Bump version: 0.25.3-beta.6 → 0.25.3

Closes #2767

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.21.2"
+current_version = "0.22.3-beta.5"
 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/codex-update-lance-dependency.yml

@@ -0,0 +1,107 @@
+name: Codex Update Lance Dependency
+
+on:
+  workflow_call:
+    inputs:
+      tag:
+        description: "Tag name from Lance"
+        required: true
+        type: string
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: "Tag name from Lance"
+        required: true
+        type: string
+
+permissions:
+  contents: write
+  pull-requests: write
+  actions: read
+
+jobs:
+  update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Show inputs
+        run: |
+          echo "tag = ${{ inputs.tag }}"
+
+      - name: Checkout Repo LanceDB
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          persist-credentials: true
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+
+      - name: Install Codex CLI
+        run: npm install -g @openai/codex
+
+      - name: Install Rust toolchain
+        uses: dtolnay/rust-toolchain@stable
+        with:
+          toolchain: stable
+          components: clippy, rustfmt
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y protobuf-compiler libssl-dev
+
+      - name: Install cargo-info
+        run: cargo install cargo-info
+
+      - name: Install Python dependencies
+        run: python3 -m pip install --upgrade pip packaging
+
+      - name: Configure git user
+        run: |
+          git config user.name "lancedb automation"
+          git config user.email "robot@lancedb.com"
+
+      - name: Configure Codex authentication
+        env:
+          CODEX_TOKEN_B64: ${{ secrets.CODEX_TOKEN }}
+        run: |
+          if [ -z "${CODEX_TOKEN_B64}" ]; then
+            echo "Repository secret CODEX_TOKEN is not defined; skipping Codex execution."
+            exit 1
+          fi
+          mkdir -p ~/.codex
+          echo "${CODEX_TOKEN_B64}" | base64 --decode > ~/.codex/auth.json
+
+      - name: Run Codex to update Lance dependency
+        env:
+          TAG: ${{ inputs.tag }}
+          GITHUB_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+          cat <<EOF >/tmp/codex-prompt.txt
+          You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
+
+          Follow these steps exactly:
+          1. Use script "ci/set_lance_version.py" to update Lance dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
+          2. Run "cargo clippy --workspace --tests --all-features -- -D warnings". If diagnostics appear, fix them yourself and rerun clippy until it exits cleanly. Do not skip any warnings.
+          3. After clippy succeeds, run "cargo fmt --all" to format the workspace.
+          4. Ensure the repository is clean except for intentional changes. Inspect "git status --short" and "git diff" to confirm the dependency update and any required fixes.
+          5. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
+          6. Stage all relevant files with "git add -A". Commit using the message "chore: update lance dependency to v${VERSION}".
+          7. Push the branch to origin. If the branch already exists, force-push your changes.
+          8. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
+          9. Create a pull request targeting "main" with title "chore: update lance dependency to v${VERSION}". In the body, summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}).
+          10. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
+
+          Constraints:
+          - Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
+          - Do not merge the PR.
+          - If any command fails, diagnose and fix the issue instead of aborting.
+          EOF
+          codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"

.github/workflows/docs.yml

@@ -56,8 +56,9 @@ jobs:
         with:
           node-version: 20
           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/docs_test.yml

@@ -24,7 +24,8 @@ env:
 jobs:
   test-python:
     name: Test doc python code
-    runs-on: ubuntu-24.04
+    runs-on: warp-ubuntu-2204-x64-8x
+    timeout-minutes: 60
     steps:
     - name: Checkout
       uses: actions/checkout@v4

.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
@@ -116,7 +117,7 @@ jobs:
         set -e
         npm ci
         npm run docs
-        if ! git diff --exit-code -- . ':(exclude)Cargo.lock'; then
+        if ! git diff --exit-code -- ../ ':(exclude)Cargo.lock'; then
           echo "Docs need to be updated"
           echo "Run 'npm run docs', fix any warnings, and commit the changes."
           exit 1

.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

@@ -56,7 +56,7 @@ jobs:
           pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
           fury_token: ${{ secrets.FURY_TOKEN }}
   mac:
-    timeout-minutes: 60
+    timeout-minutes: 90
     runs-on: ${{ matrix.config.runner }}
     strategy:
       matrix:
@@ -64,7 +64,7 @@ jobs:
           - target: x86_64-apple-darwin
             runner: macos-13
           - target: aarch64-apple-darwin
-            runner: macos-14
+            runner: warp-macos-14-arm64-6x
     env:
       MACOSX_DEPLOYMENT_TARGET: 10.15
     steps:
@@ -173,3 +173,17 @@ jobs:
           generate_release_notes: false
           name: Python LanceDB v${{ 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

@@ -96,6 +96,7 @@ jobs:
       # Need up-to-date compilers for kernels
       CC: clang-18
       CXX: clang++-18
+      GH_TOKEN: ${{ secrets.SOPHON_READ_TOKEN }}
     steps:
       - uses: actions/checkout@v4
         with:
@@ -117,15 +118,17 @@ jobs:
           sudo chmod 600 /swapfile
           sudo mkswap /swapfile
           sudo swapon /swapfile
-      - name: Start S3 integration test environment
-        working-directory: .
-        run: docker compose up --detach --wait
       - name: Build
         run: cargo build --all-features --tests --locked --examples
-      - name: Run tests
+      - name: Run feature tests
-        run: cargo test --all-features --locked
+        run: make -C ./lancedb feature-tests
       - 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:
     timeout-minutes: 30

.github/workflows/trigger-vectordb-recipes.yml

@@ -1,26 +0,0 @@
-name: Trigger vectordb-recipers workflow
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    paths:
-      - .github/workflows/trigger-vectordb-recipes.yml
-  workflow_dispatch:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Trigger vectordb-recipes workflow
-        uses: actions/github-script@v6
-        with:
-          github-token: ${{ secrets.VECTORDB_RECIPES_ACTION_TOKEN }}
-          script: |
-            const result = await github.rest.actions.createWorkflowDispatch({
-                owner: 'lancedb',
-                repo: 'vectordb-recipes',
-                workflow_id: 'examples-test.yml',
-                ref: 'main'
-            });
-            console.log(result);

AGENTS.md

@@ -0,0 +1,101 @@
+LanceDB is a database designed for retrieval, including vector, full-text, and hybrid search.
+It is a wrapper around Lance. There are two backends: local (in-process like SQLite) and
+remote (against LanceDB Cloud).
+
+The core of LanceDB is written in Rust. There are bindings in Python, Typescript, and Java.
+
+Project layout:
+
+* `rust/lancedb`: The LanceDB core Rust implementation.
+* `python`: The Python bindings, using PyO3.
+* `nodejs`: The Typescript bindings, using napi-rs
+* `java`: The Java bindings
+
+Common commands:
+
+* Check for compiler errors: `cargo check --quiet --features remote --tests --examples`
+* Run tests: `cargo test --quiet --features remote --tests`
+* Run specific test: `cargo test --quiet --features remote -p <package_name> --test <test_name>`
+* Lint: `cargo clippy --quiet --features remote --tests --examples`
+* Format: `cargo fmt --all`
+
+Before committing changes, run formatting.
+
+## Coding tips
+
+* When writing Rust doctests for things that require a connection or table reference,
+  write them as a function instead of a fully executable test. This allows type checking
+  to run but avoids needing a full test environment. For example:
+    ```rust
+    /// ```
+    /// use lance_index::scalar::FullTextSearchQuery;
+    /// use lancedb::query::{QueryBase, ExecutableQuery};
+    ///
+    /// # use lancedb::Table;
+    /// # async fn query(table: &Table) -> Result<(), Box<dyn std::error::Error>> {
+    /// let results = table.query()
+    ///     .full_text_search(FullTextSearchQuery::new("hello world".into()))
+    ///     .execute()
+    ///     .await?;
+    /// # Ok(())
+    /// # }
+    /// ```
+    ```
+
+## Example plan: adding a new method on Table
+
+Adding a new method involves first adding it to the Rust core, then exposing it
+in the Python and TypeScript bindings. There are both local and remote tables.
+Remote tables are implemented via a HTTP API and require the `remote` cargo
+feature flag to be enabled. Python has both sync and async methods.
+
+Rust core changes:
+
+1. Add method on `Table` struct in `rust/lancedb/src/table.rs` (calls `BaseTable` trait).
+2. Add method to `BaseTable` trait in `rust/lancedb/src/table.rs`.
+3. Implement new trait method on `NativeTable` in `rust/lancedb/src/table.rs`.
+    * Test with unit test in `rust/lancedb/src/table.rs`.
+4. Implement new trait method on `RemoteTable` in `rust/lancedb/src/remote/table.rs`.
+    * Test with unit test in `rust/lancedb/src/remote/table.rs` against mocked endpoint.
+
+Python bindings changes:
+
+1. Add PyO3 method binding in `python/src/table.rs`. Run `make develop` to compile bindings.
+2. Add types for PyO3 method in `python/python/lancedb/_lancedb.pyi`.
+3. Add method to `AsyncTable` class in `python/python/lancedb/table.py`.
+4. Add abstract method to `Table` abstract base class in `python/python/lancedb/table.py`.
+5. Add concrete sync method to `LanceTable` class in `python/python/lancedb/table.py`.
+    * Should use `LOOP.run()` to call the corresponding `AsyncTable` method.
+6. Add concrete sync method to `RemoteTable` class in `python/python/lancedb/remote/table.py`.
+7. Add unit test in `python/tests/test_table.py`.
+
+TypeScript bindings changes:
+
+1. Add napi-rs method binding on `Table` in `nodejs/src/table.rs`.
+2. Run `npm run build` to generate TypeScript definitions.
+3. Add typescript method on abstract class `Table` in `nodejs/src/table.ts`.
+4. Add concrete method on `LocalTable` class in `nodejs/src/native_table.ts`.
+    * Note: despite the name, this class is also used for remote tables.
+5. Add test in `nodejs/__test__/table.test.ts`.
+6. Run `npm run docs` to generate TypeScript documentation.
+
+## Review Guidelines
+
+Please consider the following when reviewing code contributions.
+
+### Rust API design
+* Design public APIs so they can be evolved easily in the future without breaking
+  changes. Often this means using builder patterns or options structs instead of
+  long argument lists.
+* For public APIs, prefer inputs that use `Into<T>` or `AsRef<T>` traits to allow
+  more flexible inputs. For example, use `name: Into<String>` instead of `name: String`,
+  so we don't have to write `func("my_string".to_string())`.
+
+### Testing
+* Ensure all new public APIs have documentation and examples.
+* Ensure that all bugfixes and features have corresponding tests. **We do not merge
+  code without tests.**
+
+### Documentation
+* New features must include updates to the rust documentation comments. Link to
+  relevant structs and methods to increase the value of documentation.

CLAUDE.md

@@ -1,22 +0,0 @@
-LanceDB is a database designed for retrieval, including vector, full-text, and hybrid search.
-It is a wrapper around Lance. There are two backends: local (in-process like SQLite) and
-remote (against LanceDB Cloud).
-
-The core of LanceDB is written in Rust. There are bindings in Python, Typescript, and Java.
-
-Project layout:
-
-* `rust/lancedb`: The LanceDB core Rust implementation.
-* `python`: The Python bindings, using PyO3.
-* `nodejs`: The Typescript bindings, using napi-rs
-* `java`: The Java bindings
-
-Common commands:
-
-* Check for compiler errors: `cargo check --features remote --tests --examples`
-* Run tests: `cargo test --features remote --tests`
-* Run specific test: `cargo test --features remote -p <package_name> --test <test_name>`
-* Lint: `cargo clippy --features remote --tests --examples`
-* Format: `cargo fmt --all`
-
-Before committing changes, run formatting.

CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

Cargo.toml

@@ -15,30 +15,37 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.33.0", "features" = ["dynamodb"] }
+lance = { "version" = "=0.39.0", default-features = false }
-lance-io = "=0.33.0"
+lance-core = "=0.39.0"
-lance-index = "=0.33.0"
+lance-datagen = "=0.39.0"
-lance-linalg = "=0.33.0"
+lance-file = "=0.39.0"
-lance-table = "=0.33.0"
+lance-io = { "version" = "=0.39.0", default-features = false }
-lance-testing = "=0.33.0"
+lance-index = "=0.39.0"
-lance-datafusion = "=0.33.0"
+lance-linalg = "=0.39.0"
-lance-encoding = "=0.33.0"
+lance-namespace = "=0.39.0"
+lance-namespace-impls = { "version" = "=0.39.0", "features" = ["dir-aws", "dir-gcp", "dir-azure", "dir-oss", "rest"] }
+lance-table = "=0.39.0"
+lance-testing = "=0.39.0"
+lance-datafusion = "=0.39.0"
+lance-encoding = "=0.39.0"
+lance-arrow = "=0.39.0"
+ahash = "0.8"
 # Note that this one does not include pyarrow
-arrow = { version = "55.1", optional = false }
+arrow = { version = "56.2", optional = false }
-arrow-array = "55.1"
+arrow-array = "56.2"
-arrow-data = "55.1"
+arrow-data = "56.2"
-arrow-ipc = "55.1"
+arrow-ipc = "56.2"
-arrow-ord = "55.1"
+arrow-ord = "56.2"
-arrow-schema = "55.1"
+arrow-schema = "56.2"
-arrow-arith = "55.1"
+arrow-select = "56.2"
-arrow-cast = "55.1"
+arrow-cast = "56.2"
 async-trait = "0"
-datafusion = { version = "48.0", default-features = false }
+datafusion = { version = "50.1", default-features = false }
-datafusion-catalog = "48.0"
+datafusion-catalog = "50.1"
-datafusion-common = { version = "48.0", default-features = false }
+datafusion-common = { version = "50.1", default-features = false }
-datafusion-execution = "48.0"
+datafusion-execution = "50.1"
-datafusion-expr = "48.0"
+datafusion-expr = "50.1"
-datafusion-physical-plan = "48.0"
+datafusion-physical-plan = "50.1"
 env_logger = "0.11"
 half = { "version" = "2.6.0", default-features = false, features = [
     "num-traits",
@@ -48,18 +55,11 @@ log = "0.4"
 moka = { version = "0.12", features = ["future"] }
 object_store = "0.12.0"
 pin-project = "1.0.7"
+rand = "0.9"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-rand = "0.9"
 regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
-crunchy = "0.2.4"
+chrono = "0.4"
-# 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"

ci/create_lancedb_test_connection.sh

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+
+export RUST_LOG=info
+exec ./lancedb server --port 0 --sql-port 0  --data-dir "${1}"

ci/run_with_docker_compose.sh

@@ -0,0 +1,18 @@
+#!/usr/bin/env bash
+
+#
+# A script for running the given command together with a docker compose environment.
+#
+
+# Bring down the docker setup once the command is done running.
+tear_down() {
+    docker compose -p fixture down
+}
+trap tear_down EXIT
+
+set +xe
+
+# Clean up any existing docker setup and bring up a new one.
+docker compose -p fixture up --detach --wait || exit 1
+
+"${@}"

ci/run_with_test_connection.sh

@@ -0,0 +1,68 @@
+#!/usr/bin/env bash
+
+#
+# A script for running the given command together with the lancedb cli.
+#
+
+die() {
+    echo $?
+    exit 1
+}
+
+check_command_exists() {
+    command="${1}"
+    which ${command} &> /dev/null || \
+        die "Unable to locate command: ${command}. Did you install it?"
+}
+
+if [[ ! -e ./lancedb ]]; then
+    if [[ -v SOPHON_READ_TOKEN ]]; then
+        INPUT="lancedb-linux-x64"
+        gh release \
+            --repo lancedb/lancedb \
+            download ci-support-binaries \
+            --pattern "${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
+        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."
+    fi
+
+    check_command_exists tar
+    tar xvf "${TARGET}" || die "tar failed."
+    [[ -e ./lancedb ]] || die "failed to extract lancedb."
+fi
+
+SCRIPT_DIR=$(dirname "$(readlink -f "$0")")
+export CREATE_LANCEDB_TEST_CONNECTION_SCRIPT="${SCRIPT_DIR}/create_lancedb_test_connection.sh"
+
+"${@}"

ci/set_lance_version.py

@@ -1,4 +1,5 @@
 import argparse
+import re
 import sys
 import json
 
@@ -18,8 +19,12 @@ def run_command(command: str) -> str:
 
 def get_latest_stable_version() -> str:
     version_line = run_command("cargo info lance | grep '^version:'")
-    version = version_line.split(" ")[1].strip()
+    # Example output: "version: 0.35.0 (latest 0.37.0)"
-    return version
+    match = re.search(r'\(latest ([0-9.]+)\)', version_line)
+    if match:
+        return match.group(1)
+    # Fallback: use the first version after 'version:'
+    return version_line.split("version:")[1].split()[0].strip()
 
 
 def get_latest_preview_version() -> str:
@@ -50,10 +55,56 @@ def extract_features(line: str) -> list:
     match = re.search(r'"features"\s*=\s*\[\s*(.*?)\s*\]', line, re.DOTALL)
     if match:
         features_str = match.group(1)
-        return [f.strip('"') for f in features_str.split(",") if len(f) > 0]
+        return [f.strip().strip('"') for f in features_str.split(",") if f.strip()]
     return []
 
 
+def extract_default_features(line: str) -> bool:
+    """
+    Checks if default-features = false is present in a line in Cargo.toml.
+    Example: 'lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"] }'
+    Returns: True if default-features = false is present, False otherwise
+    """
+    import re
+
+    match = re.search(r'default-features\s*=\s*false', line)
+    return match is not None
+
+
+def dict_to_toml_line(package_name: str, config: dict) -> str:
+    """
+    Converts a configuration dictionary to a TOML dependency line.
+    Dictionary insertion order is preserved (Python 3.7+), so the caller
+    controls the order of fields in the output.
+
+    Args:
+        package_name: The name of the package (e.g., "lance", "lance-io")
+        config: Dictionary with keys like "version", "path", "git", "tag", "features", "default-features"
+                The order of keys in this dict determines the order in the output.
+
+    Returns:
+        A properly formatted TOML line with a trailing newline
+    """
+    # If only version is specified, use simple format
+    if len(config) == 1 and "version" in config:
+        return f'{package_name} = "{config["version"]}"\n'
+
+    # Otherwise, use inline table format
+    parts = []
+    for key, value in config.items():
+        if key == "default-features" and not value:
+            parts.append("default-features = false")
+        elif key == "features":
+            parts.append(f'"features" = {json.dumps(value)}')
+        elif isinstance(value, str):
+            parts.append(f'"{key}" = "{value}"')
+        else:
+            # This shouldn't happen with our current usage
+            parts.append(f'"{key}" = {json.dumps(value)}')
+
+    return f'{package_name} = {{ {", ".join(parts)} }}\n'
+
+
 def update_cargo_toml(line_updater):
     """
     Updates the Cargo.toml file by applying the line_updater function to each line.
@@ -67,20 +118,27 @@ def update_cargo_toml(line_updater):
     is_parsing_lance_line = False
     for line in lines:
         if line.startswith("lance"):
-            # Update the line using the provided function
+            # Check if this is a single-line or multi-line entry
-            if line.strip().endswith("}"):
+            # Single-line entries either:
+            # 1. End with } (complete inline table)
+            # 2. End with " (simple version string)
+            # Multi-line entries start with { but don't end with }
+            if line.strip().endswith("}") or line.strip().endswith('"'):
+                # Single-line entry - process immediately
                 new_lines.append(line_updater(line))
-            else:
+            elif "{" in line and not line.strip().endswith("}"):
+                # Multi-line entry - start accumulating
                 lance_line = line
                 is_parsing_lance_line = True
+            else:
+                # Single-line entry without quotes or braces (shouldn't happen but handle it)
+                new_lines.append(line_updater(line))
         elif is_parsing_lance_line:
             lance_line += line
             if line.strip().endswith("}"):
                 new_lines.append(line_updater(lance_line))
                 lance_line = ""
                 is_parsing_lance_line = False
-            else:
-                print("doesn't end with }:", line)
         else:
             # Keep the line unchanged
             new_lines.append(line)
@@ -92,18 +150,25 @@ def update_cargo_toml(line_updater):
 def set_stable_version(version: str):
     """
     Sets lines to
-    lance = { "version" = "=0.29.0", "features" = ["dynamodb"] }
+    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"] }
-    lance-io = "=0.29.0"
+    lance-io = { "version" = "=0.29.0", default-features = false }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
+
+        # Build config in desired order: version, default-features, features
+        config = {"version": f"={version}"}
+
+        if extract_default_features(line):
+            config["default-features"] = False
+
         features = extract_features(line)
         if features:
-            return f'{package_name} = {{ "version" = "={version}", "features" = {json.dumps(features)} }}\n'
+            config["features"] = features
-        else:
+
-            return f'{package_name} = "={version}"\n'
+        return dict_to_toml_line(package_name, config)
 
     update_cargo_toml(line_updater)
 
@@ -111,19 +176,27 @@ def set_stable_version(version: str):
 def set_preview_version(version: str):
     """
     Sets lines to
-    lance = { "version" = "=0.29.0", "features" = ["dynamodb"], tag = "v0.29.0-beta.2", git="https://github.com/lancedb/lance.git" }
+    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"], "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-    lance-io = { version = "=0.29.0", tag = "v0.29.0-beta.2", git="https://github.com/lancedb/lance.git" }
+    lance-io = { "version" = "=0.29.0", default-features = false, "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
+        # Build config in desired order: version, default-features, features, tag, git
+        config = {"version": f"={version}"}
+
+        if extract_default_features(line):
+            config["default-features"] = False
+
         features = extract_features(line)
-        base_version = version.split("-")[0]  # Get the base version without beta suffix
         if features:
-            return f'{package_name} = {{ "version" = "={base_version}", "features" = {json.dumps(features)}, "tag" = "v{version}", "git" = "https://github.com/lancedb/lance.git" }}\n'
+            config["features"] = features
-        else:
+
-            return f'{package_name} = {{ "version" = "={base_version}", "tag" = "v{version}", "git" = "https://github.com/lancedb/lance.git" }}\n'
+        config["tag"] = f"v{version}"
+        config["git"] = "https://github.com/lancedb/lance.git"
+
+        return dict_to_toml_line(package_name, config)
 
     update_cargo_toml(line_updater)
 
@@ -131,18 +204,25 @@ def set_preview_version(version: str):
 def set_local_version():
     """
     Sets lines to
-    lance = { path = "../lance/rust/lance", features = ["dynamodb"] }
+    lance = { "path" = "../lance/rust/lance", default-features = false, "features" = ["dynamodb"] }
-    lance-io = { path = "../lance/rust/lance-io" }
+    lance-io = { "path" = "../lance/rust/lance-io", default-features = false }
     ...
     """
 
     def line_updater(line: str) -> str:
         package_name = line.split("=", maxsplit=1)[0].strip()
+
+        # Build config in desired order: path, default-features, features
+        config = {"path": f"../lance/rust/{package_name}"}
+
+        if extract_default_features(line):
+            config["default-features"] = False
+
         features = extract_features(line)
         if features:
-            return f'{package_name} = {{ "path" = "../lance/rust/{package_name}", "features" = {json.dumps(features)} }}\n'
+            config["features"] = features
-        else:
+
-            return f'{package_name} = {{ "path" = "../lance/rust/{package_name}" }}\n'
+        return dict_to_toml_line(package_name, config)
 
     update_cargo_toml(line_updater)
 

docs/mkdocs.yml

@@ -70,6 +70,23 @@ plugins:
   - mkdocs-jupyter
   - render_swagger:
       allow_arbitrary_locations: true
+  - redirects:
+      redirect_maps:
+        # Redirect the home page and other top-level markdown files. This enables maximum SEO benefit
+        # other sub-pages are handled by the ingected js in overrides/partials/header.html
+        'index.md': 'https://lancedb.com/docs/'
+        'guides/tables.md': 'https://lancedb.com/docs/tables/'
+        'ann_indexes.md': 'https://lancedb.com/docs/indexing/'
+        'basic.md': 'https://lancedb.com/docs/quickstart/'
+        'faq.md': 'https://lancedb.com/docs/faq/'
+        'embeddings/understanding_embeddings.md': 'https://lancedb.com/docs/embedding/'
+        'integrations.md': 'https://lancedb.com/docs/integrations/'
+        'examples.md': 'https://lancedb.com/docs/tutorials/'
+        'concepts/vector_search.md': 'https://lancedb.com/docs/search/vector-search/'
+        'troubleshooting.md': 'https://lancedb.com/docs/troubleshooting/'
+        'guides/storage.md': 'https://lancedb.com/docs/storage/integrations'
+
+
 
 markdown_extensions:
   - admonition

docs/overrides/partials/header.html

@@ -19,7 +19,13 @@
   FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
   IN THE SOFTWARE.
 -->
-
+<div id="deprecation-banner" style="background-color: #f8d7da; color: #721c24; padding: 1em; text-align: center;">                                                           
+    <p style="margin: 0; font-size: 1.1em;">                                                                                                           
+        <strong>This documentation site is deprecated.</strong>                                                                           
+        Please visit our new documentation site at <a href="https://lancedb.com/docs" style="color: #721c24; text-decoration: underline;">
+          lancedb.com/docs</a> for the latest information.                                                                                        
+    </p>                                                                                                                                               
+  </div>  
 {% set class = "md-header" %}
 {% if "navigation.tabs.sticky" in features %}
   {% set class = class ~ " md-header--shadow md-header--lifted" %}
@@ -150,9 +156,9 @@
 
     <div style="margin-left: 10px; margin-right: 5px;">
         <a href="https://discord.com/invite/zMM32dvNtd" target="_blank" rel="noopener noreferrer">
-            <svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
+          <svg fill="#FFFFFF" xmlns="http://www.w3.org/2000/svg"  viewBox="0 0 50 50" width="25px" height="25px"><path d="M 41.625 10.769531 C 37.644531 7.566406 31.347656 7.023438 31.078125 7.003906 C 30.660156 6.96875 30.261719 7.203125 30.089844 7.589844 C 30.074219 7.613281 29.9375 7.929688 29.785156 8.421875 C 32.417969 8.867188 35.652344 9.761719 38.578125 11.578125 C 39.046875 11.867188 39.191406 12.484375 38.902344 12.953125 C 38.710938 13.261719 38.386719 13.429688 38.050781 13.429688 C 37.871094 13.429688 37.6875 13.378906 37.523438 13.277344 C 32.492188 10.15625 26.210938 10 25 10 C 23.789063 10 17.503906 10.15625 12.476563 13.277344 C 12.007813 13.570313 11.390625 13.425781 11.101563 12.957031 C 10.808594 12.484375 10.953125 11.871094 11.421875 11.578125 C 14.347656 9.765625 17.582031 8.867188 20.214844 8.425781 C 20.0625 7.929688 19.925781 7.617188 19.914063 7.589844 C 19.738281 7.203125 19.34375 6.960938 18.921875 7.003906 C 18.652344 7.023438 12.355469 7.566406 8.320313 10.8125 C 6.214844 12.761719 2 24.152344 2 34 C 2 34.175781 2.046875 34.34375 2.132813 34.496094 C 5.039063 39.605469 12.972656 40.941406 14.78125 41 C 14.789063 41 14.800781 41 14.8125 41 C 15.132813 41 15.433594 40.847656 15.621094 40.589844 L 17.449219 38.074219 C 12.515625 36.800781 9.996094 34.636719 9.851563 34.507813 C 9.4375 34.144531 9.398438 33.511719 9.765625 33.097656 C 10.128906 32.683594 10.761719 32.644531 11.175781 33.007813 C 11.234375 33.0625 15.875 37 25 37 C 34.140625 37 38.78125 33.046875 38.828125 33.007813 C 39.242188 32.648438 39.871094 32.683594 40.238281 33.101563 C 40.601563 33.515625 40.5625 34.144531 40.148438 34.507813 C 40.003906 34.636719 37.484375 36.800781 32.550781 38.074219 L 34.378906 40.589844 C 34.566406 40.847656 34.867188 41 35.1875 41 C 35.199219 41 35.210938 41 35.21875 41 C 37.027344 40.941406 44.960938 39.605469 47.867188 34.496094 C 47.953125 34.34375 48 34.175781 48 34 C 48 24.152344 43.785156 12.761719 41.625 10.769531 Z M 18.5 30 C 16.566406 30 15 28.210938 15 26 C 15 23.789063 16.566406 22 18.5 22 C 20.433594 22 22 23.789063 22 26 C 22 28.210938 20.433594 30 18.5 30 Z M 31.5 30 C 29.566406 30 28 28.210938 28 26 C 28 23.789063 29.566406 22 31.5 22 C 33.433594 22 35 23.789063 35 26 C 35 28.210938 33.433594 30 31.5 30 Z"/></svg>
-        </a>
+      </a>
-    </div>
+  </div>
     <div style="margin-left: 5px; margin-right: 5px;">
         <a href="https://twitter.com/lancedb" target="_blank" rel="noopener noreferrer">
             <svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" viewBox="0,0,256,256" width="25px" height="25px" fill-rule="nonzero"><g fill-opacity="0" fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><path d="M0,256v-256h256v256z" id="bgRectangle"></path></g><g fill="#ffffff" fill-rule="nonzero" stroke="none" stroke-width="1" stroke-linecap="butt" stroke-linejoin="miter" stroke-miterlimit="10" stroke-dasharray="" stroke-dashoffset="0" font-family="none" font-weight="none" font-size="none" text-anchor="none" style="mix-blend-mode: normal"><g transform="scale(4,4)"><path d="M57,17.114c-1.32,1.973 -2.991,3.707 -4.916,5.097c0.018,0.423 0.028,0.847 0.028,1.274c0,13.013 -9.902,28.018 -28.016,28.018c-5.562,0 -12.81,-1.948 -15.095,-4.423c0.772,0.092 1.556,0.138 2.35,0.138c4.615,0 8.861,-1.575 12.23,-4.216c-4.309,-0.079 -7.946,-2.928 -9.199,-6.84c1.96,0.308 4.447,-0.17 4.447,-0.17c0,0 -7.7,-1.322 -7.899,-9.779c2.226,1.291 4.46,1.231 4.46,1.231c0,0 -4.441,-2.734 -4.379,-8.195c0.037,-3.221 1.331,-4.953 1.331,-4.953c8.414,10.361 20.298,10.29 20.298,10.29c0,0 -0.255,-1.471 -0.255,-2.243c0,-5.437 4.408,-9.847 9.847,-9.847c2.832,0 5.391,1.196 7.187,3.111c2.245,-0.443 4.353,-1.263 6.255,-2.391c-0.859,3.44 -4.329,5.448 -4.329,5.448c0,0 2.969,-0.329 5.655,-1.55z"></path></g></g></svg>
@@ -174,3 +180,76 @@
     {% endif %}
   {% endif %}
 </header>
+
+<script>
+  (function() {
+    function checkPathAndRedirect() {
+      var banner = document.getElementById('deprecation-banner');
+
+      if (document.querySelector('meta[http-equiv="refresh"]')) {
+        return; // The redirects plugin is already handling this page.
+      }
+
+      var currentPath = window.location.pathname;
+
+      var cleanPath = currentPath.endsWith('/') && currentPath.length > 1
+        ? currentPath.slice(0, -1)
+        : currentPath;
+
+      // These are the ONLY paths that should remain on the old site
+      var apiPaths = [
+        '/lancedb/python', 
+        '/lancedb/javascript', 
+        '/lancedb/js',
+        '/lancedb/api_reference'
+      ];
+      
+      var isApiPage = apiPaths.some(function(apiPath) {
+        return cleanPath.startsWith(apiPath);
+      });
+
+      if (isApiPage) {
+        if (banner) {
+          banner.style.display = 'none';
+        }
+      } else {
+        if (banner) {
+          banner.style.display = 'block';
+        }
+        
+        // Add noindex meta tag to prevent indexing of old docs for seo
+        var noindexMeta = document.createElement('meta');
+        noindexMeta.setAttribute('name', 'robots');
+        noindexMeta.setAttribute('content', 'noindex, follow');
+        document.head.appendChild(noindexMeta);
+
+        // Add canonical link to point to the new docs to reward new site for seo
+        var canonicalLink = document.createElement('link');
+        canonicalLink.setAttribute('rel', 'canonical');
+        canonicalLink.setAttribute('href', 'https://lancedb.com/docs');
+        document.head.appendChild(canonicalLink);
+        
+        window.location.replace('https://lancedb.com/docs');
+      }
+    }
+
+    // Run the check only if doc is ready. This makes sure we catch the initial load
+    // and redirect.
+    if (document.readyState === 'loading') {
+      document.addEventListener('DOMContentLoaded', checkPathAndRedirect);
+    } else {
+      checkPathAndRedirect();
+    }
+
+    // Use an interval to handle subsequent navigation clicks.
+    var lastPath = window.location.pathname;
+    setInterval(function() {
+      if (window.location.pathname !== lastPath) {
+        lastPath = window.location.pathname;
+        checkPathAndRedirect();
+      }
+    }, 2000); // keeping it 2 second to make it easy for user to understand
+              // what's happening
+
+  })();
+</script>

docs/requirements.txt

@@ -5,3 +5,4 @@ mkdocstrings[python]==0.25.2
 griffe
 mkdocs-render-swagger-plugin
 pydantic
+mkdocs-redirects

docs/src/embeddings/available_embedding_models/multimodal_embedding_functions/voyageai_multimodal_embedding.md

@@ -0,0 +1,97 @@
+# VoyageAI Embeddings : Multimodal
+
+VoyageAI embeddings can also be used to embed both text and image data, only some of the models support image data and you can check the list
+under [https://docs.voyageai.com/docs/multimodal-embeddings](https://docs.voyageai.com/docs/multimodal-embeddings)
+
+Supported parameters (to be passed in `create` method) are:
+
+| Parameter | Type | Default Value           | Description                               |
+|---|---|-------------------------|-------------------------------------------|
+| `name` | `str` | `"voyage-multimodal-3"` | The model ID of the VoyageAI model to use |
+
+Usage Example:
+
+```python
+import base64
+import os
+from io import BytesIO
+
+import requests
+import lancedb
+from lancedb.pydantic import LanceModel, Vector
+from lancedb.embeddings import get_registry
+import pandas as pd
+
+os.environ['VOYAGE_API_KEY'] = 'YOUR_VOYAGE_API_KEY'
+
+db = lancedb.connect(".lancedb")
+func = get_registry().get("voyageai").create(name="voyage-multimodal-3")
+
+
+def image_to_base64(image_bytes: bytes):
+    buffered = BytesIO(image_bytes)
+    img_str = base64.b64encode(buffered.getvalue())
+    return img_str.decode("utf-8")
+
+
+class Images(LanceModel):
+    label: str
+    image_uri: str = func.SourceField()  # image uri as the source
+    image_bytes: str = func.SourceField()  # image bytes base64 encoded as the source
+    vector: Vector(func.ndims()) = func.VectorField()  # vector column
+    vec_from_bytes: Vector(func.ndims()) = func.VectorField()  # Another vector column
+
+
+if "images" in db.table_names():
+    db.drop_table("images")
+table = db.create_table("images", schema=Images)
+labels = ["cat", "cat", "dog", "dog", "horse", "horse"]
+uris = [
+    "http://farm1.staticflickr.com/53/167798175_7c7845bbbd_z.jpg",
+    "http://farm1.staticflickr.com/134/332220238_da527d8140_z.jpg",
+    "http://farm9.staticflickr.com/8387/8602747737_2e5c2a45d4_z.jpg",
+    "http://farm5.staticflickr.com/4092/5017326486_1f46057f5f_z.jpg",
+    "http://farm9.staticflickr.com/8216/8434969557_d37882c42d_z.jpg",
+    "http://farm6.staticflickr.com/5142/5835678453_4f3a4edb45_z.jpg",
+]
+# get each uri as bytes
+images_bytes = [image_to_base64(requests.get(uri).content) for uri in uris]
+table.add(
+    pd.DataFrame({"label": labels, "image_uri": uris, "image_bytes": images_bytes})
+)
+```
+Now we can search using text from both the default vector column and the custom vector column
+```python
+
+# text search
+actual = table.search("man's best friend", "vec_from_bytes").limit(1).to_pydantic(Images)[0]
+print(actual.label) # prints "dog"
+
+frombytes = (
+    table.search("man's best friend", vector_column_name="vec_from_bytes")
+    .limit(1)
+    .to_pydantic(Images)[0]
+)
+print(frombytes.label)
+
+```
+
+Because we're using a multi-modal embedding function, we can also search using images
+
+```python
+# image search
+query_image_uri = "http://farm1.staticflickr.com/200/467715466_ed4a31801f_z.jpg"
+image_bytes = requests.get(query_image_uri).content
+query_image = Image.open(BytesIO(image_bytes))
+actual = table.search(query_image, "vec_from_bytes").limit(1).to_pydantic(Images)[0]
+print(actual.label == "dog")
+
+# image search using a custom vector column
+other = (
+    table.search(query_image, vector_column_name="vec_from_bytes")
+    .limit(1)
+    .to_pydantic(Images)[0]
+)
+print(actual.label)
+
+```

docs/src/guides/storage.md

@@ -397,117 +397,6 @@ For **read-only access**, LanceDB will need a policy such as:
 }
 ```
 
-#### DynamoDB Commit Store for concurrent writes
-
-By default, S3 does not support concurrent writes. Having two or more processes
-writing to the same table at the same time can lead to data corruption. This is
-because S3, unlike other object stores, does not have any atomic put or copy
-operation.
-
-To enable concurrent writes, you can configure LanceDB to use a DynamoDB table
-as a commit store. This table will be used to coordinate writes between
-different processes. To enable this feature, you must modify your connection
-URI to use the `s3+ddb` scheme and add a query parameter `ddbTableName` with the
-name of the table to use.
-
-=== "Python"
-
-    === "Sync API"
-
-        ```python
-        import lancedb
-        db = lancedb.connect(
-            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-        )
-        ```
-    === "Async API"
-
-        ```python
-        import lancedb
-        async_db = await lancedb.connect_async(
-            "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-        )    
-        ```
-
-=== "JavaScript"
-
-    ```javascript
-    const lancedb = require("lancedb");
-
-    const db = await lancedb.connect(
-        "s3+ddb://bucket/path?ddbTableName=my-dynamodb-table",
-    );
-    ```
-
-The DynamoDB table must be created with the following schema:
-
-- Hash key: `base_uri` (string)
-- Range key: `version` (number)
-
-You can create this programmatically with:
-
-=== "Python"
-
-    <!-- skip-test -->
-    ```python
-    import boto3
-
-    dynamodb = boto3.client("dynamodb")
-    table = dynamodb.create_table(
-        TableName=table_name,
-        KeySchema=[
-            {"AttributeName": "base_uri", "KeyType": "HASH"},
-            {"AttributeName": "version", "KeyType": "RANGE"},
-        ],
-        AttributeDefinitions=[
-            {"AttributeName": "base_uri", "AttributeType": "S"},
-            {"AttributeName": "version", "AttributeType": "N"},
-        ],
-        ProvisionedThroughput={"ReadCapacityUnits": 1, "WriteCapacityUnits": 1},
-    )
-    ```
-
-=== "JavaScript"
-
-    <!-- skip-test -->
-    ```javascript
-    import {
-      CreateTableCommand,
-      DynamoDBClient,
-    } from "@aws-sdk/client-dynamodb";
-
-    const dynamodb = new DynamoDBClient({
-      region: CONFIG.awsRegion,
-      credentials: {
-        accessKeyId: CONFIG.awsAccessKeyId,
-        secretAccessKey: CONFIG.awsSecretAccessKey,
-      },
-      endpoint: CONFIG.awsEndpoint,
-    });
-    const command = new CreateTableCommand({
-      TableName: table_name,
-      AttributeDefinitions: [
-        {
-          AttributeName: "base_uri",
-          AttributeType: "S",
-        },
-        {
-          AttributeName: "version",
-          AttributeType: "N",
-        },
-      ],
-      KeySchema: [
-        { AttributeName: "base_uri", KeyType: "HASH" },
-        { AttributeName: "version", KeyType: "RANGE" },
-      ],
-      ProvisionedThroughput: {
-        ReadCapacityUnits: 1,
-        WriteCapacityUnits: 1,
-      },
-    });
-    await client.send(command);
-    ```
-
 
 #### S3-compatible stores
 

docs/src/js/classes/Connection.md

@@ -25,6 +25,51 @@ the underlying connection has been closed.
 
 ## Methods
 
+### cloneTable()
+
+```ts
+abstract cloneTable(
+   targetTableName,
+   sourceUri,
+   options?): Promise<Table>
+```
+
+Clone a table from a source table.
+
+A shallow clone creates a new table that shares the underlying data files
+with the source table but has its own independent manifest. This allows
+both the source and cloned tables to evolve independently while initially
+sharing the same data, deletion, and index files.
+
+#### Parameters
+
+* **targetTableName**: `string`
+    The name of the target table to create.
+
+* **sourceUri**: `string`
+    The URI of the source table to clone from.
+
+* **options?**
+    Clone options.
+
+* **options.isShallow?**: `boolean`
+    Whether to perform a shallow clone (defaults to true).
+
+* **options.sourceTag?**: `string`
+    The tag of the source table to clone.
+
+* **options.sourceVersion?**: `number`
+    The version of the source table to clone.
+
+* **options.targetNamespace?**: `string`[]
+    The namespace for the target table (defaults to root namespace).
+
+#### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+***
+
 ### close()
 
 ```ts
@@ -45,6 +90,8 @@ Any attempt to use the connection after it is closed will result in an error.
 
 ### createEmptyTable()
 
+#### createEmptyTable(name, schema, options)
+
 ```ts
 abstract createEmptyTable(
    name,
@@ -54,7 +101,7 @@ abstract createEmptyTable(
 
 Creates a new empty Table
 
-#### Parameters
+##### Parameters
 
 * **name**: `string`
     The name of the table.
@@ -63,8 +110,39 @@ Creates a new empty Table
     The schema of the table
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options (backwards compatibility)
 
-#### Returns
+##### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+#### createEmptyTable(name, schema, namespace, options)
+
+```ts
+abstract createEmptyTable(
+   name,
+   schema,
+   namespace?,
+   options?): Promise<Table>
+```
+
+Creates a new empty Table
+
+##### Parameters
+
+* **name**: `string`
+    The name of the table.
+
+* **schema**: [`SchemaLike`](../type-aliases/SchemaLike.md)
+    The schema of the table
+
+* **namespace?**: `string`[]
+    The namespace to create the table in (defaults to root namespace)
+
+* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options
+
+##### Returns
 
 `Promise`&lt;[`Table`](Table.md)&gt;
 
@@ -72,10 +150,10 @@ Creates a new empty Table
 
 ### createTable()
 
-#### createTable(options)
+#### createTable(options, namespace)
 
 ```ts
-abstract createTable(options): Promise<Table>
+abstract createTable(options, namespace?): Promise<Table>
 ```
 
 Creates a new Table and initialize it with new data.
@@ -85,6 +163,9 @@ Creates a new Table and initialize it with new data.
 * **options**: `object` & `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
     The options object.
 
+* **namespace?**: `string`[]
+    The namespace to create the table in (defaults to root namespace)
+
 ##### Returns
 
 `Promise`&lt;[`Table`](Table.md)&gt;
@@ -110,6 +191,38 @@ Creates a new Table and initialize it with new data.
     to be inserted into the table
 
 * **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options (backwards compatibility)
+
+##### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+#### createTable(name, data, namespace, options)
+
+```ts
+abstract createTable(
+   name,
+   data,
+   namespace?,
+   options?): Promise<Table>
+```
+
+Creates a new Table and initialize it with new data.
+
+##### Parameters
+
+* **name**: `string`
+    The name of the table.
+
+* **data**: [`TableLike`](../type-aliases/TableLike.md) \| `Record`&lt;`string`, `unknown`&gt;[]
+    Non-empty Array of Records
+    to be inserted into the table
+
+* **namespace?**: `string`[]
+    The namespace to create the table in (defaults to root namespace)
+
+* **options?**: `Partial`&lt;[`CreateTableOptions`](../interfaces/CreateTableOptions.md)&gt;
+    Additional options
 
 ##### Returns
 
@@ -134,11 +247,16 @@ Return a brief description of the connection
 ### dropAllTables()
 
 ```ts
-abstract dropAllTables(): Promise<void>
+abstract dropAllTables(namespace?): Promise<void>
 ```
 
 Drop all tables in the database.
 
+#### Parameters
+
+* **namespace?**: `string`[]
+    The namespace to drop tables from (defaults to root namespace).
+
 #### Returns
 
 `Promise`&lt;`void`&gt;
@@ -148,7 +266,7 @@ Drop all tables in the database.
 ### dropTable()
 
 ```ts
-abstract dropTable(name): Promise<void>
+abstract dropTable(name, namespace?): Promise<void>
 ```
 
 Drop an existing table.
@@ -158,6 +276,9 @@ Drop an existing table.
 * **name**: `string`
     The name of the table to drop.
 
+* **namespace?**: `string`[]
+    The namespace of the table (defaults to root namespace).
+
 #### Returns
 
 `Promise`&lt;`void`&gt;
@@ -181,7 +302,10 @@ Return true if the connection has not been closed
 ### openTable()
 
 ```ts
-abstract openTable(name, options?): Promise<Table>
+abstract openTable(
+   name,
+   namespace?,
+   options?): Promise<Table>
 ```
 
 Open a table in the database.
@@ -191,7 +315,11 @@ Open a table in the database.
 * **name**: `string`
     The name of the table
 
+* **namespace?**: `string`[]
+    The namespace of the table (defaults to root namespace)
+
 * **options?**: `Partial`&lt;[`OpenTableOptions`](../interfaces/OpenTableOptions.md)&gt;
+    Additional options
 
 #### Returns
 
@@ -201,6 +329,8 @@ Open a table in the database.
 
 ### tableNames()
 
+#### tableNames(options)
+
 ```ts
 abstract tableNames(options?): Promise<string[]>
 ```
@@ -209,12 +339,35 @@ List all the table names in this database.
 
 Tables will be returned in lexicographical order.
 
-#### Parameters
+##### Parameters
+
+* **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
+    options to control the
+    paging / start point (backwards compatibility)
+
+##### Returns
+
+`Promise`&lt;`string`[]&gt;
+
+#### tableNames(namespace, options)
+
+```ts
+abstract tableNames(namespace?, options?): Promise<string[]>
+```
+
+List all the table names in this database.
+
+Tables will be returned in lexicographical order.
+
+##### Parameters
+
+* **namespace?**: `string`[]
+    The namespace to list tables from (defaults to root namespace)
 
 * **options?**: `Partial`&lt;[`TableNamesOptions`](../interfaces/TableNamesOptions.md)&gt;
     options to control the
     paging / start point
 
-#### Returns
+##### Returns
 
 `Promise`&lt;`string`[]&gt;

docs/src/js/classes/HeaderProvider.md

@@ -0,0 +1,85 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / HeaderProvider
+
+# Class: `abstract` HeaderProvider
+
+Abstract base class for providing custom headers for each request.
+
+Users can implement this interface to provide dynamic headers for various purposes
+such as authentication (OAuth tokens, API keys), request tracking (correlation IDs),
+custom metadata, or any other header-based requirements. The provider is called
+before each request to ensure fresh header values are always used.
+
+## Examples
+
+Simple JWT token provider:
+```typescript
+class JWTProvider extends HeaderProvider {
+  constructor(private token: string) {
+    super();
+  }
+
+  getHeaders(): Record<string, string> {
+    return { authorization: `Bearer ${this.token}` };
+  }
+}
+```
+
+Provider with request tracking:
+```typescript
+class RequestTrackingProvider extends HeaderProvider {
+  constructor(private sessionId: string) {
+    super();
+  }
+
+  getHeaders(): Record<string, string> {
+    return {
+      "X-Session-Id": this.sessionId,
+      "X-Request-Id": `req-${Date.now()}`
+    };
+  }
+}
+```
+
+## Extended by
+
+- [`StaticHeaderProvider`](StaticHeaderProvider.md)
+- [`OAuthHeaderProvider`](OAuthHeaderProvider.md)
+
+## Constructors
+
+### new HeaderProvider()
+
+```ts
+new HeaderProvider(): HeaderProvider
+```
+
+#### Returns
+
+[`HeaderProvider`](HeaderProvider.md)
+
+## Methods
+
+### getHeaders()
+
+```ts
+abstract getHeaders(): Record<string, string>
+```
+
+Get the latest headers to be added to requests.
+
+This method is called before each request to the remote LanceDB server.
+Implementations should return headers that will be merged with existing headers.
+
+#### Returns
+
+`Record`&lt;`string`, `string`&gt;
+
+Dictionary of header names to values to add to the request.
+
+#### Throws
+
+If unable to fetch headers, the exception will be propagated and the request will fail.

docs/src/js/classes/Index.md

@@ -194,6 +194,37 @@ currently is also a memory intensive operation.
 
 ***
 
+### ivfRq()
+
+```ts
+static ivfRq(options?): Index
+```
+
+Create an IvfRq index
+
+IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
+and organizes them into IVF partitions.
+
+The compression scheme is called RabitQ quantization. Each dimension is quantized into a small number of bits.
+The parameters `num_bits` and `num_partitions` control this process, providing a tradeoff
+between index size (and thus search speed) and index accuracy.
+
+The partitioning process is called IVF and the `num_partitions` parameter controls how
+many groups to create.
+
+Note that training an IVF RQ index on a large dataset is a slow operation and
+currently is also a memory intensive operation.
+
+#### Parameters
+
+* **options?**: `Partial`<[`IvfRqOptions`](../interfaces/IvfRqOptions.md)>
+
+#### Returns
+
+[`Index`](Index.md)
+
+***
+
 ### labelList()
 
 ```ts

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

docs/src/js/classes/NativeJsHeaderProvider.md

@@ -0,0 +1,29 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / NativeJsHeaderProvider
+
+# Class: NativeJsHeaderProvider
+
+JavaScript HeaderProvider implementation that wraps a JavaScript callback.
+This is the only native header provider - all header provider implementations
+should provide a JavaScript function that returns headers.
+
+## Constructors
+
+### new NativeJsHeaderProvider()
+
+```ts
+new NativeJsHeaderProvider(getHeadersCallback): NativeJsHeaderProvider
+```
+
+Create a new JsHeaderProvider from a JavaScript callback
+
+#### Parameters
+
+* **getHeadersCallback**
+
+#### Returns
+
+[`NativeJsHeaderProvider`](NativeJsHeaderProvider.md)

docs/src/js/classes/OAuthHeaderProvider.md

@@ -0,0 +1,108 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / OAuthHeaderProvider
+
+# Class: OAuthHeaderProvider
+
+Example implementation: OAuth token provider with automatic refresh.
+
+This is an example implementation showing how to manage OAuth tokens
+with automatic refresh when they expire.
+
+## Example
+
+```typescript
+async function fetchToken(): Promise<TokenResponse> {
+  const response = await fetch("https://oauth.example.com/token", {
+    method: "POST",
+    body: JSON.stringify({
+      grant_type: "client_credentials",
+      client_id: "your-client-id",
+      client_secret: "your-client-secret"
+    }),
+    headers: { "Content-Type": "application/json" }
+  });
+  const data = await response.json();
+  return {
+    accessToken: data.access_token,
+    expiresIn: data.expires_in
+  };
+}
+
+const provider = new OAuthHeaderProvider(fetchToken);
+const headers = provider.getHeaders();
+// Returns: {"authorization": "Bearer <your-token>"}
+```
+
+## Extends
+
+- [`HeaderProvider`](HeaderProvider.md)
+
+## Constructors
+
+### new OAuthHeaderProvider()
+
+```ts
+new OAuthHeaderProvider(tokenFetcher, refreshBufferSeconds): OAuthHeaderProvider
+```
+
+Initialize the OAuth provider.
+
+#### Parameters
+
+* **tokenFetcher**
+    Function to fetch new tokens. Should return object with 'accessToken' and optionally 'expiresIn'.
+
+* **refreshBufferSeconds**: `number` = `300`
+    Seconds before expiry to refresh token. Default 300 (5 minutes).
+
+#### Returns
+
+[`OAuthHeaderProvider`](OAuthHeaderProvider.md)
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`constructor`](HeaderProvider.md#constructors)
+
+## Methods
+
+### getHeaders()
+
+```ts
+getHeaders(): Record<string, string>
+```
+
+Get OAuth headers, refreshing token if needed.
+Note: This is synchronous for now as the Rust implementation expects sync.
+In a real implementation, this would need to handle async properly.
+
+#### Returns
+
+`Record`&lt;`string`, `string`&gt;
+
+Headers with Bearer token authorization.
+
+#### Throws
+
+If unable to fetch or refresh token.
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`getHeaders`](HeaderProvider.md#getheaders)
+
+***
+
+### refreshToken()
+
+```ts
+refreshToken(): Promise<void>
+```
+
+Manually refresh the token.
+Call this before using getHeaders() to ensure token is available.
+
+#### Returns
+
+`Promise`&lt;`void`&gt;

docs/src/js/classes/PermutationBuilder.md

@@ -0,0 +1,250 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / PermutationBuilder
+
+# Class: PermutationBuilder
+
+A PermutationBuilder for creating data permutations with splits, shuffling, and filtering.
+
+This class provides a TypeScript wrapper around the native Rust PermutationBuilder,
+offering methods to configure data splits, shuffling, and filtering before executing
+the permutation to create a new table.
+
+## Methods
+
+### execute()
+
+```ts
+execute(): Promise<Table>
+```
+
+Execute the permutation and create the destination table.
+
+#### Returns
+
+`Promise`&lt;[`Table`](Table.md)&gt;
+
+A Promise that resolves to the new Table instance
+
+#### Example
+
+```ts
+const permutationTable = await builder.execute();
+console.log(`Created table: ${permutationTable.name}`);
+```
+
+***
+
+### filter()
+
+```ts
+filter(filter): PermutationBuilder
+```
+
+Configure filtering for the permutation.
+
+#### Parameters
+
+* **filter**: `string`
+    SQL filter expression
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.filter("age > 18 AND status = 'active'");
+```
+
+***
+
+### persist()
+
+```ts
+persist(connection, tableName): PermutationBuilder
+```
+
+Configure the permutation to be persisted.
+
+#### Parameters
+
+* **connection**: [`Connection`](Connection.md)
+    The connection to persist the permutation to
+
+* **tableName**: `string`
+    The name of the table to create
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.persist(connection, "permutation_table");
+```
+
+***
+
+### shuffle()
+
+```ts
+shuffle(options): PermutationBuilder
+```
+
+Configure shuffling for the permutation.
+
+#### Parameters
+
+* **options**: [`ShuffleOptions`](../interfaces/ShuffleOptions.md)
+    Configuration for shuffling
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+// Basic shuffle
+builder.shuffle({ seed: 42 });
+
+// Shuffle with clump size
+builder.shuffle({ seed: 42, clumpSize: 10 });
+```
+
+***
+
+### splitCalculated()
+
+```ts
+splitCalculated(options): PermutationBuilder
+```
+
+Configure calculated splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitCalculatedOptions`](../interfaces/SplitCalculatedOptions.md)
+    Configuration for calculated splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.splitCalculated("user_id % 3");
+```
+
+***
+
+### splitHash()
+
+```ts
+splitHash(options): PermutationBuilder
+```
+
+Configure hash-based splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitHashOptions`](../interfaces/SplitHashOptions.md)
+    Configuration for hash-based splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+builder.splitHash({
+  columns: ["user_id"],
+  splitWeights: [70, 30],
+  discardWeight: 0
+});
+```
+
+***
+
+### splitRandom()
+
+```ts
+splitRandom(options): PermutationBuilder
+```
+
+Configure random splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitRandomOptions`](../interfaces/SplitRandomOptions.md)
+    Configuration for random splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+// Split by ratios
+builder.splitRandom({ ratios: [0.7, 0.3], seed: 42 });
+
+// Split by counts
+builder.splitRandom({ counts: [1000, 500], seed: 42 });
+
+// Split with fixed size
+builder.splitRandom({ fixed: 100, seed: 42 });
+```
+
+***
+
+### splitSequential()
+
+```ts
+splitSequential(options): PermutationBuilder
+```
+
+Configure sequential splits for the permutation.
+
+#### Parameters
+
+* **options**: [`SplitSequentialOptions`](../interfaces/SplitSequentialOptions.md)
+    Configuration for sequential splitting
+
+#### Returns
+
+[`PermutationBuilder`](PermutationBuilder.md)
+
+A new PermutationBuilder instance
+
+#### Example
+
+```ts
+// Split by ratios
+builder.splitSequential({ ratios: [0.8, 0.2] });
+
+// Split by counts
+builder.splitSequential({ counts: [800, 200] });
+
+// Split with fixed size
+builder.splitSequential({ fixed: 1000 });
+```

docs/src/js/classes/Query.md

@@ -80,7 +80,7 @@ AnalyzeExec verbose=true, metrics=[]
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -91,7 +91,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -343,6 +343,29 @@ This is useful for pagination.
 
 ***
 
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+#### Inherited from
+
+`StandardQueryBase.outputSchema`
+
+***
+
 ### select()
 
 ```ts

docs/src/js/classes/QueryBase.md

@@ -81,7 +81,7 @@ AnalyzeExec verbose=true, metrics=[]
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -92,7 +92,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -140,6 +140,25 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
 
 ***
 
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+***
+
 ### select()
 
 ```ts

docs/src/js/classes/RecordBatchIterator.md

@@ -1,43 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / RecordBatchIterator
-
-# Class: RecordBatchIterator
-
-## Implements
-
-- `AsyncIterator`<`RecordBatch`>
-
-## Constructors
-
-### new RecordBatchIterator()
-
-```ts
-new RecordBatchIterator(promise?): RecordBatchIterator
-```
-
-#### Parameters
-
-* **promise?**: `Promise`<`RecordBatchIterator`>
-
-#### Returns
-
-[`RecordBatchIterator`](RecordBatchIterator.md)
-
-## Methods
-
-### next()
-
-```ts
-next(): Promise<IteratorResult<RecordBatch<any>, any>>
-```
-
-#### Returns
-
-`Promise`&lt;`IteratorResult`&lt;`RecordBatch`&lt;`any`&gt;, `any`&gt;&gt;
-
-#### Implementation of
-
-`AsyncIterator.next`

docs/src/js/classes/StaticHeaderProvider.md

@@ -0,0 +1,70 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / StaticHeaderProvider
+
+# Class: StaticHeaderProvider
+
+Example implementation: A simple header provider that returns static headers.
+
+This is an example implementation showing how to create a HeaderProvider
+for cases where headers don't change during the session.
+
+## Example
+
+```typescript
+const provider = new StaticHeaderProvider({
+  authorization: "Bearer my-token",
+  "X-Custom-Header": "custom-value"
+});
+const headers = provider.getHeaders();
+// Returns: {authorization: 'Bearer my-token', 'X-Custom-Header': 'custom-value'}
+```
+
+## Extends
+
+- [`HeaderProvider`](HeaderProvider.md)
+
+## Constructors
+
+### new StaticHeaderProvider()
+
+```ts
+new StaticHeaderProvider(headers): StaticHeaderProvider
+```
+
+Initialize with static headers.
+
+#### Parameters
+
+* **headers**: `Record`<`string`, `string`>
+    Headers to return for every request.
+
+#### Returns
+
+[`StaticHeaderProvider`](StaticHeaderProvider.md)
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`constructor`](HeaderProvider.md#constructors)
+
+## Methods
+
+### getHeaders()
+
+```ts
+getHeaders(): Record<string, string>
+```
+
+Return the static headers.
+
+#### Returns
+
+`Record`&lt;`string`, `string`&gt;
+
+Copy of the static headers.
+
+#### Overrides
+
+[`HeaderProvider`](HeaderProvider.md).[`getHeaders`](HeaderProvider.md#getheaders)

docs/src/js/classes/TakeQuery.md

@@ -76,7 +76,7 @@ AnalyzeExec verbose=true, metrics=[]
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -87,7 +87,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -143,6 +143,29 @@ const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
 
 ***
 
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+#### Inherited from
+
+[`QueryBase`](QueryBase.md).[`outputSchema`](QueryBase.md#outputschema)
+
+***
+
 ### select()
 
 ```ts

docs/src/js/classes/VectorQuery.md

@@ -221,7 +221,7 @@ also increase the latency of your query. The default value is 1.5*limit.
 ### execute()
 
 ```ts
-protected execute(options?): RecordBatchIterator
+protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
 ```
 
 Execute the query and return the results as an
@@ -232,7 +232,7 @@ Execute the query and return the results as an
 
 #### Returns
 
-[`RecordBatchIterator`](RecordBatchIterator.md)
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
 
 #### See
 
@@ -498,6 +498,29 @@ This is useful for pagination.
 
 ***
 
+### outputSchema()
+
+```ts
+outputSchema(): Promise<Schema<any>>
+```
+
+Returns the schema of the output that will be returned by this query.
+
+This can be used to inspect the types and names of the columns that will be
+returned by the query before executing it.
+
+#### Returns
+
+`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
+
+An Arrow Schema describing the output columns.
+
+#### Inherited from
+
+`StandardQueryBase.outputSchema`
+
+***
+
 ### postfilter()
 
 ```ts

docs/src/js/functions/RecordBatchIterator.md

@@ -0,0 +1,19 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / RecordBatchIterator
+
+# Function: RecordBatchIterator()
+
+```ts
+function RecordBatchIterator(promisedInner): AsyncGenerator<RecordBatch<any>, void, unknown>
+```
+
+## Parameters
+
+* **promisedInner**: `Promise`&lt;`RecordBatchIterator`&gt;
+
+## Returns
+
+`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;

docs/src/js/functions/connect.md

@@ -6,13 +6,14 @@
 
 # Function: connect()
 
-## connect(uri, options, session)
+## connect(uri, options, session, headerProvider)
 
 ```ts
 function connect(
    uri,
    options?,
-   session?): Promise<Connection>
+   session?,
+   headerProvider?): Promise<Connection>
 ```
 
 Connect to a LanceDB instance at the given URI.
@@ -34,6 +35,8 @@ Accepted formats:
 
 * **session?**: [`Session`](../classes/Session.md)
 
+* **headerProvider?**: [`HeaderProvider`](../classes/HeaderProvider.md) \| () => `Record`&lt;`string`, `string`&gt; \| () => `Promise`&lt;`Record`&lt;`string`, `string`&gt;&gt;
+
 ### Returns
 
 `Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
@@ -55,6 +58,18 @@ const conn = await connect(
 });
 ```
 
+Using with a header provider for per-request authentication:
+```ts
+const provider = new StaticHeaderProvider({
+  "X-API-Key": "my-key"
+});
+const conn = await connectWithHeaderProvider(
+  "db://host:port",
+  options,
+  provider
+);
+```
+
 ## connect(options)
 
 ```ts

docs/src/js/functions/makeArrowTable.md

@@ -13,7 +13,7 @@ function makeArrowTable(
    metadata?): ArrowTable
 ```
 
-An enhanced version of the makeTable function from Apache Arrow
+An enhanced version of the apache-arrow makeTable function from Apache Arrow
 that supports nested fields and embeddings columns.
 
 (typically you do not need to call this function.  It will be called automatically

docs/src/js/functions/permutationBuilder.md

@@ -0,0 +1,34 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / permutationBuilder
+
+# Function: permutationBuilder()
+
+```ts
+function permutationBuilder(table): PermutationBuilder
+```
+
+Create a permutation builder for the given table.
+
+## Parameters
+
+* **table**: [`Table`](../classes/Table.md)
+    The source table to create a permutation from
+
+## Returns
+
+[`PermutationBuilder`](../classes/PermutationBuilder.md)
+
+A PermutationBuilder instance
+
+## Example
+
+```ts
+const builder = permutationBuilder(sourceTable, "training_data")
+  .splitRandom({ ratios: [0.8, 0.2], seed: 42 })
+  .shuffle({ seed: 123 });
+
+const trainingTable = await builder.execute();
+```

docs/src/js/globals.md

@@ -20,16 +20,20 @@
 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
 - [Connection](classes/Connection.md)
+- [HeaderProvider](classes/HeaderProvider.md)
 - [Index](classes/Index.md)
 - [MakeArrowTableOptions](classes/MakeArrowTableOptions.md)
 - [MatchQuery](classes/MatchQuery.md)
 - [MergeInsertBuilder](classes/MergeInsertBuilder.md)
 - [MultiMatchQuery](classes/MultiMatchQuery.md)
+- [NativeJsHeaderProvider](classes/NativeJsHeaderProvider.md)
+- [OAuthHeaderProvider](classes/OAuthHeaderProvider.md)
+- [PermutationBuilder](classes/PermutationBuilder.md)
 - [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
-- [RecordBatchIterator](classes/RecordBatchIterator.md)
 - [Session](classes/Session.md)
+- [StaticHeaderProvider](classes/StaticHeaderProvider.md)
 - [Table](classes/Table.md)
 - [TagContents](classes/TagContents.md)
 - [Tags](classes/Tags.md)
@@ -64,6 +68,7 @@
 - [IndexStatistics](interfaces/IndexStatistics.md)
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
+- [IvfRqOptions](interfaces/IvfRqOptions.md)
 - [MergeResult](interfaces/MergeResult.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
@@ -71,9 +76,16 @@
 - [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
 - [RemovalStats](interfaces/RemovalStats.md)
 - [RetryConfig](interfaces/RetryConfig.md)
+- [ShuffleOptions](interfaces/ShuffleOptions.md)
+- [SplitCalculatedOptions](interfaces/SplitCalculatedOptions.md)
+- [SplitHashOptions](interfaces/SplitHashOptions.md)
+- [SplitRandomOptions](interfaces/SplitRandomOptions.md)
+- [SplitSequentialOptions](interfaces/SplitSequentialOptions.md)
 - [TableNamesOptions](interfaces/TableNamesOptions.md)
 - [TableStatistics](interfaces/TableStatistics.md)
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
+- [TlsConfig](interfaces/TlsConfig.md)
+- [TokenResponse](interfaces/TokenResponse.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
@@ -93,6 +105,8 @@
 
 ## Functions
 
+- [RecordBatchIterator](functions/RecordBatchIterator.md)
 - [connect](functions/connect.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
+- [permutationBuilder](functions/permutationBuilder.md)

docs/src/js/interfaces/ClientConfig.md

@@ -16,6 +16,14 @@ optional extraHeaders: Record<string, string>;
 
 ***
 
+### idDelimiter?
+
+```ts
+optional idDelimiter: string;
+```
+
+***
+
 ### retryConfig?
 
 ```ts
@@ -32,6 +40,14 @@ optional timeoutConfig: TimeoutConfig;
 
 ***
 
+### tlsConfig?
+
+```ts
+optional tlsConfig: TlsConfig;
+```
+
+***
+
 ### userAgent?
 
 ```ts

docs/src/js/interfaces/IndexOptions.md

@@ -26,6 +26,18 @@ will be used to determine the most useful kind of index to create.
 
 ***
 
+### name?
+
+```ts
+optional name: string;
+```
+
+Optional custom name for the index.
+
+If not provided, a default name will be generated based on the column name.
+
+***
+
 ### replace?
 
 ```ts
@@ -42,8 +54,27 @@ The default is true
 
 ***
 
+### train?
+
+```ts
+optional train: boolean;
+```
+
+Whether to train the index with existing data.
+
+If true (default), the index will be trained with existing data in the table.
+If false, the index will be created empty and populated as new data is added.
+
+Note: This option is only supported for scalar indices. Vector indices always train.
+
+***
+
 ### waitTimeoutSeconds?
 
 ```ts
 optional waitTimeoutSeconds: number;
 ```
+
+Timeout in seconds to wait for index creation to complete.
+
+If not specified, the method will return immediately after starting the index creation.

docs/src/js/interfaces/IvfRqOptions.md

@@ -0,0 +1,101 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / IvfRqOptions
+
+# Interface: IvfRqOptions
+
+## Properties
+
+### distanceType?
+
+```ts
+optional distanceType: "l2" | "cosine" | "dot";
+```
+
+Distance type to use to build the index.
+
+Default value is "l2".
+
+This is used when training the index to calculate the IVF partitions
+(vectors are grouped in partitions with similar vectors according to this
+distance type) and during quantization.
+
+The distance type used to train an index MUST match the distance type used
+to search the index. Failure to do so will yield inaccurate results.
+
+The following distance types are available:
+
+"l2" - Euclidean distance.
+"cosine" - Cosine distance.
+"dot" - Dot product.
+
+***
+
+### maxIterations?
+
+```ts
+optional maxIterations: number;
+```
+
+Max iterations to train IVF kmeans.
+
+When training an IVF index we use kmeans to calculate the partitions. This parameter
+controls how many iterations of kmeans to run.
+
+The default value is 50.
+
+***
+
+### numBits?
+
+```ts
+optional numBits: number;
+```
+
+Number of bits per dimension for residual quantization.
+
+This value controls how much each residual component is compressed. The more
+bits, the more accurate the index will be but the slower search. Typical values
+are small integers; the default is 1 bit per dimension.
+
+***
+
+### numPartitions?
+
+```ts
+optional numPartitions: number;
+```
+
+The number of IVF partitions to create.
+
+This value should generally scale with the number of rows in the dataset.
+By default the number of partitions is the square root of the number of
+rows.
+
+If this value is too large then the first part of the search (picking the
+right partition) will be slow. If this value is too small then the second
+part of the search (searching within a partition) will be slow.
+
+***
+
+### sampleRate?
+
+```ts
+optional sampleRate: number;
+```
+
+The number of vectors, per partition, to sample when training IVF kmeans.
+
+When an IVF index is trained, we need to calculate partitions. These are groups
+of vectors that are similar to each other. To do this we use an algorithm called kmeans.
+
+Running kmeans on a large dataset can be slow. To speed this up we run kmeans on a
+random sample of the data. This parameter controls the size of the sample. The total
+number of vectors used to train the index is `sample_rate * num_partitions`.
+
+Increasing this value might improve the quality of the index but in most cases the
+default should be sufficient.
+
+The default value is 256.

docs/src/js/interfaces/ShuffleOptions.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / ShuffleOptions
+
+# Interface: ShuffleOptions
+
+## Properties
+
+### clumpSize?
+
+```ts
+optional clumpSize: number;
+```
+
+***
+
+### seed?
+
+```ts
+optional seed: number;
+```

docs/src/js/interfaces/SplitCalculatedOptions.md

@@ -0,0 +1,23 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitCalculatedOptions
+
+# Interface: SplitCalculatedOptions
+
+## Properties
+
+### calculation
+
+```ts
+calculation: string;
+```
+
+***
+
+### splitNames?
+
+```ts
+optional splitNames: string[];
+```

docs/src/js/interfaces/SplitHashOptions.md

@@ -0,0 +1,39 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitHashOptions
+
+# Interface: SplitHashOptions
+
+## Properties
+
+### columns
+
+```ts
+columns: string[];
+```
+
+***
+
+### discardWeight?
+
+```ts
+optional discardWeight: number;
+```
+
+***
+
+### splitNames?
+
+```ts
+optional splitNames: string[];
+```
+
+***
+
+### splitWeights
+
+```ts
+splitWeights: number[];
+```

docs/src/js/interfaces/SplitRandomOptions.md

@@ -0,0 +1,47 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitRandomOptions
+
+# Interface: SplitRandomOptions
+
+## Properties
+
+### counts?
+
+```ts
+optional counts: number[];
+```
+
+***
+
+### fixed?
+
+```ts
+optional fixed: number;
+```
+
+***
+
+### ratios?
+
+```ts
+optional ratios: number[];
+```
+
+***
+
+### seed?
+
+```ts
+optional seed: number;
+```
+
+***
+
+### splitNames?
+
+```ts
+optional splitNames: string[];
+```

docs/src/js/interfaces/SplitSequentialOptions.md

@@ -0,0 +1,39 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / SplitSequentialOptions
+
+# Interface: SplitSequentialOptions
+
+## Properties
+
+### counts?
+
+```ts
+optional counts: number[];
+```
+
+***
+
+### fixed?
+
+```ts
+optional fixed: number;
+```
+
+***
+
+### ratios?
+
+```ts
+optional ratios: number[];
+```
+
+***
+
+### splitNames?
+
+```ts
+optional splitNames: string[];
+```

docs/src/js/interfaces/TlsConfig.md

@@ -0,0 +1,49 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TlsConfig
+
+# Interface: TlsConfig
+
+TLS/mTLS configuration for the remote HTTP client.
+
+## Properties
+
+### assertHostname?
+
+```ts
+optional assertHostname: boolean;
+```
+
+Whether to verify the hostname in the server's certificate.
+
+***
+
+### certFile?
+
+```ts
+optional certFile: string;
+```
+
+Path to the client certificate file (PEM format) for mTLS authentication.
+
+***
+
+### keyFile?
+
+```ts
+optional keyFile: string;
+```
+
+Path to the client private key file (PEM format) for mTLS authentication.
+
+***
+
+### sslCaCert?
+
+```ts
+optional sslCaCert: string;
+```
+
+Path to the CA certificate file (PEM format) for server verification.

docs/src/js/interfaces/TokenResponse.md

@@ -0,0 +1,25 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / TokenResponse
+
+# Interface: TokenResponse
+
+Token response from OAuth provider.
+
+## Properties
+
+### accessToken
+
+```ts
+accessToken: string;
+```
+
+***
+
+### expiresIn?
+
+```ts
+optional expiresIn: number;
+```

java/core/lancedb-jni/Cargo.toml

@@ -15,7 +15,7 @@ publish = false
 crate-type = ["cdylib"]
 
 [dependencies]
-lancedb = { path = "../../../rust/lancedb" }
+lancedb = { path = "../../../rust/lancedb", default-features = false }
 lance = { workspace = true }
 arrow = { workspace = true, features = ["ffi"] }
 arrow-schema.workspace = true
@@ -25,3 +25,6 @@ snafu.workspace = true
 lazy_static.workspace = true
 serde = { version = "^1" }
 serde_json = { version = "1" }
+
+[features]
+default = ["lancedb/default"]

java/core/lancedb-jni/src/error.rs

@@ -51,8 +51,11 @@ pub enum Error {
     DatasetAlreadyExists { uri: String, location: Location },
     #[snafu(display("Table '{name}' already exists"))]
     TableAlreadyExists { name: String },
-    #[snafu(display("Table '{name}' was not found"))]
+    #[snafu(display("Table '{name}' was not found: {source}"))]
-    TableNotFound { name: String },
+    TableNotFound {
+        name: String,
+        source: Box<dyn std::error::Error + Send + Sync>,
+    },
     #[snafu(display("Invalid table name '{name}': {reason}"))]
     InvalidTableName { name: String, reason: String },
     #[snafu(display("Embedding function '{name}' was not found: {reason}, {location}"))]
@@ -191,7 +194,7 @@ impl From<lancedb::Error> for Error {
                 message,
                 location: std::panic::Location::caller().to_snafu_location(),
             },
-            lancedb::Error::TableNotFound { name } => Self::TableNotFound { name },
+            lancedb::Error::TableNotFound { name, source } => Self::TableNotFound { name, source },
             lancedb::Error::TableAlreadyExists { name } => Self::TableAlreadyExists { name },
             lancedb::Error::EmbeddingFunctionNotFound { name, reason } => {
                 Self::EmbeddingFunctionNotFound {

java/core/lancedb-jni/src/ffi.rs

@@ -16,6 +16,7 @@ pub trait JNIEnvExt {
     fn get_integers(&mut self, obj: &JObject) -> Result<Vec<i32>>;
 
     /// Get strings from Java List<String> object.
+    #[allow(dead_code)]
     fn get_strings(&mut self, obj: &JObject) -> Result<Vec<String>>;
 
     /// Get strings from Java String[] object.

java/core/lancedb-jni/src/traits.rs

@@ -6,6 +6,7 @@ use jni::JNIEnv;
 
 use crate::Result;
 
+#[allow(dead_code)]
 pub trait FromJObject<T> {
     fn extract(&self) -> Result<T>;
 }
@@ -39,6 +40,7 @@ impl FromJObject<f64> for JObject<'_> {
     }
 }
 
+#[allow(dead_code)]
 pub trait FromJString {
     fn extract(&self, env: &mut JNIEnv) -> Result<String>;
 }
@@ -66,6 +68,7 @@ pub trait JMapExt {
     fn get_f64(&self, env: &mut JNIEnv, key: &str) -> Result<Option<f64>>;
 }
 
+#[allow(dead_code)]
 fn get_map_value<T>(env: &mut JNIEnv, map: &JMap, key: &str) -> Result<Option<T>>
 where
     for<'a> JObject<'a>: FromJObject<T>,

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.21.2-final.0</version>
+        <version>0.22.3-beta.5</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>0.21.2-final.0</version>
+        <version>0.22.3-beta.5</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.21.2-final.0</version>
+    <version>0.22.3-beta.5</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/AGENTS.md

@@ -0,0 +1,13 @@
+These are the typescript bindings of LanceDB.
+The core Rust library is in the `../rust/lancedb` directory, the rust binding
+code is in the `src/` directory and the typescript bindings are in
+the `lancedb/` directory.
+
+Whenever you change the Rust code, you will need to recompile: `npm run build`.
+
+Common commands:
+* Build: `npm run build`
+* Lint: `npm run lint`
+* Fix lints: `npm run lint-fix`
+* Test: `npm test`
+* Run single test file: `npm test __test__/arrow.test.ts`

nodejs/CLAUDE.md

@@ -1,13 +0,0 @@
-These are the typescript bindings of LanceDB.
-The core Rust library is in the `../rust/lancedb` directory, the rust binding
-code is in the `src/` directory and the typescript bindings are in
-the `lancedb/` directory.
-
-Whenever you change the Rust code, you will need to recompile: `npm run build`.
-
-Common commands:
-* Build: `npm run build`
-* Lint: `npm run lint`
-* Fix lints: `npm run lint-fix`
-* Test: `npm test`
-* Run single test file: `npm test __test__/arrow.test.ts`

nodejs/CLAUDE.md

@@ -0,0 +1 @@
+AGENTS.md

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.21.2"
+version = "0.22.3-beta.5"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -18,7 +18,7 @@ arrow-array.workspace = true
 arrow-schema.workspace = true
 env_logger.workspace = true
 futures.workspace = true
-lancedb = { path = "../rust/lancedb" }
+lancedb = { path = "../rust/lancedb", default-features = false }
 napi = { version = "2.16.8", default-features = false, features = [
     "napi9",
     "async"
@@ -36,6 +36,6 @@ aws-lc-rs = "=1.13.0"
 napi-build = "2.1"
 
 [features]
-default = ["remote"]
+default = ["remote", "lancedb/default"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]

nodejs/__test__/arrow.test.ts

@@ -1,17 +1,5 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  Bool,
-  Field,
-  Int32,
-  List,
-  Schema,
-  Struct,
-  Uint8,
-  Utf8,
-} from "apache-arrow";
-
 import * as arrow15 from "apache-arrow-15";
 import * as arrow16 from "apache-arrow-16";
 import * as arrow17 from "apache-arrow-17";
@@ -25,11 +13,9 @@ import {
   fromTableToBuffer,
   makeArrowTable,
   makeEmptyTable,
-  tableFromIPC,
 } from "../lancedb/arrow";
 import {
   EmbeddingFunction,
-  FieldOptions,
   FunctionOptions,
 } from "../lancedb/embedding/embedding_function";
 import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
@@ -1008,5 +994,64 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         expect(result).toEqual(null);
       });
     });
+
+    describe("boolean null handling", function () {
+      it("should handle null values in nullable boolean fields", () => {
+        const { makeArrowTable } = require("../lancedb/arrow");
+        const schema = new Schema([new Field("test", new arrow.Bool(), true)]);
+
+        // Test with all null values
+        const data = [{ test: null }];
+        const table = makeArrowTable(data, { schema });
+
+        expect(table.numRows).toBe(1);
+        expect(table.schema.names).toEqual(["test"]);
+        expect(table.getChild("test")!.get(0)).toBeNull();
+      });
+
+      it("should handle mixed null and non-null boolean values", () => {
+        const { makeArrowTable } = require("../lancedb/arrow");
+        const schema = new Schema([new Field("test", new Bool(), true)]);
+
+        // Test with mixed values
+        const data = [{ test: true }, { test: null }, { test: false }];
+        const table = makeArrowTable(data, { schema });
+
+        expect(table.numRows).toBe(3);
+        expect(table.getChild("test")!.get(0)).toBe(true);
+        expect(table.getChild("test")!.get(1)).toBeNull();
+        expect(table.getChild("test")!.get(2)).toBe(false);
+      });
+    });
+
+    // Test for the undefined values bug fix
+    describe("undefined values handling", () => {
+      it("should handle mixed undefined and actual values", () => {
+        const schema = new Schema([
+          new Field("text", new Utf8(), true), // nullable
+          new Field("number", new Int32(), true), // nullable
+          new Field("bool", new Bool(), true), // nullable
+        ]);
+
+        const data = [
+          { text: undefined, number: 42, bool: true },
+          { text: "hello", number: undefined, bool: false },
+          { text: "world", number: 123, bool: undefined },
+        ];
+        const table = makeArrowTable(data, { schema });
+
+        const result = table.toArray();
+        expect(result).toHaveLength(3);
+        expect(result[0].text).toBe(null);
+        expect(result[0].number).toBe(42);
+        expect(result[0].bool).toBe(true);
+        expect(result[1].text).toBe("hello");
+        expect(result[1].number).toBe(null);
+        expect(result[1].bool).toBe(false);
+        expect(result[2].text).toBe("world");
+        expect(result[2].number).toBe(123);
+        expect(result[2].bool).toBe(null);
+      });
+    });
   },
 );

nodejs/__test__/connection.test.ts

@@ -203,3 +203,106 @@ describe("given a connection", () => {
     });
   });
 });
+
+describe("clone table functionality", () => {
+  let tmpDir: tmp.DirResult;
+  let db: Connection;
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    db = await connect(tmpDir.name);
+  });
+  afterEach(() => tmpDir.removeCallback());
+
+  it("should clone a table with latest version (default behavior)", async () => {
+    // Create source table with some data
+    const data = [
+      { id: 1, text: "hello", vector: [1.0, 2.0] },
+      { id: 2, text: "world", vector: [3.0, 4.0] },
+    ];
+    const sourceTable = await db.createTable("source", data);
+
+    // Add more data to create a new version
+    const moreData = [{ id: 3, text: "test", vector: [5.0, 6.0] }];
+    await sourceTable.add(moreData);
+
+    // Clone the table (should get latest version with 3 rows)
+    const sourceUri = `${tmpDir.name}/source.lance`;
+    const clonedTable = await db.cloneTable("cloned", sourceUri);
+
+    // Verify cloned table has all 3 rows
+    expect(await clonedTable.countRows()).toBe(3);
+    expect((await db.tableNames()).includes("cloned")).toBe(true);
+  });
+
+  it("should clone a table from a specific version", async () => {
+    // Create source table with initial data
+    const data = [
+      { id: 1, text: "hello", vector: [1.0, 2.0] },
+      { id: 2, text: "world", vector: [3.0, 4.0] },
+    ];
+    const sourceTable = await db.createTable("source", data);
+
+    // Get the initial version
+    const initialVersion = await sourceTable.version();
+
+    // Add more data to create a new version
+    const moreData = [{ id: 3, text: "test", vector: [5.0, 6.0] }];
+    await sourceTable.add(moreData);
+
+    // Verify source now has 3 rows
+    expect(await sourceTable.countRows()).toBe(3);
+
+    // Clone from the initial version (should have only 2 rows)
+    const sourceUri = `${tmpDir.name}/source.lance`;
+    const clonedTable = await db.cloneTable("cloned", sourceUri, {
+      sourceVersion: initialVersion,
+    });
+
+    // Verify cloned table has only the initial 2 rows
+    expect(await clonedTable.countRows()).toBe(2);
+  });
+
+  it("should clone a table from a tagged version", async () => {
+    // Create source table with initial data
+    const data = [
+      { id: 1, text: "hello", vector: [1.0, 2.0] },
+      { id: 2, text: "world", vector: [3.0, 4.0] },
+    ];
+    const sourceTable = await db.createTable("source", data);
+
+    // Create a tag for the current version
+    const tags = await sourceTable.tags();
+    await tags.create("v1.0", await sourceTable.version());
+
+    // Add more data after the tag
+    const moreData = [{ id: 3, text: "test", vector: [5.0, 6.0] }];
+    await sourceTable.add(moreData);
+
+    // Verify source now has 3 rows
+    expect(await sourceTable.countRows()).toBe(3);
+
+    // Clone from the tagged version (should have only 2 rows)
+    const sourceUri = `${tmpDir.name}/source.lance`;
+    const clonedTable = await db.cloneTable("cloned", sourceUri, {
+      sourceTag: "v1.0",
+    });
+
+    // Verify cloned table has only the tagged version's 2 rows
+    expect(await clonedTable.countRows()).toBe(2);
+  });
+
+  it("should fail when attempting deep clone", async () => {
+    // Create source table with some data
+    const data = [
+      { id: 1, text: "hello", vector: [1.0, 2.0] },
+      { id: 2, text: "world", vector: [3.0, 4.0] },
+    ];
+    await db.createTable("source", data);
+
+    // Try to create a deep clone (should fail)
+    const sourceUri = `${tmpDir.name}/source.lance`;
+    await expect(
+      db.cloneTable("cloned", sourceUri, { isShallow: false }),
+    ).rejects.toThrow("Deep clone is not yet implemented");
+  });
+});

nodejs/__test__/embedding.test.ts

@@ -256,6 +256,60 @@ describe("embedding functions", () => {
     expect(actual).toHaveProperty("text");
   });
 
+  it("should handle undefined vector field with embedding function correctly", async () => {
+    @register("undefined_test")
+    class MockEmbeddingFunction extends EmbeddingFunction<string> {
+      ndims() {
+        return 3;
+      }
+      embeddingDataType(): Float {
+        return new Float32();
+      }
+      async computeQueryEmbeddings(_data: string) {
+        return [1, 2, 3];
+      }
+      async computeSourceEmbeddings(data: string[]) {
+        return Array.from({ length: data.length }).fill([
+          1, 2, 3,
+        ]) as number[][];
+      }
+    }
+    const func = getRegistry()
+      .get<MockEmbeddingFunction>("undefined_test")!
+      .create();
+    const schema = new Schema([
+      new Field("text", new Utf8(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(3, new Field("item", new Float32(), true)),
+        true,
+      ),
+    ]);
+
+    const db = await connect(tmpDir.name);
+    const table = await db.createEmptyTable("test_undefined", schema, {
+      embeddingFunction: {
+        function: func,
+        sourceColumn: "text",
+        vectorColumn: "vector",
+      },
+    });
+
+    // Test that undefined, null, and omitted vector fields all work
+    await table.add([{ text: "test1", vector: undefined }]);
+    await table.add([{ text: "test2", vector: null }]);
+    await table.add([{ text: "test3" }]);
+
+    const rows = await table.query().toArray();
+    expect(rows.length).toBe(3);
+
+    // All rows should have vectors computed by the embedding function
+    for (const row of rows) {
+      expect(row.vector).toBeDefined();
+      expect(JSON.parse(JSON.stringify(row.vector))).toEqual([1, 2, 3]);
+    }
+  });
+
   test.each([new Float16(), new Float32(), new Float64()])(
     "should be able to provide manual embeddings with multiple float datatype",
     async (floatType) => {

nodejs/__test__/permutation.test.ts

@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import * as tmp from "tmp";
+import { Table, connect, permutationBuilder } from "../lancedb";
+import { makeArrowTable } from "../lancedb/arrow";
+
+describe("PermutationBuilder", () => {
+  let tmpDir: tmp.DirResult;
+  let table: Table;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    const db = await connect(tmpDir.name);
+
+    // Create test data
+    const data = makeArrowTable(
+      [
+        { id: 1, value: 10 },
+        { id: 2, value: 20 },
+        { id: 3, value: 30 },
+        { id: 4, value: 40 },
+        { id: 5, value: 50 },
+        { id: 6, value: 60 },
+        { id: 7, value: 70 },
+        { id: 8, value: 80 },
+        { id: 9, value: 90 },
+        { id: 10, value: 100 },
+      ],
+      { vectorColumns: {} },
+    );
+
+    table = await db.createTable("test_table", data);
+  });
+
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  test("should create permutation builder", () => {
+    const builder = permutationBuilder(table);
+    expect(builder).toBeDefined();
+  });
+
+  test("should execute basic permutation", async () => {
+    const builder = permutationBuilder(table);
+    const permutationTable = await builder.execute();
+
+    expect(permutationTable).toBeDefined();
+
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+  });
+
+  test("should create permutation with random splits", async () => {
+    const builder = permutationBuilder(table).splitRandom({
+      ratios: [1.0],
+      seed: 42,
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+  });
+
+  test("should create permutation with percentage splits", async () => {
+    const builder = permutationBuilder(table).splitRandom({
+      ratios: [0.3, 0.7],
+      seed: 42,
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Check split distribution
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+  });
+
+  test("should create permutation with count splits", async () => {
+    const builder = permutationBuilder(table).splitRandom({
+      counts: [3, 7],
+      seed: 42,
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Check split distribution
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBe(3);
+    expect(split1Count).toBe(7);
+  });
+
+  test("should create permutation with hash splits", async () => {
+    const builder = permutationBuilder(table).splitHash({
+      columns: ["id"],
+      splitWeights: [50, 50],
+      discardWeight: 0,
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Check that splits exist
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+  });
+
+  test("should create permutation with sequential splits", async () => {
+    const builder = permutationBuilder(table).splitSequential({
+      ratios: [0.5, 0.5],
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Check split distribution - sequential should give exactly 5 and 5
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBe(5);
+    expect(split1Count).toBe(5);
+  });
+
+  test("should create permutation with calculated splits", async () => {
+    const builder = permutationBuilder(table).splitCalculated({
+      calculation: "id % 2",
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Check split distribution
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+  });
+
+  test("should create permutation with shuffle", async () => {
+    const builder = permutationBuilder(table).shuffle({
+      seed: 42,
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+  });
+
+  test("should create permutation with shuffle and clump size", async () => {
+    const builder = permutationBuilder(table).shuffle({
+      seed: 42,
+      clumpSize: 2,
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+  });
+
+  test("should create permutation with filter", async () => {
+    const builder = permutationBuilder(table).filter("value > 50");
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(5); // Values 60, 70, 80, 90, 100
+  });
+
+  test("should chain multiple operations", async () => {
+    const builder = permutationBuilder(table)
+      .filter("value <= 80")
+      .splitRandom({ ratios: [0.5, 0.5], seed: 42 })
+      .shuffle({ seed: 123 });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(8); // Values 10, 20, 30, 40, 50, 60, 70, 80
+
+    // Check split distribution
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(8);
+  });
+
+  test("should throw error for invalid split arguments", () => {
+    const builder = permutationBuilder(table);
+
+    // Test no arguments provided
+    expect(() => builder.splitRandom({})).toThrow(
+      "Exactly one of 'ratios', 'counts', or 'fixed' must be provided",
+    );
+
+    // Test multiple arguments provided
+    expect(() =>
+      builder.splitRandom({ ratios: [0.5, 0.5], counts: [3, 7], seed: 42 }),
+    ).toThrow("Exactly one of 'ratios', 'counts', or 'fixed' must be provided");
+  });
+
+  test("should throw error when builder is consumed", async () => {
+    const builder = permutationBuilder(table);
+
+    // Execute once
+    await builder.execute();
+
+    // Should throw error on second execution
+    await expect(builder.execute()).rejects.toThrow("Builder already consumed");
+  });
+
+  test("should accept custom split names with random splits", async () => {
+    const builder = permutationBuilder(table).splitRandom({
+      ratios: [0.3, 0.7],
+      seed: 42,
+      splitNames: ["train", "test"],
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Split names are provided but split_id is still numeric (0, 1, etc.)
+    // The names are metadata that can be used by higher-level APIs
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+  });
+
+  test("should accept custom split names with hash splits", async () => {
+    const builder = permutationBuilder(table).splitHash({
+      columns: ["id"],
+      splitWeights: [50, 50],
+      discardWeight: 0,
+      splitNames: ["set_a", "set_b"],
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Split names are provided but split_id is still numeric
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+  });
+
+  test("should accept custom split names with sequential splits", async () => {
+    const builder = permutationBuilder(table).splitSequential({
+      ratios: [0.5, 0.5],
+      splitNames: ["first", "second"],
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Split names are provided but split_id is still numeric
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBe(5);
+    expect(split1Count).toBe(5);
+  });
+
+  test("should accept custom split names with calculated splits", async () => {
+    const builder = permutationBuilder(table).splitCalculated({
+      calculation: "id % 2",
+      splitNames: ["even", "odd"],
+    });
+
+    const permutationTable = await builder.execute();
+    const rowCount = await permutationTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Split names are provided but split_id is still numeric
+    const split0Count = await permutationTable.countRows("split_id = 0");
+    const split1Count = await permutationTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+  });
+
+  test("should persist permutation to a new table", async () => {
+    const db = await connect(tmpDir.name);
+    const builder = permutationBuilder(table)
+      .splitRandom({
+        ratios: [0.7, 0.3],
+        seed: 42,
+        splitNames: ["train", "validation"],
+      })
+      .persist(db, "my_permutation");
+
+    // Execute the builder which will persist the table
+    const permutationTable = await builder.execute();
+
+    // Verify the persisted table exists and can be opened
+    const persistedTable = await db.openTable("my_permutation");
+    expect(persistedTable).toBeDefined();
+
+    // Verify the persisted table has the correct number of rows
+    const rowCount = await persistedTable.countRows();
+    expect(rowCount).toBe(10);
+
+    // Verify splits exist (numeric split_id values)
+    const split0Count = await persistedTable.countRows("split_id = 0");
+    const split1Count = await persistedTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(10);
+
+    // Verify the table returned by execute is the same as the persisted one
+    const executedRowCount = await permutationTable.countRows();
+    expect(executedRowCount).toBe(10);
+  });
+
+  test("should persist permutation with multiple operations", async () => {
+    const db = await connect(tmpDir.name);
+    const builder = permutationBuilder(table)
+      .filter("value > 30")
+      .splitRandom({ ratios: [0.5, 0.5], seed: 123, splitNames: ["a", "b"] })
+      .shuffle({ seed: 456 })
+      .persist(db, "filtered_permutation");
+
+    // Execute the builder
+    const permutationTable = await builder.execute();
+
+    // Verify the persisted table
+    const persistedTable = await db.openTable("filtered_permutation");
+    const rowCount = await persistedTable.countRows();
+    expect(rowCount).toBe(7); // Values 40, 50, 60, 70, 80, 90, 100
+
+    // Verify splits exist (numeric split_id values)
+    const split0Count = await persistedTable.countRows("split_id = 0");
+    const split1Count = await persistedTable.countRows("split_id = 1");
+
+    expect(split0Count).toBeGreaterThan(0);
+    expect(split1Count).toBeGreaterThan(0);
+    expect(split0Count + split1Count).toBe(7);
+
+    // Verify the executed table matches
+    const executedRowCount = await permutationTable.countRows();
+    expect(executedRowCount).toBe(7);
+  });
+});

nodejs/__test__/query.test.ts

@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import * as tmp from "tmp";
+
+import { type Table, connect } from "../lancedb";
+import {
+  Field,
+  FixedSizeList,
+  Float32,
+  Int64,
+  Schema,
+  Utf8,
+  makeArrowTable,
+} from "../lancedb/arrow";
+import { Index } from "../lancedb/indices";
+
+describe("Query outputSchema", () => {
+  let tmpDir: tmp.DirResult;
+  let table: Table;
+
+  beforeEach(async () => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    const db = await connect(tmpDir.name);
+
+    // Create table with explicit schema to ensure proper types
+    const schema = new Schema([
+      new Field("a", new Int64(), true),
+      new Field("text", new Utf8(), true),
+      new Field(
+        "vec",
+        new FixedSizeList(2, new Field("item", new Float32())),
+        true,
+      ),
+    ]);
+
+    const data = makeArrowTable(
+      [
+        { a: 1n, text: "foo", vec: [1, 2] },
+        { a: 2n, text: "bar", vec: [3, 4] },
+        { a: 3n, text: "baz", vec: [5, 6] },
+      ],
+      { schema },
+    );
+    table = await db.createTable("test", data);
+  });
+
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  it("should return schema for plain query", async () => {
+    const schema = await table.query().outputSchema();
+
+    expect(schema.fields.length).toBe(3);
+    expect(schema.fields.map((f) => f.name)).toEqual(["a", "text", "vec"]);
+    expect(schema.fields[0].type.toString()).toBe("Int64");
+    expect(schema.fields[1].type.toString()).toBe("Utf8");
+  });
+
+  it("should return schema with dynamic projection", async () => {
+    const schema = await table.query().select({ bl: "a * 2" }).outputSchema();
+
+    expect(schema.fields.length).toBe(1);
+    expect(schema.fields[0].name).toBe("bl");
+    expect(schema.fields[0].type.toString()).toBe("Int64");
+  });
+
+  it("should return schema for vector search with _distance column", async () => {
+    const schema = await table
+      .vectorSearch([1, 2])
+      .select(["a"])
+      .outputSchema();
+
+    expect(schema.fields.length).toBe(2);
+    expect(schema.fields.map((f) => f.name)).toEqual(["a", "_distance"]);
+    expect(schema.fields[0].type.toString()).toBe("Int64");
+    expect(schema.fields[1].type.toString()).toBe("Float32");
+  });
+
+  it("should return schema for FTS search", async () => {
+    await table.createIndex("text", { config: Index.fts() });
+
+    const schema = await table
+      .search("foo", "fts")
+      .select(["a"])
+      .outputSchema();
+
+    // FTS search includes _score column in addition to selected columns
+    expect(schema.fields.length).toBe(2);
+    expect(schema.fields.map((f) => f.name)).toContain("a");
+    expect(schema.fields.map((f) => f.name)).toContain("_score");
+    const aField = schema.fields.find((f) => f.name === "a");
+    expect(aField?.type.toString()).toBe("Int64");
+  });
+
+  it("should return schema for take query", async () => {
+    const schema = await table.takeOffsets([0]).select(["text"]).outputSchema();
+
+    expect(schema.fields.length).toBe(1);
+    expect(schema.fields[0].name).toBe("text");
+    expect(schema.fields[0].type.toString()).toBe("Utf8");
+  });
+
+  it("should return full schema when no select is specified", async () => {
+    const schema = await table.query().outputSchema();
+
+    // Should return all columns
+    expect(schema.fields.length).toBe(3);
+  });
+});

nodejs/__test__/remote.test.ts

@@ -3,7 +3,49 @@
 
 import * as http from "http";
 import { RequestListener } from "http";
-import { Connection, ConnectionOptions, connect } from "../lancedb";
+import {
+  ClientConfig,
+  Connection,
+  ConnectionOptions,
+  TlsConfig,
+  connect,
+} from "../lancedb";
+import {
+  HeaderProvider,
+  OAuthHeaderProvider,
+  StaticHeaderProvider,
+} from "../lancedb/header";
+
+// Test-only header providers
+class CustomProvider extends HeaderProvider {
+  getHeaders(): Record<string, string> {
+    return { "X-Custom": "custom-value" };
+  }
+}
+
+class ErrorProvider extends HeaderProvider {
+  private errorMessage: string;
+  public callCount: number = 0;
+
+  constructor(errorMessage: string = "Test error") {
+    super();
+    this.errorMessage = errorMessage;
+  }
+
+  getHeaders(): Record<string, string> {
+    this.callCount++;
+    throw new Error(this.errorMessage);
+  }
+}
+
+class ConcurrentProvider extends HeaderProvider {
+  private counter: number = 0;
+
+  getHeaders(): Record<string, string> {
+    this.counter++;
+    return { "X-Request-Id": String(this.counter) };
+  }
+}
 
 async function withMockDatabase(
   listener: RequestListener,
@@ -148,4 +190,431 @@ describe("remote connection", () => {
       },
     );
   });
+
+  describe("TlsConfig", () => {
+    it("should create TlsConfig with all fields", () => {
+      const tlsConfig: TlsConfig = {
+        certFile: "/path/to/cert.pem",
+        keyFile: "/path/to/key.pem",
+        sslCaCert: "/path/to/ca.pem",
+        assertHostname: false,
+      };
+
+      expect(tlsConfig.certFile).toBe("/path/to/cert.pem");
+      expect(tlsConfig.keyFile).toBe("/path/to/key.pem");
+      expect(tlsConfig.sslCaCert).toBe("/path/to/ca.pem");
+      expect(tlsConfig.assertHostname).toBe(false);
+    });
+
+    it("should create TlsConfig with partial fields", () => {
+      const tlsConfig: TlsConfig = {
+        certFile: "/path/to/cert.pem",
+        keyFile: "/path/to/key.pem",
+      };
+
+      expect(tlsConfig.certFile).toBe("/path/to/cert.pem");
+      expect(tlsConfig.keyFile).toBe("/path/to/key.pem");
+      expect(tlsConfig.sslCaCert).toBeUndefined();
+      expect(tlsConfig.assertHostname).toBeUndefined();
+    });
+
+    it("should create ClientConfig with TlsConfig", () => {
+      const tlsConfig: TlsConfig = {
+        certFile: "/path/to/cert.pem",
+        keyFile: "/path/to/key.pem",
+        sslCaCert: "/path/to/ca.pem",
+        assertHostname: true,
+      };
+
+      const clientConfig: ClientConfig = {
+        userAgent: "test-agent",
+        tlsConfig: tlsConfig,
+      };
+
+      expect(clientConfig.userAgent).toBe("test-agent");
+      expect(clientConfig.tlsConfig).toBeDefined();
+      expect(clientConfig.tlsConfig?.certFile).toBe("/path/to/cert.pem");
+      expect(clientConfig.tlsConfig?.keyFile).toBe("/path/to/key.pem");
+      expect(clientConfig.tlsConfig?.sslCaCert).toBe("/path/to/ca.pem");
+      expect(clientConfig.tlsConfig?.assertHostname).toBe(true);
+    });
+
+    it("should handle empty TlsConfig", () => {
+      const tlsConfig: TlsConfig = {};
+
+      expect(tlsConfig.certFile).toBeUndefined();
+      expect(tlsConfig.keyFile).toBeUndefined();
+      expect(tlsConfig.sslCaCert).toBeUndefined();
+      expect(tlsConfig.assertHostname).toBeUndefined();
+    });
+
+    it("should accept TlsConfig in connection options", () => {
+      const tlsConfig: TlsConfig = {
+        certFile: "/path/to/cert.pem",
+        keyFile: "/path/to/key.pem",
+        sslCaCert: "/path/to/ca.pem",
+        assertHostname: false,
+      };
+
+      // Just verify that the ClientConfig accepts the TlsConfig
+      const clientConfig: ClientConfig = {
+        tlsConfig: tlsConfig,
+      };
+
+      const connectionOptions: ConnectionOptions = {
+        apiKey: "fake",
+        clientConfig: clientConfig,
+      };
+
+      // Verify the configuration structure is correct
+      expect(connectionOptions.clientConfig).toBeDefined();
+      expect(connectionOptions.clientConfig?.tlsConfig).toBeDefined();
+      expect(connectionOptions.clientConfig?.tlsConfig?.certFile).toBe(
+        "/path/to/cert.pem",
+      );
+    });
+  });
+
+  describe("header providers", () => {
+    it("should work with StaticHeaderProvider", async () => {
+      const provider = new StaticHeaderProvider({
+        authorization: "Bearer test-token",
+        "X-Custom": "value",
+      });
+
+      const headers = provider.getHeaders();
+      expect(headers).toEqual({
+        authorization: "Bearer test-token",
+        "X-Custom": "value",
+      });
+
+      // Test that it returns a copy
+      headers["X-Modified"] = "modified";
+      const headers2 = provider.getHeaders();
+      expect(headers2).not.toHaveProperty("X-Modified");
+    });
+
+    it("should pass headers from StaticHeaderProvider to requests", async () => {
+      const provider = new StaticHeaderProvider({
+        "X-Custom-Auth": "secret-token",
+        "X-Request-Source": "test-suite",
+      });
+
+      await withMockDatabase(
+        (req, res) => {
+          expect(req.headers["x-custom-auth"]).toEqual("secret-token");
+          expect(req.headers["x-request-source"]).toEqual("test-suite");
+
+          const body = JSON.stringify({ tables: [] });
+          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
+        },
+        async () => {
+          // Use actual header provider mechanism instead of extraHeaders
+          const conn = await connect(
+            "db://dev",
+            {
+              apiKey: "fake",
+              hostOverride: "http://localhost:8000",
+            },
+            undefined, // session
+            provider, // headerProvider
+          );
+
+          const tableNames = await conn.tableNames();
+          expect(tableNames).toEqual([]);
+        },
+      );
+    });
+
+    it("should work with CustomProvider", () => {
+      const provider = new CustomProvider();
+      const headers = provider.getHeaders();
+      expect(headers).toEqual({ "X-Custom": "custom-value" });
+    });
+
+    it("should handle ErrorProvider errors", () => {
+      const provider = new ErrorProvider("Authentication failed");
+
+      expect(() => provider.getHeaders()).toThrow("Authentication failed");
+      expect(provider.callCount).toBe(1);
+
+      // Test that error is thrown each time
+      expect(() => provider.getHeaders()).toThrow("Authentication failed");
+      expect(provider.callCount).toBe(2);
+    });
+
+    it("should work with ConcurrentProvider", () => {
+      const provider = new ConcurrentProvider();
+
+      const headers1 = provider.getHeaders();
+      const headers2 = provider.getHeaders();
+      const headers3 = provider.getHeaders();
+
+      expect(headers1).toEqual({ "X-Request-Id": "1" });
+      expect(headers2).toEqual({ "X-Request-Id": "2" });
+      expect(headers3).toEqual({ "X-Request-Id": "3" });
+    });
+
+    describe("OAuthHeaderProvider", () => {
+      it("should initialize correctly", () => {
+        const fetcher = () => ({
+          accessToken: "token123",
+          expiresIn: 3600,
+        });
+
+        const provider = new OAuthHeaderProvider(fetcher);
+        expect(provider).toBeInstanceOf(HeaderProvider);
+      });
+
+      it("should fetch token on first use", async () => {
+        let callCount = 0;
+        const fetcher = () => {
+          callCount++;
+          return {
+            accessToken: "token123",
+            expiresIn: 3600,
+          };
+        };
+
+        const provider = new OAuthHeaderProvider(fetcher);
+
+        // Need to manually refresh first due to sync limitation
+        await provider.refreshToken();
+
+        const headers = provider.getHeaders();
+        expect(headers).toEqual({ authorization: "Bearer token123" });
+        expect(callCount).toBe(1);
+
+        // Second call should not fetch again
+        const headers2 = provider.getHeaders();
+        expect(headers2).toEqual({ authorization: "Bearer token123" });
+        expect(callCount).toBe(1);
+      });
+
+      it("should handle tokens without expiry", async () => {
+        const fetcher = () => ({
+          accessToken: "permanent_token",
+        });
+
+        const provider = new OAuthHeaderProvider(fetcher);
+        await provider.refreshToken();
+
+        const headers = provider.getHeaders();
+        expect(headers).toEqual({ authorization: "Bearer permanent_token" });
+      });
+
+      it("should throw error when access_token is missing", async () => {
+        const fetcher = () =>
+          ({
+            expiresIn: 3600,
+          }) as { accessToken?: string; expiresIn?: number };
+
+        const provider = new OAuthHeaderProvider(
+          fetcher as () => {
+            accessToken: string;
+            expiresIn?: number;
+          },
+        );
+
+        await expect(provider.refreshToken()).rejects.toThrow(
+          "Token fetcher did not return 'accessToken'",
+        );
+      });
+
+      it("should handle async token fetchers", async () => {
+        const fetcher = async () => {
+          // Simulate async operation
+          await new Promise((resolve) => setTimeout(resolve, 10));
+          return {
+            accessToken: "async_token",
+            expiresIn: 3600,
+          };
+        };
+
+        const provider = new OAuthHeaderProvider(fetcher);
+        await provider.refreshToken();
+
+        const headers = provider.getHeaders();
+        expect(headers).toEqual({ authorization: "Bearer async_token" });
+      });
+    });
+
+    it("should merge header provider headers with extra headers", async () => {
+      const provider = new StaticHeaderProvider({
+        "X-From-Provider": "provider-value",
+      });
+
+      await withMockDatabase(
+        (req, res) => {
+          expect(req.headers["x-from-provider"]).toEqual("provider-value");
+          expect(req.headers["x-extra-header"]).toEqual("extra-value");
+
+          const body = JSON.stringify({ tables: [] });
+          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
+        },
+        async () => {
+          // Use header provider with additional extraHeaders
+          const conn = await connect(
+            "db://dev",
+            {
+              apiKey: "fake",
+              hostOverride: "http://localhost:8000",
+              clientConfig: {
+                extraHeaders: {
+                  "X-Extra-Header": "extra-value",
+                },
+              },
+            },
+            undefined, // session
+            provider, // headerProvider
+          );
+
+          const tableNames = await conn.tableNames();
+          expect(tableNames).toEqual([]);
+        },
+      );
+    });
+  });
+
+  describe("header provider integration", () => {
+    it("should work with TypeScript StaticHeaderProvider", async () => {
+      let requestCount = 0;
+
+      await withMockDatabase(
+        (req, res) => {
+          requestCount++;
+
+          // Check headers are present on each request
+          expect(req.headers["authorization"]).toEqual("Bearer test-token-123");
+          expect(req.headers["x-custom"]).toEqual("custom-value");
+
+          // Return different responses based on the endpoint
+          if (req.url === "/v1/table/test_table/describe/") {
+            const body = JSON.stringify({
+              name: "test_table",
+              schema: { fields: [] },
+            });
+            res
+              .writeHead(200, { "Content-Type": "application/json" })
+              .end(body);
+          } else {
+            const body = JSON.stringify({ tables: ["test_table"] });
+            res
+              .writeHead(200, { "Content-Type": "application/json" })
+              .end(body);
+          }
+        },
+        async () => {
+          // Create provider with static headers
+          const provider = new StaticHeaderProvider({
+            authorization: "Bearer test-token-123",
+            "X-Custom": "custom-value",
+          });
+
+          // Connect with the provider
+          const conn = await connect(
+            "db://dev",
+            {
+              apiKey: "fake",
+              hostOverride: "http://localhost:8000",
+            },
+            undefined, // session
+            provider, // headerProvider
+          );
+
+          // Make multiple requests to verify headers are sent each time
+          const tables1 = await conn.tableNames();
+          expect(tables1).toEqual(["test_table"]);
+
+          const tables2 = await conn.tableNames();
+          expect(tables2).toEqual(["test_table"]);
+
+          // Verify headers were sent with each request
+          expect(requestCount).toBeGreaterThanOrEqual(2);
+        },
+      );
+    });
+
+    it("should work with JavaScript function provider", async () => {
+      let requestId = 0;
+
+      await withMockDatabase(
+        (req, res) => {
+          // Check dynamic header is present
+          expect(req.headers["x-request-id"]).toBeDefined();
+          expect(req.headers["x-request-id"]).toMatch(/^req-\d+$/);
+
+          const body = JSON.stringify({ tables: [] });
+          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
+        },
+        async () => {
+          // Create a JavaScript function that returns dynamic headers
+          const getHeaders = async () => {
+            requestId++;
+            return {
+              "X-Request-Id": `req-${requestId}`,
+              "X-Timestamp": new Date().toISOString(),
+            };
+          };
+
+          // Connect with the function directly
+          const conn = await connect(
+            "db://dev",
+            {
+              apiKey: "fake",
+              hostOverride: "http://localhost:8000",
+            },
+            undefined, // session
+            getHeaders, // headerProvider
+          );
+
+          // Make requests - each should have different headers
+          const tables = await conn.tableNames();
+          expect(tables).toEqual([]);
+        },
+      );
+    });
+
+    it("should support OAuth-like token refresh pattern", async () => {
+      let tokenVersion = 0;
+
+      await withMockDatabase(
+        (req, res) => {
+          // Verify authorization header
+          const authHeader = req.headers["authorization"];
+          expect(authHeader).toBeDefined();
+          expect(authHeader).toMatch(/^Bearer token-v\d+$/);
+
+          const body = JSON.stringify({ tables: [] });
+          res.writeHead(200, { "Content-Type": "application/json" }).end(body);
+        },
+        async () => {
+          // Simulate OAuth token fetcher
+          const fetchToken = async () => {
+            tokenVersion++;
+            return {
+              authorization: `Bearer token-v${tokenVersion}`,
+            };
+          };
+
+          // Connect with the function directly
+          const conn = await connect(
+            "db://dev",
+            {
+              apiKey: "fake",
+              hostOverride: "http://localhost:8000",
+            },
+            undefined, // session
+            fetchToken, // headerProvider
+          );
+
+          // Each request will fetch a new token
+          await conn.tableNames();
+
+          // Token should be different on next request
+          await conn.tableNames();
+        },
+      );
+    });
+  });
 });

nodejs/__test__/sanitize.test.ts

@@ -0,0 +1,184 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import * as arrow from "../lancedb/arrow";
+import { sanitizeField, sanitizeType } from "../lancedb/sanitize";
+
+describe("sanitize", function () {
+  describe("sanitizeType function", function () {
+    it("should handle type objects", function () {
+      const type = new arrow.Int32();
+      const result = sanitizeType(type);
+
+      expect(result.typeId).toBe(arrow.Type.Int);
+      expect((result as arrow.Int).bitWidth).toBe(32);
+      expect((result as arrow.Int).isSigned).toBe(true);
+
+      const floatType = {
+        typeId: 3, // Type.Float = 3
+        precision: 2,
+        toString: () => "Float",
+        isFloat: true,
+        isFixedWidth: true,
+      };
+
+      const floatResult = sanitizeType(floatType);
+      expect(floatResult).toBeInstanceOf(arrow.DataType);
+      expect(floatResult.typeId).toBe(arrow.Type.Float);
+
+      const floatResult2 = sanitizeType({ ...floatType, typeId: () => 3 });
+      expect(floatResult2).toBeInstanceOf(arrow.DataType);
+      expect(floatResult2.typeId).toBe(arrow.Type.Float);
+    });
+
+    const allTypeNameTestCases = [
+      ["null", new arrow.Null()],
+      ["binary", new arrow.Binary()],
+      ["utf8", new arrow.Utf8()],
+      ["bool", new arrow.Bool()],
+      ["int8", new arrow.Int8()],
+      ["int16", new arrow.Int16()],
+      ["int32", new arrow.Int32()],
+      ["int64", new arrow.Int64()],
+      ["uint8", new arrow.Uint8()],
+      ["uint16", new arrow.Uint16()],
+      ["uint32", new arrow.Uint32()],
+      ["uint64", new arrow.Uint64()],
+      ["float16", new arrow.Float16()],
+      ["float32", new arrow.Float32()],
+      ["float64", new arrow.Float64()],
+      ["datemillisecond", new arrow.DateMillisecond()],
+      ["dateday", new arrow.DateDay()],
+      ["timenanosecond", new arrow.TimeNanosecond()],
+      ["timemicrosecond", new arrow.TimeMicrosecond()],
+      ["timemillisecond", new arrow.TimeMillisecond()],
+      ["timesecond", new arrow.TimeSecond()],
+      ["intervaldaytime", new arrow.IntervalDayTime()],
+      ["intervalyearmonth", new arrow.IntervalYearMonth()],
+      ["durationnanosecond", new arrow.DurationNanosecond()],
+      ["durationmicrosecond", new arrow.DurationMicrosecond()],
+      ["durationmillisecond", new arrow.DurationMillisecond()],
+      ["durationsecond", new arrow.DurationSecond()],
+    ] as const;
+
+    it.each(allTypeNameTestCases)(
+      'should map type name "%s" to %s',
+      function (name, expected) {
+        const result = sanitizeType(name);
+        expect(result).toBeInstanceOf(expected.constructor);
+      },
+    );
+
+    const caseVariationTestCases = [
+      ["NULL", new arrow.Null()],
+      ["Utf8", new arrow.Utf8()],
+      ["FLOAT32", new arrow.Float32()],
+      ["DaTedAy", new arrow.DateDay()],
+    ] as const;
+
+    it.each(caseVariationTestCases)(
+      'should be case insensitive for type name "%s" mapped to %s',
+      function (name, expected) {
+        const result = sanitizeType(name);
+        expect(result).toBeInstanceOf(expected.constructor);
+      },
+    );
+
+    it("should throw error for unrecognized type name", function () {
+      expect(() => sanitizeType("invalid_type")).toThrow(
+        "Unrecognized type name in schema: invalid_type",
+      );
+    });
+  });
+
+  describe("sanitizeField function", function () {
+    it("should handle field with string type name", function () {
+      const field = sanitizeField({
+        name: "string_field",
+        type: "utf8",
+        nullable: true,
+        metadata: new Map([["key", "value"]]),
+      });
+
+      expect(field).toBeInstanceOf(arrow.Field);
+      expect(field.name).toBe("string_field");
+      expect(field.type).toBeInstanceOf(arrow.Utf8);
+      expect(field.nullable).toBe(true);
+      expect(field.metadata?.get("key")).toBe("value");
+    });
+
+    it("should handle field with type object", function () {
+      const floatType = {
+        typeId: 3, // Float
+        precision: 32,
+      };
+
+      const field = sanitizeField({
+        name: "float_field",
+        type: floatType,
+        nullable: false,
+      });
+
+      expect(field).toBeInstanceOf(arrow.Field);
+      expect(field.name).toBe("float_field");
+      expect(field.type).toBeInstanceOf(arrow.DataType);
+      expect(field.type.typeId).toBe(arrow.Type.Float);
+      expect((field.type as arrow.Float64).precision).toBe(32);
+      expect(field.nullable).toBe(false);
+    });
+
+    it("should handle field with direct Type instance", function () {
+      const field = sanitizeField({
+        name: "bool_field",
+        type: new arrow.Bool(),
+        nullable: true,
+      });
+
+      expect(field).toBeInstanceOf(arrow.Field);
+      expect(field.name).toBe("bool_field");
+      expect(field.type).toBeInstanceOf(arrow.Bool);
+      expect(field.nullable).toBe(true);
+    });
+
+    it("should throw error for invalid field object", function () {
+      expect(() =>
+        sanitizeField({
+          type: "int32",
+          nullable: true,
+        }),
+      ).toThrow(
+        "The field passed in is missing a `type`/`name`/`nullable` property",
+      );
+
+      // Invalid type
+      expect(() =>
+        sanitizeField({
+          name: "invalid",
+          type: { invalid: true },
+          nullable: true,
+        }),
+      ).toThrow("Expected a Type to have a typeId property");
+
+      // Invalid nullable
+      expect(() =>
+        sanitizeField({
+          name: "invalid_nullable",
+          type: "int32",
+          nullable: "not a boolean",
+        }),
+      ).toThrow("The field passed in had a non-boolean `nullable` property");
+    });
+
+    it("should report error for invalid type name", function () {
+      expect(() =>
+        sanitizeField({
+          name: "invalid_field",
+          type: "invalid_type",
+          nullable: true,
+        }),
+      ).toThrow(
+        "Unable to sanitize type for field: invalid_field due to error: Error: Unrecognized type name in schema: invalid_type",
+      );
+    });
+  });
+});

nodejs/__test__/table.test.ts

@@ -10,7 +10,13 @@ import * as arrow16 from "apache-arrow-16";
 import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";
 
-import { MatchQuery, PhraseQuery, Table, connect } from "../lancedb";
+import {
+  Connection,
+  MatchQuery,
+  PhraseQuery,
+  Table,
+  connect,
+} from "../lancedb";
 import {
   Table as ArrowTable,
   Field,
@@ -21,6 +27,8 @@ import {
   Int64,
   List,
   Schema,
+  SchemaLike,
+  Type,
   Uint8,
   Utf8,
   makeArrowTable,
@@ -39,7 +47,6 @@ import {
   Operator,
   instanceOfFullTextQuery,
 } from "../lancedb/query";
-import exp = require("constants");
 
 describe.each([arrow15, arrow16, arrow17, arrow18])(
   "Given a table",
@@ -212,8 +219,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       },
     );
 
-    // TODO: https://github.com/lancedb/lancedb/issues/1832
+    it("should be able to omit nullable fields", async () => {
-    it.skip("should be able to omit nullable fields", async () => {
       const db = await connect(tmpDir.name);
       const schema = new arrow.Schema([
         new arrow.Field(
@@ -237,23 +243,36 @@ 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());
+      res = (await table.query().limit(10).toArray()).map((r) => ({
-      expect(res).toEqual([data1, data2, data3, data4]);
+        ...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 () => {
@@ -331,6 +350,43 @@ 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]);
+    });
   },
 );
 
@@ -488,6 +544,32 @@ describe("merge insert", () => {
         .execute(newData, { timeoutMs: 0 }),
     ).rejects.toThrow("merge insert timed out");
   });
+
+  test("useIndex", async () => {
+    const newData = [
+      { a: 2, b: "x" },
+      { a: 4, b: "z" },
+    ];
+
+    // Test with useIndex(true) - should work fine
+    const result1 = await table
+      .mergeInsert("a")
+      .whenNotMatchedInsertAll()
+      .useIndex(true)
+      .execute(newData);
+
+    expect(result1.numInsertedRows).toBe(1); // Only a=4 should be inserted
+
+    // Test with useIndex(false) - should also work fine
+    const newData2 = [{ a: 5, b: "w" }];
+    const result2 = await table
+      .mergeInsert("a")
+      .whenNotMatchedInsertAll()
+      .useIndex(false)
+      .execute(newData2);
+
+    expect(result2.numInsertedRows).toBe(1); // a=5 should be inserted
+  });
 });
 
 describe("When creating an index", () => {
@@ -779,6 +861,15 @@ describe("When creating an index", () => {
     });
   });
 
+  it("should be able to create IVF_RQ", async () => {
+    await tbl.createIndex("vec", {
+      config: Index.ivfRq({
+        numPartitions: 10,
+        numBits: 1,
+      }),
+    });
+  });
+
   it("should allow me to replace (or not) an existing index", async () => {
     await tbl.createIndex("id");
     // Default is replace=true
@@ -857,6 +948,40 @@ describe("When creating an index", () => {
     expect(stats).toBeUndefined();
   });
 
+  test("should support name and train parameters", async () => {
+    // Test with custom name
+    await tbl.createIndex("vec", {
+      config: Index.ivfPq({ numPartitions: 4 }),
+      name: "my_custom_vector_index",
+    });
+
+    const indices = await tbl.listIndices();
+    expect(indices).toHaveLength(1);
+    expect(indices[0].name).toBe("my_custom_vector_index");
+
+    // Test scalar index with train=false
+    await tbl.createIndex("id", {
+      config: Index.btree(),
+      name: "btree_empty",
+      train: false,
+    });
+
+    const allIndices = await tbl.listIndices();
+    expect(allIndices).toHaveLength(2);
+    expect(allIndices.some((idx) => idx.name === "btree_empty")).toBe(true);
+
+    // Test with both name and train=true (use tags column)
+    await tbl.createIndex("tags", {
+      config: Index.labelList(),
+      name: "tags_trained",
+      train: true,
+    });
+
+    const finalIndices = await tbl.listIndices();
+    expect(finalIndices).toHaveLength(3);
+    expect(finalIndices.some((idx) => idx.name === "tags_trained")).toBe(true);
+  });
+
   test("create ivf_flat with binary vectors", async () => {
     const db = await connect(tmpDir.name);
     const binarySchema = new Schema([
@@ -1395,7 +1520,9 @@ 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 });
@@ -1909,3 +2036,52 @@ describe("column name options", () => {
     expect(results2.length).toBe(10);
   });
 });
+
+describe("when creating an empty table", () => {
+  let con: Connection;
+  beforeEach(async () => {
+    const tmpDir = tmp.dirSync({ unsafeCleanup: true });
+    con = await connect(tmpDir.name);
+  });
+  afterEach(() => {
+    con.close();
+  });
+
+  it("can create an empty table from an arrow Schema", async () => {
+    const schema = new Schema([
+      new Field("id", new Int64()),
+      new Field("vector", new Float64()),
+    ]);
+    const table = await con.createEmptyTable("test", schema);
+    const actualSchema = await table.schema();
+    expect(actualSchema.fields[0].type.typeId).toBe(Type.Int);
+    expect((actualSchema.fields[0].type as Int64).bitWidth).toBe(64);
+    expect(actualSchema.fields[1].type.typeId).toBe(Type.Float);
+    expect((actualSchema.fields[1].type as Float64).precision).toBe(2);
+  });
+
+  it("can create an empty table from schema that specifies field types by name", async () => {
+    const schemaLike = {
+      fields: [
+        {
+          name: "id",
+          type: "int64",
+          nullable: true,
+        },
+        {
+          name: "vector",
+          type: "float64",
+          nullable: true,
+        },
+      ],
+      metadata: new Map(),
+      names: ["id", "vector"],
+    } satisfies SchemaLike;
+    const table = await con.createEmptyTable("test", schemaLike);
+    const actualSchema = await table.schema();
+    expect(actualSchema.fields[0].type.typeId).toBe(Type.Int);
+    expect((actualSchema.fields[0].type as Int64).bitWidth).toBe(64);
+    expect(actualSchema.fields[1].type.typeId).toBe(Type.Float);
+    expect((actualSchema.fields[1].type as Float64).precision).toBe(2);
+  });
+});

nodejs/biome.json

@@ -48,6 +48,7 @@
         "noUnreachableSuper": "error",
         "noUnsafeFinally": "error",
         "noUnsafeOptionalChaining": "error",
+        "noUnusedImports": "error",
         "noUnusedLabels": "error",
         "noUnusedVariables": "warn",
         "useIsNan": "error",

nodejs/lancedb/arrow.ts

@@ -41,7 +41,6 @@ import {
   vectorFromArray as badVectorFromArray,
   makeBuilder,
   makeData,
-  makeTable,
 } from "apache-arrow";
 import { Buffers } from "apache-arrow/data";
 import { type EmbeddingFunction } from "./embedding/embedding_function";
@@ -74,7 +73,7 @@ export type FieldLike =
   | {
       type: string;
       name: string;
-      nullable?: boolean;
+      nullable: boolean;
       metadata?: Map<string, string>;
     };
 
@@ -279,7 +278,7 @@ export class MakeArrowTableOptions {
 }
 
 /**
- * An enhanced version of the {@link makeTable} function from Apache Arrow
+ * An enhanced version of the apache-arrow makeTable function from Apache Arrow
  * that supports nested fields and embeddings columns.
  *
  * (typically you do not need to call this function.  It will be called automatically
@@ -512,7 +511,11 @@ function* rowPathsAndValues(
     if (isObject(value)) {
       yield* rowPathsAndValues(value, [...basePath, key]);
     } else {
-      yield [[...basePath, key], value];
+      // Skip undefined values - they should be treated the same as missing fields
+      // for embedding function purposes
+      if (value !== undefined) {
+        yield [[...basePath, key], value];
+      }
     }
   }
 }
@@ -701,7 +704,7 @@ function transposeData(
       }
       return current;
     });
-    return makeVector(values, field.type);
+    return makeVector(values, field.type, undefined, field.nullable);
   }
 }
 
@@ -748,9 +751,30 @@ function makeVector(
   values: unknown[],
   type?: DataType,
   stringAsDictionary?: boolean,
+  nullable?: boolean,
   // biome-ignore lint/suspicious/noExplicitAny: skip
 ): Vector<any> {
   if (type !== undefined) {
+    // Convert undefined values to null for nullable fields
+    if (nullable) {
+      values = values.map((v) => (v === undefined ? null : v));
+    }
+
+    // workaround for: https://github.com/apache/arrow-js/issues/68
+    if (DataType.isBool(type)) {
+      const hasNonNullValue = values.some((v) => v !== null && v !== undefined);
+      if (!hasNonNullValue) {
+        const nullBitmap = new Uint8Array(Math.ceil(values.length / 8));
+        const data = makeData({
+          type: type,
+          length: values.length,
+          nullCount: values.length,
+          nullBitmap,
+        });
+        return arrowMakeVector(data);
+      }
+    }
+
     // No need for inference, let Arrow create it
     if (type instanceof Int) {
       if (DataType.isInt(type) && type.bitWidth === 64) {
@@ -875,7 +899,12 @@ async function applyEmbeddingsFromMetadata(
   for (const field of schema.fields) {
     if (!(field.name in columns)) {
       const nullValues = new Array(table.numRows).fill(null);
-      columns[field.name] = makeVector(nullValues, field.type);
+      columns[field.name] = makeVector(
+        nullValues,
+        field.type,
+        undefined,
+        field.nullable,
+      );
     }
   }
 
@@ -939,7 +968,12 @@ async function applyEmbeddings<T>(
     } else if (schema != null) {
       const destField = schema.fields.find((f) => f.name === destColumn);
       if (destField != null) {
-        newColumns[destColumn] = makeVector([], destField.type);
+        newColumns[destColumn] = makeVector(
+          [],
+          destField.type,
+          undefined,
+          destField.nullable,
+        );
       } else {
         throw new Error(
           `Attempt to apply embeddings to an empty table failed because schema was missing embedding column '${destColumn}'`,
@@ -1251,19 +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`
-            // biome-ignore lint/suspicious/noExplicitAny: we don't know the type of `f`
+          if (embeddings.find((f: any) => f["vectorColumn"] === field.name)) {
-            embeddings.find((f: any) => f["vectorColumn"] === field.name) ===
+            hasEmbeddingFunction = true;
-            undefined
+          }
-          ) {
+        }
+
+        // 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/lancedb/connection.ts

@@ -3,7 +3,6 @@
 
 import {
   Data,
-  Schema,
   SchemaLike,
   TableLike,
   fromTableToStreamBuffer,
@@ -159,17 +158,33 @@ export abstract class Connection {
    *
    * Tables will be returned in lexicographical order.
    * @param {Partial<TableNamesOptions>} options - options to control the
-   * paging / start point
+   * paging / start point (backwards compatibility)
    *
    */
   abstract tableNames(options?: Partial<TableNamesOptions>): Promise<string[]>;
+  /**
+   * List all the table names in this database.
+   *
+   * Tables will be returned in lexicographical order.
+   * @param {string[]} namespace - The namespace to list tables from (defaults to root namespace)
+   * @param {Partial<TableNamesOptions>} options - options to control the
+   * paging / start point
+   *
+   */
+  abstract tableNames(
+    namespace?: string[],
+    options?: Partial<TableNamesOptions>,
+  ): Promise<string[]>;
 
   /**
    * Open a table in the database.
    * @param {string} name - The name of the table
+   * @param {string[]} namespace - The namespace of the table (defaults to root namespace)
+   * @param {Partial<OpenTableOptions>} options - Additional options
    */
   abstract openTable(
     name: string,
+    namespace?: string[],
     options?: Partial<OpenTableOptions>,
   ): Promise<Table>;
 
@@ -178,6 +193,7 @@ export abstract class Connection {
    * @param {object} options - The options object.
    * @param {string} options.name - The name of the table.
    * @param {Data} options.data - Non-empty Array of Records to be inserted into the table
+   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
    *
    */
   abstract createTable(
@@ -185,40 +201,99 @@ export abstract class Connection {
       name: string;
       data: Data;
     } & Partial<CreateTableOptions>,
+    namespace?: string[],
   ): Promise<Table>;
   /**
    * Creates a new Table and initialize it with new data.
    * @param {string} name - The name of the table.
    * @param {Record<string, unknown>[] | TableLike} data - Non-empty Array of Records
    * to be inserted into the table
+   * @param {Partial<CreateTableOptions>} options - Additional options (backwards compatibility)
    */
   abstract createTable(
     name: string,
     data: Record<string, unknown>[] | TableLike,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
+  /**
+   * Creates a new Table and initialize it with new data.
+   * @param {string} name - The name of the table.
+   * @param {Record<string, unknown>[] | TableLike} data - Non-empty Array of Records
+   * to be inserted into the table
+   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
+   * @param {Partial<CreateTableOptions>} options - Additional options
+   */
+  abstract createTable(
+    name: string,
+    data: Record<string, unknown>[] | TableLike,
+    namespace?: string[],
+    options?: Partial<CreateTableOptions>,
+  ): Promise<Table>;
 
   /**
    * Creates a new empty Table
    * @param {string} name - The name of the table.
    * @param {Schema} schema - The schema of the table
+   * @param {Partial<CreateTableOptions>} options - Additional options (backwards compatibility)
    */
   abstract createEmptyTable(
     name: string,
     schema: import("./arrow").SchemaLike,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table>;
+  /**
+   * Creates a new empty Table
+   * @param {string} name - The name of the table.
+   * @param {Schema} schema - The schema of the table
+   * @param {string[]} namespace - The namespace to create the table in (defaults to root namespace)
+   * @param {Partial<CreateTableOptions>} options - Additional options
+   */
+  abstract createEmptyTable(
+    name: string,
+    schema: import("./arrow").SchemaLike,
+    namespace?: string[],
+    options?: Partial<CreateTableOptions>,
+  ): Promise<Table>;
 
   /**
    * Drop an existing table.
    * @param {string} name The name of the table to drop.
+   * @param {string[]} namespace The namespace of the table (defaults to root namespace).
    */
-  abstract dropTable(name: string): Promise<void>;
+  abstract dropTable(name: string, namespace?: string[]): Promise<void>;
 
   /**
    * Drop all tables in the database.
+   * @param {string[]} namespace The namespace to drop tables from (defaults to root namespace).
    */
-  abstract dropAllTables(): Promise<void>;
+  abstract dropAllTables(namespace?: string[]): Promise<void>;
+
+  /**
+   * Clone a table from a source table.
+   *
+   * A shallow clone creates a new table that shares the underlying data files
+   * with the source table but has its own independent manifest. This allows
+   * both the source and cloned tables to evolve independently while initially
+   * sharing the same data, deletion, and index files.
+   *
+   * @param {string} targetTableName - The name of the target table to create.
+   * @param {string} sourceUri - The URI of the source table to clone from.
+   * @param {object} options - Clone options.
+   * @param {string[]} options.targetNamespace - The namespace for the target table (defaults to root namespace).
+   * @param {number} options.sourceVersion - The version of the source table to clone.
+   * @param {string} options.sourceTag - The tag of the source table to clone.
+   * @param {boolean} options.isShallow - Whether to perform a shallow clone (defaults to true).
+   */
+  abstract cloneTable(
+    targetTableName: string,
+    sourceUri: string,
+    options?: {
+      targetNamespace?: string[];
+      sourceVersion?: number;
+      sourceTag?: string;
+      isShallow?: boolean;
+    },
+  ): Promise<Table>;
 }
 
 /** @hideconstructor */
@@ -243,16 +318,39 @@ export class LocalConnection extends Connection {
     return this.inner.display();
   }
 
-  async tableNames(options?: Partial<TableNamesOptions>): Promise<string[]> {
+  async tableNames(
-    return this.inner.tableNames(options?.startAfter, options?.limit);
+    namespaceOrOptions?: string[] | Partial<TableNamesOptions>,
+    options?: Partial<TableNamesOptions>,
+  ): Promise<string[]> {
+    // Detect if first argument is namespace array or options object
+    let namespace: string[] | undefined;
+    let tableNamesOptions: Partial<TableNamesOptions> | undefined;
+
+    if (Array.isArray(namespaceOrOptions)) {
+      // First argument is namespace array
+      namespace = namespaceOrOptions;
+      tableNamesOptions = options;
+    } else {
+      // First argument is options object (backwards compatibility)
+      namespace = undefined;
+      tableNamesOptions = namespaceOrOptions;
+    }
+
+    return this.inner.tableNames(
+      namespace ?? [],
+      tableNamesOptions?.startAfter,
+      tableNamesOptions?.limit,
+    );
   }
 
   async openTable(
     name: string,
+    namespace?: string[],
     options?: Partial<OpenTableOptions>,
   ): Promise<Table> {
     const innerTable = await this.inner.openTable(
       name,
+      namespace ?? [],
       cleanseStorageOptions(options?.storageOptions),
       options?.indexCacheSize,
     );
@@ -260,6 +358,28 @@ export class LocalConnection extends Connection {
     return new LocalTable(innerTable);
   }
 
+  async cloneTable(
+    targetTableName: string,
+    sourceUri: string,
+    options?: {
+      targetNamespace?: string[];
+      sourceVersion?: number;
+      sourceTag?: string;
+      isShallow?: boolean;
+    },
+  ): Promise<Table> {
+    const innerTable = await this.inner.cloneTable(
+      targetTableName,
+      sourceUri,
+      options?.targetNamespace ?? [],
+      options?.sourceVersion ?? null,
+      options?.sourceTag ?? null,
+      options?.isShallow ?? true,
+    );
+
+    return new LocalTable(innerTable);
+  }
+
   private getStorageOptions(
     options?: Partial<CreateTableOptions>,
   ): Record<string, string> | undefined {
@@ -286,14 +406,44 @@ export class LocalConnection extends Connection {
     nameOrOptions:
       | string
       | ({ name: string; data: Data } & Partial<CreateTableOptions>),
-    data?: Record<string, unknown>[] | TableLike,
+    dataOrNamespace?: Record<string, unknown>[] | TableLike | string[],
+    namespaceOrOptions?: string[] | Partial<CreateTableOptions>,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
     if (typeof nameOrOptions !== "string" && "name" in nameOrOptions) {
-      const { name, data, ...options } = nameOrOptions;
+      // First overload: createTable(options, namespace?)
-
+      const { name, data, ...createOptions } = nameOrOptions;
-      return this.createTable(name, data, options);
+      const namespace = dataOrNamespace as string[] | undefined;
+      return this._createTableImpl(name, data, namespace, createOptions);
     }
+
+    // Second overload: createTable(name, data, namespace?, options?)
+    const name = nameOrOptions;
+    const data = dataOrNamespace as Record<string, unknown>[] | TableLike;
+
+    // Detect if third argument is namespace array or options object
+    let namespace: string[] | undefined;
+    let createOptions: Partial<CreateTableOptions> | undefined;
+
+    if (Array.isArray(namespaceOrOptions)) {
+      // Third argument is namespace array
+      namespace = namespaceOrOptions;
+      createOptions = options;
+    } else {
+      // Third argument is options object (backwards compatibility)
+      namespace = undefined;
+      createOptions = namespaceOrOptions;
+    }
+
+    return this._createTableImpl(name, data, namespace, createOptions);
+  }
+
+  private async _createTableImpl(
+    name: string,
+    data: Data,
+    namespace?: string[],
+    options?: Partial<CreateTableOptions>,
+  ): Promise<Table> {
     if (data === undefined) {
       throw new Error("data is required");
     }
@@ -302,9 +452,10 @@ export class LocalConnection extends Connection {
     const storageOptions = this.getStorageOptions(options);
 
     const innerTable = await this.inner.createTable(
-      nameOrOptions,
+      name,
       buf,
       mode,
+      namespace ?? [],
       storageOptions,
     );
 
@@ -314,39 +465,55 @@ export class LocalConnection extends Connection {
   async createEmptyTable(
     name: string,
     schema: import("./arrow").SchemaLike,
+    namespaceOrOptions?: string[] | Partial<CreateTableOptions>,
     options?: Partial<CreateTableOptions>,
   ): Promise<Table> {
-    let mode: string = options?.mode ?? "create";
+    // Detect if third argument is namespace array or options object
-    const existOk = options?.existOk ?? false;
+    let namespace: string[] | undefined;
+    let createOptions: Partial<CreateTableOptions> | undefined;
+
+    if (Array.isArray(namespaceOrOptions)) {
+      // Third argument is namespace array
+      namespace = namespaceOrOptions;
+      createOptions = options;
+    } else {
+      // Third argument is options object (backwards compatibility)
+      namespace = undefined;
+      createOptions = namespaceOrOptions;
+    }
+
+    let mode: string = createOptions?.mode ?? "create";
+    const existOk = createOptions?.existOk ?? false;
 
     if (mode === "create" && existOk) {
       mode = "exist_ok";
     }
     let metadata: Map<string, string> | undefined = undefined;
-    if (options?.embeddingFunction !== undefined) {
+    if (createOptions?.embeddingFunction !== undefined) {
-      const embeddingFunction = options.embeddingFunction;
+      const embeddingFunction = createOptions.embeddingFunction;
       const registry = getRegistry();
       metadata = registry.getTableMetadata([embeddingFunction]);
     }
 
-    const storageOptions = this.getStorageOptions(options);
+    const storageOptions = this.getStorageOptions(createOptions);
     const table = makeEmptyTable(schema, metadata);
     const buf = await fromTableToBuffer(table);
     const innerTable = await this.inner.createEmptyTable(
       name,
       buf,
       mode,
+      namespace ?? [],
       storageOptions,
     );
     return new LocalTable(innerTable);
   }
 
-  async dropTable(name: string): Promise<void> {
+  async dropTable(name: string, namespace?: string[]): Promise<void> {
-    return this.inner.dropTable(name);
+    return this.inner.dropTable(name, namespace ?? []);
   }
 
-  async dropAllTables(): Promise<void> {
+  async dropAllTables(namespace?: string[]): Promise<void> {
-    return this.inner.dropAllTables();
+    return this.inner.dropAllTables(namespace ?? []);
   }
 }
 

nodejs/lancedb/header.ts

@@ -0,0 +1,253 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+/**
+ * Header providers for LanceDB remote connections.
+ *
+ * This module provides a flexible header management framework for LanceDB remote
+ * connections, allowing users to implement custom header strategies for
+ * authentication, request tracking, custom metadata, or any other header-based
+ * requirements.
+ *
+ * @module header
+ */
+
+/**
+ * Abstract base class for providing custom headers for each request.
+ *
+ * Users can implement this interface to provide dynamic headers for various purposes
+ * such as authentication (OAuth tokens, API keys), request tracking (correlation IDs),
+ * custom metadata, or any other header-based requirements. The provider is called
+ * before each request to ensure fresh header values are always used.
+ *
+ * @example
+ * Simple JWT token provider:
+ * ```typescript
+ * class JWTProvider extends HeaderProvider {
+ *   constructor(private token: string) {
+ *     super();
+ *   }
+ *
+ *   getHeaders(): Record<string, string> {
+ *     return { authorization: `Bearer ${this.token}` };
+ *   }
+ * }
+ * ```
+ *
+ * @example
+ * Provider with request tracking:
+ * ```typescript
+ * class RequestTrackingProvider extends HeaderProvider {
+ *   constructor(private sessionId: string) {
+ *     super();
+ *   }
+ *
+ *   getHeaders(): Record<string, string> {
+ *     return {
+ *       "X-Session-Id": this.sessionId,
+ *       "X-Request-Id": `req-${Date.now()}`
+ *     };
+ *   }
+ * }
+ * ```
+ */
+export abstract class HeaderProvider {
+  /**
+   * Get the latest headers to be added to requests.
+   *
+   * This method is called before each request to the remote LanceDB server.
+   * Implementations should return headers that will be merged with existing headers.
+   *
+   * @returns Dictionary of header names to values to add to the request.
+   * @throws If unable to fetch headers, the exception will be propagated and the request will fail.
+   */
+  abstract getHeaders(): Record<string, string>;
+}
+
+/**
+ * Example implementation: A simple header provider that returns static headers.
+ *
+ * This is an example implementation showing how to create a HeaderProvider
+ * for cases where headers don't change during the session.
+ *
+ * @example
+ * ```typescript
+ * const provider = new StaticHeaderProvider({
+ *   authorization: "Bearer my-token",
+ *   "X-Custom-Header": "custom-value"
+ * });
+ * const headers = provider.getHeaders();
+ * // Returns: {authorization: 'Bearer my-token', 'X-Custom-Header': 'custom-value'}
+ * ```
+ */
+export class StaticHeaderProvider extends HeaderProvider {
+  private _headers: Record<string, string>;
+
+  /**
+   * Initialize with static headers.
+   * @param headers - Headers to return for every request.
+   */
+  constructor(headers: Record<string, string>) {
+    super();
+    this._headers = { ...headers };
+  }
+
+  /**
+   * Return the static headers.
+   * @returns Copy of the static headers.
+   */
+  getHeaders(): Record<string, string> {
+    return { ...this._headers };
+  }
+}
+
+/**
+ * Token response from OAuth provider.
+ * @public
+ */
+export interface TokenResponse {
+  accessToken: string;
+  expiresIn?: number;
+}
+
+/**
+ * Example implementation: OAuth token provider with automatic refresh.
+ *
+ * This is an example implementation showing how to manage OAuth tokens
+ * with automatic refresh when they expire.
+ *
+ * @example
+ * ```typescript
+ * async function fetchToken(): Promise<TokenResponse> {
+ *   const response = await fetch("https://oauth.example.com/token", {
+ *     method: "POST",
+ *     body: JSON.stringify({
+ *       grant_type: "client_credentials",
+ *       client_id: "your-client-id",
+ *       client_secret: "your-client-secret"
+ *     }),
+ *     headers: { "Content-Type": "application/json" }
+ *   });
+ *   const data = await response.json();
+ *   return {
+ *     accessToken: data.access_token,
+ *     expiresIn: data.expires_in
+ *   };
+ * }
+ *
+ * const provider = new OAuthHeaderProvider(fetchToken);
+ * const headers = provider.getHeaders();
+ * // Returns: {"authorization": "Bearer <your-token>"}
+ * ```
+ */
+export class OAuthHeaderProvider extends HeaderProvider {
+  private _tokenFetcher: () => Promise<TokenResponse> | TokenResponse;
+  private _refreshBufferSeconds: number;
+  private _currentToken: string | null = null;
+  private _tokenExpiresAt: number | null = null;
+  private _refreshPromise: Promise<void> | null = null;
+
+  /**
+   * Initialize the OAuth provider.
+   * @param tokenFetcher - Function to fetch new tokens. Should return object with 'accessToken' and optionally 'expiresIn'.
+   * @param refreshBufferSeconds - Seconds before expiry to refresh token. Default 300 (5 minutes).
+   */
+  constructor(
+    tokenFetcher: () => Promise<TokenResponse> | TokenResponse,
+    refreshBufferSeconds: number = 300,
+  ) {
+    super();
+    this._tokenFetcher = tokenFetcher;
+    this._refreshBufferSeconds = refreshBufferSeconds;
+  }
+
+  /**
+   * Check if token needs refresh.
+   */
+  private _needsRefresh(): boolean {
+    if (this._currentToken === null) {
+      return true;
+    }
+
+    if (this._tokenExpiresAt === null) {
+      // No expiration info, assume token is valid
+      return false;
+    }
+
+    // Refresh if we're within the buffer time of expiration
+    const now = Date.now() / 1000;
+    return now >= this._tokenExpiresAt - this._refreshBufferSeconds;
+  }
+
+  /**
+   * Refresh the token if it's expired or close to expiring.
+   */
+  private async _refreshTokenIfNeeded(): Promise<void> {
+    if (!this._needsRefresh()) {
+      return;
+    }
+
+    // If refresh is already in progress, wait for it
+    if (this._refreshPromise) {
+      await this._refreshPromise;
+      return;
+    }
+
+    // Start refresh
+    this._refreshPromise = (async () => {
+      try {
+        const tokenData = await this._tokenFetcher();
+
+        this._currentToken = tokenData.accessToken;
+        if (!this._currentToken) {
+          throw new Error("Token fetcher did not return 'accessToken'");
+        }
+
+        // Set expiration if provided
+        if (tokenData.expiresIn) {
+          this._tokenExpiresAt = Date.now() / 1000 + tokenData.expiresIn;
+        } else {
+          // Token doesn't expire or expiration unknown
+          this._tokenExpiresAt = null;
+        }
+      } finally {
+        this._refreshPromise = null;
+      }
+    })();
+
+    await this._refreshPromise;
+  }
+
+  /**
+   * Get OAuth headers, refreshing token if needed.
+   * Note: This is synchronous for now as the Rust implementation expects sync.
+   * In a real implementation, this would need to handle async properly.
+   * @returns Headers with Bearer token authorization.
+   * @throws If unable to fetch or refresh token.
+   */
+  getHeaders(): Record<string, string> {
+    // For simplicity in this example, we assume the token is already fetched
+    // In a real implementation, this would need to handle the async nature properly
+    if (!this._currentToken && !this._refreshPromise) {
+      // Synchronously trigger refresh - this is a limitation of the current implementation
+      throw new Error(
+        "Token not initialized. Call refreshToken() first or use async initialization.",
+      );
+    }
+
+    if (!this._currentToken) {
+      throw new Error("Failed to obtain OAuth token");
+    }
+
+    return { authorization: `Bearer ${this._currentToken}` };
+  }
+
+  /**
+   * Manually refresh the token.
+   * Call this before using getHeaders() to ensure token is available.
+   */
+  async refreshToken(): Promise<void> {
+    this._currentToken = null; // Force refresh
+    await this._refreshTokenIfNeeded();
+  }
+}

nodejs/lancedb/index.ts

@@ -10,9 +10,15 @@ import {
 import {
   ConnectionOptions,
   Connection as LanceDbConnection,
+  JsHeaderProvider as NativeJsHeaderProvider,
   Session,
 } from "./native.js";
 
+import { HeaderProvider } from "./header";
+
+// Re-export native header provider for use with connectWithHeaderProvider
+export { JsHeaderProvider as NativeJsHeaderProvider } from "./native.js";
+
 export {
   AddColumnsSql,
   ConnectionOptions,
@@ -21,6 +27,7 @@ export {
   ClientConfig,
   TimeoutConfig,
   RetryConfig,
+  TlsConfig,
   OptimizeStats,
   CompactionStats,
   RemovalStats,
@@ -36,6 +43,11 @@ export {
   DeleteResult,
   DropColumnsResult,
   UpdateResult,
+  SplitCalculatedOptions,
+  SplitRandomOptions,
+  SplitHashOptions,
+  SplitSequentialOptions,
+  ShuffleOptions,
 } from "./native.js";
 
 export {
@@ -78,6 +90,7 @@ export {
   Index,
   IndexOptions,
   IvfPqOptions,
+  IvfRqOptions,
   IvfFlatOptions,
   HnswPqOptions,
   HnswSqOptions,
@@ -93,9 +106,17 @@ export {
   ColumnAlteration,
 } from "./table";
 
+export {
+  HeaderProvider,
+  StaticHeaderProvider,
+  OAuthHeaderProvider,
+  TokenResponse,
+} from "./header";
+
 export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";
+export { permutationBuilder, PermutationBuilder } from "./permutation";
 export * as rerankers from "./rerankers";
 export {
   SchemaLike,
@@ -131,11 +152,27 @@ export { IntoSql, packBits } from "./util";
  *   {storageOptions: {timeout: "60s"}
  * });
  * ```
+ * @example
+ * Using with a header provider for per-request authentication:
+ * ```ts
+ * const provider = new StaticHeaderProvider({
+ *   "X-API-Key": "my-key"
+ * });
+ * const conn = await connectWithHeaderProvider(
+ *   "db://host:port",
+ *   options,
+ *   provider
+ * );
+ * ```
  */
 export async function connect(
   uri: string,
   options?: Partial<ConnectionOptions>,
   session?: Session,
+  headerProvider?:
+    | HeaderProvider
+    | (() => Record<string, string>)
+    | (() => Promise<Record<string, string>>),
 ): Promise<Connection>;
 /**
  * Connect to a LanceDB instance at the given URI.
@@ -169,18 +206,58 @@ export async function connect(
 ): Promise<Connection>;
 export async function connect(
   uriOrOptions: string | (Partial<ConnectionOptions> & { uri: string }),
-  options?: Partial<ConnectionOptions>,
+  optionsOrSession?: Partial<ConnectionOptions> | Session,
+  sessionOrHeaderProvider?:
+    | Session
+    | HeaderProvider
+    | (() => Record<string, string>)
+    | (() => Promise<Record<string, string>>),
+  headerProvider?:
+    | HeaderProvider
+    | (() => Record<string, string>)
+    | (() => Promise<Record<string, string>>),
 ): Promise<Connection> {
   let uri: string | undefined;
   let finalOptions: Partial<ConnectionOptions> = {};
+  let finalHeaderProvider:
+    | HeaderProvider
+    | (() => Record<string, string>)
+    | (() => Promise<Record<string, string>>)
+    | undefined;
 
   if (typeof uriOrOptions !== "string") {
+    // First overload: connect(options)
     const { uri: uri_, ...opts } = uriOrOptions;
     uri = uri_;
     finalOptions = opts;
   } else {
+    // Second overload: connect(uri, options?, session?, headerProvider?)
     uri = uriOrOptions;
-    finalOptions = options || {};
+
+    // Handle optionsOrSession parameter
+    if (optionsOrSession && "inner" in optionsOrSession) {
+      // Second param is session, so no options provided
+      finalOptions = {};
+    } else {
+      // Second param is options
+      finalOptions = (optionsOrSession as Partial<ConnectionOptions>) || {};
+    }
+
+    // Handle sessionOrHeaderProvider parameter
+    if (
+      sessionOrHeaderProvider &&
+      (typeof sessionOrHeaderProvider === "function" ||
+        "getHeaders" in sessionOrHeaderProvider)
+    ) {
+      // Third param is header provider
+      finalHeaderProvider = sessionOrHeaderProvider as
+        | HeaderProvider
+        | (() => Record<string, string>)
+        | (() => Promise<Record<string, string>>);
+    } else {
+      // Third param is session, header provider is fourth param
+      finalHeaderProvider = headerProvider;
+    }
   }
 
   if (!uri) {
@@ -191,6 +268,26 @@ export async function connect(
   (<ConnectionOptions>finalOptions).storageOptions = cleanseStorageOptions(
     (<ConnectionOptions>finalOptions).storageOptions,
   );
-  const nativeConn = await LanceDbConnection.new(uri, finalOptions);
+
+  // Create native header provider if one was provided
+  let nativeProvider: NativeJsHeaderProvider | undefined;
+  if (finalHeaderProvider) {
+    if (typeof finalHeaderProvider === "function") {
+      nativeProvider = new NativeJsHeaderProvider(finalHeaderProvider);
+    } else if (
+      finalHeaderProvider &&
+      typeof finalHeaderProvider.getHeaders === "function"
+    ) {
+      nativeProvider = new NativeJsHeaderProvider(async () =>
+        finalHeaderProvider.getHeaders(),
+      );
+    }
+  }
+
+  const nativeConn = await LanceDbConnection.new(
+    uri,
+    finalOptions,
+    nativeProvider,
+  );
   return new LocalConnection(nativeConn);
 }

nodejs/lancedb/indices.ts

@@ -112,6 +112,77 @@ export interface IvfPqOptions {
   sampleRate?: number;
 }
 
+export interface IvfRqOptions {
+  /**
+   * The number of IVF partitions to create.
+   *
+   * This value should generally scale with the number of rows in the dataset.
+   * By default the number of partitions is the square root of the number of
+   * rows.
+   *
+   * If this value is too large then the first part of the search (picking the
+   * right partition) will be slow. If this value is too small then the second
+   * part of the search (searching within a partition) will be slow.
+   */
+  numPartitions?: number;
+
+  /**
+   * Number of bits per dimension for residual quantization.
+   *
+   * This value controls how much each residual component is compressed. The more
+   * bits, the more accurate the index will be but the slower search. Typical values
+   * are small integers; the default is 1 bit per dimension.
+   */
+  numBits?: number;
+
+  /**
+   * Distance type to use to build the index.
+   *
+   * Default value is "l2".
+   *
+   * This is used when training the index to calculate the IVF partitions
+   * (vectors are grouped in partitions with similar vectors according to this
+   * distance type) and during quantization.
+   *
+   * The distance type used to train an index MUST match the distance type used
+   * to search the index. Failure to do so will yield inaccurate results.
+   *
+   * The following distance types are available:
+   *
+   * "l2" - Euclidean distance.
+   * "cosine" - Cosine distance.
+   * "dot" - Dot product.
+   */
+  distanceType?: "l2" | "cosine" | "dot";
+
+  /**
+   * Max iterations to train IVF kmeans.
+   *
+   * When training an IVF index we use kmeans to calculate the partitions. This parameter
+   * controls how many iterations of kmeans to run.
+   *
+   * The default value is 50.
+   */
+  maxIterations?: number;
+
+  /**
+   * The number of vectors, per partition, to sample when training IVF kmeans.
+   *
+   * When an IVF index is trained, we need to calculate partitions. These are groups
+   * of vectors that are similar to each other. To do this we use an algorithm called kmeans.
+   *
+   * Running kmeans on a large dataset can be slow. To speed this up we run kmeans on a
+   * random sample of the data. This parameter controls the size of the sample. The total
+   * number of vectors used to train the index is `sample_rate * num_partitions`.
+   *
+   * Increasing this value might improve the quality of the index but in most cases the
+   * default should be sufficient.
+   *
+   * The default value is 256.
+   */
+  sampleRate?: number;
+}
+
 /**
  * Options to create an `HNSW_PQ` index
  */
@@ -523,6 +594,35 @@ export class Index {
         options?.distanceType,
         options?.numPartitions,
         options?.numSubVectors,
+        options?.numBits,
+        options?.maxIterations,
+        options?.sampleRate,
+      ),
+    );
+  }
+
+  /**
+   * Create an IvfRq index
+   *
+   * IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
+   * and organizes them into IVF partitions.
+   *
+   * The compression scheme is called RabitQ quantization. Each dimension is quantized into a small number of bits.
+   * The parameters `num_bits` and `num_partitions` control this process, providing a tradeoff
+   * between index size (and thus search speed) and index accuracy.
+   *
+   * The partitioning process is called IVF and the `num_partitions` parameter controls how
+   * many groups to create.
+   *
+   * Note that training an IVF RQ index on a large dataset is a slow operation and
+   * currently is also a memory intensive operation.
+   */
+  static ivfRq(options?: Partial<IvfRqOptions>) {
+    return new Index(
+      LanceDbIndex.ivfRq(
+        options?.distanceType,
+        options?.numPartitions,
+        options?.numBits,
         options?.maxIterations,
         options?.sampleRate,
       ),
@@ -700,5 +800,27 @@ export interface IndexOptions {
    */
   replace?: boolean;
 
+  /**
+   * Timeout in seconds to wait for index creation to complete.
+   *
+   * If not specified, the method will return immediately after starting the index creation.
+   */
   waitTimeoutSeconds?: number;
+
+  /**
+   * Optional custom name for the index.
+   *
+   * If not provided, a default name will be generated based on the column name.
+   */
+  name?: string;
+
+  /**
+   * Whether to train the index with existing data.
+   *
+   * If true (default), the index will be trained with existing data in the table.
+   * If false, the index will be created empty and populated as new data is added.
+   *
+   * Note: This option is only supported for scalar indices. Vector indices always train.
+   */
+  train?: boolean;
 }

nodejs/lancedb/merge.ts

@@ -70,6 +70,23 @@ export class MergeInsertBuilder {
       this.#schema,
     );
   }
+
+  /**
+   * 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.
+   *
+   * @param useIndex - Whether to use indices for the merge operation. Defaults to `true`.
+   */
+  useIndex(useIndex: boolean): MergeInsertBuilder {
+    return new MergeInsertBuilder(
+      this.#native.useIndex(useIndex),
+      this.#schema,
+    );
+  }
   /**
    * Executes the merge insert operation
    *

nodejs/lancedb/permutation.ts

@@ -0,0 +1,202 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+import { Connection, LocalConnection } from "./connection.js";
+import {
+  PermutationBuilder as NativePermutationBuilder,
+  Table as NativeTable,
+  ShuffleOptions,
+  SplitCalculatedOptions,
+  SplitHashOptions,
+  SplitRandomOptions,
+  SplitSequentialOptions,
+  permutationBuilder as nativePermutationBuilder,
+} from "./native.js";
+import { LocalTable, Table } from "./table";
+
+/**
+ * A PermutationBuilder for creating data permutations with splits, shuffling, and filtering.
+ *
+ * This class provides a TypeScript wrapper around the native Rust PermutationBuilder,
+ * offering methods to configure data splits, shuffling, and filtering before executing
+ * the permutation to create a new table.
+ */
+export class PermutationBuilder {
+  private inner: NativePermutationBuilder;
+
+  /**
+   * @hidden
+   */
+  constructor(inner: NativePermutationBuilder) {
+    this.inner = inner;
+  }
+
+  /**
+   * Configure the permutation to be persisted.
+   *
+   * @param connection - The connection to persist the permutation to
+   * @param tableName - The name of the table to create
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * builder.persist(connection, "permutation_table");
+   * ```
+   */
+  persist(connection: Connection, tableName: string): PermutationBuilder {
+    const localConnection = connection as LocalConnection;
+    const newInner = this.inner.persist(localConnection.inner, tableName);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Configure random splits for the permutation.
+   *
+   * @param options - Configuration for random splitting
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * // Split by ratios
+   * builder.splitRandom({ ratios: [0.7, 0.3], seed: 42 });
+   *
+   * // Split by counts
+   * builder.splitRandom({ counts: [1000, 500], seed: 42 });
+   *
+   * // Split with fixed size
+   * builder.splitRandom({ fixed: 100, seed: 42 });
+   * ```
+   */
+  splitRandom(options: SplitRandomOptions): PermutationBuilder {
+    const newInner = this.inner.splitRandom(options);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Configure hash-based splits for the permutation.
+   *
+   * @param options - Configuration for hash-based splitting
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * builder.splitHash({
+   *   columns: ["user_id"],
+   *   splitWeights: [70, 30],
+   *   discardWeight: 0
+   * });
+   * ```
+   */
+  splitHash(options: SplitHashOptions): PermutationBuilder {
+    const newInner = this.inner.splitHash(options);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Configure sequential splits for the permutation.
+   *
+   * @param options - Configuration for sequential splitting
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * // Split by ratios
+   * builder.splitSequential({ ratios: [0.8, 0.2] });
+   *
+   * // Split by counts
+   * builder.splitSequential({ counts: [800, 200] });
+   *
+   * // Split with fixed size
+   * builder.splitSequential({ fixed: 1000 });
+   * ```
+   */
+  splitSequential(options: SplitSequentialOptions): PermutationBuilder {
+    const newInner = this.inner.splitSequential(options);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Configure calculated splits for the permutation.
+   *
+   * @param options - Configuration for calculated splitting
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * builder.splitCalculated("user_id % 3");
+   * ```
+   */
+  splitCalculated(options: SplitCalculatedOptions): PermutationBuilder {
+    const newInner = this.inner.splitCalculated(options);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Configure shuffling for the permutation.
+   *
+   * @param options - Configuration for shuffling
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * // Basic shuffle
+   * builder.shuffle({ seed: 42 });
+   *
+   * // Shuffle with clump size
+   * builder.shuffle({ seed: 42, clumpSize: 10 });
+   * ```
+   */
+  shuffle(options: ShuffleOptions): PermutationBuilder {
+    const newInner = this.inner.shuffle(options);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Configure filtering for the permutation.
+   *
+   * @param filter - SQL filter expression
+   * @returns A new PermutationBuilder instance
+   * @example
+   * ```ts
+   * builder.filter("age > 18 AND status = 'active'");
+   * ```
+   */
+  filter(filter: string): PermutationBuilder {
+    const newInner = this.inner.filter(filter);
+    return new PermutationBuilder(newInner);
+  }
+
+  /**
+   * Execute the permutation and create the destination table.
+   *
+   * @returns A Promise that resolves to the new Table instance
+   * @example
+   * ```ts
+   * const permutationTable = await builder.execute();
+   * console.log(`Created table: ${permutationTable.name}`);
+   * ```
+   */
+  async execute(): Promise<Table> {
+    const nativeTable: NativeTable = await this.inner.execute();
+    return new LocalTable(nativeTable);
+  }
+}
+
+/**
+ * Create a permutation builder for the given table.
+ *
+ * @param table - The source table to create a permutation from
+ * @returns A PermutationBuilder instance
+ * @example
+ * ```ts
+ * const builder = permutationBuilder(sourceTable, "training_data")
+ *   .splitRandom({ ratios: [0.8, 0.2], seed: 42 })
+ *   .shuffle({ seed: 123 });
+ *
+ * const trainingTable = await builder.execute();
+ * ```
+ */
+export function permutationBuilder(table: Table): PermutationBuilder {
+  // Extract the inner native table from the TypeScript wrapper
+  const localTable = table as LocalTable;
+  // Access inner through type assertion since it's private
+  const nativeBuilder = nativePermutationBuilder(
+    // biome-ignore lint/suspicious/noExplicitAny: need access to private variable
+    (localTable as any).inner,
+  );
+  return new PermutationBuilder(nativeBuilder);
+}

nodejs/lancedb/query.ts

@@ -20,35 +20,25 @@ import {
 } from "./native";
 import { Reranker } from "./rerankers";
 
-export class RecordBatchIterator implements AsyncIterator<RecordBatch> {
+export async function* RecordBatchIterator(
-  private promisedInner?: Promise<NativeBatchIterator>;
+  promisedInner: Promise<NativeBatchIterator>,
-  private inner?: NativeBatchIterator;
+) {
+  const inner = await promisedInner;
 
-  constructor(promise?: Promise<NativeBatchIterator>) {
+  if (inner === undefined) {
-    // TODO: check promise reliably so we dont need to pass two arguments.
+    throw new Error("Invalid iterator state");
-    this.promisedInner = promise;
   }
 
-  // biome-ignore lint/suspicious/noExplicitAny: skip
+  for (let buffer = await inner.next(); buffer; buffer = await inner.next()) {
-  async next(): Promise<IteratorResult<RecordBatch<any>>> {
+    const { batches } = tableFromIPC(buffer);
-    if (this.inner === undefined) {
+
-      this.inner = await this.promisedInner;
+    if (batches.length !== 1) {
-    }
-    if (this.inner === undefined) {
-      throw new Error("Invalid iterator state state");
-    }
-    const n = await this.inner.next();
-    if (n == null) {
-      return Promise.resolve({ done: true, value: null });
-    }
-    const tbl = tableFromIPC(n);
-    if (tbl.batches.length != 1) {
       throw new Error("Expected only one batch");
     }
-    return Promise.resolve({ done: false, value: tbl.batches[0] });
+
+    yield batches[0];
   }
 }
-/* eslint-enable */
 
 class RecordBatchIterable<
   NativeQueryType extends NativeQuery | NativeVectorQuery | NativeTakeQuery,
@@ -64,7 +54,7 @@ class RecordBatchIterable<
 
   // biome-ignore lint/suspicious/noExplicitAny: skip
   [Symbol.asyncIterator](): AsyncIterator<RecordBatch<any>, any, undefined> {
-    return new RecordBatchIterator(
+    return RecordBatchIterator(
       this.inner.execute(this.options?.maxBatchLength, this.options?.timeoutMs),
     );
   }
@@ -231,10 +221,8 @@ export class QueryBase<
    * single query)
    *
    */
-  protected execute(
+  protected execute(options?: Partial<QueryExecutionOptions>) {
-    options?: Partial<QueryExecutionOptions>,
+    return RecordBatchIterator(this.nativeExecute(options));
-  ): RecordBatchIterator {
-    return new RecordBatchIterator(this.nativeExecute(options));
   }
 
   /**
@@ -242,8 +230,7 @@ export class QueryBase<
    */
   // biome-ignore lint/suspicious/noExplicitAny: skip
   [Symbol.asyncIterator](): AsyncIterator<RecordBatch<any>> {
-    const promise = this.nativeExecute();
+    return RecordBatchIterator(this.nativeExecute());
-    return new RecordBatchIterator(promise);
   }
 
   /** Collect the results as an Arrow @see {@link ArrowTable}. */
@@ -326,6 +313,25 @@ export class QueryBase<
       return this.inner.analyzePlan();
     }
   }
+
+  /**
+   * Returns the schema of the output that will be returned by this query.
+   *
+   * This can be used to inspect the types and names of the columns that will be
+   * returned by the query before executing it.
+   *
+   * @returns An Arrow Schema describing the output columns.
+   */
+  async outputSchema(): Promise<import("./arrow").Schema> {
+    let schemaBuffer: Buffer;
+    if (this.inner instanceof Promise) {
+      schemaBuffer = await this.inner.then((inner) => inner.outputSchema());
+    } else {
+      schemaBuffer = await this.inner.outputSchema();
+    }
+    const schema = tableFromIPC(schemaBuffer).schema;
+    return schema;
+  }
 }
 
 export class StandardQueryBase<

nodejs/lancedb/sanitize.ts

@@ -326,6 +326,9 @@ export function sanitizeDictionary(typeLike: object) {
 
 // biome-ignore lint/suspicious/noExplicitAny: skip
 export function sanitizeType(typeLike: unknown): DataType<any> {
+  if (typeof typeLike === "string") {
+    return dataTypeFromName(typeLike);
+  }
   if (typeof typeLike !== "object" || typeLike === null) {
     throw Error("Expected a Type but object was null/undefined");
   }
@@ -447,7 +450,7 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
     case Type.DurationSecond:
       return new DurationSecond();
     default:
-      throw new Error("Unrecoginized type id in schema: " + typeId);
+      throw new Error("Unrecognized type id in schema: " + typeId);
   }
 }
 
@@ -467,7 +470,15 @@ export function sanitizeField(fieldLike: unknown): Field {
       "The field passed in is missing a `type`/`name`/`nullable` property",
     );
   }
-  const type = sanitizeType(fieldLike.type);
+  let type: DataType;
+  try {
+    type = sanitizeType(fieldLike.type);
+  } catch (error: unknown) {
+    throw Error(
+      `Unable to sanitize type for field: ${fieldLike.name} due to error: ${error}`,
+      { cause: error },
+    );
+  }
   const name = fieldLike.name;
   if (!(typeof name === "string")) {
     throw Error("The field passed in had a non-string `name` property");
@@ -581,3 +592,46 @@ function sanitizeData(
     },
   );
 }
+
+const constructorsByTypeName = {
+  null: () => new Null(),
+  binary: () => new Binary(),
+  utf8: () => new Utf8(),
+  bool: () => new Bool(),
+  int8: () => new Int8(),
+  int16: () => new Int16(),
+  int32: () => new Int32(),
+  int64: () => new Int64(),
+  uint8: () => new Uint8(),
+  uint16: () => new Uint16(),
+  uint32: () => new Uint32(),
+  uint64: () => new Uint64(),
+  float16: () => new Float16(),
+  float32: () => new Float32(),
+  float64: () => new Float64(),
+  datemillisecond: () => new DateMillisecond(),
+  dateday: () => new DateDay(),
+  timenanosecond: () => new TimeNanosecond(),
+  timemicrosecond: () => new TimeMicrosecond(),
+  timemillisecond: () => new TimeMillisecond(),
+  timesecond: () => new TimeSecond(),
+  intervaldaytime: () => new IntervalDayTime(),
+  intervalyearmonth: () => new IntervalYearMonth(),
+  durationnanosecond: () => new DurationNanosecond(),
+  durationmicrosecond: () => new DurationMicrosecond(),
+  durationmillisecond: () => new DurationMillisecond(),
+  durationsecond: () => new DurationSecond(),
+} as const;
+
+type MappableTypeName = keyof typeof constructorsByTypeName;
+
+export function dataTypeFromName(typeName: string): DataType {
+  const normalizedTypeName = typeName.toLowerCase() as MappableTypeName;
+  const _constructor = constructorsByTypeName[normalizedTypeName];
+
+  if (!_constructor) {
+    throw new Error("Unrecognized type name in schema: " + typeName);
+  }
+
+  return _constructor();
+}

nodejs/lancedb/table.ts

@@ -662,6 +662,8 @@ export class LocalTable extends Table {
       column,
       options?.replace,
       options?.waitTimeoutSeconds,
+      options?.name,
+      options?.train,
     );
   }
 

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"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": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"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": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"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": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"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": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"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": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"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": "0.21.2",
+  "version": "0.22.3-beta.5",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.21.2",
+	"version": "0.22.3-beta.5",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.21.2",
+  "version": "0.22.3-beta.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.21.2",
+      "version": "0.22.3-beta.5",
       "cpu": [
         "x64",
         "arm64"
@@ -5549,10 +5549,11 @@
       "dev": true
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.11",
+      "version": "1.1.12",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
-      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
+      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0",
         "concat-map": "0.0.1"
@@ -5629,6 +5630,20 @@
       "integrity": "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==",
       "dev": true
     },
+    "node_modules/call-bind-apply-helpers": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
+      "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "function-bind": "^1.1.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/camelcase": {
       "version": "5.3.1",
       "resolved": "https://registry.npmjs.org/camelcase/-/camelcase-5.3.1.tgz",
@@ -6032,6 +6047,21 @@
         "node": ">=6.0.0"
       }
     },
+    "node_modules/dunder-proto": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
+      "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "call-bind-apply-helpers": "^1.0.1",
+        "es-errors": "^1.3.0",
+        "gopd": "^1.2.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/eastasianwidth": {
       "version": "0.2.0",
       "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz",
@@ -6071,6 +6101,55 @@
         "is-arrayish": "^0.2.1"
       }
     },
+    "node_modules/es-define-property": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
+      "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
+      "devOptional": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-errors": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
+      "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
+      "devOptional": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-object-atoms": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
+      "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-set-tostringtag": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
+      "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "get-intrinsic": "^1.2.6",
+        "has-tostringtag": "^1.0.2",
+        "hasown": "^2.0.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/escalade": {
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.1.1.tgz",
@@ -6510,13 +6589,16 @@
       }
     },
     "node_modules/form-data": {
-      "version": "4.0.0",
+      "version": "4.0.4",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.0.tgz",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.4.tgz",
-      "integrity": "sha512-ETEklSGi5t0QMZuiXoA/Q6vcnxcLQP5vdugSpuAyi6SVGi2clPPp+xgEhuMaHC+zGgn31Kd235W35f7Hykkaww==",
+      "integrity": "sha512-KrGhL9Q4zjj0kiUt5OO4Mr/A/jlI2jDYs5eHBpYHPcBEVSiipAvn2Ko2HnPe20rmcuuvMHNdZFp+4IlGTMF0Ow==",
       "devOptional": true,
+      "license": "MIT",
       "dependencies": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
+        "es-set-tostringtag": "^2.1.0",
+        "hasown": "^2.0.2",
         "mime-types": "^2.1.12"
       },
       "engines": {
@@ -6575,7 +6657,7 @@
       "version": "1.1.2",
       "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
       "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
-      "dev": true,
+      "devOptional": true,
       "funding": {
         "url": "https://github.com/sponsors/ljharb"
       }
@@ -6598,6 +6680,31 @@
         "node": "6.* || 8.* || >= 10.*"
       }
     },
+    "node_modules/get-intrinsic": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
+      "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "call-bind-apply-helpers": "^1.0.2",
+        "es-define-property": "^1.0.1",
+        "es-errors": "^1.3.0",
+        "es-object-atoms": "^1.1.1",
+        "function-bind": "^1.1.2",
+        "get-proto": "^1.0.1",
+        "gopd": "^1.2.0",
+        "has-symbols": "^1.1.0",
+        "hasown": "^2.0.2",
+        "math-intrinsics": "^1.1.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
     "node_modules/get-package-type": {
       "version": "0.1.0",
       "resolved": "https://registry.npmjs.org/get-package-type/-/get-package-type-0.1.0.tgz",
@@ -6607,6 +6714,20 @@
         "node": ">=8.0.0"
       }
     },
+    "node_modules/get-proto": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
+      "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "dunder-proto": "^1.0.1",
+        "es-object-atoms": "^1.0.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/get-stream": {
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/get-stream/-/get-stream-6.0.1.tgz",
@@ -6698,6 +6819,19 @@
         "url": "https://github.com/sponsors/sindresorhus"
       }
     },
+    "node_modules/gopd": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
+      "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
+      "devOptional": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
     "node_modules/graceful-fs": {
       "version": "4.2.11",
       "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz",
@@ -6724,11 +6858,41 @@
         "node": ">=8"
       }
     },
+    "node_modules/has-symbols": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
+      "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
+      "devOptional": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/has-tostringtag": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
+      "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
+      "devOptional": true,
+      "license": "MIT",
+      "dependencies": {
+        "has-symbols": "^1.0.3"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
     "node_modules/hasown": {
-      "version": "2.0.0",
+      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.0.tgz",
+      "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
-      "integrity": "sha512-vUptKVTpIJhcczKBbgnS+RtcuYMB8+oNzPK2/Hp3hanz8JmpATdmmgLgSaadVREkDm+e2giHwY3ZRkyjSIDDFA==",
+      "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
-      "dev": true,
+      "devOptional": true,
+      "license": "MIT",
       "dependencies": {
         "function-bind": "^1.1.2"
       },
@@ -7943,6 +8107,16 @@
       "integrity": "sha512-8+9WqebbFzpX9OR+Wa6O29asIogeRMzcGtAINdpMHHyAg10f05aSFVBbcEqGf/PXw1EjAZ+q2/bEBg3DvurK3Q==",
       "dev": true
     },
+    "node_modules/math-intrinsics": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
+      "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
+      "devOptional": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/md5": {
       "version": "2.3.0",
       "resolved": "https://registry.npmjs.org/md5/-/md5-2.3.0.tgz",
@@ -8053,9 +8227,10 @@
       }
     },
     "node_modules/minizlib/node_modules/brace-expansion": {
-      "version": "2.0.1",
+      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
+      "license": "MIT",
       "optional": true,
       "dependencies": {
         "balanced-match": "^1.0.0"
@@ -9201,10 +9376,11 @@
       "dev": true
     },
     "node_modules/tmp": {
-      "version": "0.2.3",
+      "version": "0.2.5",
-      "resolved": "https://registry.npmjs.org/tmp/-/tmp-0.2.3.tgz",
+      "resolved": "https://registry.npmjs.org/tmp/-/tmp-0.2.5.tgz",
-      "integrity": "sha512-nZD7m9iCPC5g0pYmcaxogYKggSfLsdxl8of3Q/oIbqCqLLIO9IAF0GWjX1z9NZRHPiXv8Wex4yDCaZsgEw0Y8w==",
+      "integrity": "sha512-voyz6MApa1rQGUxT3E+BK7/ROe8itEx7vD8/HEvt4xwXucvQ5G5oeEiHkmHZJuBO21RpOf+YYm9MOivj709jow==",
       "dev": true,
+      "license": "MIT",
       "engines": {
         "node": ">=14.14"
       }
@@ -9349,10 +9525,11 @@
       }
     },
     "node_modules/typedoc/node_modules/brace-expansion": {
-      "version": "2.0.1",
+      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
@@ -9602,10 +9779,11 @@
       }
     },
     "node_modules/typescript-eslint/node_modules/brace-expansion": {
-      "version": "2.0.1",
+      "version": "2.0.2",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.21.2",
+  "version": "0.22.3-beta.5",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/connection.rs

@@ -2,12 +2,14 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use std::collections::HashMap;
+use std::sync::Arc;
 
-use lancedb::database::CreateTableMode;
+use lancedb::database::{CreateTableMode, Database};
 use napi::bindgen_prelude::*;
 use napi_derive::*;
 
 use crate::error::NapiErrorExt;
+use crate::header::JsHeaderProvider;
 use crate::table::Table;
 use crate::ConnectionOptions;
 use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection};
@@ -39,13 +41,21 @@ impl Connection {
             _ => Err(napi::Error::from_reason(format!("Invalid mode {}", mode))),
         }
     }
+
+    pub fn database(&self) -> napi::Result<Arc<dyn Database>> {
+        Ok(self.get_inner()?.database().clone())
+    }
 }
 
 #[napi]
 impl Connection {
     /// Create a new Connection instance from the given URI.
     #[napi(factory)]
-    pub async fn new(uri: String, options: ConnectionOptions) -> napi::Result<Self> {
+    pub async fn new(
+        uri: String,
+        options: ConnectionOptions,
+        header_provider: Option<&JsHeaderProvider>,
+    ) -> napi::Result<Self> {
         let mut builder = ConnectBuilder::new(&uri);
         if let Some(interval) = options.read_consistency_interval {
             builder =
@@ -57,8 +67,16 @@ impl Connection {
             }
         }
 
+        // Create client config, optionally with header provider
         let client_config = options.client_config.unwrap_or_default();
-        builder = builder.client_config(client_config.into());
+        let mut rust_config: lancedb::remote::ClientConfig = client_config.into();
+
+        if let Some(provider) = header_provider {
+            rust_config.header_provider =
+                Some(Arc::new(provider.clone()) as Arc<dyn lancedb::remote::HeaderProvider>);
+        }
+
+        builder = builder.client_config(rust_config);
 
         if let Some(api_key) = options.api_key {
             builder = builder.api_key(&api_key);
@@ -100,10 +118,12 @@ impl Connection {
     #[napi(catch_unwind)]
     pub async fn table_names(
         &self,
+        namespace: Vec<String>,
         start_after: Option<String>,
         limit: Option<u32>,
     ) -> napi::Result<Vec<String>> {
         let mut op = self.get_inner()?.table_names();
+        op = op.namespace(namespace);
         if let Some(start_after) = start_after {
             op = op.start_after(start_after);
         }
@@ -125,6 +145,7 @@ impl Connection {
         name: String,
         buf: Buffer,
         mode: String,
+        namespace: Vec<String>,
         storage_options: Option<HashMap<String, String>>,
     ) -> napi::Result<Table> {
         let batches = ipc_file_to_batches(buf.to_vec())
@@ -132,6 +153,8 @@ impl Connection {
         let mode = Self::parse_create_mode_str(&mode)?;
         let mut builder = self.get_inner()?.create_table(&name, batches).mode(mode);
 
+        builder = builder.namespace(namespace);
+
         if let Some(storage_options) = storage_options {
             for (key, value) in storage_options {
                 builder = builder.storage_option(key, value);
@@ -147,6 +170,7 @@ impl Connection {
         name: String,
         schema_buf: Buffer,
         mode: String,
+        namespace: Vec<String>,
         storage_options: Option<HashMap<String, String>>,
     ) -> napi::Result<Table> {
         let schema = ipc_file_to_schema(schema_buf.to_vec()).map_err(|e| {
@@ -157,6 +181,9 @@ impl Connection {
             .get_inner()?
             .create_empty_table(&name, schema)
             .mode(mode);
+
+        builder = builder.namespace(namespace);
+
         if let Some(storage_options) = storage_options {
             for (key, value) in storage_options {
                 builder = builder.storage_option(key, value);
@@ -170,10 +197,14 @@ impl Connection {
     pub async fn open_table(
         &self,
         name: String,
+        namespace: Vec<String>,
         storage_options: Option<HashMap<String, String>>,
         index_cache_size: Option<u32>,
     ) -> napi::Result<Table> {
         let mut builder = self.get_inner()?.open_table(&name);
+
+        builder = builder.namespace(namespace);
+
         if let Some(storage_options) = storage_options {
             for (key, value) in storage_options {
                 builder = builder.storage_option(key, value);
@@ -186,14 +217,50 @@ impl Connection {
         Ok(Table::new(tbl))
     }
 
+    #[napi(catch_unwind)]
+    pub async fn clone_table(
+        &self,
+        target_table_name: String,
+        source_uri: String,
+        target_namespace: Vec<String>,
+        source_version: Option<i64>,
+        source_tag: Option<String>,
+        is_shallow: bool,
+    ) -> napi::Result<Table> {
+        let mut builder = self
+            .get_inner()?
+            .clone_table(&target_table_name, &source_uri);
+
+        builder = builder.target_namespace(target_namespace);
+
+        if let Some(version) = source_version {
+            builder = builder.source_version(version as u64);
+        }
+
+        if let Some(tag) = source_tag {
+            builder = builder.source_tag(tag);
+        }
+
+        builder = builder.is_shallow(is_shallow);
+
+        let tbl = builder.execute().await.default_error()?;
+        Ok(Table::new(tbl))
+    }
+
     /// Drop table with the name. Or raise an error if the table does not exist.
     #[napi(catch_unwind)]
-    pub async fn drop_table(&self, name: String) -> napi::Result<()> {
+    pub async fn drop_table(&self, name: String, namespace: Vec<String>) -> napi::Result<()> {
-        self.get_inner()?.drop_table(&name).await.default_error()
+        self.get_inner()?
+            .drop_table(&name, &namespace)
+            .await
+            .default_error()
     }
 
     #[napi(catch_unwind)]
-    pub async fn drop_all_tables(&self) -> napi::Result<()> {
+    pub async fn drop_all_tables(&self, namespace: Vec<String>) -> napi::Result<()> {
-        self.get_inner()?.drop_all_tables().await.default_error()
+        self.get_inner()?
+            .drop_all_tables(&namespace)
+            .await
+            .default_error()
     }
 }

nodejs/src/header.rs

@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+use napi::{
+    bindgen_prelude::*,
+    threadsafe_function::{ErrorStrategy, ThreadsafeFunction},
+};
+use napi_derive::napi;
+use std::collections::HashMap;
+use std::sync::Arc;
+
+/// JavaScript HeaderProvider implementation that wraps a JavaScript callback.
+/// This is the only native header provider - all header provider implementations
+/// should provide a JavaScript function that returns headers.
+#[napi]
+pub struct JsHeaderProvider {
+    get_headers_fn: Arc<ThreadsafeFunction<(), ErrorStrategy::CalleeHandled>>,
+}
+
+impl Clone for JsHeaderProvider {
+    fn clone(&self) -> Self {
+        Self {
+            get_headers_fn: self.get_headers_fn.clone(),
+        }
+    }
+}
+
+#[napi]
+impl JsHeaderProvider {
+    /// Create a new JsHeaderProvider from a JavaScript callback
+    #[napi(constructor)]
+    pub fn new(get_headers_callback: JsFunction) -> Result<Self> {
+        let get_headers_fn = get_headers_callback
+            .create_threadsafe_function(0, |ctx| Ok(vec![ctx.value]))
+            .map_err(|e| {
+                Error::new(
+                    Status::GenericFailure,
+                    format!("Failed to create threadsafe function: {}", e),
+                )
+            })?;
+
+        Ok(Self {
+            get_headers_fn: Arc::new(get_headers_fn),
+        })
+    }
+}
+
+#[cfg(feature = "remote")]
+#[async_trait::async_trait]
+impl lancedb::remote::HeaderProvider for JsHeaderProvider {
+    async fn get_headers(&self) -> lancedb::error::Result<HashMap<String, String>> {
+        // Call the JavaScript function asynchronously
+        let promise: Promise<HashMap<String, String>> =
+            self.get_headers_fn.call_async(Ok(())).await.map_err(|e| {
+                lancedb::error::Error::Runtime {
+                    message: format!("Failed to call JavaScript get_headers: {}", e),
+                }
+            })?;
+
+        // Await the promise result
+        promise.await.map_err(|e| lancedb::error::Error::Runtime {
+            message: format!("JavaScript get_headers failed: {}", e),
+        })
+    }
+}
+
+impl std::fmt::Debug for JsHeaderProvider {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        write!(f, "JsHeaderProvider")
+    }
+}

nodejs/src/index.rs

@@ -6,6 +6,7 @@ use std::sync::Mutex;
 use lancedb::index::scalar::{BTreeIndexBuilder, FtsIndexBuilder};
 use lancedb::index::vector::{
     IvfFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder,
+    IvfRqIndexBuilder,
 };
 use lancedb::index::Index as LanceDbIndex;
 use napi_derive::napi;
@@ -65,6 +66,36 @@ impl Index {
         })
     }
 
+    #[napi(factory)]
+    pub fn ivf_rq(
+        distance_type: Option<String>,
+        num_partitions: Option<u32>,
+        num_bits: Option<u32>,
+        max_iterations: Option<u32>,
+        sample_rate: Option<u32>,
+    ) -> napi::Result<Self> {
+        let mut ivf_rq_builder = IvfRqIndexBuilder::default();
+        if let Some(distance_type) = distance_type {
+            let distance_type = parse_distance_type(distance_type)?;
+            ivf_rq_builder = ivf_rq_builder.distance_type(distance_type);
+        }
+        if let Some(num_partitions) = num_partitions {
+            ivf_rq_builder = ivf_rq_builder.num_partitions(num_partitions);
+        }
+        if let Some(num_bits) = num_bits {
+            ivf_rq_builder = ivf_rq_builder.num_bits(num_bits);
+        }
+        if let Some(max_iterations) = max_iterations {
+            ivf_rq_builder = ivf_rq_builder.max_iterations(max_iterations);
+        }
+        if let Some(sample_rate) = sample_rate {
+            ivf_rq_builder = ivf_rq_builder.sample_rate(sample_rate);
+        }
+        Ok(Self {
+            inner: Mutex::new(Some(LanceDbIndex::IvfRq(ivf_rq_builder))),
+        })
+    }
+
     #[napi(factory)]
     pub fn ivf_flat(
         distance_type: Option<String>,

nodejs/src/lib.rs

@@ -8,9 +8,11 @@ use napi_derive::*;
 
 mod connection;
 mod error;
+mod header;
 mod index;
 mod iterator;
 pub mod merge;
+pub mod permutation;
 mod query;
 pub mod remote;
 mod rerankers;

nodejs/src/merge.rs

@@ -43,6 +43,13 @@ impl NativeMergeInsertBuilder {
         self.inner.timeout(Duration::from_millis(timeout as u64));
     }
 
+    #[napi]
+    pub fn use_index(&self, use_index: bool) -> Self {
+        let mut this = self.clone();
+        this.inner.use_index(use_index);
+        this
+    }
+
     #[napi(catch_unwind)]
     pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
         let data = ipc_file_to_batches(buf.to_vec())