chore: update lance dependency to v5.1.0-beta.1

.agents/skills/README.md

@@ -1,7 +0,0 @@
-# Agent Skills
-
-This directory contains repo-scoped code agent skills for the LanceDB project.
-
-Each skill is a folder that contains a required `SKILL.md` and optional bundled resources.
-
-Codex discovers skills from `.agents/skills` in the current working directory and parent directories.

.agents/skills/lancedb-update-lance-dependency/SKILL.md

@@ -1,98 +0,0 @@
----
-name: lancedb-update-lance-dependency
-description: Update LanceDB to a specific Lance release or tag. Use when bumping Lance dependencies in the lancedb repository, including Rust workspace Lance crates, Java lance-core, validation, branch creation, commit, push, and PR creation when requested.
----
-
-# LanceDB Update Lance Dependency
-
-## Scope
-
-Use this skill in the `lancedb/lancedb` repository when updating the Lance dependency to a specific Lance version or tag.
-
-Inputs can be a version (`7.2.0-beta.1`), a tag (`v7.2.0-beta.1`), a tag ref (`refs/tags/v7.2.0-beta.1`), or `latest`.
-
-## Workflow
-
-1. Confirm the worktree status with `git status --short`.
-2. Resolve the target Lance version:
-
-   - If the input is `latest`, empty, or omitted, run:
-
-     ```bash
-     python3 ci/check_lance_release.py
-     ```
-
-     Parse the JSON output. If `needs_update` is not `true`, stop without creating a PR. Otherwise use `latest_tag`.
-
-   - If the input is explicit, use it directly.
-
-3. Compute update metadata without changing files:
-
-   ```bash
-   python3 ci/update_lance_dependency.py "$TAG_OR_VERSION" --metadata-only
-   ```
-
-   Before making changes, check for an existing open PR with the emitted `pr_title`:
-
-   ```bash
-   gh pr list --search "\"$PR_TITLE\" in:title" --state open --limit 1 --json number,url,title
-   ```
-
-   If a matching open PR exists, stop and report it instead of creating a duplicate.
-
-4. Run the deterministic update entrypoint:
-
-   ```bash
-   python3 ci/update_lance_dependency.py "$TAG_OR_VERSION"
-   ```
-
-   This updates the Rust workspace Lance dependencies through `ci/set_lance_version.py`, updates `java/pom.xml`, refreshes Cargo metadata, and prints JSON metadata containing `branch_name`, `commit_message`, and `pr_title`.
-
-5. Run validation:
-
-   ```bash
-   cargo clippy --quiet --workspace --tests --all-features -- -D warnings
-   cargo fmt --all --quiet
-   ```
-
-   Fix real diagnostics and rerun clippy until it succeeds. Do not skip warnings.
-
-6. Inspect `git status --short` and `git diff` to ensure only the Lance dependency update and required compatibility fixes are present.
-
-7. If the task only asks to prepare local changes, stop here and report the changed files and validation result.
-
-8. If the task asks to publish the update, create a branch using the printed `branch_name`, stage all relevant files, and commit using the printed `commit_message`. Do not amend or rewrite existing commits.
-
-9. Push to `origin`. Before creating the PR, check that the current token has push permission:
-
-   ```bash
-   gh api repos/lancedb/lancedb --jq .permissions.push
-   ```
-
-   If the remote branch already exists for the same generated branch name, delete the remote ref with `gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/$BRANCH_NAME`, then push. Do not force-push.
-
-10. Create a PR targeting `main` with the printed `pr_title`. If there is no PR template, keep the body to two or three concise sentences: state the Lance dependency bump, note any required compatibility fixes, and link the triggering Lance tag or release.
-
-11. Read back the remote PR title after creation. If it is not a Conventional Commit title, fix it immediately.
-
-12. When running in GitHub Actions after creating the LanceDB PR, trigger the Sophon dependency update:
-
-    ```bash
-    gh workflow run codex-bump-lancedb-lance.yml \
-      --repo lancedb/sophon \
-      -f lance_ref="$LANCE_TAG" \
-      -f lancedb_ref="$BRANCH_NAME"
-    gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle
-    ```
-
-    Use the emitted metadata `tag` value as `LANCE_TAG`. Do this only after a new LanceDB PR has been created. If the update was skipped because no update is needed or an open PR already exists, do not trigger Sophon.
-
-## GitHub Actions
-
-When this skill is used from GitHub Actions, `TAG`, `GH_TOKEN`, and `GITHUB_TOKEN` may already be set. Resolve `latest` first when `TAG` is empty. Once an explicit tag or version is known, use:
-
-```bash
-python3 ci/update_lance_dependency.py "$TAG" --github-output "$GITHUB_OUTPUT"
-```
-
-Then use the emitted `branch_name`, `commit_message`, and `pr_title` values for branch, commit, and PR creation.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.30.1-beta.0"
+current_version = "0.28.0-beta.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/ISSUE_TEMPLATE/documentation.yml

@@ -18,6 +18,6 @@ body:
       label: Link
       description: >
         Provide a link to the existing documentation, if applicable.
-      placeholder: ex. https://docs.lancedb.com/tables/...
+      placeholder: ex. https://lancedb.com/docs/tables/...
     validations:
       required: false

.github/dependabot.yml

@@ -1,23 +0,0 @@
-version: 2
-
-# Scope: the root Cargo workspace, which produces the Rust binaries we
-# ship to users (the Node.js and Python native extensions). The
-# `rust/lancedb` library crate shares the same lockfile; its consumers
-# pick their own dependency versions, but bumping transitive deps here
-# keeps the binaries we ship current.
-updates:
-  - package-ecosystem: cargo
-    directory: /
-    schedule:
-      interval: weekly
-    open-pull-requests-limit: 10
-    # Only update Cargo.lock, never widen/raise the version requirements in
-    # Cargo.toml. The goal is keeping the lockfile (and the binaries we ship)
-    # current on security fixes, not forcing our library's consumers onto
-    # newer minimum versions.
-    versioning-strategy: lockfile-only
-    groups:
-      rust-minor-patch:
-        update-types:
-          - minor
-          - patch

.github/workflows/build_windows_wheel/action.yml

@@ -29,3 +29,7 @@ runs:
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python
+    - uses: actions/upload-artifact@v4
+      with:
+        name: windows-wheels
+        path: python\target\wheels

.github/workflows/codex-fix-ci.yml

@@ -45,9 +45,7 @@ jobs:
       - name: Set up Node.js
         uses: actions/setup-node@v4
         with:
-          # pnpm 11 (used by the nodejs install step below) requires
+          node-version: 20
-          # Node >= 22.13; use 24 since 22 hits EOL in October.
-          node-version: 24
 
       - name: Install Codex CLI
         run: npm install -g @openai/codex
@@ -81,14 +79,10 @@ jobs:
           java-version: '11'
           cache: maven
 
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 11.1.1
       - name: Install Node.js dependencies for TypeScript bindings
         run: |
           cd nodejs
-          pnpm install --frozen-lockfile
+          npm ci
 
       - name: Configure git user
         run: |
@@ -143,7 +137,7 @@ jobs:
                - For Rust test failures: Run the specific test with "cargo test -p <crate> <test_name>"
                - For Python test failures: Build with "cd python && maturin develop" then run "pytest <specific_test_file>::<test_name>"
                - For Java test failures: Run "cd java && mvn test -Dtest=<TestClass>#<testMethod>"
-               - For TypeScript test failures: Run "cd nodejs && pnpm build && pnpm test -- --testNamePattern='<test_name>'"
+               - For TypeScript test failures: Run "cd nodejs && npm run build && npm test -- --testNamePattern='<test_name>'"
                - Do NOT run the full test suite - only run the tests that were failing
 
           7. If the additional guidelines are provided, follow them as well.

.github/workflows/codex-update-lance-dependency.yml

@@ -4,16 +4,14 @@ on:
   workflow_call:
     inputs:
       tag:
-        description: "Tag name from Lance. If omitted, the skill will use the latest Lance release that needs an update."
+        description: "Tag name from Lance"
-        required: false
+        required: true
-        default: ""
         type: string
   workflow_dispatch:
     inputs:
       tag:
-        description: "Tag name from Lance. Leave empty to use the latest Lance release that needs an update."
+        description: "Tag name from Lance"
-        required: false
+        required: true
-        default: ""
         type: string
 
 permissions:
@@ -27,7 +25,7 @@ jobs:
     steps:
       - name: Show inputs
         run: |
-          echo "tag = ${{ inputs.tag || 'latest' }}"
+          echo "tag = ${{ inputs.tag }}"
 
       - name: Checkout Repo LanceDB
         uses: actions/checkout@v4
@@ -73,21 +71,65 @@ jobs:
           OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
         run: |
           set -euo pipefail
-          TARGET_TAG="${TAG:-latest}"
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          # Use "chore" for beta/rc versions, "feat" for stable releases
+          if [[ "${VERSION}" == *beta* ]] || [[ "${VERSION}" == *rc* ]]; then
+            COMMIT_TYPE="chore"
+          else
+            COMMIT_TYPE="feat"
+          fi
 
           cat <<EOF >/tmp/codex-prompt.txt
-          You are running inside the lancedb repository on a GitHub Actions runner.
+          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.
 
-          Use \$lancedb-update-lance-dependency with target "${TARGET_TAG}".
+          Follow these steps exactly:
+          1. Use script "ci/set_lance_version.py" to update Lance Rust dependencies. The script already refreshes Cargo metadata, so allow it to finish even if it takes time.
+          2. Update the Java lance-core dependency version in "java/pom.xml": change the "<lance-core.version>...</lance-core.version>" property to "${VERSION}".
+          3. 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.
+          4. After clippy succeeds, run "cargo fmt --all" to format the workspace.
+          5. 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.
+          6. Create and switch to a new branch named "${BRANCH_NAME}" (replace any duplicated hyphens if necessary).
+          7. Stage all relevant files with "git add -A". Commit using the message "${COMMIT_TYPE}: update lance dependency to v${VERSION}".
+          8. Push the branch to origin. If the remote branch already exists, delete it first with "gh api -X DELETE repos/lancedb/lancedb/git/refs/heads/${BRANCH_NAME}" then push with "git push origin ${BRANCH_NAME}". Do NOT use "git push --force" or "git push -f".
+          9. env "GH_TOKEN" is available, use "gh" tools for github related operations like creating pull request.
+          10. Create a pull request targeting "main" with title "${COMMIT_TYPE}: update lance dependency to v${VERSION}". First, write the PR body to /tmp/pr-body.md using a heredoc (cat <<'EOF' > /tmp/pr-body.md). The body should summarize the dependency bump, clippy/fmt verification, and link the triggering tag (${TAG}). Then run "gh pr create --body-file /tmp/pr-body.md".
+          11. After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
 
           Constraints:
-          - Use env "GH_TOKEN" for GitHub operations.
+          - Use bash commands; avoid modifying GitHub workflow files other than through the scripted task above.
-          - Do not merge the pull request.
+          - Do not merge the PR.
-          - Do not force-push.
+          - If any command fails, diagnose and fix the issue instead of aborting.
-          - Do not create a duplicate pull request if an open PR already exists for the target Lance version.
-          - If any command fails, diagnose and fix the root cause instead of aborting.
-          - After creating the PR, display the PR URL, "git status --short", and a concise summary of the commands run and their results.
           EOF
 
           printenv OPENAI_API_KEY | codex login --with-api-key
           codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"
+
+      - name: Trigger sophon dependency update
+        env:
+          TAG: ${{ inputs.tag }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          LANCEDB_BRANCH="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          echo "Triggering sophon workflow with:"
+          echo "  lance_ref: ${TAG#refs/tags/}"
+          echo "  lancedb_ref: ${LANCEDB_BRANCH}"
+
+          gh workflow run codex-bump-lancedb-lance.yml \
+            --repo lancedb/sophon \
+            -f lance_ref="${TAG#refs/tags/}" \
+            -f lancedb_ref="${LANCEDB_BRANCH}"
+
+      - name: Show latest sophon workflow run
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          echo "Latest sophon workflow run:"
+          gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/dev.yml

@@ -8,9 +8,6 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
-permissions:
-  contents: read
-
 jobs:
   labeler:
     permissions:

.github/workflows/java-publish.yml

@@ -19,9 +19,6 @@ on:
     paths:
       - .github/workflows/java-publish.yml
 
-permissions:
-  contents: read
-
 jobs:
   publish:
     name: Build and Publish
@@ -43,7 +40,7 @@ jobs:
           server-username: SONATYPE_USER
           server-password: SONATYPE_TOKEN
           gpg-private-key: ${{ secrets.GPG_PRIVATE_KEY }}
-          gpg-passphrase: MAVEN_GPG_PASSPHRASE
+          gpg-passphrase: ${{ secrets.GPG_PASSPHRASE }}
       - name: Set git config
         run: |
           git config --global user.email "dev+gha@lancedb.com"
@@ -58,11 +55,10 @@ jobs:
           echo "use-agent" >> ~/.gnupg/gpg.conf
           echo "pinentry-mode loopback" >> ~/.gnupg/gpg.conf
           export GPG_TTY=$(tty)
-          ./mvnw --batch-mode -DskipTests -DpushChanges=false deploy -pl lancedb-core -am -P deploy-to-ossrh
+          ./mvnw --batch-mode -DskipTests -DpushChanges=false -Dgpg.passphrase=${{ secrets.GPG_PASSPHRASE }} deploy -pl lancedb-core -am -P deploy-to-ossrh
         env:
           SONATYPE_USER: ${{ secrets.SONATYPE_USER }}
           SONATYPE_TOKEN: ${{ secrets.SONATYPE_TOKEN }}
-          MAVEN_GPG_PASSPHRASE: ${{ secrets.GPG_PASSPHRASE }}
 
   report-failure:
     name: Report Workflow Failure

.github/workflows/java.yml

@@ -24,9 +24,6 @@ on:
       - java/**
       - .github/workflows/java.yml
 
-permissions:
-  contents: read
-
 jobs:
   build-java:
     runs-on: ubuntu-24.04

.github/workflows/lance-release-timer.yml

@@ -0,0 +1,62 @@
+name: Lance Release Timer
+
+on:
+  schedule:
+    - cron: "*/10 * * * *"
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  actions: write
+
+concurrency:
+  group: lance-release-timer
+  cancel-in-progress: false
+
+jobs:
+  trigger-update:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Check for new Lance tag
+        id: check
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          python3 ci/check_lance_release.py --github-output "$GITHUB_OUTPUT"
+
+      - name: Look for existing PR
+        if: steps.check.outputs.needs_update == 'true'
+        id: pr
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          TITLE="chore: update lance dependency to v${{ steps.check.outputs.latest_version }}"
+          COUNT=$(gh pr list --search "\"$TITLE\" in:title" --state open --limit 1 --json number --jq 'length')
+          if [ "$COUNT" -gt 0 ]; then
+            echo "Open PR already exists for $TITLE"
+            echo "pr_exists=true" >> "$GITHUB_OUTPUT"
+          else
+            echo "No existing PR for $TITLE"
+            echo "pr_exists=false" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Trigger codex update workflow
+        if: steps.check.outputs.needs_update == 'true' && steps.pr.outputs.pr_exists != 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          TAG=${{ steps.check.outputs.latest_tag }}
+          gh workflow run codex-update-lance-dependency.yml -f tag=refs/tags/$TAG
+
+      - name: Show latest codex workflow run
+        if: steps.check.outputs.needs_update == 'true' && steps.pr.outputs.pr_exists != 'true'
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/license-header-check.yml

@@ -10,10 +10,6 @@ on:
       - nodejs/**
       - java/**
       - .github/workflows/license-header-check.yml
-
-permissions:
-  contents: read
-
 jobs:
   check-licenses:
     runs-on: ubuntu-latest

.github/workflows/nodejs.yml

@@ -15,9 +15,6 @@ on:
       - .github/workflows/nodejs.yml
       - docker-compose.yml
 
-permissions:
-  contents: read
-
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -42,17 +39,11 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v4
-      with:
-        version: 11.1.1
     - uses: actions/setup-node@v4
       with:
-        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        node-version: 20
-        # in October. The library itself still supports Node >= 18
+        cache: 'npm'
-        # (see test matrix below).
+        cache-dependency-path: nodejs/package-lock.json
-        node-version: 24
-        cache: 'pnpm'
-        cache-dependency-path: nodejs/pnpm-lock.yaml
     - uses: actions-rust-lang/setup-rust-toolchain@v1
       with:
         components: rustfmt, clippy
@@ -67,13 +58,11 @@ jobs:
       run: cargo clippy --profile ci --all --all-features -- -D warnings
     - name: Lint Typescript
       run: |
-        pnpm install --frozen-lockfile
+        npm ci
-        pnpm lint-ci
+        npm run lint-ci
     - name: Lint examples
       working-directory: nodejs/examples
-      # The `@lancedb/lancedb` dep points at file:../dist; pnpm errors if
+      run: npm ci && npm run lint-ci
-      # that dir is missing, so create an empty one for lint-only runs.
-      run: mkdir -p ../dist && pnpm install --frozen-lockfile && pnpm lint-ci
   linux:
     name: Linux (NodeJS ${{ matrix.node-version }})
     timeout-minutes: 30
@@ -90,18 +79,14 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v4
-      with:
-        version: 11.1.1
     - uses: actions/setup-node@v4
-      name: Setup Node.js 24 for build
+      name: Setup Node.js 20 for build
       with:
-        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # @napi-rs/cli v3 requires Node >= 20.12 (via @inquirer/prompts@8).
-        # in October. Build/install runs on Node 24; tests run on the
+        # Build always on Node 20; tests run on the matrix version below.
-        # matrix version below using direct jest invocation.
+        node-version: 20
-        node-version: 24
+        cache: 'npm'
-        cache: 'pnpm'
+        cache-dependency-path: nodejs/package-lock.json
-        cache-dependency-path: nodejs/pnpm-lock.yaml
     - uses: Swatinem/rust-cache@v2
     - name: Install dependencies
       run: |
@@ -109,58 +94,48 @@ jobs:
         sudo apt install -y protobuf-compiler libssl-dev
     - name: Build
       run: |
-        pnpm install --frozen-lockfile
+        npm ci --include=optional
-        # No `--` separator: pnpm forwards it literally, which would
+        npm run build:debug -- --profile ci
-        # make napi-rs treat `--profile ci` as a cargo passthrough arg.
-        pnpm build:debug --profile ci
-        pnpm tsc
-    - name: Setup examples
-      working-directory: nodejs/examples
-      run: pnpm install --frozen-lockfile
-    - name: Check docs
-      run: |
-        # We run this as part of the job because the binary needs to be built
-        # first to export the types of the native code.
-        set -e
-        # `pnpm docs` would invoke pnpm's built-in `docs` command, not
-        # the script — use `pnpm run docs`.
-        pnpm run docs
-        if ! git diff --exit-code -- ../ ':(exclude)Cargo.lock'; then
-          echo "Docs need to be updated"
-          echo "Run 'pnpm run docs', fix any warnings, and commit the changes."
-          exit 1
-        fi
     - uses: actions/setup-node@v4
       name: Setup Node.js ${{ matrix.node-version }} for test
       with:
         node-version: ${{ matrix.node-version }}
+    - name: Compile TypeScript
+      run: npm run tsc
     - name: Setup localstack
       working-directory: .
       run: docker compose up --detach --wait
     - name: Test
       env:
         S3_TEST: "1"
-        # Newer @smithy/core uses dynamic ESM imports.
+      run: npm run test
-        NODE_OPTIONS: "--experimental-vm-modules"
+    - name: Setup examples
-      # Invoke jest directly because pnpm 11 itself requires Node 22+
+      working-directory: nodejs/examples
-      # while the matrix tests on older Node versions.
+      run: npm ci
-      run: npx jest --verbose
     - name: Test examples
       working-directory: ./
       env:
         OPENAI_API_KEY: test
         OPENAI_BASE_URL: http://0.0.0.0:8000
-        NODE_OPTIONS: "--experimental-vm-modules"
       run: |
         python ci/mock_openai.py &
         cd nodejs/examples
-        npx jest --testEnvironment jest-environment-node-single-context --verbose
+        npm test
+    - name: Check docs
+      run: |
+        # We run this as part of the job because the binary needs to be built
+        # first to export the types of the native code.
+        set -e
+        npm ci
+        npm run docs
+        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
+        fi
   macos:
     timeout-minutes: 30
-    # macos-15 ships a newer linker; the older macos-14 linker fails to insert
+    runs-on: "macos-14"
-    # branch islands when the debug cdylib's __text section exceeds the 128 MB
-    # AArch64 B/BL branch range.
-    runs-on: "macos-15"
     defaults:
       run:
         shell: bash
@@ -170,28 +145,20 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: pnpm/action-setup@v4
-      with:
-        version: 11.1.1
     - uses: actions/setup-node@v4
       with:
-        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        node-version: 20
-        # in October.
+        cache: 'npm'
-        node-version: 24
+        cache-dependency-path: nodejs/package-lock.json
-        cache: 'pnpm'
-        cache-dependency-path: nodejs/pnpm-lock.yaml
-    - uses: dtolnay/rust-toolchain@stable
     - uses: Swatinem/rust-cache@v2
     - name: Install dependencies
       run: |
         brew install protobuf
     - name: Build
       run: |
-        pnpm install --frozen-lockfile
+        npm ci --include=optional
-        # No `--` separator: pnpm forwards it literally, which would
+        npm run build:debug -- --profile ci
-        # make napi-rs treat `--profile ci` as a cargo passthrough arg.
+        npm run tsc
-        pnpm build:debug --profile ci
-        pnpm tsc
     - name: Test
       run: |
-        pnpm test
+        npm run test

.github/workflows/npm-publish.yml

@@ -171,18 +171,13 @@ jobs:
         working-directory: nodejs
     steps:
       - uses: actions/checkout@v4
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 11.1.1
       - name: Setup node
         uses: actions/setup-node@v4
+        if: ${{ !matrix.settings.docker }}
         with:
-          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+          node-version: 20
-          # in October.
+          cache: npm
-          node-version: 24
+          cache-dependency-path: nodejs/package-lock.json
-          cache: pnpm
-          cache-dependency-path: nodejs/pnpm-lock.yaml
       - name: Install
         uses: dtolnay/rust-toolchain@stable
         if: ${{ !matrix.settings.docker }}
@@ -200,7 +195,7 @@ jobs:
             target/
           key: nodejs-${{ matrix.settings.target }}-cargo-${{ matrix.settings.host }}
       - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+        run: npm ci
       - name: Install Zig
         uses: mlugg/setup-zig@v2
         if: ${{ contains(matrix.settings.target, 'musl') }}
@@ -253,7 +248,7 @@ jobs:
       # one to do the upload.
       - name: Make generic artifacts
         if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
-        run: pnpm tsc
+        run: npm run tsc
       - name: Upload Generic Artifacts
         if: ${{ matrix.settings.target == 'aarch64-apple-darwin' }}
         uses: actions/upload-artifact@v4
@@ -288,24 +283,14 @@ jobs:
         working-directory: nodejs
     steps:
       - uses: actions/checkout@v4
-      - name: Setup pnpm
+      - name: Setup node
-        uses: pnpm/action-setup@v4
-        with:
-          version: 11.1.1
-      - name: Setup Node.js 24 for install
-        uses: actions/setup-node@v4
-        with:
-          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
-          # in October.
-          node-version: 24
-          cache: pnpm
-          cache-dependency-path: nodejs/pnpm-lock.yaml
-      - name: Install dependencies
-        run: pnpm install --frozen-lockfile
-      - name: Setup Node.js ${{ matrix.node }} for test
         uses: actions/setup-node@v4
         with:
           node-version: ${{ matrix.node }}
+          cache: npm
+          cache-dependency-path: nodejs/package-lock.json
+      - name: Install dependencies
+        run: npm ci
       - name: Download artifacts
         uses: actions/download-artifact@v4
         with:
@@ -326,9 +311,7 @@ jobs:
       - name: Move built files
         run: cp dist/native.d.ts dist/native.js dist/*.node lancedb/
       - name: Test bindings
-        # Invoke jest directly because pnpm 11 itself requires Node 22+
+        run: npm test
-        # while the matrix tests on older Node versions.
-        run: npx jest --verbose
   publish:
     name: Publish
     runs-on: ubuntu-latest
@@ -340,19 +323,15 @@ jobs:
       - test-lancedb
     steps:
       - uses: actions/checkout@v4
-      - name: Setup pnpm
-        uses: pnpm/action-setup@v4
-        with:
-          version: 11.1.1
       - name: Setup node
         uses: actions/setup-node@v4
         with:
           node-version: 24
-          cache: pnpm
+          cache: npm
-          cache-dependency-path: nodejs/pnpm-lock.yaml
+          cache-dependency-path: nodejs/package-lock.json
           registry-url: "https://registry.npmjs.org"
       - name: Install dependencies
-        run: pnpm install --frozen-lockfile
+        run: npm ci
       - uses: actions/download-artifact@v4
         with:
           name: nodejs-dist
@@ -372,7 +351,7 @@ jobs:
       - name: Display structure of downloaded files
         run: find dist && find nodejs-artifacts
       - name: Move artifacts
-        run: pnpm exec napi artifacts -d nodejs-artifacts
+        run: npx napi artifacts -d nodejs-artifacts
       - name: List packages
         run: find npm
       - name: Publish

.github/workflows/pypi-publish.yml

@@ -8,18 +8,12 @@ on:
     # This should trigger a dry run (we skip the final publish step)
     paths:
       - .github/workflows/pypi-publish.yml
-      - .github/workflows/build_linux_wheel/action.yml
-      - .github/workflows/build_mac_wheel/action.yml
-      - .github/workflows/build_windows_wheel/action.yml
       - Cargo.toml # Change in dependency frequently breaks builds
       - Cargo.lock
 
 env:
   PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
-permissions:
-  contents: read
-
 jobs:
   linux:
     name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}
@@ -27,18 +21,26 @@ jobs:
     strategy:
       matrix:
         config:
+          - platform: x86_64
+            manylinux: "2_17"
+            extra_args: ""
+            runner: ubuntu-22.04
           - platform: x86_64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
             runner: ubuntu-22.04
-          # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+          - platform: aarch64
+            manylinux: "2_17"
+            extra_args: ""
+            # For successful fat LTO builds, we need a large runner to avoid OOM errors.
+            runner: ubuntu-2404-8x-arm64
           - platform: aarch64
             manylinux: "2_28"
             extra_args: "--features fp16kernels"
             runner: ubuntu-2404-8x-arm64
     runs-on: ${{ matrix.config.runner }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -52,12 +54,11 @@ jobs:
           args: "--release --strip ${{ matrix.config.extra_args }}"
           arm-build: ${{ matrix.config.platform == 'aarch64' }}
           manylinux: ${{ matrix.config.manylinux }}
-      - uses: actions/upload-artifact@v7
+      - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-linux-${{ matrix.config.platform }}-${{ matrix.config.manylinux }}
+          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          path: target/wheels/lancedb-*.whl
+          fury_token: ${{ secrets.FURY_TOKEN }}
-          if-no-files-found: error
   mac:
     timeout-minutes: 90
     runs-on: ${{ matrix.config.runner }}
@@ -69,7 +70,7 @@ jobs:
     env:
       MACOSX_DEPLOYMENT_TARGET: 10.15
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -81,21 +82,16 @@ jobs:
         with:
           python-minor-version: 10
           args: "--release --strip --target ${{ matrix.config.target }} --features fp16kernels"
-      - uses: actions/upload-artifact@v7
+      - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-mac-${{ matrix.config.target }}
+          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          path: target/wheels/lancedb-*.whl
+          fury_token: ${{ secrets.FURY_TOKEN }}
-          if-no-files-found: error
   windows:
-    timeout-minutes: 90
+    timeout-minutes: 60
     runs-on: windows-latest
-    env:
-      # link.exe is single-threaded and the long pole on Windows builds. Use
-      # rustc's bundled lld-link instead.
-      CARGO_TARGET_X86_64_PC_WINDOWS_MSVC_LINKER: rust-lld
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -107,70 +103,19 @@ jobs:
         with:
           python-minor-version: 10
           args: "--release --strip"
-      - uses: actions/upload-artifact@v7
+          vcpkg_token: ${{ secrets.VCPKG_GITHUB_PACKAGES }}
+      - uses: ./.github/workflows/upload_wheel
         if: startsWith(github.ref, 'refs/tags/python-v')
         with:
-          name: wheels-windows
+          pypi_token: ${{ secrets.LANCEDB_PYPI_API_TOKEN }}
-          path: target/wheels/lancedb-*.whl
+          fury_token: ${{ secrets.FURY_TOKEN }}
-          if-no-files-found: error
-  publish:
-    name: Publish wheels
-    if: startsWith(github.ref, 'refs/tags/python-v')
-    needs: [linux, mac, windows]
-    runs-on: ubuntu-latest
-    permissions:
-      id-token: write
-      contents: read
-    steps:
-      - uses: actions/checkout@v6
-      - name: Download wheel artifacts
-        uses: actions/download-artifact@v8
-        with:
-          pattern: wheels-*
-          path: target/wheels
-          merge-multiple: true
-      - name: List wheels
-        run: ls -la target/wheels
-      - name: Choose repo
-        id: choose_repo
-        run: |
-          if [[ ${{ github.ref }} == *beta* ]]; then
-            echo "repo=fury" >> $GITHUB_OUTPUT
-          else
-            echo "repo=pypi" >> $GITHUB_OUTPUT
-          fi
-      - name: Publish to Fury
-        if: steps.choose_repo.outputs.repo == 'fury'
-        env:
-          FURY_TOKEN: ${{ secrets.FURY_TOKEN }}
-        run: |
-          shopt -s nullglob
-          WHEELS=(target/wheels/lancedb-*.whl)
-          if [[ ${#WHEELS[@]} -eq 0 ]]; then
-            echo "No wheels found in target/wheels/" >&2
-            exit 1
-          fi
-          for WHEEL in "${WHEELS[@]}"; do
-            echo "Uploading $WHEEL to Fury"
-            curl -f -F package=@"$WHEEL" "https://$FURY_TOKEN@push.fury.io/lancedb/"
-          done
-      # NOTE: pypa/gh-action-pypi-publish must be invoked directly from a
-      # workflow file, not from inside a composite action. When called from a
-      # composite, `github.action_repository` is empty (actions/runner#2473)
-      # and the action falls back to `github.repository`, producing a bogus
-      # `docker://ghcr.io/<repo>:<ref>` image reference that GHA tries to pull.
-      - name: Publish to PyPI
-        if: steps.choose_repo.outputs.repo == 'pypi'
-        uses: pypa/gh-action-pypi-publish@release/v1
-        with:
-          packages-dir: target/wheels/
   gh-release:
     if: startsWith(github.ref, 'refs/tags/python-v')
     runs-on: ubuntu-latest
     permissions:
       contents: write
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
         with:
           fetch-depth: 0
           lfs: true
@@ -233,13 +178,13 @@ jobs:
   report-failure:
     name: Report Workflow Failure
     runs-on: ubuntu-latest
-    needs: [linux, mac, windows, publish]
+    needs: [linux, mac, windows]
     permissions:
       contents: read
       issues: write
     if: always() && failure() && startsWith(github.ref, 'refs/tags/python-v')
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v4
       - uses: ./.github/actions/create-failure-issue
         with:
           job-results: ${{ toJSON(needs) }}

.github/workflows/python.yml

@@ -17,9 +17,6 @@ on:
       - .github/workflows/build_windows_wheel/**
       - .github/workflows/run_tests/**
 
-permissions:
-  contents: read
-
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -111,6 +108,7 @@ jobs:
       - name: Install
         run: |
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
+          pip install tantivy
           pip install mlx
       - name: Doctest
         run: pytest --doctest-modules python/lancedb
@@ -205,7 +203,7 @@ jobs:
       - name: Delete wheels
         run: rm -rf target/wheels
   pydantic1x:
-    timeout-minutes: 60
+    timeout-minutes: 30
     runs-on: "ubuntu-24.04"
     defaults:
       run:
@@ -229,5 +227,6 @@ jobs:
           pip install "pydantic<2"
           pip install pyarrow==16
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
+          pip install tantivy
       - name: Run tests
         run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/rust.yml

@@ -9,15 +9,9 @@ on:
       - Cargo.toml
       - Cargo.lock
       - rust-toolchain.toml
-      - deny.toml
       - rust/**
-      - nodejs/Cargo.toml
-      - python/Cargo.toml
       - .github/workflows/rust.yml
 
-permissions:
-  contents: read
-
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -59,17 +53,6 @@ jobs:
       - name: Run clippy (without remote feature)
         run: cargo clippy --profile ci --workspace --tests -- -D warnings
 
-  deny:
-    # Supply-chain checks: advisories, licenses, banned crates, and source
-    # restrictions. Configuration lives in `deny.toml` at the workspace root.
-    timeout-minutes: 10
-    runs-on: ubuntu-24.04
-    steps:
-      - uses: actions/checkout@v4
-      - uses: EmbarkStudios/cargo-deny-action@v2
-        with:
-          command: check advisories bans licenses sources
-
   build-no-lock:
     runs-on: ubuntu-24.04
     timeout-minutes: 30
@@ -233,26 +216,6 @@ jobs:
           cargo update -p aws-sdk-sso --precise 1.62.0
           cargo update -p aws-sdk-ssooidc --precise 1.63.0
           cargo update -p aws-sdk-sts --precise 1.63.0
-          # aws-runtime/sigv4/credential-types/types and the aws-smithy-*
-          # crates bumped their MSRV to 1.91.1 in late 2026; pin to the last
-          # 1.91.0-compatible versions. The order matters — each downgrade
-          # only succeeds once everything that still pins it at a higher
-          # version has itself been downgraded.
-          cargo update -p aws-runtime --precise 1.5.12
-          cargo update -p aws-types --precise 1.3.9
-          cargo update -p aws-sigv4 --precise 1.3.5
-          cargo update -p aws-credential-types --precise 1.2.8
-          cargo update -p aws-smithy-checksums --precise 0.63.9
-          cargo update -p aws-smithy-runtime --precise 1.9.3
-          cargo update -p aws-smithy-http --precise 0.62.4
-          cargo update -p aws-smithy-eventstream --precise 0.60.12
-          cargo update -p aws-smithy-http-client --precise 1.1.3
-          cargo update -p aws-smithy-observability --precise 0.1.4
-          cargo update -p aws-smithy-query --precise 0.60.8
-          cargo update -p aws-smithy-runtime-api --precise 1.9.1
-          cargo update -p aws-smithy-async --precise 1.2.6
-          cargo update -p aws-smithy-types --precise 1.3.5
-          cargo update -p aws-smithy-xml --precise 0.60.11
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
         env:

.github/workflows/update_package_lock_run.yml

@@ -3,9 +3,6 @@ name: Update package-lock.json
 on:
   workflow_dispatch:
 
-permissions:
-  contents: read
-
 jobs:
   publish:
     runs-on: ubuntu-latest

.github/workflows/update_package_lock_run_nodejs.yml

@@ -3,9 +3,6 @@ name: Update NodeJs package-lock.json
 on:
   workflow_dispatch:
 
-permissions:
-  contents: read
-
 jobs:
   publish:
     runs-on: ubuntu-latest

.github/workflows/upload_wheel/action.yml

@@ -0,0 +1,45 @@
+name: upload-wheel
+
+description: "Upload wheels to Pypi"
+inputs:
+  pypi_token:
+    required: true
+    description: "release token for the repo"
+  fury_token:
+    required: true
+    description: "release token for the fury repo"
+
+runs:
+  using: "composite"
+  steps:
+  - name: Install dependencies
+    shell: bash
+    run: |
+      python -m pip install --upgrade pip
+      pip install twine
+      python3 -m pip install --upgrade pkginfo
+  - name: Choose repo
+    shell: bash
+    id: choose_repo
+    run: |
+      if [[ ${{ github.ref }} == *beta* ]]; then
+        echo "repo=fury" >> $GITHUB_OUTPUT
+      else
+        echo "repo=pypi" >> $GITHUB_OUTPUT
+      fi
+  - name: Publish to PyPI
+    shell: bash
+    env:
+      FURY_TOKEN: ${{ inputs.fury_token }}
+      PYPI_TOKEN: ${{ inputs.pypi_token }}
+    run: |
+      if [[ ${{ steps.choose_repo.outputs.repo }} == fury ]]; then
+        WHEEL=$(ls target/wheels/lancedb-*.whl 2> /dev/null | head -n 1)
+        echo "Uploading $WHEEL to Fury"
+        curl -f -F package=@$WHEEL https://$FURY_TOKEN@push.fury.io/lancedb/
+      else
+        twine upload --repository ${{ steps.choose_repo.outputs.repo }} \
+          --username __token__ \
+          --password $PYPI_TOKEN \
+          target/wheels/lancedb-*.whl
+      fi

AGENTS.md

@@ -17,33 +17,9 @@ Common commands:
 * 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 Rust: `cargo fmt --all`
+* Format: `cargo fmt --all`
-* Format Python: `ruff format .`
-* Lint Python: `ruff check .`
-* Bootstrap Python dev env: `cd python && uv run --extra tests --extra dev maturin develop --extras tests,dev`
-* Run Python tests: `cd python && uv run --extra tests pytest python/tests -vv --durations=10 -m "not slow and not s3_test"`
-* Run specific Python test: `cd python && uv run --extra tests pytest python/tests/<test_file>.py::<test_name> -q`
 
-For Python validation, prefer the uv-managed environment declared by `python/uv.lock`.
+Before committing changes, run formatting.
-Do not treat system `python`, global `pytest`, or missing editable-install errors as
-final blockers; bootstrap or enter the uv environment instead. If `lancedb._lancedb`
-is missing or stale, or if Rust/PyO3 binding code changed, rebuild the Python
-extension with the bootstrap command above before running tests.
-
-Before committing changes, run formatting for every language you touched. At minimum:
-
-* Rust changes: run `cargo fmt --all`.
-* Python changes: run `ruff format .` and `ruff check .` from the repository root,
-  and run targeted tests through `cd python && uv run ...`.
-* TypeScript changes: run the relevant `npm`/`pnpm` lint, format, build, and docs commands in `nodejs`.
-
-Before creating a PR, the exact value passed to `gh pr create --title` must follow
-Conventional Commits, such as `fix: support nested field paths in native index creation`
-or `feat(python): add dataset multiprocessing support`. Do not use a plain natural
-language summary like `Support nested field paths in native index creation` as the PR
-title. The semantic-release check uses the PR title and body as the merge commit message,
-so a non-conventional PR title will fail CI. After creating a PR, read the remote PR title
-back and fix it immediately if it is not conventional.
 
 ## Coding tips
 

Cargo.toml

@@ -1,5 +1,7 @@
 [workspace]
 members = ["rust/lancedb", "nodejs", "python"]
+# Python package needs to be built by maturin.
+exclude = ["python"]
 resolver = "2"
 
 [workspace.package]
@@ -13,40 +15,40 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=7.2.0-beta.3", default-features = false, "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=5.1.0-beta.1", default-features = false, "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=7.2.0-beta.3", default-features = false, "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=5.1.0-beta.1", default-features = false, "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=7.2.0-beta.3", default-features = false, "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=5.1.0-beta.1", default-features = false, "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=7.2.0-beta.3", "tag" = "v7.2.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=5.1.0-beta.1", "tag" = "v5.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
-arrow = { version = "58.0.0", optional = false }
+arrow = { version = "57.2", optional = false }
-arrow-array = "58.0.0"
+arrow-array = "57.2"
-arrow-data = "58.0.0"
+arrow-data = "57.2"
-arrow-ipc = "58.0.0"
+arrow-ipc = "57.2"
-arrow-ord = "58.0.0"
+arrow-ord = "57.2"
-arrow-schema = "58.0.0"
+arrow-schema = "57.2"
-arrow-select = "58.0.0"
+arrow-select = "57.2"
-arrow-cast = "58.0.0"
+arrow-cast = "57.2"
 async-trait = "0"
-datafusion = { version = "53.0.0", default-features = false }
+datafusion = { version = "52.1", default-features = false }
-datafusion-catalog = "53.0.0"
+datafusion-catalog = "52.1"
-datafusion-common = { version = "53.0.0", default-features = false }
+datafusion-common = { version = "52.1", default-features = false }
-datafusion-execution = "53.0.0"
+datafusion-execution = "52.1"
-datafusion-expr = "53.0.0"
+datafusion-expr = "52.1"
-datafusion-functions = "53.0.0"
+datafusion-functions = "52.1"
-datafusion-physical-plan = "53.0.0"
+datafusion-physical-plan = "52.1"
-datafusion-physical-expr = "53.0.0"
+datafusion-physical-expr = "52.1"
-datafusion-sql = "53.0.0"
+datafusion-sql = "52.1"
 env_logger = "0.11"
 half = { "version" = "2.7.1", default-features = false, features = [
     "num-traits",
@@ -54,7 +56,7 @@ half = { "version" = "2.7.1", default-features = false, features = [
 futures = "0"
 log = "0.4"
 moka = { version = "0.12", features = ["future"] }
-object_store = "0.13.2"
+object_store = "0.12.0"
 pin-project = "1.0.7"
 rand = "0.9"
 snafu = "0.8"

README.md

@@ -15,7 +15,7 @@
 
 # **The Multimodal AI Lakehouse**
 
-[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://docs.lancedb.com) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
+[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://lancedb.com/docs) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
 
 **The ultimate multimodal data platform for AI/ML applications.** 
 
@@ -57,7 +57,7 @@ LanceDB is a central location where developers can build, train and analyze thei
 
 ## **How to Install**:
 
-Follow the [Quickstart](https://docs.lancedb.com/quickstart) doc to set up LanceDB locally. 
+Follow the [Quickstart](https://lancedb.com/docs/quickstart/) doc to set up LanceDB locally. 
 
 **API & SDK:** We also support Python, Typescript and Rust SDKs
 

ci/check_lance_release.py

@@ -112,25 +112,25 @@ def fetch_remote_tags() -> List[TagInfo]:
             "api",
             "-X",
             "GET",
-            f"repos/{LANCE_REPO}/releases",
+            f"repos/{LANCE_REPO}/git/refs/tags",
+            "--paginate",
             "--jq",
-            ".[].tag_name",
+            ".[].ref",
-            "-F",
-            "per_page=20",
         ]
     )
     tags: List[TagInfo] = []
     for line in output.splitlines():
-        tag = line.strip()
+        ref = line.strip()
-        if not tag.startswith("v"):
+        if not ref.startswith("refs/tags/v"):
             continue
+        tag = ref.split("refs/tags/")[-1]
         version = tag.lstrip("v")
         try:
             tags.append(TagInfo(tag=tag, version=version, semver=parse_semver(version)))
         except ValueError:
             continue
     if not tags:
-        raise RuntimeError("No Lance releases could be parsed from GitHub API output")
+        raise RuntimeError("No Lance tags could be parsed from GitHub API output")
     return tags
 
 

ci/update_lance_dependency.py

@@ -1,126 +0,0 @@
-#!/usr/bin/env python3
-"""Prepare a Lance dependency update for LanceDB."""
-
-from __future__ import annotations
-
-import argparse
-import json
-import re
-import subprocess
-import sys
-from pathlib import Path
-from typing import Sequence
-
-try:
-    from check_lance_release import parse_semver
-except ModuleNotFoundError:
-    # Supports importing as ci.update_lance_dependency from tests or ad hoc checks.
-    from ci.check_lance_release import parse_semver  # type: ignore
-
-
-def normalize_version(raw: str) -> str:
-    value = raw.strip()
-    value = value.removeprefix("refs/tags/")
-    value = value.removeprefix("v")
-    try:
-        parse_semver(value)
-    except ValueError:
-        raise ValueError(f"Unsupported Lance version or tag: {raw}")
-    return value
-
-
-def normalized_tag(version: str) -> str:
-    return f"v{version}"
-
-
-def branch_name(version: str) -> str:
-    suffix = re.sub(r"[^a-zA-Z0-9]+", "-", version).strip("-")
-    suffix = re.sub(r"-+", "-", suffix)
-    return f"codex/update-lance-{suffix}"
-
-
-def commit_type(version: str) -> str:
-    prerelease = version.split("-", maxsplit=1)[1] if "-" in version else ""
-    return "chore" if "beta" in prerelease or "rc" in prerelease else "feat"
-
-
-def metadata_for(version: str) -> dict[str, str]:
-    kind = commit_type(version)
-    message = f"{kind}: update lance dependency to v{version}"
-    return {
-        "version": version,
-        "tag": normalized_tag(version),
-        "branch_name": branch_name(version),
-        "commit_type": kind,
-        "commit_message": message,
-        "pr_title": message,
-    }
-
-
-def run_command(cmd: Sequence[str], *, cwd: Path) -> None:
-    subprocess.run(cmd, cwd=cwd, check=True)
-
-
-def update_java_lance_core_version(repo_root: Path, version: str) -> None:
-    pom_path = repo_root / "java" / "pom.xml"
-    contents = pom_path.read_text(encoding="utf-8")
-    updated, count = re.subn(
-        r"(<lance-core\.version>)[^<]+(</lance-core\.version>)",
-        rf"\g<1>{version}\g<2>",
-        contents,
-        count=1,
-    )
-    if count != 1:
-        raise RuntimeError(
-            "Expected exactly one <lance-core.version> entry in java/pom.xml"
-        )
-    pom_path.write_text(updated, encoding="utf-8")
-
-
-def write_github_outputs(path: str | None, payload: dict[str, str]) -> None:
-    if not path:
-        return
-    with open(path, "a", encoding="utf-8") as output:
-        for key, value in payload.items():
-            output.write(f"{key}={value}\n")
-
-
-def main(argv: Sequence[str] | None = None) -> int:
-    parser = argparse.ArgumentParser(description=__doc__)
-    parser.add_argument(
-        "tag_or_version",
-        help="Lance tag or version, for example refs/tags/v7.2.0-beta.1 or 7.2.0",
-    )
-    parser.add_argument(
-        "--repo-root",
-        type=Path,
-        default=Path(__file__).resolve().parents[1],
-        help="Path to the lancedb repository root",
-    )
-    parser.add_argument(
-        "--github-output",
-        default=None,
-        help="Optional GitHub Actions output file to receive metadata fields",
-    )
-    parser.add_argument(
-        "--metadata-only",
-        action="store_true",
-        help="Only print derived metadata; do not modify dependency files",
-    )
-    args = parser.parse_args(argv)
-
-    repo_root = args.repo_root.resolve()
-    version = normalize_version(args.tag_or_version)
-    payload = metadata_for(version)
-
-    if not args.metadata_only:
-        run_command([sys.executable, "ci/set_lance_version.py", version], cwd=repo_root)
-        update_java_lance_core_version(repo_root, version)
-
-    write_github_outputs(args.github_output, payload)
-    print(json.dumps(payload, sort_keys=True))
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

deny.toml

@@ -1,196 +0,0 @@
-# cargo-deny configuration for LanceDB.
-#
-# Run locally with `cargo deny check`. See
-# https://embarkstudios.github.io/cargo-deny/ for the full reference.
-
-# The set of target triples we care about. cargo-deny will only consider
-# dependencies that are used on at least one of these targets. Keeping this
-# explicit avoids noise from platform-specific crates (e.g. wasm, android,
-# ios) that we never actually ship.
-[graph]
-targets = [
-    "x86_64-unknown-linux-gnu",
-    "aarch64-unknown-linux-gnu",
-    "x86_64-apple-darwin",
-    "aarch64-apple-darwin",
-    "x86_64-pc-windows-msvc",
-    "aarch64-pc-windows-msvc",
-]
-all-features = true
-
-[output]
-feature-depth = 1
-
-# ---------------------------------------------------------------------------
-# Advisories: security vulnerabilities and yanked crates.
-# ---------------------------------------------------------------------------
-[advisories]
-version = 2
-# Fail the check if any crate in the lockfile has been yanked from crates.io.
-# Yanked crates are a signal the author retracted the release (often due to
-# bugs or security issues) and should not be depended on.
-yanked = "deny"
-# Advisory IDs we have explicitly reviewed and chosen to accept. Every
-# entry must include a rationale and, where possible, an upstream issue
-# pointing to a fix. Revisit this list whenever dependencies are updated.
-ignore = [
-    # rsa: Marvin Attack timing side-channel in PKCS#1 v1.5 decryption.
-    # Reached only through opendal → reqsign → rsa. We do not use RSA
-    # decryption in LanceDB ourselves; this is dormant in the signing path.
-    # No fixed release exists upstream as of this writing.
-    # https://rustsec.org/advisories/RUSTSEC-2023-0071
-    { id = "RUSTSEC-2023-0071", reason = "rsa crate via opendal/reqsign; no fixed upstream release" },
-
-    # instant: unmaintained. Pulled in via backoff → instant. Upstream
-    # recommends switching to `web-time`; fix has to come from backoff.
-    # https://rustsec.org/advisories/RUSTSEC-2024-0384
-    { id = "RUSTSEC-2024-0384", reason = "transitive via backoff; waiting on backoff replacement" },
-
-    # paste: unmaintained (author archived the repo). Used transitively by
-    # datafusion and the arrow ecosystem; widespread, no drop-in replacement.
-    # https://rustsec.org/advisories/RUSTSEC-2024-0436
-    { id = "RUSTSEC-2024-0436", reason = "transitive via datafusion; awaiting ecosystem migration" },
-
-    # encoding: unmaintained. Reached through lindera-dictionary, which is
-    # required by the native Lindera tokenizer path. Lindera has not migrated
-    # off this crate yet.
-    # https://rustsec.org/advisories/RUSTSEC-2021-0153
-    { id = "RUSTSEC-2021-0153", reason = "transitive via lindera-dictionary for native Lindera tokenizer" },
-
-    # fast-float: unsound and unmaintained. Reached only through polars-arrow
-    # from the optional Polars integration; replacement requires a Polars
-    # dependency upgrade.
-    # https://rustsec.org/advisories/RUSTSEC-2024-0379
-    { id = "RUSTSEC-2024-0379", reason = "transitive via polars-arrow; waiting on Polars migration" },
-
-    # tantivy: segfault on malformed input due to missing bounds check.
-    # Pulled in via lance for full-text search. We only feed tantivy
-    # documents we construct ourselves, not attacker-controlled bytes.
-    # Tracked for a lance dependency bump.
-    # https://rustsec.org/advisories/RUSTSEC-2025-0003
-    { id = "RUSTSEC-2025-0003", reason = "tantivy via lance; inputs are internally produced, not user-supplied bytes" },
-
-    # backoff: unmaintained. Reached only via async-openai. Replacement
-    # requires async-openai to migrate (or us to drop async-openai).
-    # https://rustsec.org/advisories/RUSTSEC-2025-0012
-    { id = "RUSTSEC-2025-0012", reason = "transitive via async-openai; waiting on upstream migration" },
-
-    # number_prefix: unmaintained. Transitive via indicatif → hf-hub.
-    # No security impact, just maintenance status.
-    # https://rustsec.org/advisories/RUSTSEC-2025-0119
-    { id = "RUSTSEC-2025-0119", reason = "transitive via hf-hub/indicatif; cosmetic formatting crate" },
-
-    # bincode: unmaintained. Reached through lindera and lindera-dictionary,
-    # which are required by the native Lindera tokenizer path. Lindera has not
-    # migrated to another serialization format yet.
-    # https://rustsec.org/advisories/RUSTSEC-2025-0141
-    { id = "RUSTSEC-2025-0141", reason = "transitive via lindera/lindera-dictionary for native Lindera tokenizer" },
-
-    # lru: soundness issue in IterMut. Reached only through aws-sdk-s3 in
-    # LanceDB's dev-dependency graph; LanceDB does not use that iterator
-    # directly. Clearing this requires the AWS SDK chain to update lru.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0002
-    { id = "RUSTSEC-2026-0002", reason = "transitive via aws-sdk-s3 dev-dependency; waiting on AWS SDK lru upgrade" },
-
-    # rustls-webpki 0.101.7 (old major line): name-constraint checks for
-    # URI / wildcard names. Pulled in only via the legacy rustls 0.21 chain
-    # from aws-smithy-http-client. The 0.103 line we actively use is patched.
-    # Clearing the 0.101 copy requires the aws-sdk chain to migrate off
-    # rustls 0.21.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0098
-    # https://rustsec.org/advisories/RUSTSEC-2026-0099
-    { id = "RUSTSEC-2026-0098", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
-    { id = "RUSTSEC-2026-0099", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
-
-    # rustls-webpki 0.101.7: reachable panic in CRL parsing. Same legacy
-    # rustls 0.21 chain from aws-smithy-http-client as above. The 0.103 line
-    # we actively use is upgraded to 0.103.13 which contains the fix.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0104
-    { id = "RUSTSEC-2026-0104", reason = "only affects rustls-webpki 0.101 from legacy aws-smithy/rustls 0.21 chain" },
-
-    # rand 0.8.5: soundness issue only when ThreadRng reseeds inside a custom
-    # logger. Reached through several transitive chains. LanceDB does not use
-    # rand from a custom logger; upgrade once all pinned chains accept 0.8.6+.
-    # https://rustsec.org/advisories/RUSTSEC-2026-0097
-    { id = "RUSTSEC-2026-0097", reason = "transitive rand 0.8.5; LanceDB does not call ThreadRng from custom logging" },
-]
-
-# ---------------------------------------------------------------------------
-# Licenses: only allow licenses we've reviewed as compatible with Apache-2.0.
-# ---------------------------------------------------------------------------
-[licenses]
-version = 2
-# SPDX identifiers for licenses that are compatible with our Apache-2.0
-# distribution. Additions require legal review.
-allow = [
-    "Apache-2.0",
-    "Apache-2.0 WITH LLVM-exception",
-    "MIT",
-    "BSD-2-Clause",
-    "BSD-3-Clause",
-    "ISC",
-    "Unicode-3.0",
-    "Unicode-DFS-2016",
-    "Zlib",
-    "CC0-1.0",
-    "MPL-2.0",
-    "BSL-1.0",
-    "OpenSSL",
-    # 0BSD ("BSD Zero Clause") is effectively public domain — no attribution
-    # required. Pulled in by `mock_instant`.
-    "0BSD",
-    # bzip2-1.0.6 is the permissive upstream bzip2 license (BSD-like). Pulled
-    # in by `libbz2-rs-sys`, the pure-Rust bzip2 implementation.
-    "bzip2-1.0.6",
-    # CDLA-Permissive-2.0 is a permissive data license used by `webpki-roots`
-    # for the Mozilla CA root bundle. Data-only, distribution-compatible.
-    "CDLA-Permissive-2.0",
-]
-confidence-threshold = 0.8
-# Crates whose license cannot be determined from Cargo metadata but whose
-# license we've manually confirmed from upstream. Keep this list minimal.
-[[licenses.clarify]]
-# polars-arrow-format omits the `license` field in its Cargo.toml, but the
-# upstream repo (pola-rs/polars-arrow-format) is dual-licensed Apache-2.0 OR
-# MIT. See https://github.com/pola-rs/polars-arrow-format/blob/main/LICENSE
-crate = "polars-arrow-format"
-expression = "Apache-2.0 OR MIT"
-license-files = []
-
-# ---------------------------------------------------------------------------
-# Bans: disallow specific crates and flag dependency hygiene issues.
-# ---------------------------------------------------------------------------
-[bans]
-# Warn (not deny) on duplicate versions of the same crate. In a large
-# workspace like this one, duplicates are common and often unavoidable
-# transitively. We surface them to discourage growth, but don't fail CI.
-multiple-versions = "warn"
-# Wildcard version requirements (`foo = "*"`) are a footgun — they let any
-# future release in without review. Ban them outright.
-wildcards = "deny"
-# Internal workspace crates reference each other via `path = "..."`, which
-# cargo-deny sees as a wildcard version. That's fine for private workspace
-# members (not published to crates.io), so allow it specifically for paths.
-allow-wildcard-paths = true
-# Features that, if enabled, should cause the check to fail.
-deny = []
-# Crates to skip when checking for duplicate versions.
-skip = []
-# Similar to `skip`, but also skips the entire transitive subtree.
-skip-tree = []
-
-# ---------------------------------------------------------------------------
-# Sources: restrict where crates can come from.
-# ---------------------------------------------------------------------------
-[sources]
-# Deny any registry other than the ones explicitly listed below.
-unknown-registry = "deny"
-# Deny any git dependency whose host isn't in the allow-list below. This
-# prevents accidental pulls from arbitrary forks.
-unknown-git = "deny"
-allow-registry = ["https://github.com/rust-lang/crates.io-index"]
-# Lance is developed in a sibling repo and pulled as a git dependency until
-# releases are cut to crates.io. Allow that specific host.
-allow-git = [
-    "https://github.com/lance-format/lance",
-]

dockerfiles/Dockerfile

@@ -24,4 +24,4 @@ RUN python --version && \
   rustc --version && \
   protoc --version
 
-RUN pip install --no-cache-dir lancedb
+RUN pip install --no-cache-dir tantivy lancedb

docs/README.md

@@ -1,6 +1,6 @@
 # LanceDB Documentation
 
-LanceDB docs are available at [docs.lancedb.com](https://docs.lancedb.com).
+LanceDB docs are available at [lancedb.com/docs](https://lancedb.com/docs).
 
 The SDK docs are built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
 whenever a commit is pushed to the `main` branch. So it is possible for the docs to show

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.30.1-beta.0</version>
+    <version>0.28.0-beta.1</version>
 </dependency>
 ```
 

docs/src/js/README.md

@@ -34,7 +34,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
+The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
 
 ## Development
 

docs/src/js/_media/CONTRIBUTING.md

@@ -12,22 +12,20 @@ Typescript.
 * `src/`: Rust bindings source code
 * `lancedb/`: Typescript package source code
 * `__test__/`: Unit tests
-* `examples/`: A pnpm package with the examples shown in the documentation
+* `examples/`: An npm package with the examples shown in the documentation
 
 ## Development environment
 
 To set up your development environment, you will need to install the following:
 
-1. Node.js 22 or later (required by pnpm 11)
+1. Node.js 14 or later
-2. [pnpm](https://pnpm.io/installation) 11 or later (or run via `corepack enable`,
+2. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
-   which uses the `packageManager` field in `package.json`)
+3. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
-3. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
-4. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
 
 Initial setup:
 
 ```shell
-pnpm install
+npm install
 ```
 
 ### Commit Hooks
@@ -41,38 +39,38 @@ pre-commit install
 
 ## Development
 
-Most common development commands can be run using the pnpm scripts.
+Most common development commands can be run using the npm scripts.
 
 Build the package
 
 ```shell
-pnpm install
+npm install
-pnpm build
+npm run build
 ```
 
 Lint:
 
 ```shell
-pnpm lint
+npm run lint
 ```
 
 Format and fix lints:
 
 ```shell
-pnpm lint-fix
+npm run lint-fix
 ```
 
 Run tests:
 
 ```shell
-pnpm test
+npm test
 ```
 
 To run a single test:
 
 ```shell
 # Single file: table.test.ts
-pnpm test -- table.test.ts
+npm test -- table.test.ts
 # Single test: 'merge insert' in table.test.ts
-pnpm test -- table.test.ts --testNamePattern=merge\ insert
+npm test -- table.test.ts --testNamePattern=merge\ insert
 ```

docs/src/js/classes/Connection.md

@@ -148,33 +148,6 @@ Creates a new empty Table
 
 ***
 
-### createNamespace()
-
-```ts
-abstract createNamespace(namespacePath, options?): Promise<CreateNamespaceResponse>
-```
-
-Create a new namespace at the given path.
-
-#### Parameters
-
-* **namespacePath**: `string`[]
-    The namespace path to create.
-
-* **options?**: `Partial`&lt;[`CreateNamespaceOptions`](../interfaces/CreateNamespaceOptions.md)&gt;
-    Creation `mode`
-    ("create" | "exist_ok" | "overwrite") and optional `properties`
-    to attach to the namespace.
-
-#### Returns
-
-`Promise`&lt;[`CreateNamespaceResponse`](../interfaces/CreateNamespaceResponse.md)&gt;
-
-The properties of the
-  created namespace and an optional transaction id.
-
-***
-
 ### createTable()
 
 #### createTable(options, namespacePath)
@@ -257,29 +230,6 @@ Creates a new Table and initialize it with new data.
 
 ***
 
-### describeNamespace()
-
-```ts
-abstract describeNamespace(namespacePath): Promise<DescribeNamespaceResponse>
-```
-
-Describe a namespace, returning its properties.
-
-#### Parameters
-
-* **namespacePath**: `string`[]
-    The namespace path to describe, in
-    parent → child order, e.g. `["analytics", "sales"]`.
-
-#### Returns
-
-`Promise`&lt;[`DescribeNamespaceResponse`](../interfaces/DescribeNamespaceResponse.md)&gt;
-
-The namespace's properties
-  (may be undefined if the namespace has none).
-
-***
-
 ### display()
 
 ```ts
@@ -313,36 +263,6 @@ Drop all tables in the database.
 
 ***
 
-### dropNamespace()
-
-```ts
-abstract dropNamespace(namespacePath, options?): Promise<DropNamespaceResponse>
-```
-
-Drop a namespace.
-
-Use `behavior: "cascade"` to also drop everything contained in the
-namespace (sub-namespaces and tables). The default `"restrict"`
-behavior refuses to drop a non-empty namespace.
-
-#### Parameters
-
-* **namespacePath**: `string`[]
-    The namespace path to drop.
-
-* **options?**: `Partial`&lt;[`DropNamespaceOptions`](../interfaces/DropNamespaceOptions.md)&gt;
-    `mode` ("skip" | "fail"
-    for missing-namespace handling) and `behavior` ("restrict" | "cascade").
-
-#### Returns
-
-`Promise`&lt;[`DropNamespaceResponse`](../interfaces/DropNamespaceResponse.md)&gt;
-
-Any properties returned by
-  the server and an optional transaction id.
-
-***
-
 ### dropTable()
 
 ```ts
@@ -379,36 +299,6 @@ Return true if the connection has not been closed
 
 ***
 
-### listNamespaces()
-
-```ts
-abstract listNamespaces(namespacePath?, options?): Promise<ListNamespacesResponse>
-```
-
-List the immediate child namespaces under the given parent.
-
-Results may be paginated. To retrieve subsequent pages, pass the
-`pageToken` returned by a previous call.
-
-#### Parameters
-
-* **namespacePath?**: `string`[]
-    The parent namespace path. Defaults
-    to the root namespace if omitted.
-
-* **options?**: `Partial`&lt;[`ListNamespacesOptions`](../interfaces/ListNamespacesOptions.md)&gt;
-    Pagination options
-    (`pageToken`, `limit`).
-
-#### Returns
-
-`Promise`&lt;[`ListNamespacesResponse`](../interfaces/ListNamespacesResponse.md)&gt;
-
-Child namespace names and
-  an optional token for fetching the next page.
-
-***
-
 ### openTable()
 
 ```ts
@@ -437,39 +327,6 @@ Open a table in the database.
 
 ***
 
-### renameTable()
-
-```ts
-abstract renameTable(
-   currentName,
-   newName,
-   options?): Promise<void>
-```
-
-Rename a table.
-
-Currently only supported by LanceDB Cloud. Local OSS connections and
-namespace-backed connections (via [connectNamespace](../functions/connectNamespace.md)) reject with
-a "not supported" error.
-
-#### Parameters
-
-* **currentName**: `string`
-    The current name of the table.
-
-* **newName**: `string`
-    The new name for the table.
-
-* **options?**: [`RenameTableOptions`](../interfaces/RenameTableOptions.md)
-    Optional namespace paths. When
-    `newNamespacePath` is omitted the table stays in `namespacePath`.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### tableNames()
 
 #### tableNames(options)

docs/src/js/classes/MergeInsertBuilder.md

@@ -76,57 +76,6 @@ the query optimizer chooses a suboptimal path.
 
 ***
 
-### useLsmWrite()
-
-```ts
-useLsmWrite(useLsmWrite): MergeInsertBuilder
-```
-
-Controls whether the merge uses the MemWAL LSM write path.
-
-By default (unset), a `mergeInsert` on a table with an LSM write spec is
-routed through Lance's MemWAL shard writer, and a table without one uses
-the standard path. Pass `false` to force the standard path even when a
-spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
-is installed.
-
-#### Parameters
-
-* **useLsmWrite**: `boolean`
-    Whether to use the LSM write path.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
-### validateSingleShard()
-
-```ts
-validateSingleShard(validateSingleShard): MergeInsertBuilder
-```
-
-Controls how an LSM merge checks that its input targets a single shard.
-
-When a table has an LSM write spec, every row in a `mergeInsert` call must
-route to the same shard. When `true` (the default), every row is inspected
-to verify this. When `false`, only the first row is inspected and the
-shard it routes to is used for the whole input — a faster path for callers
-that have already pre-sharded their input. Has no effect on tables without
-an LSM write spec.
-
-#### Parameters
-
-* **validateSingleShard**: `boolean`
-    Whether to check every row routes to one shard. Defaults to `true`.
-
-#### Returns
-
-[`MergeInsertBuilder`](MergeInsertBuilder.md)
-
-***
-
 ### whenMatchedUpdateAll()
 
 ```ts

docs/src/js/classes/Query.md

@@ -343,30 +343,6 @@ This is useful for pagination.
 
 ***
 
-### orderBy()
-
-```ts
-orderBy(ordering): this
-```
-
-Sort the results by the specified column(s).
-
-#### Parameters
-
-* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
-
-#### Returns
-
-`this`
-
-This query builder.
-
-#### Inherited from
-
-`StandardQueryBase.orderBy`
-
-***
-
 ### outputSchema()
 
 ```ts

docs/src/js/classes/Scannable.md

@@ -1,173 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / Scannable
-
-# Class: Scannable
-
-A data source that can be scanned as a stream of Arrow `RecordBatch`es.
-
-`Scannable` wraps the schema + optional row count + rescannable flag and
-a callback that yields batches one at a time. It is passed to consumers
-(e.g. `Table.add`, `createTable`, `mergeInsert` — follow-up work) that
-need to pull data without materializing the full dataset in JS memory.
-
-Batches cross the JS↔Rust boundary as Arrow IPC Stream messages; a fresh
-writer serializes each batch, and the Rust side decodes it with
-`arrow_ipc::reader::StreamReader`. One batch is in flight at a time.
-
-## Properties
-
-### numRows
-
-```ts
-readonly numRows: null | number;
-```
-
-***
-
-### rescannable
-
-```ts
-readonly rescannable: boolean;
-```
-
-***
-
-### schema
-
-```ts
-readonly schema: Schema<any>;
-```
-
-## Methods
-
-### fromFactory()
-
-```ts
-static fromFactory(
-   schema,
-   factory,
-   opts): Promise<Scannable>
-```
-
-Build a Scannable from an explicit schema and a factory that returns a
-fresh batch iterator on each call.
-
-The factory is invoked once per scan. Each iterator yields
-`RecordBatch`es matching the declared schema. Use this when you need
-direct control over the pull loop — for example, to wrap a streaming
-source whose batches are produced lazily.
-
-#### Parameters
-
-* **schema**: `Schema`&lt;`any`&gt;
-    The Arrow schema of the produced batches.
-
-* **factory**
-    Called at the start of each scan to produce a batch
-    iterator. Must be idempotent when `rescannable` is true.
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-    Optional hints. `rescannable` defaults to `true`; set to
-    `false` if calling `factory()` twice would not reproduce the same data.
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;
-
-***
-
-### fromIterable()
-
-```ts
-static fromIterable(
-   schema,
-   iter,
-   opts): Promise<Scannable>
-```
-
-Build a Scannable from an iterable of `RecordBatch`es. `rescannable`
-defaults to `false`. Pass an explicit schema so the consumer can
-validate before any batch is pulled.
-
-`opts.rescannable: true` is honest for replayable iterables (Arrays,
-Sets, or custom iterables whose `[Symbol.iterator]()` returns a fresh
-iterator each call). It is rejected for one-shot iterables (generators,
-async generators, or already-an-iterator inputs) because their
-`[Symbol.iterator]()` returns the same exhausted object on the second
-scan. For replayable sources outside this shape, use
-`fromFactory(schema, () => createIter(), { rescannable: true })`.
-
-Note: when `opts.rescannable` is `true`, the constructor calls
-`[Symbol.iterator]()` once on the input to perform the structural check.
-
-#### Parameters
-
-* **schema**: `Schema`&lt;`any`&gt;
-
-* **iter**: `Iterable`&lt;`RecordBatch`&lt;`any`&gt;&gt; \| `AsyncIterable`&lt;`RecordBatch`&lt;`any`&gt;&gt;
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;
-
-***
-
-### fromRecordBatchReader()
-
-```ts
-static fromRecordBatchReader(reader, opts): Promise<Scannable>
-```
-
-Build a Scannable from an Arrow `RecordBatchReader`. A reader can only
-be consumed once; `rescannable` defaults to `false`.
-
-The reader must already be opened (via `.open()`) so its `.schema` is
-populated. `RecordBatchReader.from(...)` returns an unopened reader.
-
-`opts.rescannable: true` is rejected because `RecordBatchReader` is a
-self-iterator (its `[Symbol.iterator]()` returns itself), and this
-constructor does not call `reader.reset()` between scans, so a second
-scan would always see an exhausted reader. For genuinely replayable
-sources, use
-`fromFactory(schema, () => openReader(), { rescannable: true })`,
-which mints a fresh reader on each scan.
-
-#### Parameters
-
-* **reader**: `RecordBatchReader`&lt;`any`&gt;
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;
-
-***
-
-### fromTable()
-
-```ts
-static fromTable(table, opts): Promise<Scannable>
-```
-
-Build a Scannable from an in-memory Arrow `Table`. Always rescannable;
-the table's batches are replayed on each scan.
-
-The table's row count is authoritative: `opts.numRows` must either be
-omitted or equal to `table.numRows`. `opts.rescannable` of `false` is
-rejected because in-memory Tables are always rescannable.
-
-#### Parameters
-
-* **table**: `Table`&lt;`any`&gt;
-
-* **opts**: [`ScannableOptions`](../interfaces/ScannableOptions.md) = `{}`
-
-#### Returns
-
-`Promise`&lt;[`Scannable`](Scannable.md)&gt;

docs/src/js/classes/Table.md

@@ -187,25 +187,6 @@ Any attempt to use the table after it is closed will result in an error.
 
 ***
 
-### closeLsmWriters()
-
-```ts
-abstract closeLsmWriters(): Promise<void>
-```
-
-Drain and close any cached MemWAL shard writers held for this table.
-
-When an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) is installed, `mergeInsert` opens MemWAL
-shard writers and caches them for reuse across calls. This closes them,
-flushing pending data; writers reopen lazily on the next `mergeInsert`.
-It is a no-op when no writers are cached.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### countRows()
 
 ```ts
@@ -520,34 +501,6 @@ Modeled after ``VACUUM`` in PostgreSQL.
 
 ***
 
-### prewarmData()
-
-```ts
-abstract prewarmData(columns?): Promise<void>
-```
-
-Prewarm one or more columns of data in the table.
-
-#### Parameters
-
-* **columns?**: `string`[]
-    The columns to prewarm. If undefined, all columns are prewarmed.
-    This will load the column data into the page cache so that future queries that
-    read those columns avoid the initial cold-start latency.  This call initiates
-    prewarming and returns once the request is accepted; the warming itself may
-    continue in the background.  Calling it on already-prewarmed columns is a
-    no-op on the server.
-    Prewarming is generally useful for columns used in filters or projections.
-    Large columns (e.g. high-dimensional vectors or binary data) may not be
-    practical to prewarm.
-    This feature is currently only supported on remote tables.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### prewarmIndex()
 
 ```ts
@@ -709,74 +662,6 @@ of the given query
 
 ***
 
-### setLsmWriteSpec()
-
-```ts
-abstract setLsmWriteSpec(spec): Promise<void>
-```
-
-Install an [LsmWriteSpec](../interfaces/LsmWriteSpec.md) on this table, selecting Lance's MemWAL
-LSM-style write path for future `mergeInsert` calls.
-
-`LsmWriteSpec` chooses one of three sharding strategies via `specType`:
-
-- `"bucket"` — hash-bucket writes by the single-column unenforced primary
-  key (`column` and `numBuckets` required).
-- `"identity"` — shard by the raw value of a scalar `column`.
-- `"unsharded"` — route every write to a single shard.
-
-All variants require the table to have an unenforced primary key
-([Table#setUnenforcedPrimaryKey](Table.md#setunenforcedprimarykey)); bucket sharding additionally
-requires it to be the single column being bucketed.
-
-#### Parameters
-
-* **spec**: [`LsmWriteSpec`](../interfaces/LsmWriteSpec.md)
-    The sharding spec to install.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-#### Example
-
-```ts
-await table.setUnenforcedPrimaryKey("id");
-await table.setLsmWriteSpec({
-  specType: "bucket",
-  column: "id",
-  numBuckets: 16,
-  maintainedIndexes: ["id_idx"],
-});
-```
-
-***
-
-### setUnenforcedPrimaryKey()
-
-```ts
-abstract setUnenforcedPrimaryKey(columns): Promise<void>
-```
-
-Set the unenforced primary key for this table to a single column.
-
-"Unenforced" means LanceDB does not check uniqueness on writes; the
-column is recorded in the schema as the primary key for use by features
-such as `merge_insert`. Only single-column primary keys are supported,
-and the key cannot be changed once set.
-
-#### Parameters
-
-* **columns**: `string` \| `string`[]
-    The primary key column. A one-element
-    array is also accepted; passing more than one column is rejected.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### stats()
 
 ```ts
@@ -880,23 +765,6 @@ Return the table as an arrow table
 
 ***
 
-### unsetLsmWriteSpec()
-
-```ts
-abstract unsetLsmWriteSpec(): Promise<void>
-```
-
-Remove the [LsmWriteSpec](../interfaces/LsmWriteSpec.md) from this table, reverting to the standard
-`mergeInsert` write path.
-
-Errors if no spec is currently set.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### update()
 
 #### update(opts)
@@ -994,29 +862,6 @@ based on the row being updated (e.g. "my_col + 1")
 
 ***
 
-### updateFieldMetadata()
-
-```ts
-abstract updateFieldMetadata(updates): Promise<UpdateFieldMetadataResult>
-```
-
-Update per-field (column) metadata.
-
-#### Parameters
-
-* **updates**: [`FieldMetadataUpdate`](../interfaces/FieldMetadataUpdate.md)[]
-    One or more per-field updates. Each
-    update's metadata is merged into the field's existing metadata by default;
-    a value of `null` deletes that key, and `replace: true` swaps the whole map.
-
-#### Returns
-
-`Promise`&lt;[`UpdateFieldMetadataResult`](../interfaces/UpdateFieldMetadataResult.md)&gt;
-
-resolves to the new table version.
-
-***
-
 ### vectorSearch()
 
 ```ts

docs/src/js/classes/VectorQuery.md

@@ -498,30 +498,6 @@ This is useful for pagination.
 
 ***
 
-### orderBy()
-
-```ts
-orderBy(ordering): this
-```
-
-Sort the results by the specified column(s).
-
-#### Parameters
-
-* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
-
-#### Returns
-
-`this`
-
-This query builder.
-
-#### Inherited from
-
-`StandardQueryBase.orderBy`
-
-***
-
 ### outputSchema()
 
 ```ts

docs/src/js/functions/connectNamespace.md

@@ -1,131 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / connectNamespace
-
-# Function: connectNamespace()
-
-## connectNamespace(implName, config, options)
-
-```ts
-function connectNamespace(
-   implName,
-   config,
-   options?): Promise<Connection>
-```
-
-Connect to a LanceDB database through a namespace.
-
-Unlike [connect](connect.md), which routes by URI scheme (local path vs.
-`db://` cloud), `connectNamespace` always returns a namespace-backed
-connection. The `implName` selects the namespace implementation:
-
-- `"dir"` — directory namespace, configured with [DirNamespaceConfig](../interfaces/DirNamespaceConfig.md).
-- `"rest"` — remote REST catalog, configured with [RestNamespaceConfig](../interfaces/RestNamespaceConfig.md).
-- Any other string — full module path for a custom implementation,
-  configured with a free-form string-keyed `properties` map.
-
-### Parameters
-
-* **implName**: `"dir"`
-
-* **config**: [`DirNamespaceConfig`](../interfaces/DirNamespaceConfig.md)
-
-* **options?**: `Partial`&lt;[`ConnectNamespaceOptions`](../interfaces/ConnectNamespaceOptions.md)&gt;
-
-### Returns
-
-`Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
-
-### Examples
-
-```ts
-const db = await connectNamespace("dir", { root: "/path/to/db" });
-await db.createTable("users", [{ id: 1 }]);
-```
-
-```ts
-const db = await connectNamespace("rest", {
-  uri: "https://catalog.example.com",
-  headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
-});
-```
-
-```ts
-const db = await connectNamespace("my.custom.Namespace", {
-  endpoint: "...",
-});
-```
-
-## connectNamespace(implName, config, options)
-
-```ts
-function connectNamespace(
-   implName,
-   config,
-   options?): Promise<Connection>
-```
-
-Connect through the built-in REST namespace.
-
-Configured with [RestNamespaceConfig](../interfaces/RestNamespaceConfig.md). See the function-level
-documentation above for the full surface, examples, and how this
-relates to [connect](connect.md).
-
-### Parameters
-
-* **implName**: `"rest"`
-
-* **config**: [`RestNamespaceConfig`](../interfaces/RestNamespaceConfig.md)
-
-* **options?**: `Partial`&lt;[`ConnectNamespaceOptions`](../interfaces/ConnectNamespaceOptions.md)&gt;
-
-### Returns
-
-`Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
-
-### Example
-
-```ts
-const db = await connectNamespace("rest", {
-  uri: "https://catalog.example.com",
-  headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
-});
-```
-
-## connectNamespace(implName, properties, options)
-
-```ts
-function connectNamespace(
-   implName,
-   properties,
-   options?): Promise<Connection>
-```
-
-Connect through a custom namespace implementation by full module path,
-configured with a free-form string-keyed `properties` map. Use the
-typed overloads above for the built-in `"dir"` and `"rest"` impls.
-
-See the function-level documentation above for examples and how this
-relates to [connect](connect.md).
-
-### Parameters
-
-* **implName**: `string`
-
-* **properties**: `Record`&lt;`string`, `string`&gt;
-
-* **options?**: `Partial`&lt;[`ConnectNamespaceOptions`](../interfaces/ConnectNamespaceOptions.md)&gt;
-
-### Returns
-
-`Promise`&lt;[`Connection`](../classes/Connection.md)&gt;
-
-### Example
-
-```ts
-const db = await connectNamespace("my.custom.Namespace", {
-  endpoint: "...",
-});
-```

docs/src/js/globals.md

@@ -32,7 +32,6 @@
 - [PhraseQuery](classes/PhraseQuery.md)
 - [Query](classes/Query.md)
 - [QueryBase](classes/QueryBase.md)
-- [Scannable](classes/Scannable.md)
 - [Session](classes/Session.md)
 - [StaticHeaderProvider](classes/StaticHeaderProvider.md)
 - [Table](classes/Table.md)
@@ -51,21 +50,12 @@
 - [AlterColumnsResult](interfaces/AlterColumnsResult.md)
 - [ClientConfig](interfaces/ClientConfig.md)
 - [ColumnAlteration](interfaces/ColumnAlteration.md)
-- [ColumnOrdering](interfaces/ColumnOrdering.md)
 - [CompactionStats](interfaces/CompactionStats.md)
-- [ConnectNamespaceOptions](interfaces/ConnectNamespaceOptions.md)
 - [ConnectionOptions](interfaces/ConnectionOptions.md)
-- [CreateNamespaceOptions](interfaces/CreateNamespaceOptions.md)
-- [CreateNamespaceResponse](interfaces/CreateNamespaceResponse.md)
 - [CreateTableOptions](interfaces/CreateTableOptions.md)
 - [DeleteResult](interfaces/DeleteResult.md)
-- [DescribeNamespaceResponse](interfaces/DescribeNamespaceResponse.md)
-- [DirNamespaceConfig](interfaces/DirNamespaceConfig.md)
 - [DropColumnsResult](interfaces/DropColumnsResult.md)
-- [DropNamespaceOptions](interfaces/DropNamespaceOptions.md)
-- [DropNamespaceResponse](interfaces/DropNamespaceResponse.md)
 - [ExecutableQuery](interfaces/ExecutableQuery.md)
-- [FieldMetadataUpdate](interfaces/FieldMetadataUpdate.md)
 - [FragmentStatistics](interfaces/FragmentStatistics.md)
 - [FragmentSummaryStats](interfaces/FragmentSummaryStats.md)
 - [FtsOptions](interfaces/FtsOptions.md)
@@ -79,19 +69,13 @@
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
-- [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
-- [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
-- [LsmWriteSpec](interfaces/LsmWriteSpec.md)
 - [MergeResult](interfaces/MergeResult.md)
 - [OpenTableOptions](interfaces/OpenTableOptions.md)
 - [OptimizeOptions](interfaces/OptimizeOptions.md)
 - [OptimizeStats](interfaces/OptimizeStats.md)
 - [QueryExecutionOptions](interfaces/QueryExecutionOptions.md)
 - [RemovalStats](interfaces/RemovalStats.md)
-- [RenameTableOptions](interfaces/RenameTableOptions.md)
-- [RestNamespaceConfig](interfaces/RestNamespaceConfig.md)
 - [RetryConfig](interfaces/RetryConfig.md)
-- [ScannableOptions](interfaces/ScannableOptions.md)
 - [ShuffleOptions](interfaces/ShuffleOptions.md)
 - [SplitCalculatedOptions](interfaces/SplitCalculatedOptions.md)
 - [SplitHashOptions](interfaces/SplitHashOptions.md)
@@ -102,12 +86,10 @@
 - [TimeoutConfig](interfaces/TimeoutConfig.md)
 - [TlsConfig](interfaces/TlsConfig.md)
 - [TokenResponse](interfaces/TokenResponse.md)
-- [UpdateFieldMetadataResult](interfaces/UpdateFieldMetadataResult.md)
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
 - [WriteExecutionOptions](interfaces/WriteExecutionOptions.md)
-- [WriteProgress](interfaces/WriteProgress.md)
 
 ## Type Aliases
 
@@ -125,7 +107,6 @@
 
 - [RecordBatchIterator](functions/RecordBatchIterator.md)
 - [connect](functions/connect.md)
-- [connectNamespace](functions/connectNamespace.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
 - [permutationBuilder](functions/permutationBuilder.md)

docs/src/js/interfaces/AddDataOptions.md

@@ -19,39 +19,3 @@ mode: "append" | "overwrite";
 If "append" (the default) then the new data will be added to the table
 
 If "overwrite" then the new data will replace the existing data in the table.
-
-***
-
-### progress()
-
-```ts
-progress: (progress) => void;
-```
-
-Optional callback invoked periodically with write progress.
-
-The callback is fired once per batch written and once more with
-`done: true` when the write completes. Calls are dispatched
-asynchronously to the JS event loop and never block the write — a slow
-callback will queue events rather than back-pressure the writer.
-
-Errors thrown from the callback are logged with `console.warn` and
-swallowed — they do not abort the write.
-
-#### Parameters
-
-* **progress**: [`WriteProgress`](WriteProgress.md)
-
-#### Returns
-
-`void`
-
-#### Example
-
-```ts
-await table.add(data, {
-  progress: (p) => {
-    console.log(`${p.outputRows}/${p.totalRows ?? "?"} rows`);
-  },
-});
-```

docs/src/js/interfaces/ColumnOrdering.md

@@ -1,31 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ColumnOrdering
-
-# Interface: ColumnOrdering
-
-## Properties
-
-### ascending?
-
-```ts
-optional ascending: boolean;
-```
-
-***
-
-### columnName
-
-```ts
-columnName: string;
-```
-
-***
-
-### nullsFirst?
-
-```ts
-optional nullsFirst: boolean;
-```

docs/src/js/interfaces/ConnectNamespaceOptions.md

@@ -1,54 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ConnectNamespaceOptions
-
-# Interface: ConnectNamespaceOptions
-
-## Properties
-
-### namespaceClientProperties?
-
-```ts
-optional namespaceClientProperties: Record<string, string>;
-```
-
-Extra properties for the backing namespace client.
-
-***
-
-### readConsistencyInterval?
-
-```ts
-optional readConsistencyInterval: number;
-```
-
-The interval, in seconds, at which to check for updates to the table
-from other processes. If None, then consistency is not checked. For
-performance reasons, this is the default. For strong consistency, set
-this to zero seconds. Then every read will check for updates from other
-processes. As a compromise, you can set this to a non-zero value for
-eventual consistency.
-
-***
-
-### session?
-
-```ts
-optional session: Session;
-```
-
-The session to use for this connection. Holds shared caches and other
-session-specific state.
-
-***
-
-### storageOptions?
-
-```ts
-optional storageOptions: Record<string, string>;
-```
-
-Configuration for object storage. The available options are described
-at https://docs.lancedb.com/storage/

docs/src/js/interfaces/ConnectionOptions.md

@@ -41,49 +41,22 @@ for testing purposes.
 
 ***
 
-### manifestEnabled?
-
-```ts
-optional manifestEnabled: boolean;
-```
-
-(For LanceDB OSS only): use directory namespace manifests as the source
-of truth for table metadata. Existing directory-listed root tables are
-migrated into the manifest on access.
-
-***
-
-### namespaceClientProperties?
-
-```ts
-optional namespaceClientProperties: Record<string, string>;
-```
-
-(For LanceDB OSS only): extra properties for the backing namespace
-client used by manifest-enabled native connections.
-
-***
-
 ### readConsistencyInterval?
 
 ```ts
 optional readConsistencyInterval: number;
 ```
 
-The interval, in seconds, at which to check for updates to the table
+(For LanceDB OSS only): The interval, in seconds, at which to check for
-from other processes. If None, then consistency is not checked. For
+updates to the table from other processes. If None, then consistency is not
-performance reasons, this is the default. For strong consistency, set
+checked. For performance reasons, this is the default. For strong
-this to zero seconds. Then every read will check for updates from other
+consistency, set this to zero seconds. Then every read will check for
-processes. As a compromise, you can set this to a non-zero value for
+updates from other processes. As a compromise, you can set this to a
-eventual consistency. If more than that interval has passed since the
+non-zero value for eventual consistency. If more than that interval
-last check, then the table will be checked for updates. Note: this
+has passed since the last check, then the table will be checked for updates.
-consistency only applies to read operations. Write operations are
+Note: this consistency only applies to read operations. Write operations are
 always consistent.
 
-Stronger consistency is not free. The smaller the interval, the more
-often each read pays the cost of checking for updates against object
-storage, raising per-read latency and cost.
-
 ***
 
 ### region?
@@ -116,4 +89,4 @@ optional storageOptions: Record<string, string>;
 
 (For LanceDB OSS only): configuration for object storage.
 
-The available options are described at https://docs.lancedb.com/storage/
+The available options are described at https://lancedb.com/docs/storage/

docs/src/js/interfaces/CreateNamespaceOptions.md

@@ -1,27 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / CreateNamespaceOptions
-
-# Interface: CreateNamespaceOptions
-
-## Properties
-
-### mode?
-
-```ts
-optional mode: "overwrite" | "create" | "exist_ok";
-```
-
-Creation mode.
-
-***
-
-### properties?
-
-```ts
-optional properties: Record<string, string>;
-```
-
-Properties to set on the new namespace.

docs/src/js/interfaces/CreateNamespaceResponse.md

@@ -1,23 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / CreateNamespaceResponse
-
-# Interface: CreateNamespaceResponse
-
-## Properties
-
-### properties?
-
-```ts
-optional properties: Record<string, string>;
-```
-
-***
-
-### transactionId?
-
-```ts
-optional transactionId: string;
-```

docs/src/js/interfaces/CreateTableOptions.md

@@ -97,4 +97,4 @@ Configuration for object storage.
 Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
-The available options are described at https://docs.lancedb.com/storage/
+The available options are described at https://lancedb.com/docs/storage/

docs/src/js/interfaces/DescribeNamespaceResponse.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / DescribeNamespaceResponse
-
-# Interface: DescribeNamespaceResponse
-
-## Properties
-
-### properties?
-
-```ts
-optional properties: Record<string, string>;
-```

docs/src/js/interfaces/DirNamespaceConfig.md

@@ -1,47 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / DirNamespaceConfig
-
-# Interface: DirNamespaceConfig
-
-Configuration for the built-in directory namespace (`"dir"`).
-
-The directory namespace stores tables under a single root path (local
-filesystem or object storage URI). See
-[https://docs.lancedb.com/namespaces](https://docs.lancedb.com/namespaces) for the documented surface;
-less-common knobs live under [DirNamespaceConfig.extraProperties](DirNamespaceConfig.md#extraproperties).
-
-## Properties
-
-### extraProperties?
-
-```ts
-optional extraProperties: Record<string, string>;
-```
-
-Additional raw properties passed verbatim to the namespace
-implementation (e.g. `storage.*`, `credential_vendor.*`). Typed
-fields above take precedence on key collision.
-
-***
-
-### manifestEnabled?
-
-```ts
-optional manifestEnabled: boolean;
-```
-
-Whether to maintain a namespace manifest at the root. Required for
-child namespaces. Defaults to true on the impl side.
-
-***
-
-### root
-
-```ts
-root: string;
-```
-
-Root path or URI containing the LanceDB tables.

docs/src/js/interfaces/DropNamespaceOptions.md

@@ -1,27 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / DropNamespaceOptions
-
-# Interface: DropNamespaceOptions
-
-## Properties
-
-### behavior?
-
-```ts
-optional behavior: "restrict" | "cascade";
-```
-
-Refuse to drop if non-empty (restrict) or drop recursively (cascade).
-
-***
-
-### mode?
-
-```ts
-optional mode: "fail" | "skip";
-```
-
-Whether to skip if the namespace doesn't exist, or fail.

docs/src/js/interfaces/DropNamespaceResponse.md

@@ -1,23 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / DropNamespaceResponse
-
-# Interface: DropNamespaceResponse
-
-## Properties
-
-### properties?
-
-```ts
-optional properties: Record<string, string>;
-```
-
-***
-
-### transactionId?
-
-```ts
-optional transactionId: string[];
-```

docs/src/js/interfaces/FieldMetadataUpdate.md

@@ -1,41 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / FieldMetadataUpdate
-
-# Interface: FieldMetadataUpdate
-
-A per-field metadata update, addressed by dot-path.
-
-## Properties
-
-### metadata
-
-```ts
-metadata: Record<string, null | string>;
-```
-
-Metadata key/value pairs. Merged into the field's existing metadata by
-default; a value of `null` deletes that key.
-
-***
-
-### path
-
-```ts
-path: string;
-```
-
-Dot-separated path to the field. For a top-level column this is just its
-name; for a nested field it's the path, e.g. "a.b.c".
-
-***
-
-### replace?
-
-```ts
-optional replace: boolean;
-```
-
-If true, replace the field's entire metadata map instead of merging.

docs/src/js/interfaces/ListNamespacesOptions.md

@@ -1,27 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ListNamespacesOptions
-
-# Interface: ListNamespacesOptions
-
-## Properties
-
-### limit?
-
-```ts
-optional limit: number;
-```
-
-An optional limit to the number of results to return.
-
-***
-
-### pageToken?
-
-```ts
-optional pageToken: string;
-```
-
-Token from a previous response for pagination.

docs/src/js/interfaces/ListNamespacesResponse.md

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

docs/src/js/interfaces/LsmWriteSpec.md

@@ -1,67 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / LsmWriteSpec
-
-# Interface: LsmWriteSpec
-
-Specification selecting Lance's MemWAL LSM-style write path for
-`mergeInsert`.
-
-`specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
-`column` and `numBuckets` are required; for `"identity"`, `column` is
-required and must be a deterministic function of the unenforced primary
-key (every row with a given primary key must always produce the same
-`column` value, or upserts of that key can land in different shards and a
-stale version can win).
-
-## Properties
-
-### column?
-
-```ts
-optional column: string;
-```
-
-Bucket and identity variants: the sharding column.
-
-***
-
-### maintainedIndexes?
-
-```ts
-optional maintainedIndexes: string[];
-```
-
-Names of indexes the MemWAL should keep up to date during writes.
-
-***
-
-### numBuckets?
-
-```ts
-optional numBuckets: number;
-```
-
-Bucket variant: the number of buckets, in `[1, 1024]`.
-
-***
-
-### specType
-
-```ts
-specType: "bucket" | "identity" | "unsharded";
-```
-
-One of `"bucket"`, `"identity"`, or `"unsharded"`.
-
-***
-
-### writerConfigDefaults?
-
-```ts
-optional writerConfigDefaults: Record<string, string>;
-```
-
-Default `ShardWriter` configuration recorded in the MemWAL index.

docs/src/js/interfaces/MergeResult.md

@@ -32,14 +32,6 @@ numInsertedRows: number;
 
 ***
 
-### numRows
-
-```ts
-numRows: number;
-```
-
-***
-
 ### numUpdatedRows
 
 ```ts

docs/src/js/interfaces/OpenTableOptions.md

@@ -42,4 +42,4 @@ Configuration for object storage.
 Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
-The available options are described at https://docs.lancedb.com/storage/
+The available options are described at https://lancedb.com/docs/storage/

docs/src/js/interfaces/RenameTableOptions.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / RenameTableOptions
-
-# Interface: RenameTableOptions
-
-## Properties
-
-### namespacePath?
-
-```ts
-optional namespacePath: string[];
-```
-
-The namespace path of the table being renamed. Defaults to the root
-namespace (`[]`) when omitted.
-
-***
-
-### newNamespacePath?
-
-```ts
-optional newNamespacePath: string[];
-```
-
-The namespace path to move the table to as part of the rename. When
-omitted the table stays in `namespacePath`.

docs/src/js/interfaces/RestNamespaceConfig.md

@@ -1,47 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / RestNamespaceConfig
-
-# Interface: RestNamespaceConfig
-
-Configuration for the built-in REST namespace (`"rest"`).
-
-The REST namespace talks to a remote catalog server over HTTP. See
-[https://docs.lancedb.com/namespaces](https://docs.lancedb.com/namespaces) for the documented surface;
-less-common knobs (TLS, metrics) live under
-[RestNamespaceConfig.extraProperties](RestNamespaceConfig.md#extraproperties).
-
-## Properties
-
-### extraProperties?
-
-```ts
-optional extraProperties: Record<string, string>;
-```
-
-Additional raw properties passed verbatim to the namespace
-implementation (e.g. `tls.*`, `ops_metrics_enabled`, `delimiter`).
-Typed fields above take precedence on key collision.
-
-***
-
-### headers?
-
-```ts
-optional headers: Record<string, string>;
-```
-
-HTTP headers forwarded with each request. Keys are passed through
-as-is (e.g. `"x-api-key"`, `"Authorization"`).
-
-***
-
-### uri
-
-```ts
-uri: string;
-```
-
-Catalog endpoint URL.

docs/src/js/interfaces/ScannableOptions.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ScannableOptions
-
-# Interface: ScannableOptions
-
-## Properties
-
-### numRows?
-
-```ts
-optional numRows: number;
-```
-
-Hint about the number of rows. Not validated against the stream.
-
-***
-
-### rescannable?
-
-```ts
-optional rescannable: boolean;
-```
-
-Whether the source can be scanned more than once. Defaults to `true` for
-`fromTable` / `fromFactory` and `false` for `fromIterable` /
-`fromRecordBatchReader`.

docs/src/js/interfaces/UpdateFieldMetadataResult.md

@@ -1,15 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / UpdateFieldMetadataResult
-
-# Interface: UpdateFieldMetadataResult
-
-## Properties
-
-### version
-
-```ts
-version: number;
-```

docs/src/js/interfaces/WriteProgress.md

@@ -1,84 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / WriteProgress
-
-# Interface: WriteProgress
-
-Progress snapshot for a write operation, delivered to the `progress`
-callback passed to [Table.add](../classes/Table.md#add).
-
-## Properties
-
-### activeTasks
-
-```ts
-activeTasks: number;
-```
-
-Number of parallel write tasks currently in flight.
-
-***
-
-### done
-
-```ts
-done: boolean;
-```
-
-`true` for the final callback; `false` otherwise.
-
-***
-
-### elapsedSeconds
-
-```ts
-elapsedSeconds: number;
-```
-
-Wall-clock seconds since the write started.
-
-***
-
-### outputBytes
-
-```ts
-outputBytes: number;
-```
-
-Number of bytes written so far.
-
-***
-
-### outputRows
-
-```ts
-outputRows: number;
-```
-
-Number of rows written so far.
-
-***
-
-### totalRows?
-
-```ts
-optional totalRows: number;
-```
-
-Total rows expected, when the input source reports it.
-
-Always set on the final callback (the one with `done: true`), falling
-back to the actual number of rows written when the source could not
-report a row count up front.
-
-***
-
-### totalTasks
-
-```ts
-totalTasks: number;
-```
-
-Total number of parallel write tasks (the write parallelism).

docs/src/python/python.md

@@ -94,11 +94,11 @@ of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and
 
 ## Full text search
 
-Use [lancedb.table.Table.create_fts_index][] for the synchronous API or
+::: lancedb.fts.create_index
-[lancedb.table.AsyncTable.create_index][] with [lancedb.index.FTS][] for the
-asynchronous API.
 
-::: lancedb.index.FTS
+::: lancedb.fts.populate_index
+
+::: lancedb.fts.search_index
 
 ## Utilities
 
@@ -166,12 +166,6 @@ lists the indices that LanceDb supports.
 
 ::: lancedb.index.IvfFlat
 
-::: lancedb.index.IvfSq
-
-::: lancedb.index.IvfRq
-
-::: lancedb.index.HnswFlat
-
 ::: lancedb.table.IndexStatistics
 
 ## Querying (Asynchronous)

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.30.1-beta.0</version>
+      <version>0.28.0-beta.1</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.30.1-beta.0</version>
+    <version>0.28.0-beta.1</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>7.2.0-beta.1</lance-core.version>
+        <lance-core.version>5.1.0-beta.1</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/AGENTS.md

@@ -3,11 +3,11 @@ 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: `pnpm build`.
+Whenever you change the Rust code, you will need to recompile: `npm run build`.
 
 Common commands:
-* Build: `pnpm build`
+* Build: `npm run build`
-* Lint: `pnpm lint`
+* Lint: `npm run lint`
-* Fix lints: `pnpm lint-fix`
+* Fix lints: `npm run lint-fix`
-* Test: `pnpm test`
+* Test: `npm test`
-* Run single test file: `pnpm test __test__/arrow.test.ts`
+* Run single test file: `npm test __test__/arrow.test.ts`

nodejs/CONTRIBUTING.md

@@ -12,22 +12,20 @@ Typescript.
 * `src/`: Rust bindings source code
 * `lancedb/`: Typescript package source code
 * `__test__/`: Unit tests
-* `examples/`: A pnpm package with the examples shown in the documentation
+* `examples/`: An npm package with the examples shown in the documentation
 
 ## Development environment
 
 To set up your development environment, you will need to install the following:
 
-1. Node.js 22 or later (required by pnpm 11)
+1. Node.js 14 or later
-2. [pnpm](https://pnpm.io/installation) 11 or later (or run via `corepack enable`,
+2. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
-   which uses the `packageManager` field in `package.json`)
+3. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
-3. Rust's package manager, Cargo. Use [rustup](https://rustup.rs/) to install.
-4. [protoc](https://grpc.io/docs/protoc-installation/) (Protocol Buffers compiler)
 
 Initial setup:
 
 ```shell
-pnpm install
+npm install
 ```
 
 ### Commit Hooks
@@ -41,38 +39,38 @@ pre-commit install
 
 ## Development
 
-Most common development commands can be run using the pnpm scripts.
+Most common development commands can be run using the npm scripts.
 
 Build the package
 
 ```shell
-pnpm install
+npm install
-pnpm build
+npm run build
 ```
 
 Lint:
 
 ```shell
-pnpm lint
+npm run lint
 ```
 
 Format and fix lints:
 
 ```shell
-pnpm lint-fix
+npm run lint-fix
 ```
 
 Run tests:
 
 ```shell
-pnpm test
+npm test
 ```
 
 To run a single test:
 
 ```shell
 # Single file: table.test.ts
-pnpm test -- table.test.ts
+npm test -- table.test.ts
 # Single test: 'merge insert' in table.test.ts
-pnpm test -- table.test.ts --testNamePattern=merge\ insert
+npm test -- table.test.ts --testNamePattern=merge\ insert
 ```

nodejs/Cargo.toml

@@ -1,8 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.30.1-beta.0"
+version = "0.28.0-beta.1"
-publish = false
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -16,13 +15,12 @@ crate-type = ["cdylib"]
 async-trait.workspace = true
 arrow-ipc.workspace = true
 arrow-array.workspace = true
-arrow-buffer = "58.0.0"
+arrow-buffer = "57.2"
 half.workspace = true
 arrow-schema.workspace = true
 env_logger.workspace = true
 futures.workspace = true
 lancedb = { path = "../rust/lancedb", default-features = false }
-lance-namespace.workspace = true
 napi = { version = "3.8.3", default-features = false, features = [
     "napi9",
     "async"
@@ -33,8 +31,8 @@ lzma-sys = { version = "0.1", features = ["static"] }
 log.workspace = true
 
 # Pin to resolve build failures; update periodically for security patches.
-aws-lc-sys = "=0.40.0"
+aws-lc-sys = "=0.38.0"
-aws-lc-rs = "=1.16.3"
+aws-lc-rs = "=1.16.1"
 
 [build-dependencies]
 napi-build = "2.3.1"

nodejs/README.md

@@ -30,7 +30,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
+The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
 
 ## Development
 

nodejs/__test__/connection.test.ts

@@ -4,7 +4,7 @@
 import { readdirSync } from "fs";
 import { Field, Float64, Schema } from "apache-arrow";
 import * as tmp from "tmp";
-import { Connection, Table, connect, connectNamespace } from "../lancedb";
+import { Connection, Table, connect } from "../lancedb";
 import { LocalTable } from "../lancedb/table";
 
 describe("when connecting", () => {
@@ -47,14 +47,6 @@ describe("given a connection", () => {
     await db.close();
     expect(db.isOpen()).toBe(false);
     await expect(db.tableNames()).rejects.toThrow("Connection is closed");
-    await expect(db.renameTable("a", "b")).rejects.toThrow(
-      "Connection is closed",
-    );
-  });
-
-  it("should report renameTable as unsupported on an OSS connection", async () => {
-    await db.createTable("a", [{ id: 1 }]);
-    await expect(db.renameTable("a", "b")).rejects.toThrow(/not supported/);
   });
   it("should be able to create a table from an object arg `createTable(options)`, or args `createTable(name, data, options)`", async () => {
     let tbl = await db.createTable("test", [{ id: 1 }, { id: 2 }]);
@@ -171,22 +163,18 @@ describe("given a connection", () => {
 
     let manifestDir =
       tmpDir.name + "/test_manifest_paths_v2_empty.lance/_versions";
-    readdirSync(manifestDir)
+    readdirSync(manifestDir).forEach((file) => {
-      .filter((f) => f.endsWith(".manifest"))
+      expect(file).toMatch(/^\d{20}\.manifest$/);
-      .forEach((file) => {
+    });
-        expect(file).toMatch(/^\d{20}\.manifest$/);
-      });
 
     table = (await db.createTable("test_manifest_paths_v2", [{ id: 1 }], {
       enableV2ManifestPaths: true,
     })) as LocalTable;
     expect(await table.usesV2ManifestPaths()).toBe(true);
     manifestDir = tmpDir.name + "/test_manifest_paths_v2.lance/_versions";
-    readdirSync(manifestDir)
+    readdirSync(manifestDir).forEach((file) => {
-      .filter((f) => f.endsWith(".manifest"))
+      expect(file).toMatch(/^\d{20}\.manifest$/);
-      .forEach((file) => {
+    });
-        expect(file).toMatch(/^\d{20}\.manifest$/);
-      });
   });
 
   it("should be able to migrate tables to the V2 manifest paths", async () => {
@@ -203,20 +191,16 @@ describe("given a connection", () => {
 
     const manifestDir =
       tmpDir.name + "/test_manifest_path_migration.lance/_versions";
-    readdirSync(manifestDir)
+    readdirSync(manifestDir).forEach((file) => {
-      .filter((f) => f.endsWith(".manifest"))
+      expect(file).toMatch(/^\d\.manifest$/);
-      .forEach((file) => {
+    });
-        expect(file).toMatch(/^\d\.manifest$/);
-      });
 
     await table.migrateManifestPathsV2();
     expect(await table.usesV2ManifestPaths()).toBe(true);
 
-    readdirSync(manifestDir)
+    readdirSync(manifestDir).forEach((file) => {
-      .filter((f) => f.endsWith(".manifest"))
+      expect(file).toMatch(/^\d{20}\.manifest$/);
-      .forEach((file) => {
+    });
-        expect(file).toMatch(/^\d{20}\.manifest$/);
-      });
   });
 });
 
@@ -322,186 +306,3 @@ describe("clone table functionality", () => {
     ).rejects.toThrow("Deep clone is not yet implemented");
   });
 });
-
-describe("namespaces", () => {
-  let tmpDir: tmp.DirResult;
-  let db: Connection;
-
-  beforeEach(async () => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    // The local DirectoryNamespace backend only supports child namespaces
-    // when manifest mode is enabled (see lance-namespace-impls/src/dir.rs).
-    db = await connect(tmpDir.name, {
-      // biome-ignore lint/style/useNamingConvention: opaque backend property key, must match Rust
-      namespaceClientProperties: { manifest_enabled: "true" },
-    });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("should create and describe a namespace", async () => {
-    await db.createNamespace(["myns"]);
-    const desc = await db.describeNamespace(["myns"]);
-    expect(desc).toBeDefined();
-  });
-
-  it("should list namespaces created at the root", async () => {
-    await db.createNamespace(["alpha"]);
-    await db.createNamespace(["beta"]);
-    const list = await db.listNamespaces();
-    expect(list.namespaces).toEqual(expect.arrayContaining(["alpha", "beta"]));
-  });
-
-  it("should list child namespaces under a parent", async () => {
-    await db.createNamespace(["parent"]);
-    await db.createNamespace(["parent", "child"]);
-    const list = await db.listNamespaces(["parent"]);
-    expect(list.namespaces).toContain("child");
-  });
-
-  it("should drop a namespace", async () => {
-    await db.createNamespace(["ephemeral"]);
-    await db.dropNamespace(["ephemeral"]);
-    const list = await db.listNamespaces();
-    expect(list.namespaces).not.toContain("ephemeral");
-  });
-
-  it("should raise an error on any namespace op after close", async () => {
-    await db.close();
-    await expect(db.describeNamespace(["foo"])).rejects.toThrow(
-      "Connection is closed",
-    );
-    await expect(db.listNamespaces()).rejects.toThrow("Connection is closed");
-    await expect(db.createNamespace(["foo"])).rejects.toThrow(
-      "Connection is closed",
-    );
-    await expect(db.dropNamespace(["foo"])).rejects.toThrow(
-      "Connection is closed",
-    );
-  });
-
-  it("should raise an understandable error when describing a non-existent namespace", async () => {
-    await expect(db.describeNamespace(["does-not-exist"])).rejects.toThrow(
-      /not found/i,
-    );
-  });
-
-  it("should raise an error when creating a namespace that already exists", async () => {
-    await db.createNamespace(["dup"]);
-    await expect(db.createNamespace(["dup"])).rejects.toThrow();
-  });
-
-  it("should reject an unrecognized createNamespace mode with a clear error", async () => {
-    await expect(
-      // biome-ignore lint/suspicious/noExplicitAny: deliberately bypass TS to test runtime validation
-      db.createNamespace(["x"], { mode: "frobnicate" as any }),
-    ).rejects.toThrow(/Invalid mode 'frobnicate'/);
-  });
-
-  it("should reject an unrecognized dropNamespace mode with a clear error", async () => {
-    await db.createNamespace(["x"]);
-    await expect(
-      // biome-ignore lint/suspicious/noExplicitAny: deliberately bypass TS to test runtime validation
-      db.dropNamespace(["x"], { mode: "frobnicate" as any }),
-    ).rejects.toThrow(/Invalid mode 'frobnicate'/);
-  });
-
-  it("should reject an unrecognized dropNamespace behavior with a clear error", async () => {
-    await db.createNamespace(["x"]);
-    await expect(
-      // biome-ignore lint/suspicious/noExplicitAny: deliberately bypass TS to test runtime validation
-      db.dropNamespace(["x"], { behavior: "frobnicate" as any }),
-    ).rejects.toThrow(/Invalid behavior 'frobnicate'/);
-  });
-});
-
-describe("connectNamespace", () => {
-  let tmpDir: tmp.DirResult;
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("connects via the dir implementation and supports table ops", async () => {
-    const db = await connectNamespace("dir", { root: tmpDir.name });
-    await db.createTable("users", [{ id: 1 }, { id: 2 }]);
-    await expect(db.tableNames()).resolves.toContain("users");
-  });
-
-  it("throws a clear error when implName is empty", async () => {
-    await expect(connectNamespace("", {})).rejects.toThrow(
-      "implName must be a non-empty string",
-    );
-  });
-
-  it("throws when the namespace implementation is unknown", async () => {
-    await expect(connectNamespace("not-a-real-impl", {})).rejects.toThrow();
-  });
-
-  it("passes storage options through to the namespace", async () => {
-    const db = await connectNamespace(
-      "dir",
-      { root: tmpDir.name },
-      { storageOptions: { newTableDataStorageVersion: "stable" } },
-    );
-    await db.createTable("plumbing", [{ id: 1 }]);
-    await expect(db.tableNames()).resolves.toContain("plumbing");
-  });
-
-  it("supports child namespaces when manifestEnabled is true on the dir config", async () => {
-    const writer = await connectNamespace("dir", {
-      root: tmpDir.name,
-      manifestEnabled: true,
-    });
-    await writer.createNamespace(["analytics"]);
-    await writer.createTable("orders", [{ id: 1 }, { id: 2 }], ["analytics"]);
-    await writer.close();
-
-    const reader = await connectNamespace("dir", {
-      root: tmpDir.name,
-      manifestEnabled: true,
-    });
-    await expect(reader.tableNames(["analytics"])).resolves.toContain("orders");
-    const orders = await reader.openTable("orders", ["analytics"]);
-    await expect(orders.countRows()).resolves.toBe(2);
-  });
-
-  it("merges extraProperties into the dir config and is overridden by typed fields", async () => {
-    // Two observable assertions:
-    // - Typed `root` overrides extraProperties.root: createTable would fail
-    //   under the bogus path if the override didn't happen.
-    // - extraProperties.manifest_enabled="false" is honored end-to-end. Child
-    //   namespaces require manifest mode (default true), so explicitly
-    //   disabling it via extraProperties must make createNamespace reject. If
-    //   extraProperties pass-through were silently broken, the default would
-    //   let createNamespace succeed.
-    const db = await connectNamespace("dir", {
-      root: tmpDir.name,
-      extraProperties: {
-        root: "/should/be/overridden",
-        // biome-ignore lint/style/useNamingConvention: backend property key
-        manifest_enabled: "false",
-      },
-    });
-    await db.createTable("base", [{ id: 1 }]);
-    await expect(db.tableNames()).resolves.toContain("base");
-    await expect(db.createNamespace(["analytics"])).rejects.toThrow();
-  });
-
-  it("flows unknown top-level keys through when implName is dynamic (no silent drop)", async () => {
-    // Routes via the third overload because `impl` is `string`, not the
-    // literal `"dir"`. The dispatcher still notices the runtime value is
-    // "dir", but unknown keys like `manifest_enabled` must not be silently
-    // dropped during the conversion.
-    //
-    // Asserting a *negative* outcome (manifest disabled -> createNamespace
-    // rejects) is required for observability, since the backend default for
-    // `manifest_enabled` is true.
-    const impl: string = "dir";
-    const db = await connectNamespace(impl, {
-      root: tmpDir.name,
-      // biome-ignore lint/style/useNamingConvention: backend property key
-      manifest_enabled: "false",
-    });
-    await expect(db.createNamespace(["mixed"])).rejects.toThrow();
-  });
-});

nodejs/__test__/query.test.ts

@@ -109,209 +109,3 @@ describe("Query outputSchema", () => {
     expect(schema.fields.length).toBe(3);
   });
 });
-
-describe("Query orderBy", () => {
-  let tmpDir: tmp.DirResult;
-  let table: Table;
-
-  beforeEach(async () => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    const db = await connect(tmpDir.name);
-
-    // Create table with numeric data for sorting
-    const schema = new Schema([
-      new Field("id", new Int64(), true),
-      new Field("score", new Float32(), true),
-      new Field("name", new Utf8(), true),
-    ]);
-
-    const data = makeArrowTable(
-      [
-        { id: 1n, score: 3.5, name: "charlie" },
-        { id: 2n, score: 1.2, name: "alice" },
-        { id: 3n, score: 2.8, name: "bob" },
-        { id: 4n, score: 0.5, name: "david" },
-        { id: 5n, score: 4.1, name: "eve" },
-      ],
-      { schema },
-    );
-    table = await db.createTable("test", data);
-  });
-
-  afterEach(() => {
-    tmpDir.removeCallback();
-  });
-
-  it("should sort by single column ascending", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score", ascending: true, nullsFirst: false })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify ascending order
-    expect(results[0].score).toBeCloseTo(0.5, 0.001);
-    expect(results[1].score).toBeCloseTo(1.2, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(results[3].score).toBeCloseTo(3.5, 0.001);
-    expect(results[4].score).toBeCloseTo(4.1, 0.001);
-  });
-
-  it("should sort by single column descending", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score", ascending: false, nullsFirst: false })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify descending order
-    expect(results[0].score).toBeCloseTo(4.1, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(results[3].score).toBeCloseTo(1.2, 0.001);
-    expect(results[4].score).toBeCloseTo(0.5, 0.001);
-  });
-
-  it("should use ascending as default direction", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score" })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify ascending order (default)
-    expect(results[0].score).toBeCloseTo(0.5, 0.001);
-    expect(results[1].score).toBeCloseTo(1.2, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(results[3].score).toBeCloseTo(3.5, 0.001);
-    expect(results[4].score).toBeCloseTo(4.1, 0.001);
-  });
-
-  it("should sort by string column", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "name" })
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify alphabetical order
-    expect(results[0].name).toBe("alice");
-    expect(results[1].name).toBe("bob");
-    expect(results[2].name).toBe("charlie");
-    expect(results[3].name).toBe("david");
-    expect(results[4].name).toBe("eve");
-  });
-
-  it("should support method chaining with where", async () => {
-    const results = await table
-      .query()
-      .where("score > 2.0")
-      .orderBy({ columnName: "score" })
-      .toArray();
-    expect(results.length).toBe(3);
-    // Verify filtered and sorted
-    expect(results[0].score).toBeCloseTo(2.8, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(4.1, 0.001);
-  });
-
-  it("should support method chaining with limit", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score", ascending: false })
-      .limit(3)
-      .toArray();
-
-    expect(results.length).toBe(3);
-    // Verify top 3 in descending order
-    expect(results[0].score).toBeCloseTo(4.1, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-  });
-
-  it("should support method chaining with offset", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "score" })
-      .offset(2)
-      .limit(2)
-      .toArray();
-
-    expect(results.length).toBe(2);
-    // Verify results skip first 2 and take next 2
-    expect(results[0].score).toBeCloseTo(2.8, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-  });
-
-  it("should support method chaining with select", async () => {
-    const results = await table
-      .query()
-      .orderBy({ columnName: "name" })
-      .select(["name", "score"])
-      .toArray();
-
-    expect(results.length).toBe(5);
-    // Verify only selected columns are present
-    expect(Object.keys(results[0])).toEqual(["name", "score"]);
-    expect(Object.keys(results[4])).toEqual(["name", "score"]);
-    // Verify sorted by name
-    expect(results[0].name).toBe("alice");
-    expect(results[4].name).toBe("eve");
-  });
-
-  it("should support complex method chaining", async () => {
-    const results = await table
-      .query()
-      .where("score > 1.0")
-      .orderBy({ columnName: "score", ascending: false })
-      .limit(3)
-      .select(["id", "score", "name"])
-      .toArray();
-
-    expect(results.length).toBe(3);
-    // Verify filtered, sorted, limited, and projected
-    expect(results[0].score).toBeCloseTo(4.1, 0.001);
-    expect(results[1].score).toBeCloseTo(3.5, 0.001);
-    expect(results[2].score).toBeCloseTo(2.8, 0.001);
-    expect(Object.keys(results[0])).toEqual(["id", "score", "name"]);
-  });
-
-  it("should support multi-column ordering and null placement", async () => {
-    const schema = new Schema([
-      new Field("group", new Int64(), true),
-      new Field("score", new Float32(), true),
-      new Field("name", new Utf8(), true),
-    ]);
-
-    const data = makeArrowTable(
-      [
-        { group: 1n, score: null, name: "z" },
-        { group: 1n, score: 1.0, name: "b" },
-        { group: 1n, score: 1.0, name: "a" },
-        { group: 2n, score: 0.5, name: "c" },
-      ],
-      { schema },
-    );
-    const nullTable = await (await connect(tmpDir.name)).createTable(
-      "test_multi_order",
-      data,
-      { mode: "overwrite" },
-    );
-
-    const results = await nullTable
-      .query()
-      .orderBy([
-        { columnName: "group", ascending: true, nullsFirst: false },
-        { columnName: "score", ascending: true, nullsFirst: true },
-        { columnName: "name", ascending: true, nullsFirst: false },
-      ])
-      .toArray();
-
-    expect(results.map((r) => [r.group, r.score, r.name])).toEqual([
-      [1n, null, "z"],
-      [1n, 1.0, "a"],
-      [1n, 1.0, "b"],
-      [2n, 0.5, "c"],
-    ]);
-  });
-});

nodejs/__test__/remote.test.ts

@@ -617,68 +617,4 @@ describe("remote connection", () => {
       );
     });
   });
-
-  describe("renameTable", () => {
-    async function captureRenameRequest(
-      call: (db: Connection) => Promise<void>,
-    ): Promise<{ url: string; body: Record<string, unknown> }> {
-      let captured: { url: string; body: Record<string, unknown> } | undefined;
-      await withMockDatabase((req, res) => {
-        let raw = "";
-        req.on("data", (chunk) => {
-          raw += chunk;
-        });
-        req.on("end", () => {
-          captured = {
-            url: req.url ?? "",
-            body: raw ? JSON.parse(raw) : {},
-          };
-          res.writeHead(200, { "Content-Type": "application/json" }).end("");
-        });
-      }, call);
-      if (!captured) {
-        throw new Error("mock server never saw a request");
-      }
-      return captured;
-    }
-
-    it("sends rename request for a table in the root namespace", async () => {
-      const { url, body } = await captureRenameRequest(async (db) => {
-        await db.renameTable("table1", "table2");
-      });
-      expect(url).toBe("/v1/table/table1/rename/");
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      expect(body).toEqual({ new_table_name: "table2" });
-    });
-
-    it("omits new_namespace when only the current namespace is supplied", async () => {
-      // Safe-default check: passing namespacePath alone must not send
-      // `new_namespace`, so the server keeps the table in its current
-      // namespace instead of silently moving it to root.
-      const { url, body } = await captureRenameRequest(async (db) => {
-        await db.renameTable("table1", "table2", {
-          namespacePath: ["ns1"],
-        });
-      });
-      expect(url).toBe("/v1/table/ns1$table1/rename/");
-      // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-      expect(body).toEqual({ new_table_name: "table2" });
-    });
-
-    it("includes new_namespace in the body for a cross-namespace rename", async () => {
-      const { url, body } = await captureRenameRequest(async (db) => {
-        await db.renameTable("table1", "table2", {
-          namespacePath: ["ns1"],
-          newNamespacePath: ["ns2"],
-        });
-      });
-      expect(url).toBe("/v1/table/ns1$table1/rename/");
-      expect(body).toEqual({
-        // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-        new_table_name: "table2",
-        // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-        new_namespace: ["ns2"],
-      });
-    });
-  });
 });

nodejs/__test__/rerankers.test.ts

@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-import { spawn } from "node:child_process";
-import * as path from "node:path";
 import { RecordBatch } from "apache-arrow";
 import * as tmp from "tmp";
 import { Connection, Index, Table, connect, makeArrowTable } from "../lancedb";
@@ -78,91 +76,4 @@ describe("rerankers", function () {
 
     expect(result).toHaveLength(2);
   });
-
-  it("does not keep process alive after rerank query", async function () {
-    const script = `
-import * as lancedb from "./dist/index.js";
-import * as os from "node:os";
-import * as path from "node:path";
-import * as fs from "node:fs/promises";
-
-const dir = await fs.mkdtemp(path.join(os.tmpdir(), "lancedb-rerank-exit-"));
-const db = await lancedb.connect(dir);
-const table = await db.createTable("test", [{ text: "hello", vector: [1, 2, 3] }], {
-  mode: "overwrite",
-});
-await table.createIndex("text", { config: lancedb.Index.fts() });
-await table.waitForIndex(["text_idx"], 30);
-
-const reranker = await lancedb.rerankers.RRFReranker.create();
-await table
-  .query()
-  .nearestTo([1, 2, 3])
-  .fullTextSearch("hello")
-  .rerank(reranker)
-  .toArray();
-
-table.close();
-db.close();
-`;
-
-    await new Promise<void>((resolve, reject) => {
-      const child = spawn(
-        process.execPath,
-        ["--input-type=module", "-e", script],
-        {
-          cwd: path.resolve(__dirname, ".."),
-          stdio: ["ignore", "pipe", "pipe"],
-        },
-      );
-
-      let stdout = "";
-      let stderr = "";
-
-      child.stdout.on("data", (chunk) => {
-        stdout += chunk.toString();
-      });
-
-      child.stderr.on("data", (chunk) => {
-        stderr += chunk.toString();
-      });
-
-      const timeout = setTimeout(() => {
-        child.kill();
-        reject(
-          new Error(
-            `child process did not exit in time\nstdout:\n${stdout}\nstderr:\n${stderr}`,
-          ),
-        );
-      }, 20_000);
-
-      child.on("error", (err) => {
-        clearTimeout(timeout);
-        reject(err);
-      });
-
-      child.on("exit", (code, signal) => {
-        clearTimeout(timeout);
-        if (signal !== null) {
-          reject(
-            new Error(
-              `child process exited with signal ${signal}\nstdout:\n${stdout}\nstderr:\n${stderr}`,
-            ),
-          );
-          return;
-        }
-
-        if (code !== 0) {
-          reject(
-            new Error(
-              `child process exited with code ${code}\nstdout:\n${stdout}\nstderr:\n${stderr}`,
-            ),
-          );
-          return;
-        }
-
-        resolve();
-      });
-    });
-  });
 });

nodejs/__test__/scannable.test.ts

@@ -1,438 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  Field,
-  Float16,
-  Int32,
-  type RecordBatch,
-  RecordBatchReader,
-  Schema,
-  tableToIPC,
-} from "apache-arrow";
-import { makeArrowTable, makeEmptyTable } from "../lancedb/arrow";
-import { Scannable } from "../lancedb/scannable";
-
-function makeTable() {
-  return makeArrowTable(
-    [
-      { id: 1, name: "a" },
-      { id: 2, name: "b" },
-      { id: 3, name: "c" },
-    ],
-    { vectorColumns: {} },
-  );
-}
-
-async function makeReader(): Promise<RecordBatchReader> {
-  // `RecordBatchReader.from()` returns an unopened reader; `.schema` is only
-  // populated after `.open()`. Opening sync readers is synchronous.
-  const reader = RecordBatchReader.from(tableToIPC(makeTable()));
-  return reader.open() as RecordBatchReader;
-}
-
-describe("Scannable", () => {
-  describe("fromTable", () => {
-    test("reflects schema, numRows, and defaults rescannable=true", async () => {
-      const table = makeTable();
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBe(table.numRows);
-      expect(scannable.rescannable).toBe(true);
-    });
-
-    test("throws when opts.numRows does not match table.numRows", async () => {
-      await expect(
-        Scannable.fromTable(makeTable(), { numRows: 42 }),
-      ).rejects.toThrow(/does not match table\.numRows/);
-    });
-
-    test("throws when opts.rescannable is false", async () => {
-      await expect(
-        Scannable.fromTable(makeTable(), { rescannable: false }),
-      ).rejects.toThrow(/always rescannable/);
-    });
-  });
-
-  describe("fromRecordBatchReader", () => {
-    test("reflects schema and defaults numRows=null, rescannable=false", async () => {
-      const reader = await makeReader();
-      const scannable = await Scannable.fromRecordBatchReader(reader);
-
-      expect(scannable.schema).toBe(reader.schema);
-      expect(scannable.numRows).toBeNull();
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("honors numRows override", async () => {
-      const scannable = await Scannable.fromRecordBatchReader(
-        await makeReader(),
-        { numRows: 3 },
-      );
-
-      expect(scannable.numRows).toBe(3);
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("rescannable: false explicit does not throw", async () => {
-      const reader = await makeReader();
-      const scannable = await Scannable.fromRecordBatchReader(reader, {
-        rescannable: false,
-      });
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("throws when opts.rescannable is true", async () => {
-      const reader = await makeReader();
-      await expect(
-        Scannable.fromRecordBatchReader(reader, { rescannable: true }),
-      ).rejects.toThrow(/does not accept rescannable/);
-    });
-
-    test("throws when opts.rescannable is true even alongside numRows", async () => {
-      const reader = await makeReader();
-      await expect(
-        Scannable.fromRecordBatchReader(reader, {
-          numRows: 3,
-          rescannable: true,
-        }),
-      ).rejects.toThrow(/does not accept rescannable/);
-    });
-  });
-
-  describe("fromIterable", () => {
-    test("accepts a sync iterable of batches", async () => {
-      const table = makeTable();
-      const scannable = await Scannable.fromIterable(
-        table.schema,
-        table.batches,
-      );
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBeNull();
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    test("accepts an async iterable of batches", async () => {
-      const table = makeTable();
-      async function* generator(): AsyncGenerator<RecordBatch> {
-        for (const batch of table.batches) {
-          yield batch;
-        }
-      }
-
-      const scannable = await Scannable.fromIterable(table.schema, generator());
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.rescannable).toBe(false);
-    });
-
-    describe("rescannable: true detection", () => {
-      // Replayable inputs: [Symbol.iterator]() / [Symbol.asyncIterator]()
-      // returns a fresh iterator each call. Must NOT throw.
-
-      test("Array passes (fresh ArrayIterator each call)", async () => {
-        const table = makeTable();
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          table.batches,
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("Set passes (fresh SetIterator each call)", async () => {
-        const table = makeTable();
-        const set = new Set<RecordBatch>(table.batches);
-        const scannable = await Scannable.fromIterable(table.schema, set, {
-          rescannable: true,
-        });
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("custom Iterable returning a fresh iterator passes", async () => {
-        const table = makeTable();
-        const replayable: Iterable<RecordBatch> = {
-          [Symbol.iterator]() {
-            return table.batches[Symbol.iterator]();
-          },
-        };
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          replayable,
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("object with generator method passes (fresh generator each call)", async () => {
-        const table = makeTable();
-        const replayable: Iterable<RecordBatch> = {
-          *[Symbol.iterator]() {
-            for (const batch of table.batches) yield batch;
-          },
-        };
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          replayable,
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      test("empty Array passes (replayable degenerate case)", async () => {
-        const schema = makeTable().schema;
-        const scannable = await Scannable.fromIterable(
-          schema,
-          [] as RecordBatch[],
-          { rescannable: true },
-        );
-        expect(scannable.rescannable).toBe(true);
-      });
-
-      // One-shot inputs: [Symbol.iterator]() / [Symbol.asyncIterator]()
-      // returns the same object, or the input is already-an-iterator.
-      // Must throw with a /one-shot/ message.
-
-      test("sync generator throws", async () => {
-        const table = makeTable();
-        function* generator(): Generator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        await expect(
-          Scannable.fromIterable(table.schema, generator(), {
-            rescannable: true,
-          }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("async generator throws", async () => {
-        const table = makeTable();
-        async function* generator(): AsyncGenerator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        await expect(
-          Scannable.fromIterable(table.schema, generator(), {
-            rescannable: true,
-          }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("empty generator throws (one-shot degenerate case)", async () => {
-        const schema = makeTable().schema;
-        function* generator(): Generator<RecordBatch> {
-          // intentionally empty; yields nothing.
-        }
-        await expect(
-          Scannable.fromIterable(schema, generator(), { rescannable: true }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("custom self-iterator throws", async () => {
-        const table = makeTable();
-        const batches = table.batches;
-        let i = 0;
-        const oneShot: Iterable<RecordBatch> & Iterator<RecordBatch> = {
-          [Symbol.iterator]() {
-            return this;
-          },
-          next() {
-            if (i >= batches.length) {
-              return { done: true, value: undefined };
-            }
-            return { done: false, value: batches[i++] };
-          },
-        };
-        await expect(
-          Scannable.fromIterable(table.schema, oneShot, { rescannable: true }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("Array.values() (IterableIterator) throws", async () => {
-        const table = makeTable();
-        const iter = table.batches.values();
-        await expect(
-          Scannable.fromIterable(table.schema, iter, { rescannable: true }),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      test("raw iterator (only `.next`) throws", async () => {
-        const table = makeTable();
-        const batches = table.batches;
-        let i = 0;
-        const rawIter = {
-          next(): IteratorResult<RecordBatch> {
-            if (i >= batches.length) {
-              return { done: true, value: undefined };
-            }
-            return { done: false, value: batches[i++] };
-          },
-        };
-        await expect(
-          Scannable.fromIterable(
-            table.schema,
-            rawIter as unknown as Iterable<RecordBatch>,
-            { rescannable: true },
-          ),
-        ).rejects.toThrow(/one-shot/);
-      });
-
-      // Edge: null/undefined must not crash the detection helper. The
-      // null check belongs to `normalizeIterator` and only fires when a
-      // scan starts.
-
-      test("null input does not crash detection at construction", async () => {
-        const schema = makeTable().schema;
-        await expect(
-          Scannable.fromIterable(
-            schema,
-            null as unknown as Iterable<RecordBatch>,
-            {
-              rescannable: true,
-            },
-          ),
-        ).resolves.toBeDefined();
-      });
-
-      test("undefined input does not crash detection at construction", async () => {
-        const schema = makeTable().schema;
-        await expect(
-          Scannable.fromIterable(
-            schema,
-            undefined as unknown as Iterable<RecordBatch>,
-            { rescannable: true },
-          ),
-        ).resolves.toBeDefined();
-      });
-
-      // Default (rescannable omitted) skips the check entirely, so even
-      // pathological inputs construct without throwing here.
-
-      test("rescannable omitted skips detection entirely (generator passes)", async () => {
-        const table = makeTable();
-        function* generator(): Generator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          generator(),
-        );
-        expect(scannable.rescannable).toBe(false);
-      });
-
-      test("rescannable: false explicit skips detection entirely (generator passes)", async () => {
-        const table = makeTable();
-        function* generator(): Generator<RecordBatch> {
-          for (const batch of table.batches) yield batch;
-        }
-        const scannable = await Scannable.fromIterable(
-          table.schema,
-          generator(),
-          { rescannable: false },
-        );
-        expect(scannable.rescannable).toBe(false);
-      });
-    });
-  });
-
-  describe("fromFactory", () => {
-    test("defaults rescannable=true and does not invoke the factory eagerly", async () => {
-      const table = makeTable();
-      const factory = jest.fn(() => table.batches);
-
-      const scannable = await Scannable.fromFactory(table.schema, factory);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.rescannable).toBe(true);
-      expect(factory).not.toHaveBeenCalled();
-    });
-
-    test("honors rescannable and numRows overrides", async () => {
-      const table = makeTable();
-      const scannable = await Scannable.fromFactory(
-        table.schema,
-        () => table.batches,
-        { numRows: 7, rescannable: false },
-      );
-
-      expect(scannable.numRows).toBe(7);
-      expect(scannable.rescannable).toBe(false);
-    });
-  });
-
-  describe("validation", () => {
-    test("throws when numRows is negative", async () => {
-      await expect(
-        Scannable.fromFactory(makeTable().schema, () => [], { numRows: -1 }),
-      ).rejects.toThrow(/non-negative/);
-    });
-
-    test("throws when numRows is not an integer", async () => {
-      await expect(
-        Scannable.fromFactory(makeTable().schema, () => [], { numRows: 3.5 }),
-      ).rejects.toThrow(/integer/);
-    });
-  });
-
-  describe("native handle", () => {
-    test("exposes a native handle via inner", async () => {
-      const scannable = await Scannable.fromTable(makeTable());
-      expect(scannable.inner).toBeDefined();
-      expect(typeof scannable.inner).toBe("object");
-      expect(scannable.inner).not.toBeNull();
-    });
-  });
-
-  // Schema-variety construction tests. Each asserts that construction
-  // succeeds against a richer Arrow schema, which transitively exercises
-  // schema serialization and the Rust-side `ipc_file_to_schema` for types
-  // beyond flat primitives.
-  describe("schema variety", () => {
-    test("accepts an empty table", async () => {
-      const schema = new Schema([new Field("id", new Int32(), true)]);
-      const table = makeEmptyTable(schema);
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.numRows).toBe(0);
-      expect(scannable.schema).toBe(table.schema);
-    });
-
-    test("accepts nested struct and list columns", async () => {
-      const table = makeArrowTable(
-        [
-          { id: 1, point: { x: 0, y: 0 }, tags: ["a", "b"] },
-          { id: 2, point: { x: 1, y: 2 }, tags: ["c"] },
-        ],
-        { vectorColumns: {} },
-      );
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBe(2);
-    });
-
-    test("accepts a FixedSizeList (vector) column", async () => {
-      const table = makeArrowTable(
-        [
-          { id: 1, vec: [1, 2, 3] },
-          { id: 2, vec: [4, 5, 6] },
-        ],
-        { vectorColumns: { vec: { type: new Float16() } } },
-      );
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema).toBe(table.schema);
-      expect(scannable.numRows).toBe(2);
-    });
-
-    test("accepts a table with many columns", async () => {
-      const row: Record<string, number> = {};
-      for (let i = 0; i < 50; i++) row[`c${i}`] = i;
-      const table = makeArrowTable([row, row], { vectorColumns: {} });
-      const scannable = await Scannable.fromTable(table);
-
-      expect(scannable.schema.fields.length).toBe(50);
-      expect(scannable.numRows).toBe(2);
-    });
-  });
-});

nodejs/__test__/table.test.ts

@@ -28,7 +28,6 @@ import {
   List,
   Schema,
   SchemaLike,
-  Struct,
   Type,
   Uint8,
   Utf8,
@@ -116,48 +115,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await expect(table.countRows()).resolves.toBe(1);
     });
 
-    it("should invoke the progress callback", async () => {
-      const events: import("../lancedb").WriteProgress[] = [];
-      await table.add([{ id: 1 }, { id: 2 }, { id: 3 }], {
-        progress: (p) => events.push(p),
-      });
-
-      expect(events.length).toBeGreaterThan(0);
-      const last = events[events.length - 1];
-      expect(last.done).toBe(true);
-      // Earlier callbacks must have done=false.
-      for (const ev of events.slice(0, -1)) {
-        expect(ev.done).toBe(false);
-      }
-      // outputRows reflects the rows added in this call, not table size.
-      expect(last.outputRows).toBe(3);
-      // The input source (an array) reports a row count, so totalRows is set.
-      expect(last.totalRows).toBe(3);
-      // outputRows is monotonic.
-      for (let i = 1; i < events.length; i++) {
-        expect(events[i].outputRows).toBeGreaterThanOrEqual(
-          events[i - 1].outputRows,
-        );
-      }
-    });
-
-    it("should swallow errors thrown from the progress callback", async () => {
-      const warn = jest
-        .spyOn(console, "warn")
-        .mockImplementation(() => undefined);
-      try {
-        const res = await table.add([{ id: 1 }, { id: 2 }], {
-          progress: () => {
-            throw new Error("callback bomb");
-          },
-        });
-        expect(res.version).toBeGreaterThan(0);
-        expect(warn).toHaveBeenCalled();
-      } finally {
-        warn.mockRestore();
-      }
-    });
-
     it("should let me close the table", async () => {
       expect(table.isOpen()).toBe(true);
       table.close();
@@ -781,113 +738,6 @@ describe("When creating an index", () => {
     expect(indices2.length).toBe(0);
   });
 
-  it("should create and search a nested vector index", async () => {
-    const db = await connect(tmpDir.name);
-    const nestedSchema = new Schema([
-      new Field("id", new Int32(), true),
-      new Field(
-        "image",
-        new Struct([
-          new Field(
-            "embedding",
-            new FixedSizeList(2, new Field("item", new Float32(), true)),
-            true,
-          ),
-        ]),
-        true,
-      ),
-    ]);
-    const nestedTable = await db.createTable(
-      "nested_vector",
-      makeArrowTable(
-        Array.from({ length: 300 }, (_, id) => ({
-          id,
-          image: { embedding: [id, id + 1] },
-        })),
-        { schema: nestedSchema },
-      ),
-    );
-
-    await nestedTable.createIndex("image.embedding", {
-      name: "image_embedding_idx",
-    });
-    const indices = await nestedTable.listIndices();
-    expect(indices).toContainEqual({
-      name: "image_embedding_idx",
-      indexType: "IvfPq",
-      columns: ["image.embedding"],
-    });
-
-    const explicit = await nestedTable
-      .query()
-      .nearestTo([0.0, 1.0])
-      .column("image.embedding")
-      .limit(1)
-      .toArray();
-    const inferred = await nestedTable
-      .query()
-      .nearestTo([0.0, 1.0])
-      .limit(1)
-      .toArray();
-    expect(inferred[0].id).toEqual(explicit[0].id);
-  });
-
-  it("should report multiple nested vector candidates", async () => {
-    const db = await connect(tmpDir.name);
-    const nestedSchema = new Schema([
-      new Field(
-        "image",
-        new Struct([
-          new Field(
-            "embedding",
-            new FixedSizeList(2, new Field("item", new Float32(), true)),
-            true,
-          ),
-        ]),
-        true,
-      ),
-      new Field(
-        "text",
-        new Struct([
-          new Field(
-            "embedding",
-            new FixedSizeList(2, new Field("item", new Float32(), true)),
-            true,
-          ),
-        ]),
-        true,
-      ),
-    ]);
-    const nestedTable = await db.createTable(
-      "multiple_nested_vectors",
-      makeArrowTable(
-        [
-          {
-            image: { embedding: [0.0, 1.0] },
-            text: { embedding: [2.0, 3.0] },
-          },
-        ],
-        { schema: nestedSchema },
-      ),
-    );
-
-    await expect(
-      nestedTable.query().nearestTo([0.0, 1.0]).limit(1).toArray(),
-    ).rejects.toThrow(/image\.embedding.*text\.embedding/);
-  });
-
-  it("should report when no default vector column exists", async () => {
-    const db = await connect(tmpDir.name);
-    const noVectorTable = await db.createTable(
-      "no_vector",
-      makeArrowTable([{ id: 0, label: "cat" }]),
-    );
-
-    await expect(
-      noVectorTable.query().nearestTo([0.0, 1.0]).limit(1).toArray(),
-    ).rejects.toThrow(/No vector column/);
-  });
-
   it("should wait for index readiness", async () => {
     // Create an index and then wait for it to be ready
     await tbl.createIndex("vec");
@@ -1571,33 +1421,6 @@ describe("schema evolution", function () {
     expect(await table.schema()).toEqual(expectedSchema3);
   });
 
-  it("can update field metadata", async function () {
-    const con = await connect(tmpDir.name);
-    const table = await con.createTable("fm", [
-      { id: 1, category: "a" },
-      { id: 2, category: "b" },
-    ]);
-
-    const res = await table.updateFieldMetadata([
-      { path: "category", metadata: { unit: "label", pii: "false" } },
-    ]);
-    expect(res).toHaveProperty("version");
-    expect(res.version).toBe(2);
-
-    let cat = (await table.schema()).fields.find((f) => f.name === "category");
-    expect(cat?.metadata.get("unit")).toBe("label");
-    expect(cat?.metadata.get("pii")).toBe("false");
-
-    // merge: add a key, delete one via null, keep the rest
-    await table.updateFieldMetadata([
-      { path: "category", metadata: { source: "import", pii: null } },
-    ]);
-    cat = (await table.schema()).fields.find((f) => f.name === "category");
-    expect(cat?.metadata.get("unit")).toBe("label"); // preserved
-    expect(cat?.metadata.get("source")).toBe("import"); // added
-    expect(cat?.metadata.has("pii")).toBe(false); // deleted
-  });
-
   it("can cast to various types", async function () {
     const con = await connect(tmpDir.name);
 
@@ -2047,25 +1870,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results.length).toBe(3);
     });
 
-    test("prewarmData errors on local tables", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: "alpha", vector: [0.1, 0.2, 0.3] },
-        { text: "beta", vector: [0.4, 0.5, 0.6] },
-      ];
-      const table = await db.createTable("prewarm_data_test", data);
-
-      // prewarmData is only supported on remote tables. We verify the call
-      // is wired through napi and surfaces the expected error for both
-      // arg shapes (undefined and string[]).
-      await expect(table.prewarmData()).rejects.toThrow(
-        "prewarm_data is currently only supported on remote tables",
-      );
-      await expect(table.prewarmData(["text"])).rejects.toThrow(
-        "prewarm_data is currently only supported on remote tables",
-      );
-    });
-
     test("full text index on list", async () => {
       const db = await connect(tmpDir.name);
       const data = [
@@ -2525,224 +2329,3 @@ describe("when creating a table with Float32Array vectors", () => {
     expect((fsl.children[0].type as Float32).precision).toBe(1);
   });
 });
-
-describe("setUnenforcedPrimaryKey", () => {
-  let tmpDir: tmp.DirResult;
-
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  it("sets a single-column primary key (string or one-element array)", async () => {
-    const conn = await connect(tmpDir.name);
-    const schema = new arrow.Schema([
-      new arrow.Field("id", new arrow.Int64(), false),
-    ]);
-    const t1 = await conn.createEmptyTable("t1", schema);
-    await t1.setUnenforcedPrimaryKey("id");
-
-    const t2 = await conn.createEmptyTable("t2", schema);
-    await t2.setUnenforcedPrimaryKey(["id"]);
-  });
-
-  it("rejects a compound primary key", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await conn.createEmptyTable(
-      "t",
-      new arrow.Schema([
-        new arrow.Field("id", new arrow.Int64(), false),
-        new arrow.Field("name", new arrow.Utf8(), false),
-      ]),
-    );
-    await expect(
-      table.setUnenforcedPrimaryKey(["id", "name"]),
-    ).rejects.toThrow();
-  });
-
-  it("rejects changing the primary key once set", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await conn.createEmptyTable(
-      "t",
-      new arrow.Schema([
-        new arrow.Field("id", new arrow.Int64(), false),
-        new arrow.Field("name", new arrow.Utf8(), false),
-      ]),
-    );
-    await table.setUnenforcedPrimaryKey("id");
-    await expect(table.setUnenforcedPrimaryKey("name")).rejects.toThrow();
-    await expect(table.setUnenforcedPrimaryKey("id")).rejects.toThrow();
-  });
-});
-
-describe("setLsmWriteSpec / unsetLsmWriteSpec", () => {
-  let tmpDir: tmp.DirResult;
-
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  async function makeTable(conn: Connection): Promise<Table> {
-    return await conn.createEmptyTable(
-      "t",
-      new arrow.Schema([new arrow.Field("id", new arrow.Int64(), false)]),
-    );
-  }
-
-  it("installs and removes a bucket spec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await makeTable(conn);
-
-    await table.setUnenforcedPrimaryKey("id");
-    await table.setLsmWriteSpec({
-      specType: "bucket",
-      column: "id",
-      numBuckets: 4,
-    });
-    await table.unsetLsmWriteSpec();
-    // A second unset errors — there is no spec left to remove.
-    await expect(table.unsetLsmWriteSpec()).rejects.toThrow();
-    // A fresh spec can be installed after unset.
-    await table.setLsmWriteSpec({
-      specType: "bucket",
-      column: "id",
-      numBuckets: 8,
-    });
-  });
-
-  it("installs an unsharded spec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await makeTable(conn);
-
-    await table.setUnenforcedPrimaryKey("id");
-    await table.setLsmWriteSpec({ specType: "unsharded" });
-    await table.unsetLsmWriteSpec();
-  });
-
-  it("installs an identity spec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await makeTable(conn);
-
-    await table.setUnenforcedPrimaryKey("id");
-    await table.setLsmWriteSpec({ specType: "identity", column: "id" });
-    await table.unsetLsmWriteSpec();
-  });
-
-  it("rejects an invalid spec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await makeTable(conn);
-
-    await table.setUnenforcedPrimaryKey("id");
-    // num_buckets out of range.
-    await expect(
-      table.setLsmWriteSpec({
-        specType: "bucket",
-        column: "id",
-        numBuckets: 0,
-      }),
-    ).rejects.toThrow();
-    // Column mismatch.
-    await expect(
-      table.setLsmWriteSpec({
-        specType: "bucket",
-        column: "missing",
-        numBuckets: 4,
-      }),
-    ).rejects.toThrow();
-  });
-});
-
-describe("LSM merge insert", () => {
-  let tmpDir: tmp.DirResult;
-
-  beforeEach(() => {
-    tmpDir = tmp.dirSync({ unsafeCleanup: true });
-  });
-  afterEach(() => tmpDir.removeCallback());
-
-  async function bucketTable(conn: Connection): Promise<Table> {
-    // The primary key column must be non-nullable.
-    const table = await conn.createEmptyTable(
-      "t",
-      new arrow.Schema([
-        new arrow.Field("id", new arrow.Utf8(), false),
-        new arrow.Field("value", new arrow.Float64(), true),
-      ]),
-    );
-    await table.add([
-      { id: "a", value: 1 },
-      { id: "b", value: 2 },
-    ]);
-    await table.setUnenforcedPrimaryKey("id");
-    // numBuckets = 1: every row routes to the single bucket.
-    await table.setLsmWriteSpec({
-      specType: "bucket",
-      column: "id",
-      numBuckets: 1,
-    });
-    return table;
-  }
-
-  it("routes merge_insert through the shard writer", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    const res = await table
-      .mergeInsert("id")
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .execute([
-        { id: "c", value: 3 },
-        { id: "d", value: 4 },
-      ]);
-    // LSM path: rows go to the MemWAL, so only numRows is populated.
-    expect(res.numRows).toBe(2);
-    expect(res.version).toBe(0);
-    expect(res.numInsertedRows).toBe(0);
-
-    await table.closeLsmWriters();
-  });
-
-  it("falls back to the standard path with useLsmWrite(false)", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    const res = await table
-      .mergeInsert("id")
-      .whenNotMatchedInsertAll()
-      .useLsmWrite(false)
-      .execute([
-        { id: "b", value: 9 },
-        { id: "e", value: 5 },
-      ]);
-    // Standard path commits: id="e" inserted ("b" already exists).
-    expect(res.numInsertedRows).toBe(1);
-    expect(await table.countRows()).toBe(3);
-  });
-
-  it("supports validateSingleShard(false)", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    const res = await table
-      .mergeInsert("id")
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .validateSingleShard(false)
-      .execute([{ id: "f", value: 6 }]);
-    expect(res.numRows).toBe(1);
-  });
-
-  it("rejects a non-upsert merge under an LSM spec", async () => {
-    const conn = await connect(tmpDir.name);
-    const table = await bucketTable(conn);
-
-    await expect(
-      table
-        .mergeInsert("id")
-        .whenNotMatchedInsertAll()
-        .execute([{ id: "g", value: 7 }]),
-    ).rejects.toThrow();
-  });
-});

nodejs/examples/filtering.test.ts

@@ -38,14 +38,5 @@ test("filtering examples", async () => {
     // --8<-- [start:sql_search]
     await tbl.query().where("id = 10").limit(10).toArray();
     // --8<-- [end:sql_search]
-
-    // --8<-- [start:orderby_search]
-    await tbl
-      .query()
-      .where("id > 10")
-      .orderBy({ columnName: "id", ascending: false })
-      .limit(5)
-      .toArray();
-    // --8<-- [end:orderby_search]
   });
 });

nodejs/examples/package.json

@@ -11,17 +11,16 @@
     "test": "node --experimental-vm-modules node_modules/.bin/jest --testEnvironment jest-environment-node-single-context --verbose",
     "lint": "biome check *.ts && biome format *.ts",
     "lint-ci": "biome ci .",
-    "lint-fix": "biome check --write *.ts && pnpm format",
+    "lint-fix": "biome check --write *.ts && npm run format",
     "format": "biome format --write *.ts"
   },
   "author": "Lance Devs",
   "license": "Apache-2.0",
-  "packageManager": "pnpm@11.1.1",
   "dependencies": {
-    "@huggingface/transformers": "3.0.2",
+    "@huggingface/transformers": "^3.0.2",
     "@lancedb/lancedb": "file:../dist",
-    "openai": "4.29.2",
+    "openai": "^4.29.2",
-    "sharp": "0.33.5"
+    "sharp": "^0.33.5"
   },
   "devDependencies": {
     "@biomejs/biome": "^1.7.3",

nodejs/examples/pnpm-workspace.yaml

@@ -1,13 +0,0 @@
-# Block resolution of versions less than 24h old (Shai-Hulud window).
-# This is the pnpm 11 default but pinned here so it's visible to
-# reviewers and survives a future pnpm major flipping the default.
-minimumReleaseAge: 1440
-
-# Fail install if a transitive dep tries to run an unapproved script.
-strictDepBuilds: true
-
-allowBuilds:
-  '@biomejs/biome': true
-  onnxruntime-node: true
-  protobufjs: true
-  sharp: true

nodejs/lancedb/arrow.ts

@@ -1291,18 +1291,6 @@ export async function fromRecordBatchToBuffer(
   return Buffer.from(await writer.toUint8Array());
 }
 
-/**
- * Create a buffer containing a single record batch using the Arrow IPC Stream
- * serialization. Each call produces a self-contained Stream message (schema +
- * batch + EOS) suitable for incremental decode by `arrow_ipc::reader::StreamReader`.
- */
-export async function fromRecordBatchToStreamBuffer(
-  batch: RecordBatch,
-): Promise<Buffer> {
-  const writer = RecordBatchStreamWriter.writeAll([batch]);
-  return Buffer.from(await writer.toUint8Array());
-}
-
 /**
  * Serialize an Arrow Table into a buffer using the Arrow IPC Stream serialization
  *

nodejs/lancedb/connection.ts

@@ -16,18 +16,6 @@ import {
 } from "./arrow";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { Connection as LanceDbConnection } from "./native";
-import type {
-  CreateNamespaceResponse,
-  DescribeNamespaceResponse,
-  DropNamespaceResponse,
-  ListNamespacesResponse,
-} from "./native";
-export type {
-  CreateNamespaceResponse,
-  DescribeNamespaceResponse,
-  DropNamespaceResponse,
-  ListNamespacesResponse,
-};
 import { sanitizeTable } from "./sanitize";
 import { LocalTable, Table } from "./table";
 
@@ -54,7 +42,7 @@ export interface CreateTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://docs.lancedb.com/storage/
+   * The available options are described at https://lancedb.com/docs/storage/
    */
   storageOptions?: Record<string, string>;
 
@@ -90,7 +78,7 @@ export interface OpenTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://docs.lancedb.com/storage/
+   * The available options are described at https://lancedb.com/docs/storage/
    */
   storageOptions?: Record<string, string>;
   /**
@@ -122,41 +110,6 @@ export interface TableNamesOptions {
   /** An optional limit to the number of results to return. */
   limit?: number;
 }
-
-export interface ListNamespacesOptions {
-  /** Token from a previous response for pagination. */
-  pageToken?: string;
-  /** An optional limit to the number of results to return. */
-  limit?: number;
-}
-
-export interface CreateNamespaceOptions {
-  /** Creation mode. */
-  mode?: "create" | "exist_ok" | "overwrite";
-  /** Properties to set on the new namespace. */
-  properties?: Record<string, string>;
-}
-
-export interface DropNamespaceOptions {
-  /** Whether to skip if the namespace doesn't exist, or fail. */
-  mode?: "skip" | "fail";
-  /** Refuse to drop if non-empty (restrict) or drop recursively (cascade). */
-  behavior?: "restrict" | "cascade";
-}
-
-export interface RenameTableOptions {
-  /**
-   * The namespace path of the table being renamed. Defaults to the root
-   * namespace (`[]`) when omitted.
-   */
-  namespacePath?: string[];
-  /**
-   * The namespace path to move the table to as part of the rename. When
-   * omitted the table stays in `namespacePath`.
-   */
-  newNamespacePath?: string[];
-}
-
 /**
  * A LanceDB Connection that allows you to open tables and create new ones.
  *
@@ -315,69 +268,6 @@ export abstract class Connection {
    */
   abstract dropAllTables(namespacePath?: string[]): Promise<void>;
 
-  /**
-   * Describe a namespace, returning its properties.
-   *
-   * @param {string[]} namespacePath - The namespace path to describe, in
-   *   parent → child order, e.g. `["analytics", "sales"]`.
-   * @returns {Promise<DescribeNamespaceResponse>} The namespace's properties
-   *   (may be undefined if the namespace has none).
-   */
-  abstract describeNamespace(
-    namespacePath: string[],
-  ): Promise<DescribeNamespaceResponse>;
-
-  /**
-   * List the immediate child namespaces under the given parent.
-   *
-   * Results may be paginated. To retrieve subsequent pages, pass the
-   * `pageToken` returned by a previous call.
-   *
-   * @param {string[]} namespacePath - The parent namespace path. Defaults
-   *   to the root namespace if omitted.
-   * @param {Partial<ListNamespacesOptions>} options - Pagination options
-   *   (`pageToken`, `limit`).
-   * @returns {Promise<ListNamespacesResponse>} Child namespace names and
-   *   an optional token for fetching the next page.
-   */
-  abstract listNamespaces(
-    namespacePath?: string[],
-    options?: Partial<ListNamespacesOptions>,
-  ): Promise<ListNamespacesResponse>;
-
-  /**
-   * Create a new namespace at the given path.
-   *
-   * @param {string[]} namespacePath - The namespace path to create.
-   * @param {Partial<CreateNamespaceOptions>} options - Creation `mode`
-   *   ("create" | "exist_ok" | "overwrite") and optional `properties`
-   *   to attach to the namespace.
-   * @returns {Promise<CreateNamespaceResponse>} The properties of the
-   *   created namespace and an optional transaction id.
-   */
-  abstract createNamespace(
-    namespacePath: string[],
-    options?: Partial<CreateNamespaceOptions>,
-  ): Promise<CreateNamespaceResponse>;
-
-  /**
-   * Drop a namespace.
-   *
-   * Use `behavior: "cascade"` to also drop everything contained in the
-   * namespace (sub-namespaces and tables). The default `"restrict"`
-   * behavior refuses to drop a non-empty namespace.
-   *
-   * @param {string[]} namespacePath - The namespace path to drop.
-   * @param {Partial<DropNamespaceOptions>} options - `mode` ("skip" | "fail"
-   *   for missing-namespace handling) and `behavior` ("restrict" | "cascade").
-   * @returns {Promise<DropNamespaceResponse>} Any properties returned by
-   *   the server and an optional transaction id.
-   */
-  abstract dropNamespace(
-    namespacePath: string[],
-    options?: Partial<DropNamespaceOptions>,
-  ): Promise<DropNamespaceResponse>;
-
   /**
    * Clone a table from a source table.
    *
@@ -404,24 +294,6 @@ export abstract class Connection {
       isShallow?: boolean;
     },
   ): Promise<Table>;
-
-  /**
-   * Rename a table.
-   *
-   * Currently only supported by LanceDB Cloud. Local OSS connections and
-   * namespace-backed connections (via {@link connectNamespace}) reject with
-   * a "not supported" error.
-   *
-   * @param {string} currentName - The current name of the table.
-   * @param {string} newName - The new name for the table.
-   * @param {RenameTableOptions} options - Optional namespace paths. When
-   *   `newNamespacePath` is omitted the table stays in `namespacePath`.
-   */
-  abstract renameTable(
-    currentName: string,
-    newName: string,
-    options?: RenameTableOptions,
-  ): Promise<void>;
 }
 
 /** @hideconstructor */
@@ -643,58 +515,6 @@ export class LocalConnection extends Connection {
   async dropAllTables(namespacePath?: string[]): Promise<void> {
     return this.inner.dropAllTables(namespacePath ?? []);
   }
-
-  describeNamespace(
-    namespacePath: string[],
-  ): Promise<DescribeNamespaceResponse> {
-    return this.inner.describeNamespace(namespacePath);
-  }
-
-  listNamespaces(
-    namespacePath?: string[],
-    options?: Partial<ListNamespacesOptions>,
-  ): Promise<ListNamespacesResponse> {
-    return this.inner.listNamespaces(
-      namespacePath ?? [],
-      options?.pageToken,
-      options?.limit,
-    );
-  }
-
-  createNamespace(
-    namespacePath: string[],
-    options?: Partial<CreateNamespaceOptions>,
-  ): Promise<CreateNamespaceResponse> {
-    return this.inner.createNamespace(
-      namespacePath,
-      options?.mode,
-      options?.properties,
-    );
-  }
-
-  dropNamespace(
-    namespacePath: string[],
-    options?: Partial<DropNamespaceOptions>,
-  ): Promise<DropNamespaceResponse> {
-    return this.inner.dropNamespace(
-      namespacePath,
-      options?.mode,
-      options?.behavior,
-    );
-  }
-
-  async renameTable(
-    currentName: string,
-    newName: string,
-    options?: RenameTableOptions,
-  ): Promise<void> {
-    return this.inner.renameTable(
-      currentName,
-      newName,
-      options?.namespacePath ?? [],
-      options?.newNamespacePath,
-    );
-  }
 }
 
 /**

nodejs/lancedb/index.ts

@@ -8,7 +8,6 @@ import {
 } from "./connection";
 
 import {
-  ConnectNamespaceOptions,
   ConnectionOptions,
   Connection as LanceDbConnection,
   JsHeaderProvider as NativeJsHeaderProvider,
@@ -23,7 +22,6 @@ export { JsHeaderProvider as NativeJsHeaderProvider } from "./native.js";
 export {
   AddColumnsSql,
   ConnectionOptions,
-  ConnectNamespaceOptions,
   IndexStatistics,
   IndexConfig,
   ClientConfig,
@@ -42,7 +40,6 @@ export {
   AddResult,
   AddColumnsResult,
   AlterColumnsResult,
-  UpdateFieldMetadataResult,
   DeleteResult,
   DropColumnsResult,
   UpdateResult,
@@ -65,14 +62,6 @@ export {
   CreateTableOptions,
   TableNamesOptions,
   OpenTableOptions,
-  ListNamespacesOptions,
-  CreateNamespaceOptions,
-  DropNamespaceOptions,
-  ListNamespacesResponse,
-  CreateNamespaceResponse,
-  DropNamespaceResponse,
-  DescribeNamespaceResponse,
-  RenameTableOptions,
 } from "./connection";
 
 export { Session } from "./native.js";
@@ -84,7 +73,6 @@ export {
   VectorQuery,
   TakeQuery,
   QueryExecutionOptions,
-  ColumnOrdering,
   FullTextSearchOptions,
   RecordBatchIterator,
   FullTextQuery,
@@ -115,10 +103,7 @@ export {
   UpdateOptions,
   OptimizeOptions,
   Version,
-  WriteProgress,
-  LsmWriteSpec,
   ColumnAlteration,
-  FieldMetadataUpdate,
 } from "./table";
 
 export {
@@ -132,7 +117,6 @@ export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";
 export { permutationBuilder, PermutationBuilder } from "./permutation";
-export { Scannable, ScannableOptions } from "./scannable";
 export * as rerankers from "./rerankers";
 export {
   SchemaLike,
@@ -309,197 +293,3 @@ export async function connect(
   );
   return new LocalConnection(nativeConn);
 }
-
-/**
- * Configuration for the built-in directory namespace (`"dir"`).
- *
- * The directory namespace stores tables under a single root path (local
- * filesystem or object storage URI). See
- * {@link https://docs.lancedb.com/namespaces} for the documented surface;
- * less-common knobs live under {@link DirNamespaceConfig.extraProperties}.
- */
-export interface DirNamespaceConfig {
-  /** Root path or URI containing the LanceDB tables. */
-  root: string;
-  /**
-   * Whether to maintain a namespace manifest at the root. Required for
-   * child namespaces. Defaults to true on the impl side.
-   */
-  manifestEnabled?: boolean;
-  /**
-   * Additional raw properties passed verbatim to the namespace
-   * implementation (e.g. `storage.*`, `credential_vendor.*`). Typed
-   * fields above take precedence on key collision.
-   */
-  extraProperties?: Record<string, string>;
-}
-
-/**
- * Configuration for the built-in REST namespace (`"rest"`).
- *
- * The REST namespace talks to a remote catalog server over HTTP. See
- * {@link https://docs.lancedb.com/namespaces} for the documented surface;
- * less-common knobs (TLS, metrics) live under
- * {@link RestNamespaceConfig.extraProperties}.
- */
-export interface RestNamespaceConfig {
-  /** Catalog endpoint URL. */
-  uri: string;
-  /**
-   * HTTP headers forwarded with each request. Keys are passed through
-   * as-is (e.g. `"x-api-key"`, `"Authorization"`).
-   */
-  headers?: Record<string, string>;
-  /**
-   * Additional raw properties passed verbatim to the namespace
-   * implementation (e.g. `tls.*`, `ops_metrics_enabled`, `delimiter`).
-   * Typed fields above take precedence on key collision.
-   */
-  extraProperties?: Record<string, string>;
-}
-
-function dirConfigToProperties(
-  config: DirNamespaceConfig,
-): Record<string, string> {
-  // Spread the whole input so that unknown keys (e.g. a raw `manifest_enabled`
-  // passed via the dynamic-impl path) flow through instead of being dropped.
-  // Typed transformations layer on top.
-  const { manifestEnabled, extraProperties, ...rest } = config;
-  const properties: Record<string, string> = {
-    ...(extraProperties ?? {}),
-    ...(rest as Record<string, string>),
-  };
-  if (manifestEnabled !== undefined) {
-    properties.manifest_enabled = String(manifestEnabled);
-  }
-  return properties;
-}
-
-function restConfigToProperties(
-  config: RestNamespaceConfig,
-): Record<string, string> {
-  const { headers, extraProperties, ...rest } = config;
-  const properties: Record<string, string> = {
-    ...(extraProperties ?? {}),
-    ...(rest as Record<string, string>),
-  };
-  if (headers) {
-    for (const [name, value] of Object.entries(headers)) {
-      properties[`headers.${name}`] = value;
-    }
-  }
-  return properties;
-}
-
-/**
- * Connect to a LanceDB database through a namespace.
- *
- * Unlike {@link connect}, which routes by URI scheme (local path vs.
- * `db://` cloud), `connectNamespace` always returns a namespace-backed
- * connection. The `implName` selects the namespace implementation:
- *
- * - `"dir"` — directory namespace, configured with {@link DirNamespaceConfig}.
- * - `"rest"` — remote REST catalog, configured with {@link RestNamespaceConfig}.
- * - Any other string — full module path for a custom implementation,
- *   configured with a free-form string-keyed `properties` map.
- *
- * @example Typed dir namespace
- * ```ts
- * const db = await connectNamespace("dir", { root: "/path/to/db" });
- * await db.createTable("users", [{ id: 1 }]);
- * ```
- *
- * @example Typed REST namespace with auth headers
- * ```ts
- * const db = await connectNamespace("rest", {
- *   uri: "https://catalog.example.com",
- *   headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
- * });
- * ```
- *
- * @example Custom implementation with raw properties
- * ```ts
- * const db = await connectNamespace("my.custom.Namespace", {
- *   endpoint: "...",
- * });
- * ```
- */
-export function connectNamespace(
-  implName: "dir",
-  config: DirNamespaceConfig,
-  options?: Partial<ConnectNamespaceOptions>,
-): Promise<Connection>;
-/**
- * Connect through the built-in REST namespace.
- *
- * Configured with {@link RestNamespaceConfig}. See the function-level
- * documentation above for the full surface, examples, and how this
- * relates to {@link connect}.
- *
- * @example
- * ```ts
- * const db = await connectNamespace("rest", {
- *   uri: "https://catalog.example.com",
- *   headers: { "x-api-key": process.env.CATALOG_KEY ?? "" },
- * });
- * ```
- */
-export function connectNamespace(
-  implName: "rest",
-  config: RestNamespaceConfig,
-  options?: Partial<ConnectNamespaceOptions>,
-): Promise<Connection>;
-/**
- * Connect through a custom namespace implementation by full module path,
- * configured with a free-form string-keyed `properties` map. Use the
- * typed overloads above for the built-in `"dir"` and `"rest"` impls.
- *
- * See the function-level documentation above for examples and how this
- * relates to {@link connect}.
- *
- * @example
- * ```ts
- * const db = await connectNamespace("my.custom.Namespace", {
- *   endpoint: "...",
- * });
- * ```
- */
-export function connectNamespace(
-  implName: string,
-  properties: Record<string, string>,
-  options?: Partial<ConnectNamespaceOptions>,
-): Promise<Connection>;
-export async function connectNamespace(
-  implName: string,
-  configOrProperties:
-    | DirNamespaceConfig
-    | RestNamespaceConfig
-    | Record<string, string>,
-  options?: Partial<ConnectNamespaceOptions>,
-): Promise<Connection> {
-  let properties: Record<string, string>;
-  if (implName === "dir") {
-    properties = dirConfigToProperties(
-      configOrProperties as DirNamespaceConfig,
-    );
-  } else if (implName === "rest") {
-    properties = restConfigToProperties(
-      configOrProperties as RestNamespaceConfig,
-    );
-  } else {
-    properties = configOrProperties as Record<string, string>;
-  }
-
-  const finalOptions: ConnectNamespaceOptions = (options ??
-    {}) as ConnectNamespaceOptions;
-  finalOptions.storageOptions = cleanseStorageOptions(
-    finalOptions.storageOptions,
-  );
-
-  const nativeConn = await LanceDbConnection.newWithNamespace(
-    implName,
-    properties,
-    finalOptions,
-  );
-  return new LocalConnection(nativeConn);
-}

nodejs/lancedb/merge.ts

@@ -87,41 +87,6 @@ export class MergeInsertBuilder {
       this.#schema,
     );
   }
-  /**
-   * Controls whether the merge uses the MemWAL LSM write path.
-   *
-   * By default (unset), a `mergeInsert` on a table with an LSM write spec is
-   * routed through Lance's MemWAL shard writer, and a table without one uses
-   * the standard path. Pass `false` to force the standard path even when a
-   * spec is set. Pass `true` to require a spec — `mergeInsert` rejects if none
-   * is installed.
-   *
-   * @param useLsmWrite - Whether to use the LSM write path.
-   */
-  useLsmWrite(useLsmWrite: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(
-      this.#native.useLsmWrite(useLsmWrite),
-      this.#schema,
-    );
-  }
-  /**
-   * Controls how an LSM merge checks that its input targets a single shard.
-   *
-   * When a table has an LSM write spec, every row in a `mergeInsert` call must
-   * route to the same shard. When `true` (the default), every row is inspected
-   * to verify this. When `false`, only the first row is inspected and the
-   * shard it routes to is used for the whole input — a faster path for callers
-   * that have already pre-sharded their input. Has no effect on tables without
-   * an LSM write spec.
-   *
-   * @param validateSingleShard - Whether to check every row routes to one shard. Defaults to `true`.
-   */
-  validateSingleShard(validateSingleShard: boolean): MergeInsertBuilder {
-    return new MergeInsertBuilder(
-      this.#native.validateSingleShard(validateSingleShard),
-      this.#schema,
-    );
-  }
   /**
    * Executes the merge insert operation
    *

nodejs/lancedb/query.ts

@@ -79,12 +79,6 @@ export interface QueryExecutionOptions {
   timeoutMs?: number;
 }
 
-export interface ColumnOrdering {
-  columnName: string;
-  ascending?: boolean;
-  nullsFirst?: boolean;
-}
-
 /**
  * Options that control the behavior of a full text search
  */
@@ -423,21 +417,6 @@ export class StandardQueryBase<
     return this;
   }
 
-  /**
-   * Sort the results by the specified column(s).
-   * @returns This query builder.
-   */
-  orderBy(ordering: ColumnOrdering | ColumnOrdering[]): this {
-    const orderings = Array.isArray(ordering) ? ordering : [ordering];
-    const normalized = orderings.map((o) => ({
-      columnName: o.columnName,
-      ascending: o.ascending ?? true,
-      nullsFirst: o.nullsFirst ?? false,
-    }));
-    this.doCall((inner) => inner.orderBy(normalized));
-    return this;
-  }
-
   /**
    * Skip searching un-indexed data. This can make search faster, but will miss
    * any data that is not yet indexed.

nodejs/lancedb/scannable.ts

@@ -1,274 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  Table as ArrowTable,
-  RecordBatch,
-  RecordBatchReader,
-  Schema,
-} from "apache-arrow";
-import {
-  fromRecordBatchToStreamBuffer,
-  fromTableToBuffer,
-  makeEmptyTable,
-} from "./arrow";
-import { NapiScannable } from "./native.js";
-
-export interface ScannableOptions {
-  /** Hint about the number of rows. Not validated against the stream. */
-  numRows?: number;
-  /**
-   * Whether the source can be scanned more than once. Defaults to `true` for
-   * `fromTable` / `fromFactory` and `false` for `fromIterable` /
-   * `fromRecordBatchReader`.
-   */
-  rescannable?: boolean;
-}
-
-/**
- * A data source that can be scanned as a stream of Arrow `RecordBatch`es.
- *
- * `Scannable` wraps the schema + optional row count + rescannable flag and
- * a callback that yields batches one at a time. It is passed to consumers
- * (e.g. `Table.add`, `createTable`, `mergeInsert` — follow-up work) that
- * need to pull data without materializing the full dataset in JS memory.
- *
- * Batches cross the JS↔Rust boundary as Arrow IPC Stream messages; a fresh
- * writer serializes each batch, and the Rust side decodes it with
- * `arrow_ipc::reader::StreamReader`. One batch is in flight at a time.
- */
-export class Scannable {
-  readonly schema: Schema;
-  readonly numRows: number | null;
-  readonly rescannable: boolean;
-
-  /** @hidden */
-  private readonly native: NapiScannable;
-
-  private constructor(
-    native: NapiScannable,
-    schema: Schema,
-    numRows: number | null,
-    rescannable: boolean,
-  ) {
-    this.native = native;
-    this.schema = schema;
-    this.numRows = numRows;
-    this.rescannable = rescannable;
-  }
-
-  /** @hidden Access the native handle for passing through to Rust consumers. */
-  get inner(): NapiScannable {
-    return this.native;
-  }
-
-  /**
-   * Build a Scannable from an explicit schema and a factory that returns a
-   * fresh batch iterator on each call.
-   *
-   * The factory is invoked once per scan. Each iterator yields
-   * `RecordBatch`es matching the declared schema. Use this when you need
-   * direct control over the pull loop — for example, to wrap a streaming
-   * source whose batches are produced lazily.
-   *
-   * @param schema - The Arrow schema of the produced batches.
-   * @param factory - Called at the start of each scan to produce a batch
-   *   iterator. Must be idempotent when `rescannable` is true.
-   * @param opts - Optional hints. `rescannable` defaults to `true`; set to
-   *   `false` if calling `factory()` twice would not reproduce the same data.
-   */
-  static async fromFactory(
-    schema: Schema,
-    factory: () =>
-      | AsyncIterable<RecordBatch>
-      | Iterable<RecordBatch>
-      | AsyncIterator<RecordBatch>
-      | Iterator<RecordBatch>,
-    opts: ScannableOptions = {},
-  ): Promise<Scannable> {
-    const numRows = opts.numRows ?? null;
-    if (numRows != null && !Number.isInteger(numRows)) {
-      throw new TypeError("numRows must be an integer");
-    }
-    const rescannable = opts.rescannable ?? true;
-
-    let iter: AsyncIterator<RecordBatch> | Iterator<RecordBatch> | null = null;
-    const getNextBatch = async (isStart: boolean): Promise<Buffer | null> => {
-      // `isStart` is true on the first pull of every new scan_as_stream.
-      // Drop any cached iterator so factory() is re-invoked for the next scan
-      if (isStart) {
-        iter = null;
-      }
-      if (iter === null) {
-        iter = normalizeIterator(factory());
-      }
-      const result = await iter.next();
-      if (result.done) {
-        iter = null;
-        return null;
-      }
-      return fromRecordBatchToStreamBuffer(result.value);
-    };
-
-    const schemaBuf = await fromTableToBuffer(makeEmptyTable(schema));
-    const native = new NapiScannable(
-      schemaBuf,
-      numRows,
-      rescannable,
-      getNextBatch,
-    );
-    return new Scannable(native, schema, numRows, rescannable);
-  }
-
-  /**
-   * Build a Scannable from an in-memory Arrow `Table`. Always rescannable;
-   * the table's batches are replayed on each scan.
-   *
-   * The table's row count is authoritative: `opts.numRows` must either be
-   * omitted or equal to `table.numRows`. `opts.rescannable` of `false` is
-   * rejected because in-memory Tables are always rescannable.
-   */
-  static async fromTable(
-    table: ArrowTable,
-    opts: ScannableOptions = {},
-  ): Promise<Scannable> {
-    if (opts.numRows != null && opts.numRows !== table.numRows) {
-      throw new TypeError(
-        `opts.numRows (${opts.numRows}) does not match table.numRows (${table.numRows}). ` +
-          `The table's row count is authoritative; omit numRows or pass the matching value.`,
-      );
-    }
-    if (opts.rescannable === false) {
-      throw new TypeError(
-        `fromTable does not accept rescannable: false. ` +
-          `In-memory Arrow Tables are always rescannable; omit the option or pass true.`,
-      );
-    }
-    return Scannable.fromFactory(table.schema, () => table.batches, {
-      numRows: table.numRows,
-      rescannable: true,
-    });
-  }
-
-  /**
-   * Build a Scannable from an iterable of `RecordBatch`es. `rescannable`
-   * defaults to `false`. Pass an explicit schema so the consumer can
-   * validate before any batch is pulled.
-   *
-   * `opts.rescannable: true` is honest for replayable iterables (Arrays,
-   * Sets, or custom iterables whose `[Symbol.iterator]()` returns a fresh
-   * iterator each call). It is rejected for one-shot iterables (generators,
-   * async generators, or already-an-iterator inputs) because their
-   * `[Symbol.iterator]()` returns the same exhausted object on the second
-   * scan. For replayable sources outside this shape, use
-   * `fromFactory(schema, () => createIter(), { rescannable: true })`.
-   *
-   * Note: when `opts.rescannable` is `true`, the constructor calls
-   * `[Symbol.iterator]()` once on the input to perform the structural check.
-   */
-  static async fromIterable(
-    schema: Schema,
-    iter: AsyncIterable<RecordBatch> | Iterable<RecordBatch>,
-    opts: ScannableOptions = {},
-  ): Promise<Scannable> {
-    if (opts.rescannable === true && isOneShotIterable(iter)) {
-      throw new TypeError(
-        `fromIterable: rescannable: true is not honest for one-shot iterables ` +
-          `(generators, async generators, or iterators where [Symbol.iterator]() ` +
-          `returns the same object). The source would be exhausted after the first scan. ` +
-          `Use fromFactory(schema, () => createIter(), { rescannable: true }) for sources ` +
-          `where each call mints a fresh iterator.`,
-      );
-    }
-    return Scannable.fromFactory(schema, () => iter, {
-      numRows: opts.numRows,
-      rescannable: opts.rescannable ?? false,
-    });
-  }
-
-  /**
-   * Build a Scannable from an Arrow `RecordBatchReader`. A reader can only
-   * be consumed once; `rescannable` defaults to `false`.
-   *
-   * The reader must already be opened (via `.open()`) so its `.schema` is
-   * populated. `RecordBatchReader.from(...)` returns an unopened reader.
-   *
-   * `opts.rescannable: true` is rejected because `RecordBatchReader` is a
-   * self-iterator (its `[Symbol.iterator]()` returns itself), and this
-   * constructor does not call `reader.reset()` between scans, so a second
-   * scan would always see an exhausted reader. For genuinely replayable
-   * sources, use
-   * `fromFactory(schema, () => openReader(), { rescannable: true })`,
-   * which mints a fresh reader on each scan.
-   */
-  static async fromRecordBatchReader(
-    reader: RecordBatchReader,
-    opts: ScannableOptions = {},
-  ): Promise<Scannable> {
-    if (opts.rescannable === true) {
-      throw new TypeError(
-        `fromRecordBatchReader does not accept rescannable: true. ` +
-          `RecordBatchReader is a self-iterator (its [Symbol.iterator]() ` +
-          `returns itself) and would be exhausted after the first scan. ` +
-          `Use fromFactory(schema, () => openReader(), { rescannable: true }) ` +
-          `for sources where each call mints a fresh reader.`,
-      );
-    }
-    return Scannable.fromFactory(reader.schema, () => reader, {
-      numRows: opts.numRows,
-      rescannable: false,
-    });
-  }
-}
-
-function normalizeIterator<T>(
-  source: AsyncIterable<T> | Iterable<T> | AsyncIterator<T> | Iterator<T>,
-): AsyncIterator<T> | Iterator<T> {
-  if (source == null) {
-    throw new TypeError("Scannable factory returned null/undefined");
-  }
-  if (
-    typeof (source as AsyncIterable<T>)[Symbol.asyncIterator] === "function"
-  ) {
-    return (source as AsyncIterable<T>)[Symbol.asyncIterator]();
-  }
-  if (typeof (source as Iterable<T>)[Symbol.iterator] === "function") {
-    return (source as Iterable<T>)[Symbol.iterator]();
-  }
-  // Already an iterator (has `.next`).
-  if (typeof (source as Iterator<T>).next === "function") {
-    return source as Iterator<T>;
-  }
-  throw new TypeError("Scannable factory returned a non-iterable value");
-}
-
-// A "self-iterator" returns the same object from `[Symbol.iterator]()` /
-// `[Symbol.asyncIterator]()`. Generators behave this way, so they exhaust
-// after one pass. Replayable iterables (Array, Set, custom) return a fresh
-// iterator each call. Detection mirrors `normalizeIterator`'s ordering so
-// classification matches scan-time behavior.
-function isOneShotIterable(
-  source: AsyncIterable<unknown> | Iterable<unknown>,
-): boolean {
-  // null/undefined are not one-shot in any meaningful sense; let
-  // `normalizeIterator` raise the actual error at scan time.
-  if (source == null) return false;
-  const ref = source as unknown;
-  if (
-    typeof (source as AsyncIterable<unknown>)[Symbol.asyncIterator] ===
-    "function"
-  ) {
-    const it = (source as AsyncIterable<unknown>)[
-      Symbol.asyncIterator
-    ]() as unknown;
-    return it === ref;
-  }
-  if (typeof (source as Iterable<unknown>)[Symbol.iterator] === "function") {
-    const it = (source as Iterable<unknown>)[Symbol.iterator]() as unknown;
-    return it === ref;
-  }
-  // Already-an-iterator (has `.next` but no `Symbol.iterator`) is by
-  // definition one-shot.
-  if (typeof (source as { next?: unknown }).next === "function") return true;
-  return false;
-}

nodejs/lancedb/table.ts

@@ -32,7 +32,6 @@ import {
   OptimizeStats,
   TableStatistics,
   Tags,
-  UpdateFieldMetadataResult,
   UpdateResult,
   Table as _NativeTable,
 } from "./native";
@@ -47,33 +46,6 @@ import { sanitizeType } from "./sanitize";
 import { IntoSql, toSQL } from "./util";
 export { IndexConfig } from "./native";
 
-/**
- * Progress snapshot for a write operation, delivered to the `progress`
- * callback passed to {@link Table.add}.
- */
-export interface WriteProgress {
-  /** Number of rows written so far. */
-  outputRows: number;
-  /** Number of bytes written so far. */
-  outputBytes: number;
-  /**
-   * Total rows expected, when the input source reports it.
-   *
-   * Always set on the final callback (the one with `done: true`), falling
-   * back to the actual number of rows written when the source could not
-   * report a row count up front.
-   */
-  totalRows?: number;
-  /** Wall-clock seconds since the write started. */
-  elapsedSeconds: number;
-  /** Number of parallel write tasks currently in flight. */
-  activeTasks: number;
-  /** Total number of parallel write tasks (the write parallelism). */
-  totalTasks: number;
-  /** `true` for the final callback; `false` otherwise. */
-  done: boolean;
-}
-
 /**
  * Options for adding data to a table.
  */
@@ -84,28 +56,6 @@ export interface AddDataOptions {
    * If "overwrite" then the new data will replace the existing data in the table.
    */
   mode: "append" | "overwrite";
-
-  /**
-   * Optional callback invoked periodically with write progress.
-   *
-   * The callback is fired once per batch written and once more with
-   * `done: true` when the write completes. Calls are dispatched
-   * asynchronously to the JS event loop and never block the write — a slow
-   * callback will queue events rather than back-pressure the writer.
-   *
-   * Errors thrown from the callback are logged with `console.warn` and
-   * swallowed — they do not abort the write.
-   *
-   * @example
-   * ```ts
-   * await table.add(data, {
-   *   progress: (p) => {
-   *     console.log(`${p.outputRows}/${p.totalRows ?? "?"} rows`);
-   *   },
-   * });
-   * ```
-   */
-  progress: (progress: WriteProgress) => void;
 }
 
 export interface UpdateOptions {
@@ -156,30 +106,6 @@ export interface Version {
   metadata: Record<string, string>;
 }
 
-/**
- * Specification selecting Lance's MemWAL LSM-style write path for
- * `mergeInsert`.
- *
- * `specType` is `"bucket"`, `"identity"`, or `"unsharded"`. For `"bucket"`,
- * `column` and `numBuckets` are required; for `"identity"`, `column` is
- * required and must be a deterministic function of the unenforced primary
- * key (every row with a given primary key must always produce the same
- * `column` value, or upserts of that key can land in different shards and a
- * stale version can win).
- */
-export interface LsmWriteSpec {
-  /** One of `"bucket"`, `"identity"`, or `"unsharded"`. */
-  specType: "bucket" | "identity" | "unsharded";
-  /** Bucket and identity variants: the sharding column. */
-  column?: string;
-  /** Bucket variant: the number of buckets, in `[1, 1024]`. */
-  numBuckets?: number;
-  /** Names of indexes the MemWAL should keep up to date during writes. */
-  maintainedIndexes?: string[];
-  /** Default `ShardWriter` configuration recorded in the MemWAL index. */
-  writerConfigDefaults?: Record<string, string>;
-}
-
 /**
  * A Table is a collection of Records in a LanceDB Database.
  *
@@ -359,25 +285,6 @@ export abstract class Table {
    */
   abstract prewarmIndex(name: string): Promise<void>;
 
-  /**
-   * Prewarm one or more columns of data in the table.
-   *
-   * @param columns The columns to prewarm. If undefined, all columns are prewarmed.
-   *
-   * This will load the column data into the page cache so that future queries that
-   * read those columns avoid the initial cold-start latency.  This call initiates
-   * prewarming and returns once the request is accepted; the warming itself may
-   * continue in the background.  Calling it on already-prewarmed columns is a
-   * no-op on the server.
-   *
-   * Prewarming is generally useful for columns used in filters or projections.
-   * Large columns (e.g. high-dimensional vectors or binary data) may not be
-   * practical to prewarm.
-   *
-   * This feature is currently only supported on remote tables.
-   */
-  abstract prewarmData(columns?: string[]): Promise<void>;
-
   /**
    * Waits for asynchronous indexing to complete on the table.
    *
@@ -509,18 +416,6 @@ export abstract class Table {
   abstract alterColumns(
     columnAlterations: ColumnAlteration[],
   ): Promise<AlterColumnsResult>;
-
-  /**
-   * Update per-field (column) metadata.
-   * @param {FieldMetadataUpdate[]} updates One or more per-field updates. Each
-   * update's metadata is merged into the field's existing metadata by default;
-   * a value of `null` deletes that key, and `replace: true` swaps the whole map.
-   * @returns {Promise<UpdateFieldMetadataResult>} resolves to the new table version.
-   */
-  abstract updateFieldMetadata(
-    updates: FieldMetadataUpdate[],
-  ): Promise<UpdateFieldMetadataResult>;
-
   /**
    * Drop one or more columns from the dataset
    *
@@ -535,64 +430,6 @@ export abstract class Table {
    * containing the new version number of the table after dropping the columns.
    */
   abstract dropColumns(columnNames: string[]): Promise<DropColumnsResult>;
-  /**
-   * Set the unenforced primary key for this table to a single column.
-   *
-   * "Unenforced" means LanceDB does not check uniqueness on writes; the
-   * column is recorded in the schema as the primary key for use by features
-   * such as `merge_insert`. Only single-column primary keys are supported,
-   * and the key cannot be changed once set.
-   * @param {string | string[]} columns The primary key column. A one-element
-   * array is also accepted; passing more than one column is rejected.
-   * @returns {Promise<void>}
-   */
-  abstract setUnenforcedPrimaryKey(columns: string | string[]): Promise<void>;
-  /**
-   * Install an {@link LsmWriteSpec} on this table, selecting Lance's MemWAL
-   * LSM-style write path for future `mergeInsert` calls.
-   *
-   * `LsmWriteSpec` chooses one of three sharding strategies via `specType`:
-   *
-   * - `"bucket"` — hash-bucket writes by the single-column unenforced primary
-   *   key (`column` and `numBuckets` required).
-   * - `"identity"` — shard by the raw value of a scalar `column`.
-   * - `"unsharded"` — route every write to a single shard.
-   *
-   * All variants require the table to have an unenforced primary key
-   * ({@link Table#setUnenforcedPrimaryKey}); bucket sharding additionally
-   * requires it to be the single column being bucketed.
-   * @param {LsmWriteSpec} spec The sharding spec to install.
-   * @returns {Promise<void>}
-   * @example
-   * ```ts
-   * await table.setUnenforcedPrimaryKey("id");
-   * await table.setLsmWriteSpec({
-   *   specType: "bucket",
-   *   column: "id",
-   *   numBuckets: 16,
-   *   maintainedIndexes: ["id_idx"],
-   * });
-   * ```
-   */
-  abstract setLsmWriteSpec(spec: LsmWriteSpec): Promise<void>;
-  /**
-   * Remove the {@link LsmWriteSpec} from this table, reverting to the standard
-   * `mergeInsert` write path.
-   *
-   * Errors if no spec is currently set.
-   * @returns {Promise<void>}
-   */
-  abstract unsetLsmWriteSpec(): Promise<void>;
-  /**
-   * Drain and close any cached MemWAL shard writers held for this table.
-   *
-   * When an {@link LsmWriteSpec} is installed, `mergeInsert` opens MemWAL
-   * shard writers and caches them for reuse across calls. This closes them,
-   * flushing pending data; writers reopen lazily on the next `mergeInsert`.
-   * It is a no-op when no writers are cached.
-   * @returns {Promise<void>}
-   */
-  abstract closeLsmWriters(): Promise<void>;
   /** Retrieve the version of the table */
 
   abstract version(): Promise<number>;
@@ -780,20 +617,7 @@ export class LocalTable extends Table {
     const schema = await this.schema();
 
     const buffer = await fromDataToBuffer(data, undefined, schema);
-    // Wrap the user callback so a thrown error doesn't surface as an
+    return await this.inner.add(buffer, mode);
-    // unhandled exception (the callback fires from a napi threadsafe
-    // function — exceptions there crash the process).
-    const userProgress = options?.progress;
-    const progress = userProgress
-      ? (p: WriteProgress) => {
-          try {
-            userProgress(p);
-          } catch (e) {
-            console.warn("Table.add progress callback threw:", e);
-          }
-        }
-      : undefined;
-    return await this.inner.add(buffer, mode, progress);
   }
 
   async update(
@@ -886,10 +710,6 @@ export class LocalTable extends Table {
     await this.inner.prewarmIndex(name);
   }
 
-  async prewarmData(columns?: string[]): Promise<void> {
-    await this.inner.prewarmData(columns);
-  }
-
   async waitForIndex(
     indexNames: string[],
     timeoutSeconds: number,
@@ -1050,33 +870,10 @@ export class LocalTable extends Table {
     return await this.inner.alterColumns(processedAlterations);
   }
 
-  async updateFieldMetadata(
-    updates: FieldMetadataUpdate[],
-  ): Promise<UpdateFieldMetadataResult> {
-    return await this.inner.updateFieldMetadata(updates);
-  }
-
   async dropColumns(columnNames: string[]): Promise<DropColumnsResult> {
     return await this.inner.dropColumns(columnNames);
   }
 
-  async setUnenforcedPrimaryKey(columns: string | string[]): Promise<void> {
-    const cols = typeof columns === "string" ? [columns] : columns;
-    return await this.inner.setUnenforcedPrimaryKey(cols);
-  }
-
-  async setLsmWriteSpec(spec: LsmWriteSpec): Promise<void> {
-    return await this.inner.setLsmWriteSpec(spec);
-  }
-
-  async unsetLsmWriteSpec(): Promise<void> {
-    return await this.inner.unsetLsmWriteSpec();
-  }
-
-  async closeLsmWriters(): Promise<void> {
-    return await this.inner.closeLsmWriters();
-  }
-
   async version(): Promise<number> {
     return await this.inner.version();
   }
@@ -1222,19 +1019,3 @@ export interface ColumnAlteration {
   /** Set the new nullability. Note that a nullable column cannot be made non-nullable. */
   nullable?: boolean;
 }
-
-/** A per-field metadata update, addressed by dot-path. */
-export interface FieldMetadataUpdate {
-  /**
-   * Dot-separated path to the field. For a top-level column this is just its
-   * name; for a nested field it's the path, e.g. "a.b.c".
-   */
-  path: string;
-  /**
-   * Metadata key/value pairs. Merged into the field's existing metadata by
-   * default; a value of `null` deletes that key.
-   */
-  metadata: Record<string, string | null>;
-  /** If true, replace the field's entire metadata map instead of merging. */
-  replace?: boolean;
-}

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.30.1-beta.0",
+	"version": "0.28.0-beta.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.30.1-beta.0",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.30.1-beta.0",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.30.1-beta.0",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.30.1-beta.0",
+	"version": "0.28.0-beta.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.30.1-beta.0",
+  "version": "0.28.0-beta.1",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.30.1-beta.0",
+	"version": "0.28.0-beta.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.30.1-beta.0",
+  "version": "0.28.0-beta.1",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -38,15 +38,15 @@
     "url": "https://github.com/lancedb/lancedb"
   },
   "devDependencies": {
-    "@aws-sdk/client-dynamodb": "3.1003.0",
+    "@aws-sdk/client-dynamodb": "^3.33.0",
-    "@aws-sdk/client-kms": "3.1003.0",
+    "@aws-sdk/client-kms": "^3.33.0",
-    "@aws-sdk/client-s3": "3.1003.0",
+    "@aws-sdk/client-s3": "^3.33.0",
     "@biomejs/biome": "^1.7.3",
     "@jest/globals": "^29.7.0",
-    "@napi-rs/cli": "3.5.1",
+    "@napi-rs/cli": "^3.5.1",
     "@types/axios": "^0.14.0",
     "@types/jest": "^29.1.2",
-    "@types/node": "22.7.4",
+    "@types/node": "^22.7.4",
     "@types/tmp": "^0.2.6",
     "apache-arrow-15": "npm:apache-arrow@15.0.0",
     "apache-arrow-16": "npm:apache-arrow@16.0.0",
@@ -57,9 +57,9 @@
     "shx": "^0.3.4",
     "tmp": "^0.2.3",
     "ts-jest": "^29.1.2",
-    "typedoc": "0.26.4",
+    "typedoc": "^0.26.4",
-    "typedoc-plugin-markdown": "4.2.1",
+    "typedoc-plugin-markdown": "^4.2.1",
-    "typescript": "5.5.4",
+    "typescript": "^5.5.4",
     "typescript-eslint": "^7.1.0"
   },
   "ava": {
@@ -68,16 +68,16 @@
   "engines": {
     "node": ">= 18"
   },
-  "packageManager": "pnpm@11.1.1",
   "cpu": ["x64", "arm64"],
   "os": ["darwin", "linux", "win32"],
   "scripts": {
     "artifacts": "napi artifacts",
     "build:debug": "napi build --platform --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir lancedb",
-    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/ && node -e \"require('fs').writeFileSync('dist/package.json', JSON.stringify({name:'@lancedb/lancedb',type:'commonjs'}))\"",
+    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
     "build:release": "napi build --platform --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js --output-dir dist",
-    "build": "pnpm build:debug && pnpm tsc",
+    "postbuild:release": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
-    "build-release": "pnpm build:release && pnpm tsc",
+    "build": "npm run build:debug && npm run tsc",
+    "build-release": "npm run build:release && npm run tsc",
     "tsc": "tsc -b",
     "posttsc": "shx cp lancedb/native.d.ts dist/native.d.ts",
     "lint-ci": "biome ci .",
@@ -87,7 +87,7 @@
     "lint-fix": "biome check --write . && biome format --write .",
     "prepublishOnly": "napi prepublish -t npm",
     "test": "jest --verbose",
-    "integration": "S3_TEST=1 pnpm test",
+    "integration": "S3_TEST=1 npm run test",
     "universal": "napi universalize",
     "version": "napi version"
   },
@@ -95,8 +95,8 @@
     "reflect-metadata": "^0.2.2"
   },
   "optionalDependencies": {
-    "@huggingface/transformers": "3.0.2",
+    "@huggingface/transformers": "^3.0.2",
-    "openai": "4.29.2"
+    "openai": "^4.29.2"
   },
   "peerDependencies": {
     "apache-arrow": ">=15.0.0 <=18.1.0"

nodejs/pnpm-workspace.yaml

@@ -1,18 +0,0 @@
-# Flat node_modules layout. The @napi-rs/cli build step fails to locate
-# the cdylib artifact under pnpm's isolated layout; the hoisted linker
-# mirrors npm's structure and unblocks the native build.
-nodeLinker: hoisted
-
-# Block resolution of versions less than 24h old (Shai-Hulud window).
-# This is the pnpm 11 default but pinned here so it's visible to
-# reviewers and survives a future pnpm major flipping the default.
-minimumReleaseAge: 1440
-
-# Fail install if a transitive dep tries to run an unapproved script.
-strictDepBuilds: true
-
-allowBuilds:
-  '@biomejs/biome': true
-  onnxruntime-node: true
-  protobufjs: true
-  sharp: true

nodejs/src/connection.rs

@@ -8,16 +8,12 @@ use lancedb::database::{CreateTableMode, Database};
 use napi::bindgen_prelude::*;
 use napi_derive::*;
 
-use crate::ConnectNamespaceOptions;
 use crate::ConnectionOptions;
 use crate::error::NapiErrorExt;
 use crate::header::JsHeaderProvider;
 use crate::table::Table;
-use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection, connect_namespace};
+use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection};
 
-use lance_namespace::models::{
-    CreateNamespaceRequest, DescribeNamespaceRequest, DropNamespaceRequest, ListNamespacesRequest,
-};
 use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
 
 #[napi]
@@ -25,29 +21,6 @@ pub struct Connection {
     inner: Option<LanceDBConnection>,
 }
 
-#[napi(object)]
-pub struct DescribeNamespaceResponse {
-    pub properties: Option<HashMap<String, String>>,
-}
-
-#[napi(object)]
-pub struct ListNamespacesResponse {
-    pub namespaces: Vec<String>,
-    pub page_token: Option<String>,
-}
-
-#[napi(object)]
-pub struct CreateNamespaceResponse {
-    pub properties: Option<HashMap<String, String>>,
-    pub transaction_id: Option<String>,
-}
-
-#[napi(object)]
-pub struct DropNamespaceResponse {
-    pub properties: Option<HashMap<String, String>>,
-    pub transaction_id: Option<Vec<String>>,
-}
-
 impl Connection {
     pub(crate) fn inner_new(inner: LanceDBConnection) -> Self {
         Self { inner: Some(inner) }
@@ -94,12 +67,6 @@ impl Connection {
                 builder = builder.storage_option(key, value);
             }
         }
-        if let Some(manifest_enabled) = options.manifest_enabled {
-            builder = builder.manifest_enabled(manifest_enabled);
-        }
-        if let Some(namespace_client_properties) = options.namespace_client_properties {
-            builder = builder.namespace_client_properties(namespace_client_properties);
-        }
 
         // Create client config, optionally with header provider
         let client_config = options.client_config.unwrap_or_default();
@@ -133,39 +100,6 @@ impl Connection {
         Ok(Self::inner_new(builder.execute().await.default_error()?))
     }
 
-    /// Create a new Connection instance backed by a namespace implementation.
-    #[napi(factory)]
-    pub async fn new_with_namespace(
-        impl_name: String,
-        properties: HashMap<String, String>,
-        options: ConnectNamespaceOptions,
-    ) -> napi::Result<Self> {
-        if impl_name.is_empty() {
-            return Err(napi::Error::from_reason(
-                "implName must be a non-empty string",
-            ));
-        }
-
-        let mut builder = connect_namespace(&impl_name, properties);
-        if let Some(interval) = options.read_consistency_interval {
-            builder =
-                builder.read_consistency_interval(std::time::Duration::from_secs_f64(interval));
-        }
-        if let Some(storage_options) = options.storage_options {
-            for (key, value) in storage_options {
-                builder = builder.storage_option(key, value);
-            }
-        }
-        if let Some(namespace_client_properties) = options.namespace_client_properties {
-            builder = builder.namespace_client_properties(namespace_client_properties);
-        }
-        if let Some(session) = options.session {
-            builder = builder.session(session.inner.clone());
-        }
-
-        Ok(Self::inner_new(builder.execute().await.default_error()?))
-    }
-
     #[napi]
     pub fn display(&self) -> napi::Result<String> {
         Ok(self.get_inner()?.to_string())
@@ -333,149 +267,4 @@ impl Connection {
         let ns = namespace_path.unwrap_or_default();
         self.get_inner()?.drop_all_tables(&ns).await.default_error()
     }
-
-    #[napi(catch_unwind)]
-    /// Describe a namespace and return its properties.
-    pub async fn describe_namespace(
-        &self,
-        namespace_path: Vec<String>,
-    ) -> napi::Result<DescribeNamespaceResponse> {
-        let req = DescribeNamespaceRequest {
-            id: Some(namespace_path),
-            ..Default::default()
-        };
-        let resp = self
-            .get_inner()?
-            .describe_namespace(req)
-            .await
-            .default_error()?;
-        Ok(DescribeNamespaceResponse {
-            properties: resp.properties,
-        })
-    }
-
-    #[napi(catch_unwind)]
-    /// List child namespaces under the given namespace path
-    pub async fn list_namespaces(
-        &self,
-        namespace_path: Option<Vec<String>>,
-        page_token: Option<String>,
-        limit: Option<u32>,
-    ) -> napi::Result<ListNamespacesResponse> {
-        let req = ListNamespacesRequest {
-            id: namespace_path,
-            page_token,
-            limit: limit.map(|l| l as i32),
-            ..Default::default()
-        };
-        let resp = self
-            .get_inner()?
-            .list_namespaces(req)
-            .await
-            .default_error()?;
-        Ok(ListNamespacesResponse {
-            namespaces: resp.namespaces,
-            page_token: resp.page_token,
-        })
-    }
-
-    #[napi(catch_unwind)]
-    /// Create a new namespace with optional properties.
-    pub async fn create_namespace(
-        &self,
-        namespace_path: Vec<String>,
-        mode: Option<String>,
-        properties: Option<HashMap<String, String>>,
-    ) -> napi::Result<CreateNamespaceResponse> {
-        let mode_str = mode
-            .map(|m| match m.to_lowercase().as_str() {
-                "create" => Ok("Create".to_string()),
-                "exist_ok" => Ok("ExistOk".to_string()),
-                "overwrite" => Ok("Overwrite".to_string()),
-                _ => Err(napi::Error::from_reason(format!(
-                    "Invalid mode '{}': expected one of 'create', 'exist_ok', 'overwrite'",
-                    m
-                ))),
-            })
-            .transpose()?;
-        let req = CreateNamespaceRequest {
-            id: Some(namespace_path),
-            mode: mode_str,
-            properties,
-            ..Default::default()
-        };
-        let resp = self
-            .get_inner()?
-            .create_namespace(req)
-            .await
-            .default_error()?;
-        Ok(CreateNamespaceResponse {
-            properties: resp.properties,
-            transaction_id: resp.transaction_id,
-        })
-    }
-
-    #[napi(catch_unwind)]
-    /// Drop a namespace.
-    pub async fn drop_namespace(
-        &self,
-        namespace_path: Vec<String>,
-        mode: Option<String>,
-        behavior: Option<String>,
-    ) -> napi::Result<DropNamespaceResponse> {
-        let mode_str = mode
-            .map(|m| match m.to_lowercase().as_str() {
-                "skip" => Ok("Skip".to_string()),
-                "fail" => Ok("Fail".to_string()),
-                _ => Err(napi::Error::from_reason(format!(
-                    "Invalid mode '{}': expected one of 'skip', 'fail'",
-                    m
-                ))),
-            })
-            .transpose()?;
-        let behavior_str = behavior
-            .map(|b| match b.to_lowercase().as_str() {
-                "restrict" => Ok("Restrict".to_string()),
-                "cascade" => Ok("Cascade".to_string()),
-                _ => Err(napi::Error::from_reason(format!(
-                    "Invalid behavior '{}': expected one of 'restrict', 'cascade'",
-                    b
-                ))),
-            })
-            .transpose()?;
-        let req = DropNamespaceRequest {
-            id: Some(namespace_path),
-            mode: mode_str,
-            behavior: behavior_str,
-            ..Default::default()
-        };
-        let resp = self
-            .get_inner()?
-            .drop_namespace(req)
-            .await
-            .default_error()?;
-        Ok(DropNamespaceResponse {
-            properties: resp.properties,
-            transaction_id: resp.transaction_id,
-        })
-    }
-
-    /// Rename a table. `current_namespace_path` and `new_namespace_path` default to
-    /// the root namespace when omitted; the caller is expected to either pass both
-    /// or pass neither.
-    #[napi(catch_unwind)]
-    pub async fn rename_table(
-        &self,
-        current_name: String,
-        new_name: String,
-        current_namespace_path: Option<Vec<String>>,
-        new_namespace_path: Option<Vec<String>>,
-    ) -> napi::Result<()> {
-        let cur_ns = current_namespace_path.unwrap_or_default();
-        let new_ns = new_namespace_path.unwrap_or_default();
-        self.get_inner()?
-            .rename_table(&current_name, &new_name, &cur_ns, &new_ns)
-            .await
-            .default_error()
-    }
 }