Bump version: 0.25.4-beta.2 → 0.25.4-beta.3

Add support for enabling stable row IDs when creating tables via the
`new_table_enable_stable_row_ids` storage option.

Stable row IDs ensure that row identifiers remain constant after
compaction, update, delete, and merge operations. This is useful for
materialized views and other use cases that need to track source rows
across these operations.

The option can be set at two levels:
- Connection level: applies to all tables created with that connection
- Table level: per-table override via create_table storage_options

🤖 Generated with [Claude Code](https://claude.com/claude-code)

---------

Co-authored-by: Claude <noreply@anthropic.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.3"
+current_version = "0.22.4-beta.2"
 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

@@ -63,27 +63,18 @@ jobs:
           git config user.name "lancedb automation"
           git config user.email "robot@lancedb.com"
 
-      - name: Configure Codex authentication
-        env:
-          CODEX_TOKEN_B64: ${{ secrets.CODEX_TOKEN }}
-        run: |
-          if [ -z "${CODEX_TOKEN_B64}" ]; then
-            echo "Repository secret CODEX_TOKEN is not defined; skipping Codex execution."
-            exit 1
-          fi
-          mkdir -p ~/.codex
-          echo "${CODEX_TOKEN_B64}" | base64 --decode > ~/.codex/auth.json
-
       - name: Run Codex to update Lance dependency
         env:
           TAG: ${{ inputs.tag }}
           GITHUB_TOKEN: ${{ secrets.ROBOT_TOKEN }}
           GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+          OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
         run: |
           set -euo pipefail
           VERSION="${TAG#refs/tags/}"
           VERSION="${VERSION#v}"
           BRANCH_NAME="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
           cat <<EOF >/tmp/codex-prompt.txt
           You are running inside the lancedb repository on a GitHub Actions runner. Update the Lance dependency to version ${VERSION} and prepare a pull request for maintainers to review.
 
@@ -104,4 +95,33 @@ jobs:
           - Do not merge the PR.
           - If any command fails, diagnose and fix the issue instead of aborting.
           EOF
+
+          printenv OPENAI_API_KEY | codex login --with-api-key
           codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"
+
+      - name: Trigger sophon dependency update
+        env:
+          TAG: ${{ inputs.tag }}
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          VERSION="${TAG#refs/tags/}"
+          VERSION="${VERSION#v}"
+          LANCEDB_BRANCH="codex/update-lance-${VERSION//[^a-zA-Z0-9]/-}"
+
+          echo "Triggering sophon workflow with:"
+          echo "  lance_ref: ${TAG#refs/tags/}"
+          echo "  lancedb_ref: ${LANCEDB_BRANCH}"
+
+          gh workflow run codex-bump-lancedb-lance.yml \
+            --repo lancedb/sophon \
+            -f lance_ref="${TAG#refs/tags/}" \
+            -f lancedb_ref="${LANCEDB_BRANCH}"
+
+      - name: Show latest sophon workflow run
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          echo "Latest sophon workflow run:"
+          gh run list --repo lancedb/sophon --workflow codex-bump-lancedb-lance.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/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/lance-format/ --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/ -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
+    - uses: Swatinem/rust-cache@v2
-      with:
+    - name: Format Rust
-        components: rustfmt, clippy
+      run: cargo fmt --all -- --check
-    - name: Lint
+    - 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/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:
@@ -65,7 +65,7 @@ jobs:
       matrix:
         config:
           - target: x86_64-apple-darwin
-            runner: macos-13
+            runner: macos-15-large
           - 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.${{ matrix.python-minor-version }}
-      - uses: Swatinem/rust-cache@v2
-        with:
-          workspaces: python
       - uses: ./.github/workflows/build_linux_wheel
+        with:
+          args: --profile ci
       - uses: ./.github/workflows/run_tests
         with:
           integration: true
@@ -152,7 +149,7 @@ jobs:
       matrix:
         config:
           - name: x86
-            runner: macos-13
+            runner: macos-15-large
           - name: Arm
             runner: macos-14
     runs-on: "${{ matrix.config.runner }}"
@@ -169,10 +166,9 @@ 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 +195,9 @@ 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 +226,7 @@ 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: |
+        run: sudo apt install -y protobuf-compiler libssl-dev
-          # 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
       - 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 = { "version" = "=1.0.0-beta.16", default-features = false, "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+lance-core = { "version" = "=1.0.0-beta.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "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.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "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.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/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-io = { "version" = "=1.0.0-beta.16", default-features = false, "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+lance-index = { "version" = "=1.0.0-beta.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "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.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/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 = { "version" = "=1.0.0-beta.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/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-namespace-impls = { "version" = "=1.0.0-beta.16", default-features = false, "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=1.0.0-beta.2", "tag" = "v1.0.0-beta.2", "git" = "https://github.com/lancedb/lance.git" }
+lance-table = { "version" = "=1.0.0-beta.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "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.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "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.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "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.16", "tag" = "v1.0.0-beta.16", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "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.16", "tag" = "v1.0.0-beta.16", "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 = { "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" = "https://github.com/lancedb/lance.git" }
+    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>0.22.3-final.0</version>
+        <version>0.22.4-beta.2</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>0.22.3-final.0</version>
+        <version>0.22.4-beta.2</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.22.3-final.0</version>
+    <version>0.22.4-beta.2</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 = "0.22.3"
+version = "0.22.4-beta.2"
 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": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

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

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.22.3",
+  "version": "0.22.4-beta.2",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.22.3",
+	"version": "0.22.4-beta.2",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.22.3",
+  "version": "0.22.4-beta.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.22.3",
+      "version": "0.22.4-beta.2",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.22.3",
+  "version": "0.22.4-beta.2",
   "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 = "0.25.4-beta.3"
 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 = "0.25.4-beta.3"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

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

@@ -26,7 +26,7 @@ class Connection(object):
     async def close(self): ...
     async def list_namespaces(
         self,
-        namespace: List[str],
+        namespace: Optional[List[str]],
         page_token: Optional[str],
         limit: Optional[int],
     ) -> List[str]: ...
@@ -34,7 +34,7 @@ class Connection(object):
     async def drop_namespace(self, namespace: List[str]) -> None: ...
     async def table_names(
         self,
-        namespace: List[str],
+        namespace: Optional[List[str]],
         start_after: Optional[str],
         limit: Optional[int],
     ) -> list[str]: ...
@@ -43,7 +43,7 @@ class Connection(object):
         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 +53,7 @@ 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 +61,7 @@ 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 +71,7 @@ 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 +80,13 @@ class Connection(object):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
-        new_namespace: List[str] = [],
+        new_namespace: Optional[List[str]] = None,
     ) -> None: ...
-    async def drop_table(self, name: str, namespace: List[str] = []) -> None: ...
+    async def drop_table(
-    async def drop_all_tables(self, namespace: List[str] = []) -> None: ...
+        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: ...
@@ -306,6 +308,7 @@ 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

@@ -54,7 +54,7 @@ class DBConnection(EnforceOverrides):
 
     def list_namespaces(
         self,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
         limit: int = 10,
     ) -> Iterable[str]:
@@ -75,6 +75,8 @@ class DBConnection(EnforceOverrides):
         Iterable of str
             List of immediate child namespace names
         """
+        if namespace is None:
+            namespace = []
         return []
 
     def create_namespace(self, namespace: List[str]) -> None:
@@ -107,7 +109,7 @@ class DBConnection(EnforceOverrides):
         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 +144,7 @@ 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 +193,11 @@ 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 +314,7 @@ 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 +345,7 @@ 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 +353,7 @@ 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 +364,16 @@ 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] = [],
+        cur_namespace: Optional[List[str]] = None,
-        new_namespace: List[str] = [],
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -382,6 +390,10 @@ 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 +403,7 @@ 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 +413,8 @@ 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 +486,12 @@ 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)
@@ -535,7 +555,7 @@ 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]:
@@ -556,6 +576,8 @@ class LanceDBConnection(DBConnection):
         Iterable of str
             List of immediate child namespace names
         """
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.list_namespaces(
                 namespace=namespace, page_token=page_token, limit=limit
@@ -590,7 +612,7 @@ 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.
 
@@ -608,6 +630,8 @@ class LanceDBConnection(DBConnection):
         Iterator of str.
             A list of table names.
         """
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.table_names(
                 namespace=namespace, start_after=page_token, limit=limit
@@ -632,7 +656,7 @@ 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 +673,8 @@ 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 +700,7 @@ 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 +718,8 @@ 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 +745,7 @@ 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 +778,8 @@ 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 +800,7 @@ 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 +814,8 @@ 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 +823,9 @@ 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 +833,8 @@ class LanceDBConnection(DBConnection):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
-        new_namespace: List[str] = [],
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -815,6 +849,10 @@ 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,
@@ -904,7 +942,7 @@ 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]:
@@ -925,6 +963,8 @@ class AsyncConnection(object):
         Iterable of str
             List of immediate child namespace names (not full paths)
         """
+        if namespace is None:
+            namespace = []
         return await self._inner.list_namespaces(
             namespace=namespace, page_token=page_token, limit=limit
         )
@@ -952,7 +992,7 @@ class AsyncConnection(object):
     async def table_names(
         self,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
         start_after: Optional[str] = None,
         limit: Optional[int] = None,
     ) -> Iterable[str]:
@@ -976,6 +1016,8 @@ class AsyncConnection(object):
         -------
         Iterable of str
         """
+        if namespace is None:
+            namespace = []
         return await self._inner.table_names(
             namespace=namespace, start_after=start_after, limit=limit
         )
@@ -992,7 +1034,7 @@ 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 +1081,11 @@ 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 +1195,8 @@ 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 +1254,7 @@ 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 +1273,7 @@ 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 +1296,8 @@ 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 +1313,7 @@ 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 +1346,8 @@ 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 +1362,8 @@ class AsyncConnection(object):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
-        new_namespace: List[str] = [],
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -1328,6 +1380,10 @@ 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 +1392,7 @@ 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 +1407,8 @@ 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 +1417,7 @@ 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 +1426,8 @@ 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

@@ -609,9 +609,19 @@ class IvfPq:
 class IvfRq:
     """Describes an IVF RQ Index
 
-    IVF-RQ (Residual Quantization) stores a compressed copy of each vector using
+    IVF-RQ (RabitQ Quantization) compresses vectors using RabitQ quantization
-    residual quantization and organizes them into IVF partitions. Parameters
+    and organizes them into IVF partitions.
-    largely mirror IVF-PQ for consistency.
+
+    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 +638,7 @@ 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.

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
 
@@ -23,7 +24,7 @@ import pyarrow as pa
 
 from lancedb.db import DBConnection, LanceDBConnection
 from lancedb.io import StorageOptionsProvider
-from lancedb.table import LanceTable, Table
+from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
 from lancedb.common import DATA
 from lancedb.pydantic import LanceModel
@@ -99,7 +100,14 @@ def _convert_pyarrow_schema_to_json(schema: pa.Schema) -> JsonArrowSchema:
         )
         fields.append(json_field)
 
-    return JsonArrowSchema(fields=fields, metadata=schema.metadata)
+    # decode binary metadata to strings for JSON
+    meta = None
+    if schema.metadata:
+        meta = {
+            k.decode("utf-8"): v.decode("utf-8") for k, v in schema.metadata.items()
+        }
+
+    return JsonArrowSchema(fields=fields, metadata=meta)
 
 
 class LanceNamespaceStorageOptionsProvider(StorageOptionsProvider):
@@ -119,13 +127,17 @@ class LanceNamespaceStorageOptionsProvider(StorageOptionsProvider):
 
     Examples
     --------
-    >>> from lance_namespace import connect as namespace_connect
+    Create a provider and fetch storage options::
-    >>> namespace = namespace_connect("rest", {"url": "https://..."})
+
-    >>> provider = LanceNamespaceStorageOptionsProvider(
+        from lance_namespace import connect as namespace_connect
-    ...     namespace=namespace,
+
-    ...     table_id=["my_namespace", "my_table"]
+        # Connect to namespace (requires a running namespace server)
-    ... )
+        namespace = namespace_connect("rest", {"uri": "https://..."})
-    >>> options = provider.fetch_storage_options()
+        provider = LanceNamespaceStorageOptionsProvider(
+            namespace=namespace,
+            table_id=["my_namespace", "my_table"]
+        )
+        options = provider.fetch_storage_options()
     """
 
     def __init__(self, namespace: LanceNamespace, table_id: List[str]):
@@ -227,8 +239,10 @@ class LanceNamespaceDBConnection(DBConnection):
         page_token: Optional[str] = None,
         limit: int = 10,
         *,
-        namespace: List[str] = [],
+        namespace: Optional[List[str]] = None,
     ) -> Iterable[str]:
+        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 []
@@ -245,12 +259,14 @@ 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)
@@ -339,11 +355,13 @@ 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)
@@ -373,8 +391,10 @@ 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)
@@ -384,9 +404,13 @@ class LanceNamespaceDBConnection(DBConnection):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
-        new_namespace: List[str] = [],
+        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"
         )
@@ -398,14 +422,16 @@ 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]:
@@ -427,6 +453,8 @@ class LanceNamespaceDBConnection(DBConnection):
         Iterable[str]
             Names of child namespaces.
         """
+        if namespace is None:
+            namespace = []
         request = ListNamespacesRequest(
             id=namespace, page_token=page_token, limit=limit
         )
@@ -464,13 +492,15 @@ class LanceNamespaceDBConnection(DBConnection):
         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,
@@ -490,6 +520,310 @@ 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."""
+        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: int = 10,
+    ) -> Iterable[str]:
+        """
+        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]
+            Pagination token for listing results.
+        limit : int
+            Maximum number of namespaces to return.
+
+        Returns
+        -------
+        Iterable[str]
+            Names of child namespaces.
+        """
+        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 []
+
+    async def create_namespace(self, namespace: List[str]) -> None:
+        """
+        Create a new namespace.
+
+        Parameters
+        ----------
+        namespace : List[str]
+            The namespace path to create.
+        """
+        request = CreateNamespaceRequest(id=namespace)
+        self._ns.create_namespace(request)
+
+    async def drop_namespace(self, namespace: List[str]) -> None:
+        """
+        Drop a namespace.
+
+        Parameters
+        ----------
+        namespace : List[str]
+            The namespace path to drop.
+        """
+        request = DropNamespaceRequest(id=namespace)
+        self._ns.drop_namespace(request)
+
+
 def connect_namespace(
     impl: str,
     properties: Dict[str, str],
@@ -534,3 +868,62 @@ 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/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 [
+        return [model(**row) for row in self.to_arrow(timeout=timeout).to_pylist()]
-            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()
-        ]
 
     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]}])
+        ...     table = await conn.create_table("my_table", [{"vector": [99.0, 99.0]}])
-        ...     query = [100, 100]
+        ...     plan = await table.query().nearest_to([1.0, 2.0]).explain_plan(True)
-        ...     plan = await table.query().nearest_to([1, 2]).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([1.0, 2.0]).nearest_to_text("hello").explain_plan(True)
-        ...     plan = await table.query().nearest_to([1, 2]).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]}])
+        ...     table = await conn.create_table("my_table", [{"vector": [99.0, 99.0]}])
-        ...     query = [100, 100]
+        ...     plan = await table.query().nearest_to([1.0, 2.0]).explain_plan(True)
-        ...     plan = await table.query().nearest_to([1, 2]).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

@@ -104,7 +104,7 @@ 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]:
@@ -125,6 +125,8 @@ class RemoteDBConnection(DBConnection):
         Iterable of str
             List of immediate child namespace names
         """
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.list_namespaces(
                 namespace=namespace, page_token=page_token, limit=limit
@@ -159,7 +161,7 @@ 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.
 
@@ -177,6 +179,8 @@ class RemoteDBConnection(DBConnection):
         -------
         An iterator of table names.
         """
+        if namespace is None:
+            namespace = []
         return LOOP.run(
             self._conn.table_names(
                 namespace=namespace, start_after=page_token, limit=limit
@@ -188,7 +192,7 @@ 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 +212,8 @@ 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 +228,7 @@ 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 +258,8 @@ 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 +283,7 @@ 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 +380,8 @@ class RemoteDBConnection(DBConnection):
         LanceTable(table4)
 
         """
+        if namespace is None:
+            namespace = []
         validate_table_name(name)
         if embedding_functions is not None:
             logging.warning(
@@ -396,7 +406,7 @@ 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 +417,8 @@ 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 +426,8 @@ class RemoteDBConnection(DBConnection):
         self,
         cur_name: str,
         new_name: str,
-        cur_namespace: List[str] = [],
+        cur_namespace: Optional[List[str]] = None,
-        new_namespace: List[str] = [],
+        new_namespace: Optional[List[str]] = None,
     ):
         """Rename a table in the database.
 
@@ -426,6 +438,10 @@ 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

@@ -652,6 +652,17 @@ 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

@@ -178,7 +178,7 @@ 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 +1018,7 @@ 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 +1708,18 @@ 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 +1768,14 @@ 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 +1799,10 @@ 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:
@@ -2618,7 +2627,7 @@ 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 +2687,12 @@ 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(
@@ -3622,7 +3634,7 @@ 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/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

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_namespace.py

@@ -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(list(namespaces)) == 0
+
+        # Create a namespace
+        await db.create_namespace(["test_namespace"])
+
+        # Verify namespace exists
+        namespaces = list(await db.list_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 = list(await db.list_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/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 = "0.22.3"
+version = "0.22.4-beta.2"
 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"]
+aws = ["lance/aws", "lance-io/aws", "lance-namespace-impls/dir-aws"]
-oss = ["lance/oss", "lance-io/oss"]
+oss = ["lance/oss", "lance-io/oss", "lance-namespace-impls/dir-oss"]
-gcs = ["lance/gcp", "lance-io/gcp"]
+gcs = ["lance/gcp", "lance-io/gcp", "lance-namespace-impls/dir-gcp"]
-azure = ["lance/azure", "lance-io/azure"]
+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

@@ -239,7 +239,7 @@ 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 +259,7 @@ 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>)>,
@@ -442,7 +442,7 @@ 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 +461,7 @@ 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>)>,
@@ -959,7 +959,7 @@ 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 +967,7 @@ 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>)>,
@@ -1102,7 +1102,7 @@ impl ConnectNamespaceBuilder {
 
     /// 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 +1110,7 @@ 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>)>,

rust/lancedb/src/database/listing.rs

@@ -35,6 +35,7 @@ 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 +49,12 @@ 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 +67,7 @@ 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 +94,14 @@ 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 +109,7 @@ 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 +134,12 @@ 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 +179,7 @@ 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 +189,7 @@ 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 +497,7 @@ 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 +519,7 @@ 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 +540,19 @@ 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 +561,7 @@ 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 +606,13 @@ 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;
         }
@@ -706,11 +748,15 @@ 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 =
+        let write_params = self.prepare_write_params(
-            self.prepare_write_params(&request, storage_version_override, v2_manifest_override);
+            &request,
+            storage_version_override,
+            v2_manifest_override,
+            stable_row_ids_override,
+        );
 
         let data_schema = request.data.arrow_schema();
 
@@ -921,7 +967,7 @@ 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};
@@ -1621,4 +1667,267 @@ 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,
+            })
+            .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,
+            })
+            .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,
+            })
+            .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/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

@@ -90,7 +90,7 @@ 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.

rust/lancedb/src/remote/table.rs

@@ -1183,6 +1183,7 @@ 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

@@ -467,6 +467,11 @@ 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)]
@@ -1810,8 +1815,17 @@ impl NativeTable {
     }
 
     // Helper to get num_sub_vectors with default calculation
-    fn get_num_sub_vectors(provided: Option<u32>, dim: u32) -> u32 {
+    fn get_num_sub_vectors(provided: Option<u32>, dim: u32, num_bits: Option<u32>) -> u32 {
-        provided.unwrap_or_else(|| suggested_num_sub_vectors(dim))
+        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 +1848,7 @@ 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 =
@@ -1901,7 +1915,8 @@ 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 +1952,8 @@ 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);
@@ -2520,6 +2536,7 @@ 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,
         })
     }
 
@@ -2979,9 +2996,13 @@ 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 +4143,8 @@ 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![