trigger ci

We have very low download stats for mac x86, and also latest github
runners for mac are all arm, so it makes sense at this point to
deprecate x86 support in general.

.bumpversion.toml

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

.cargo/config.toml

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

.github/ISSUE_TEMPLATE/documentation.yml

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

.github/workflows/build_linux_wheel/action.yml

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

.github/workflows/build_mac_wheel/action.yml

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

.github/workflows/build_windows_wheel/action.yml

@@ -26,7 +26,7 @@ runs:
       with:
         command: build
         args: ${{ inputs.args }}
-        docker-options: "-e PIP_EXTRA_INDEX_URL=https://pypi.fury.io/lancedb/"
+        docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python
     - uses: actions/upload-artifact@v4
       with:

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

@@ -1,6 +1,9 @@
 name: Codex Update Lance Dependency
 
 on:
+  pull_request:
+    paths:
+      - '.github/workflows/codex-update-lance-dependency.yml'
   workflow_call:
     inputs:
       tag:
@@ -11,7 +14,8 @@ on:
     inputs:
       tag:
         description: "Tag name from Lance"
-        required: true
+        required: false
+        default: "v1.0.0-rc.1"
         type: string
 
 permissions:
@@ -25,7 +29,7 @@ jobs:
     steps:
       - name: Show inputs
         run: |
-          echo "tag = ${{ inputs.tag }}"
+          echo "tag = ${{ inputs.tag || 'v1.0.0-rc.1' }}"
 
       - name: Checkout Repo LanceDB
         uses: actions/checkout@v4
@@ -65,7 +69,7 @@ jobs:
 
       - name: Run Codex to update Lance dependency
         env:
-          TAG: ${{ inputs.tag }}
+          TAG: ${{ inputs.tag || 'v1.0.0-rc.1' }}
           GITHUB_TOKEN: ${{ secrets.ROBOT_TOKEN }}
           GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
           OPENAI_API_KEY: ${{ secrets.CODEX_TOKEN }}
@@ -98,3 +102,50 @@ jobs:
 
           printenv OPENAI_API_KEY | codex login --with-api-key
           codex --config shell_environment_policy.ignore_default_excludes=true exec --dangerously-bypass-approvals-and-sandbox "$(cat /tmp/codex-prompt.txt)"
+
+      - name: Debug token access
+        env:
+          GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
+        run: |
+          set -euo pipefail
+          echo "=== Checking authenticated user ==="
+          gh api user --jq '.login' || echo "Failed to get user info"
+
+          echo ""
+          echo "=== Listing repos in lancedb org that token can access ==="
+          gh repo list lancedb --limit 50 --json name,visibility --jq '.[] | "\(.name) (\(.visibility))"' || echo "Failed to list repos"
+
+          echo ""
+          echo "=== Checking if sophon repo exists and is accessible ==="
+          gh repo view lancedb/sophon --json name,visibility 2>&1 || echo "Cannot access lancedb/sophon"
+
+          echo ""
+          echo "=== Checking token scopes ==="
+          gh api -i user 2>&1 | grep -i "x-oauth-scopes" || echo "Could not determine token scopes"
+
+      - name: Trigger sophon dependency update
+        env:
+          TAG: ${{ inputs.tag || 'v1.0.0-rc.1' }}
+          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

@@ -59,4 +59,4 @@ jobs:
           GH_TOKEN: ${{ secrets.ROBOT_TOKEN }}
         run: |
           set -euo pipefail
-          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,htmlUrl,displayTitle
+          gh run list --workflow codex-update-lance-dependency.yml --limit 1 --json databaseId,url,displayTitle

.github/workflows/npm-publish.yml

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

.github/workflows/pypi-publish.yml

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

.github/workflows/python.yml

@@ -18,7 +18,7 @@ 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:
@@ -79,7 +79,7 @@ jobs:
   doctest:
     name: "Doctest"
     timeout-minutes: 30
-    runs-on: "ubuntu-24.04"
+    runs-on: ubuntu-2404-8x-x64
     defaults:
       run:
         shell: bash
@@ -100,7 +100,7 @@ jobs:
           sudo apt install -y protobuf-compiler
       - 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
@@ -143,16 +143,9 @@ jobs:
       - name: Delete wheels
         run: rm -rf target/wheels
   platform:
-    name: "Mac: ${{ matrix.config.name }}"
+    name: "Mac"
     timeout-minutes: 30
-    strategy:
+    runs-on: macos-14
-      matrix:
-        config:
-          - name: x86
-            runner: macos-13
-          - name: Arm
-            runner: macos-14
-    runs-on: "${{ matrix.config.runner }}"
     defaults:
       run:
         shell: bash
@@ -226,7 +219,7 @@ jobs:
         run: |
           pip install "pydantic<2"
           pip install pyarrow==16
-          pip install --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
+          pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
           pip install tantivy
       - name: Run tests
         run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/run_tests/action.yml

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

.github/workflows/rust.yml

@@ -122,7 +122,7 @@ jobs:
     timeout-minutes: 30
     strategy:
       matrix:
-        mac-runner: ["macos-13", "macos-14"]
+        mac-runner: ["macos-14", "macos-15"]
     runs-on: "${{ matrix.mac-runner }}"
     defaults:
       run:

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=1.0.0-beta.3", default-features = false, "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", default-features = false, "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "features" = ["dir-aws", "dir-gcp", "dir-azure", "dir-oss", "rest"], "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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.3", "tag" = "v1.0.0-beta.3", "git" = "https://github.com/lance-format/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 }

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.** 
 

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/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/OpenTableOptions.md

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

docs/src/python/python.md

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

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.4-beta.1</version>
+        <version>0.22.4-beta.3</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/lance-namespace/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.22.4-beta.1</version>
+        <version>0.22.4-beta.3</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.22.4-beta.1</version>
+    <version>0.22.4-beta.3</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

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

nodejs/README.md

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

nodejs/lancedb/connection.ts

@@ -42,7 +42,7 @@ export interface CreateTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://lancedb.github.io/lancedb/guides/storage/
+   * The available options are described at https://lancedb.com/docs/storage/
    */
   storageOptions?: Record<string, string>;
 
@@ -78,7 +78,7 @@ export interface OpenTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://lancedb.github.io/lancedb/guides/storage/
+   * The available options are described at https://lancedb.com/docs/storage/
    */
   storageOptions?: Record<string, string>;
   /**

nodejs/lancedb/permutation.ts

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

nodejs/npm/darwin-arm64/package.json

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

nodejs/npm/darwin-x64/package.json

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

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

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

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

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

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

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

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

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

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

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

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

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

nodejs/package-lock.json

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

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.22.4-beta.1",
+  "version": "0.22.4-beta.3",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

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.

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.25.4-beta.2"
+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.2"
+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>=1.0.0b4",
+    "pylance>=1.0.0b14",
     "requests",
     "datafusion",
 ]

python/python/lancedb/__init__.py

@@ -72,7 +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
@@ -174,7 +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

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: ...

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
@@ -541,7 +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]:
@@ -562,6 +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
@@ -596,7 +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.
 
@@ -614,6 +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
@@ -638,7 +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,
@@ -655,6 +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)
@@ -680,7 +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,
@@ -698,6 +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
 
@@ -723,7 +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,
@@ -756,6 +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,
@@ -776,7 +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.
@@ -790,6 +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
@@ -797,7 +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
@@ -805,8 +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.
 
@@ -821,6 +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,
@@ -910,7 +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]:
@@ -931,6 +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
         )
@@ -958,7 +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]:
@@ -982,6 +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
         )
@@ -998,7 +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:
@@ -1045,7 +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
         -------
@@ -1155,6 +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:
@@ -1212,7 +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,
@@ -1231,7 +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().
@@ -1254,6 +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,
@@ -1269,7 +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,
@@ -1302,6 +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,
@@ -1316,8 +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.
 
@@ -1334,6 +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
         )
@@ -1342,7 +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.
@@ -1357,6 +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:
@@ -1365,7 +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
@@ -1374,6 +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

@@ -127,13 +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]):
@@ -235,8 +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 []
@@ -253,12 +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)
@@ -347,11 +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)
@@ -381,8 +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)
@@ -392,9 +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"
         )
@@ -406,14 +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]:
@@ -435,6 +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
         )
@@ -472,13 +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,
@@ -539,9 +561,11 @@ class AsyncLanceNamespaceDBConnection:
         page_token: Optional[str] = None,
         limit: int = 10,
         *,
-        namespace: List[str] = [],
+        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 []
@@ -557,13 +581,15 @@ class AsyncLanceNamespaceDBConnection:
         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,
     ) -> 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)
@@ -655,12 +681,14 @@ class AsyncLanceNamespaceDBConnection:
         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,
     ) -> 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)
@@ -701,8 +729,10 @@ class AsyncLanceNamespaceDBConnection:
         lance_table = await asyncio.to_thread(_open_table)
         return lance_table._table
 
-    async def drop_table(self, name: str, namespace: List[str] = []):
+    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)
@@ -711,10 +741,14 @@ class AsyncLanceNamespaceDBConnection:
         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 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"
         )
@@ -725,15 +759,17 @@ class AsyncLanceNamespaceDBConnection:
             "drop_database is deprecated, use drop_all_tables instead"
         )
 
-    async def drop_all_tables(self, namespace: List[str] = []):
+    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: List[str] = [],
+        namespace: Optional[List[str]] = None,
         page_token: Optional[str] = None,
         limit: int = 10,
     ) -> Iterable[str]:
@@ -755,6 +791,8 @@ class AsyncLanceNamespaceDBConnection:
         Iterable[str]
             Names of child namespaces.
         """
+        if namespace is None:
+            namespace = []
         request = ListNamespacesRequest(
             id=namespace, page_token=page_token, limit=limit
         )

python/python/lancedb/query.py

@@ -883,7 +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
@@ -1356,7 +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
@@ -1495,7 +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
             ):
@@ -2429,9 +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]
@@ -2440,6 +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
         ----------
@@ -3141,10 +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:
@@ -3418,9 +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]
@@ -3429,6 +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()
@@ -1708,13 +1708,15 @@ 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
@@ -1766,12 +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,
@@ -2623,7 +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,
@@ -2683,6 +2687,8 @@ 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
@@ -3628,7 +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

@@ -325,11 +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()
     )

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 {

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.22.4-beta.1"
+version = "0.22.4-beta.3"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -105,12 +105,12 @@ test-log = "0.2"
 
 [features]
 default = ["aws", "gcs", "azure", "dynamodb", "oss"]
-aws = ["lance/aws", "lance-io/aws"]
+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/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.