Bump version: 0.25.4-beta.3 → 0.26.0-beta.0

## Summary
- bump Lance workspace dependencies to v1.1.0-beta.1 via
ci/set_lance_version.py
- verified `cargo clippy --workspace --tests --all-features -- -D
warnings` and `cargo fmt --all` after the bump

Link: refs/tags/v1.1.0-beta.1

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.4-beta.0"
+current_version = "0.22.4-beta.3"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.cargo/config.toml

@@ -19,7 +19,7 @@ rustflags = [
     "-Wclippy::string_add_assign",
     "-Wclippy::string_add",
     "-Wclippy::string_lit_as_bytes",
-    "-Wclippy::string_to_string",
+    "-Wclippy::implicit_clone",
     "-Wclippy::use_self",
     "-Dclippy::cargo",
     "-Dclippy::dbg_macro",

.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://lancedb.github.io/lancedb/guides/tables/...
+      placeholder: ex. https://lancedb.com/docs/tables/...
     validations:
       required: false

.github/workflows/build_linux_wheel/action.yml

@@ -31,7 +31,7 @@ runs:
       with:
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         target: x86_64-unknown-linux-gnu
         manylinux: ${{ inputs.manylinux }}
         args: ${{ inputs.args }}
@@ -46,7 +46,7 @@ runs:
       with:
         command: build
         working-directory: python
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         target: aarch64-unknown-linux-gnu
         manylinux: ${{ inputs.manylinux }}
         args: ${{ inputs.args }}

.github/workflows/build_mac_wheel/action.yml

@@ -22,5 +22,5 @@ runs:
         command: build
         # TODO: pass through interpreter
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python

.github/workflows/build_windows_wheel/action.yml

@@ -26,7 +26,7 @@ runs:
       with:
         command: build
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        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:

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

@@ -98,3 +98,30 @@ jobs:
 
           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/docs.yml

@@ -24,7 +24,7 @@ env:
   # according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
   # CI builds are faster with incremental disabled.
   CARGO_INCREMENTAL: "0"
-  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lancedb/"
+  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
 jobs:
   # Single deploy job since we're just deploying
@@ -50,8 +50,8 @@ jobs:
       - name: Build Python
         working-directory: python
         run: |
-          python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .
-          python -m pip install --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
+          python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .
+          python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
       - name: Set up node
         uses: actions/setup-node@v3
         with:

.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/nodejs.yml

@@ -16,9 +16,6 @@ concurrency:
   cancel-in-progress: true
 
 env:
-  # Disable full debug symbol generation to speed up CI build and keep memory down
-  # "1" means line tables only, which is useful for panic tracebacks.
-  RUSTFLAGS: "-C debuginfo=1"
   RUST_BACKTRACE: "1"
 
 jobs:
@@ -43,18 +40,20 @@ jobs:
         node-version: 20
         cache: 'npm'
         cache-dependency-path: nodejs/package-lock.json
-    - uses: Swatinem/rust-cache@v2
+    - uses: actions-rust-lang/setup-rust-toolchain@v1
+      with:
+        components: rustfmt, clippy
     - name: Install dependencies
       run: |
         sudo apt update
         sudo apt install -y protobuf-compiler libssl-dev
-    - uses: actions-rust-lang/setup-rust-toolchain@v1
-      with:
-        components: rustfmt, clippy
-    - name: Lint
+    - uses: Swatinem/rust-cache@v2
+    - name: Format Rust
+      run: cargo fmt --all -- --check
+    - name: Lint Rust
+      run: cargo clippy --profile ci --all --all-features -- -D warnings
+    - name: Lint Typescript
       run: |
-        cargo fmt --all -- --check
-        cargo clippy --all --all-features -- -D warnings
         npm ci
         npm run lint-ci
     - name: Lint examples
@@ -90,7 +89,8 @@ jobs:
     - name: Build
       run: |
         npm ci
-        npm run build
+        npm run build:debug -- --profile ci
+        npm run tsc
     - name: Setup localstack
       working-directory: .
       run: docker compose up --detach --wait
@@ -147,7 +147,8 @@ jobs:
     - name: Build
       run: |
         npm ci
-        npm run build
+        npm run build:debug -- --profile ci
+        npm run tsc
     - name: Test
       run: |
         npm run test

.github/workflows/npm-publish.yml

@@ -97,12 +97,6 @@ jobs:
       fail-fast: false
       matrix:
         settings:
-          - target: x86_64-apple-darwin
-            host: macos-latest
-            features: ","
-            pre_build: |-
-                brew install protobuf
-                rustup target add x86_64-apple-darwin
           - target: aarch64-apple-darwin
             host: macos-latest
             features: fp16kernels

.github/workflows/pypi-publish.yml

@@ -11,7 +11,7 @@ on:
       - Cargo.toml # Change in dependency frequently breaks builds
 
 env:
-  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lancedb/"
+  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
 jobs:
   linux:
@@ -64,8 +64,6 @@ jobs:
     strategy:
       matrix:
         config:
-          - target: x86_64-apple-darwin
-            runner: macos-13
           - target: aarch64-apple-darwin
             runner: warp-macos-14-arm64-6x
     env:

.github/workflows/python.yml

@@ -18,7 +18,8 @@ env:
   # Color output for pytest is off by default.
   PYTEST_ADDOPTS: "--color=yes"
   FORCE_COLOR: "1"
-  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lancedb/"
+  PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
+  RUST_BACKTRACE: "1"
 
 jobs:
   lint:
@@ -78,7 +79,7 @@ jobs:
   doctest:
     name: "Doctest"
     timeout-minutes: 30
-    runs-on: "ubuntu-24.04"
+    runs-on: ubuntu-2404-8x-x64
     defaults:
       run:
         shell: bash
@@ -97,12 +98,9 @@ jobs:
         run: |
           sudo apt update
           sudo apt install -y protobuf-compiler
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
       - name: Install
         run: |
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
+          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
@@ -131,10 +129,9 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: 3.${{ matrix.python-minor-version }}
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
       - uses: ./.github/workflows/build_linux_wheel
+        with:
+          args: --profile ci
       - uses: ./.github/workflows/run_tests
         with:
           integration: true
@@ -146,16 +143,9 @@ jobs:
       - name: Delete wheels
         run: rm -rf target/wheels
   platform:
-    name: "Mac: ${{ matrix.config.name }}"
+    name: "Mac"
     timeout-minutes: 30
-    strategy:
-      matrix:
-        config:
-          - name: x86
-            runner: macos-13
-          - name: Arm
-            runner: macos-14
-    runs-on: "${{ matrix.config.runner }}"
+    runs-on: macos-14
     defaults:
       run:
         shell: bash
@@ -169,10 +159,9 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
       - uses: ./.github/workflows/build_mac_wheel
+        with:
+          args: --profile ci
       - uses: ./.github/workflows/run_tests
       # Make sure wheels are not included in the Rust cache
       - name: Delete wheels
@@ -199,10 +188,9 @@ jobs:
         uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
       - uses: ./.github/workflows/build_windows_wheel
+        with:
+          args: --profile ci
       - uses: ./.github/workflows/run_tests
       # Make sure wheels are not included in the Rust cache
       - name: Delete wheels
@@ -231,7 +219,7 @@ jobs:
         run: |
           pip install "pydantic<2"
           pip install pyarrow==16
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
+          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/run_tests/action.yml

@@ -15,7 +15,7 @@ runs:
     - name: Install lancedb
       shell: bash
       run: |
-        pip3 install --extra-index-url https://pypi.fury.io/lancedb/ $(ls target/wheels/lancedb-*.whl)[tests,dev]
+        pip3 install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ $(ls target/wheels/lancedb-*.whl)[tests,dev]
     - name: Setup localstack for integration tests
       if: ${{ inputs.integration == 'true' }}
       shell: bash

.github/workflows/rust.yml

@@ -18,11 +18,7 @@ env:
   # This env var is used by Swatinem/rust-cache@v2 for the cache
   # key, so we set it to make sure it is always consistent.
   CARGO_TERM_COLOR: always
-  # Disable full debug symbol generation to speed up CI build and keep memory down
-  # "1" means line tables only, which is useful for panic tracebacks.
-  RUSTFLAGS: "-C debuginfo=1"
   RUST_BACKTRACE: "1"
-  CARGO_INCREMENTAL: 0
 
 jobs:
   lint:
@@ -44,8 +40,6 @@ jobs:
         with:
           components: rustfmt, clippy
       - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: rust
       - name: Install dependencies
         run: |
           sudo apt update
@@ -53,7 +47,7 @@ jobs:
       - name: Run format
         run: cargo fmt --all -- --check
       - name: Run clippy
-        run: cargo clippy --workspace --tests --all-features -- -D warnings
+        run: cargo clippy --profile ci --workspace --tests --all-features -- -D warnings
 
   build-no-lock:
     runs-on: ubuntu-24.04
@@ -80,7 +74,7 @@ jobs:
           sudo apt install -y protobuf-compiler libssl-dev
       - name: Build all
         run: |
-          cargo build --benches --all-features --tests
+          cargo build --profile ci --benches --all-features --tests
 
   linux:
     timeout-minutes: 30
@@ -103,14 +97,8 @@ jobs:
           fetch-depth: 0
           lfs: true
       - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: rust
       - name: Install dependencies
-        run: |
-          # This shaves 2 minutes off this step in CI. This doesn't seem to be
-          # necessary in standard runners, but it is in the 4x runners.
-          sudo rm /var/lib/man-db/auto-update
-          sudo apt install -y protobuf-compiler libssl-dev
+        run: sudo apt install -y protobuf-compiler libssl-dev
       - uses: rui314/setup-mold@v1
       - name: Make Swap
         run: |
@@ -119,22 +107,22 @@ jobs:
           sudo mkswap /swapfile
           sudo swapon /swapfile
       - name: Build
-        run: cargo build --all-features --tests --locked --examples
+        run: cargo build --profile ci --all-features --tests --locked --examples
       - name: Run feature tests
-        run: make -C ./lancedb feature-tests
+        run: CARGO_ARGS="--profile ci" make -C ./lancedb feature-tests
       - name: Run examples
-        run: cargo run --example simple --locked
+        run: cargo run  --profile ci --example simple --locked
       - name: Run remote tests
         # Running this requires access to secrets, so skip if this is
         # a PR from a fork.
         if: github.event_name != 'pull_request' || !github.event.pull_request.head.repo.fork
-        run: make -C ./lancedb remote-tests
+        run: CARGO_ARGS="--profile ci" make -C ./lancedb remote-tests
 
   macos:
     timeout-minutes: 30
     strategy:
       matrix:
-        mac-runner: ["macos-13", "macos-14"]
+        mac-runner: ["macos-14", "macos-15"]
     runs-on: "${{ matrix.mac-runner }}"
     defaults:
       run:
@@ -148,8 +136,6 @@ jobs:
       - name: CPU features
         run: sysctl -a | grep cpu
       - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: rust
       - name: Install dependencies
         run: brew install protobuf
       - name: Run tests
@@ -159,7 +145,7 @@ jobs:
           ALL_FEATURES=`cargo metadata --format-version=1 --no-deps \
             | jq -r '.packages[] | .features | keys | .[]' \
             | grep -v s3-test | sort | uniq | paste -s -d "," -`
-          cargo test --features $ALL_FEATURES --locked
+          cargo test --profile ci --features $ALL_FEATURES --locked
 
   windows:
     runs-on: windows-2022
@@ -173,22 +159,21 @@ jobs:
         working-directory: rust/lancedb
     steps:
       - uses: actions/checkout@v4
+      - name: Set target
+        run: rustup target add ${{ matrix.target }}
       - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: rust
       - name: Install Protoc v21.12
         run: choco install --no-progress protoc
       - name: Build
         run: |
-          rustup target add ${{ matrix.target }}
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo build --features remote --tests --locked --target ${{ matrix.target }}
+          cargo build --profile ci --features remote --tests --locked --target ${{ matrix.target }}
       - name: Run tests
         # Can only run tests when target matches host
         if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
         run: |
           $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo test --features remote --locked
+          cargo test --profile ci --features remote --locked
 
   msrv:
     # Check the minimum supported Rust version
@@ -213,6 +198,7 @@ jobs:
         uses: dtolnay/rust-toolchain@master
         with:
           toolchain: ${{ matrix.msrv }}
+      - uses: Swatinem/rust-cache@v2
       - name: Downgrade  dependencies
         # These packages have newer requirements for MSRV
         run: |
@@ -226,4 +212,4 @@ jobs:
           cargo update -p aws-sdk-sts --precise 1.51.0
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
-        run: cargo check --workspace --tests --benches --all-features
+        run: cargo check --profile ci --workspace --tests --benches --all-features

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=1.0.0-beta.2", default-features = false, "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-core = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-datagen = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-file = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-io = { "version" = "=1.0.0-beta.2", default-features = false, "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-index = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-linalg = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-namespace = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-namespace-impls = { "version" = "=1.0.0-beta.2", "features" = ["dir-aws", "dir-gcp", "dir-azure", "dir-oss", "rest"], "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-table = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-testing = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-datafusion = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-encoding = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-lance-arrow = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+lance = { "version" = "=1.1.0-beta.1", default-features = false, "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=1.1.0-beta.1", default-features = false, "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=1.1.0-beta.1", default-features = false, "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=1.1.0-beta.1", "tag" = "v1.1.0-beta.1", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "56.2", optional = false }
@@ -63,3 +63,17 @@ regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"
+
+[profile.ci]
+debug = "line-tables-only"
+inherits = "dev"
+incremental = false
+
+# This rule applies to every package except workspace members (dependencies
+# such as `arrow` and `tokio`). It disables debug info and related features on
+# dependencies so their binaries stay smaller, improving cache reuse.
+[profile.ci.package."*"]
+debug = false
+debug-assertions = false
+strip = "debuginfo"
+incremental = false

README.md

@@ -15,7 +15,7 @@
 
 # **The Multimodal AI Lakehouse**
 
-[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://lancedb.github.io/lancedb/) ✦ [**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.** 
 

ci/check_lance_release.py

@@ -0,0 +1,208 @@
+#!/usr/bin/env python3
+"""Determine whether a newer Lance tag exists and expose results for CI."""
+from __future__ import annotations
+
+import argparse
+import json
+import os
+import re
+import subprocess
+import sys
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Iterable, List, Sequence, Tuple, Union
+
+try:  # Python >=3.11
+    import tomllib  # type: ignore
+except ModuleNotFoundError:  # pragma: no cover - fallback for older Python
+    import tomli as tomllib  # type: ignore
+
+LANCE_REPO = "lance-format/lance"
+
+SEMVER_RE = re.compile(
+    r"^\s*(?P<major>0|[1-9]\d*)\.(?P<minor>0|[1-9]\d*)\.(?P<patch>0|[1-9]\d*)"
+    r"(?:-(?P<prerelease>[0-9A-Za-z.-]+))?"
+    r"(?:\+[0-9A-Za-z.-]+)?\s*$"
+)
+
+
+@dataclass(frozen=True)
+class SemVer:
+    major: int
+    minor: int
+    patch: int
+    prerelease: Tuple[Union[int, str], ...]
+
+    def __lt__(self, other: "SemVer") -> bool:  # pragma: no cover - simple comparison
+        if (self.major, self.minor, self.patch) != (other.major, other.minor, other.patch):
+            return (self.major, self.minor, self.patch) < (other.major, other.minor, other.patch)
+        if self.prerelease == other.prerelease:
+            return False
+        if not self.prerelease:
+            return False  # release > anything else
+        if not other.prerelease:
+            return True
+        for left, right in zip(self.prerelease, other.prerelease):
+            if left == right:
+                continue
+            if isinstance(left, int) and isinstance(right, int):
+                return left < right
+            if isinstance(left, int):
+                return True
+            if isinstance(right, int):
+                return False
+            return str(left) < str(right)
+        return len(self.prerelease) < len(other.prerelease)
+
+    def __eq__(self, other: object) -> bool:  # pragma: no cover - trivial
+        if not isinstance(other, SemVer):
+            return NotImplemented
+        return (
+            self.major == other.major
+            and self.minor == other.minor
+            and self.patch == other.patch
+            and self.prerelease == other.prerelease
+        )
+
+
+def parse_semver(raw: str) -> SemVer:
+    match = SEMVER_RE.match(raw)
+    if not match:
+        raise ValueError(f"Unsupported version format: {raw}")
+    prerelease = match.group("prerelease")
+    parts: Tuple[Union[int, str], ...] = ()
+    if prerelease:
+        parsed: List[Union[int, str]] = []
+        for piece in prerelease.split("."):
+            if piece.isdigit():
+                parsed.append(int(piece))
+            else:
+                parsed.append(piece)
+        parts = tuple(parsed)
+    return SemVer(
+        major=int(match.group("major")),
+        minor=int(match.group("minor")),
+        patch=int(match.group("patch")),
+        prerelease=parts,
+    )
+
+
+@dataclass
+class TagInfo:
+    tag: str  # e.g. v1.0.0-beta.2
+    version: str  # e.g. 1.0.0-beta.2
+    semver: SemVer
+
+
+def run_command(cmd: Sequence[str]) -> str:
+    result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+    if result.returncode != 0:
+        raise RuntimeError(
+            f"Command {' '.join(cmd)} failed with {result.returncode}: {result.stderr.strip()}"
+        )
+    return result.stdout.strip()
+
+
+def fetch_remote_tags() -> List[TagInfo]:
+    output = run_command(
+        [
+            "gh",
+            "api",
+            "-X",
+            "GET",
+            f"repos/{LANCE_REPO}/git/refs/tags",
+            "--paginate",
+            "--jq",
+            ".[].ref",
+        ]
+    )
+    tags: List[TagInfo] = []
+    for line in output.splitlines():
+        ref = line.strip()
+        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 tags could be parsed from GitHub API output")
+    return tags
+
+
+def read_current_version(repo_root: Path) -> str:
+    cargo_path = repo_root / "Cargo.toml"
+    with cargo_path.open("rb") as fh:
+        data = tomllib.load(fh)
+    try:
+        deps = data["workspace"]["dependencies"]
+        entry = deps["lance"]
+    except KeyError as exc:  # pragma: no cover - configuration guard
+        raise RuntimeError("Failed to locate workspace.dependencies.lance in Cargo.toml") from exc
+
+    if isinstance(entry, str):
+        raw_version = entry
+    elif isinstance(entry, dict):
+        raw_version = entry.get("version", "")
+    else:  # pragma: no cover - defensive
+        raise RuntimeError("Unexpected lance dependency format")
+
+    raw_version = raw_version.strip()
+    if not raw_version:
+        raise RuntimeError("lance dependency does not declare a version")
+    return raw_version.lstrip("=")
+
+
+def determine_latest_tag(tags: Iterable[TagInfo]) -> TagInfo:
+    return max(tags, key=lambda tag: tag.semver)
+
+
+def write_outputs(args: argparse.Namespace, payload: dict) -> None:
+    target = getattr(args, "github_output", None)
+    if not target:
+        return
+    with open(target, "a", encoding="utf-8") as handle:
+        for key, value in payload.items():
+            handle.write(f"{key}={value}\n")
+
+
+def main(argv: Sequence[str] | None = None) -> int:
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        "--repo-root",
+        default=Path(__file__).resolve().parents[1],
+        type=Path,
+        help="Path to the lancedb repository root",
+    )
+    parser.add_argument(
+        "--github-output",
+        default=os.environ.get("GITHUB_OUTPUT"),
+        help="Optional file path for writing GitHub Action outputs",
+    )
+    args = parser.parse_args(argv)
+
+    repo_root = Path(args.repo_root)
+    current_version = read_current_version(repo_root)
+    current_semver = parse_semver(current_version)
+
+    tags = fetch_remote_tags()
+    latest = determine_latest_tag(tags)
+    needs_update = latest.semver > current_semver
+
+    payload = {
+        "current_version": current_version,
+        "current_tag": f"v{current_version}",
+        "latest_version": latest.version,
+        "latest_tag": latest.tag,
+        "needs_update": "true" if needs_update else "false",
+    }
+
+    print(json.dumps(payload))
+    write_outputs(args, payload)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

ci/set_lance_version.py

@@ -3,6 +3,8 @@ import re
 import sys
 import json
 
+LANCE_GIT_URL = "https://github.com/lance-format/lance.git"
+
 
 def run_command(command: str) -> str:
     """
@@ -29,7 +31,7 @@ def get_latest_stable_version() -> str:
 
 def get_latest_preview_version() -> str:
     lance_tags = run_command(
-        "git ls-remote --tags https://github.com/lancedb/lance.git | grep 'refs/tags/v[0-9beta.-]\\+$'"
+        f"git ls-remote --tags {LANCE_GIT_URL} | grep 'refs/tags/v[0-9beta.-]\\+$'"
     ).splitlines()
     lance_tags = (
         tag.split("refs/tags/")[1]
@@ -176,8 +178,8 @@ def set_stable_version(version: str):
 def set_preview_version(version: str):
     """
     Sets lines to
-    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"], "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
-    lance-io = { "version" = "=0.29.0", default-features = false, "tag" = "v0.29.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+    lance = { "version" = "=0.29.0", default-features = false, "features" = ["dynamodb"], "tag" = "v0.29.0-beta.2", "git" = LANCE_GIT_URL }
+    lance-io = { "version" = "=0.29.0", default-features = false, "tag" = "v0.29.0-beta.2", "git" = LANCE_GIT_URL }
     ...
     """
 
@@ -194,7 +196,7 @@ def set_preview_version(version: str):
             config["features"] = features
 
         config["tag"] = f"v{version}"
-        config["git"] = "https://github.com/lancedb/lance.git"
+        config["git"] = LANCE_GIT_URL
 
         return dict_to_toml_line(package_name, config)
 

docs/README.md

@@ -1,8 +1,8 @@
 # LanceDB Documentation
 
-LanceDB docs are deployed to https://lancedb.github.io/lancedb/.
+LanceDB docs are available at [lancedb.com/docs](https://lancedb.com/docs).
 
-Docs is built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
+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
 unreleased features.
 

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://lancedb.github.io/lancedb/basic/) contains a more complete example.
+The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
 
 ## Development
 

docs/src/js/_media/CONTRIBUTING.md

@@ -1,7 +1,7 @@
 # Contributing to LanceDB Typescript
 
 This document outlines the process for contributing to LanceDB Typescript.
-For general contribution guidelines, see [CONTRIBUTING.md](../../../../CONTRIBUTING.md).
+For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).
 
 ## Project layout
 

docs/src/js/classes/PermutationBuilder.md

@@ -147,7 +147,7 @@ A new PermutationBuilder instance
 #### Example
 
 ```ts
-builder.splitCalculated("user_id % 3");
+builder.splitCalculated({ calculation: "user_id % 3" });
 ```
 
 ***

docs/src/js/interfaces/ConnectionOptions.md

@@ -89,4 +89,4 @@ optional storageOptions: Record<string, string>;
 
 (For LanceDB OSS only): configuration for object storage.
 
-The available options are described at https://lancedb.github.io/lancedb/guides/storage/
+The available options are described at https://lancedb.com/docs/storage/

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://lancedb.github.io/lancedb/guides/storage/
+The available options are described at https://lancedb.com/docs/storage/

docs/src/js/interfaces/MergeResult.md

@@ -8,6 +8,14 @@
 
 ## Properties
 
+### numAttempts
+
+```ts
+numAttempts: number;
+```
+
+***
+
 ### numDeletedRows
 
 ```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://lancedb.github.io/lancedb/guides/storage/
+The available options are described at https://lancedb.com/docs/storage/

docs/src/python/python.md

@@ -30,6 +30,12 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ::: lancedb.table.Table
 
+::: lancedb.table.FragmentStatistics
+
+::: lancedb.table.FragmentSummaryStats
+
+::: lancedb.table.Tags
+
 ## Querying (Synchronous)
 
 ::: lancedb.query.Query
@@ -58,6 +64,14 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ::: lancedb.embeddings.open_clip.OpenClipEmbeddings
 
+## Remote configuration
+
+::: lancedb.remote.ClientConfig
+
+::: lancedb.remote.TimeoutConfig
+
+::: lancedb.remote.RetryConfig
+
 ## Context
 
 ::: lancedb.context.contextualize
@@ -115,6 +129,8 @@ Table hold your actual data as a collection of records / rows.
 
 ::: lancedb.table.AsyncTable
 
+::: lancedb.table.AsyncTags
+
 ## Indices (Asynchronous)
 
 Indices can be created on a table to speed up queries. This section
@@ -136,6 +152,8 @@ lists the indices that LanceDb supports.
 
 ::: lancedb.index.IvfFlat
 
+::: lancedb.table.IndexStatistics
+
 ## Querying (Asynchronous)
 
 Queries allow you to return data from your database. Basic queries can be

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.4-beta.0</version>
+        <version>0.22.4-beta.3</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/lance-namespace/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.4-beta.0</version>
+        <version>0.22.4-beta.3</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.22.4-beta.0</version>
+    <version>0.22.4-beta.3</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.22.4-beta.0"
+version = "0.22.4-beta.3"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

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://lancedb.github.io/lancedb/basic/) contains a more complete example.
+The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
 
 ## Development
 

nodejs/lancedb/connection.ts

@@ -42,7 +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://lancedb.github.io/lancedb/guides/storage/
+   * The available options are described at https://lancedb.com/docs/storage/
    */
   storageOptions?: Record<string, string>;
 
@@ -78,7 +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://lancedb.github.io/lancedb/guides/storage/
+   * The available options are described at https://lancedb.com/docs/storage/
    */
   storageOptions?: Record<string, string>;
   /**

nodejs/lancedb/permutation.ts

@@ -118,7 +118,7 @@ export class PermutationBuilder {
    * @returns A new PermutationBuilder instance
    * @example
    * ```ts
-   * builder.splitCalculated("user_id % 3");
+   * builder.splitCalculated({ calculation: "user_id % 3" });
    * ```
    */
   splitCalculated(options: SplitCalculatedOptions): PermutationBuilder {

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

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

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.22.4-beta.0",
+  "version": "0.22.4-beta.3",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.22.4-beta.0",
+	"version": "0.22.4-beta.3",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.22.4-beta.0",
+  "version": "0.22.4-beta.3",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.22.4-beta.0",
+      "version": "0.22.4-beta.3",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.22.4-beta.0",
+  "version": "0.22.4-beta.3",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -73,8 +73,10 @@
   "scripts": {
     "artifacts": "napi artifacts",
     "build:debug": "napi build --platform --no-const-enum --dts ../lancedb/native.d.ts --js ../lancedb/native.js lancedb",
+    "postbuild:debug": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
     "build:release": "napi build --platform --no-const-enum --release --dts ../lancedb/native.d.ts --js ../lancedb/native.js dist/",
-    "build": "npm run build:debug && npm run tsc && shx cp lancedb/*.node dist/",
+    "postbuild:release": "shx mkdir -p dist && shx cp lancedb/*.node dist/",
+    "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",

nodejs/src/lib.rs

@@ -35,7 +35,7 @@ pub struct ConnectionOptions {
     pub read_consistency_interval: Option<f64>,
     /// (For LanceDB OSS only): configuration for object storage.
     ///
-    /// The available options are described at https://lancedb.github.io/lancedb/guides/storage/
+    /// The available options are described at https://lancedb.com/docs/storage/
     pub storage_options: Option<HashMap<String, String>>,
     /// (For LanceDB OSS only): the session to use for this connection. Holds
     /// shared caches and other session-specific state.

nodejs/src/table.rs

@@ -740,6 +740,7 @@ pub struct MergeResult {
     pub num_inserted_rows: i64,
     pub num_updated_rows: i64,
     pub num_deleted_rows: i64,
+    pub num_attempts: i64,
 }
 
 impl From<lancedb::table::MergeResult> for MergeResult {
@@ -749,6 +750,7 @@ impl From<lancedb::table::MergeResult> for MergeResult {
             num_inserted_rows: value.num_inserted_rows as i64,
             num_updated_rows: value.num_updated_rows as i64,
             num_deleted_rows: value.num_deleted_rows as i64,
+            num_attempts: value.num_attempts as i64,
         }
     }
 }

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.25.4-beta.0"
+current_version = "0.26.0-beta.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.25.4-beta.0"
+version = "0.26.0-beta.0"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -18,6 +18,7 @@ arrow = { version = "56.2", features = ["pyarrow"] }
 async-trait = "0.1"
 lancedb = { path = "../rust/lancedb", default-features = false }
 lance-core.workspace = true
+lance-namespace.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
 pyo3 = { version = "0.25", features = ["extension-module", "abi3-py39"] }

python/Makefile

@@ -1,11 +1,11 @@
-PIP_EXTRA_INDEX_URL ?= https://pypi.fury.io/lancedb/
+PIP_EXTRA_INDEX_URL ?= https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/
 
 help:		## Show this help.
 	@sed -ne '/@sed/!s/## //p' $(MAKEFILE_LIST)
 
 .PHONY: develop
 develop:	## Install the package in development mode.
-	PIP_EXTRA_INDEX_URL=$(PIP_EXTRA_INDEX_URL) maturin develop --extras tests,dev,embeddings
+	PIP_EXTRA_INDEX_URL="$(PIP_EXTRA_INDEX_URL)" maturin develop --extras tests,dev,embeddings
 
 .PHONY: format
 format:		## Format the code.

python/pyproject.toml

@@ -10,7 +10,7 @@ dependencies = [
     "pyarrow>=16",
     "pydantic>=1.10",
     "tqdm>=4.27.0",
-    "lance-namespace>=0.0.21"
+    "lance-namespace>=0.2.1"
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
@@ -45,7 +45,7 @@ repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
 pylance = [
-    "pylance>=0.25",
+    "pylance>=1.0.0b14",
 ]
 tests = [
     "aiohttp",
@@ -59,7 +59,7 @@ tests = [
     "polars>=0.19, <=1.3.0",
     "tantivy",
     "pyarrow-stubs",
-    "pylance>=1.0.0b2",
+    "pylance>=1.0.0b14",
     "requests",
     "datafusion",
 ]

python/python/lancedb/__init__.py

@@ -20,7 +20,12 @@ from .remote.db import RemoteDBConnection
 from .schema import vector
 from .table import AsyncTable, Table
 from ._lancedb import Session
-from .namespace import connect_namespace, LanceNamespaceDBConnection
+from .namespace import (
+    connect_namespace,
+    connect_namespace_async,
+    LanceNamespaceDBConnection,
+    AsyncLanceNamespaceDBConnection,
+)
 
 
 def connect(
@@ -36,7 +41,7 @@ def connect(
     session: Optional[Session] = None,
     **kwargs: Any,
 ) -> DBConnection:
-    """Connect to a LanceDB database. YAY!
+    """Connect to a LanceDB database.
 
     Parameters
     ----------
@@ -67,7 +72,7 @@ def connect(
         default configuration is used.
     storage_options: dict, optional
         Additional options for the storage backend. See available options at
-        <https://lancedb.github.io/lancedb/guides/storage/>
+        <https://lancedb.com/docs/storage/>
     session: Session, optional
         (For LanceDB OSS only)
         A session to use for this connection. Sessions allow you to configure
@@ -169,7 +174,7 @@ async def connect_async(
         default configuration is used.
     storage_options: dict, optional
         Additional options for the storage backend. See available options at
-        <https://lancedb.github.io/lancedb/guides/storage/>
+        <https://lancedb.com/docs/storage/>
     session: Session, optional
         (For LanceDB OSS only)
         A session to use for this connection. Sessions allow you to configure
@@ -224,7 +229,9 @@ __all__ = [
     "connect",
     "connect_async",
     "connect_namespace",
+    "connect_namespace_async",
     "AsyncConnection",
+    "AsyncLanceNamespaceDBConnection",
     "AsyncTable",
     "URI",
     "sanitize_uri",

python/python/lancedb/_lancedb.pyi

@@ -3,10 +3,30 @@ from typing import Dict, List, Optional, Tuple, Any, TypedDict, Union, Literal
 
 import pyarrow as pa
 
-from .index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq, FTS
+from .index import (
+    BTree,
+    IvfFlat,
+    IvfPq,
+    IvfSq,
+    Bitmap,
+    LabelList,
+    HnswPq,
+    HnswSq,
+    FTS,
+)
 from .io import StorageOptionsProvider
+from lance_namespace import (
+    ListNamespacesResponse,
+    CreateNamespaceResponse,
+    DropNamespaceResponse,
+    DescribeNamespaceResponse,
+    ListTablesResponse,
+)
 from .remote import ClientConfig
 
+IvfHnswPq: type[HnswPq] = HnswPq
+IvfHnswSq: type[HnswSq] = HnswSq
+
 class Session:
     def __init__(
         self,
@@ -26,24 +46,44 @@ class Connection(object):
     async def close(self): ...
     async def list_namespaces(
         self,
-        namespace: List[str],
-        page_token: Optional[str],
-        limit: Optional[int],
-    ) -> List[str]: ...
-    async def create_namespace(self, namespace: List[str]) -> None: ...
-    async def drop_namespace(self, namespace: List[str]) -> None: ...
-    async def table_names(
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse: ...
+    async def create_namespace(
         self,
         namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse: ...
+    async def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse: ...
+    async def describe_namespace(
+        self,
+        namespace: List[str],
+    ) -> DescribeNamespaceResponse: ...
+    async def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse: ...
+    async def table_names(
+        self,
+        namespace: Optional[List[str]],
         start_after: Optional[str],
         limit: Optional[int],
-    ) -> list[str]: ...
+    ) -> list[str]: ...  # Deprecated: Use list_tables instead
     async def create_table(
         self,
         name: str,
         mode: str,
         data: pa.RecordBatchReader,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         location: Optional[str] = None,
@@ -53,7 +93,7 @@ class Connection(object):
         name: str,
         mode: str,
         schema: pa.Schema,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         location: Optional[str] = None,
@@ -61,7 +101,7 @@ class Connection(object):
     async def open_table(
         self,
         name: str,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         index_cache_size: Optional[int] = None,
@@ -71,7 +111,7 @@ class Connection(object):
         self,
         target_table_name: str,
         source_uri: str,
-        target_namespace: List[str] = [],
+        target_namespace: Optional[List[str]] = None,
         source_version: Optional[int] = None,
         source_tag: Optional[str] = None,
         is_shallow: bool = True,
@@ -80,11 +120,13 @@ class Connection(object):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
     ) -> None: ...
-    async def drop_table(self, name: str, namespace: List[str] = []) -> None: ...
-    async def drop_all_tables(self, namespace: List[str] = []) -> None: ...
+    async def drop_table(
+        self, name: str, namespace: Optional[List[str]] = None
+    ) -> None: ...
+    async def drop_all_tables(self, namespace: Optional[List[str]] = None) -> None: ...
 
 class Table:
     def name(self) -> str: ...
@@ -102,7 +144,17 @@ class Table:
     async def create_index(
         self,
         column: str,
-        index: Union[IvfFlat, IvfPq, HnswPq, HnswSq, BTree, Bitmap, LabelList, FTS],
+        index: Union[
+            IvfFlat,
+            IvfSq,
+            IvfPq,
+            HnswPq,
+            HnswSq,
+            BTree,
+            Bitmap,
+            LabelList,
+            FTS,
+        ],
         replace: Optional[bool],
         wait_timeout: Optional[object],
         *,
@@ -306,6 +358,7 @@ class MergeResult:
     num_updated_rows: int
     num_inserted_rows: int
     num_deleted_rows: int
+    num_attempts: int
 
 class AddColumnsResult:
     version: int

python/python/lancedb/common.py

@@ -96,7 +96,7 @@ def data_to_reader(
             f"Unknown data type {type(data)}. "
             "Supported types: list of dicts, pandas DataFrame, polars DataFrame, "
             "pyarrow Table/RecordBatch, or Pydantic models. "
-            "See https://lancedb.github.io/lancedb/guides/tables/ for examples."
+            "See https://lancedb.com/docs/tables/ for examples."
         )
 
 

python/python/lancedb/db.py

@@ -22,6 +22,13 @@ from lancedb.embeddings.registry import EmbeddingFunctionRegistry
 
 from lancedb.common import data_to_reader, sanitize_uri, validate_schema
 from lancedb.background_loop import LOOP
+from lance_namespace import (
+    ListNamespacesResponse,
+    CreateNamespaceResponse,
+    DropNamespaceResponse,
+    DescribeNamespaceResponse,
+    ListTablesResponse,
+)
 
 from . import __version__
 from ._lancedb import connect as lancedb_connect  # type: ignore
@@ -48,16 +55,22 @@ if TYPE_CHECKING:
     from .io import StorageOptionsProvider
     from ._lancedb import Session
 
+from .namespace_utils import (
+    _normalize_create_namespace_mode,
+    _normalize_drop_namespace_mode,
+    _normalize_drop_namespace_behavior,
+)
+
 
 class DBConnection(EnforceOverrides):
     """An active LanceDB connection interface."""
 
     def list_namespaces(
         self,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse:
         """List immediate child namespace names in the given namespace.
 
         Parameters
@@ -66,48 +79,126 @@ class DBConnection(EnforceOverrides):
             The parent namespace to list namespaces in.
             Empty list represents root namespace.
         page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
 
         Returns
         -------
-        Iterable of str
-            List of immediate child namespace names
+        ListNamespacesResponse
+            Response containing namespace names and optional page_token for pagination.
         """
-        return []
+        if namespace is None:
+            namespace = []
+        return ListNamespacesResponse(namespaces=[], page_token=None)
 
-    def create_namespace(self, namespace: List[str]) -> None:
+    def create_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse:
         """Create a new namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to create.
+        mode: str, optional
+            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
+            or "overwrite" (replace if exists). Case insensitive.
+        properties: Dict[str, str], optional
+            Properties to set on the namespace.
+
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing the properties of the created namespace.
         """
         raise NotImplementedError(
             "Namespace operations are not supported for this connection type"
         )
 
-    def drop_namespace(self, namespace: List[str]) -> None:
+    def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse:
         """Drop a namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to drop.
+        mode: str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior: str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
         """
         raise NotImplementedError(
             "Namespace operations are not supported for this connection type"
         )
 
+    def describe_namespace(self, namespace: List[str]) -> DescribeNamespaceResponse:
+        """Describe a namespace.
+
+        Parameters
+        ----------
+        namespace: List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        raise NotImplementedError(
+            "Namespace operations are not supported for this connection type"
+        )
+
+    def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse:
+        """List all tables in this database with pagination support.
+
+        Parameters
+        ----------
+        namespace: List[str], optional
+            The namespace to list tables in.
+            None or empty list represents root namespace.
+        page_token: str, optional
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
+
+        Returns
+        -------
+        ListTablesResponse
+            Response containing table names and optional page_token for pagination.
+        """
+        raise NotImplementedError(
+            "list_tables is not supported for this connection type"
+        )
+
     @abstractmethod
     def table_names(
         self,
         page_token: Optional[str] = None,
         limit: int = 10,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
     ) -> Iterable[str]:
         """List all tables in this database, in sorted order
 
@@ -142,7 +233,7 @@ class DBConnection(EnforceOverrides):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         data_storage_version: Optional[str] = None,
@@ -191,7 +282,11 @@ class DBConnection(EnforceOverrides):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.github.io/lancedb/guides/storage/>
+            <https://lancedb.com/docs/storage/>
+
+            To enable stable row IDs (row IDs remain stable after compaction,
+            update, delete, and merges), set `new_table_enable_stable_row_ids`
+            to `"true"` in storage_options when connecting to the database.
         data_storage_version: optional, str, default "stable"
             Deprecated.  Set `storage_options` when connecting to the database and set
             `new_table_data_storage_version` in the options.
@@ -308,7 +403,7 @@ class DBConnection(EnforceOverrides):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
@@ -339,7 +434,7 @@ class DBConnection(EnforceOverrides):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.github.io/lancedb/guides/storage/>
+            <https://lancedb.com/docs/storage/>
 
         Returns
         -------
@@ -347,7 +442,7 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError
 
-    def drop_table(self, name: str, namespace: List[str] = []):
+    def drop_table(self, name: str, namespace: Optional[List[str]] = None):
         """Drop a table from the database.
 
         Parameters
@@ -358,14 +453,16 @@ class DBConnection(EnforceOverrides):
             The namespace to drop the table from.
             Empty list represents root namespace.
         """
+        if namespace is None:
+            namespace = []
         raise NotImplementedError
 
     def rename_table(
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -382,6 +479,10 @@ class DBConnection(EnforceOverrides):
             The namespace to move the table to.
             If not specified, defaults to the same as cur_namespace.
         """
+        if cur_namespace is None:
+            cur_namespace = []
+        if new_namespace is None:
+            new_namespace = []
         raise NotImplementedError
 
     def drop_database(self):
@@ -391,7 +492,7 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError
 
-    def drop_all_tables(self, namespace: List[str] = []):
+    def drop_all_tables(self, namespace: Optional[List[str]] = None):
         """
         Drop all tables from the database
 
@@ -401,6 +502,8 @@ class DBConnection(EnforceOverrides):
             The namespace to drop all tables from.
             None or empty list represents root namespace.
         """
+        if namespace is None:
+            namespace = []
         raise NotImplementedError
 
     @property
@@ -472,6 +575,12 @@ class LanceDBConnection(DBConnection):
                     uri = uri[7:]  # Remove "file://"
                 elif uri.startswith("file:/"):
                     uri = uri[5:]  # Remove "file:"
+
+                if sys.platform == "win32":
+                    # On Windows, a path like /C:/path should become C:/path
+                    if len(uri) >= 3 and uri[0] == "/" and uri[2] == ":":
+                        uri = uri[1:]
+
                 uri = Path(uri)
             uri = uri.expanduser().absolute()
             Path(uri).mkdir(parents=True, exist_ok=True)
@@ -535,10 +644,10 @@ class LanceDBConnection(DBConnection):
     @override
     def list_namespaces(
         self,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse:
         """List immediate child namespace names in the given namespace.
 
         Parameters
@@ -547,15 +656,18 @@ class LanceDBConnection(DBConnection):
             The parent namespace to list namespaces in.
             None or empty list represents root namespace.
         page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
 
         Returns
         -------
-        Iterable of str
-            List of immediate child namespace names
+        ListNamespacesResponse
+            Response containing namespace names and optional page_token for pagination.
         """
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.list_namespaces(
                 namespace=namespace, page_token=page_token, limit=limit
@@ -563,26 +675,111 @@ class LanceDBConnection(DBConnection):
         )
 
     @override
-    def create_namespace(self, namespace: List[str]) -> None:
+    def create_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse:
         """Create a new namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to create.
+        mode: str, optional
+            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
+            or "overwrite" (replace if exists). Case insensitive.
+        properties: Dict[str, str], optional
+            Properties to set on the namespace.
+
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing the properties of the created namespace.
         """
-        LOOP.run(self._conn.create_namespace(namespace=namespace))
+        return LOOP.run(
+            self._conn.create_namespace(
+                namespace=namespace, mode=mode, properties=properties
+            )
+        )
 
     @override
-    def drop_namespace(self, namespace: List[str]) -> None:
+    def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse:
         """Drop a namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to drop.
+        mode: str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior: str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
         """
-        return LOOP.run(self._conn.drop_namespace(namespace=namespace))
+        return LOOP.run(
+            self._conn.drop_namespace(namespace=namespace, mode=mode, behavior=behavior)
+        )
+
+    @override
+    def describe_namespace(self, namespace: List[str]) -> DescribeNamespaceResponse:
+        """Describe a namespace.
+
+        Parameters
+        ----------
+        namespace: List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        return LOOP.run(self._conn.describe_namespace(namespace=namespace))
+
+    @override
+    def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse:
+        """List all tables in this database with pagination support.
+
+        Parameters
+        ----------
+        namespace: List[str], optional
+            The namespace to list tables in.
+            None or empty list represents root namespace.
+        page_token: str, optional
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
+
+        Returns
+        -------
+        ListTablesResponse
+            Response containing table names and optional page_token for pagination.
+        """
+        if namespace is None:
+            namespace = []
+        return LOOP.run(
+            self._conn.list_tables(
+                namespace=namespace, page_token=page_token, limit=limit
+            )
+        )
 
     @override
     def table_names(
@@ -590,10 +787,13 @@ class LanceDBConnection(DBConnection):
         page_token: Optional[str] = None,
         limit: int = 10,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
     ) -> Iterable[str]:
         """Get the names of all tables in the database. The names are sorted.
 
+        .. deprecated::
+            Use :meth:`list_tables` instead, which provides proper pagination support.
+
         Parameters
         ----------
         namespace: List[str], optional
@@ -608,6 +808,15 @@ class LanceDBConnection(DBConnection):
         Iterator of str.
             A list of table names.
         """
+        import warnings
+
+        warnings.warn(
+            "table_names() is deprecated, use list_tables() instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.table_names(
                 namespace=namespace, start_after=page_token, limit=limit
@@ -632,7 +841,7 @@ class LanceDBConnection(DBConnection):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         data_storage_version: Optional[str] = None,
@@ -649,6 +858,8 @@ class LanceDBConnection(DBConnection):
         ---
         DBConnection.create_table
         """
+        if namespace is None:
+            namespace = []
         if mode.lower() not in ["create", "overwrite"]:
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
@@ -674,7 +885,7 @@ class LanceDBConnection(DBConnection):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
@@ -692,6 +903,8 @@ class LanceDBConnection(DBConnection):
         -------
         A LanceTable object representing the table.
         """
+        if namespace is None:
+            namespace = []
         if index_cache_size is not None:
             import warnings
 
@@ -717,7 +930,7 @@ class LanceDBConnection(DBConnection):
         target_table_name: str,
         source_uri: str,
         *,
-        target_namespace: List[str] = [],
+        target_namespace: Optional[List[str]] = None,
         source_version: Optional[int] = None,
         source_tag: Optional[str] = None,
         is_shallow: bool = True,
@@ -750,6 +963,8 @@ class LanceDBConnection(DBConnection):
         -------
         A LanceTable object representing the cloned table.
         """
+        if target_namespace is None:
+            target_namespace = []
         LOOP.run(
             self._conn.clone_table(
                 target_table_name,
@@ -770,7 +985,7 @@ class LanceDBConnection(DBConnection):
     def drop_table(
         self,
         name: str,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         ignore_missing: bool = False,
     ):
         """Drop a table from the database.
@@ -784,6 +999,8 @@ class LanceDBConnection(DBConnection):
         ignore_missing: bool, default False
             If True, ignore if the table does not exist.
         """
+        if namespace is None:
+            namespace = []
         LOOP.run(
             self._conn.drop_table(
                 name, namespace=namespace, ignore_missing=ignore_missing
@@ -791,7 +1008,9 @@ class LanceDBConnection(DBConnection):
         )
 
     @override
-    def drop_all_tables(self, namespace: List[str] = []):
+    def drop_all_tables(self, namespace: Optional[List[str]] = None):
+        if namespace is None:
+            namespace = []
         LOOP.run(self._conn.drop_all_tables(namespace=namespace))
 
     @override
@@ -799,8 +1018,8 @@ class LanceDBConnection(DBConnection):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -815,6 +1034,10 @@ class LanceDBConnection(DBConnection):
         new_namespace: List[str], optional
             The namespace to move the table to.
         """
+        if cur_namespace is None:
+            cur_namespace = []
+        if new_namespace is None:
+            new_namespace = []
         LOOP.run(
             self._conn.rename_table(
                 cur_name,
@@ -904,10 +1127,10 @@ class AsyncConnection(object):
 
     async def list_namespaces(
         self,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse:
         """List immediate child namespace names in the given namespace.
 
         Parameters
@@ -917,47 +1140,141 @@ class AsyncConnection(object):
             None or empty list represents root namespace.
         page_token: str, optional
             The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
+        limit: int, optional
+            The maximum number of results to return.
 
         Returns
         -------
-        Iterable of str
-            List of immediate child namespace names (not full paths)
+        ListNamespacesResponse
+            Response containing namespace names and optional pagination token
         """
-        return await self._inner.list_namespaces(
+        if namespace is None:
+            namespace = []
+        result = await self._inner.list_namespaces(
             namespace=namespace, page_token=page_token, limit=limit
         )
+        return ListNamespacesResponse(**result)
 
-    async def create_namespace(self, namespace: List[str]) -> None:
+    async def create_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse:
         """Create a new namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to create.
-        """
-        await self._inner.create_namespace(namespace)
+        mode: str, optional
+            Creation mode - "create", "exist_ok", or "overwrite". Case insensitive.
+        properties: Dict[str, str], optional
+            Properties to associate with the namespace
 
-    async def drop_namespace(self, namespace: List[str]) -> None:
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing namespace properties
+        """
+        result = await self._inner.create_namespace(
+            namespace,
+            mode=_normalize_create_namespace_mode(mode),
+            properties=properties,
+        )
+        return CreateNamespaceResponse(**result)
+
+    async def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse:
         """Drop a namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to drop.
+        mode: str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior: str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
         """
-        await self._inner.drop_namespace(namespace)
+        result = await self._inner.drop_namespace(
+            namespace,
+            mode=_normalize_drop_namespace_mode(mode),
+            behavior=_normalize_drop_namespace_behavior(behavior),
+        )
+        return DropNamespaceResponse(**result)
+
+    async def describe_namespace(
+        self, namespace: List[str]
+    ) -> DescribeNamespaceResponse:
+        """Describe a namespace.
+
+        Parameters
+        ----------
+        namespace: List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        result = await self._inner.describe_namespace(namespace)
+        return DescribeNamespaceResponse(**result)
+
+    async def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse:
+        """List all tables in this database with pagination support.
+
+        Parameters
+        ----------
+        namespace: List[str], optional
+            The namespace to list tables in.
+            None or empty list represents root namespace.
+        page_token: str, optional
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
+
+        Returns
+        -------
+        ListTablesResponse
+            Response containing table names and optional page_token for pagination.
+        """
+        if namespace is None:
+            namespace = []
+        result = await self._inner.list_tables(
+            namespace=namespace, page_token=page_token, limit=limit
+        )
+        return ListTablesResponse(**result)
 
     async def table_names(
         self,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         start_after: Optional[str] = None,
         limit: Optional[int] = None,
     ) -> Iterable[str]:
         """List all tables in this database, in sorted order
 
+        .. deprecated::
+            Use :meth:`list_tables` instead, which provides proper pagination support.
+
         Parameters
         ----------
         namespace: List[str], optional
@@ -976,6 +1293,15 @@ class AsyncConnection(object):
         -------
         Iterable of str
         """
+        import warnings
+
+        warnings.warn(
+            "table_names() is deprecated, use list_tables() instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        if namespace is None:
+            namespace = []
         return await self._inner.table_names(
             namespace=namespace, start_after=start_after, limit=limit
         )
@@ -992,7 +1318,7 @@ class AsyncConnection(object):
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         location: Optional[str] = None,
     ) -> AsyncTable:
@@ -1039,7 +1365,11 @@ class AsyncConnection(object):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.github.io/lancedb/guides/storage/>
+            <https://lancedb.com/docs/storage/>
+
+            To enable stable row IDs (row IDs remain stable after compaction,
+            update, delete, and merges), set `new_table_enable_stable_row_ids`
+            to `"true"` in storage_options when connecting to the database.
 
         Returns
         -------
@@ -1149,6 +1479,8 @@ class AsyncConnection(object):
         ...     await db.create_table("table4", make_batches(), schema=schema)
         >>> asyncio.run(iterable_example())
         """
+        if namespace is None:
+            namespace = []
         metadata = None
 
         if embedding_functions is not None:
@@ -1206,7 +1538,7 @@ class AsyncConnection(object):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
@@ -1225,7 +1557,7 @@ class AsyncConnection(object):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.github.io/lancedb/guides/storage/>
+            <https://lancedb.com/docs/storage/>
         index_cache_size: int, default 256
             **Deprecated**: Use session-level cache configuration instead.
             Create a Session with custom cache sizes and pass it to lancedb.connect().
@@ -1248,6 +1580,8 @@ class AsyncConnection(object):
         -------
         A LanceTable object representing the table.
         """
+        if namespace is None:
+            namespace = []
         table = await self._inner.open_table(
             name,
             namespace=namespace,
@@ -1263,7 +1597,7 @@ class AsyncConnection(object):
         target_table_name: str,
         source_uri: str,
         *,
-        target_namespace: List[str] = [],
+        target_namespace: Optional[List[str]] = None,
         source_version: Optional[int] = None,
         source_tag: Optional[str] = None,
         is_shallow: bool = True,
@@ -1296,6 +1630,8 @@ class AsyncConnection(object):
         -------
         An AsyncTable object representing the cloned table.
         """
+        if target_namespace is None:
+            target_namespace = []
         table = await self._inner.clone_table(
             target_table_name,
             source_uri,
@@ -1310,8 +1646,8 @@ class AsyncConnection(object):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -1328,6 +1664,10 @@ class AsyncConnection(object):
             The namespace to move the table to.
             If not specified, defaults to the same as cur_namespace.
         """
+        if cur_namespace is None:
+            cur_namespace = []
+        if new_namespace is None:
+            new_namespace = []
         await self._inner.rename_table(
             cur_name, new_name, cur_namespace=cur_namespace, new_namespace=new_namespace
         )
@@ -1336,7 +1676,7 @@ class AsyncConnection(object):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         ignore_missing: bool = False,
     ):
         """Drop a table from the database.
@@ -1351,6 +1691,8 @@ class AsyncConnection(object):
         ignore_missing: bool, default False
             If True, ignore if the table does not exist.
         """
+        if namespace is None:
+            namespace = []
         try:
             await self._inner.drop_table(name, namespace=namespace)
         except ValueError as e:
@@ -1359,7 +1701,7 @@ class AsyncConnection(object):
             if f"Table '{name}' was not found" not in str(e):
                 raise e
 
-    async def drop_all_tables(self, namespace: List[str] = []):
+    async def drop_all_tables(self, namespace: Optional[List[str]] = None):
         """Drop all tables from the database.
 
         Parameters
@@ -1368,6 +1710,8 @@ class AsyncConnection(object):
             The namespace to drop all tables from.
             None or empty list represents root namespace.
         """
+        if namespace is None:
+            namespace = []
         await self._inner.drop_all_tables(namespace=namespace)
 
     @deprecation.deprecated(

python/python/lancedb/index.py

@@ -376,6 +376,11 @@ class HnswSq:
     target_partition_size: Optional[int] = None
 
 
+# Backwards-compatible aliases
+IvfHnswPq = HnswPq
+IvfHnswSq = HnswSq
+
+
 @dataclass
 class IvfFlat:
     """Describes an IVF Flat Index
@@ -475,6 +480,36 @@ class IvfFlat:
     target_partition_size: Optional[int] = None
 
 
+@dataclass
+class IvfSq:
+    """Describes an IVF Scalar Quantization (SQ) index.
+
+    This index applies scalar quantization to compress vectors and organizes the
+    quantized vectors into IVF partitions. It offers a balance between search
+    speed and storage efficiency while keeping good recall.
+
+    Attributes
+    ----------
+    distance_type: str, default "l2"
+        The distance metric used to train and search the index. Supported values
+        are "l2", "cosine", and "dot".
+    num_partitions: int, default sqrt(num_rows)
+        Number of IVF partitions to create.
+    max_iterations: int, default 50
+        Maximum iterations for kmeans during partition training.
+    sample_rate: int, default 256
+        Controls the number of training vectors: sample_rate * num_partitions.
+    target_partition_size: int, optional
+        Target size for each partition; adjusts the balance between speed and accuracy.
+    """
+
+    distance_type: Literal["l2", "cosine", "dot"] = "l2"
+    num_partitions: Optional[int] = None
+    max_iterations: int = 50
+    sample_rate: int = 256
+    target_partition_size: Optional[int] = None
+
+
 @dataclass
 class IvfPq:
     """Describes an IVF PQ Index
@@ -609,9 +644,19 @@ class IvfPq:
 class IvfRq:
     """Describes an IVF RQ Index
 
-    IVF-RQ (Residual Quantization) stores a compressed copy of each vector using
-    residual quantization and organizes them into IVF partitions. Parameters
-    largely mirror IVF-PQ for consistency.
+    IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
+    and organizes them into IVF partitions.
+
+    The compression scheme is called RabitQ quantization. Each dimension is
+    quantized into a small number of bits. The parameters `num_bits` and
+    `num_partitions` control this process, providing a tradeoff between
+    index size (and thus search speed) and index accuracy.
+
+    The partitioning process is called IVF and the `num_partitions` parameter
+    controls how many groups to create.
+
+    Note that training an IVF RQ index on a large dataset is a slow operation
+    and currently is also a memory intensive operation.
 
     Attributes
     ----------
@@ -628,7 +673,7 @@ class IvfRq:
         Number of IVF partitions to create.
 
     num_bits: int, default 1
-        Number of bits to encode each dimension.
+        Number of bits to encode each dimension in the RabitQ codebook.
 
     max_iterations: int, default 50
         Max iterations to train kmeans when computing IVF partitions.
@@ -651,6 +696,9 @@ class IvfRq:
 __all__ = [
     "BTree",
     "IvfPq",
+    "IvfHnswPq",
+    "IvfHnswSq",
+    "IvfSq",
     "IvfRq",
     "IvfFlat",
     "HnswPq",

python/python/lancedb/namespace.py

@@ -10,6 +10,7 @@ through a namespace abstraction.
 
 from __future__ import annotations
 
+import asyncio
 import sys
 from typing import Dict, Iterable, List, Optional, Union
 
@@ -22,27 +23,39 @@ from datetime import timedelta
 import pyarrow as pa
 
 from lancedb.db import DBConnection, LanceDBConnection
+from lancedb.namespace_utils import (
+    _normalize_create_namespace_mode,
+    _normalize_drop_namespace_mode,
+    _normalize_drop_namespace_behavior,
+)
 from lancedb.io import StorageOptionsProvider
-from lancedb.table import LanceTable, Table
+from lance_namespace import (
+    LanceNamespace,
+    connect as namespace_connect,
+    CreateNamespaceResponse,
+    DescribeNamespaceResponse,
+    DropNamespaceResponse,
+    ListNamespacesResponse,
+    ListTablesResponse,
+    ListTablesRequest,
+    DescribeTableRequest,
+    DescribeNamespaceRequest,
+    DropTableRequest,
+    ListNamespacesRequest,
+    CreateNamespaceRequest,
+    DropNamespaceRequest,
+    CreateEmptyTableRequest,
+)
+from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
 from lancedb.common import DATA
 from lancedb.pydantic import LanceModel
 from lancedb.embeddings import EmbeddingFunctionConfig
 from ._lancedb import Session
 
-from lance_namespace import LanceNamespace, connect as namespace_connect
-from lance_namespace_urllib3_client.models import (
-    ListTablesRequest,
-    DescribeTableRequest,
-    DropTableRequest,
-    ListNamespacesRequest,
-    CreateNamespaceRequest,
-    DropNamespaceRequest,
-    CreateEmptyTableRequest,
-    JsonArrowSchema,
-    JsonArrowField,
-    JsonArrowDataType,
-)
+from lance_namespace_urllib3_client.models.json_arrow_schema import JsonArrowSchema
+from lance_namespace_urllib3_client.models.json_arrow_field import JsonArrowField
+from lance_namespace_urllib3_client.models.json_arrow_data_type import JsonArrowDataType
 
 
 def _convert_pyarrow_type_to_json(arrow_type: pa.DataType) -> JsonArrowDataType:
@@ -126,13 +139,17 @@ class LanceNamespaceStorageOptionsProvider(StorageOptionsProvider):
 
     Examples
     --------
-    >>> from lance_namespace import connect as namespace_connect
-    >>> namespace = namespace_connect("rest", {"url": "https://..."})
-    >>> provider = LanceNamespaceStorageOptionsProvider(
-    ...     namespace=namespace,
-    ...     table_id=["my_namespace", "my_table"]
-    ... )
-    >>> options = provider.fetch_storage_options()
+    Create a provider and fetch storage options::
+
+        from lance_namespace import connect as namespace_connect
+
+        # Connect to namespace (requires a running namespace server)
+        namespace = namespace_connect("rest", {"uri": "https://..."})
+        provider = LanceNamespaceStorageOptionsProvider(
+            namespace=namespace,
+            table_id=["my_namespace", "my_table"]
+        )
+        options = provider.fetch_storage_options()
     """
 
     def __init__(self, namespace: LanceNamespace, table_id: List[str]):
@@ -234,8 +251,23 @@ class LanceNamespaceDBConnection(DBConnection):
         page_token: Optional[str] = None,
         limit: int = 10,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
     ) -> Iterable[str]:
+        """
+        List table names in the database.
+
+        .. deprecated::
+            Use :meth:`list_tables` instead, which provides proper pagination support.
+        """
+        import warnings
+
+        warnings.warn(
+            "table_names() is deprecated, use list_tables() instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        if namespace is None:
+            namespace = []
         request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
         response = self._ns.list_tables(request)
         return response.tables if response.tables else []
@@ -252,12 +284,14 @@ class LanceNamespaceDBConnection(DBConnection):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         data_storage_version: Optional[str] = None,
         enable_v2_manifest_paths: Optional[bool] = None,
     ) -> Table:
+        if namespace is None:
+            namespace = []
         if mode.lower() not in ["create", "overwrite"]:
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
@@ -346,11 +380,13 @@ class LanceNamespaceDBConnection(DBConnection):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         index_cache_size: Optional[int] = None,
     ) -> Table:
+        if namespace is None:
+            namespace = []
         table_id = namespace + [name]
         request = DescribeTableRequest(id=table_id)
         response = self._ns.describe_table(request)
@@ -380,8 +416,10 @@ class LanceNamespaceDBConnection(DBConnection):
         )
 
     @override
-    def drop_table(self, name: str, namespace: List[str] = []):
+    def drop_table(self, name: str, namespace: Optional[List[str]] = None):
         # Use namespace drop_table directly
+        if namespace is None:
+            namespace = []
         table_id = namespace + [name]
         request = DropTableRequest(id=table_id)
         self._ns.drop_table(request)
@@ -391,9 +429,13 @@ class LanceNamespaceDBConnection(DBConnection):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
     ):
+        if cur_namespace is None:
+            cur_namespace = []
+        if new_namespace is None:
+            new_namespace = []
         raise NotImplementedError(
             "rename_table is not supported for namespace connections"
         )
@@ -405,17 +447,19 @@ class LanceNamespaceDBConnection(DBConnection):
         )
 
     @override
-    def drop_all_tables(self, namespace: List[str] = []):
+    def drop_all_tables(self, namespace: Optional[List[str]] = None):
+        if namespace is None:
+            namespace = []
         for table_name in self.table_names(namespace=namespace):
             self.drop_table(table_name, namespace=namespace)
 
     @override
     def list_namespaces(
         self,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse:
         """
         List child namespaces under the given namespace.
 
@@ -425,23 +469,34 @@ class LanceNamespaceDBConnection(DBConnection):
             The parent namespace to list children from.
             If None, lists root-level namespaces.
         page_token : Optional[str]
-            Pagination token for listing results.
-        limit : int
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit : int, optional
             Maximum number of namespaces to return.
 
         Returns
         -------
-        Iterable[str]
-            Names of child namespaces.
+        ListNamespacesResponse
+            Response containing namespace names and optional page_token for pagination.
         """
+        if namespace is None:
+            namespace = []
         request = ListNamespacesRequest(
             id=namespace, page_token=page_token, limit=limit
         )
         response = self._ns.list_namespaces(request)
-        return response.namespaces if response.namespaces else []
+        return ListNamespacesResponse(
+            namespaces=response.namespaces if response.namespaces else [],
+            page_token=response.page_token,
+        )
 
     @override
-    def create_namespace(self, namespace: List[str]) -> None:
+    def create_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse:
         """
         Create a new namespace.
 
@@ -449,12 +504,34 @@ class LanceNamespaceDBConnection(DBConnection):
         ----------
         namespace : List[str]
             The namespace path to create.
+        mode : str, optional
+            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
+            or "overwrite" (replace if exists). Case insensitive.
+        properties : Dict[str, str], optional
+            Properties to set on the namespace.
+
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing the properties of the created namespace.
         """
-        request = CreateNamespaceRequest(id=namespace)
-        self._ns.create_namespace(request)
+        request = CreateNamespaceRequest(
+            id=namespace,
+            mode=_normalize_create_namespace_mode(mode),
+            properties=properties,
+        )
+        response = self._ns.create_namespace(request)
+        return CreateNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
 
     @override
-    def drop_namespace(self, namespace: List[str]) -> None:
+    def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse:
         """
         Drop a namespace.
 
@@ -462,22 +539,102 @@ class LanceNamespaceDBConnection(DBConnection):
         ----------
         namespace : List[str]
             The namespace path to drop.
+        mode : str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior : str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
         """
-        request = DropNamespaceRequest(id=namespace)
-        self._ns.drop_namespace(request)
+        request = DropNamespaceRequest(
+            id=namespace,
+            mode=_normalize_drop_namespace_mode(mode),
+            behavior=_normalize_drop_namespace_behavior(behavior),
+        )
+        response = self._ns.drop_namespace(request)
+        return DropNamespaceResponse(
+            properties=(
+                response.properties if hasattr(response, "properties") else None
+            ),
+            transaction_id=(
+                response.transaction_id if hasattr(response, "transaction_id") else None
+            ),
+        )
+
+    @override
+    def describe_namespace(self, namespace: List[str]) -> DescribeNamespaceResponse:
+        """
+        Describe a namespace.
+
+        Parameters
+        ----------
+        namespace : List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        request = DescribeNamespaceRequest(id=namespace)
+        response = self._ns.describe_namespace(request)
+        return DescribeNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
+
+    @override
+    def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse:
+        """
+        List all tables in this database with pagination support.
+
+        Parameters
+        ----------
+        namespace : List[str], optional
+            The namespace to list tables in.
+            None or empty list represents root namespace.
+        page_token : str, optional
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit : int, optional
+            The maximum number of results to return.
+
+        Returns
+        -------
+        ListTablesResponse
+            Response containing table names and optional page_token for pagination.
+        """
+        if namespace is None:
+            namespace = []
+        request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
+        response = self._ns.list_tables(request)
+        return ListTablesResponse(
+            tables=response.tables if response.tables else [],
+            page_token=response.page_token,
+        )
 
     def _lance_table_from_uri(
         self,
         name: str,
         table_uri: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         index_cache_size: Optional[int] = None,
     ) -> LanceTable:
         # Open a table directly from a URI using the location parameter
         # Note: storage_options should already be merged by the caller
+        if namespace is None:
+            namespace = []
         temp_conn = LanceDBConnection(
             table_uri,  # Use the table location as the connection URI
             read_consistency_interval=self.read_consistency_interval,
@@ -497,6 +654,431 @@ class LanceNamespaceDBConnection(DBConnection):
         )
 
 
+class AsyncLanceNamespaceDBConnection:
+    """
+    An async LanceDB connection that uses a namespace for table management.
+
+    This connection delegates table URI resolution to a lance_namespace instance,
+    while providing async methods for all operations.
+    """
+
+    def __init__(
+        self,
+        namespace: LanceNamespace,
+        *,
+        read_consistency_interval: Optional[timedelta] = None,
+        storage_options: Optional[Dict[str, str]] = None,
+        session: Optional[Session] = None,
+    ):
+        """
+        Initialize an async namespace-based LanceDB connection.
+
+        Parameters
+        ----------
+        namespace : LanceNamespace
+            The namespace instance to use for table management
+        read_consistency_interval : Optional[timedelta]
+            The interval at which to check for updates to the table from other
+            processes. If None, then consistency is not checked.
+        storage_options : Optional[Dict[str, str]]
+            Additional options for the storage backend
+        session : Optional[Session]
+            A session to use for this connection
+        """
+        self._ns = namespace
+        self.read_consistency_interval = read_consistency_interval
+        self.storage_options = storage_options or {}
+        self.session = session
+
+    async def table_names(
+        self,
+        page_token: Optional[str] = None,
+        limit: int = 10,
+        *,
+        namespace: Optional[List[str]] = None,
+    ) -> Iterable[str]:
+        """
+        List table names in the namespace.
+
+        .. deprecated::
+            Use :meth:`list_tables` instead, which provides proper pagination support.
+        """
+        import warnings
+
+        warnings.warn(
+            "table_names() is deprecated, use list_tables() instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        if namespace is None:
+            namespace = []
+        request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
+        response = self._ns.list_tables(request)
+        return response.tables if response.tables else []
+
+    async def create_table(
+        self,
+        name: str,
+        data: Optional[DATA] = None,
+        schema: Optional[Union[pa.Schema, LanceModel]] = None,
+        mode: str = "create",
+        exist_ok: bool = False,
+        on_bad_vectors: str = "error",
+        fill_value: float = 0.0,
+        embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
+        *,
+        namespace: Optional[List[str]] = None,
+        storage_options: Optional[Dict[str, str]] = None,
+        storage_options_provider: Optional[StorageOptionsProvider] = None,
+        data_storage_version: Optional[str] = None,
+        enable_v2_manifest_paths: Optional[bool] = None,
+    ) -> AsyncTable:
+        """Create a new table in the namespace."""
+        if namespace is None:
+            namespace = []
+        if mode.lower() not in ["create", "overwrite"]:
+            raise ValueError("mode must be either 'create' or 'overwrite'")
+        validate_table_name(name)
+
+        # Get location from namespace
+        table_id = namespace + [name]
+
+        # Step 1: Get the table location and storage options from namespace
+        location = None
+        namespace_storage_options = None
+        if mode.lower() == "overwrite":
+            # Try to describe the table first to see if it exists
+            try:
+                describe_request = DescribeTableRequest(id=table_id)
+                describe_response = self._ns.describe_table(describe_request)
+                location = describe_response.location
+                namespace_storage_options = describe_response.storage_options
+            except Exception:
+                # Table doesn't exist, will create a new one below
+                pass
+
+        if location is None:
+            # Table doesn't exist or mode is "create", reserve a new location
+            create_empty_request = CreateEmptyTableRequest(
+                id=table_id,
+                location=None,
+                properties=self.storage_options if self.storage_options else None,
+            )
+            create_empty_response = self._ns.create_empty_table(create_empty_request)
+
+            if not create_empty_response.location:
+                raise ValueError(
+                    "Table location is missing from create_empty_table response"
+                )
+
+            location = create_empty_response.location
+            namespace_storage_options = create_empty_response.storage_options
+
+        # Merge storage options: self.storage_options < user options < namespace options
+        merged_storage_options = dict(self.storage_options)
+        if storage_options:
+            merged_storage_options.update(storage_options)
+        if namespace_storage_options:
+            merged_storage_options.update(namespace_storage_options)
+
+        # Step 2: Create table using LanceTable.create with the location
+        # Run the sync operation in a thread
+        def _create_table():
+            temp_conn = LanceDBConnection(
+                location,
+                read_consistency_interval=self.read_consistency_interval,
+                storage_options=merged_storage_options,
+                session=self.session,
+            )
+
+            # Create a storage options provider if not provided by user
+            if (
+                storage_options_provider is None
+                and namespace_storage_options is not None
+            ):
+                provider = LanceNamespaceStorageOptionsProvider(
+                    namespace=self._ns,
+                    table_id=table_id,
+                )
+            else:
+                provider = storage_options_provider
+
+            return LanceTable.create(
+                temp_conn,
+                name,
+                data,
+                schema,
+                mode=mode,
+                exist_ok=exist_ok,
+                on_bad_vectors=on_bad_vectors,
+                fill_value=fill_value,
+                embedding_functions=embedding_functions,
+                namespace=namespace,
+                storage_options=merged_storage_options,
+                storage_options_provider=provider,
+                location=location,
+            )
+
+        lance_table = await asyncio.to_thread(_create_table)
+        # Get the underlying async table from LanceTable
+        return lance_table._table
+
+    async def open_table(
+        self,
+        name: str,
+        *,
+        namespace: Optional[List[str]] = None,
+        storage_options: Optional[Dict[str, str]] = None,
+        storage_options_provider: Optional[StorageOptionsProvider] = None,
+        index_cache_size: Optional[int] = None,
+    ) -> AsyncTable:
+        """Open an existing table from the namespace."""
+        if namespace is None:
+            namespace = []
+        table_id = namespace + [name]
+        request = DescribeTableRequest(id=table_id)
+        response = self._ns.describe_table(request)
+
+        # Merge storage options: self.storage_options < user options < namespace options
+        merged_storage_options = dict(self.storage_options)
+        if storage_options:
+            merged_storage_options.update(storage_options)
+        if response.storage_options:
+            merged_storage_options.update(response.storage_options)
+
+        # Create a storage options provider if not provided by user
+        if storage_options_provider is None and response.storage_options is not None:
+            storage_options_provider = LanceNamespaceStorageOptionsProvider(
+                namespace=self._ns,
+                table_id=table_id,
+            )
+
+        # Open table in a thread
+        def _open_table():
+            temp_conn = LanceDBConnection(
+                response.location,
+                read_consistency_interval=self.read_consistency_interval,
+                storage_options=merged_storage_options,
+                session=self.session,
+            )
+
+            return LanceTable.open(
+                temp_conn,
+                name,
+                namespace=namespace,
+                storage_options=merged_storage_options,
+                storage_options_provider=storage_options_provider,
+                index_cache_size=index_cache_size,
+                location=response.location,
+            )
+
+        lance_table = await asyncio.to_thread(_open_table)
+        return lance_table._table
+
+    async def drop_table(self, name: str, namespace: Optional[List[str]] = None):
+        """Drop a table from the namespace."""
+        if namespace is None:
+            namespace = []
+        table_id = namespace + [name]
+        request = DropTableRequest(id=table_id)
+        self._ns.drop_table(request)
+
+    async def rename_table(
+        self,
+        cur_name: str,
+        new_name: str,
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
+    ):
+        """Rename is not supported for namespace connections."""
+        if cur_namespace is None:
+            cur_namespace = []
+        if new_namespace is None:
+            new_namespace = []
+        raise NotImplementedError(
+            "rename_table is not supported for namespace connections"
+        )
+
+    async def drop_database(self):
+        """Deprecated method."""
+        raise NotImplementedError(
+            "drop_database is deprecated, use drop_all_tables instead"
+        )
+
+    async def drop_all_tables(self, namespace: Optional[List[str]] = None):
+        """Drop all tables in the namespace."""
+        if namespace is None:
+            namespace = []
+        table_names = await self.table_names(namespace=namespace)
+        for table_name in table_names:
+            await self.drop_table(table_name, namespace=namespace)
+
+    async def list_namespaces(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse:
+        """
+        List child namespaces under the given namespace.
+
+        Parameters
+        ----------
+        namespace : Optional[List[str]]
+            The parent namespace to list children from.
+            If None, lists root-level namespaces.
+        page_token : Optional[str]
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit : int, optional
+            Maximum number of namespaces to return.
+
+        Returns
+        -------
+        ListNamespacesResponse
+            Response containing namespace names and optional page_token for pagination.
+        """
+        if namespace is None:
+            namespace = []
+        request = ListNamespacesRequest(
+            id=namespace, page_token=page_token, limit=limit
+        )
+        response = self._ns.list_namespaces(request)
+        return ListNamespacesResponse(
+            namespaces=response.namespaces if response.namespaces else [],
+            page_token=response.page_token,
+        )
+
+    async def create_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse:
+        """
+        Create a new namespace.
+
+        Parameters
+        ----------
+        namespace : List[str]
+            The namespace path to create.
+        mode : str, optional
+            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
+            or "overwrite" (replace if exists). Case insensitive.
+        properties : Dict[str, str], optional
+            Properties to set on the namespace.
+
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing the properties of the created namespace.
+        """
+        request = CreateNamespaceRequest(
+            id=namespace,
+            mode=_normalize_create_namespace_mode(mode),
+            properties=properties,
+        )
+        response = self._ns.create_namespace(request)
+        return CreateNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
+
+    async def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse:
+        """
+        Drop a namespace.
+
+        Parameters
+        ----------
+        namespace : List[str]
+            The namespace path to drop.
+        mode : str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior : str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
+        """
+        request = DropNamespaceRequest(
+            id=namespace,
+            mode=_normalize_drop_namespace_mode(mode),
+            behavior=_normalize_drop_namespace_behavior(behavior),
+        )
+        response = self._ns.drop_namespace(request)
+        return DropNamespaceResponse(
+            properties=(
+                response.properties if hasattr(response, "properties") else None
+            ),
+            transaction_id=(
+                response.transaction_id if hasattr(response, "transaction_id") else None
+            ),
+        )
+
+    async def describe_namespace(
+        self, namespace: List[str]
+    ) -> DescribeNamespaceResponse:
+        """
+        Describe a namespace.
+
+        Parameters
+        ----------
+        namespace : List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        request = DescribeNamespaceRequest(id=namespace)
+        response = self._ns.describe_namespace(request)
+        return DescribeNamespaceResponse(
+            properties=response.properties if hasattr(response, "properties") else None
+        )
+
+    async def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse:
+        """
+        List all tables in this database with pagination support.
+
+        Parameters
+        ----------
+        namespace : List[str], optional
+            The namespace to list tables in.
+            None or empty list represents root namespace.
+        page_token : str, optional
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit : int, optional
+            The maximum number of results to return.
+
+        Returns
+        -------
+        ListTablesResponse
+            Response containing table names and optional page_token for pagination.
+        """
+        if namespace is None:
+            namespace = []
+        request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
+        response = self._ns.list_tables(request)
+        return ListTablesResponse(
+            tables=response.tables if response.tables else [],
+            page_token=response.page_token,
+        )
+
+
 def connect_namespace(
     impl: str,
     properties: Dict[str, str],
@@ -541,3 +1123,62 @@ def connect_namespace(
         storage_options=storage_options,
         session=session,
     )
+
+
+def connect_namespace_async(
+    impl: str,
+    properties: Dict[str, str],
+    *,
+    read_consistency_interval: Optional[timedelta] = None,
+    storage_options: Optional[Dict[str, str]] = None,
+    session: Optional[Session] = None,
+) -> AsyncLanceNamespaceDBConnection:
+    """
+    Connect to a LanceDB database through a namespace (returns async connection).
+
+    This function is synchronous but returns an AsyncLanceNamespaceDBConnection
+    that provides async methods for all database operations.
+
+    Parameters
+    ----------
+    impl : str
+        The namespace implementation to use. For examples:
+        - "dir" for DirectoryNamespace
+        - "rest" for REST-based namespace
+        - Full module path for custom implementations
+    properties : Dict[str, str]
+        Configuration properties for the namespace implementation.
+        Different namespace implemenation has different config properties.
+        For example, use DirectoryNamespace with {"root": "/path/to/directory"}
+    read_consistency_interval : Optional[timedelta]
+        The interval at which to check for updates to the table from other
+        processes. If None, then consistency is not checked.
+    storage_options : Optional[Dict[str, str]]
+        Additional options for the storage backend
+    session : Optional[Session]
+        A session to use for this connection
+
+    Returns
+    -------
+    AsyncLanceNamespaceDBConnection
+        An async namespace-based connection to LanceDB
+
+    Examples
+    --------
+    >>> import lancedb
+    >>> # This function is sync, but returns an async connection
+    >>> db = lancedb.connect_namespace_async("dir", {"root": "/path/to/db"})
+    >>> # Use async methods on the connection
+    >>> async def use_db():
+    ...     tables = await db.table_names()
+    ...     table = await db.create_table("my_table", schema=schema)
+    """
+    namespace = namespace_connect(impl, properties)
+
+    # Return the async namespace-based connection
+    return AsyncLanceNamespaceDBConnection(
+        namespace,
+        read_consistency_interval=read_consistency_interval,
+        storage_options=storage_options,
+        session=session,
+    )

python/python/lancedb/namespace_utils.py

@@ -0,0 +1,27 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+"""Utility functions for namespace operations."""
+
+from typing import Optional
+
+
+def _normalize_create_namespace_mode(mode: Optional[str]) -> Optional[str]:
+    """Normalize create namespace mode to lowercase (API expects lowercase)."""
+    if mode is None:
+        return None
+    return mode.lower()
+
+
+def _normalize_drop_namespace_mode(mode: Optional[str]) -> Optional[str]:
+    """Normalize drop namespace mode to uppercase (API expects uppercase)."""
+    if mode is None:
+        return None
+    return mode.upper()
+
+
+def _normalize_drop_namespace_behavior(behavior: Optional[str]) -> Optional[str]:
+    """Normalize drop namespace behavior to uppercase (API expects uppercase)."""
+    if behavior is None:
+        return None
+    return behavior.upper()

python/python/lancedb/query.py

@@ -14,6 +14,7 @@ from typing import (
     Literal,
     Optional,
     Tuple,
+    Type,
     TypeVar,
     Union,
     Any,
@@ -786,10 +787,7 @@ class LanceQueryBuilder(ABC):
         -------
         List[LanceModel]
         """
-        return [
-            model(**{k: v for k, v in row.items() if k in model.field_names()})
-            for row in self.to_arrow(timeout=timeout).to_pylist()
-        ]
+        return [model(**row) for row in self.to_arrow(timeout=timeout).to_pylist()]
 
     def to_polars(self, *, timeout: Optional[timedelta] = None) -> "pl.DataFrame":
         """
@@ -885,7 +883,7 @@ class LanceQueryBuilder(ABC):
         ----------
         where: str
             The where clause which is a valid SQL where clause. See
-            `Lance filter pushdown <https://lancedb.github.io/lance/read_and_write.html#filter-push-down>`_
+            `Lance filter pushdown <https://lance.org/guide/read_and_write#filter-push-down>`_
             for valid SQL expressions.
         prefilter: bool, default True
             If True, apply the filter before vector search, otherwise the
@@ -1358,7 +1356,7 @@ class LanceVectorQueryBuilder(LanceQueryBuilder):
         ----------
         where: str
             The where clause which is a valid SQL where clause. See
-            `Lance filter pushdown <https://lancedb.github.io/lance/read_and_write.html#filter-push-down>`_
+            `Lance filter pushdown <https://lance.org/guide/read_and_write#filter-push-down>`_
             for valid SQL expressions.
         prefilter: bool, default True
             If True, apply the filter before vector search, otherwise the
@@ -1497,7 +1495,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
         if self._phrase_query:
             if isinstance(query, str):
                 if not query.startswith('"') or not query.endswith('"'):
-                    query = f'"{query}"'
+                    self._query = f'"{query}"'
             elif isinstance(query, FullTextQuery) and not isinstance(
                 query, PhraseQuery
             ):
@@ -2400,6 +2398,28 @@ class AsyncQueryBase(object):
 
         return pl.from_arrow(await self.to_arrow(timeout=timeout))
 
+    async def to_pydantic(
+        self, model: Type[LanceModel], *, timeout: Optional[timedelta] = None
+    ) -> List[LanceModel]:
+        """
+        Convert results to a list of pydantic models.
+
+        Parameters
+        ----------
+        model : Type[LanceModel]
+            The pydantic model to use.
+        timeout : timedelta, optional
+            The maximum time to wait for the query to complete.
+            If None, wait indefinitely.
+
+        Returns
+        -------
+        list[LanceModel]
+        """
+        return [
+            model(**row) for row in (await self.to_arrow(timeout=timeout)).to_pylist()
+        ]
+
     async def explain_plan(self, verbose: Optional[bool] = False):
         """Return the execution plan for this query.
 
@@ -2409,9 +2429,8 @@ class AsyncQueryBase(object):
         >>> from lancedb import connect_async
         >>> async def doctest_example():
         ...     conn = await connect_async("./.lancedb")
-        ...     table = await conn.create_table("my_table", [{"vector": [99, 99]}])
-        ...     query = [100, 100]
-        ...     plan = await table.query().nearest_to([1, 2]).explain_plan(True)
+        ...     table = await conn.create_table("my_table", [{"vector": [99.0, 99.0]}])
+        ...     plan = await table.query().nearest_to([1.0, 2.0]).explain_plan(True)
         ...     print(plan)
         >>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
         ProjectionExec: expr=[vector@0 as vector, _distance@2 as _distance]
@@ -2420,6 +2439,7 @@ class AsyncQueryBase(object):
               SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
                 KNNVectorDistance: metric=l2
                   LanceRead: uri=..., projection=[vector], ...
+        <BLANKLINE>
 
         Parameters
         ----------
@@ -3121,10 +3141,9 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         >>> from lancedb.index import FTS
         >>> async def doctest_example():
         ...     conn = await connect_async("./.lancedb")
-        ...     table = await conn.create_table("my_table", [{"vector": [99, 99], "text": "hello world"}])
+        ...     table = await conn.create_table("my_table", [{"vector": [99.0, 99.0], "text": "hello world"}])
         ...     await table.create_index("text", config=FTS(with_position=False))
-        ...     query = [100, 100]
-        ...     plan = await table.query().nearest_to([1, 2]).nearest_to_text("hello").explain_plan(True)
+        ...     plan = await table.query().nearest_to([1.0, 2.0]).nearest_to_text("hello").explain_plan(True)
         ...     print(plan)
         >>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
         Vector Search Plan:
@@ -3398,9 +3417,8 @@ class BaseQueryBuilder(object):
         >>> from lancedb import connect_async
         >>> async def doctest_example():
         ...     conn = await connect_async("./.lancedb")
-        ...     table = await conn.create_table("my_table", [{"vector": [99, 99]}])
-        ...     query = [100, 100]
-        ...     plan = await table.query().nearest_to([1, 2]).explain_plan(True)
+        ...     table = await conn.create_table("my_table", [{"vector": [99.0, 99.0]}])
+        ...     plan = await table.query().nearest_to([1.0, 2.0]).explain_plan(True)
         ...     print(plan)
         >>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
         ProjectionExec: expr=[vector@0 as vector, _distance@2 as _distance]
@@ -3409,6 +3427,7 @@ class BaseQueryBuilder(object):
               SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
                 KNNVectorDistance: metric=l2
                   LanceRead: uri=..., projection=[vector], ...
+        <BLANKLINE>
 
         Parameters
         ----------

python/python/lancedb/remote/db.py

@@ -23,6 +23,13 @@ import pyarrow as pa
 from ..common import DATA
 from ..db import DBConnection, LOOP
 from ..embeddings import EmbeddingFunctionConfig
+from lance_namespace import (
+    CreateNamespaceResponse,
+    DescribeNamespaceResponse,
+    DropNamespaceResponse,
+    ListNamespacesResponse,
+    ListTablesResponse,
+)
 from ..pydantic import LanceModel
 from ..table import Table
 from ..util import validate_table_name
@@ -104,10 +111,10 @@ class RemoteDBConnection(DBConnection):
     @override
     def list_namespaces(
         self,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
-        limit: int = 10,
-    ) -> Iterable[str]:
+        limit: Optional[int] = None,
+    ) -> ListNamespacesResponse:
         """List immediate child namespace names in the given namespace.
 
         Parameters
@@ -116,15 +123,18 @@ class RemoteDBConnection(DBConnection):
             The parent namespace to list namespaces in.
             None or empty list represents root namespace.
         page_token: str, optional
-            The token to use for pagination. If not present, start from the beginning.
-        limit: int, default 10
-            The size of the page to return.
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
 
         Returns
         -------
-        Iterable of str
-            List of immediate child namespace names
+        ListNamespacesResponse
+            Response containing namespace names and optional page_token for pagination.
         """
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.list_namespaces(
                 namespace=namespace, page_token=page_token, limit=limit
@@ -132,26 +142,111 @@ class RemoteDBConnection(DBConnection):
         )
 
     @override
-    def create_namespace(self, namespace: List[str]) -> None:
+    def create_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        properties: Optional[Dict[str, str]] = None,
+    ) -> CreateNamespaceResponse:
         """Create a new namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to create.
+        mode: str, optional
+            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
+            or "overwrite" (replace if exists). Case insensitive.
+        properties: Dict[str, str], optional
+            Properties to set on the namespace.
+
+        Returns
+        -------
+        CreateNamespaceResponse
+            Response containing the properties of the created namespace.
         """
-        LOOP.run(self._conn.create_namespace(namespace=namespace))
+        return LOOP.run(
+            self._conn.create_namespace(
+                namespace=namespace, mode=mode, properties=properties
+            )
+        )
 
     @override
-    def drop_namespace(self, namespace: List[str]) -> None:
+    def drop_namespace(
+        self,
+        namespace: List[str],
+        mode: Optional[str] = None,
+        behavior: Optional[str] = None,
+    ) -> DropNamespaceResponse:
         """Drop a namespace.
 
         Parameters
         ----------
         namespace: List[str]
             The namespace identifier to drop.
+        mode: str, optional
+            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
+        behavior: str, optional
+            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
+            Case insensitive.
+
+        Returns
+        -------
+        DropNamespaceResponse
+            Response containing properties and transaction_id if applicable.
         """
-        return LOOP.run(self._conn.drop_namespace(namespace=namespace))
+        return LOOP.run(
+            self._conn.drop_namespace(namespace=namespace, mode=mode, behavior=behavior)
+        )
+
+    @override
+    def describe_namespace(self, namespace: List[str]) -> DescribeNamespaceResponse:
+        """Describe a namespace.
+
+        Parameters
+        ----------
+        namespace: List[str]
+            The namespace identifier to describe.
+
+        Returns
+        -------
+        DescribeNamespaceResponse
+            Response containing the namespace properties.
+        """
+        return LOOP.run(self._conn.describe_namespace(namespace=namespace))
+
+    @override
+    def list_tables(
+        self,
+        namespace: Optional[List[str]] = None,
+        page_token: Optional[str] = None,
+        limit: Optional[int] = None,
+    ) -> ListTablesResponse:
+        """List all tables in this database with pagination support.
+
+        Parameters
+        ----------
+        namespace: List[str], optional
+            The namespace to list tables in.
+            None or empty list represents root namespace.
+        page_token: str, optional
+            Token for pagination. Use the token from a previous response
+            to get the next page of results.
+        limit: int, optional
+            The maximum number of results to return.
+
+        Returns
+        -------
+        ListTablesResponse
+            Response containing table names and optional page_token for pagination.
+        """
+        if namespace is None:
+            namespace = []
+        return LOOP.run(
+            self._conn.list_tables(
+                namespace=namespace, page_token=page_token, limit=limit
+            )
+        )
 
     @override
     def table_names(
@@ -159,10 +254,13 @@ class RemoteDBConnection(DBConnection):
         page_token: Optional[str] = None,
         limit: int = 10,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
     ) -> Iterable[str]:
         """List the names of all tables in the database.
 
+        .. deprecated::
+            Use :meth:`list_tables` instead, which provides proper pagination support.
+
         Parameters
         ----------
         namespace: List[str], default []
@@ -177,6 +275,15 @@ class RemoteDBConnection(DBConnection):
         -------
         An iterator of table names.
         """
+        import warnings
+
+        warnings.warn(
+            "table_names() is deprecated, use list_tables() instead",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.table_names(
                 namespace=namespace, start_after=page_token, limit=limit
@@ -188,7 +295,7 @@ class RemoteDBConnection(DBConnection):
         self,
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         index_cache_size: Optional[int] = None,
     ) -> Table:
@@ -208,6 +315,8 @@ class RemoteDBConnection(DBConnection):
         """
         from .table import RemoteTable
 
+        if namespace is None:
+            namespace = []
         if index_cache_size is not None:
             logging.info(
                 "index_cache_size is ignored in LanceDb Cloud"
@@ -222,7 +331,7 @@ class RemoteDBConnection(DBConnection):
         target_table_name: str,
         source_uri: str,
         *,
-        target_namespace: List[str] = [],
+        target_namespace: Optional[List[str]] = None,
         source_version: Optional[int] = None,
         source_tag: Optional[str] = None,
         is_shallow: bool = True,
@@ -252,6 +361,8 @@ class RemoteDBConnection(DBConnection):
         """
         from .table import RemoteTable
 
+        if target_namespace is None:
+            target_namespace = []
         table = LOOP.run(
             self._conn.clone_table(
                 target_table_name,
@@ -275,7 +386,7 @@ class RemoteDBConnection(DBConnection):
         mode: Optional[str] = None,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
     ) -> Table:
         """Create a [Table][lancedb.table.Table] in the database.
 
@@ -372,6 +483,8 @@ class RemoteDBConnection(DBConnection):
         LanceTable(table4)
 
         """
+        if namespace is None:
+            namespace = []
         validate_table_name(name)
         if embedding_functions is not None:
             logging.warning(
@@ -396,7 +509,7 @@ class RemoteDBConnection(DBConnection):
         return RemoteTable(table, self.db_name)
 
     @override
-    def drop_table(self, name: str, namespace: List[str] = []):
+    def drop_table(self, name: str, namespace: Optional[List[str]] = None):
         """Drop a table from the database.
 
         Parameters
@@ -407,6 +520,8 @@ class RemoteDBConnection(DBConnection):
             The namespace to drop the table from.
             None or empty list represents root namespace.
         """
+        if namespace is None:
+            namespace = []
         LOOP.run(self._conn.drop_table(name, namespace=namespace))
 
     @override
@@ -414,8 +529,8 @@ class RemoteDBConnection(DBConnection):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
-        new_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -426,6 +541,10 @@ class RemoteDBConnection(DBConnection):
         new_name: str
             The new name of the table.
         """
+        if cur_namespace is None:
+            cur_namespace = []
+        if new_namespace is None:
+            new_namespace = []
         LOOP.run(
             self._conn.rename_table(
                 cur_name,

python/python/lancedb/remote/table.py

@@ -18,7 +18,7 @@ from lancedb._lancedb import (
     UpdateResult,
 )
 from lancedb.embeddings.base import EmbeddingFunctionConfig
-from lancedb.index import FTS, BTree, Bitmap, HnswSq, IvfFlat, IvfPq, LabelList
+from lancedb.index import FTS, BTree, Bitmap, HnswSq, IvfFlat, IvfPq, IvfSq, LabelList
 from lancedb.remote.db import LOOP
 import pyarrow as pa
 
@@ -265,6 +265,8 @@ class RemoteTable(Table):
                 num_sub_vectors=num_sub_vectors,
                 num_bits=num_bits,
             )
+        elif index_type == "IVF_SQ":
+            config = IvfSq(distance_type=metric, num_partitions=num_partitions)
         elif index_type == "IVF_HNSW_PQ":
             raise ValueError(
                 "IVF_HNSW_PQ is not supported on LanceDB cloud."
@@ -277,7 +279,7 @@ class RemoteTable(Table):
         else:
             raise ValueError(
                 f"Unknown vector index type: {index_type}. Valid options are"
-                " 'IVF_FLAT', 'IVF_PQ', 'IVF_HNSW_PQ', 'IVF_HNSW_SQ'"
+                " 'IVF_FLAT', 'IVF_SQ', 'IVF_PQ', 'IVF_HNSW_PQ', 'IVF_HNSW_SQ'"
             )
 
         LOOP.run(
@@ -652,6 +654,17 @@ class RemoteTable(Table):
             "migrate_v2_manifest_paths() is not supported on the LanceDB Cloud"
         )
 
+    def head(self, n=5) -> pa.Table:
+        """
+        Return the first `n` rows of the table.
+
+        Parameters
+        ----------
+        n: int, default 5
+            The number of rows to return.
+        """
+        return LOOP.run(self._table.query().limit(n).to_arrow())
+
 
 def add_index(tbl: pa.Table, i: int) -> pa.Table:
     return tbl.add_column(

python/python/lancedb/table.py

@@ -44,7 +44,18 @@ import numpy as np
 
 from .common import DATA, VEC, VECTOR_COLUMN_NAME
 from .embeddings import EmbeddingFunctionConfig, EmbeddingFunctionRegistry
-from .index import BTree, IvfFlat, IvfPq, Bitmap, IvfRq, LabelList, HnswPq, HnswSq, FTS
+from .index import (
+    BTree,
+    IvfFlat,
+    IvfPq,
+    IvfSq,
+    Bitmap,
+    IvfRq,
+    LabelList,
+    HnswPq,
+    HnswSq,
+    FTS,
+)
 from .merge import LanceMergeInsertBuilder
 from .pydantic import LanceModel, model_to_dict
 from .query import (
@@ -178,7 +189,7 @@ def _into_pyarrow_reader(
             f"Unknown data type {type(data)}. "
             "Supported types: list of dicts, pandas DataFrame, polars DataFrame, "
             "pyarrow Table/RecordBatch, or Pydantic models. "
-            "See https://lancedb.github.io/lancedb/guides/tables/ for examples."
+            "See https://lancedb.com/docs/tables/ for examples."
         )
 
 
@@ -1018,7 +1029,7 @@ class Table(ABC):
         ...      .when_not_matched_insert_all() \\
         ...      .execute(new_data)
         >>> res
-        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0)
+        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1)
         >>> # The order of new rows is non-deterministic since we use
         >>> # a hash-join as part of this operation and so we sort here
         >>> table.to_arrow().sort_by("a").to_pandas()
@@ -1708,15 +1719,18 @@ class LanceTable(Table):
         connection: "LanceDBConnection",
         name: str,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
         location: Optional[str] = None,
         _async: AsyncTable = None,
     ):
+        if namespace is None:
+            namespace = []
         self._conn = connection
         self._namespace = namespace
+        self._location = location  # Store location for use in _dataset_path
         if _async is not None:
             self._table = _async
         else:
@@ -1765,12 +1779,14 @@ class LanceTable(Table):
         db,
         name,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
         location: Optional[str] = None,
     ):
+        if namespace is None:
+            namespace = []
         tbl = cls(
             db,
             name,
@@ -1794,6 +1810,10 @@ class LanceTable(Table):
     @cached_property
     def _dataset_path(self) -> str:
         # Cacheable since it's deterministic
+        # If table was opened with explicit location (e.g., from namespace),
+        # use that location directly instead of constructing from base URI
+        if self._location is not None:
+            return self._location
         return _table_path(self._conn.uri, self.name)
 
     def to_lance(self, **kwargs) -> lance.LanceDataset:
@@ -2045,7 +2065,7 @@ class LanceTable(Table):
         index_cache_size: Optional[int] = None,
         num_bits: int = 8,
         index_type: Literal[
-            "IVF_FLAT", "IVF_PQ", "IVF_RQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
+            "IVF_FLAT", "IVF_SQ", "IVF_PQ", "IVF_RQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
         ] = "IVF_PQ",
         max_iterations: int = 50,
         sample_rate: int = 256,
@@ -2083,6 +2103,14 @@ class LanceTable(Table):
                 sample_rate=sample_rate,
                 target_partition_size=target_partition_size,
             )
+        elif index_type == "IVF_SQ":
+            config = IvfSq(
+                distance_type=metric,
+                num_partitions=num_partitions,
+                max_iterations=max_iterations,
+                sample_rate=sample_rate,
+                target_partition_size=target_partition_size,
+            )
         elif index_type == "IVF_PQ":
             config = IvfPq(
                 distance_type=metric,
@@ -2618,7 +2646,7 @@ class LanceTable(Table):
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         storage_options: Optional[Dict[str, str | bool]] = None,
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         data_storage_version: Optional[str] = None,
@@ -2678,9 +2706,12 @@ class LanceTable(Table):
             Deprecated.  Set `storage_options` when connecting to the database and set
             `new_table_enable_v2_manifest_paths` in the options.
         """
+        if namespace is None:
+            namespace = []
         self = cls.__new__(cls)
         self._conn = db
         self._namespace = namespace
+        self._location = location
 
         if data_storage_version is not None:
             warnings.warn(
@@ -3444,11 +3475,22 @@ class AsyncTable:
         if config is not None:
             if not isinstance(
                 config,
-                (IvfFlat, IvfPq, IvfRq, HnswPq, HnswSq, BTree, Bitmap, LabelList, FTS),
+                (
+                    IvfFlat,
+                    IvfSq,
+                    IvfPq,
+                    IvfRq,
+                    HnswPq,
+                    HnswSq,
+                    BTree,
+                    Bitmap,
+                    LabelList,
+                    FTS,
+                ),
             ):
                 raise TypeError(
-                    "config must be an instance of IvfPq, IvfRq, HnswPq, HnswSq, BTree,"
-                    " Bitmap, LabelList, or FTS, but got " + str(type(config))
+                    "config must be an instance of IvfSq, IvfPq, IvfRq, HnswPq, HnswSq,"
+                    " BTree, Bitmap, LabelList, or FTS, but got " + str(type(config))
                 )
         try:
             await self._inner.create_index(
@@ -3622,7 +3664,7 @@ class AsyncTable:
         ...      .when_not_matched_insert_all() \\
         ...      .execute(new_data)
         >>> res
-        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0)
+        MergeResult(version=2, num_updated_rows=2, num_inserted_rows=1, num_deleted_rows=0, num_attempts=1)
         >>> # The order of new rows is non-deterministic since we use
         >>> # a hash-join as part of this operation and so we sort here
         >>> table.to_arrow().sort_by("a").to_pandas()

python/python/lancedb/types.py

@@ -18,12 +18,20 @@ AddMode = Literal["append", "overwrite"]
 CreateMode = Literal["create", "overwrite"]
 
 # Index type literals
-VectorIndexType = Literal["IVF_FLAT", "IVF_PQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ", "IVF_RQ"]
+VectorIndexType = Literal[
+    "IVF_FLAT",
+    "IVF_SQ",
+    "IVF_PQ",
+    "IVF_HNSW_SQ",
+    "IVF_HNSW_PQ",
+    "IVF_RQ",
+]
 ScalarIndexType = Literal["BTREE", "BITMAP", "LABEL_LIST"]
 IndexType = Literal[
     "IVF_PQ",
     "IVF_HNSW_PQ",
     "IVF_HNSW_SQ",
+    "IVF_SQ",
     "FTS",
     "BTREE",
     "BITMAP",

python/python/tests/test_db.py

@@ -441,6 +441,150 @@ async def test_create_table_v2_manifest_paths_async(tmp_path):
         assert re.match(r"\d{20}\.manifest", manifest)
 
 
+@pytest.mark.asyncio
+async def test_create_table_stable_row_ids_via_storage_options(tmp_path):
+    """Test stable_row_ids via storage_options at connect time."""
+    import lance
+
+    # Connect with stable row IDs enabled as default for new tables
+    db_with = await lancedb.connect_async(
+        tmp_path, storage_options={"new_table_enable_stable_row_ids": "true"}
+    )
+    # Connect without stable row IDs (default)
+    db_without = await lancedb.connect_async(
+        tmp_path, storage_options={"new_table_enable_stable_row_ids": "false"}
+    )
+
+    # Create table using connection with stable row IDs enabled
+    await db_with.create_table(
+        "with_stable_via_opts",
+        data=[{"id": i} for i in range(10)],
+    )
+    lance_ds_with = lance.dataset(tmp_path / "with_stable_via_opts.lance")
+    fragments_with = lance_ds_with.get_fragments()
+    assert len(fragments_with) > 0
+    assert fragments_with[0].metadata.row_id_meta is not None
+
+    # Create table using connection without stable row IDs
+    await db_without.create_table(
+        "without_stable_via_opts",
+        data=[{"id": i} for i in range(10)],
+    )
+    lance_ds_without = lance.dataset(tmp_path / "without_stable_via_opts.lance")
+    fragments_without = lance_ds_without.get_fragments()
+    assert len(fragments_without) > 0
+    assert fragments_without[0].metadata.row_id_meta is None
+
+
+def test_create_table_stable_row_ids_via_storage_options_sync(tmp_path):
+    """Test that enable_stable_row_ids can be set via storage_options (sync API)."""
+    # Connect with stable row IDs enabled as default for new tables
+    db_with = lancedb.connect(
+        tmp_path, storage_options={"new_table_enable_stable_row_ids": "true"}
+    )
+    # Connect without stable row IDs (default)
+    db_without = lancedb.connect(
+        tmp_path, storage_options={"new_table_enable_stable_row_ids": "false"}
+    )
+
+    # Create table using connection with stable row IDs enabled
+    tbl_with = db_with.create_table(
+        "with_stable_sync",
+        data=[{"id": i} for i in range(10)],
+    )
+    lance_ds_with = tbl_with.to_lance()
+    fragments_with = lance_ds_with.get_fragments()
+    assert len(fragments_with) > 0
+    assert fragments_with[0].metadata.row_id_meta is not None
+
+    # Create table using connection without stable row IDs
+    tbl_without = db_without.create_table(
+        "without_stable_sync",
+        data=[{"id": i} for i in range(10)],
+    )
+    lance_ds_without = tbl_without.to_lance()
+    fragments_without = lance_ds_without.get_fragments()
+    assert len(fragments_without) > 0
+    assert fragments_without[0].metadata.row_id_meta is None
+
+
+@pytest.mark.asyncio
+async def test_create_table_stable_row_ids_table_level_override(tmp_path):
+    """Test that stable_row_ids can be enabled/disabled at create_table level."""
+    import lance
+
+    # Connect without any stable row ID setting
+    db_default = await lancedb.connect_async(tmp_path)
+
+    # Connect with stable row IDs enabled at connection level
+    db_with_stable = await lancedb.connect_async(
+        tmp_path, storage_options={"new_table_enable_stable_row_ids": "true"}
+    )
+
+    # Case 1: No connection setting, enable at table level
+    await db_default.create_table(
+        "table_level_enabled",
+        data=[{"id": i} for i in range(10)],
+        storage_options={"new_table_enable_stable_row_ids": "true"},
+    )
+    lance_ds = lance.dataset(tmp_path / "table_level_enabled.lance")
+    fragments = lance_ds.get_fragments()
+    assert len(fragments) > 0
+    assert fragments[0].metadata.row_id_meta is not None, (
+        "Table should have stable row IDs when enabled at table level"
+    )
+
+    # Case 2: Connection has stable row IDs, override with false at table level
+    await db_with_stable.create_table(
+        "table_level_disabled",
+        data=[{"id": i} for i in range(10)],
+        storage_options={"new_table_enable_stable_row_ids": "false"},
+    )
+    lance_ds = lance.dataset(tmp_path / "table_level_disabled.lance")
+    fragments = lance_ds.get_fragments()
+    assert len(fragments) > 0
+    assert fragments[0].metadata.row_id_meta is None, (
+        "Table should NOT have stable row IDs when disabled at table level"
+    )
+
+
+def test_create_table_stable_row_ids_table_level_override_sync(tmp_path):
+    """Test that stable_row_ids can be enabled/disabled at create_table level (sync)."""
+    # Connect without any stable row ID setting
+    db_default = lancedb.connect(tmp_path)
+
+    # Connect with stable row IDs enabled at connection level
+    db_with_stable = lancedb.connect(
+        tmp_path, storage_options={"new_table_enable_stable_row_ids": "true"}
+    )
+
+    # Case 1: No connection setting, enable at table level
+    tbl = db_default.create_table(
+        "table_level_enabled_sync",
+        data=[{"id": i} for i in range(10)],
+        storage_options={"new_table_enable_stable_row_ids": "true"},
+    )
+    lance_ds = tbl.to_lance()
+    fragments = lance_ds.get_fragments()
+    assert len(fragments) > 0
+    assert fragments[0].metadata.row_id_meta is not None, (
+        "Table should have stable row IDs when enabled at table level"
+    )
+
+    # Case 2: Connection has stable row IDs, override with false at table level
+    tbl = db_with_stable.create_table(
+        "table_level_disabled_sync",
+        data=[{"id": i} for i in range(10)],
+        storage_options={"new_table_enable_stable_row_ids": "false"},
+    )
+    lance_ds = tbl.to_lance()
+    fragments = lance_ds.get_fragments()
+    assert len(fragments) > 0
+    assert fragments[0].metadata.row_id_meta is None, (
+        "Table should NOT have stable row IDs when disabled at table level"
+    )
+
+
 def test_open_table_sync(tmp_db: lancedb.DBConnection):
     tmp_db.create_table("test", data=[{"id": 0}])
     assert tmp_db.open_table("test").count_rows() == 1
@@ -748,7 +892,7 @@ def test_local_namespace_operations(tmp_path):
     db = lancedb.connect(tmp_path)
 
     # Test list_namespaces returns empty list for root namespace
-    namespaces = list(db.list_namespaces())
+    namespaces = db.list_namespaces().namespaces
     assert namespaces == []
 
     # Test list_namespaces with non-empty namespace raises NotImplementedError
@@ -756,7 +900,7 @@ def test_local_namespace_operations(tmp_path):
         NotImplementedError,
         match="Namespace operations are not supported for listing database",
     ):
-        list(db.list_namespaces(namespace=["test"]))
+        db.list_namespaces(namespace=["test"])
 
 
 def test_local_create_namespace_not_supported(tmp_path):

python/python/tests/test_fts.py

@@ -32,6 +32,7 @@ import numpy as np
 import pyarrow as pa
 import pandas as pd
 import pytest
+import pytest_asyncio
 from utils import exception_output
 
 pytest.importorskip("lancedb.fts")
@@ -90,7 +91,7 @@ def table(tmp_path) -> ldb.table.LanceTable:
     return table
 
 
-@pytest.fixture
+@pytest_asyncio.fixture
 async def async_table(tmp_path) -> ldb.table.AsyncTable:
     # Use local random state to avoid affecting other tests
     rng = np.random.RandomState(42)
@@ -253,7 +254,7 @@ def test_search_fts(table, use_tantivy):
 
 @pytest.mark.asyncio
 async def test_fts_select_async(async_table):
-    tbl = await async_table
+    tbl = async_table
     await tbl.create_index("text", config=FTS())
     await tbl.create_index("text2", config=FTS())
     results = (
@@ -324,11 +325,18 @@ def test_search_fts_phrase_query(table):
         pass
     table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
     results = table.search("puppy").limit(100).to_list()
+
+    # Test with quotation marks
     phrase_results = table.search('"puppy runs"').limit(100).to_list()
     assert len(results) > len(phrase_results)
     assert len(phrase_results) > 0
 
-    # Test with a query
+    # Test with .phrase_query()
+    phrase_results = table.search("puppy runs").phrase_query().limit(100).to_list()
+    assert len(results) > len(phrase_results)
+    assert len(phrase_results) > 0
+
+    # Test with PhraseQuery()
     phrase_results = (
         table.search(PhraseQuery("puppy runs", "text")).limit(100).to_list()
     )
@@ -338,7 +346,6 @@ def test_search_fts_phrase_query(table):
 
 @pytest.mark.asyncio
 async def test_search_fts_phrase_query_async(async_table):
-    async_table = await async_table
     await async_table.create_index("text", config=FTS(with_position=False))
     try:
         phrase_results = (
@@ -393,7 +400,6 @@ def test_search_fts_specify_column(table):
 
 @pytest.mark.asyncio
 async def test_search_fts_async(async_table):
-    async_table = await async_table
     await async_table.create_index("text", config=FTS())
     results = await async_table.query().nearest_to_text("puppy").limit(5).to_list()
     assert len(results) == 5
@@ -424,7 +430,6 @@ async def test_search_fts_async(async_table):
 
 @pytest.mark.asyncio
 async def test_search_fts_specify_column_async(async_table):
-    async_table = await async_table
     await async_table.create_index("text", config=FTS())
     await async_table.create_index("text2", config=FTS())
 

python/python/tests/test_index.py

@@ -12,6 +12,9 @@ from lancedb.index import (
     BTree,
     IvfFlat,
     IvfPq,
+    IvfSq,
+    IvfHnswPq,
+    IvfHnswSq,
     IvfRq,
     Bitmap,
     LabelList,
@@ -229,6 +232,35 @@ async def test_create_hnswsq_index(some_table: AsyncTable):
     assert len(indices) == 1
 
 
+@pytest.mark.asyncio
+async def test_create_hnswsq_alias_index(some_table: AsyncTable):
+    await some_table.create_index("vector", config=IvfHnswSq(num_partitions=5))
+    indices = await some_table.list_indices()
+    assert len(indices) == 1
+    assert indices[0].index_type in {"HnswSq", "IvfHnswSq"}
+
+
+@pytest.mark.asyncio
+async def test_create_hnswpq_alias_index(some_table: AsyncTable):
+    await some_table.create_index("vector", config=IvfHnswPq(num_partitions=5))
+    indices = await some_table.list_indices()
+    assert len(indices) == 1
+    assert indices[0].index_type in {"HnswPq", "IvfHnswPq"}
+
+
+@pytest.mark.asyncio
+async def test_create_ivfsq_index(some_table: AsyncTable):
+    await some_table.create_index("vector", config=IvfSq(num_partitions=10))
+    indices = await some_table.list_indices()
+    assert len(indices) == 1
+    assert indices[0].index_type == "IvfSq"
+    stats = await some_table.index_stats(indices[0].name)
+    assert stats.index_type == "IVF_SQ"
+    assert stats.distance_type == "l2"
+    assert stats.num_indexed_rows == await some_table.count_rows()
+    assert stats.num_unindexed_rows == 0
+
+
 @pytest.mark.asyncio
 async def test_create_index_with_binary_vectors(binary_table: AsyncTable):
     await binary_table.create_index(

python/python/tests/test_namespace.py

@@ -279,13 +279,13 @@ class TestNamespaceConnection:
         db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
 
         # Initially no namespaces
-        assert len(list(db.list_namespaces())) == 0
+        assert len(db.list_namespaces().namespaces) == 0
 
         # Create a namespace
         db.create_namespace(["test_namespace"])
 
         # Verify namespace exists
-        namespaces = list(db.list_namespaces())
+        namespaces = db.list_namespaces().namespaces
         assert "test_namespace" in namespaces
         assert len(namespaces) == 1
 
@@ -322,7 +322,7 @@ class TestNamespaceConnection:
         db.drop_namespace(["test_namespace"])
 
         # Verify namespace no longer exists
-        namespaces = list(db.list_namespaces())
+        namespaces = db.list_namespaces().namespaces
         assert len(namespaces) == 0
 
     def test_namespace_with_tables_cannot_be_dropped(self):
@@ -423,3 +423,218 @@ class TestNamespaceConnection:
         db.drop_table("same_name_table", namespace=["namespace_b"])
         db.drop_namespace(["namespace_a"])
         db.drop_namespace(["namespace_b"])
+
+
+@pytest.mark.asyncio
+class TestAsyncNamespaceConnection:
+    """Test async namespace-based LanceDB connection using DirectoryNamespace."""
+
+    def setup_method(self):
+        """Set up test fixtures."""
+        self.temp_dir = tempfile.mkdtemp()
+
+    def teardown_method(self):
+        """Clean up test fixtures."""
+        shutil.rmtree(self.temp_dir, ignore_errors=True)
+
+    async def test_connect_namespace_async(self):
+        """Test connecting to LanceDB through DirectoryNamespace asynchronously."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+
+        # Should be an AsyncLanceNamespaceDBConnection
+        assert isinstance(db, lancedb.AsyncLanceNamespaceDBConnection)
+
+        # Initially no tables in root
+        table_names = await db.table_names()
+        assert len(list(table_names)) == 0
+
+    async def test_create_table_async(self):
+        """Test creating a table asynchronously through namespace."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+
+        # Create a child namespace first
+        await db.create_namespace(["test_ns"])
+
+        # Define schema for empty table
+        schema = pa.schema(
+            [
+                pa.field("id", pa.int64()),
+                pa.field("vector", pa.list_(pa.float32(), 2)),
+                pa.field("text", pa.string()),
+            ]
+        )
+
+        # Create empty table in child namespace
+        table = await db.create_table(
+            "test_table", schema=schema, namespace=["test_ns"]
+        )
+        assert table is not None
+        assert isinstance(table, lancedb.AsyncTable)
+
+        # Table should appear in child namespace
+        table_names = await db.table_names(namespace=["test_ns"])
+        assert "test_table" in list(table_names)
+
+    async def test_open_table_async(self):
+        """Test opening an existing table asynchronously through namespace."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+
+        # Create a child namespace first
+        await db.create_namespace(["test_ns"])
+
+        # Create a table with schema in child namespace
+        schema = pa.schema(
+            [
+                pa.field("id", pa.int64()),
+                pa.field("vector", pa.list_(pa.float32(), 2)),
+            ]
+        )
+        await db.create_table("test_table", schema=schema, namespace=["test_ns"])
+
+        # Open the table
+        table = await db.open_table("test_table", namespace=["test_ns"])
+        assert table is not None
+        assert isinstance(table, lancedb.AsyncTable)
+
+        # Test write operation - add data to the table
+        test_data = [
+            {"id": 1, "vector": [1.0, 2.0]},
+            {"id": 2, "vector": [3.0, 4.0]},
+            {"id": 3, "vector": [5.0, 6.0]},
+        ]
+        await table.add(test_data)
+
+        # Test read operation - query the table
+        result = await table.to_arrow()
+        assert len(result) == 3
+        assert result.schema.field("id").type == pa.int64()
+        assert result.schema.field("vector").type == pa.list_(pa.float32(), 2)
+
+        # Verify data content
+        result_df = result.to_pandas()
+        assert result_df["id"].tolist() == [1, 2, 3]
+        assert [v.tolist() for v in result_df["vector"]] == [
+            [1.0, 2.0],
+            [3.0, 4.0],
+            [5.0, 6.0],
+        ]
+
+        # Test update operation
+        await table.update({"id": 20}, where="id = 2")
+        result = await table.to_arrow()
+        result_df = result.to_pandas().sort_values("id").reset_index(drop=True)
+        assert result_df["id"].tolist() == [1, 3, 20]
+
+        # Test delete operation
+        await table.delete("id = 1")
+        result = await table.to_arrow()
+        assert len(result) == 2
+        result_df = result.to_pandas().sort_values("id").reset_index(drop=True)
+        assert result_df["id"].tolist() == [3, 20]
+
+    async def test_drop_table_async(self):
+        """Test dropping a table asynchronously through namespace."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+
+        # Create a child namespace first
+        await db.create_namespace(["test_ns"])
+
+        # Create tables in child namespace
+        schema = pa.schema(
+            [
+                pa.field("id", pa.int64()),
+                pa.field("vector", pa.list_(pa.float32(), 2)),
+            ]
+        )
+        await db.create_table("table1", schema=schema, namespace=["test_ns"])
+        await db.create_table("table2", schema=schema, namespace=["test_ns"])
+
+        # Verify both tables exist in child namespace
+        table_names = list(await db.table_names(namespace=["test_ns"]))
+        assert "table1" in table_names
+        assert "table2" in table_names
+        assert len(table_names) == 2
+
+        # Drop one table
+        await db.drop_table("table1", namespace=["test_ns"])
+
+        # Verify only table2 remains
+        table_names = list(await db.table_names(namespace=["test_ns"]))
+        assert "table1" not in table_names
+        assert "table2" in table_names
+        assert len(table_names) == 1
+
+    async def test_namespace_operations_async(self):
+        """Test namespace management operations asynchronously."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+
+        # Initially no namespaces
+        namespaces = await db.list_namespaces()
+        assert len(namespaces.namespaces) == 0
+
+        # Create a namespace
+        await db.create_namespace(["test_namespace"])
+
+        # Verify namespace exists
+        namespaces = (await db.list_namespaces()).namespaces
+        assert "test_namespace" in namespaces
+        assert len(namespaces) == 1
+
+        # Create table in namespace
+        schema = pa.schema(
+            [
+                pa.field("id", pa.int64()),
+                pa.field("vector", pa.list_(pa.float32(), 2)),
+            ]
+        )
+        table = await db.create_table(
+            "test_table", schema=schema, namespace=["test_namespace"]
+        )
+        assert table is not None
+
+        # Verify table exists in namespace
+        tables_in_namespace = list(await db.table_names(namespace=["test_namespace"]))
+        assert "test_table" in tables_in_namespace
+        assert len(tables_in_namespace) == 1
+
+        # Drop table from namespace
+        await db.drop_table("test_table", namespace=["test_namespace"])
+
+        # Verify table no longer exists in namespace
+        tables_in_namespace = list(await db.table_names(namespace=["test_namespace"]))
+        assert len(tables_in_namespace) == 0
+
+        # Drop namespace
+        await db.drop_namespace(["test_namespace"])
+
+        # Verify namespace no longer exists
+        namespaces = (await db.list_namespaces()).namespaces
+        assert len(namespaces) == 0
+
+    async def test_drop_all_tables_async(self):
+        """Test dropping all tables asynchronously through namespace."""
+        db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
+
+        # Create a child namespace first
+        await db.create_namespace(["test_ns"])
+
+        # Create multiple tables in child namespace
+        schema = pa.schema(
+            [
+                pa.field("id", pa.int64()),
+                pa.field("vector", pa.list_(pa.float32(), 2)),
+            ]
+        )
+        for i in range(3):
+            await db.create_table(f"table{i}", schema=schema, namespace=["test_ns"])
+
+        # Verify tables exist in child namespace
+        table_names = await db.table_names(namespace=["test_ns"])
+        assert len(list(table_names)) == 3
+
+        # Drop all tables in child namespace
+        await db.drop_all_tables(namespace=["test_ns"])
+
+        # Verify all tables are gone from child namespace
+        table_names = await db.table_names(namespace=["test_ns"])
+        assert len(list(table_names)) == 0

python/python/tests/test_pydantic.py

@@ -412,3 +412,50 @@ def test_multi_vector_in_lance_model():
 
     t = TestModel(id=1)
     assert t.vectors == [[0.0] * 16]
+
+
+def test_aliases_in_lance_model(mem_db):
+    data = [
+        {"vector": [3.1, 4.1], "item": "foo", "price": 10.0},
+        {"vector": [5.9, 6.5], "item": "bar", "price": 20.0},
+    ]
+    tbl = mem_db.create_table("items", data=data)
+
+    class TestModel(LanceModel):
+        name: str = Field(alias="item")
+        price: float
+        distance: float = Field(alias="_distance")
+
+    model = (
+        tbl.search([5.9, 6.5])
+        .distance_type("cosine")
+        .limit(1)
+        .to_pydantic(TestModel)[0]
+    )
+    assert hasattr(model, "name")
+    assert hasattr(model, "distance")
+    assert model.distance < 0.01
+
+
+@pytest.mark.asyncio
+async def test_aliases_in_lance_model_async(mem_db_async):
+    data = [
+        {"vector": [8.3, 2.5], "item": "foo", "price": 12.0},
+        {"vector": [7.7, 3.9], "item": "bar", "price": 11.2},
+    ]
+    tbl = await mem_db_async.create_table("items", data=data)
+
+    class TestModel(LanceModel):
+        name: str = Field(alias="item")
+        price: float
+        distance: float = Field(alias="_distance")
+
+    model = (
+        await tbl.vector_search([7.7, 3.9])
+        .distance_type("cosine")
+        .limit(1)
+        .to_pydantic(TestModel)
+    )[0]
+    assert hasattr(model, "name")
+    assert hasattr(model, "distance")
+    assert model.distance < 0.01

python/python/tests/test_remote_db.py

@@ -546,6 +546,22 @@ def query_test_table(query_handler, *, server_version=Version("0.1.0")):
         yield table
 
 
+def test_head():
+    def handler(body):
+        assert body == {
+            "k": 5,
+            "prefilter": True,
+            "vector": [],
+            "version": None,
+        }
+
+        return pa.table({"id": [1, 2, 3]})
+
+    with query_test_table(handler) as table:
+        data = table.head(5)
+        assert data == pa.table({"id": [1, 2, 3]})
+
+
 def test_query_sync_minimal():
     def handler(body):
         assert body == {

python/python/tests/test_table.py

@@ -1487,7 +1487,7 @@ def setup_hybrid_search_table(db: DBConnection, embedding_func):
     table.add([{"text": p} for p in phrases])
 
     # Create a fts index
-    table.create_fts_index("text")
+    table.create_fts_index("text", with_position=True)
 
     return table, MyTable, emb
 

python/src/connection.rs

@@ -10,8 +10,9 @@ use lancedb::{
 };
 use pyo3::{
     exceptions::{PyRuntimeError, PyValueError},
-    pyclass, pyfunction, pymethods, Bound, FromPyObject, Py, PyAny, PyObject, PyRef, PyResult,
-    Python,
+    pyclass, pyfunction, pymethods,
+    types::{PyDict, PyDictMethods},
+    Bound, FromPyObject, Py, PyAny, PyObject, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
@@ -292,40 +293,155 @@ impl Connection {
         limit: Option<u32>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            use lancedb::database::ListNamespacesRequest;
+        let py = self_.py();
+        future_into_py(py, async move {
+            use lance_namespace::models::ListNamespacesRequest;
             let request = ListNamespacesRequest {
-                namespace,
+                id: if namespace.is_empty() {
+                    None
+                } else {
+                    Some(namespace)
+                },
                 page_token,
-                limit,
+                limit: limit.map(|l| l as i32),
             };
-            inner.list_namespaces(request).await.infer_error()
+            let response = inner.list_namespaces(request).await.infer_error()?;
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+                let dict = PyDict::new(py);
+                dict.set_item("namespaces", response.namespaces)?;
+                dict.set_item("page_token", response.page_token)?;
+                Ok(dict.unbind())
+            })
         })
     }
 
-    #[pyo3(signature = (namespace,))]
+    #[pyo3(signature = (namespace, mode=None, properties=None))]
     pub fn create_namespace(
         self_: PyRef<'_, Self>,
         namespace: Vec<String>,
+        mode: Option<String>,
+        properties: Option<std::collections::HashMap<String, String>>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            use lancedb::database::CreateNamespaceRequest;
-            let request = CreateNamespaceRequest { namespace };
-            inner.create_namespace(request).await.infer_error()
+        let py = self_.py();
+        future_into_py(py, async move {
+            use lance_namespace::models::{create_namespace_request, CreateNamespaceRequest};
+            let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
+                "create" => Some(create_namespace_request::Mode::Create),
+                "exist_ok" => Some(create_namespace_request::Mode::ExistOk),
+                "overwrite" => Some(create_namespace_request::Mode::Overwrite),
+                _ => None,
+            });
+            let request = CreateNamespaceRequest {
+                id: if namespace.is_empty() {
+                    None
+                } else {
+                    Some(namespace)
+                },
+                mode: mode_enum,
+                properties,
+            };
+            let response = inner.create_namespace(request).await.infer_error()?;
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+                let dict = PyDict::new(py);
+                dict.set_item("properties", response.properties)?;
+                Ok(dict.unbind())
+            })
+        })
+    }
+
+    #[pyo3(signature = (namespace, mode=None, behavior=None))]
+    pub fn drop_namespace(
+        self_: PyRef<'_, Self>,
+        namespace: Vec<String>,
+        mode: Option<String>,
+        behavior: Option<String>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        let py = self_.py();
+        future_into_py(py, async move {
+            use lance_namespace::models::{drop_namespace_request, DropNamespaceRequest};
+            let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
+                "SKIP" => Some(drop_namespace_request::Mode::Skip),
+                "FAIL" => Some(drop_namespace_request::Mode::Fail),
+                _ => None,
+            });
+            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
+                "RESTRICT" => Some(drop_namespace_request::Behavior::Restrict),
+                "CASCADE" => Some(drop_namespace_request::Behavior::Cascade),
+                _ => None,
+            });
+            let request = DropNamespaceRequest {
+                id: if namespace.is_empty() {
+                    None
+                } else {
+                    Some(namespace)
+                },
+                mode: mode_enum,
+                behavior: behavior_enum,
+            };
+            let response = inner.drop_namespace(request).await.infer_error()?;
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+                let dict = PyDict::new(py);
+                dict.set_item("properties", response.properties)?;
+                dict.set_item("transaction_id", response.transaction_id)?;
+                Ok(dict.unbind())
+            })
         })
     }
 
     #[pyo3(signature = (namespace,))]
-    pub fn drop_namespace(
+    pub fn describe_namespace(
         self_: PyRef<'_, Self>,
         namespace: Vec<String>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            use lancedb::database::DropNamespaceRequest;
-            let request = DropNamespaceRequest { namespace };
-            inner.drop_namespace(request).await.infer_error()
+        let py = self_.py();
+        future_into_py(py, async move {
+            use lance_namespace::models::DescribeNamespaceRequest;
+            let request = DescribeNamespaceRequest {
+                id: if namespace.is_empty() {
+                    None
+                } else {
+                    Some(namespace)
+                },
+            };
+            let response = inner.describe_namespace(request).await.infer_error()?;
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+                let dict = PyDict::new(py);
+                dict.set_item("properties", response.properties)?;
+                Ok(dict.unbind())
+            })
+        })
+    }
+
+    #[pyo3(signature = (namespace=vec![], page_token=None, limit=None))]
+    pub fn list_tables(
+        self_: PyRef<'_, Self>,
+        namespace: Vec<String>,
+        page_token: Option<String>,
+        limit: Option<u32>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        let py = self_.py();
+        future_into_py(py, async move {
+            use lance_namespace::models::ListTablesRequest;
+            let request = ListTablesRequest {
+                id: if namespace.is_empty() {
+                    None
+                } else {
+                    Some(namespace)
+                },
+                page_token,
+                limit: limit.map(|l| l as i32),
+            };
+            let response = inner.list_tables(request).await.infer_error()?;
+            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
+                let dict = PyDict::new(py);
+                dict.set_item("tables", response.tables)?;
+                dict.set_item("page_token", response.page_token)?;
+                Ok(dict.unbind())
+            })
         })
     }
 }

python/src/index.rs

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use lancedb::index::vector::{IvfFlatIndexBuilder, IvfRqIndexBuilder};
+use lancedb::index::vector::{IvfFlatIndexBuilder, IvfRqIndexBuilder, IvfSqIndexBuilder};
 use lancedb::index::{
     scalar::{BTreeIndexBuilder, FtsIndexBuilder},
     vector::{IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder},
@@ -87,6 +87,21 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                 }
                 Ok(LanceDbIndex::IvfPq(ivf_pq_builder))
             },
+            "IvfSq" => {
+                let params = source.extract::<IvfSqParams>()?;
+                let distance_type = parse_distance_type(params.distance_type)?;
+                let mut ivf_sq_builder = IvfSqIndexBuilder::default()
+                    .distance_type(distance_type)
+                    .max_iterations(params.max_iterations)
+                    .sample_rate(params.sample_rate);
+                if let Some(num_partitions) = params.num_partitions {
+                    ivf_sq_builder = ivf_sq_builder.num_partitions(num_partitions);
+                }
+                if let Some(target_partition_size) = params.target_partition_size {
+                    ivf_sq_builder = ivf_sq_builder.target_partition_size(target_partition_size);
+                }
+                Ok(LanceDbIndex::IvfSq(ivf_sq_builder))
+            },
             "IvfRq" => {
                 let params = source.extract::<IvfRqParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -142,7 +157,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                 Ok(LanceDbIndex::IvfHnswSq(hnsw_sq_builder))
             },
             not_supported => Err(PyValueError::new_err(format!(
-                "Invalid index type '{}'.  Must be one of BTree, Bitmap, LabelList, FTS, IvfPq, IvfHnswPq, or IvfHnswSq",
+                "Invalid index type '{}'.  Must be one of BTree, Bitmap, LabelList, FTS, IvfPq, IvfSq, IvfHnswPq, or IvfHnswSq",
                 not_supported
             ))),
         }
@@ -186,6 +201,15 @@ struct IvfPqParams {
     target_partition_size: Option<u32>,
 }
 
+#[derive(FromPyObject)]
+struct IvfSqParams {
+    distance_type: String,
+    num_partitions: Option<u32>,
+    max_iterations: u32,
+    sample_rate: u32,
+    target_partition_size: Option<u32>,
+}
+
 #[derive(FromPyObject)]
 struct IvfRqParams {
     distance_type: String,

python/src/query.rs

@@ -690,7 +690,7 @@ impl FTSQuery {
     }
 
     pub fn get_query(&self) -> String {
-        self.fts_query.query.query().to_owned()
+        self.fts_query.query.query().clone()
     }
 
     pub fn to_query_request(&self) -> PyQueryRequest {

python/src/table.rs

@@ -134,17 +134,19 @@ pub struct MergeResult {
     pub num_updated_rows: u64,
     pub num_inserted_rows: u64,
     pub num_deleted_rows: u64,
+    pub num_attempts: u32,
 }
 
 #[pymethods]
 impl MergeResult {
     pub fn __repr__(&self) -> String {
         format!(
-            "MergeResult(version={}, num_updated_rows={}, num_inserted_rows={}, num_deleted_rows={})",
+            "MergeResult(version={}, num_updated_rows={}, num_inserted_rows={}, num_deleted_rows={}, num_attempts={})",
             self.version,
             self.num_updated_rows,
             self.num_inserted_rows,
-            self.num_deleted_rows
+            self.num_deleted_rows,
+            self.num_attempts
         )
     }
 }
@@ -156,6 +158,7 @@ impl From<lancedb::table::MergeResult> for MergeResult {
             num_updated_rows: result.num_updated_rows,
             num_inserted_rows: result.num_inserted_rows,
             num_deleted_rows: result.num_deleted_rows,
+            num_attempts: result.num_attempts,
         }
     }
 }

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.22.4-beta.0"
+version = "0.22.4-beta.3"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -105,12 +105,12 @@ test-log = "0.2"
 
 [features]
 default = ["aws", "gcs", "azure", "dynamodb", "oss"]
-aws = ["lance/aws", "lance-io/aws"]
-oss = ["lance/oss", "lance-io/oss"]
-gcs = ["lance/gcp", "lance-io/gcp"]
-azure = ["lance/azure", "lance-io/azure"]
+aws = ["lance/aws", "lance-io/aws", "lance-namespace-impls/dir-aws"]
+oss = ["lance/oss", "lance-io/oss", "lance-namespace-impls/dir-oss"]
+gcs = ["lance/gcp", "lance-io/gcp", "lance-namespace-impls/dir-gcp"]
+azure = ["lance/azure", "lance-io/azure", "lance-namespace-impls/dir-azure"]
 dynamodb = ["lance/dynamodb", "aws"]
-remote = ["dep:reqwest", "dep:http"]
+remote = ["dep:reqwest", "dep:http", "lance-namespace-impls/rest"]
 fp16kernels = ["lance-linalg/fp16kernels"]
 s3-test = []
 bedrock = ["dep:aws-sdk-bedrockruntime"]

rust/lancedb/Makefile

@@ -9,11 +9,11 @@ all-tests: feature-tests remote-tests
 # the environment.
 feature-tests:
 	../../ci/run_with_docker_compose.sh \
-		cargo test --all-features --tests --locked --examples
+		cargo test --all-features --tests --locked --examples $(CARGO_ARGS)
 .PHONY: feature-tests
 
 # Run tests against remote endpoints.
 remote-tests:
 	../../ci/run_with_test_connection.sh \
-		cargo test --features remote --locked
+		cargo test --features remote --locked $(CARGO_ARGS)
 .PHONY: remote-tests

rust/lancedb/src/connection.rs

@@ -9,6 +9,11 @@ use std::sync::Arc;
 use arrow_array::RecordBatchReader;
 use arrow_schema::{Field, SchemaRef};
 use lance::dataset::ReadParams;
+use lance_namespace::models::{
+    CreateNamespaceRequest, CreateNamespaceResponse, DescribeNamespaceRequest,
+    DescribeNamespaceResponse, DropNamespaceRequest, DropNamespaceResponse, ListNamespacesRequest,
+    ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+};
 #[cfg(feature = "aws")]
 use object_store::aws::AwsCredential;
 
@@ -17,9 +22,8 @@ use crate::database::listing::{
     ListingDatabase, OPT_NEW_TABLE_STORAGE_VERSION, OPT_NEW_TABLE_V2_MANIFEST_PATHS,
 };
 use crate::database::{
-    CloneTableRequest, CreateNamespaceRequest, CreateTableData, CreateTableMode,
-    CreateTableRequest, Database, DatabaseOptions, DropNamespaceRequest, ListNamespacesRequest,
-    OpenTableRequest, ReadConsistency, TableNamesRequest,
+    CloneTableRequest, CreateTableData, CreateTableMode, CreateTableRequest, Database,
+    DatabaseOptions, OpenTableRequest, ReadConsistency, TableNamesRequest,
 };
 use crate::embeddings::{
     EmbeddingDefinition, EmbeddingFunction, EmbeddingRegistry, MemoryRegistry, WithEmbeddings,
@@ -74,6 +78,7 @@ impl TableNamesBuilder {
     }
 
     /// Execute the table names operation
+    #[allow(deprecated)]
     pub async fn execute(self) -> Result<Vec<String>> {
         self.parent.clone().table_names(self.request).await
     }
@@ -239,7 +244,7 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         let store_options = self
             .request
@@ -259,7 +264,7 @@ impl<const HAS_DATA: bool> CreateTableBuilder<HAS_DATA> {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -408,6 +413,7 @@ impl OpenTableBuilder {
                 index_cache_size: None,
                 lance_read_params: None,
                 location: None,
+                namespace_client: None,
             },
             embedding_registry,
         }
@@ -442,7 +448,7 @@ impl OpenTableBuilder {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         let storage_options = self
             .request
@@ -461,7 +467,7 @@ impl OpenTableBuilder {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -767,20 +773,42 @@ impl Connection {
     }
 
     /// List immediate child namespace names in the given namespace
-    pub async fn list_namespaces(&self, request: ListNamespacesRequest) -> Result<Vec<String>> {
+    pub async fn list_namespaces(
+        &self,
+        request: ListNamespacesRequest,
+    ) -> Result<ListNamespacesResponse> {
         self.internal.list_namespaces(request).await
     }
 
     /// Create a new namespace
-    pub async fn create_namespace(&self, request: CreateNamespaceRequest) -> Result<()> {
+    pub async fn create_namespace(
+        &self,
+        request: CreateNamespaceRequest,
+    ) -> Result<CreateNamespaceResponse> {
         self.internal.create_namespace(request).await
     }
 
     /// Drop a namespace
-    pub async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<()> {
+    pub async fn drop_namespace(
+        &self,
+        request: DropNamespaceRequest,
+    ) -> Result<DropNamespaceResponse> {
         self.internal.drop_namespace(request).await
     }
 
+    /// Describe a namespace
+    pub async fn describe_namespace(
+        &self,
+        request: DescribeNamespaceRequest,
+    ) -> Result<DescribeNamespaceResponse> {
+        self.internal.describe_namespace(request).await
+    }
+
+    /// List tables with pagination support
+    pub async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
+        self.internal.list_tables(request).await
+    }
+
     /// Get the in-memory embedding registry.
     /// It's important to note that the embedding registry is not persisted across connections.
     /// So if a table contains embeddings, you will need to make sure that you are using a connection that has the same embedding functions registered
@@ -959,7 +987,7 @@ impl ConnectBuilder {
 
     /// Set an option for the storage layer.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         self.request.options.insert(key.into(), value.into());
         self
@@ -967,7 +995,7 @@ impl ConnectBuilder {
 
     /// Set multiple options for the storage layer.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -1086,6 +1114,7 @@ pub struct ConnectNamespaceBuilder {
     read_consistency_interval: Option<std::time::Duration>,
     embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
     session: Option<Arc<lance::session::Session>>,
+    server_side_query_enabled: bool,
 }
 
 impl ConnectNamespaceBuilder {
@@ -1097,12 +1126,13 @@ impl ConnectNamespaceBuilder {
             read_consistency_interval: None,
             embedding_registry: None,
             session: None,
+            server_side_query_enabled: false,
         }
     }
 
     /// Set an option for the storage layer.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         self.storage_options.insert(key.into(), value.into());
         self
@@ -1110,7 +1140,7 @@ impl ConnectNamespaceBuilder {
 
     /// Set multiple options for the storage layer.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -1151,6 +1181,18 @@ impl ConnectNamespaceBuilder {
         self
     }
 
+    /// Enable server-side query execution.
+    ///
+    /// When enabled, queries will be executed on the namespace server instead of
+    /// locally. This can improve performance by reducing data transfer and
+    /// leveraging server-side compute resources.
+    ///
+    /// Default is `false` (queries executed locally).
+    pub fn server_side_query(mut self, enabled: bool) -> Self {
+        self.server_side_query_enabled = enabled;
+        self
+    }
+
     /// Execute the connection
     pub async fn execute(self) -> Result<Connection> {
         use crate::database::namespace::LanceNamespaceDatabase;
@@ -1162,6 +1204,7 @@ impl ConnectNamespaceBuilder {
                 self.storage_options,
                 self.read_consistency_interval,
                 self.session,
+                self.server_side_query_enabled,
             )
             .await?,
         );

rust/lancedb/src/database.rs

@@ -24,6 +24,12 @@ use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
 use futures::stream;
 use lance::dataset::ReadParams;
 use lance_datafusion::utils::StreamingWriteSource;
+use lance_namespace::models::{
+    CreateNamespaceRequest, CreateNamespaceResponse, DescribeNamespaceRequest,
+    DescribeNamespaceResponse, DropNamespaceRequest, DropNamespaceResponse, ListNamespacesRequest,
+    ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+};
+use lance_namespace::LanceNamespace;
 
 use crate::arrow::{SendableRecordBatchStream, SendableRecordBatchStreamExt};
 use crate::error::Result;
@@ -36,32 +42,7 @@ pub trait DatabaseOptions {
     fn serialize_into_map(&self, map: &mut HashMap<String, String>);
 }
 
-/// A request to list namespaces in the database
-#[derive(Clone, Debug, Default)]
-pub struct ListNamespacesRequest {
-    /// The parent namespace to list namespaces in. Empty list represents root namespace.
-    pub namespace: Vec<String>,
-    /// If present, only return names that come lexicographically after the supplied value.
-    pub page_token: Option<String>,
-    /// The maximum number of namespace names to return
-    pub limit: Option<u32>,
-}
-
-/// A request to create a namespace
-#[derive(Clone, Debug)]
-pub struct CreateNamespaceRequest {
-    /// The namespace identifier to create
-    pub namespace: Vec<String>,
-}
-
-/// A request to drop a namespace
-#[derive(Clone, Debug)]
-pub struct DropNamespaceRequest {
-    /// The namespace identifier to drop
-    pub namespace: Vec<String>,
-}
-
-/// A request to list names of tables in the database
+/// A request to list names of tables in the database (deprecated, use ListTablesRequest)
 #[derive(Clone, Debug, Default)]
 pub struct TableNamesRequest {
     /// The namespace to list tables in. Empty list represents root namespace.
@@ -77,7 +58,7 @@ pub struct TableNamesRequest {
 }
 
 /// A request to open a table
-#[derive(Clone, Debug)]
+#[derive(Clone)]
 pub struct OpenTableRequest {
     pub name: String,
     /// The namespace to open the table from. Empty list represents root namespace.
@@ -87,6 +68,22 @@ pub struct OpenTableRequest {
     /// Optional custom location for the table. If not provided, the database will
     /// derive a location based on its URI and the table name.
     pub location: Option<String>,
+    /// Optional namespace client for server-side query execution.
+    /// When set, queries will be executed on the namespace server instead of locally.
+    pub namespace_client: Option<Arc<dyn LanceNamespace>>,
+}
+
+impl std::fmt::Debug for OpenTableRequest {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("OpenTableRequest")
+            .field("name", &self.name)
+            .field("namespace", &self.namespace)
+            .field("index_cache_size", &self.index_cache_size)
+            .field("lance_read_params", &self.lance_read_params)
+            .field("location", &self.location)
+            .field("namespace_client", &self.namespace_client)
+            .finish()
+    }
 }
 
 pub type TableBuilderCallback = Box<dyn FnOnce(OpenTableRequest) -> OpenTableRequest + Send>;
@@ -170,6 +167,9 @@ pub struct CreateTableRequest {
     /// Optional custom location for the table. If not provided, the database will
     /// derive a location based on its URI and the table name.
     pub location: Option<String>,
+    /// Optional namespace client for server-side query execution.
+    /// When set, queries will be executed on the namespace server instead of locally.
+    pub namespace_client: Option<Arc<dyn LanceNamespace>>,
 }
 
 impl CreateTableRequest {
@@ -181,6 +181,7 @@ impl CreateTableRequest {
             mode: CreateTableMode::default(),
             write_options: WriteOptions::default(),
             location: None,
+            namespace_client: None,
         }
     }
 }
@@ -247,13 +248,30 @@ pub trait Database:
     /// Get the read consistency of the database
     async fn read_consistency(&self) -> Result<ReadConsistency>;
     /// List immediate child namespace names in the given namespace
-    async fn list_namespaces(&self, request: ListNamespacesRequest) -> Result<Vec<String>>;
+    async fn list_namespaces(
+        &self,
+        request: ListNamespacesRequest,
+    ) -> Result<ListNamespacesResponse>;
     /// Create a new namespace
-    async fn create_namespace(&self, request: CreateNamespaceRequest) -> Result<()>;
+    async fn create_namespace(
+        &self,
+        request: CreateNamespaceRequest,
+    ) -> Result<CreateNamespaceResponse>;
     /// Drop a namespace
-    async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<()>;
+    async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<DropNamespaceResponse>;
+    /// Describe a namespace (get its properties)
+    async fn describe_namespace(
+        &self,
+        request: DescribeNamespaceRequest,
+    ) -> Result<DescribeNamespaceResponse>;
     /// List the names of tables in the database
+    ///
+    /// # Deprecated
+    /// Use `list_tables` instead for pagination support
+    #[deprecated(note = "Use list_tables instead")]
     async fn table_names(&self, request: TableNamesRequest) -> Result<Vec<String>>;
+    /// List tables in the database with pagination support
+    async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse>;
     /// Create a table in the database
     async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>>;
     /// Clone a table in the database.

rust/lancedb/src/database/listing.rs

@@ -24,10 +24,15 @@ use crate::io::object_store::MirroringObjectStoreWrapper;
 use crate::table::NativeTable;
 use crate::utils::validate_table_name;
 
+use lance_namespace::models::{
+    CreateNamespaceRequest, CreateNamespaceResponse, DescribeNamespaceRequest,
+    DescribeNamespaceResponse, DropNamespaceRequest, DropNamespaceResponse, ListNamespacesRequest,
+    ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+};
+
 use super::{
-    BaseTable, CloneTableRequest, CreateNamespaceRequest, CreateTableMode, CreateTableRequest,
-    Database, DatabaseOptions, DropNamespaceRequest, ListNamespacesRequest, OpenTableRequest,
-    TableNamesRequest,
+    BaseTable, CloneTableRequest, CreateTableMode, CreateTableRequest, Database, DatabaseOptions,
+    OpenTableRequest, TableNamesRequest,
 };
 
 /// File extension to indicate a lance table
@@ -35,6 +40,7 @@ pub const LANCE_FILE_EXTENSION: &str = "lance";
 
 pub const OPT_NEW_TABLE_STORAGE_VERSION: &str = "new_table_data_storage_version";
 pub const OPT_NEW_TABLE_V2_MANIFEST_PATHS: &str = "new_table_enable_v2_manifest_paths";
+pub const OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS: &str = "new_table_enable_stable_row_ids";
 
 /// Controls how new tables should be created
 #[derive(Clone, Debug, Default)]
@@ -48,6 +54,12 @@ pub struct NewTableConfig {
     /// V2 manifest paths are more efficient than V2 manifest paths but are not
     /// supported by old clients.
     pub enable_v2_manifest_paths: Option<bool>,
+    /// Whether to enable stable row IDs for new tables
+    ///
+    /// When enabled, row IDs remain stable after compaction, update, delete,
+    /// and merges. This is useful for materialized views and other use cases
+    /// that need to track source rows across these operations.
+    pub enable_stable_row_ids: Option<bool>,
 }
 
 /// Options specific to the listing database
@@ -60,7 +72,7 @@ pub struct ListingDatabaseOptions {
     /// These are used to create/list tables and they are inherited by all tables
     /// opened by this database.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub storage_options: HashMap<String, String>,
 }
 
@@ -87,6 +99,14 @@ impl ListingDatabaseOptions {
                     })
                 })
                 .transpose()?,
+            enable_stable_row_ids: map
+                .get(OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS)
+                .map(|s| {
+                    s.parse::<bool>().map_err(|_| Error::InvalidInput {
+                        message: format!("enable_stable_row_ids must be a boolean, received {}", s),
+                    })
+                })
+                .transpose()?,
         };
         // We just assume that any options that are not new table config options are storage options
         let storage_options = map
@@ -94,6 +114,7 @@ impl ListingDatabaseOptions {
             .filter(|(key, _)| {
                 key.as_str() != OPT_NEW_TABLE_STORAGE_VERSION
                     && key.as_str() != OPT_NEW_TABLE_V2_MANIFEST_PATHS
+                    && key.as_str() != OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS
             })
             .map(|(key, value)| (key.clone(), value.clone()))
             .collect();
@@ -118,6 +139,12 @@ impl DatabaseOptions for ListingDatabaseOptions {
                 enable_v2_manifest_paths.to_string(),
             );
         }
+        if let Some(enable_stable_row_ids) = self.new_table_config.enable_stable_row_ids {
+            map.insert(
+                OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+                enable_stable_row_ids.to_string(),
+            );
+        }
     }
 }
 
@@ -157,7 +184,7 @@ impl ListingDatabaseOptionsBuilder {
 
     /// Set an option for the storage layer.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         self.options
             .storage_options
@@ -167,7 +194,7 @@ impl ListingDatabaseOptionsBuilder {
 
     /// Set multiple options for the storage layer.
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -475,7 +502,7 @@ impl ListingDatabase {
                     // this error is not lance::Error::DatasetNotFound, as the method
                     // `remove_dir_all` may be used to remove something not be a dataset
                     lance::Error::NotFound { .. } => Error::TableNotFound {
-                        name: name.to_owned(),
+                        name: name.clone(),
                         source: Box::new(err),
                     },
                     _ => Error::from(err),
@@ -497,7 +524,7 @@ impl ListingDatabase {
     fn extract_storage_overrides(
         &self,
         request: &CreateTableRequest,
-    ) -> Result<(Option<LanceFileVersion>, Option<bool>)> {
+    ) -> Result<(Option<LanceFileVersion>, Option<bool>, Option<bool>)> {
         let storage_options = request
             .write_options
             .lance_write_params
@@ -518,7 +545,19 @@ impl ListingDatabase {
                 message: "enable_v2_manifest_paths must be a boolean".to_string(),
             })?;
 
-        Ok((storage_version_override, v2_manifest_override))
+        let stable_row_ids_override = storage_options
+            .and_then(|opts| opts.get(OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS))
+            .map(|s| s.parse::<bool>())
+            .transpose()
+            .map_err(|_| Error::InvalidInput {
+                message: "enable_stable_row_ids must be a boolean".to_string(),
+            })?;
+
+        Ok((
+            storage_version_override,
+            v2_manifest_override,
+            stable_row_ids_override,
+        ))
     }
 
     /// Prepare write parameters for table creation
@@ -527,6 +566,7 @@ impl ListingDatabase {
         request: &CreateTableRequest,
         storage_version_override: Option<LanceFileVersion>,
         v2_manifest_override: Option<bool>,
+        stable_row_ids_override: Option<bool>,
     ) -> lance::dataset::WriteParams {
         let mut write_params = request
             .write_options
@@ -571,6 +611,13 @@ impl ListingDatabase {
             write_params.enable_v2_manifest_paths = enable_v2_manifest_paths;
         }
 
+        // Apply enable_stable_row_ids: table-level override takes precedence over connection config
+        if let Some(enable_stable_row_ids) =
+            stable_row_ids_override.or(self.new_table_config.enable_stable_row_ids)
+        {
+            write_params.enable_stable_row_ids = enable_stable_row_ids;
+        }
+
         if matches!(&request.mode, CreateTableMode::Overwrite) {
             write_params.mode = WriteMode::Overwrite;
         }
@@ -599,6 +646,7 @@ impl ListingDatabase {
                     index_cache_size: None,
                     lance_read_params: None,
                     location: None,
+                    namespace_client: None,
                 };
                 let req = (callback)(req);
                 let table = self.open_table(req).await?;
@@ -620,14 +668,20 @@ impl ListingDatabase {
 
 #[async_trait::async_trait]
 impl Database for ListingDatabase {
-    async fn list_namespaces(&self, request: ListNamespacesRequest) -> Result<Vec<String>> {
-        if !request.namespace.is_empty() {
+    async fn list_namespaces(
+        &self,
+        request: ListNamespacesRequest,
+    ) -> Result<ListNamespacesResponse> {
+        if request.id.as_ref().map(|v| !v.is_empty()).unwrap_or(false) {
             return Err(Error::NotSupported {
                 message: "Namespace operations are not supported for listing database".into(),
             });
         }
 
-        Ok(Vec::new())
+        Ok(ListNamespacesResponse {
+            namespaces: Vec::new(),
+            page_token: None,
+        })
     }
 
     fn uri(&self) -> &str {
@@ -646,13 +700,28 @@ impl Database for ListingDatabase {
         }
     }
 
-    async fn create_namespace(&self, _request: CreateNamespaceRequest) -> Result<()> {
+    async fn create_namespace(
+        &self,
+        _request: CreateNamespaceRequest,
+    ) -> Result<CreateNamespaceResponse> {
         Err(Error::NotSupported {
             message: "Namespace operations are not supported for listing database".into(),
         })
     }
 
-    async fn drop_namespace(&self, _request: DropNamespaceRequest) -> Result<()> {
+    async fn drop_namespace(
+        &self,
+        _request: DropNamespaceRequest,
+    ) -> Result<DropNamespaceResponse> {
+        Err(Error::NotSupported {
+            message: "Namespace operations are not supported for listing database".into(),
+        })
+    }
+
+    async fn describe_namespace(
+        &self,
+        _request: DescribeNamespaceRequest,
+    ) -> Result<DescribeNamespaceResponse> {
         Err(Error::NotSupported {
             message: "Namespace operations are not supported for listing database".into(),
         })
@@ -693,6 +762,57 @@ impl Database for ListingDatabase {
         Ok(f)
     }
 
+    async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
+        if request.id.as_ref().map(|v| !v.is_empty()).unwrap_or(false) {
+            return Err(Error::NotSupported {
+                message: "Namespace parameter is not supported for listing database. Only root namespace is supported.".into(),
+            });
+        }
+        let mut f = self
+            .object_store
+            .read_dir(self.base_path.clone())
+            .await?
+            .iter()
+            .map(Path::new)
+            .filter(|path| {
+                let is_lance = path
+                    .extension()
+                    .and_then(|e| e.to_str())
+                    .map(|e| e == LANCE_EXTENSION);
+                is_lance.unwrap_or(false)
+            })
+            .filter_map(|p| p.file_stem().and_then(|s| s.to_str().map(String::from)))
+            .collect::<Vec<String>>();
+        f.sort();
+
+        // Handle pagination with page_token
+        if let Some(ref page_token) = request.page_token {
+            let index = f
+                .iter()
+                .position(|name| name.as_str() > page_token.as_str())
+                .unwrap_or(f.len());
+            f.drain(0..index);
+        }
+
+        // Determine if there's a next page
+        let next_page_token = if let Some(limit) = request.limit {
+            if f.len() > limit as usize {
+                let token = f[limit as usize].clone();
+                f.truncate(limit as usize);
+                Some(token)
+            } else {
+                None
+            }
+        } else {
+            None
+        };
+
+        Ok(ListTablesResponse {
+            tables: f,
+            page_token: next_page_token,
+        })
+    }
+
     async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>> {
         // When namespace is not empty, location must be provided
         if !request.namespace.is_empty() && request.location.is_none() {
@@ -706,11 +826,15 @@ impl Database for ListingDatabase {
             .clone()
             .unwrap_or_else(|| self.table_uri(&request.name).unwrap());
 
-        let (storage_version_override, v2_manifest_override) =
+        let (storage_version_override, v2_manifest_override, stable_row_ids_override) =
             self.extract_storage_overrides(&request)?;
 
-        let write_params =
-            self.prepare_write_params(&request, storage_version_override, v2_manifest_override);
+        let write_params = self.prepare_write_params(
+            &request,
+            storage_version_override,
+            v2_manifest_override,
+            stable_row_ids_override,
+        );
 
         let data_schema = request.data.arrow_schema();
 
@@ -722,6 +846,7 @@ impl Database for ListingDatabase {
             self.store_wrapper.clone(),
             Some(write_params),
             self.read_consistency_interval,
+            request.namespace_client,
         )
         .await
         {
@@ -793,6 +918,7 @@ impl Database for ListingDatabase {
             self.store_wrapper.clone(),
             None,
             self.read_consistency_interval,
+            None,
         )
         .await?;
 
@@ -864,6 +990,7 @@ impl Database for ListingDatabase {
                 self.store_wrapper.clone(),
                 Some(read_params),
                 self.read_consistency_interval,
+                request.namespace_client,
             )
             .await?,
         );
@@ -901,6 +1028,7 @@ impl Database for ListingDatabase {
         self.drop_tables(vec![name.to_string()]).await
     }
 
+    #[allow(deprecated)]
     async fn drop_all_tables(&self, namespace: &[String]) -> Result<()> {
         // Check if namespace parameter is provided
         if !namespace.is_empty() {
@@ -921,7 +1049,7 @@ impl Database for ListingDatabase {
 mod tests {
     use super::*;
     use crate::connection::ConnectRequest;
-    use crate::database::{CreateTableData, CreateTableMode, CreateTableRequest};
+    use crate::database::{CreateTableData, CreateTableMode, CreateTableRequest, WriteOptions};
     use crate::table::{Table, TableDefinition};
     use arrow_array::{Int32Array, RecordBatch, StringArray};
     use arrow_schema::{DataType, Field, Schema};
@@ -965,6 +1093,7 @@ mod tests {
                 mode: CreateTableMode::Create,
                 write_options: Default::default(),
                 location: None,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -986,6 +1115,7 @@ mod tests {
             .unwrap();
 
         // Verify both tables exist
+        #[allow(deprecated)]
         let table_names = db.table_names(TableNamesRequest::default()).await.unwrap();
         assert!(table_names.contains(&"source_table".to_string()));
         assert!(table_names.contains(&"cloned_table".to_string()));
@@ -1029,6 +1159,7 @@ mod tests {
                 mode: CreateTableMode::Create,
                 write_options: Default::default(),
                 location: None,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1087,6 +1218,7 @@ mod tests {
             mode: CreateTableMode::Create,
             write_options: Default::default(),
             location: None,
+            namespace_client: None,
         })
         .await
         .unwrap();
@@ -1122,6 +1254,7 @@ mod tests {
             mode: CreateTableMode::Create,
             write_options: Default::default(),
             location: None,
+            namespace_client: None,
         })
         .await
         .unwrap();
@@ -1161,6 +1294,7 @@ mod tests {
             mode: CreateTableMode::Create,
             write_options: Default::default(),
             location: None,
+            namespace_client: None,
         })
         .await
         .unwrap();
@@ -1200,6 +1334,7 @@ mod tests {
             mode: CreateTableMode::Create,
             write_options: Default::default(),
             location: None,
+            namespace_client: None,
         })
         .await
         .unwrap();
@@ -1254,6 +1389,7 @@ mod tests {
             mode: CreateTableMode::Create,
             write_options: Default::default(),
             location: None,
+            namespace_client: None,
         })
         .await
         .unwrap();
@@ -1311,6 +1447,7 @@ mod tests {
                 mode: CreateTableMode::Create,
                 write_options: Default::default(),
                 location: None,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1396,6 +1533,7 @@ mod tests {
                 mode: CreateTableMode::Create,
                 write_options: Default::default(),
                 location: None,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1482,6 +1620,7 @@ mod tests {
                 mode: CreateTableMode::Create,
                 write_options: Default::default(),
                 location: None,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1575,6 +1714,7 @@ mod tests {
                 mode: CreateTableMode::Create,
                 write_options: Default::default(),
                 location: None,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1621,4 +1761,270 @@ mod tests {
         // Cloned table should have all 8 rows from the latest version
         assert_eq!(cloned_table.count_rows(None).await.unwrap(), 8);
     }
+
+    #[tokio::test]
+    async fn test_create_table_with_stable_row_ids_connection_level() {
+        let tempdir = tempdir().unwrap();
+        let uri = tempdir.path().to_str().unwrap();
+
+        // Create database with stable row IDs enabled at connection level
+        let mut options = HashMap::new();
+        options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "true".to_string(),
+        );
+
+        let request = ConnectRequest {
+            uri: uri.to_string(),
+            #[cfg(feature = "remote")]
+            client_config: Default::default(),
+            options,
+            read_consistency_interval: None,
+            session: None,
+        };
+
+        let db = ListingDatabase::connect_with_options(&request)
+            .await
+            .unwrap();
+
+        // Verify the config was parsed correctly
+        assert_eq!(db.new_table_config.enable_stable_row_ids, Some(true));
+
+        // Create a table - it should inherit the stable row IDs setting
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
+        )
+        .unwrap();
+
+        let reader = Box::new(arrow_array::RecordBatchIterator::new(
+            vec![Ok(batch)],
+            schema.clone(),
+        ));
+
+        let table = db
+            .create_table(CreateTableRequest {
+                name: "test_stable".to_string(),
+                namespace: vec![],
+                data: CreateTableData::Data(reader),
+                mode: CreateTableMode::Create,
+                write_options: Default::default(),
+                location: None,
+                namespace_client: None,
+            })
+            .await
+            .unwrap();
+
+        // Verify table was created successfully
+        assert_eq!(table.count_rows(None).await.unwrap(), 3);
+    }
+
+    #[tokio::test]
+    async fn test_create_table_with_stable_row_ids_table_level() {
+        let (_tempdir, db) = setup_database().await;
+
+        // Verify connection has no stable row IDs config
+        assert_eq!(db.new_table_config.enable_stable_row_ids, None);
+
+        // Create a table with stable row IDs enabled at table level via storage_options
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
+        )
+        .unwrap();
+
+        let reader = Box::new(arrow_array::RecordBatchIterator::new(
+            vec![Ok(batch)],
+            schema.clone(),
+        ));
+
+        let mut storage_options = HashMap::new();
+        storage_options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "true".to_string(),
+        );
+
+        let write_options = WriteOptions {
+            lance_write_params: Some(lance::dataset::WriteParams {
+                store_params: Some(lance::io::ObjectStoreParams {
+                    storage_options: Some(storage_options),
+                    ..Default::default()
+                }),
+                ..Default::default()
+            }),
+        };
+
+        let table = db
+            .create_table(CreateTableRequest {
+                name: "test_stable_table_level".to_string(),
+                namespace: vec![],
+                data: CreateTableData::Data(reader),
+                mode: CreateTableMode::Create,
+                write_options,
+                location: None,
+                namespace_client: None,
+            })
+            .await
+            .unwrap();
+
+        // Verify table was created successfully
+        assert_eq!(table.count_rows(None).await.unwrap(), 3);
+    }
+
+    #[tokio::test]
+    async fn test_create_table_stable_row_ids_table_overrides_connection() {
+        let tempdir = tempdir().unwrap();
+        let uri = tempdir.path().to_str().unwrap();
+
+        // Create database with stable row IDs enabled at connection level
+        let mut options = HashMap::new();
+        options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "true".to_string(),
+        );
+
+        let request = ConnectRequest {
+            uri: uri.to_string(),
+            #[cfg(feature = "remote")]
+            client_config: Default::default(),
+            options,
+            read_consistency_interval: None,
+            session: None,
+        };
+
+        let db = ListingDatabase::connect_with_options(&request)
+            .await
+            .unwrap();
+
+        assert_eq!(db.new_table_config.enable_stable_row_ids, Some(true));
+
+        // Create table with stable row IDs disabled at table level (overrides connection)
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
+        )
+        .unwrap();
+
+        let reader = Box::new(arrow_array::RecordBatchIterator::new(
+            vec![Ok(batch)],
+            schema.clone(),
+        ));
+
+        let mut storage_options = HashMap::new();
+        storage_options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "false".to_string(),
+        );
+
+        let write_options = WriteOptions {
+            lance_write_params: Some(lance::dataset::WriteParams {
+                store_params: Some(lance::io::ObjectStoreParams {
+                    storage_options: Some(storage_options),
+                    ..Default::default()
+                }),
+                ..Default::default()
+            }),
+        };
+
+        let table = db
+            .create_table(CreateTableRequest {
+                name: "test_override".to_string(),
+                namespace: vec![],
+                data: CreateTableData::Data(reader),
+                mode: CreateTableMode::Create,
+                write_options,
+                location: None,
+                namespace_client: None,
+            })
+            .await
+            .unwrap();
+
+        // Verify table was created successfully
+        assert_eq!(table.count_rows(None).await.unwrap(), 3);
+    }
+
+    #[tokio::test]
+    async fn test_stable_row_ids_invalid_value() {
+        let tempdir = tempdir().unwrap();
+        let uri = tempdir.path().to_str().unwrap();
+
+        // Try to create database with invalid stable row IDs value
+        let mut options = HashMap::new();
+        options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "not_a_boolean".to_string(),
+        );
+
+        let request = ConnectRequest {
+            uri: uri.to_string(),
+            #[cfg(feature = "remote")]
+            client_config: Default::default(),
+            options,
+            read_consistency_interval: None,
+            session: None,
+        };
+
+        let result = ListingDatabase::connect_with_options(&request).await;
+
+        assert!(result.is_err());
+        assert!(matches!(
+            result.unwrap_err(),
+            Error::InvalidInput { message } if message.contains("enable_stable_row_ids must be a boolean")
+        ));
+    }
+
+    #[test]
+    fn test_stable_row_ids_config_serialization() {
+        // Test that ListingDatabaseOptions correctly serializes stable_row_ids
+        let mut options = HashMap::new();
+        options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "true".to_string(),
+        );
+
+        // Parse the options
+        let db_options = ListingDatabaseOptions::parse_from_map(&options).unwrap();
+        assert_eq!(
+            db_options.new_table_config.enable_stable_row_ids,
+            Some(true)
+        );
+
+        // Serialize back to map
+        let mut serialized = HashMap::new();
+        db_options.serialize_into_map(&mut serialized);
+
+        assert_eq!(
+            serialized.get(OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS),
+            Some(&"true".to_string())
+        );
+    }
+
+    #[test]
+    fn test_stable_row_ids_config_parse_false() {
+        let mut options = HashMap::new();
+        options.insert(
+            OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS.to_string(),
+            "false".to_string(),
+        );
+
+        let db_options = ListingDatabaseOptions::parse_from_map(&options).unwrap();
+        assert_eq!(
+            db_options.new_table_config.enable_stable_row_ids,
+            Some(false)
+        );
+    }
+
+    #[test]
+    fn test_stable_row_ids_config_not_set() {
+        let options = HashMap::new();
+
+        let db_options = ListingDatabaseOptions::parse_from_map(&options).unwrap();
+        assert_eq!(db_options.new_table_config.enable_stable_row_ids, None);
+    }
 }

rust/lancedb/src/database/namespace.rs

@@ -10,8 +10,10 @@ use async_trait::async_trait;
 use lance_io::object_store::{LanceNamespaceStorageOptionsProvider, StorageOptionsProvider};
 use lance_namespace::{
     models::{
-        CreateEmptyTableRequest, CreateNamespaceRequest, DescribeTableRequest,
-        DropNamespaceRequest, DropTableRequest, ListNamespacesRequest, ListTablesRequest,
+        CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
+        DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
+        DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
+        ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
     },
     LanceNamespace,
 };
@@ -22,11 +24,8 @@ use crate::database::ReadConsistency;
 use crate::error::{Error, Result};
 
 use super::{
-    listing::ListingDatabase, BaseTable, CloneTableRequest,
-    CreateNamespaceRequest as DbCreateNamespaceRequest, CreateTableMode,
-    CreateTableRequest as DbCreateTableRequest, Database,
-    DropNamespaceRequest as DbDropNamespaceRequest,
-    ListNamespacesRequest as DbListNamespacesRequest, OpenTableRequest, TableNamesRequest,
+    listing::ListingDatabase, BaseTable, CloneTableRequest, CreateTableMode,
+    CreateTableRequest as DbCreateTableRequest, Database, OpenTableRequest, TableNamesRequest,
 };
 
 /// A database implementation that uses lance-namespace for table management
@@ -40,6 +39,8 @@ pub struct LanceNamespaceDatabase {
     session: Option<Arc<lance::session::Session>>,
     // database URI
     uri: String,
+    // Whether to enable server-side query execution
+    server_side_query_enabled: bool,
 }
 
 impl LanceNamespaceDatabase {
@@ -49,6 +50,7 @@ impl LanceNamespaceDatabase {
         storage_options: HashMap<String, String>,
         read_consistency_interval: Option<std::time::Duration>,
         session: Option<Arc<lance::session::Session>>,
+        server_side_query_enabled: bool,
     ) -> Result<Self> {
         let mut builder = ConnectBuilder::new(ns_impl);
         for (key, value) in ns_properties.clone() {
@@ -67,6 +69,7 @@ impl LanceNamespaceDatabase {
             read_consistency_interval,
             session,
             uri: format!("namespace://{}", ns_impl),
+            server_side_query_enabled,
         })
     }
 }
@@ -76,6 +79,7 @@ impl std::fmt::Debug for LanceNamespaceDatabase {
         f.debug_struct("LanceNamespaceDatabase")
             .field("storage_options", &self.storage_options)
             .field("read_consistency_interval", &self.read_consistency_interval)
+            .field("server_side_query_enabled", &self.server_side_query_enabled)
             .finish()
     }
 }
@@ -149,92 +153,47 @@ impl Database for LanceNamespaceDatabase {
         }
     }
 
-    async fn list_namespaces(&self, request: DbListNamespacesRequest) -> Result<Vec<String>> {
-        let ns_request = ListNamespacesRequest {
-            id: if request.namespace.is_empty() {
-                None
-            } else {
-                Some(request.namespace)
-            },
-            page_token: request.page_token,
-            limit: request.limit.map(|l| l as i32),
-        };
-
-        let response = self
-            .namespace
-            .list_namespaces(ns_request)
-            .await
-            .map_err(|e| Error::Runtime {
-                message: format!("Failed to list namespaces: {}", e),
-            })?;
-
-        Ok(response.namespaces)
+    async fn list_namespaces(
+        &self,
+        request: ListNamespacesRequest,
+    ) -> Result<ListNamespacesResponse> {
+        Ok(self.namespace.list_namespaces(request).await?)
     }
 
-    async fn create_namespace(&self, request: DbCreateNamespaceRequest) -> Result<()> {
-        let ns_request = CreateNamespaceRequest {
-            id: if request.namespace.is_empty() {
-                None
-            } else {
-                Some(request.namespace)
-            },
-            mode: None,
-            properties: None,
-        };
-
-        self.namespace
-            .create_namespace(ns_request)
-            .await
-            .map_err(|e| Error::Runtime {
-                message: format!("Failed to create namespace: {}", e),
-            })?;
-
-        Ok(())
+    async fn create_namespace(
+        &self,
+        request: CreateNamespaceRequest,
+    ) -> Result<CreateNamespaceResponse> {
+        Ok(self.namespace.create_namespace(request).await?)
     }
 
-    async fn drop_namespace(&self, request: DbDropNamespaceRequest) -> Result<()> {
-        let ns_request = DropNamespaceRequest {
-            id: if request.namespace.is_empty() {
-                None
-            } else {
-                Some(request.namespace)
-            },
-            mode: None,
-            behavior: None,
-        };
+    async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<DropNamespaceResponse> {
+        Ok(self.namespace.drop_namespace(request).await?)
+    }
 
-        self.namespace
-            .drop_namespace(ns_request)
-            .await
-            .map_err(|e| Error::Runtime {
-                message: format!("Failed to drop namespace: {}", e),
-            })?;
-
-        Ok(())
+    async fn describe_namespace(
+        &self,
+        request: DescribeNamespaceRequest,
+    ) -> Result<DescribeNamespaceResponse> {
+        Ok(self.namespace.describe_namespace(request).await?)
     }
 
     async fn table_names(&self, request: TableNamesRequest) -> Result<Vec<String>> {
         let ns_request = ListTablesRequest {
-            id: if request.namespace.is_empty() {
-                None
-            } else {
-                Some(request.namespace)
-            },
+            id: Some(request.namespace),
             page_token: request.start_after,
             limit: request.limit.map(|l| l as i32),
         };
 
-        let response =
-            self.namespace
-                .list_tables(ns_request)
-                .await
-                .map_err(|e| Error::Runtime {
-                    message: format!("Failed to list tables: {}", e),
-                })?;
+        let response = self.namespace.list_tables(ns_request).await?;
 
         Ok(response.tables)
     }
 
+    async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
+        Ok(self.namespace.list_tables(request).await?)
+    }
+
     async fn create_table(&self, request: DbCreateTableRequest) -> Result<Arc<dyn BaseTable>> {
         // Extract user-provided storage options from request
         let user_storage_options = request
@@ -290,6 +249,10 @@ impl Database for LanceNamespaceDatabase {
                         )
                         .await?;
 
+                    let namespace_client = self
+                        .server_side_query_enabled
+                        .then(|| self.namespace.clone());
+
                     return listing_db
                         .open_table(OpenTableRequest {
                             name: request.name.clone(),
@@ -297,6 +260,7 @@ impl Database for LanceNamespaceDatabase {
                             index_cache_size: None,
                             lance_read_params: None,
                             location: Some(location),
+                            namespace_client,
                         })
                         .await;
                 }
@@ -333,12 +297,16 @@ impl Database for LanceNamespaceDatabase {
         let listing_db = self
             .create_listing_database(
                 &location,
-                table_id,
+                table_id.clone(),
                 user_storage_options,
                 create_empty_response.storage_options.as_ref(),
             )
             .await?;
 
+        let namespace_client = self
+            .server_side_query_enabled
+            .then(|| self.namespace.clone());
+
         let create_request = DbCreateTableRequest {
             name: request.name,
             namespace: request.namespace,
@@ -346,7 +314,9 @@ impl Database for LanceNamespaceDatabase {
             mode: request.mode,
             write_options: request.write_options,
             location: Some(location),
+            namespace_client,
         };
+
         listing_db.create_table(create_request).await
     }
 
@@ -380,19 +350,25 @@ impl Database for LanceNamespaceDatabase {
         let listing_db = self
             .create_listing_database(
                 &location,
-                table_id,
+                table_id.clone(),
                 user_storage_options,
                 response.storage_options.as_ref(),
             )
             .await?;
 
+        let namespace_client = self
+            .server_side_query_enabled
+            .then(|| self.namespace.clone());
+
         let open_request = OpenTableRequest {
             name: request.name.clone(),
             namespace: request.namespace.clone(),
             index_cache_size: request.index_cache_size,
             lance_read_params: request.lance_read_params,
             location: Some(location),
+            namespace_client,
         };
+
         listing_db.open_table(open_request).await
     }
 
@@ -429,6 +405,7 @@ impl Database for LanceNamespaceDatabase {
         Ok(())
     }
 
+    #[allow(deprecated)]
     async fn drop_all_tables(&self, namespace: &[String]) -> Result<()> {
         let tables = self
             .table_names(TableNamesRequest {
@@ -455,7 +432,6 @@ impl Database for LanceNamespaceDatabase {
 mod tests {
     use super::*;
     use crate::connect_namespace;
-    use crate::database::CreateNamespaceRequest;
     use crate::query::ExecutableQuery;
     use arrow_array::{Int32Array, RecordBatch, RecordBatchIterator, StringArray};
     use arrow_schema::{DataType, Field, Schema};
@@ -568,7 +544,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -627,7 +605,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -689,7 +669,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -771,7 +753,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -825,7 +809,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -904,7 +890,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -936,7 +924,9 @@ mod tests {
 
         // Create a child namespace first
         conn.create_namespace(CreateNamespaceRequest {
-            namespace: vec!["test_ns".into()],
+            id: Some(vec!["test_ns".into()]),
+            mode: None,
+            properties: None,
         })
         .await
         .expect("Failed to create namespace");
@@ -977,4 +967,46 @@ mod tests {
         let open_result = conn.open_table("drop_test").execute().await;
         assert!(open_result.is_err());
     }
+
+    #[tokio::test]
+    async fn test_table_names_at_root() {
+        // Test that table_names at root (empty namespace) works correctly
+        // This is a regression test for a bug where empty namespace was converted to None
+        let tmp_dir = tempdir().unwrap();
+        let root_path = tmp_dir.path().to_str().unwrap().to_string();
+
+        let mut properties = HashMap::new();
+        properties.insert("root".to_string(), root_path);
+
+        let conn = connect_namespace("dir", properties)
+            .execute()
+            .await
+            .expect("Failed to connect to namespace");
+
+        // Create multiple tables at root namespace
+        let test_data1 = create_test_data();
+        let _table1 = conn
+            .create_table("table1", test_data1)
+            .execute()
+            .await
+            .expect("Failed to create table1 at root");
+
+        let test_data2 = create_test_data();
+        let _table2 = conn
+            .create_table("table2", test_data2)
+            .execute()
+            .await
+            .expect("Failed to create table2 at root");
+
+        // List tables at root using table_names (empty namespace means root)
+        let table_names = conn
+            .table_names()
+            .execute()
+            .await
+            .expect("Failed to list tables at root");
+
+        assert!(table_names.contains(&"table1".to_string()));
+        assert!(table_names.contains(&"table2".to_string()));
+        assert_eq!(table_names.len(), 2);
+    }
 }

rust/lancedb/src/index.rs

@@ -13,7 +13,7 @@ use crate::{table::BaseTable, DistanceType, Error, Result};
 
 use self::{
     scalar::{BTreeIndexBuilder, BitmapIndexBuilder, LabelListIndexBuilder},
-    vector::{IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder},
+    vector::{IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder, IvfSqIndexBuilder},
 };
 
 pub mod scalar;
@@ -54,6 +54,9 @@ pub enum Index {
     /// IVF index with Product Quantization
     IvfPq(IvfPqIndexBuilder),
 
+    /// IVF index with Scalar Quantization
+    IvfSq(IvfSqIndexBuilder),
+
     /// IVF index with RabitQ Quantization
     IvfRq(IvfRqIndexBuilder),
 
@@ -277,6 +280,8 @@ pub enum IndexType {
     // Vector
     #[serde(alias = "IVF_FLAT")]
     IvfFlat,
+    #[serde(alias = "IVF_SQ")]
+    IvfSq,
     #[serde(alias = "IVF_PQ")]
     IvfPq,
     #[serde(alias = "IVF_RQ")]
@@ -301,6 +306,7 @@ impl std::fmt::Display for IndexType {
     fn fmt(&self, f: &mut std::fmt::Formatter) -> std::fmt::Result {
         match self {
             Self::IvfFlat => write!(f, "IVF_FLAT"),
+            Self::IvfSq => write!(f, "IVF_SQ"),
             Self::IvfPq => write!(f, "IVF_PQ"),
             Self::IvfRq => write!(f, "IVF_RQ"),
             Self::IvfHnswPq => write!(f, "IVF_HNSW_PQ"),
@@ -323,6 +329,7 @@ impl std::str::FromStr for IndexType {
             "LABEL_LIST" | "LABELLIST" => Ok(Self::LabelList),
             "FTS" | "INVERTED" => Ok(Self::FTS),
             "IVF_FLAT" => Ok(Self::IvfFlat),
+            "IVF_SQ" => Ok(Self::IvfSq),
             "IVF_PQ" => Ok(Self::IvfPq),
             "IVF_RQ" => Ok(Self::IvfRq),
             "IVF_HNSW_PQ" => Ok(Self::IvfHnswPq),

rust/lancedb/src/index/vector.rs

@@ -209,6 +209,38 @@ impl IvfFlatIndexBuilder {
     impl_ivf_params_setter!();
 }
 
+/// Builder for an IVF SQ index.
+///
+/// This index compresses vectors using scalar quantization and groups them into IVF partitions.
+/// It offers a balance between search performance and storage footprint.
+#[derive(Debug, Clone)]
+pub struct IvfSqIndexBuilder {
+    pub(crate) distance_type: DistanceType,
+
+    // IVF
+    pub(crate) num_partitions: Option<u32>,
+    pub(crate) sample_rate: u32,
+    pub(crate) max_iterations: u32,
+    pub(crate) target_partition_size: Option<u32>,
+}
+
+impl Default for IvfSqIndexBuilder {
+    fn default() -> Self {
+        Self {
+            distance_type: DistanceType::L2,
+            num_partitions: None,
+            sample_rate: 256,
+            max_iterations: 50,
+            target_partition_size: None,
+        }
+    }
+}
+
+impl IvfSqIndexBuilder {
+    impl_distance_type_setter!();
+    impl_ivf_params_setter!();
+}
+
 /// Builder for an IVF PQ index.
 ///
 /// This index stores a compressed (quantized) copy of every vector.  These vectors

rust/lancedb/src/lib.rs

@@ -71,7 +71,7 @@
 //! It treats [`FixedSizeList<Float16/Float32>`](https://docs.rs/arrow/latest/arrow/array/struct.FixedSizeListArray.html)
 //! columns as vector columns.
 //!
-//! For more details, please refer to [LanceDB documentation](https://lancedb.github.io/lancedb/).
+//! For more details, please refer to the [LanceDB documentation](https://lancedb.com/docs).
 //!
 //! #### Create a table
 //!

rust/lancedb/src/remote/db.rs

@@ -10,13 +10,17 @@ use http::StatusCode;
 use lance_io::object_store::StorageOptions;
 use moka::future::Cache;
 use reqwest::header::CONTENT_TYPE;
-use serde::Deserialize;
 use tokio::task::spawn_blocking;
 
+use lance_namespace::models::{
+    CreateNamespaceRequest, CreateNamespaceResponse, DescribeNamespaceRequest,
+    DescribeNamespaceResponse, DropNamespaceRequest, DropNamespaceResponse, ListNamespacesRequest,
+    ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+};
+
 use crate::database::{
-    CloneTableRequest, CreateNamespaceRequest, CreateTableData, CreateTableMode,
-    CreateTableRequest, Database, DatabaseOptions, DropNamespaceRequest, ListNamespacesRequest,
-    OpenTableRequest, ReadConsistency, TableNamesRequest,
+    CloneTableRequest, CreateTableData, CreateTableMode, CreateTableRequest, Database,
+    DatabaseOptions, OpenTableRequest, ReadConsistency, TableNamesRequest,
 };
 use crate::error::Result;
 use crate::table::BaseTable;
@@ -90,7 +94,7 @@ pub struct RemoteDatabaseOptions {
     pub host_override: Option<String>,
     /// Storage options configure the storage layer (e.g. S3, GCS, Azure, etc.)
     ///
-    /// See available options at <https://lancedb.github.io/lancedb/guides/storage/>
+    /// See available options at <https://lancedb.com/docs/storage/>
     ///
     /// These options are only used for LanceDB Enterprise and only a subset of options
     /// are supported.
@@ -180,11 +184,6 @@ impl RemoteDatabaseOptionsBuilder {
     }
 }
 
-#[derive(Deserialize)]
-struct ListTablesResponse {
-    tables: Vec<String>,
-}
-
 #[derive(Debug)]
 pub struct RemoteDatabase<S: HttpSend = Sender> {
     client: RestfulLanceDbClient<S>,
@@ -337,7 +336,6 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
             self.client
                 .get(&format!("/v1/namespace/{}/table/list", namespace_id))
         } else {
-            // TODO: use new API for all listing operations once stable
             self.client.get("/v1/table/")
         };
 
@@ -371,6 +369,44 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
         Ok(tables)
     }
 
+    async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
+        let namespace_parts = request.id.as_deref().unwrap_or(&[]);
+        let namespace_id = build_namespace_identifier(namespace_parts, &self.client.id_delimiter);
+        let mut req = self
+            .client
+            .get(&format!("/v1/namespace/{}/table/list", namespace_id));
+
+        if let Some(limit) = request.limit {
+            req = req.query(&[("limit", limit)]);
+        }
+        if let Some(ref page_token) = request.page_token {
+            req = req.query(&[("page_token", page_token)]);
+        }
+
+        let (request_id, rsp) = self.client.send_with_retry(req, None, true).await?;
+        let rsp = self.client.check_response(&request_id, rsp).await?;
+        let version = parse_server_version(&request_id, &rsp)?;
+        let response: ListTablesResponse = rsp.json().await.err_to_http(request_id)?;
+
+        // Cache the tables for future use
+        let namespace_vec = namespace_parts.to_vec();
+        for table in &response.tables {
+            let table_identifier =
+                build_table_identifier(table, &namespace_vec, &self.client.id_delimiter);
+            let cache_key = build_cache_key(table, &namespace_vec);
+            let remote_table = Arc::new(RemoteTable::new(
+                self.client.clone(),
+                table.clone(),
+                namespace_vec.clone(),
+                table_identifier.clone(),
+                version.clone(),
+            ));
+            self.table_cache.insert(cache_key, remote_table).await;
+        }
+
+        Ok(response)
+    }
+
     async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>> {
         let data = match request.data {
             CreateTableData::Data(data) => data,
@@ -417,6 +453,7 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
                             index_cache_size: None,
                             lance_read_params: None,
                             location: None,
+                            namespace_client: None,
                         };
                         let req = (callback)(req);
                         self.open_table(req).await
@@ -590,53 +627,101 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
         })
     }
 
-    async fn list_namespaces(&self, request: ListNamespacesRequest) -> Result<Vec<String>> {
-        let namespace_id =
-            build_namespace_identifier(request.namespace.as_slice(), &self.client.id_delimiter);
+    async fn list_namespaces(
+        &self,
+        request: ListNamespacesRequest,
+    ) -> Result<ListNamespacesResponse> {
+        let namespace_parts = request.id.as_deref().unwrap_or(&[]);
+        let namespace_id = build_namespace_identifier(namespace_parts, &self.client.id_delimiter);
         let mut req = self
             .client
             .get(&format!("/v1/namespace/{}/list", namespace_id));
         if let Some(limit) = request.limit {
             req = req.query(&[("limit", limit)]);
         }
-        if let Some(page_token) = request.page_token {
+        if let Some(ref page_token) = request.page_token {
             req = req.query(&[("page_token", page_token)]);
         }
 
         let (request_id, resp) = self.client.send(req).await?;
         let resp = self.client.check_response(&request_id, resp).await?;
 
-        #[derive(Deserialize)]
-        struct ListNamespacesResponse {
-            namespaces: Vec<String>,
-        }
-
-        let parsed: ListNamespacesResponse = resp.json().await.map_err(|e| Error::Runtime {
-            message: format!("Failed to parse namespace response: {}", e),
-        })?;
-        Ok(parsed.namespaces)
+        resp.json().await.err_to_http(request_id)
     }
 
-    async fn create_namespace(&self, request: CreateNamespaceRequest) -> Result<()> {
-        let namespace_id =
-            build_namespace_identifier(request.namespace.as_slice(), &self.client.id_delimiter);
-        let req = self
+    async fn create_namespace(
+        &self,
+        request: CreateNamespaceRequest,
+    ) -> Result<CreateNamespaceResponse> {
+        let namespace_parts = request.id.as_deref().unwrap_or(&[]);
+        let namespace_id = build_namespace_identifier(namespace_parts, &self.client.id_delimiter);
+        let mut req = self
             .client
             .post(&format!("/v1/namespace/{}/create", namespace_id));
+
+        // Build request body with mode and properties if present
+        #[derive(serde::Serialize)]
+        struct CreateNamespaceRequestBody {
+            #[serde(skip_serializing_if = "Option::is_none")]
+            mode: Option<String>,
+            #[serde(skip_serializing_if = "Option::is_none")]
+            properties: Option<HashMap<String, String>>,
+        }
+
+        let body = CreateNamespaceRequestBody {
+            mode: request.mode.as_ref().map(|m| format!("{:?}", m)),
+            properties: request.properties,
+        };
+
+        req = req.json(&body);
         let (request_id, resp) = self.client.send(req).await?;
-        self.client.check_response(&request_id, resp).await?;
-        Ok(())
+        let resp = self.client.check_response(&request_id, resp).await?;
+
+        resp.json().await.err_to_http(request_id)
     }
 
-    async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<()> {
-        let namespace_id =
-            build_namespace_identifier(request.namespace.as_slice(), &self.client.id_delimiter);
-        let req = self
+    async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<DropNamespaceResponse> {
+        let namespace_parts = request.id.as_deref().unwrap_or(&[]);
+        let namespace_id = build_namespace_identifier(namespace_parts, &self.client.id_delimiter);
+        let mut req = self
             .client
             .post(&format!("/v1/namespace/{}/drop", namespace_id));
+
+        // Build request body with mode and behavior if present
+        #[derive(serde::Serialize)]
+        struct DropNamespaceRequestBody {
+            #[serde(skip_serializing_if = "Option::is_none")]
+            mode: Option<String>,
+            #[serde(skip_serializing_if = "Option::is_none")]
+            behavior: Option<String>,
+        }
+
+        let body = DropNamespaceRequestBody {
+            mode: request.mode.as_ref().map(|m| format!("{:?}", m)),
+            behavior: request.behavior.as_ref().map(|b| format!("{:?}", b)),
+        };
+
+        req = req.json(&body);
         let (request_id, resp) = self.client.send(req).await?;
-        self.client.check_response(&request_id, resp).await?;
-        Ok(())
+        let resp = self.client.check_response(&request_id, resp).await?;
+
+        resp.json().await.err_to_http(request_id)
+    }
+
+    async fn describe_namespace(
+        &self,
+        request: DescribeNamespaceRequest,
+    ) -> Result<DescribeNamespaceResponse> {
+        let namespace_parts = request.id.as_deref().unwrap_or(&[]);
+        let namespace_id = build_namespace_identifier(namespace_parts, &self.client.id_delimiter);
+        let req = self
+            .client
+            .get(&format!("/v1/namespace/{}/describe", namespace_id));
+
+        let (request_id, resp) = self.client.send(req).await?;
+        let resp = self.client.check_response(&request_id, resp).await?;
+
+        resp.json().await.err_to_http(request_id)
     }
 
     fn as_any(&self) -> &dyn std::any::Any {

rust/lancedb/src/remote/table.rs

@@ -1072,6 +1072,14 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
                     body["num_bits"] = serde_json::Value::Number(num_bits.into());
                 }
             }
+            Index::IvfSq(index) => {
+                body[INDEX_TYPE_KEY] = serde_json::Value::String("IVF_SQ".to_string());
+                body[METRIC_TYPE_KEY] =
+                    serde_json::Value::String(index.distance_type.to_string().to_lowercase());
+                if let Some(num_partitions) = index.num_partitions {
+                    body["num_partitions"] = serde_json::Value::Number(num_partitions.into());
+                }
+            }
             Index::IvfHnswSq(index) => {
                 body[INDEX_TYPE_KEY] = serde_json::Value::String("IVF_HNSW_SQ".to_string());
                 body[METRIC_TYPE_KEY] =
@@ -1183,6 +1191,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
                 num_deleted_rows: 0,
                 num_inserted_rows: 0,
                 num_updated_rows: 0,
+                num_attempts: 0,
             });
         }
 

rust/lancedb/src/table.rs

@@ -40,6 +40,11 @@ use lance_index::vector::pq::PQBuildParams;
 use lance_index::vector::sq::builder::SQBuildParams;
 use lance_index::DatasetIndexExt;
 use lance_index::IndexType;
+use lance_namespace::models::{
+    QueryTableRequest as NsQueryTableRequest, QueryTableRequestFullTextQuery,
+    QueryTableRequestVector, StringFtsQuery,
+};
+use lance_namespace::LanceNamespace;
 use lance_table::format::Manifest;
 use lance_table::io::commit::ManifestNamingScheme;
 use log::info;
@@ -467,6 +472,11 @@ pub struct MergeResult {
     /// However those rows are not shared with the user.
     #[serde(default)]
     pub num_deleted_rows: u64,
+    /// Number of attempts performed during the merge operation.
+    /// This includes the initial attempt plus any retries due to transaction conflicts.
+    /// A value of 1 means the operation succeeded on the first try.
+    #[serde(default)]
+    pub num_attempts: u32,
 }
 
 #[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
@@ -1475,7 +1485,7 @@ impl NativeTableExt for Arc<dyn BaseTable> {
 }
 
 /// A table in a LanceDB database.
-#[derive(Debug, Clone)]
+#[derive(Clone)]
 pub struct NativeTable {
     name: String,
     namespace: Vec<String>,
@@ -1485,6 +1495,22 @@ pub struct NativeTable {
     // This comes from the connection options. We store here so we can pass down
     // to the dataset when we recreate it (for example, in checkout_latest).
     read_consistency_interval: Option<std::time::Duration>,
+    // Optional namespace client for server-side query execution.
+    // When set, queries will be executed on the namespace server instead of locally.
+    namespace_client: Option<Arc<dyn LanceNamespace>>,
+}
+
+impl std::fmt::Debug for NativeTable {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("NativeTable")
+            .field("name", &self.name)
+            .field("namespace", &self.namespace)
+            .field("id", &self.id)
+            .field("uri", &self.uri)
+            .field("read_consistency_interval", &self.read_consistency_interval)
+            .field("namespace_client", &self.namespace_client)
+            .finish()
+    }
 }
 
 impl std::fmt::Display for NativeTable {
@@ -1519,7 +1545,7 @@ impl NativeTable {
     /// * A [NativeTable] object.
     pub async fn open(uri: &str) -> Result<Self> {
         let name = Self::get_table_name(uri)?;
-        Self::open_with_params(uri, &name, vec![], None, None, None).await
+        Self::open_with_params(uri, &name, vec![], None, None, None, None).await
     }
 
     /// Opens an existing Table
@@ -1529,10 +1555,12 @@ impl NativeTable {
     /// * `base_path` - The base path where the table is located
     /// * `name` The Table name
     /// * `params` The [ReadParams] to use when opening the table
+    /// * `namespace_client` - Optional namespace client for server-side query execution
     ///
     /// # Returns
     ///
     /// * A [NativeTable] object.
+    #[allow(clippy::too_many_arguments)]
     pub async fn open_with_params(
         uri: &str,
         name: &str,
@@ -1540,6 +1568,7 @@ impl NativeTable {
         write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
         params: Option<ReadParams>,
         read_consistency_interval: Option<std::time::Duration>,
+        namespace_client: Option<Arc<dyn LanceNamespace>>,
     ) -> Result<Self> {
         let params = params.unwrap_or_default();
         // patch the params if we have a write store wrapper
@@ -1570,9 +1599,18 @@ impl NativeTable {
             uri: uri.to_string(),
             dataset,
             read_consistency_interval,
+            namespace_client,
         })
     }
 
+    /// Set the namespace client for server-side query execution.
+    ///
+    /// When set, queries will be executed on the namespace server instead of locally.
+    pub fn with_namespace_client(mut self, namespace_client: Arc<dyn LanceNamespace>) -> Self {
+        self.namespace_client = Some(namespace_client);
+        self
+    }
+
     fn get_table_name(uri: &str) -> Result<String> {
         let path = Path::new(uri);
         let name = path
@@ -1609,10 +1647,12 @@ impl NativeTable {
     /// * `namespace` - The namespace path. When non-empty, an explicit URI must be provided.
     /// * `batches` RecordBatch to be saved in the database.
     /// * `params` - Write parameters.
+    /// * `namespace_client` - Optional namespace client for server-side query execution
     ///
     /// # Returns
     ///
     /// * A [TableImpl] object.
+    #[allow(clippy::too_many_arguments)]
     pub async fn create(
         uri: &str,
         name: &str,
@@ -1621,6 +1661,7 @@ impl NativeTable {
         write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
         params: Option<WriteParams>,
         read_consistency_interval: Option<std::time::Duration>,
+        namespace_client: Option<Arc<dyn LanceNamespace>>,
     ) -> Result<Self> {
         // Default params uses format v1.
         let params = params.unwrap_or(WriteParams {
@@ -1652,9 +1693,11 @@ impl NativeTable {
             uri: uri.to_string(),
             dataset: DatasetConsistencyWrapper::new_latest(dataset, read_consistency_interval),
             read_consistency_interval,
+            namespace_client,
         })
     }
 
+    #[allow(clippy::too_many_arguments)]
     pub async fn create_empty(
         uri: &str,
         name: &str,
@@ -1663,6 +1706,7 @@ impl NativeTable {
         write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
         params: Option<WriteParams>,
         read_consistency_interval: Option<std::time::Duration>,
+        namespace_client: Option<Arc<dyn LanceNamespace>>,
     ) -> Result<Self> {
         let batches = RecordBatchIterator::new(vec![], schema);
         Self::create(
@@ -1673,6 +1717,7 @@ impl NativeTable {
             write_store_wrapper,
             params,
             read_consistency_interval,
+            namespace_client,
         )
         .await
     }
@@ -1810,8 +1855,17 @@ impl NativeTable {
     }
 
     // Helper to get num_sub_vectors with default calculation
-    fn get_num_sub_vectors(provided: Option<u32>, dim: u32) -> u32 {
-        provided.unwrap_or_else(|| suggested_num_sub_vectors(dim))
+    fn get_num_sub_vectors(provided: Option<u32>, dim: u32, num_bits: Option<u32>) -> u32 {
+        if let Some(provided) = provided {
+            return provided;
+        }
+        let suggested = suggested_num_sub_vectors(dim);
+        if num_bits.is_some_and(|num_bits| num_bits == 4) && suggested % 2 != 0 {
+            // num_sub_vectors must be even when 4 bits are used
+            suggested + 1
+        } else {
+            suggested
+        }
     }
 
     // Helper to extract vector dimension from field
@@ -1834,7 +1888,7 @@ impl NativeTable {
                     // Use IvfPq as the default for auto vector indices
                     let dim = Self::get_vector_dimension(field)?;
                     let ivf_params = lance_index::vector::ivf::IvfBuildParams::default();
-                    let num_sub_vectors = Self::get_num_sub_vectors(None, dim);
+                    let num_sub_vectors = Self::get_num_sub_vectors(None, dim, None);
                     let pq_params =
                         lance_index::vector::pq::PQBuildParams::new(num_sub_vectors as usize, 8);
                     let lance_idx_params =
@@ -1892,6 +1946,25 @@ impl NativeTable {
                     VectorIndexParams::with_ivf_flat_params(index.distance_type.into(), ivf_params);
                 Ok(Box::new(lance_idx_params))
             }
+            Index::IvfSq(index) => {
+                Self::validate_index_type(field, "IVF SQ", supported_vector_data_type)?;
+                let ivf_params = Self::build_ivf_params(
+                    index.num_partitions,
+                    index.target_partition_size,
+                    index.sample_rate,
+                    index.max_iterations,
+                );
+                let sq_params = SQBuildParams {
+                    sample_rate: index.sample_rate as usize,
+                    ..Default::default()
+                };
+                let lance_idx_params = VectorIndexParams::with_ivf_sq_params(
+                    index.distance_type.into(),
+                    ivf_params,
+                    sq_params,
+                );
+                Ok(Box::new(lance_idx_params))
+            }
             Index::IvfPq(index) => {
                 Self::validate_index_type(field, "IVF PQ", supported_vector_data_type)?;
                 let dim = Self::get_vector_dimension(field)?;
@@ -1901,7 +1974,8 @@ impl NativeTable {
                     index.sample_rate,
                     index.max_iterations,
                 );
-                let num_sub_vectors = Self::get_num_sub_vectors(index.num_sub_vectors, dim);
+                let num_sub_vectors =
+                    Self::get_num_sub_vectors(index.num_sub_vectors, dim, index.num_bits);
                 let num_bits = index.num_bits.unwrap_or(8) as usize;
                 let mut pq_params = PQBuildParams::new(num_sub_vectors as usize, num_bits);
                 pq_params.max_iters = index.max_iterations as usize;
@@ -1937,7 +2011,8 @@ impl NativeTable {
                     index.sample_rate,
                     index.max_iterations,
                 );
-                let num_sub_vectors = Self::get_num_sub_vectors(index.num_sub_vectors, dim);
+                let num_sub_vectors =
+                    Self::get_num_sub_vectors(index.num_sub_vectors, dim, index.num_bits);
                 let hnsw_params = HnswBuildParams::default()
                     .num_edges(index.m as usize)
                     .ef_construction(index.ef_construction as usize);
@@ -1997,6 +2072,7 @@ impl NativeTable {
             Index::LabelList(_) => IndexType::LabelList,
             Index::FTS(_) => IndexType::Inverted,
             Index::IvfFlat(_)
+            | Index::IvfSq(_)
             | Index::IvfPq(_)
             | Index::IvfRq(_)
             | Index::IvfHnswPq(_)
@@ -2019,6 +2095,278 @@ impl NativeTable {
         Ok(DatasetRecordBatchStream::new(inner))
     }
 
+    /// Execute a query on the namespace server instead of locally.
+    async fn namespace_query(
+        &self,
+        namespace_client: Arc<dyn LanceNamespace>,
+        query: &AnyQuery,
+        _options: QueryExecutionOptions,
+    ) -> Result<DatasetRecordBatchStream> {
+        // Build table_id from namespace + table name
+        let mut table_id = self.namespace.clone();
+        table_id.push(self.name.clone());
+
+        // Convert AnyQuery to namespace QueryTableRequest
+        let mut ns_request = self.convert_to_namespace_query(query)?;
+        // Set the table ID on the request
+        ns_request.id = Some(table_id);
+
+        // Call the namespace query_table API
+        let response_bytes = namespace_client
+            .query_table(ns_request)
+            .await
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to execute server-side query: {}", e),
+            })?;
+
+        // Parse the Arrow IPC response into a RecordBatchStream
+        self.parse_arrow_ipc_response(response_bytes).await
+    }
+
+    /// Convert a QueryFilter to a SQL string for the namespace API.
+    fn filter_to_sql(&self, filter: &QueryFilter) -> Result<String> {
+        match filter {
+            QueryFilter::Sql(sql) => Ok(sql.clone()),
+            QueryFilter::Substrait(_) => Err(Error::NotSupported {
+                message: "Substrait filters are not supported for server-side queries".to_string(),
+            }),
+            QueryFilter::Datafusion(_) => Err(Error::NotSupported {
+                message: "Datafusion expression filters are not supported for server-side queries. Use SQL filter instead.".to_string(),
+            }),
+        }
+    }
+
+    /// Convert an AnyQuery to the namespace QueryTableRequest format.
+    fn convert_to_namespace_query(&self, query: &AnyQuery) -> Result<NsQueryTableRequest> {
+        match query {
+            AnyQuery::VectorQuery(vq) => {
+                // Extract the query vector(s)
+                let vector = self.extract_query_vector(&vq.query_vector)?;
+
+                // Convert filter to SQL string
+                let filter = match &vq.base.filter {
+                    Some(f) => Some(self.filter_to_sql(f)?),
+                    None => None,
+                };
+
+                // Convert select to columns list
+                let columns = match &vq.base.select {
+                    Select::All => None,
+                    Select::Columns(cols) => Some(cols.clone()),
+                    Select::Dynamic(_) => {
+                        return Err(Error::NotSupported {
+                            message:
+                                "Dynamic column selection is not supported for server-side queries"
+                                    .to_string(),
+                        });
+                    }
+                };
+
+                // Check for unsupported features
+                if vq.base.reranker.is_some() {
+                    return Err(Error::NotSupported {
+                        message: "Reranker is not supported for server-side queries".to_string(),
+                    });
+                }
+
+                // Convert FTS query if present
+                let full_text_query = vq.base.full_text_search.as_ref().map(|fts| {
+                    let columns = fts.columns();
+                    let columns_vec = if columns.is_empty() {
+                        None
+                    } else {
+                        Some(columns.into_iter().collect())
+                    };
+                    Box::new(QueryTableRequestFullTextQuery {
+                        string_query: Some(Box::new(StringFtsQuery {
+                            query: fts.query.to_string(),
+                            columns: columns_vec,
+                        })),
+                        structured_query: None,
+                    })
+                });
+
+                Ok(NsQueryTableRequest {
+                    id: None, // Will be set in namespace_query
+                    k: vq.base.limit.unwrap_or(10) as i32,
+                    vector: Box::new(vector),
+                    vector_column: vq.column.clone(),
+                    filter,
+                    columns,
+                    offset: vq.base.offset.map(|o| o as i32),
+                    distance_type: vq.distance_type.map(|dt| dt.to_string()),
+                    nprobes: Some(vq.minimum_nprobes as i32),
+                    ef: vq.ef.map(|e| e as i32),
+                    refine_factor: vq.refine_factor.map(|r| r as i32),
+                    lower_bound: vq.lower_bound,
+                    upper_bound: vq.upper_bound,
+                    prefilter: Some(vq.base.prefilter),
+                    fast_search: Some(vq.base.fast_search),
+                    with_row_id: Some(vq.base.with_row_id),
+                    bypass_vector_index: Some(!vq.use_index),
+                    full_text_query,
+                    version: None,
+                })
+            }
+            AnyQuery::Query(q) => {
+                // For non-vector queries, pass an empty vector (similar to remote table implementation)
+                if q.reranker.is_some() {
+                    return Err(Error::NotSupported {
+                        message: "Reranker is not supported for server-side query execution"
+                            .to_string(),
+                    });
+                }
+
+                let filter = q
+                    .filter
+                    .as_ref()
+                    .map(|f| self.filter_to_sql(f))
+                    .transpose()?;
+
+                let columns = match &q.select {
+                    Select::All => None,
+                    Select::Columns(cols) => Some(cols.clone()),
+                    Select::Dynamic(_) => {
+                        return Err(Error::NotSupported {
+                            message: "Dynamic columns are not supported for server-side query"
+                                .to_string(),
+                        });
+                    }
+                };
+
+                // Handle full text search if present
+                let full_text_query = q.full_text_search.as_ref().map(|fts| {
+                    let columns_vec = if fts.columns().is_empty() {
+                        None
+                    } else {
+                        Some(fts.columns().iter().cloned().collect())
+                    };
+                    Box::new(QueryTableRequestFullTextQuery {
+                        string_query: Some(Box::new(StringFtsQuery {
+                            query: fts.query.to_string(),
+                            columns: columns_vec,
+                        })),
+                        structured_query: None,
+                    })
+                });
+
+                // Empty vector for non-vector queries
+                let vector = Box::new(QueryTableRequestVector {
+                    single_vector: Some(vec![]),
+                    multi_vector: None,
+                });
+
+                Ok(NsQueryTableRequest {
+                    id: None, // Will be set by caller
+                    vector,
+                    k: q.limit.unwrap_or(10) as i32,
+                    filter,
+                    columns,
+                    prefilter: Some(q.prefilter),
+                    offset: q.offset.map(|o| o as i32),
+                    ef: None,
+                    refine_factor: None,
+                    distance_type: None,
+                    nprobes: None,
+                    vector_column: None, // No vector column for plain queries
+                    with_row_id: Some(q.with_row_id),
+                    bypass_vector_index: Some(true), // No vector index for plain queries
+                    full_text_query,
+                    version: None,
+                    fast_search: None,
+                    lower_bound: None,
+                    upper_bound: None,
+                })
+            }
+        }
+    }
+
+    /// Extract query vector(s) from Arrow arrays into the namespace format.
+    fn extract_query_vector(
+        &self,
+        query_vectors: &[Arc<dyn arrow_array::Array>],
+    ) -> Result<QueryTableRequestVector> {
+        if query_vectors.is_empty() {
+            return Err(Error::InvalidInput {
+                message: "Query vector is required for vector search".to_string(),
+            });
+        }
+
+        // Handle single vector case
+        if query_vectors.len() == 1 {
+            let arr = &query_vectors[0];
+            let single_vector = self.array_to_f32_vec(arr)?;
+            Ok(QueryTableRequestVector {
+                single_vector: Some(single_vector),
+                multi_vector: None,
+            })
+        } else {
+            // Handle multi-vector case
+            let multi_vector: Result<Vec<Vec<f32>>> = query_vectors
+                .iter()
+                .map(|arr| self.array_to_f32_vec(arr))
+                .collect();
+            Ok(QueryTableRequestVector {
+                single_vector: None,
+                multi_vector: Some(multi_vector?),
+            })
+        }
+    }
+
+    /// Convert an Arrow array to a Vec<f32>.
+    fn array_to_f32_vec(&self, arr: &Arc<dyn arrow_array::Array>) -> Result<Vec<f32>> {
+        // Handle FixedSizeList (common for vectors)
+        if let Some(fsl) = arr
+            .as_any()
+            .downcast_ref::<arrow_array::FixedSizeListArray>()
+        {
+            let values = fsl.values();
+            if let Some(f32_arr) = values.as_any().downcast_ref::<arrow_array::Float32Array>() {
+                return Ok(f32_arr.values().to_vec());
+            }
+        }
+
+        // Handle direct Float32Array
+        if let Some(f32_arr) = arr.as_any().downcast_ref::<arrow_array::Float32Array>() {
+            return Ok(f32_arr.values().to_vec());
+        }
+
+        Err(Error::InvalidInput {
+            message: "Query vector must be Float32 type".to_string(),
+        })
+    }
+
+    /// Parse Arrow IPC response from the namespace server.
+    async fn parse_arrow_ipc_response(
+        &self,
+        bytes: bytes::Bytes,
+    ) -> Result<DatasetRecordBatchStream> {
+        use arrow_ipc::reader::StreamReader;
+        use std::io::Cursor;
+
+        let cursor = Cursor::new(bytes);
+        let reader = StreamReader::try_new(cursor, None).map_err(|e| Error::Runtime {
+            message: format!("Failed to parse Arrow IPC response: {}", e),
+        })?;
+
+        // Collect all record batches
+        let schema = reader.schema();
+        let batches: Vec<_> = reader
+            .into_iter()
+            .collect::<std::result::Result<Vec<_>, _>>()
+            .map_err(|e| Error::Runtime {
+                message: format!("Failed to read Arrow IPC batches: {}", e),
+            })?;
+
+        // Create a stream from the batches
+        let stream = futures::stream::iter(batches.into_iter().map(Ok));
+        let record_batch_stream = Box::pin(
+            datafusion_physical_plan::stream::RecordBatchStreamAdapter::new(schema, stream),
+        );
+
+        Ok(DatasetRecordBatchStream::new(record_batch_stream))
+    }
+
     /// Check whether the table uses V2 manifest paths.
     ///
     /// See [Self::migrate_manifest_paths_v2] and [ManifestNamingScheme] for
@@ -2450,6 +2798,12 @@ impl BaseTable for NativeTable {
         query: &AnyQuery,
         options: QueryExecutionOptions,
     ) -> Result<DatasetRecordBatchStream> {
+        // If namespace client is configured, use server-side query execution
+        if let Some(ref namespace_client) = self.namespace_client {
+            return self
+                .namespace_query(namespace_client.clone(), query, options)
+                .await;
+        }
         self.generic_query(query, options).await
     }
 
@@ -2520,6 +2874,7 @@ impl BaseTable for NativeTable {
             num_updated_rows: stats.num_updated_rows,
             num_inserted_rows: stats.num_inserted_rows,
             num_deleted_rows: stats.num_deleted_rows,
+            num_attempts: stats.num_attempts,
         })
     }
 
@@ -2917,7 +3272,7 @@ mod tests {
 
         let batches = make_test_batches();
         let batches = Box::new(batches) as Box<dyn RecordBatchReader + Send>;
-        let table = NativeTable::create(uri, "test", vec![], batches, None, None, None)
+        let table = NativeTable::create(uri, "test", vec![], batches, None, None, None, None)
             .await
             .unwrap();
 
@@ -2979,9 +3334,13 @@ mod tests {
         // Perform a "insert if not exists"
         let mut merge_insert_builder = table.merge_insert(&["i"]);
         merge_insert_builder.when_not_matched_insert_all();
-        merge_insert_builder.execute(new_batches).await.unwrap();
+        let result = merge_insert_builder.execute(new_batches).await.unwrap();
         // Only 5 rows should actually be inserted
         assert_eq!(table.count_rows(None).await.unwrap(), 15);
+        assert_eq!(result.num_inserted_rows, 5);
+        assert_eq!(result.num_updated_rows, 0);
+        assert_eq!(result.num_deleted_rows, 0);
+        assert_eq!(result.num_attempts, 1);
 
         // Create new data with i=15..25 (no id matches)
         let new_batches = Box::new(merge_insert_test_batches(15, 2));
@@ -4122,6 +4481,8 @@ mod tests {
         table.prewarm_index("text_idx").await.unwrap();
     }
 
+    // Windows does not support precise sleep durations due to timer resolution limitations.
+    #[cfg(not(target_os = "windows"))]
     #[tokio::test]
     async fn test_read_consistency_interval() {
         let intervals = vec![
@@ -4551,4 +4912,91 @@ mod tests {
         assert_eq!(result.len(), 1);
         assert_eq!(result[0].index_type, crate::index::IndexType::Bitmap);
     }
+
+    #[tokio::test]
+    async fn test_convert_to_namespace_query_vector() {
+        let tmp_dir = tempdir().unwrap();
+        let dataset_path = tmp_dir.path().join("test_ns_query.lance");
+
+        let batches = make_test_batches();
+        Dataset::write(batches, dataset_path.to_str().unwrap(), None)
+            .await
+            .unwrap();
+
+        let table = NativeTable::open(dataset_path.to_str().unwrap())
+            .await
+            .unwrap();
+
+        // Create a vector query
+        let query_vector = Arc::new(Float32Array::from(vec![1.0, 2.0, 3.0, 4.0]));
+        let vq = VectorQueryRequest {
+            base: QueryRequest {
+                limit: Some(10),
+                offset: Some(5),
+                filter: Some(QueryFilter::Sql("id > 0".to_string())),
+                select: Select::Columns(vec!["id".to_string()]),
+                ..Default::default()
+            },
+            column: Some("vector".to_string()),
+            query_vector: vec![query_vector as Arc<dyn Array>],
+            minimum_nprobes: 20,
+            distance_type: Some(crate::DistanceType::L2),
+            ..Default::default()
+        };
+
+        let any_query = AnyQuery::VectorQuery(vq);
+        let ns_request = table.convert_to_namespace_query(&any_query).unwrap();
+
+        assert_eq!(ns_request.k, 10);
+        assert_eq!(ns_request.offset, Some(5));
+        assert_eq!(ns_request.filter, Some("id > 0".to_string()));
+        assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(ns_request.vector_column, Some("vector".to_string()));
+        assert_eq!(ns_request.distance_type, Some("l2".to_string()));
+        assert!(ns_request.vector.single_vector.is_some());
+        assert_eq!(
+            ns_request.vector.single_vector.as_ref().unwrap(),
+            &vec![1.0, 2.0, 3.0, 4.0]
+        );
+    }
+
+    #[tokio::test]
+    async fn test_convert_to_namespace_query_plain_query() {
+        let tmp_dir = tempdir().unwrap();
+        let dataset_path = tmp_dir.path().join("test_ns_plain.lance");
+
+        let batches = make_test_batches();
+        Dataset::write(batches, dataset_path.to_str().unwrap(), None)
+            .await
+            .unwrap();
+
+        let table = NativeTable::open(dataset_path.to_str().unwrap())
+            .await
+            .unwrap();
+
+        // Create a plain (non-vector) query with filter and select
+        let q = QueryRequest {
+            limit: Some(20),
+            offset: Some(5),
+            filter: Some(QueryFilter::Sql("id > 5".to_string())),
+            select: Select::Columns(vec!["id".to_string()]),
+            with_row_id: true,
+            ..Default::default()
+        };
+
+        let any_query = AnyQuery::Query(q);
+        let ns_request = table.convert_to_namespace_query(&any_query).unwrap();
+
+        // Plain queries should pass an empty vector
+        assert_eq!(ns_request.k, 20);
+        assert_eq!(ns_request.offset, Some(5));
+        assert_eq!(ns_request.filter, Some("id > 5".to_string()));
+        assert_eq!(ns_request.columns, Some(vec!["id".to_string()]));
+        assert_eq!(ns_request.with_row_id, Some(true));
+        assert_eq!(ns_request.bypass_vector_index, Some(true));
+        assert!(ns_request.vector_column.is_none()); // No vector column for plain queries
+
+        // Should have an empty vector
+        assert!(ns_request.vector.single_vector.as_ref().unwrap().is_empty());
+    }
 }