -1383,30 +1383,35 @@ impl Table {
 }
 
 pub struct NativeTags {
-    inner: LanceTags,
+    dataset: dataset::DatasetConsistencyWrapper,
 }
 #[async_trait]
 impl Tags for NativeTags {
     async fn list(&self) -> Result<HashMap<String, TagContents>> {
-        Ok(self.inner.list().await?)
+        let dataset = self.dataset.get().await?;
+        Ok(dataset.tags().list().await?)
     }
 
     async fn get_version(&self, tag: &str) -> Result<u64> {
-        Ok(self.inner.get_version(tag).await?)
+        let dataset = self.dataset.get().await?;
+        Ok(dataset.tags().get_version(tag).await?)
     }
 
     async fn create(&mut self, tag: &str, version: u64) -> Result<()> {
-        self.inner.create(tag, version).await?;
+        let dataset = self.dataset.get().await?;
+        dataset.tags().create(tag, version).await?;
         Ok(())
     }
 
     async fn delete(&mut self, tag: &str) -> Result<()> {
-        self.inner.delete(tag).await?;
+        let dataset = self.dataset.get().await?;
+        dataset.tags().delete(tag).await?;
         Ok(())
     }
 
     async fn update(&mut self, tag: &str, version: u64) -> Result<()> {
-        self.inner.update(tag, version).await?;
+        let dataset = self.dataset.get().await?;
+        dataset.tags().update(tag, version).await?;
         Ok(())
     }
 }
@@ -1780,13 +1785,13 @@ impl NativeTable {
                         BuiltinIndexType::BTree,
                     )))
                 } else {
-                    return Err(Error::InvalidInput {
+                    Err(Error::InvalidInput {
                         message: format!(
                             "there are no indices supported for the field `{}` with the data type {}",
                             field.name(),
                             field.data_type()
                         ),
-                    });
+                    })?
                 }
             }
             Index::BTree(_) => {
@@ -2440,10 +2445,8 @@ impl BaseTable for NativeTable {
     }
 
     async fn tags(&self) -> Result<Box<dyn Tags + '_>> {
-        let dataset = self.dataset.get().await?;
-
         Ok(Box::new(NativeTags {
-            inner: dataset.tags.clone(),
+            dataset: self.dataset.clone(),
         }))
     }
 

rust/lancedb/src/table/datafusion.rs

@@ -172,7 +172,7 @@ impl TableProvider for BaseTableAdapter {
         if let Some(projection) = projection {
             let field_names = projection
                 .iter()
-                .map(|i| self.schema.field(*i).name().to_string())
+                .map(|i| self.schema.field(*i).name().clone())
                 .collect();
             query.select = Select::Columns(field_names);
         }

rust/lancedb/src/table/dataset.rs

@@ -98,8 +98,9 @@ impl DatasetRef {
             }
             Self::TimeTravel { dataset, version } => {
                 let should_checkout = match &target_ref {
-                    refs::Ref::Version(target_ver) => version != target_ver,
-                    refs::Ref::Tag(_) => true, // Always checkout for tags
+                    refs::Ref::Version(_, Some(target_ver)) => version != target_ver,
+                    refs::Ref::Version(_, None) => true, // No specific version, always checkout
+                    refs::Ref::Tag(_) => true,           // Always checkout for tags
                 };
 
                 if should_checkout {

rust/lancedb/src/utils.rs

@@ -174,7 +174,7 @@ pub(crate) fn default_vector_column(schema: &Schema, dim: Option<i32>) -> Result
             ),
         })
     } else {
-        Ok(candidates[0].to_string())
+        Ok(candidates[0].clone())
     }
 }