Bump version: 0.30.2-beta.0 → 0.30.2-beta.1

## Summary
- Update all lance workspace dependencies from v3.0.1 (crates.io) to
v4.0.0-rc.3 (git tag)
- Pin AWS SDK transitive dependencies to versions compatible with Rust
1.91.0 MSRV

## Test plan
- [x] `cargo check --features remote --tests --examples` passes
- [x] `cargo clippy --features remote --tests --examples` passes
- [x] Python bindings compile (`cargo check -p lancedb-python`)
- [ ] CI passes

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

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.0-beta.2"
+current_version = "0.27.2-beta.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/build_linux_wheel/action.yml

@@ -29,6 +29,7 @@ runs:
       if: ${{ inputs.arm-build == 'false' }}
       uses: PyO3/maturin-action@v1
       with:
+        maturin-version: "1.12.4"
         command: build
         working-directory: python
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
@@ -44,6 +45,7 @@ runs:
       if: ${{ inputs.arm-build == 'true' }}
       uses: PyO3/maturin-action@v1
       with:
+        maturin-version: "1.12.4"
         command: build
         working-directory: python
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"

.github/workflows/build_mac_wheel/action.yml

@@ -20,6 +20,7 @@ runs:
       uses: PyO3/maturin-action@v1
       with:
         command: build
+        maturin-version: "1.12.4"
         # TODO: pass through interpreter
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"

.github/workflows/build_windows_wheel/action.yml

@@ -25,6 +25,7 @@ runs:
       uses: PyO3/maturin-action@v1
       with:
         command: build
+        maturin-version: "1.12.4"
         args: ${{ inputs.args }}
         docker-options: "-e PIP_EXTRA_INDEX_URL='https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/'"
         working-directory: python

.github/workflows/dev.yml

@@ -15,7 +15,7 @@ jobs:
     name: Label PR
     runs-on: ubuntu-latest
     steps:
-      - uses: srvaroa/labeler@master
+      - uses: srvaroa/labeler@v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
   commitlint:
@@ -24,7 +24,7 @@ jobs:
     name: Verify PR title / description conforms to semantic-release
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
         with:
           node-version: "18"
       # These rules are disabled because Github will always ensure there
@@ -47,7 +47,7 @@ jobs:
 
             ${{ github.event.pull_request.body }}
       - if: failure()
-        uses: actions/github-script@v6
+        uses: actions/github-script@v7
         with:
           script: |
             const message = `**ACTION NEEDED**

.github/workflows/docs.yml

@@ -53,7 +53,7 @@ jobs:
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .
           python -m pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -r ../docs/requirements.txt
       - name: Set up node
-        uses: actions/setup-node@v3
+        uses: actions/setup-node@v4
         with:
           node-version: 20
           cache: 'npm'
@@ -68,7 +68,7 @@ jobs:
         run: |
           PYTHONPATH=. mkdocs build
       - name: Setup Pages
-        uses: actions/configure-pages@v2
+        uses: actions/configure-pages@v5
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v3
         with:

.github/workflows/nodejs.yml

@@ -7,6 +7,7 @@ on:
   pull_request:
     paths:
       - Cargo.toml
+      - Cargo.lock
       - nodejs/**
       - rust/**
       - docs/src/js/**
@@ -37,7 +38,7 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: actions/setup-node@v3
+    - uses: actions/setup-node@v4
       with:
         node-version: 20
         cache: 'npm'
@@ -77,7 +78,7 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: actions/setup-node@v3
+    - uses: actions/setup-node@v4
       name: Setup Node.js 20 for build
       with:
         # @napi-rs/cli v3 requires Node >= 20.12 (via @inquirer/prompts@8).
@@ -94,7 +95,7 @@ jobs:
       run: |
         npm ci --include=optional
         npm run build:debug -- --profile ci
-    - uses: actions/setup-node@v3
+    - uses: actions/setup-node@v4
       name: Setup Node.js ${{ matrix.node-version }} for test
       with:
         node-version: ${{ matrix.node-version }}
@@ -143,7 +144,7 @@ jobs:
       with:
         fetch-depth: 0
         lfs: true
-    - uses: actions/setup-node@v3
+    - uses: actions/setup-node@v4
       with:
         node-version: 20
         cache: 'npm'

.github/workflows/npm-publish.yml

@@ -19,6 +19,7 @@ on:
     paths:
       - .github/workflows/npm-publish.yml
       - Cargo.toml # Change in dependency frequently breaks builds
+      - Cargo.lock
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -124,7 +125,12 @@ jobs:
             pre_build: |-
               set -e &&
               apt-get update &&
-              apt-get install -y protobuf-compiler pkg-config
+              apt-get install -y protobuf-compiler pkg-config &&
+              # The base image (manylinux2014-cross) sets TARGET_CC to the old
+              # GCC 4.8 cross-compiler. aws-lc-sys checks TARGET_CC before CC,
+              # so it picks up GCC even though the napi-rs image sets CC=clang.
+              # Override to use the image's clang-18 which supports -fuse-ld=lld.
+              export TARGET_CC=clang TARGET_CXX=clang++
           - target: x86_64-unknown-linux-musl
             # This one seems to need some extra memory
             host: ubuntu-2404-8x-x64
@@ -144,9 +150,10 @@ jobs:
               set -e &&
               apt-get update &&
               apt-get install -y protobuf-compiler pkg-config &&
-              # https://github.com/aws/aws-lc-rs/issues/737#issuecomment-2725918627
-              ln -s /usr/aarch64-unknown-linux-gnu/lib/gcc/aarch64-unknown-linux-gnu/4.8.5/crtbeginS.o /usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot/usr/lib/crtbeginS.o &&
-              ln -s /usr/aarch64-unknown-linux-gnu/lib/gcc /usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot/usr/lib/gcc &&
+              export TARGET_CC=clang TARGET_CXX=clang++ &&
+              # The manylinux2014 sysroot has glibc 2.17 headers which lack
+              # AT_HWCAP2 (added in Linux 3.17). Define it for aws-lc-sys.
+              export CFLAGS="$CFLAGS -DAT_HWCAP2=26" &&
               rustup target add aarch64-unknown-linux-gnu
           - target: aarch64-unknown-linux-musl
             host: ubuntu-2404-8x-x64
@@ -266,7 +273,7 @@ jobs:
           - target: x86_64-unknown-linux-gnu
             host: ubuntu-latest
           - target: aarch64-unknown-linux-gnu
-            host: buildjet-16vcpu-ubuntu-2204-arm
+            host: ubuntu-2404-8x-arm64
         node:
           - '20'
     runs-on: ${{ matrix.settings.host }}
@@ -356,7 +363,8 @@ jobs:
           if [[ $DRY_RUN == "true" ]]; then
             ARGS="$ARGS --dry-run"
           fi
-          if [[ $GITHUB_REF =~ refs/tags/v(.*)-beta.* ]]; then
+          VERSION=$(node -p "require('./package.json').version")
+          if [[ $VERSION == *-* ]]; then
             ARGS="$ARGS --tag preview"
           fi
           npm publish $ARGS

.github/workflows/pypi-publish.yml

@@ -9,6 +9,7 @@ on:
     paths:
       - .github/workflows/pypi-publish.yml
       - Cargo.toml # Change in dependency frequently breaks builds
+      - Cargo.lock
 
 env:
   PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"

.github/workflows/python.yml

@@ -7,9 +7,14 @@ on:
   pull_request:
     paths:
       - Cargo.toml
+      - Cargo.lock
       - python/**
       - rust/**
       - .github/workflows/python.yml
+      - .github/workflows/build_linux_wheel/**
+      - .github/workflows/build_mac_wheel/**
+      - .github/workflows/build_windows_wheel/**
+      - .github/workflows/run_tests/**
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}

.github/workflows/rust.yml

@@ -7,6 +7,7 @@ on:
   pull_request:
     paths:
       - Cargo.toml
+      - Cargo.lock
       - rust/**
       - .github/workflows/rust.yml
 
@@ -206,14 +207,14 @@ jobs:
       - name: Downgrade  dependencies
         # These packages have newer requirements for MSRV
         run: |
-          cargo update -p aws-sdk-bedrockruntime --precise 1.64.0
-          cargo update -p aws-sdk-dynamodb --precise 1.55.0
-          cargo update -p aws-config --precise 1.5.10
-          cargo update -p aws-sdk-kms --precise 1.51.0
-          cargo update -p aws-sdk-s3 --precise 1.65.0
-          cargo update -p aws-sdk-sso --precise 1.50.0
-          cargo update -p aws-sdk-ssooidc --precise 1.51.0
-          cargo update -p aws-sdk-sts --precise 1.51.0
+          cargo update -p aws-sdk-bedrockruntime --precise 1.77.0
+          cargo update -p aws-sdk-dynamodb --precise 1.68.0
+          cargo update -p aws-config --precise 1.6.0
+          cargo update -p aws-sdk-kms --precise 1.63.0
+          cargo update -p aws-sdk-s3 --precise 1.79.0
+          cargo update -p aws-sdk-sso --precise 1.62.0
+          cargo update -p aws-sdk-ssooidc --precise 1.63.0
+          cargo update -p aws-sdk-sts --precise 1.63.0
           cargo update -p home --precise 0.5.9
       - name: cargo +${{ matrix.msrv }} check
         env:

Cargo.toml

@@ -5,7 +5,7 @@ exclude = ["python"]
 resolver = "2"
 
 [workspace.package]
-edition = "2021"
+edition = "2024"
 authors = ["LanceDB Devs <dev@lancedb.com>"]
 license = "Apache-2.0"
 repository = "https://github.com/lancedb/lancedb"
@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=4.0.0-rc.3", default-features = false, "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=4.0.0-rc.3", default-features = false, "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=4.0.0-rc.3", default-features = false, "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=4.0.0-rc.3", "tag" = "v4.0.0-rc.3", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }

ci/check_lance_release.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import argparse
+import functools
 import json
 import os
 import re
@@ -26,6 +27,7 @@ SEMVER_RE = re.compile(
 )
 
 
+@functools.total_ordering
 @dataclass(frozen=True)
 class SemVer:
     major: int
@@ -156,7 +158,9 @@ def read_current_version(repo_root: Path) -> str:
 
 
 def determine_latest_tag(tags: Iterable[TagInfo]) -> TagInfo:
-    return max(tags, key=lambda tag: tag.semver)
+    # Stable releases (no prerelease) are always preferred over pre-releases.
+    # Within each group, standard semver ordering applies.
+    return max(tags, key=lambda tag: (not tag.semver.prerelease, tag.semver))
 
 
 def write_outputs(args: argparse.Namespace, payload: dict) -> None:

docker-compose.yml

@@ -1,7 +1,7 @@
 version: "3.9"
 services:
   localstack:
-    image: localstack/localstack:3.3
+    image: localstack/localstack:4.0
     ports:
       - 4566:4566
     environment:

dockerfiles/Dockerfile

@@ -1,27 +1,27 @@
-#Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
-#Usage docker build -t lancedb:latest -f Dockerfile .
-FROM python:3.10-slim-buster
+# Simple base dockerfile that supports basic dependencies required to run lance with FTS and Hybrid Search
+# Usage: docker build -t lancedb:latest -f Dockerfile .
+FROM python:3.12-slim-bookworm
 
-# Install Rust
-RUN apt-get update && apt-get install -y curl build-essential && \
-  curl https://sh.rustup.rs -sSf | sh -s -- -y
-
-# Set the environment variable for Rust
-ENV PATH="/root/.cargo/bin:${PATH}"
-
-# Install protobuf compiler
-RUN apt-get install -y protobuf-compiler && \
+# Install build dependencies in a single layer
+RUN apt-get update && \
+  apt-get install -y --no-install-recommends \
+    curl \
+    build-essential \
+    protobuf-compiler \
+    git \
+    ca-certificates && \
   apt-get clean && \
   rm -rf /var/lib/apt/lists/*
 
-RUN apt-get -y update &&\
-  apt-get -y upgrade && \
-  apt-get -y install git
+# Install Rust (pinned installer, non-interactive)
+RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --default-toolchain stable --profile minimal
 
+# Set the environment variable for Rust
+ENV PATH="/root/.cargo/bin:${PATH}"
 
 # Verify installations
 RUN python --version && \
   rustc --version && \
   protoc --version
 
-RUN pip install tantivy lancedb
+RUN pip install --no-cache-dir tantivy lancedb

docs/mkdocs.yml

@@ -52,14 +52,21 @@ plugins:
           options:
             docstring_style: numpy
             heading_level: 3
-            show_source: true
-            show_symbol_type_in_heading: true
             show_signature_annotations: true
             show_root_heading: true
+            show_docstring_examples: true
+            show_docstring_attributes: false
+            show_docstring_other_parameters: true
+            show_symbol_type_heading: true
+            show_labels: false
+            show_if_no_docstring: true
+            show_source: false
             members_order: source
             docstring_section_style: list
             signature_crossrefs: true
             separate_signature: true
+            filters:
+              - "!^_"
           import:
             # for cross references
             - https://arrow.apache.org/docs/objects.inv
@@ -113,7 +120,7 @@ markdown_extensions:
       emoji_index: !!python/name:material.extensions.emoji.twemoji
       emoji_generator: !!python/name:material.extensions.emoji.to_svg
   - markdown.extensions.toc:
-      toc_depth: 3
+      toc_depth: 4
       permalink: true
       permalink_title: Anchor link to this section
 

docs/requirements.txt

@@ -1,9 +1,9 @@
-mkdocs==1.5.3
+mkdocs==1.6.1
 mkdocs-jupyter==0.24.1
-mkdocs-material==9.5.3
-mkdocs-autorefs<=1.0
-mkdocstrings[python]==0.25.2
-griffe
-mkdocs-render-swagger-plugin
-pydantic
-mkdocs-redirects
+mkdocs-material==9.6.23
+mkdocs-autorefs>=0.5,<=1.0
+mkdocstrings[python]>=0.24,<1.0
+griffe>=0.40,<1.0
+mkdocs-render-swagger-plugin>=0.1.0
+pydantic>=2.0,<3.0
+mkdocs-redirects>=1.2.0

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.27.0-beta.2</version>
+    <version>0.27.2-beta.0</version>
 </dependency>
 ```
 

docs/src/js/classes/Table.md

@@ -71,11 +71,12 @@ Add new columns with defined values.
 
 #### Parameters
 
-* **newColumnTransforms**: [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
-    pairs of column names and
-    the SQL expression to use to calculate the value of the new column. These
-    expressions will be evaluated for each row in the table, and can
-    reference existing columns in the table.
+* **newColumnTransforms**: `Field`<`any`> \| `Field`<`any`>[] \| `Schema`<`any`> \| [`AddColumnsSql`](../interfaces/AddColumnsSql.md)[]
+    Either:
+    - An array of objects with column names and SQL expressions to calculate values
+    - A single Arrow Field defining one column with its data type (column will be initialized with null values)
+    - An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
+    - An Arrow Schema defining columns with their data types (columns will be initialized with null values)
 
 #### Returns
 
@@ -484,19 +485,7 @@ Modeled after ``VACUUM`` in PostgreSQL.
  - Prune: Removes old versions of the dataset
  - Index: Optimizes the indices, adding new data to existing indices
 
- Experimental API
- ----------------
-
- The optimization process is undergoing active development and may change.
- Our goal with these changes is to improve the performance of optimization and
- reduce the complexity.
-
- That being said, it is essential today to run optimize if you want the best
- performance.  It should be stable and safe to use in production, but it our
- hope that the API may be simplified (or not even need to be called) in the
- future.
-
- The frequency an application shoudl call optimize is based on the frequency of
+ The frequency an application should call optimize is based on the frequency of
  data modifications.  If data is frequently added, deleted, or updated then
  optimize should be run frequently.  A good rule of thumb is to run optimize if
  you have added or modified 100,000 or more records or run more than 20 data

docs/src/js/interfaces/DeleteResult.md

@@ -8,6 +8,14 @@
 
 ## Properties
 
+### numDeletedRows
+
+```ts
+numDeletedRows: number;
+```
+
+***
+
 ### version
 
 ```ts

docs/src/js/interfaces/OptimizeOptions.md

@@ -37,3 +37,12 @@ tbl.optimize({cleanupOlderThan: new Date()});
 ```ts
 deleteUnverified: boolean;
 ```
+
+Because they may be part of an in-progress transaction, files newer than
+7 days old are not deleted by default. If you are sure that there are no
+in-progress transactions, then you can set this to true to delete all
+files older than `cleanupOlderThan`.
+
+**WARNING**: This should only be set to true if you can guarantee that
+no other process is currently working on this dataset. Otherwise the
+dataset could be put into a corrupted state.

java/README.md

@@ -1,4 +1,4 @@
-# LanceDB Java SDK
+# LanceDB Java Enterprise Client
 
 ## Configuration and Initialization
 

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.27.0-beta.2</version>
+      <version>0.27.2-beta.0</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 
@@ -56,21 +56,21 @@
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-slf4j2-impl</artifactId>
-            <version>2.24.3</version>
+            <version>2.25.3</version>
             <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-core</artifactId>
-            <version>2.24.3</version>
+            <version>2.25.3</version>
             <scope>test</scope>
         </dependency>
 
         <dependency>
             <groupId>org.apache.logging.log4j</groupId>
             <artifactId>log4j-api</artifactId>
-            <version>2.24.3</version>
+            <version>2.25.3</version>
             <scope>test</scope>
         </dependency>
     </dependencies>

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.27.0-beta.2</version>
+    <version>0.27.2-beta.0</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>3.1.0-beta.2</lance-core.version>
+        <lance-core.version>3.0.1</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>
@@ -111,7 +111,7 @@
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-source-plugin</artifactId>
-                <version>2.2.1</version>
+                <version>3.3.1</version>
                 <executions>
                     <execution>
                         <id>attach-sources</id>
@@ -124,7 +124,7 @@
             <plugin>
                 <groupId>org.apache.maven.plugins</groupId>
                 <artifactId>maven-javadoc-plugin</artifactId>
-                <version>2.9.1</version>
+                <version>3.11.2</version>
                 <executions>
                     <execution>
                         <id>attach-javadocs</id>
@@ -178,15 +178,15 @@
             <plugins>
                 <plugin>
                     <artifactId>maven-clean-plugin</artifactId>
-                    <version>3.1.0</version>
+                    <version>3.4.1</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-resources-plugin</artifactId>
-                    <version>3.0.2</version>
+                    <version>3.3.1</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-compiler-plugin</artifactId>
-                    <version>3.8.1</version>
+                    <version>3.14.0</version>
                     <configuration>
                         <compilerArgs>
                             <arg>-h</arg>
@@ -205,11 +205,11 @@
                 </plugin>
                 <plugin>
                     <artifactId>maven-jar-plugin</artifactId>
-                    <version>3.0.2</version>
+                    <version>3.4.2</version>
                 </plugin>
                 <plugin>
                     <artifactId>maven-install-plugin</artifactId>
-                    <version>2.5.2</version>
+                    <version>3.1.3</version>
                 </plugin>
                 <plugin>
                     <groupId>com.diffplug.spotless</groupId>
@@ -327,7 +327,7 @@
                     <plugin>
                         <groupId>org.apache.maven.plugins</groupId>
                         <artifactId>maven-gpg-plugin</artifactId>
-                        <version>1.5</version>
+                        <version>3.2.7</version>
                         <executions>
                             <execution>
                                 <id>sign-artifacts</id>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.27.0-beta.2"
+version = "0.27.2-beta.0"
 license.workspace = true
 description.workspace = true
 repository.workspace = true
@@ -25,12 +25,12 @@ napi = { version = "3.8.3", default-features = false, features = [
 ] }
 napi-derive = "3.5.2"
 # Prevent dynamic linking of lzma, which comes from datafusion
-lzma-sys = { version = "*", features = ["static"] }
+lzma-sys = { version = "0.1", features = ["static"] }
 log.workspace = true
 
-# Workaround for build failure until we can fix it.
-aws-lc-sys = "=0.28.0"
-aws-lc-rs = "=1.13.0"
+# Pin to resolve build failures; update periodically for security patches.
+aws-lc-sys = "=0.38.0"
+aws-lc-rs = "=1.16.1"
 
 [build-dependencies]
 napi-build = "2.3.1"

nodejs/__test__/arrow.test.ts

@@ -63,6 +63,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       tableFromIPC,
       DataType,
       Dictionary,
+      Uint8: ArrowUint8,
       // biome-ignore lint/suspicious/noExplicitAny: <explanation>
     } = <any>arrow;
     type Schema = ApacheArrow["Schema"];
@@ -362,6 +363,38 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         ).toEqual(new Float64().toString());
       });
 
+      it("will infer FixedSizeList<Float32> from Float32Array values", async function () {
+        const table = makeArrowTable([
+          { id: "a", vector: new Float32Array([0.1, 0.2, 0.3]) },
+          { id: "b", vector: new Float32Array([0.4, 0.5, 0.6]) },
+        ]);
+
+        expect(DataType.isFixedSizeList(table.getChild("vector")?.type)).toBe(
+          true,
+        );
+        const vectorType = table.getChild("vector")?.type;
+        expect(vectorType.listSize).toBe(3);
+        expect(vectorType.children[0].type.toString()).toEqual(
+          new Float32().toString(),
+        );
+      });
+
+      it("will infer FixedSizeList<Uint8> from Uint8Array values", async function () {
+        const table = makeArrowTable([
+          { id: "a", vector: new Uint8Array([1, 2, 3]) },
+          { id: "b", vector: new Uint8Array([4, 5, 6]) },
+        ]);
+
+        expect(DataType.isFixedSizeList(table.getChild("vector")?.type)).toBe(
+          true,
+        );
+        const vectorType = table.getChild("vector")?.type;
+        expect(vectorType.listSize).toBe(3);
+        expect(vectorType.children[0].type.toString()).toEqual(
+          new ArrowUint8().toString(),
+        );
+      });
+
       it("will use dictionary encoded strings if asked", async function () {
         const table = makeArrowTable([{ str: "hello" }]);
         expect(DataType.isUtf8(table.getChild("str")?.type)).toBe(true);

nodejs/__test__/table.test.ts

@@ -1259,6 +1259,98 @@ describe("schema evolution", function () {
     expect(await table.schema()).toEqual(expectedSchema);
   });
 
+  it("can add columns with schema for explicit data types", async function () {
+    const con = await connect(tmpDir.name);
+    const table = await con.createTable("vectors", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+
+    // Define schema for new columns with explicit data types
+    // Note: All columns must be nullable when using addColumns with Schema
+    // because they are initially populated with null values
+    const newColumnsSchema = new Schema([
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+      new Field("rating", new Int32(), true),
+    ]);
+
+    const result = await table.addColumns(newColumnsSchema);
+    expect(result).toHaveProperty("version");
+    expect(result.version).toBe(2);
+
+    const expectedSchema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32(), true)),
+        true,
+      ),
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+      new Field("rating", new Int32(), true),
+    ]);
+    expect(await table.schema()).toEqual(expectedSchema);
+
+    // Verify that new columns are populated with null values
+    const results = await table.query().toArray();
+    expect(results).toHaveLength(1);
+    expect(results[0].price).toBeNull();
+    expect(results[0].category).toBeNull();
+    expect(results[0].rating).toBeNull();
+  });
+
+  it("can add a single column using Field", async function () {
+    const con = await connect(tmpDir.name);
+    const table = await con.createTable("vectors", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+
+    // Add a single field
+    const priceField = new Field("price", new Float64(), true);
+    const result = await table.addColumns(priceField);
+    expect(result).toHaveProperty("version");
+    expect(result.version).toBe(2);
+
+    const expectedSchema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32(), true)),
+        true,
+      ),
+      new Field("price", new Float64(), true),
+    ]);
+    expect(await table.schema()).toEqual(expectedSchema);
+  });
+
+  it("can add multiple columns using array of Fields", async function () {
+    const con = await connect(tmpDir.name);
+    const table = await con.createTable("vectors", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+
+    // Add multiple fields as array
+    const fields = [
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+    ];
+    const result = await table.addColumns(fields);
+    expect(result).toHaveProperty("version");
+    expect(result.version).toBe(2);
+
+    const expectedSchema = new Schema([
+      new Field("id", new Int64(), true),
+      new Field(
+        "vector",
+        new FixedSizeList(2, new Field("item", new Float32(), true)),
+        true,
+      ),
+      new Field("price", new Float64(), true),
+      new Field("category", new Utf8(), true),
+    ]);
+    expect(await table.schema()).toEqual(expectedSchema);
+  });
+
   it("can alter the columns in the schema", async function () {
     const con = await connect(tmpDir.name);
     const schema = new Schema([
@@ -1697,6 +1789,65 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results2[0].text).toBe(data[1].text);
     });
 
+    test("full text search fast search", async () => {
+      const db = await connect(tmpDir.name);
+      const data = [{ text: "hello world", vector: [0.1, 0.2, 0.3], id: 1 }];
+      const table = await db.createTable("test", data);
+      await table.createIndex("text", {
+        config: Index.fts(),
+      });
+
+      // Insert unindexed data after creating the index.
+      await table.add([{ text: "xyz", vector: [0.4, 0.5, 0.6], id: 2 }]);
+
+      const withFlatSearch = await table
+        .search("xyz", "fts")
+        .limit(10)
+        .toArray();
+      expect(withFlatSearch.length).toBeGreaterThan(0);
+
+      const fastSearchResults = await table
+        .search("xyz", "fts")
+        .fastSearch()
+        .limit(10)
+        .toArray();
+      expect(fastSearchResults.length).toBe(0);
+
+      const nearestToTextFastSearch = await table
+        .query()
+        .nearestToText("xyz")
+        .fastSearch()
+        .limit(10)
+        .toArray();
+      expect(nearestToTextFastSearch.length).toBe(0);
+
+      // fastSearch should be chainable with other methods.
+      const chainedFastSearch = await table
+        .search("xyz", "fts")
+        .fastSearch()
+        .select(["text"])
+        .limit(5)
+        .toArray();
+      expect(chainedFastSearch.length).toBe(0);
+
+      await table.optimize();
+
+      const indexedFastSearch = await table
+        .search("xyz", "fts")
+        .fastSearch()
+        .limit(10)
+        .toArray();
+      expect(indexedFastSearch.length).toBeGreaterThan(0);
+
+      const indexedNearestToTextFastSearch = await table
+        .query()
+        .nearestToText("xyz")
+        .fastSearch()
+        .limit(10)
+        .toArray();
+      expect(indexedNearestToTextFastSearch.length).toBeGreaterThan(0);
+    });
+
     test("prewarm full text search index", async () => {
       const db = await connect(tmpDir.name);
       const data = [
@@ -2145,3 +2296,36 @@ describe("when creating an empty table", () => {
     expect((actualSchema.fields[1].type as Float64).precision).toBe(2);
   });
 });
+
+// Ensure we can create float32 arrays without using Arrow
+// by utilizing native JS TypedArray support
+//
+// https://github.com/lancedb/lancedb/issues/3115
+describe("when creating a table with Float32Array vectors", () => {
+  let tmpDir: tmp.DirResult;
+  beforeEach(() => {
+    tmpDir = tmp.dirSync({ unsafeCleanup: true });
+  });
+  afterEach(() => {
+    tmpDir.removeCallback();
+  });
+
+  it("should persist Float32Array as FixedSizeList<Float32> in the LanceDB schema", async () => {
+    const db = await connect(tmpDir.name);
+    const table = await db.createTable("test", [
+      { id: "a", vector: new Float32Array([0.1, 0.2, 0.3]) },
+      { id: "b", vector: new Float32Array([0.4, 0.5, 0.6]) },
+    ]);
+
+    const schema = await table.schema();
+    const vectorField = schema.fields.find((f) => f.name === "vector");
+    expect(vectorField).toBeDefined();
+    expect(vectorField!.type).toBeInstanceOf(FixedSizeList);
+
+    const fsl = vectorField!.type as FixedSizeList;
+    expect(fsl.listSize).toBe(3);
+    expect(fsl.children[0].type.typeId).toBe(Type.Float);
+    // precision: HALF=0, SINGLE=1, DOUBLE=2
+    expect((fsl.children[0].type as Float32).precision).toBe(1);
+  });
+});

nodejs/examples/package-lock.json

@@ -30,12 +30,15 @@
         "x64",
         "arm64"
       ],
+      "dev": true,
       "license": "Apache-2.0",
+      "optional": true,
       "os": [
         "darwin",
         "linux",
         "win32"
       ],
+      "peer": true,
       "dependencies": {
         "reflect-metadata": "^0.2.2"
       },
@@ -91,14 +94,15 @@
       }
     },
     "node_modules/@babel/code-frame": {
-      "version": "7.26.2",
-      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.26.2.tgz",
-      "integrity": "sha512-RJlIHRueQgwWitWgF8OdFYGZX328Ax5BCemNGlqHfplnRT9ESi8JkFlvaVYbS+UubVY6dpv87Fs2u5M29iNFVQ==",
+      "version": "7.29.0",
+      "resolved": "https://registry.npmjs.org/@babel/code-frame/-/code-frame-7.29.0.tgz",
+      "integrity": "sha512-9NhCeYjq9+3uxgdtp20LSiJXJvN0FeCtNGpJxuMFZ1Kv3cWUNb6DOhJwUvcVCzKGR66cw4njwM6hrJLqgOwbcw==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/helper-validator-identifier": "^7.25.9",
+        "@babel/helper-validator-identifier": "^7.28.5",
         "js-tokens": "^4.0.0",
-        "picocolors": "^1.0.0"
+        "picocolors": "^1.1.1"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -233,19 +237,21 @@
       }
     },
     "node_modules/@babel/helper-string-parser": {
-      "version": "7.25.9",
-      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.25.9.tgz",
-      "integrity": "sha512-4A/SCr/2KLd5jrtOMFzaKjVtAei3+2r/NChoBNoZ3EyP/+GlhoaEGoWOZUmFmoITP7zOJyHIMm+DYRd8o3PvHA==",
+      "version": "7.27.1",
+      "resolved": "https://registry.npmjs.org/@babel/helper-string-parser/-/helper-string-parser-7.27.1.tgz",
+      "integrity": "sha512-qMlSxKbpRlAridDExk92nSobyDdpPijUq2DW6oDnUqd0iOGxmQjyqhMIihI9+zv4LPyZdRje2cavWPbCbWm3eA==",
       "dev": true,
+      "license": "MIT",
       "engines": {
         "node": ">=6.9.0"
       }
     },
     "node_modules/@babel/helper-validator-identifier": {
-      "version": "7.25.9",
-      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.25.9.tgz",
-      "integrity": "sha512-Ed61U6XJc3CVRfkERJWDz4dJwKe7iLmmJsbOGu9wSloNSFttHV0I8g6UAgb7qnK5ly5bGLPd4oXZlxCdANBOWQ==",
+      "version": "7.28.5",
+      "resolved": "https://registry.npmjs.org/@babel/helper-validator-identifier/-/helper-validator-identifier-7.28.5.tgz",
+      "integrity": "sha512-qSs4ifwzKJSV39ucNjsvc6WVHs6b7S03sOh2OcHF9UHfVPqWWALUsNUVzhSBiItjRZoLHx7nIarVjqKVusUZ1Q==",
       "dev": true,
+      "license": "MIT",
       "engines": {
         "node": ">=6.9.0"
       }
@@ -260,25 +266,27 @@
       }
     },
     "node_modules/@babel/helpers": {
-      "version": "7.26.0",
-      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.26.0.tgz",
-      "integrity": "sha512-tbhNuIxNcVb21pInl3ZSjksLCvgdZy9KwJ8brv993QtIVKJBBkYXz4q4ZbAv31GdnC+R90np23L5FbEBlthAEw==",
+      "version": "7.28.6",
+      "resolved": "https://registry.npmjs.org/@babel/helpers/-/helpers-7.28.6.tgz",
+      "integrity": "sha512-xOBvwq86HHdB7WUDTfKfT/Vuxh7gElQ+Sfti2Cy6yIWNW05P8iUslOVcZ4/sKbE+/jQaukQAdz/gf3724kYdqw==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/template": "^7.25.9",
-        "@babel/types": "^7.26.0"
+        "@babel/template": "^7.28.6",
+        "@babel/types": "^7.28.6"
       },
       "engines": {
         "node": ">=6.9.0"
       }
     },
     "node_modules/@babel/parser": {
-      "version": "7.26.2",
-      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.26.2.tgz",
-      "integrity": "sha512-DWMCZH9WA4Maitz2q21SRKHo9QXZxkDsbNZoVD62gusNtNBBqDg9i7uOhASfTfIGNzW+O+r7+jAlM8dwphcJKQ==",
+      "version": "7.29.0",
+      "resolved": "https://registry.npmjs.org/@babel/parser/-/parser-7.29.0.tgz",
+      "integrity": "sha512-IyDgFV5GeDUVX4YdF/3CPULtVGSXXMLh1xVIgdCgxApktqnQV0r7/8Nqthg+8YLGaAtdyIlo2qIdZrbCv4+7ww==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/types": "^7.26.0"
+        "@babel/types": "^7.29.0"
       },
       "bin": {
         "parser": "bin/babel-parser.js"
@@ -510,14 +518,15 @@
       }
     },
     "node_modules/@babel/template": {
-      "version": "7.25.9",
-      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.25.9.tgz",
-      "integrity": "sha512-9DGttpmPvIxBb/2uwpVo3dqJ+O6RooAFOS+lB+xDqoE2PVCE8nfoHMdZLpfCQRLwvohzXISPZcgxt80xLfsuwg==",
+      "version": "7.28.6",
+      "resolved": "https://registry.npmjs.org/@babel/template/-/template-7.28.6.tgz",
+      "integrity": "sha512-YA6Ma2KsCdGb+WC6UpBVFJGXL58MDA6oyONbjyF/+5sBgxY/dwkhLogbMT2GXXyU84/IhRw/2D1Os1B/giz+BQ==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/code-frame": "^7.25.9",
-        "@babel/parser": "^7.25.9",
-        "@babel/types": "^7.25.9"
+        "@babel/code-frame": "^7.28.6",
+        "@babel/parser": "^7.28.6",
+        "@babel/types": "^7.28.6"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -542,13 +551,14 @@
       }
     },
     "node_modules/@babel/types": {
-      "version": "7.26.0",
-      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.26.0.tgz",
-      "integrity": "sha512-Z/yiTPj+lDVnF7lWeKCIJzaIkI0vYO87dMpZ4bg4TDrFe4XXLFWL1TbXU27gBP3QccxV9mZICCrnjnYlJjXHOA==",
+      "version": "7.29.0",
+      "resolved": "https://registry.npmjs.org/@babel/types/-/types-7.29.0.tgz",
+      "integrity": "sha512-LwdZHpScM4Qz8Xw2iKSzS+cfglZzJGvofQICy7W7v4caru4EaAmyUuO6BGrbyQ2mYV11W0U8j5mBhd14dd3B0A==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
-        "@babel/helper-string-parser": "^7.25.9",
-        "@babel/helper-validator-identifier": "^7.25.9"
+        "@babel/helper-string-parser": "^7.27.1",
+        "@babel/helper-validator-identifier": "^7.28.5"
       },
       "engines": {
         "node": ">=6.9.0"
@@ -1151,95 +1161,6 @@
         "url": "https://opencollective.com/libvips"
       }
     },
-    "node_modules/@isaacs/cliui": {
-      "version": "8.0.2",
-      "resolved": "https://registry.npmjs.org/@isaacs/cliui/-/cliui-8.0.2.tgz",
-      "integrity": "sha512-O8jcjabXaleOG9DQ0+ARXWZBTfnP4WNAqzuiJK7ll44AmxGKv/J2M4TPjxjY3znBCfvBXFzucm1twdyFybFqEA==",
-      "dependencies": {
-        "string-width": "^5.1.2",
-        "string-width-cjs": "npm:string-width@^4.2.0",
-        "strip-ansi": "^7.0.1",
-        "strip-ansi-cjs": "npm:strip-ansi@^6.0.1",
-        "wrap-ansi": "^8.1.0",
-        "wrap-ansi-cjs": "npm:wrap-ansi@^7.0.0"
-      },
-      "engines": {
-        "node": ">=12"
-      }
-    },
-    "node_modules/@isaacs/cliui/node_modules/ansi-regex": {
-      "version": "6.1.0",
-      "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-6.1.0.tgz",
-      "integrity": "sha512-7HSX4QQb4CspciLpVFwyRe79O3xsIZDDLER21kERQ71oaPodF8jL725AgJMFAYbooIqolJoRLuM81SpeUkpkvA==",
-      "engines": {
-        "node": ">=12"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/ansi-regex?sponsor=1"
-      }
-    },
-    "node_modules/@isaacs/cliui/node_modules/ansi-styles": {
-      "version": "6.2.1",
-      "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-6.2.1.tgz",
-      "integrity": "sha512-bN798gFfQX+viw3R7yrGWRqnrN2oRkEkUjjl4JNn4E8GxxbjtG3FbrEIIY3l8/hrwUwIeCZvi4QuOTP4MErVug==",
-      "engines": {
-        "node": ">=12"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/ansi-styles?sponsor=1"
-      }
-    },
-    "node_modules/@isaacs/cliui/node_modules/emoji-regex": {
-      "version": "9.2.2",
-      "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-9.2.2.tgz",
-      "integrity": "sha512-L18DaJsXSUk2+42pv8mLs5jJT2hqFkFE4j21wOmgbUqsZ2hL72NsUU785g9RXgo3s0ZNgVl42TiHp3ZtOv/Vyg=="
-    },
-    "node_modules/@isaacs/cliui/node_modules/string-width": {
-      "version": "5.1.2",
-      "resolved": "https://registry.npmjs.org/string-width/-/string-width-5.1.2.tgz",
-      "integrity": "sha512-HnLOCR3vjcY8beoNLtcjZ5/nxn2afmME6lhrDrebokqMap+XbeW8n9TXpPDOqdGK5qcI3oT0GKTW6wC7EMiVqA==",
-      "dependencies": {
-        "eastasianwidth": "^0.2.0",
-        "emoji-regex": "^9.2.2",
-        "strip-ansi": "^7.0.1"
-      },
-      "engines": {
-        "node": ">=12"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/sindresorhus"
-      }
-    },
-    "node_modules/@isaacs/cliui/node_modules/strip-ansi": {
-      "version": "7.1.0",
-      "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-7.1.0.tgz",
-      "integrity": "sha512-iq6eVVI64nQQTRYq2KtEg2d2uU7LElhTJwsH4YzIHZshxlgZms/wIc4VoDQTlG/IvVIrBKG06CrZnp0qv7hkcQ==",
-      "dependencies": {
-        "ansi-regex": "^6.0.1"
-      },
-      "engines": {
-        "node": ">=12"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/strip-ansi?sponsor=1"
-      }
-    },
-    "node_modules/@isaacs/cliui/node_modules/wrap-ansi": {
-      "version": "8.1.0",
-      "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-8.1.0.tgz",
-      "integrity": "sha512-si7QWI6zUMq56bESFvagtmzMdGOtoxfR+Sez11Mobfc7tm+VkUckk9bW2UeffTGVUbOksxmSw0AA2gs8g71NCQ==",
-      "dependencies": {
-        "ansi-styles": "^6.1.0",
-        "string-width": "^5.0.1",
-        "strip-ansi": "^7.0.1"
-      },
-      "engines": {
-        "node": ">=12"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/wrap-ansi?sponsor=1"
-      }
-    },
     "node_modules/@isaacs/fs-minipass": {
       "version": "4.0.1",
       "resolved": "https://registry.npmjs.org/@isaacs/fs-minipass/-/fs-minipass-4.0.1.tgz",
@@ -1606,15 +1527,6 @@
       "resolved": "../dist",
       "link": true
     },
-    "node_modules/@pkgjs/parseargs": {
-      "version": "0.11.0",
-      "resolved": "https://registry.npmjs.org/@pkgjs/parseargs/-/parseargs-0.11.0.tgz",
-      "integrity": "sha512-+1VkjdD0QBLPodGrJUeqarH8VAIvQODIbwh9XpP5Syisf7YoQgsJKPNFoqqLQlu+VQ/tVSshMR6loPMn8U+dPg==",
-      "optional": true,
-      "engines": {
-        "node": ">=14"
-      }
-    },
     "node_modules/@protobufjs/aspromise": {
       "version": "1.1.2",
       "resolved": "https://registry.npmjs.org/@protobufjs/aspromise/-/aspromise-1.1.2.tgz",
@@ -1846,6 +1758,7 @@
       "version": "5.0.1",
       "resolved": "https://registry.npmjs.org/ansi-regex/-/ansi-regex-5.0.1.tgz",
       "integrity": "sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==",
+      "dev": true,
       "engines": {
         "node": ">=8"
       }
@@ -1854,6 +1767,7 @@
       "version": "4.3.0",
       "resolved": "https://registry.npmjs.org/ansi-styles/-/ansi-styles-4.3.0.tgz",
       "integrity": "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==",
+      "dev": true,
       "dependencies": {
         "color-convert": "^2.0.1"
       },
@@ -2019,13 +1933,15 @@
     "node_modules/balanced-match": {
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/balanced-match/-/balanced-match-1.0.2.tgz",
-      "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw=="
+      "integrity": "sha512-3oSeUO0TMV67hN1AmbXsK4yaqU7tjiHlbxRDZOpH0KW9+CeX4bRAaX0Anxt0tx2MrpRpWwQaPwIlISEJhYU5Pw==",
+      "dev": true
     },
     "node_modules/brace-expansion": {
-      "version": "1.1.11",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.11.tgz",
-      "integrity": "sha512-iCuPHDFgrHX7H2vEI/5xpz07zSHB00TpugqhmYtVmMO6518mCuRMoOYFldEBl0g187ufozdaHgWKcYFb61qGiA==",
+      "version": "1.1.12",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-1.1.12.tgz",
+      "integrity": "sha512-9T9UjW3r0UW5c1Q7GTwllptXwhvYmEzFhzMfZ9H7FQWt+uZePjZPjBP/W1ZEyZ1twGWom5/56TF4lPcqjnDHcg==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0",
         "concat-map": "0.0.1"
@@ -2102,6 +2018,19 @@
       "integrity": "sha512-E+XQCRwSbaaiChtv6k6Dwgc+bx+Bs6vuKJHHl5kox/BaKbhiXzqQOwK4cO22yElGp2OCmjwVhT3HmxgyPGnJfQ==",
       "dev": true
     },
+    "node_modules/call-bind-apply-helpers": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/call-bind-apply-helpers/-/call-bind-apply-helpers-1.0.2.tgz",
+      "integrity": "sha512-Sp1ablJ0ivDkSzjcaJdxEunN5/XvksFJ2sMBFfq6x0ryhQV/2b/KwFe21cMpmHtPOSij8K99/wSfoEuTObmuMQ==",
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "function-bind": "^1.1.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/callsites": {
       "version": "3.1.0",
       "resolved": "https://registry.npmjs.org/callsites/-/callsites-3.1.0.tgz",
@@ -2298,9 +2227,11 @@
       }
     },
     "node_modules/cross-spawn": {
-      "version": "7.0.3",
-      "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.3.tgz",
-      "integrity": "sha512-iRDPJKUPVEND7dHPO8rkbOnPpyDygcDFtWjpeWNCgy8WP2rXcxXL8TskReQl6OrB2G7+UJrags1q15Fudc7G6w==",
+      "version": "7.0.6",
+      "resolved": "https://registry.npmjs.org/cross-spawn/-/cross-spawn-7.0.6.tgz",
+      "integrity": "sha512-uV2QOWP2nWzsy2aMp8aRibhi9dlzF5Hgh5SHaB9OiTGEyDTiJJyx0uy51QXdyWbtAHNua4XJzUKca3OzKUd3vA==",
+      "dev": true,
+      "license": "MIT",
       "dependencies": {
         "path-key": "^3.1.0",
         "shebang-command": "^2.0.0",
@@ -2384,10 +2315,19 @@
         "node": "^14.15.0 || ^16.10.0 || >=18.0.0"
       }
     },
-    "node_modules/eastasianwidth": {
-      "version": "0.2.0",
-      "resolved": "https://registry.npmjs.org/eastasianwidth/-/eastasianwidth-0.2.0.tgz",
-      "integrity": "sha512-I88TYZWc9XiYHRQ4/3c5rjjfgkjhLyW2luGIheGERbNQ6OY7yTybanSpDXZa8y7VUP9YmDcYa+eyq4ca7iLqWA=="
+    "node_modules/dunder-proto": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/dunder-proto/-/dunder-proto-1.0.1.tgz",
+      "integrity": "sha512-KIN/nDJBQRcXw0MLVhZE9iQHmG68qAVIBg9CqmUYjmQIhgij9U5MFvrqkUL5FbtyyzZuOeOt0zdeRe4UY7ct+A==",
+      "license": "MIT",
+      "dependencies": {
+        "call-bind-apply-helpers": "^1.0.1",
+        "es-errors": "^1.3.0",
+        "gopd": "^1.2.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
     },
     "node_modules/ejs": {
       "version": "3.1.10",
@@ -2425,7 +2365,8 @@
     "node_modules/emoji-regex": {
       "version": "8.0.0",
       "resolved": "https://registry.npmjs.org/emoji-regex/-/emoji-regex-8.0.0.tgz",
-      "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A=="
+      "integrity": "sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==",
+      "dev": true
     },
     "node_modules/error-ex": {
       "version": "1.3.2",
@@ -2442,6 +2383,51 @@
       "integrity": "sha512-zz06S8t0ozoDXMG+ube26zeCTNXcKIPJZJi8hBrF4idCLms4CG9QtK7qBl1boi5ODzFpjswb5JPmHCbMpjaYzg==",
       "dev": true
     },
+    "node_modules/es-define-property": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/es-define-property/-/es-define-property-1.0.1.tgz",
+      "integrity": "sha512-e3nRfgfUZ4rNGL232gUgX06QNyyez04KdjFrF+LTRoOXmrOgFKDg4BCdsjW8EnT69eqdYGmRpJwiPVYNrCaW3g==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-errors": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/es-errors/-/es-errors-1.3.0.tgz",
+      "integrity": "sha512-Zf5H2Kxt2xjTvbJvP2ZWLEICxA6j+hAmMzIlypy4xcBg1vKVnx89Wy0GbS+kf5cwCVFFzdCFh2XSCFNULS6csw==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-object-atoms": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/es-object-atoms/-/es-object-atoms-1.1.1.tgz",
+      "integrity": "sha512-FGgH2h8zKNim9ljj7dankFPcICIK9Cp5bm+c2gQSYePhpaG5+esrLODihIorn+Pe6FGJzWhXQotPv73jTaldXA==",
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
+    "node_modules/es-set-tostringtag": {
+      "version": "2.1.0",
+      "resolved": "https://registry.npmjs.org/es-set-tostringtag/-/es-set-tostringtag-2.1.0.tgz",
+      "integrity": "sha512-j6vWzfrGVfyXxge+O0x5sh6cvxAog0a/4Rdd2K36zCMV5eJ+/+tOAngRO8cODMNWbVRdVlmGZQL2YS3yR8bIUA==",
+      "license": "MIT",
+      "dependencies": {
+        "es-errors": "^1.3.0",
+        "get-intrinsic": "^1.2.6",
+        "has-tostringtag": "^1.0.2",
+        "hasown": "^2.0.2"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/escalade": {
       "version": "3.2.0",
       "resolved": "https://registry.npmjs.org/escalade/-/escalade-3.2.0.tgz",
@@ -2554,19 +2540,21 @@
       }
     },
     "node_modules/filelist/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
+      "version": "2.0.2",
+      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.2.tgz",
+      "integrity": "sha512-Jt0vHyM+jmUBqojB7E1NIYadt0vI0Qxjxd2TErW94wDz+E2LAm5vKMXXwg6ZZBTHPuUlDgQHKXvjGBdfcF1ZDQ==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "balanced-match": "^1.0.0"
       }
     },
     "node_modules/filelist/node_modules/minimatch": {
-      "version": "5.1.6",
-      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-5.1.6.tgz",
-      "integrity": "sha512-lKwV/1brpG6mBUFHtb7NUmtABCb2WZZmm2wNiOA5hAb8VdCS4B3dtMWyvcoViccwAW/COERjXLt0zP1zXUN26g==",
+      "version": "5.1.9",
+      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-5.1.9.tgz",
+      "integrity": "sha512-7o1wEA2RyMP7Iu7GNba9vc0RWWGACJOCZBJX2GJWip0ikV+wcOsgVuY9uE8CPiyQhkGFSlhuSkZPavN7u1c2Fw==",
       "dev": true,
+      "license": "ISC",
       "dependencies": {
         "brace-expansion": "^2.0.1"
       },
@@ -2604,39 +2592,16 @@
       "resolved": "https://registry.npmjs.org/flatbuffers/-/flatbuffers-1.12.0.tgz",
       "integrity": "sha512-c7CZADjRcl6j0PlvFy0ZqXQ67qSEZfrVPynmnL+2zPc+NtMvrF8Y0QceMo7QqnSPc7+uWjUIAbvCQ5WIKlMVdQ=="
     },
-    "node_modules/foreground-child": {
-      "version": "3.3.0",
-      "resolved": "https://registry.npmjs.org/foreground-child/-/foreground-child-3.3.0.tgz",
-      "integrity": "sha512-Ld2g8rrAyMYFXBhEqMz8ZAHBi4J4uS1i/CxGMDnjyFWddMXLVcDp051DZfu+t7+ab7Wv6SMqpWmyFIj5UbfFvg==",
-      "dependencies": {
-        "cross-spawn": "^7.0.0",
-        "signal-exit": "^4.0.1"
-      },
-      "engines": {
-        "node": ">=14"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
-    "node_modules/foreground-child/node_modules/signal-exit": {
-      "version": "4.1.0",
-      "resolved": "https://registry.npmjs.org/signal-exit/-/signal-exit-4.1.0.tgz",
-      "integrity": "sha512-bzyZ1e88w9O1iNJbKnOlvYTrWPDl46O1bG0D3XInv+9tkPrxrN8jUUTiFlDkkmKWgn1M6CfIA13SuGqOa9Korw==",
-      "engines": {
-        "node": ">=14"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
     "node_modules/form-data": {
-      "version": "4.0.1",
-      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.1.tgz",
-      "integrity": "sha512-tzN8e4TX8+kkxGPK8D5u0FNmjPUjw3lwC9lSLxxoB/+GtsJG91CO8bSWy73APlgAZzZbXEYZJuxjkHH2w+Ezhw==",
+      "version": "4.0.5",
+      "resolved": "https://registry.npmjs.org/form-data/-/form-data-4.0.5.tgz",
+      "integrity": "sha512-8RipRLol37bNs2bhoV67fiTEvdTrbMUYcFTiy3+wuuOnUog2QBHCZWXDRijWQfAkhBj2Uf5UnVaiWwA5vdd82w==",
+      "license": "MIT",
       "dependencies": {
         "asynckit": "^0.4.0",
         "combined-stream": "^1.0.8",
+        "es-set-tostringtag": "^2.1.0",
+        "hasown": "^2.0.2",
         "mime-types": "^2.1.12"
       },
       "engines": {
@@ -2684,7 +2649,6 @@
       "version": "1.1.2",
       "resolved": "https://registry.npmjs.org/function-bind/-/function-bind-1.1.2.tgz",
       "integrity": "sha512-7XHNxH7qX9xG5mIwxkhumTox/MIRNcOgDrxWsMt2pAr23WHp6MrRlN7FBSFpCpr+oVO0F744iUgR82nJMfG2SA==",
-      "dev": true,
       "funding": {
         "url": "https://github.com/sponsors/ljharb"
       }
@@ -2707,6 +2671,30 @@
         "node": "6.* || 8.* || >= 10.*"
       }
     },
+    "node_modules/get-intrinsic": {
+      "version": "1.3.0",
+      "resolved": "https://registry.npmjs.org/get-intrinsic/-/get-intrinsic-1.3.0.tgz",
+      "integrity": "sha512-9fSjSaos/fRIVIp+xSJlE6lfwhES7LNtKaCBIamHsjr2na1BiABJPo0mOjjz8GJDURarmCPGqaiVg5mfjb98CQ==",
+      "license": "MIT",
+      "dependencies": {
+        "call-bind-apply-helpers": "^1.0.2",
+        "es-define-property": "^1.0.1",
+        "es-errors": "^1.3.0",
+        "es-object-atoms": "^1.1.1",
+        "function-bind": "^1.1.2",
+        "get-proto": "^1.0.1",
+        "gopd": "^1.2.0",
+        "has-symbols": "^1.1.0",
+        "hasown": "^2.0.2",
+        "math-intrinsics": "^1.1.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
     "node_modules/get-package-type": {
       "version": "0.1.0",
       "resolved": "https://registry.npmjs.org/get-package-type/-/get-package-type-0.1.0.tgz",
@@ -2716,6 +2704,19 @@
         "node": ">=8.0.0"
       }
     },
+    "node_modules/get-proto": {
+      "version": "1.0.1",
+      "resolved": "https://registry.npmjs.org/get-proto/-/get-proto-1.0.1.tgz",
+      "integrity": "sha512-sTSfBjoXBp89JvIKIefqw7U2CCebsc74kiY6awiGogKtoSGbgjYE/G/+l9sF3MWFPNc9IcoOC4ODfKHfxFmp0g==",
+      "license": "MIT",
+      "dependencies": {
+        "dunder-proto": "^1.0.1",
+        "es-object-atoms": "^1.0.0"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/get-stream": {
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/get-stream/-/get-stream-6.0.1.tgz",
@@ -2758,6 +2759,18 @@
         "node": ">=4"
       }
     },
+    "node_modules/gopd": {
+      "version": "1.2.0",
+      "resolved": "https://registry.npmjs.org/gopd/-/gopd-1.2.0.tgz",
+      "integrity": "sha512-ZUKRh6/kUFoAiTAtTYPZJ3hw9wNxx+BIBOijnlG9PnrJsCcSjs1wyyD6vJpaYtgnzDrKYRSqf3OO6Rfa93xsRg==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
     "node_modules/graceful-fs": {
       "version": "4.2.11",
       "resolved": "https://registry.npmjs.org/graceful-fs/-/graceful-fs-4.2.11.tgz",
@@ -2778,11 +2791,37 @@
         "node": ">=8"
       }
     },
+    "node_modules/has-symbols": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/has-symbols/-/has-symbols-1.1.0.tgz",
+      "integrity": "sha512-1cDNdwJ2Jaohmb3sg4OmKaMBwuC48sYni5HUw2DvsC8LjGTLK9h+eb1X6RyuOHe4hT0ULCW68iomhjUoKUqlPQ==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
+    "node_modules/has-tostringtag": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/has-tostringtag/-/has-tostringtag-1.0.2.tgz",
+      "integrity": "sha512-NqADB8VjPFLM2V0VvHUewwwsw0ZWBaIdgo+ieHtK3hasLz4qeCRjYcqfB6AQrBggRKppKF8L52/VqdVsO47Dlw==",
+      "license": "MIT",
+      "dependencies": {
+        "has-symbols": "^1.0.3"
+      },
+      "engines": {
+        "node": ">= 0.4"
+      },
+      "funding": {
+        "url": "https://github.com/sponsors/ljharb"
+      }
+    },
     "node_modules/hasown": {
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/hasown/-/hasown-2.0.2.tgz",
       "integrity": "sha512-0hJU9SCPvmMzIBdZFqNPXWa6dqh7WdH0cII9y+CyS8rG3nL48Bclra9HmKhVVUHyPWNH5Y7xDwAB7bfgSjkUMQ==",
-      "dev": true,
       "dependencies": {
         "function-bind": "^1.1.2"
       },
@@ -2882,6 +2921,7 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz",
       "integrity": "sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==",
+      "dev": true,
       "engines": {
         "node": ">=8"
       }
@@ -2919,7 +2959,8 @@
     "node_modules/isexe": {
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/isexe/-/isexe-2.0.0.tgz",
-      "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw=="
+      "integrity": "sha512-RHxMLp9lnKHGHRng9QFhRCMbYAcVpn69smSGcq3f36xjgVVWThj4qqLbTLlq7Ssj8B+fIQ1EuCEGI2lKsyQeIw==",
+      "dev": true
     },
     "node_modules/istanbul-lib-coverage": {
       "version": "3.2.2",
@@ -2987,20 +3028,6 @@
         "node": ">=8"
       }
     },
-    "node_modules/jackspeak": {
-      "version": "3.4.3",
-      "resolved": "https://registry.npmjs.org/jackspeak/-/jackspeak-3.4.3.tgz",
-      "integrity": "sha512-OGlZQpz2yfahA/Rd1Y8Cd9SIEsqvXkLVoSw/cgwhnhFMDbsQFeZYoJJ7bIZBS9BcamUW96asq/npPWugM+RQBw==",
-      "dependencies": {
-        "@isaacs/cliui": "^8.0.2"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      },
-      "optionalDependencies": {
-        "@pkgjs/parseargs": "^0.11.0"
-      }
-    },
     "node_modules/jake": {
       "version": "10.9.2",
       "resolved": "https://registry.npmjs.org/jake/-/jake-10.9.2.tgz",
@@ -3605,10 +3632,11 @@
       "dev": true
     },
     "node_modules/js-yaml": {
-      "version": "3.14.1",
-      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.1.tgz",
-      "integrity": "sha512-okMH7OXXJ7YrN9Ok3/SXrnu4iX9yOk+25nqX4imS2npuvTYDmo/QEZoqwZkYaIDk3jVvBOTOIEgEhaLOynBS9g==",
+      "version": "3.14.2",
+      "resolved": "https://registry.npmjs.org/js-yaml/-/js-yaml-3.14.2.tgz",
+      "integrity": "sha512-PMSmkqxr106Xa156c2M265Z+FTrPl+oxd/rgOQy2tijQeK5TxQ43psO1ZCwhVOSdnn+RzkzlRz/eY4BgJBYVpg==",
       "dev": true,
+      "license": "MIT",
       "dependencies": {
         "argparse": "^1.0.7",
         "esprima": "^4.0.0"
@@ -3728,6 +3756,15 @@
         "tmpl": "1.0.5"
       }
     },
+    "node_modules/math-intrinsics": {
+      "version": "1.1.0",
+      "resolved": "https://registry.npmjs.org/math-intrinsics/-/math-intrinsics-1.1.0.tgz",
+      "integrity": "sha512-/IXtbwEk5HTPyEwyKX6hGkYXxM9nbj64B+ilVJnC/R6B0pH5G4V3b0pVbL7DBj4tkhBAppbQUlf6F6Xl9LHu1g==",
+      "license": "MIT",
+      "engines": {
+        "node": ">= 0.4"
+      }
+    },
     "node_modules/merge-stream": {
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/merge-stream/-/merge-stream-2.0.0.tgz",
@@ -3776,10 +3813,11 @@
       }
     },
     "node_modules/minimatch": {
-      "version": "3.1.2",
-      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.2.tgz",
-      "integrity": "sha512-J7p63hRiAjw1NDEww1W7i37+ByIrOWO5XQQAzZ3VOcL0PNybwpfmV/N05zFAzwQ9USyEcX6t3UO+K5aqBQOIHw==",
+      "version": "3.1.5",
+      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-3.1.5.tgz",
+      "integrity": "sha512-VgjWUsnnT6n+NUk6eZq77zeFdpW2LWDzP6zFGrCbHXiYNul5Dzqk2HHQ5uFH2DNW5Xbp8+jVzaeNt94ssEEl4w==",
       "dev": true,
+      "license": "ISC",
       "dependencies": {
         "brace-expansion": "^1.1.7"
       },
@@ -3796,31 +3834,17 @@
       }
     },
     "node_modules/minizlib": {
-      "version": "3.0.1",
-      "resolved": "https://registry.npmjs.org/minizlib/-/minizlib-3.0.1.tgz",
-      "integrity": "sha512-umcy022ILvb5/3Djuu8LWeqUa8D68JaBzlttKeMWen48SjabqS3iY5w/vzeMzMUNhLDifyhbOwKDSznB1vvrwg==",
+      "version": "3.1.0",
+      "resolved": "https://registry.npmjs.org/minizlib/-/minizlib-3.1.0.tgz",
+      "integrity": "sha512-KZxYo1BUkWD2TVFLr0MQoM8vUUigWD3LlD83a/75BqC+4qE0Hb1Vo5v1FgcfaNXvfXzr+5EhQ6ing/CaBijTlw==",
+      "license": "MIT",
       "dependencies": {
-        "minipass": "^7.0.4",
-        "rimraf": "^5.0.5"
+        "minipass": "^7.1.2"
       },
       "engines": {
         "node": ">= 18"
       }
     },
-    "node_modules/mkdirp": {
-      "version": "3.0.1",
-      "resolved": "https://registry.npmjs.org/mkdirp/-/mkdirp-3.0.1.tgz",
-      "integrity": "sha512-+NsyUUAZDmo6YVHzL/stxSu3t9YS1iljliy3BSDrXJ/dkn1KYdmtZODGGjLcc9XLgVVpH4KshHB8XmZgMhaBXg==",
-      "bin": {
-        "mkdirp": "dist/cjs/src/bin.js"
-      },
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
     "node_modules/ms": {
       "version": "2.1.3",
       "resolved": "https://registry.npmjs.org/ms/-/ms-2.1.3.tgz",
@@ -4010,11 +4034,6 @@
         "node": ">=6"
       }
     },
-    "node_modules/package-json-from-dist": {
-      "version": "1.0.1",
-      "resolved": "https://registry.npmjs.org/package-json-from-dist/-/package-json-from-dist-1.0.1.tgz",
-      "integrity": "sha512-UEZIS3/by4OC8vL3P2dTXRETpebLI2NiI5vIrjaD/5UtrkFX/tNbwjTSRAGC/+7CAo2pIcBaRgWmcBBHcsaCIw=="
-    },
     "node_modules/parse-json": {
       "version": "5.2.0",
       "resolved": "https://registry.npmjs.org/parse-json/-/parse-json-5.2.0.tgz",
@@ -4055,6 +4074,7 @@
       "version": "3.1.1",
       "resolved": "https://registry.npmjs.org/path-key/-/path-key-3.1.1.tgz",
       "integrity": "sha512-ojmeN0qd+y0jszEtoY48r0Peq5dwMEkIlCOu6Q5f41lfkswXuKtYrhgoTpLnyIcHm24Uhqx+5Tqm2InSwLhE6Q==",
+      "dev": true,
       "engines": {
         "node": ">=8"
       }
@@ -4065,26 +4085,6 @@
       "integrity": "sha512-LDJzPVEEEPR+y48z93A0Ed0yXb8pAByGWo/k5YYdYgpY2/2EsOsksJrq7lOHxryrVOn1ejG6oAp8ahvOIQD8sw==",
       "dev": true
     },
-    "node_modules/path-scurry": {
-      "version": "1.11.1",
-      "resolved": "https://registry.npmjs.org/path-scurry/-/path-scurry-1.11.1.tgz",
-      "integrity": "sha512-Xa4Nw17FS9ApQFJ9umLiJS4orGjm7ZzwUrwamcGQuHSzDyth9boKDaycYdDcZDuqYATXw4HFXgaqWTctW/v1HA==",
-      "dependencies": {
-        "lru-cache": "^10.2.0",
-        "minipass": "^5.0.0 || ^6.0.2 || ^7.0.0"
-      },
-      "engines": {
-        "node": ">=16 || 14 >=14.18"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
-    "node_modules/path-scurry/node_modules/lru-cache": {
-      "version": "10.4.3",
-      "resolved": "https://registry.npmjs.org/lru-cache/-/lru-cache-10.4.3.tgz",
-      "integrity": "sha512-JNAzZcXrCt42VGLuYz0zfAzDfAvJWW6AfYlDBQyDV5DClI2m5sAmK+OIO7s59XfsRsWHp02jAJrRadPRGTt6SQ=="
-    },
     "node_modules/picocolors": {
       "version": "1.1.1",
       "resolved": "https://registry.npmjs.org/picocolors/-/picocolors-1.1.1.tgz",
@@ -4246,61 +4246,6 @@
         "node": ">=10"
       }
     },
-    "node_modules/rimraf": {
-      "version": "5.0.10",
-      "resolved": "https://registry.npmjs.org/rimraf/-/rimraf-5.0.10.tgz",
-      "integrity": "sha512-l0OE8wL34P4nJH/H2ffoaniAokM2qSmrtXHmlpvYr5AVVX8msAyW0l8NVJFDxlSK4u3Uh/f41cQheDVdnYijwQ==",
-      "dependencies": {
-        "glob": "^10.3.7"
-      },
-      "bin": {
-        "rimraf": "dist/esm/bin.mjs"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
-    "node_modules/rimraf/node_modules/brace-expansion": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/brace-expansion/-/brace-expansion-2.0.1.tgz",
-      "integrity": "sha512-XnAIvQ8eM+kC6aULx6wuQiwVsnzsi9d3WxzV3FpWTGA19F621kwdbsAcFKXgKUHZWsy+mY6iL1sHTxWEFCytDA==",
-      "dependencies": {
-        "balanced-match": "^1.0.0"
-      }
-    },
-    "node_modules/rimraf/node_modules/glob": {
-      "version": "10.4.5",
-      "resolved": "https://registry.npmjs.org/glob/-/glob-10.4.5.tgz",
-      "integrity": "sha512-7Bv8RF0k6xjo7d4A/PxYLbUCfb6c+Vpd2/mB2yRDlew7Jb5hEXiCD9ibfO7wpk8i4sevK6DFny9h7EYbM3/sHg==",
-      "dependencies": {
-        "foreground-child": "^3.1.0",
-        "jackspeak": "^3.1.2",
-        "minimatch": "^9.0.4",
-        "minipass": "^7.1.2",
-        "package-json-from-dist": "^1.0.0",
-        "path-scurry": "^1.11.1"
-      },
-      "bin": {
-        "glob": "dist/esm/bin.mjs"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
-    "node_modules/rimraf/node_modules/minimatch": {
-      "version": "9.0.5",
-      "resolved": "https://registry.npmjs.org/minimatch/-/minimatch-9.0.5.tgz",
-      "integrity": "sha512-G6T0ZX48xgozx7587koeX9Ys2NYy6Gmv//P89sEte9V9whIapMNF4idKxnW2QtCcLiTWlb/wfCabAtAFWhhBow==",
-      "dependencies": {
-        "brace-expansion": "^2.0.1"
-      },
-      "engines": {
-        "node": ">=16 || 14 >=14.17"
-      },
-      "funding": {
-        "url": "https://github.com/sponsors/isaacs"
-      }
-    },
     "node_modules/semver": {
       "version": "7.6.3",
       "resolved": "https://registry.npmjs.org/semver/-/semver-7.6.3.tgz",
@@ -4354,6 +4299,7 @@
       "version": "2.0.0",
       "resolved": "https://registry.npmjs.org/shebang-command/-/shebang-command-2.0.0.tgz",
       "integrity": "sha512-kHxr2zZpYtdmrN1qDjrrX/Z1rR1kG8Dx+gkpK1G4eXmvXswmcE1hTWBWYUzlraYw1/yZp6YuDY77YtvbN0dmDA==",
+      "dev": true,
       "dependencies": {
         "shebang-regex": "^3.0.0"
       },
@@ -4365,6 +4311,7 @@
       "version": "3.0.0",
       "resolved": "https://registry.npmjs.org/shebang-regex/-/shebang-regex-3.0.0.tgz",
       "integrity": "sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==",
+      "dev": true,
       "engines": {
         "node": ">=8"
       }
@@ -4452,20 +4399,7 @@
       "version": "4.2.3",
       "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
       "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
-      "dependencies": {
-        "emoji-regex": "^8.0.0",
-        "is-fullwidth-code-point": "^3.0.0",
-        "strip-ansi": "^6.0.1"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/string-width-cjs": {
-      "name": "string-width",
-      "version": "4.2.3",
-      "resolved": "https://registry.npmjs.org/string-width/-/string-width-4.2.3.tgz",
-      "integrity": "sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==",
+      "dev": true,
       "dependencies": {
         "emoji-regex": "^8.0.0",
         "is-fullwidth-code-point": "^3.0.0",
@@ -4479,18 +4413,7 @@
       "version": "6.0.1",
       "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz",
       "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==",
-      "dependencies": {
-        "ansi-regex": "^5.0.1"
-      },
-      "engines": {
-        "node": ">=8"
-      }
-    },
-    "node_modules/strip-ansi-cjs": {
-      "name": "strip-ansi",
-      "version": "6.0.1",
-      "resolved": "https://registry.npmjs.org/strip-ansi/-/strip-ansi-6.0.1.tgz",
-      "integrity": "sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==",
+      "dev": true,
       "dependencies": {
         "ansi-regex": "^5.0.1"
       },
@@ -4541,15 +4464,15 @@
       }
     },
     "node_modules/tar": {
-      "version": "7.4.3",
-      "resolved": "https://registry.npmjs.org/tar/-/tar-7.4.3.tgz",
-      "integrity": "sha512-5S7Va8hKfV7W5U6g3aYxXmlPoZVAwUMy9AOKyF2fVuZa2UD3qZjg578OrLRt8PcNN1PleVaL/5/yYATNL0ICUw==",
+      "version": "7.5.10",
+      "resolved": "https://registry.npmjs.org/tar/-/tar-7.5.10.tgz",
+      "integrity": "sha512-8mOPs1//5q/rlkNSPcCegA6hiHJYDmSLEI8aMH/CdSQJNWztHC9WHNam5zdQlfpTwB9Xp7IBEsHfV5LKMJGVAw==",
+      "license": "BlueOak-1.0.0",
       "dependencies": {
         "@isaacs/fs-minipass": "^4.0.0",
         "chownr": "^3.0.0",
         "minipass": "^7.1.2",
-        "minizlib": "^3.0.1",
-        "mkdirp": "^3.0.1",
+        "minizlib": "^3.1.0",
         "yallist": "^5.0.0"
       },
       "engines": {
@@ -4782,6 +4705,7 @@
       "version": "2.0.2",
       "resolved": "https://registry.npmjs.org/which/-/which-2.0.2.tgz",
       "integrity": "sha512-BLI3Tl1TW3Pvl70l3yq3Y64i+awpwXqsGBYWkkqMtnbXgrMD+yj7rhW0kuEDxzJaYXGjEW5ogapKNMEKNMjibA==",
+      "dev": true,
       "dependencies": {
         "isexe": "^2.0.0"
       },
@@ -4809,23 +4733,6 @@
         "url": "https://github.com/chalk/wrap-ansi?sponsor=1"
       }
     },
-    "node_modules/wrap-ansi-cjs": {
-      "name": "wrap-ansi",
-      "version": "7.0.0",
-      "resolved": "https://registry.npmjs.org/wrap-ansi/-/wrap-ansi-7.0.0.tgz",
-      "integrity": "sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==",
-      "dependencies": {
-        "ansi-styles": "^4.0.0",
-        "string-width": "^4.1.0",
-        "strip-ansi": "^6.0.0"
-      },
-      "engines": {
-        "node": ">=10"
-      },
-      "funding": {
-        "url": "https://github.com/chalk/wrap-ansi?sponsor=1"
-      }
-    },
     "node_modules/wrappy": {
       "version": "1.0.2",
       "resolved": "https://registry.npmjs.org/wrappy/-/wrappy-1.0.2.tgz",

nodejs/lancedb/arrow.ts

@@ -20,6 +20,8 @@ import {
   Float32,
   Float64,
   Int,
+  Int8,
+  Int16,
   Int32,
   Int64,
   LargeBinary,
@@ -35,6 +37,8 @@ import {
   Timestamp,
   Type,
   Uint8,
+  Uint16,
+  Uint32,
   Utf8,
   Vector,
   makeVector as arrowMakeVector,
@@ -529,7 +533,8 @@ function isObject(value: unknown): value is Record<string, unknown> {
     !(value instanceof Date) &&
     !(value instanceof Set) &&
     !(value instanceof Map) &&
-    !(value instanceof Buffer)
+    !(value instanceof Buffer) &&
+    !ArrayBuffer.isView(value)
   );
 }
 
@@ -588,6 +593,13 @@ function inferType(
     return new Bool();
   } else if (value instanceof Buffer) {
     return new Binary();
+  } else if (ArrayBuffer.isView(value) && !(value instanceof DataView)) {
+    const info = typedArrayToArrowType(value);
+    if (info !== undefined) {
+      const child = new Field("item", info.elementType, true);
+      return new FixedSizeList(info.length, child);
+    }
+    return undefined;
   } else if (Array.isArray(value)) {
     if (value.length === 0) {
       return undefined; // Without any values we can't infer the type
@@ -746,6 +758,32 @@ function makeListVector(lists: unknown[][]): Vector<unknown> {
   return listBuilder.finish().toVector();
 }
 
+/**
+ * Map a JS TypedArray instance to the corresponding Arrow element DataType
+ * and its length. Returns undefined if the value is not a recognized TypedArray.
+ */
+function typedArrayToArrowType(
+  value: ArrayBufferView,
+): { elementType: DataType; length: number } | undefined {
+  if (value instanceof Float32Array)
+    return { elementType: new Float32(), length: value.length };
+  if (value instanceof Float64Array)
+    return { elementType: new Float64(), length: value.length };
+  if (value instanceof Uint8Array)
+    return { elementType: new Uint8(), length: value.length };
+  if (value instanceof Uint16Array)
+    return { elementType: new Uint16(), length: value.length };
+  if (value instanceof Uint32Array)
+    return { elementType: new Uint32(), length: value.length };
+  if (value instanceof Int8Array)
+    return { elementType: new Int8(), length: value.length };
+  if (value instanceof Int16Array)
+    return { elementType: new Int16(), length: value.length };
+  if (value instanceof Int32Array)
+    return { elementType: new Int32(), length: value.length };
+  return undefined;
+}
+
 /** Helper function to convert an Array of JS values to an Arrow Vector */
 function makeVector(
   values: unknown[],
@@ -814,6 +852,16 @@ function makeVector(
       "makeVector cannot infer the type if all values are null or undefined",
     );
   }
+  if (ArrayBuffer.isView(sampleValue) && !(sampleValue instanceof DataView)) {
+    const info = typedArrayToArrowType(sampleValue);
+    if (info !== undefined) {
+      const fslType = new FixedSizeList(
+        info.length,
+        new Field("item", info.elementType, true),
+      );
+      return vectorFromArray(values, fslType);
+    }
+  }
   if (Array.isArray(sampleValue)) {
     // Default Arrow inference doesn't handle list types
     return makeListVector(values as unknown[][]);

nodejs/lancedb/table.ts

@@ -5,12 +5,15 @@ import {
   Table as ArrowTable,
   Data,
   DataType,
+  Field,
   IntoVector,
   MultiVector,
   Schema,
   dataTypeToJson,
   fromDataToBuffer,
+  fromTableToBuffer,
   isMultiVector,
+  makeEmptyTable,
   tableFromIPC,
 } from "./arrow";
 
@@ -84,6 +87,16 @@ export interface OptimizeOptions {
    * tbl.optimize({cleanupOlderThan: new Date()});
    */
   cleanupOlderThan: Date;
+  /**
+   * Because they may be part of an in-progress transaction, files newer than
+   * 7 days old are not deleted by default. If you are sure that there are no
+   * in-progress transactions, then you can set this to true to delete all
+   * files older than `cleanupOlderThan`.
+   *
+   * **WARNING**: This should only be set to true if you can guarantee that
+   * no other process is currently working on this dataset. Otherwise the
+   * dataset could be put into a corrupted state.
+   */
   deleteUnverified: boolean;
 }
 
@@ -381,15 +394,16 @@ export abstract class Table {
   abstract vectorSearch(vector: IntoVector | MultiVector): VectorQuery;
   /**
    * Add new columns with defined values.
-   * @param {AddColumnsSql[]} newColumnTransforms pairs of column names and
-   * the SQL expression to use to calculate the value of the new column. These
-   * expressions will be evaluated for each row in the table, and can
-   * reference existing columns in the table.
+   * @param {AddColumnsSql[] | Field | Field[] | Schema} newColumnTransforms Either:
+   *   - An array of objects with column names and SQL expressions to calculate values
+   *   - A single Arrow Field defining one column with its data type (column will be initialized with null values)
+   *   - An array of Arrow Fields defining columns with their data types (columns will be initialized with null values)
+   *   - An Arrow Schema defining columns with their data types (columns will be initialized with null values)
    * @returns {Promise<AddColumnsResult>} A promise that resolves to an object
    * containing the new version number of the table after adding the columns.
    */
   abstract addColumns(
-    newColumnTransforms: AddColumnsSql[],
+    newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
   ): Promise<AddColumnsResult>;
 
   /**
@@ -501,19 +515,7 @@ export abstract class Table {
    *  - Index: Optimizes the indices, adding new data to existing indices
    *
    *
-   *  Experimental API
-   *  ----------------
-   *
-   *  The optimization process is undergoing active development and may change.
-   *  Our goal with these changes is to improve the performance of optimization and
-   *  reduce the complexity.
-   *
-   *  That being said, it is essential today to run optimize if you want the best
-   *  performance.  It should be stable and safe to use in production, but it our
-   *  hope that the API may be simplified (or not even need to be called) in the
-   *  future.
-   *
-   *  The frequency an application shoudl call optimize is based on the frequency of
+   *  The frequency an application should call optimize is based on the frequency of
    *  data modifications.  If data is frequently added, deleted, or updated then
    *  optimize should be run frequently.  A good rule of thumb is to run optimize if
    *  you have added or modified 100,000 or more records or run more than 20 data
@@ -806,9 +808,40 @@ export class LocalTable extends Table {
   // TODO: Support BatchUDF
 
   async addColumns(
-    newColumnTransforms: AddColumnsSql[],
+    newColumnTransforms: AddColumnsSql[] | Field | Field[] | Schema,
   ): Promise<AddColumnsResult> {
-    return await this.inner.addColumns(newColumnTransforms);
+    // Handle single Field -> convert to array of Fields
+    if (newColumnTransforms instanceof Field) {
+      newColumnTransforms = [newColumnTransforms];
+    }
+
+    // Handle array of Fields -> convert to Schema
+    if (
+      Array.isArray(newColumnTransforms) &&
+      newColumnTransforms.length > 0 &&
+      newColumnTransforms[0] instanceof Field
+    ) {
+      const fields = newColumnTransforms as Field[];
+      newColumnTransforms = new Schema(fields);
+    }
+
+    // Handle Schema -> use schema-based approach
+    if (newColumnTransforms instanceof Schema) {
+      const schema = newColumnTransforms;
+      // Convert schema to buffer using Arrow IPC format
+      const emptyTable = makeEmptyTable(schema);
+      const schemaBuf = await fromTableToBuffer(emptyTable);
+      return await this.inner.addColumnsWithSchema(schemaBuf);
+    }
+
+    // Handle SQL expressions (existing functionality)
+    if (Array.isArray(newColumnTransforms)) {
+      return await this.inner.addColumns(
+        newColumnTransforms as AddColumnsSql[],
+      );
+    }
+
+    throw new Error("Invalid input type for addColumns");
   }
 
   async alterColumns(

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.27.0-beta.2",
+	"version": "0.27.2-beta.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.27.0-beta.2",
+	"version": "0.27.2-beta.0",
 	"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": "0.27.0-beta.2",
+	"version": "0.27.2-beta.0",
 	"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": "0.27.0-beta.2",
+	"version": "0.27.2-beta.0",
 	"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": "0.27.0-beta.2",
+	"version": "0.27.2-beta.0",
 	"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": "0.27.0-beta.2",
+  "version": "0.27.2-beta.0",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.27.0-beta.2",
+	"version": "0.27.2-beta.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.27.0-beta.2",
+  "version": "0.27.2-beta.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/connection.rs

@@ -8,10 +8,10 @@ use lancedb::database::{CreateTableMode, Database};
 use napi::bindgen_prelude::*;
 use napi_derive::*;
 
+use crate::ConnectionOptions;
 use crate::error::NapiErrorExt;
 use crate::header::JsHeaderProvider;
 use crate::table::Table;
-use crate::ConnectionOptions;
 use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection};
 
 use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};

nodejs/src/index.rs

@@ -3,12 +3,12 @@
 
 use std::sync::Mutex;
 
+use lancedb::index::Index as LanceDbIndex;
 use lancedb::index::scalar::{BTreeIndexBuilder, FtsIndexBuilder};
 use lancedb::index::vector::{
     IvfFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder,
     IvfRqIndexBuilder,
 };
-use lancedb::index::Index as LanceDbIndex;
 use napi_derive::napi;
 
 use crate::util::parse_distance_type;

nodejs/src/query.rs

@@ -17,8 +17,8 @@ use lancedb::query::VectorQuery as LanceDbVectorQuery;
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
 
-use crate::error::convert_error;
 use crate::error::NapiErrorExt;
+use crate::error::convert_error;
 use crate::iterator::RecordBatchIterator;
 use crate::rerankers::RerankHybridCallbackArgs;
 use crate::rerankers::Reranker;
@@ -551,15 +551,12 @@ fn parse_fts_query(query: Object) -> napi::Result<FullTextSearchQuery> {
             }
         };
         let mut query = FullTextSearchQuery::new_query(query);
-        if let Some(cols) = columns {
-            if !cols.is_empty() {
-                query = query.with_columns(&cols).map_err(|e| {
-                    napi::Error::from_reason(format!(
-                        "Failed to set full text search columns: {}",
-                        e
-                    ))
-                })?;
-            }
+        if let Some(cols) = columns
+            && !cols.is_empty()
+        {
+            query = query.with_columns(&cols).map_err(|e| {
+                napi::Error::from_reason(format!("Failed to set full text search columns: {}", e))
+            })?;
         }
         Ok(query)
     } else {

nodejs/src/session.rs

@@ -95,7 +95,7 @@ impl napi::bindgen_prelude::FromNapiValue for Session {
         napi_val: napi::sys::napi_value,
     ) -> napi::Result<Self> {
         let object: napi::bindgen_prelude::ClassInstance<Self> =
-            napi::bindgen_prelude::ClassInstance::from_napi_value(env, napi_val)?;
+            unsafe { napi::bindgen_prelude::ClassInstance::from_napi_value(env, napi_val)? };
         Ok((*object).clone())
     }
 }

nodejs/src/table.rs

@@ -3,7 +3,7 @@
 
 use std::collections::HashMap;
 
-use lancedb::ipc::ipc_file_to_batches;
+use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
 use lancedb::table::{
     AddDataMode, ColumnAlteration as LanceColumnAlteration, Duration, NewColumnTransform,
     OptimizeAction, OptimizeOptions, Table as LanceDbTable,
@@ -279,6 +279,23 @@ impl Table {
         Ok(res.into())
     }
 
+    #[napi(catch_unwind)]
+    pub async fn add_columns_with_schema(
+        &self,
+        schema_buf: Buffer,
+    ) -> napi::Result<AddColumnsResult> {
+        let schema = ipc_file_to_schema(schema_buf.to_vec())
+            .map_err(|e| napi::Error::from_reason(format!("Failed to read IPC schema: {}", e)))?;
+
+        let transforms = NewColumnTransform::AllNulls(schema);
+        let res = self
+            .inner_ref()?
+            .add_columns(transforms, None)
+            .await
+            .default_error()?;
+        Ok(res.into())
+    }
+
     #[napi(catch_unwind)]
     pub async fn alter_columns(
         &self,
@@ -753,12 +770,14 @@ impl From<lancedb::table::AddResult> for AddResult {
 
 #[napi(object)]
 pub struct DeleteResult {
+    pub num_deleted_rows: i64,
     pub version: i64,
 }
 
 impl From<lancedb::table::DeleteResult> for DeleteResult {
     fn from(value: lancedb::table::DeleteResult) -> Self {
         Self {
+            num_deleted_rows: value.num_deleted_rows as i64,
             version: value.version as i64,
         }
     }

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.30.0-beta.3"
+current_version = "0.30.2-beta.1"
 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 = "0.30.0-beta.3"
+version = "0.30.2-beta.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -16,11 +16,14 @@ crate-type = ["cdylib"]
 [dependencies]
 arrow = { version = "57.2", features = ["pyarrow"] }
 async-trait = "0.1"
+bytes = "1"
 lancedb = { path = "../rust/lancedb", default-features = false }
 lance-core.workspace = true
 lance-namespace.workspace = true
+lance-namespace-impls.workspace = true
 lance-io.workspace = true
 env_logger.workspace = true
+log.workspace = true
 pyo3 = { version = "0.26", features = ["extension-module", "abi3-py39"] }
 pyo3-async-runtimes = { version = "0.26", features = [
     "attributes",
@@ -28,6 +31,8 @@ pyo3-async-runtimes = { version = "0.26", features = [
 ] }
 pin-project = "1.1.5"
 futures.workspace = true
+serde = "1"
+serde_json = "1"
 snafu.workspace = true
 tokio = { version = "1.40", features = ["sync"] }
 

python/README.md

@@ -1,4 +1,4 @@
-# LanceDB
+# LanceDB Python SDK
 
 A Python library for [LanceDB](https://github.com/lancedb/lancedb).
 

python/pyproject.toml

@@ -3,10 +3,10 @@ name = "lancedb"
 # version in Cargo.toml
 dynamic = ["version"]
 dependencies = [
-    "deprecation",
-    "numpy",
+    "deprecation>=2.1.0",
+    "numpy>=1.24.0",
     "overrides>=0.7; python_version<'3.12'",
-    "packaging",
+    "packaging>=23.0",
     "pyarrow>=16",
     "pydantic>=1.10",
     "tqdm>=4.27.0",
@@ -45,51 +45,51 @@ repository = "https://github.com/lancedb/lancedb"
 
 [project.optional-dependencies]
 pylance = [
-    "pylance>=1.0.0b14",
+    "pylance>=4.0.0b7",
 ]
 tests = [
-    "aiohttp",
-    "boto3",
+    "aiohttp>=3.9.0",
+    "boto3>=1.28.57",
     "pandas>=1.4",
-    "pytest",
-    "pytest-mock",
-    "pytest-asyncio",
-    "duckdb",
-    "pytz",
+    "pytest>=7.0",
+    "pytest-mock>=3.10",
+    "pytest-asyncio>=0.21",
+    "duckdb>=0.9.0",
+    "pytz>=2023.3",
     "polars>=0.19, <=1.3.0",
-    "tantivy",
-    "pyarrow-stubs",
-    "pylance>=1.0.0b14,<3.0.0",
-    "requests",
-    "datafusion<52",
+    "tantivy>=0.20.0",
+    "pyarrow-stubs>=16.0",
+    "pylance>=4.0.0b7",
+    "requests>=2.31.0",
+    "datafusion>=52,<53",
 ]
 dev = [
-    "ruff",
-    "pre-commit",
-    "pyright",
+    "ruff>=0.3.0",
+    "pre-commit>=3.5.0",
+    "pyright>=1.1.350",
     'typing-extensions>=4.0.0; python_version < "3.11"',
 ]
 docs = ["mkdocs", "mkdocs-jupyter", "mkdocs-material", "mkdocstrings-python"]
-clip = ["torch", "pillow", "open-clip-torch"]
-siglip = ["torch", "pillow", "transformers>=4.41.0","sentencepiece"]
+clip = ["torch", "pillow>=12.1.1", "open-clip-torch"]
+siglip = ["torch", "pillow>=12.1.1", "transformers>=4.41.0","sentencepiece"]
 embeddings = [
     "requests>=2.31.0",
     "openai>=1.6.1",
-    "sentence-transformers",
-    "torch",
-    "pillow",
-    "open-clip-torch",
-    "cohere",
+    "sentence-transformers>=2.2.0",
+    "torch>=2.0.0",
+    "pillow>=12.1.1",
+    "open-clip-torch>=2.20.0",
+    "cohere>=4.0",
     "colpali-engine>=0.3.10",
-    "huggingface_hub",
-    "InstructorEmbedding",
-    "google.generativeai",
+    "huggingface_hub>=0.19.0",
+    "InstructorEmbedding>=1.0.1",
+    "google.generativeai>=0.3.0",
     "boto3>=1.28.57",
-    "awscli>=1.29.57",
+    "awscli>=1.44.38",
     "botocore>=1.31.57",
     'ibm-watsonx-ai>=1.1.2; python_version >= "3.10"',
     "ollama>=0.3.0",
-    "sentencepiece"
+    "sentencepiece>=0.1.99"
 ]
 azure = ["adlfs>=2024.2.0"]
 

python/python/lancedb/_lancedb.pyi

@@ -135,7 +135,10 @@ class Table:
     def close(self) -> None: ...
     async def schema(self) -> pa.Schema: ...
     async def add(
-        self, data: pa.RecordBatchReader, mode: Literal["append", "overwrite"]
+        self,
+        data: pa.RecordBatchReader,
+        mode: Literal["append", "overwrite"],
+        progress: Optional[Any] = None,
     ) -> AddResult: ...
     async def update(
         self, updates: Dict[str, str], where: Optional[str]
@@ -166,6 +169,8 @@ class Table:
     async def checkout(self, version: Union[int, str]): ...
     async def checkout_latest(self): ...
     async def restore(self, version: Optional[Union[int, str]] = None): ...
+    async def prewarm_index(self, index_name: str) -> None: ...
+    async def prewarm_data(self, columns: Optional[List[str]] = None) -> None: ...
     async def list_indices(self) -> list[IndexConfig]: ...
     async def delete(self, filter: str) -> DeleteResult: ...
     async def add_columns(self, columns: list[tuple[str, str]]) -> AddColumnsResult: ...

python/python/lancedb/db.py

@@ -8,7 +8,7 @@ from abc import abstractmethod
 from datetime import timedelta
 from pathlib import Path
 import sys
-from typing import TYPE_CHECKING, Dict, Iterable, List, Literal, Optional, Union
+from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Literal, Optional, Union
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -1541,6 +1541,8 @@ class AsyncConnection(object):
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
         location: Optional[str] = None,
+        namespace_client: Optional[Any] = None,
+        managed_versioning: Optional[bool] = None,
     ) -> AsyncTable:
         """Open a Lance Table in the database.
 
@@ -1573,6 +1575,9 @@ class AsyncConnection(object):
             The explicit location (URI) of the table. If provided, the table will be
             opened from this location instead of deriving it from the database URI
             and table name.
+        managed_versioning: bool, optional
+            Whether managed versioning is enabled for this table. If provided,
+            avoids a redundant describe_table call when namespace_client is set.
 
         Returns
         -------
@@ -1587,6 +1592,8 @@ class AsyncConnection(object):
             storage_options_provider=storage_options_provider,
             index_cache_size=index_cache_size,
             location=location,
+            namespace_client=namespace_client,
+            managed_versioning=managed_versioning,
         )
         return AsyncTable(table)
 

python/python/lancedb/namespace.py

@@ -12,7 +12,7 @@ from __future__ import annotations
 
 import asyncio
 import sys
-from typing import Dict, Iterable, List, Optional, Union
+from typing import Any, Dict, Iterable, List, Optional, Union
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -240,7 +240,7 @@ class LanceNamespaceDBConnection(DBConnection):
         session : Optional[Session]
             A session to use for this connection
         """
-        self._ns = namespace
+        self._namespace_client = namespace
         self.read_consistency_interval = read_consistency_interval
         self.storage_options = storage_options or {}
         self.session = session
@@ -269,7 +269,7 @@ class LanceNamespaceDBConnection(DBConnection):
         if namespace is None:
             namespace = []
         request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
-        response = self._ns.list_tables(request)
+        response = self._namespace_client.list_tables(request)
         return response.tables if response.tables else []
 
     @override
@@ -309,7 +309,9 @@ class LanceNamespaceDBConnection(DBConnection):
             # Try to describe the table first to see if it exists
             try:
                 describe_request = DescribeTableRequest(id=table_id)
-                describe_response = self._ns.describe_table(describe_request)
+                describe_response = self._namespace_client.describe_table(
+                    describe_request
+                )
                 location = describe_response.location
                 namespace_storage_options = describe_response.storage_options
             except Exception:
@@ -323,7 +325,7 @@ class LanceNamespaceDBConnection(DBConnection):
                 location=None,
                 properties=self.storage_options if self.storage_options else None,
             )
-            declare_response = self._ns.declare_table(declare_request)
+            declare_response = self._namespace_client.declare_table(declare_request)
 
             if not declare_response.location:
                 raise ValueError(
@@ -353,7 +355,7 @@ class LanceNamespaceDBConnection(DBConnection):
         # Only create if namespace returned storage_options (not None)
         if storage_options_provider is None and namespace_storage_options is not None:
             storage_options_provider = LanceNamespaceStorageOptionsProvider(
-                namespace=self._ns,
+                namespace=self._namespace_client,
                 table_id=table_id,
             )
 
@@ -371,6 +373,7 @@ class LanceNamespaceDBConnection(DBConnection):
             storage_options=merged_storage_options,
             storage_options_provider=storage_options_provider,
             location=location,
+            namespace_client=self._namespace_client,
         )
 
         return tbl
@@ -389,7 +392,7 @@ class LanceNamespaceDBConnection(DBConnection):
             namespace = []
         table_id = namespace + [name]
         request = DescribeTableRequest(id=table_id)
-        response = self._ns.describe_table(request)
+        response = self._namespace_client.describe_table(request)
 
         # Merge storage options: self.storage_options < user options < namespace options
         merged_storage_options = dict(self.storage_options)
@@ -402,10 +405,14 @@ class LanceNamespaceDBConnection(DBConnection):
         # Only create if namespace returned storage_options (not None)
         if storage_options_provider is None and response.storage_options is not None:
             storage_options_provider = LanceNamespaceStorageOptionsProvider(
-                namespace=self._ns,
+                namespace=self._namespace_client,
                 table_id=table_id,
             )
 
+        # Pass managed_versioning to avoid redundant describe_table call in Rust.
+        # Convert None to False since we already have the answer from describe_table.
+        managed_versioning = response.managed_versioning is True
+
         return self._lance_table_from_uri(
             name,
             response.location,
@@ -413,6 +420,8 @@ class LanceNamespaceDBConnection(DBConnection):
             storage_options=merged_storage_options,
             storage_options_provider=storage_options_provider,
             index_cache_size=index_cache_size,
+            namespace_client=self._namespace_client,
+            managed_versioning=managed_versioning,
         )
 
     @override
@@ -422,7 +431,7 @@ class LanceNamespaceDBConnection(DBConnection):
             namespace = []
         table_id = namespace + [name]
         request = DropTableRequest(id=table_id)
-        self._ns.drop_table(request)
+        self._namespace_client.drop_table(request)
 
     @override
     def rename_table(
@@ -484,7 +493,7 @@ class LanceNamespaceDBConnection(DBConnection):
         request = ListNamespacesRequest(
             id=namespace, page_token=page_token, limit=limit
         )
-        response = self._ns.list_namespaces(request)
+        response = self._namespace_client.list_namespaces(request)
         return ListNamespacesResponse(
             namespaces=response.namespaces if response.namespaces else [],
             page_token=response.page_token,
@@ -520,7 +529,7 @@ class LanceNamespaceDBConnection(DBConnection):
             mode=_normalize_create_namespace_mode(mode),
             properties=properties,
         )
-        response = self._ns.create_namespace(request)
+        response = self._namespace_client.create_namespace(request)
         return CreateNamespaceResponse(
             properties=response.properties if hasattr(response, "properties") else None
         )
@@ -555,7 +564,7 @@ class LanceNamespaceDBConnection(DBConnection):
             mode=_normalize_drop_namespace_mode(mode),
             behavior=_normalize_drop_namespace_behavior(behavior),
         )
-        response = self._ns.drop_namespace(request)
+        response = self._namespace_client.drop_namespace(request)
         return DropNamespaceResponse(
             properties=(
                 response.properties if hasattr(response, "properties") else None
@@ -581,7 +590,7 @@ class LanceNamespaceDBConnection(DBConnection):
             Response containing the namespace properties.
         """
         request = DescribeNamespaceRequest(id=namespace)
-        response = self._ns.describe_namespace(request)
+        response = self._namespace_client.describe_namespace(request)
         return DescribeNamespaceResponse(
             properties=response.properties if hasattr(response, "properties") else None
         )
@@ -615,7 +624,7 @@ class LanceNamespaceDBConnection(DBConnection):
         if namespace is None:
             namespace = []
         request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
-        response = self._ns.list_tables(request)
+        response = self._namespace_client.list_tables(request)
         return ListTablesResponse(
             tables=response.tables if response.tables else [],
             page_token=response.page_token,
@@ -630,6 +639,8 @@ class LanceNamespaceDBConnection(DBConnection):
         storage_options: Optional[Dict[str, str]] = None,
         storage_options_provider: Optional[StorageOptionsProvider] = None,
         index_cache_size: Optional[int] = None,
+        namespace_client: Optional[Any] = None,
+        managed_versioning: Optional[bool] = None,
     ) -> LanceTable:
         # Open a table directly from a URI using the location parameter
         # Note: storage_options should already be merged by the caller
@@ -643,6 +654,8 @@ class LanceNamespaceDBConnection(DBConnection):
         )
 
         # Open the table using the temporary connection with the location parameter
+        # Pass namespace_client to enable managed versioning support
+        # Pass managed_versioning to avoid redundant describe_table call
         return LanceTable.open(
             temp_conn,
             name,
@@ -651,6 +664,8 @@ class LanceNamespaceDBConnection(DBConnection):
             storage_options_provider=storage_options_provider,
             index_cache_size=index_cache_size,
             location=table_uri,
+            namespace_client=namespace_client,
+            managed_versioning=managed_versioning,
         )
 
 
@@ -685,7 +700,7 @@ class AsyncLanceNamespaceDBConnection:
         session : Optional[Session]
             A session to use for this connection
         """
-        self._ns = namespace
+        self._namespace_client = namespace
         self.read_consistency_interval = read_consistency_interval
         self.storage_options = storage_options or {}
         self.session = session
@@ -713,7 +728,7 @@ class AsyncLanceNamespaceDBConnection:
         if namespace is None:
             namespace = []
         request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
-        response = self._ns.list_tables(request)
+        response = self._namespace_client.list_tables(request)
         return response.tables if response.tables else []
 
     async def create_table(
@@ -750,7 +765,9 @@ class AsyncLanceNamespaceDBConnection:
             # Try to describe the table first to see if it exists
             try:
                 describe_request = DescribeTableRequest(id=table_id)
-                describe_response = self._ns.describe_table(describe_request)
+                describe_response = self._namespace_client.describe_table(
+                    describe_request
+                )
                 location = describe_response.location
                 namespace_storage_options = describe_response.storage_options
             except Exception:
@@ -764,7 +781,7 @@ class AsyncLanceNamespaceDBConnection:
                 location=None,
                 properties=self.storage_options if self.storage_options else None,
             )
-            declare_response = self._ns.declare_table(declare_request)
+            declare_response = self._namespace_client.declare_table(declare_request)
 
             if not declare_response.location:
                 raise ValueError(
@@ -797,7 +814,7 @@ class AsyncLanceNamespaceDBConnection:
                 and namespace_storage_options is not None
             ):
                 provider = LanceNamespaceStorageOptionsProvider(
-                    namespace=self._ns,
+                    namespace=self._namespace_client,
                     table_id=table_id,
                 )
             else:
@@ -817,6 +834,7 @@ class AsyncLanceNamespaceDBConnection:
                 storage_options=merged_storage_options,
                 storage_options_provider=provider,
                 location=location,
+                namespace_client=self._namespace_client,
             )
 
         lance_table = await asyncio.to_thread(_create_table)
@@ -837,7 +855,7 @@ class AsyncLanceNamespaceDBConnection:
             namespace = []
         table_id = namespace + [name]
         request = DescribeTableRequest(id=table_id)
-        response = self._ns.describe_table(request)
+        response = self._namespace_client.describe_table(request)
 
         # Merge storage options: self.storage_options < user options < namespace options
         merged_storage_options = dict(self.storage_options)
@@ -849,10 +867,14 @@ class AsyncLanceNamespaceDBConnection:
         # Create a storage options provider if not provided by user
         if storage_options_provider is None and response.storage_options is not None:
             storage_options_provider = LanceNamespaceStorageOptionsProvider(
-                namespace=self._ns,
+                namespace=self._namespace_client,
                 table_id=table_id,
             )
 
+        # Capture managed_versioning from describe response.
+        # Convert None to False since we already have the answer from describe_table.
+        managed_versioning = response.managed_versioning is True
+
         # Open table in a thread
         def _open_table():
             temp_conn = LanceDBConnection(
@@ -870,6 +892,8 @@ class AsyncLanceNamespaceDBConnection:
                 storage_options_provider=storage_options_provider,
                 index_cache_size=index_cache_size,
                 location=response.location,
+                namespace_client=self._namespace_client,
+                managed_versioning=managed_versioning,
             )
 
         lance_table = await asyncio.to_thread(_open_table)
@@ -881,7 +905,7 @@ class AsyncLanceNamespaceDBConnection:
             namespace = []
         table_id = namespace + [name]
         request = DropTableRequest(id=table_id)
-        self._ns.drop_table(request)
+        self._namespace_client.drop_table(request)
 
     async def rename_table(
         self,
@@ -943,7 +967,7 @@ class AsyncLanceNamespaceDBConnection:
         request = ListNamespacesRequest(
             id=namespace, page_token=page_token, limit=limit
         )
-        response = self._ns.list_namespaces(request)
+        response = self._namespace_client.list_namespaces(request)
         return ListNamespacesResponse(
             namespaces=response.namespaces if response.namespaces else [],
             page_token=response.page_token,
@@ -978,7 +1002,7 @@ class AsyncLanceNamespaceDBConnection:
             mode=_normalize_create_namespace_mode(mode),
             properties=properties,
         )
-        response = self._ns.create_namespace(request)
+        response = self._namespace_client.create_namespace(request)
         return CreateNamespaceResponse(
             properties=response.properties if hasattr(response, "properties") else None
         )
@@ -1012,7 +1036,7 @@ class AsyncLanceNamespaceDBConnection:
             mode=_normalize_drop_namespace_mode(mode),
             behavior=_normalize_drop_namespace_behavior(behavior),
         )
-        response = self._ns.drop_namespace(request)
+        response = self._namespace_client.drop_namespace(request)
         return DropNamespaceResponse(
             properties=(
                 response.properties if hasattr(response, "properties") else None
@@ -1039,7 +1063,7 @@ class AsyncLanceNamespaceDBConnection:
             Response containing the namespace properties.
         """
         request = DescribeNamespaceRequest(id=namespace)
-        response = self._ns.describe_namespace(request)
+        response = self._namespace_client.describe_namespace(request)
         return DescribeNamespaceResponse(
             properties=response.properties if hasattr(response, "properties") else None
         )
@@ -1072,7 +1096,7 @@ class AsyncLanceNamespaceDBConnection:
         if namespace is None:
             namespace = []
         request = ListTablesRequest(id=namespace, page_token=page_token, limit=limit)
-        response = self._ns.list_tables(request)
+        response = self._namespace_client.list_tables(request)
         return ListTablesResponse(
             tables=response.tables if response.tables else [],
             page_token=response.page_token,

python/python/lancedb/query.py

@@ -606,6 +606,7 @@ class LanceQueryBuilder(ABC):
                 query,
                 ordering_field_name=ordering_field_name,
                 fts_columns=fts_columns,
+                fast_search=fast_search,
             )
 
         if isinstance(query, list):
@@ -1456,13 +1457,14 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
         query: str | FullTextQuery,
         ordering_field_name: Optional[str] = None,
         fts_columns: Optional[Union[str, List[str]]] = None,
+        fast_search: bool = None,
     ):
         super().__init__(table)
         self._query = query
         self._phrase_query = False
         self.ordering_field_name = ordering_field_name
         self._reranker = None
-        self._fast_search = None
+        self._fast_search = fast_search
         if isinstance(fts_columns, str):
             fts_columns = [fts_columns]
         self._fts_columns = fts_columns
@@ -2203,8 +2205,8 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
             self._vector_query.select(self._columns)
             self._fts_query.select(self._columns)
         if self._where:
-            self._vector_query.where(self._where, self._postfilter)
-            self._fts_query.where(self._where, self._postfilter)
+            self._vector_query.where(self._where, not self._postfilter)
+            self._fts_query.where(self._where, not self._postfilter)
         if self._with_row_id:
             self._vector_query.with_row_id(True)
             self._fts_query.with_row_id(True)

python/python/lancedb/remote/table.py

@@ -4,7 +4,7 @@
 from datetime import timedelta
 import logging
 from functools import cached_property
-from typing import Dict, Iterable, List, Optional, Union, Literal
+from typing import Any, Callable, Dict, Iterable, List, Optional, Union, Literal
 import warnings
 
 from lancedb._lancedb import (
@@ -35,6 +35,7 @@ import pyarrow as pa
 from lancedb.common import DATA, VEC, VECTOR_COLUMN_NAME
 from lancedb.merge import LanceMergeInsertBuilder
 from lancedb.embeddings import EmbeddingFunctionRegistry
+from lancedb.table import _normalize_progress
 
 from ..query import LanceVectorQueryBuilder, LanceQueryBuilder, LanceTakeQueryBuilder
 from ..table import AsyncTable, IndexStatistics, Query, Table, Tags
@@ -218,8 +219,6 @@ class RemoteTable(Table):
         train: bool = True,
     ):
         """Create an index on the table.
-        Currently, the only parameters that matter are
-        the metric and the vector column name.
 
         Parameters
         ----------
@@ -250,11 +249,6 @@ class RemoteTable(Table):
         >>> table.create_index("l2", "vector") # doctest: +SKIP
         """
 
-        if num_sub_vectors is not None:
-            logging.warning(
-                "num_sub_vectors is not supported on LanceDB cloud."
-                "This parameter will be tuned automatically."
-            )
         if accelerator is not None:
             logging.warning(
                 "GPU accelerator is not yet supported on LanceDB cloud."
@@ -315,6 +309,7 @@ class RemoteTable(Table):
         mode: str = "append",
         on_bad_vectors: str = "error",
         fill_value: float = 0.0,
+        progress: Optional[Union[bool, Callable, Any]] = None,
     ) -> AddResult:
         """Add more data to the [Table](Table). It has the same API signature as
         the OSS version.
@@ -337,17 +332,29 @@ class RemoteTable(Table):
             One of "error", "drop", "fill".
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
+        progress: bool, callable, or tqdm-like, optional
+            A callback or tqdm-compatible progress bar. See
+            :meth:`Table.add` for details.
 
         Returns
         -------
         AddResult
             An object containing the new version number of the table after adding data.
         """
-        return LOOP.run(
-            self._table.add(
-                data, mode=mode, on_bad_vectors=on_bad_vectors, fill_value=fill_value
+        progress, owns = _normalize_progress(progress)
+        try:
+            return LOOP.run(
+                self._table.add(
+                    data,
+                    mode=mode,
+                    on_bad_vectors=on_bad_vectors,
+                    fill_value=fill_value,
+                    progress=progress,
+                )
             )
-        )
+        finally:
+            if owns:
+                progress.close()
 
     def search(
         self,
@@ -647,6 +654,45 @@ class RemoteTable(Table):
     def drop_index(self, index_name: str):
         return LOOP.run(self._table.drop_index(index_name))
 
+    def prewarm_index(self, name: str) -> None:
+        """Prewarm an index in the table.
+
+        This is a hint to the database that the index will be accessed in the
+        future and should be loaded into memory if possible.  This can reduce
+        cold-start latency for subsequent queries.
+
+        This call initiates prewarming and returns once the request is accepted.
+        It is idempotent and safe to call from multiple clients concurrently.
+
+        Parameters
+        ----------
+        name: str
+            The name of the index to prewarm
+        """
+        return LOOP.run(self._table.prewarm_index(name))
+
+    def prewarm_data(self, columns: Optional[List[str]] = None) -> None:
+        """Prewarm data for the table.
+
+        This is a hint to the database that the given columns will be accessed
+        in the future and the database should prefetch the data if possible.
+        Currently only supported on remote tables.
+
+        This call initiates prewarming and returns once the request is accepted.
+        It is idempotent and safe to call from multiple clients concurrently.
+
+        This operation has a large upfront cost but can speed up future queries
+        that need to fetch the given columns.  Large columns such as embeddings
+        or binary data may not be practical to prewarm.  This feature is intended
+        for workloads that issue many queries against the same columns.
+
+        Parameters
+        ----------
+        columns: list of str, optional
+            The columns to prewarm. If None, all columns are prewarmed.
+        """
+        return LOOP.run(self._table.prewarm_data(columns))
+
     def wait_for_index(
         self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
     ):

python/python/lancedb/table.py

@@ -14,6 +14,7 @@ from functools import cached_property
 from typing import (
     TYPE_CHECKING,
     Any,
+    Callable,
     Dict,
     Iterable,
     List,
@@ -556,6 +557,21 @@ def _table_uri(base: str, table_name: str) -> str:
     return join_uri(base, f"{table_name}.lance")
 
 
+def _normalize_progress(progress):
+    """Normalize a ``progress`` parameter for :meth:`Table.add`.
+
+    Returns ``(progress_obj, owns)`` where *owns* is True when we created a
+    tqdm bar that the caller must close.
+    """
+    if progress is True:
+        from tqdm.auto import tqdm
+
+        return tqdm(unit=" rows"), True
+    if progress is False or progress is None:
+        return None, False
+    return progress, False
+
+
 class Table(ABC):
     """
     A Table is a collection of Records in a LanceDB Database.
@@ -974,6 +990,7 @@ class Table(ABC):
         mode: AddMode = "append",
         on_bad_vectors: OnBadVectorsType = "error",
         fill_value: float = 0.0,
+        progress: Optional[Union[bool, Callable, Any]] = None,
     ) -> AddResult:
         """Add more data to the [Table](Table).
 
@@ -995,6 +1012,29 @@ class Table(ABC):
             One of "error", "drop", "fill".
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
+        progress: bool, callable, or tqdm-like, optional
+            Progress reporting during the add operation. Can be:
+
+            - ``True`` to automatically create and display a tqdm progress
+              bar (requires ``tqdm`` to be installed)::
+
+                table.add(data, progress=True)
+
+            - A **callable** that receives a dict with keys ``output_rows``,
+              ``output_bytes``, ``total_rows``, ``elapsed_seconds``,
+              ``active_tasks``, ``total_tasks``, and ``done``::
+
+                def on_progress(p):
+                    print(f"{p['output_rows']}/{p['total_rows']} rows, "
+                          f"{p['active_tasks']}/{p['total_tasks']} workers")
+                table.add(data, progress=on_progress)
+
+            - A **tqdm-compatible** progress bar whose ``total`` and
+              ``update()`` will be called automatically. The postfix shows
+              write throughput (MB/s) and active worker count::
+
+                with tqdm() as pbar:
+                    table.add(data, progress=pbar)
 
         Returns
         -------
@@ -1331,7 +1371,7 @@ class Table(ABC):
         1  2  [3.0, 4.0]
         2  3  [5.0, 6.0]
         >>> table.delete("x = 2")
-        DeleteResult(version=2)
+        DeleteResult(num_deleted_rows=1, version=2)
         >>> table.to_pandas()
            x      vector
         0  1  [1.0, 2.0]
@@ -1345,7 +1385,7 @@ class Table(ABC):
         >>> to_remove
         '1, 5'
         >>> table.delete(f"x IN ({to_remove})")
-        DeleteResult(version=3)
+        DeleteResult(num_deleted_rows=1, version=3)
         >>> table.to_pandas()
            x      vector
         0  3  [5.0, 6.0]
@@ -1506,22 +1546,17 @@ class Table(ABC):
             in-progress operation (e.g. appending new data) and these files will not
             be deleted unless they are at least 7 days old. If delete_unverified is True
             then these files will be deleted regardless of their age.
+
+            .. warning::
+
+                This should only be set to True if you can guarantee that no other
+                process is currently working on this dataset. Otherwise the dataset
+                could be put into a corrupted state.
+
         retrain: bool, default False
             This parameter is no longer used and is deprecated.
 
-        Experimental API
-        ----------------
-
-        The optimization process is undergoing active development and may change.
-        Our goal with these changes is to improve the performance of optimization and
-        reduce the complexity.
-
-        That being said, it is essential today to run optimize if you want the best
-        performance.  It should be stable and safe to use in production, but it our
-        hope that the API may be simplified (or not even need to be called) in the
-        future.
-
-        The frequency an application shoudl call optimize is based on the frequency of
+        The frequency an application should call optimize is based on the frequency of
         data modifications.  If data is frequently added, deleted, or updated then
         optimize should be run frequently.  A good rule of thumb is to run optimize if
         you have added or modified 100,000 or more records or run more than 20 data
@@ -1746,6 +1781,8 @@ class LanceTable(Table):
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
         location: Optional[str] = None,
+        namespace_client: Optional[Any] = None,
+        managed_versioning: Optional[bool] = None,
         _async: AsyncTable = None,
     ):
         if namespace is None:
@@ -1753,6 +1790,7 @@ class LanceTable(Table):
         self._conn = connection
         self._namespace = namespace
         self._location = location  # Store location for use in _dataset_path
+        self._namespace_client = namespace_client
         if _async is not None:
             self._table = _async
         else:
@@ -1764,6 +1802,8 @@ class LanceTable(Table):
                     storage_options_provider=storage_options_provider,
                     index_cache_size=index_cache_size,
                     location=location,
+                    namespace_client=namespace_client,
+                    managed_versioning=managed_versioning,
                 )
             )
 
@@ -1806,6 +1846,8 @@ class LanceTable(Table):
         storage_options_provider: Optional["StorageOptionsProvider"] = None,
         index_cache_size: Optional[int] = None,
         location: Optional[str] = None,
+        namespace_client: Optional[Any] = None,
+        managed_versioning: Optional[bool] = None,
     ):
         if namespace is None:
             namespace = []
@@ -1817,6 +1859,8 @@ class LanceTable(Table):
             storage_options_provider=storage_options_provider,
             index_cache_size=index_cache_size,
             location=location,
+            namespace_client=namespace_client,
+            managed_versioning=managed_versioning,
         )
 
         # check the dataset exists
@@ -1848,6 +1892,16 @@ class LanceTable(Table):
                 "Please install with `pip install pylance`."
             )
 
+        if self._namespace_client is not None:
+            table_id = self._namespace + [self.name]
+            return lance.dataset(
+                version=self.version,
+                storage_options=self._conn.storage_options,
+                namespace=self._namespace_client,
+                table_id=table_id,
+                **kwargs,
+            )
+
         return lance.dataset(
             self._dataset_path,
             version=self.version,
@@ -2200,12 +2254,18 @@ class LanceTable(Table):
 
     def prewarm_index(self, name: str) -> None:
         """
-        Prewarms an index in the table
+        Prewarm an index in the table.
 
-        This loads the entire index into memory
+        This is a hint to the database that the index will be accessed in the
+        future and should be loaded into memory if possible.  This can reduce
+        cold-start latency for subsequent queries.
 
-        If the index does not fit into the available cache this call
-        may be wasteful
+        This call initiates prewarming and returns once the request is accepted.
+        It is idempotent and safe to call from multiple clients concurrently.
+
+        It is generally wasteful to call this if the index does not fit into the
+        available cache.  Not all index types support prewarming; unsupported
+        indices will silently ignore the request.
 
         Parameters
         ----------
@@ -2214,6 +2274,29 @@ class LanceTable(Table):
         """
         return LOOP.run(self._table.prewarm_index(name))
 
+    def prewarm_data(self, columns: Optional[List[str]] = None) -> None:
+        """
+        Prewarm data for the table.
+
+        This is a hint to the database that the given columns will be accessed
+        in the future and the database should prefetch the data if possible.
+        Currently only supported on remote tables.
+
+        This call initiates prewarming and returns once the request is accepted.
+        It is idempotent and safe to call from multiple clients concurrently.
+
+        This operation has a large upfront cost but can speed up future queries
+        that need to fetch the given columns.  Large columns such as embeddings
+        or binary data may not be practical to prewarm.  This feature is intended
+        for workloads that issue many queries against the same columns.
+
+        Parameters
+        ----------
+        columns: list of str, optional
+            The columns to prewarm. If None, all columns are prewarmed.
+        """
+        return LOOP.run(self._table.prewarm_data(columns))
+
     def wait_for_index(
         self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
     ) -> None:
@@ -2449,6 +2532,7 @@ class LanceTable(Table):
         mode: AddMode = "append",
         on_bad_vectors: OnBadVectorsType = "error",
         fill_value: float = 0.0,
+        progress: Optional[Union[bool, Callable, Any]] = None,
     ) -> AddResult:
         """Add data to the table.
         If vector columns are missing and the table
@@ -2467,17 +2551,29 @@ class LanceTable(Table):
             One of "error", "drop", "fill", "null".
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
+        progress: bool, callable, or tqdm-like, optional
+            A callback or tqdm-compatible progress bar. See
+            :meth:`Table.add` for details.
 
         Returns
         -------
         int
             The number of vectors in the table.
         """
-        return LOOP.run(
-            self._table.add(
-                data, mode=mode, on_bad_vectors=on_bad_vectors, fill_value=fill_value
+        progress, owns = _normalize_progress(progress)
+        try:
+            return LOOP.run(
+                self._table.add(
+                    data,
+                    mode=mode,
+                    on_bad_vectors=on_bad_vectors,
+                    fill_value=fill_value,
+                    progress=progress,
+                )
             )
-        )
+        finally:
+            if owns:
+                progress.close()
 
     def merge(
         self,
@@ -2713,6 +2809,7 @@ class LanceTable(Table):
         data_storage_version: Optional[str] = None,
         enable_v2_manifest_paths: Optional[bool] = None,
         location: Optional[str] = None,
+        namespace_client: Optional[Any] = None,
     ):
         """
         Create a new table.
@@ -2773,6 +2870,7 @@ class LanceTable(Table):
         self._conn = db
         self._namespace = namespace
         self._location = location
+        self._namespace_client = namespace_client
 
         if data_storage_version is not None:
             warnings.warn(
@@ -2997,22 +3095,17 @@ class LanceTable(Table):
             in-progress operation (e.g. appending new data) and these files will not
             be deleted unless they are at least 7 days old. If delete_unverified is True
             then these files will be deleted regardless of their age.
+
+            .. warning::
+
+                This should only be set to True if you can guarantee that no other
+                process is currently working on this dataset. Otherwise the dataset
+                could be put into a corrupted state.
+
         retrain: bool, default False
             This parameter is no longer used and is deprecated.
 
-        Experimental API
-        ----------------
-
-        The optimization process is undergoing active development and may change.
-        Our goal with these changes is to improve the performance of optimization and
-        reduce the complexity.
-
-        That being said, it is essential today to run optimize if you want the best
-        performance.  It should be stable and safe to use in production, but it our
-        hope that the API may be simplified (or not even need to be called) in the
-        future.
-
-        The frequency an application shoudl call optimize is based on the frequency of
+        The frequency an application should call optimize is based on the frequency of
         data modifications.  If data is frequently added, deleted, or updated then
         optimize should be run frequently.  A good rule of thumb is to run optimize if
         you have added or modified 100,000 or more records or run more than 20 data
@@ -3613,19 +3706,47 @@ class AsyncTable:
         """
         Prewarm an index in the table.
 
+        This is a hint to the database that the index will be accessed in the
+        future and should be loaded into memory if possible.  This can reduce
+        cold-start latency for subsequent queries.
+
+        This call initiates prewarming and returns once the request is accepted.
+        It is idempotent and safe to call from multiple clients concurrently.
+
+        It is generally wasteful to call this if the index does not fit into the
+        available cache.  Not all index types support prewarming; unsupported
+        indices will silently ignore the request.
+
         Parameters
         ----------
         name: str
             The name of the index to prewarm
-
-        Notes
-        -----
-        This will load the index into memory.  This may reduce the cold-start time for
-        future queries.  If the index does not fit in the cache then this call may be
-        wasteful.
         """
         await self._inner.prewarm_index(name)
 
+    async def prewarm_data(self, columns: Optional[List[str]] = None) -> None:
+        """
+        Prewarm data for the table.
+
+        This is a hint to the database that the given columns will be accessed
+        in the future and the database should prefetch the data if possible.
+        Currently only supported on remote tables.
+
+        This call initiates prewarming and returns once the request is accepted.
+        It is idempotent and safe to call from multiple clients concurrently.
+
+        This operation has a large upfront cost but can speed up future queries
+        that need to fetch the given columns.  Large columns such as embeddings
+        or binary data may not be practical to prewarm.  This feature is intended
+        for workloads that issue many queries against the same columns.
+
+        Parameters
+        ----------
+        columns: list of str, optional
+            The columns to prewarm. If None, all columns are prewarmed.
+        """
+        await self._inner.prewarm_data(columns)
+
     async def wait_for_index(
         self, index_names: Iterable[str], timeout: timedelta = timedelta(seconds=300)
     ) -> None:
@@ -3701,6 +3822,7 @@ class AsyncTable:
         mode: Optional[Literal["append", "overwrite"]] = "append",
         on_bad_vectors: Optional[OnBadVectorsType] = None,
         fill_value: Optional[float] = None,
+        progress: Optional[Union[bool, Callable, Any]] = None,
     ) -> AddResult:
         """Add more data to the [Table](Table).
 
@@ -3722,6 +3844,9 @@ class AsyncTable:
             One of "error", "drop", "fill", "null".
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
+        progress: callable or tqdm-like, optional
+            A callback or tqdm-compatible progress bar. See
+            :meth:`Table.add` for details.
 
         """
         schema = await self.schema()
@@ -3745,8 +3870,9 @@ class AsyncTable:
             )
         _register_optional_converters()
         data = to_scannable(data)
+        progress, owns = _normalize_progress(progress)
         try:
-            return await self._inner.add(data, mode or "append")
+            return await self._inner.add(data, mode or "append", progress=progress)
         except RuntimeError as e:
             if "Cast error" in str(e):
                 raise ValueError(e)
@@ -3754,6 +3880,9 @@ class AsyncTable:
                 raise ValueError(e)
             else:
                 raise
+        finally:
+            if owns:
+                progress.close()
 
     def merge_insert(self, on: Union[str, Iterable[str]]) -> LanceMergeInsertBuilder:
         """
@@ -4215,7 +4344,7 @@ class AsyncTable:
         1  2  [3.0, 4.0]
         2  3  [5.0, 6.0]
         >>> table.delete("x = 2")
-        DeleteResult(version=2)
+        DeleteResult(num_deleted_rows=1, version=2)
         >>> table.to_pandas()
            x      vector
         0  1  [1.0, 2.0]
@@ -4229,7 +4358,7 @@ class AsyncTable:
         >>> to_remove
         '1, 5'
         >>> table.delete(f"x IN ({to_remove})")
-        DeleteResult(version=3)
+        DeleteResult(num_deleted_rows=1, version=3)
         >>> table.to_pandas()
            x      vector
         0  3  [5.0, 6.0]
@@ -4552,22 +4681,17 @@ class AsyncTable:
             in-progress operation (e.g. appending new data) and these files will not
             be deleted unless they are at least 7 days old. If delete_unverified is True
             then these files will be deleted regardless of their age.
+
+            .. warning::
+
+                This should only be set to True if you can guarantee that no other
+                process is currently working on this dataset. Otherwise the dataset
+                could be put into a corrupted state.
+
         retrain: bool, default False
             This parameter is no longer used and is deprecated.
 
-        Experimental API
-        ----------------
-
-        The optimization process is undergoing active development and may change.
-        Our goal with these changes is to improve the performance of optimization and
-        reduce the complexity.
-
-        That being said, it is essential today to run optimize if you want the best
-        performance.  It should be stable and safe to use in production, but it our
-        hope that the API may be simplified (or not even need to be called) in the
-        future.
-
-        The frequency an application shoudl call optimize is based on the frequency of
+        The frequency an application should call optimize is based on the frequency of
         data modifications.  If data is frequently added, deleted, or updated then
         optimize should be run frequently.  A good rule of thumb is to run optimize if
         you have added or modified 100,000 or more records or run more than 20 data
@@ -4688,7 +4812,16 @@ class IndexStatistics:
     num_indexed_rows: int
     num_unindexed_rows: int
     index_type: Literal[
-        "IVF_PQ", "IVF_HNSW_PQ", "IVF_HNSW_SQ", "FTS", "BTREE", "BITMAP", "LABEL_LIST"
+        "IVF_FLAT",
+        "IVF_SQ",
+        "IVF_PQ",
+        "IVF_RQ",
+        "IVF_HNSW_SQ",
+        "IVF_HNSW_PQ",
+        "FTS",
+        "BTREE",
+        "BITMAP",
+        "LABEL_LIST",
     ]
     distance_type: Optional[Literal["l2", "cosine", "dot"]] = None
     num_indices: Optional[int] = None

python/python/lancedb/util.py

@@ -324,6 +324,16 @@ def _(value: list):
     return "[" + ", ".join(map(value_to_sql, value)) + "]"
 
 
+@value_to_sql.register(dict)
+def _(value: dict):
+    # https://datafusion.apache.org/user-guide/sql/scalar_functions.html#named-struct
+    return (
+        "named_struct("
+        + ", ".join(f"'{k}', {value_to_sql(v)}" for k, v in value.items())
+        + ")"
+    )
+
+
 @value_to_sql.register(np.ndarray)
 def _(value: np.ndarray):
     return value_to_sql(value.tolist())

python/python/tests/test_fts.py

@@ -27,6 +27,7 @@ from lancedb.query import (
     PhraseQuery,
     BooleanQuery,
     Occur,
+    LanceFtsQueryBuilder,
 )
 import numpy as np
 import pyarrow as pa
@@ -920,6 +921,10 @@ def test_fts_fast_search(table):
     assert query.limit == 5
     assert query.columns == ["text"]
 
+    # fast_search should be enabled by keyword argument too
+    query = LanceFtsQueryBuilder(table, "xyz", fast_search=True).to_query_object()
+    assert query.fast_search is True
+
     # Verify it executes without error and skips unindexed data
     results = table.search("xyz", query_type="fts").fast_search().limit(5).to_list()
     assert len(results) == 0

python/python/tests/test_hybrid_query.py

@@ -177,6 +177,60 @@ async def test_analyze_plan(table: AsyncTable):
     assert "metrics=" in res
 
 
+@pytest.fixture
+def table_with_id(tmpdir_factory) -> Table:
+    tmp_path = str(tmpdir_factory.mktemp("data"))
+    db = lancedb.connect(tmp_path)
+    data = pa.table(
+        {
+            "id": pa.array([1, 2, 3, 4], type=pa.int64()),
+            "text": pa.array(["a", "b", "cat", "dog"]),
+            "vector": pa.array(
+                [[0.1, 0.1], [2, 2], [-0.1, -0.1], [0.5, -0.5]],
+                type=pa.list_(pa.float32(), list_size=2),
+            ),
+        }
+    )
+    table = db.create_table("test_with_id", data)
+    table.create_fts_index("text", with_position=False, use_tantivy=False)
+    return table
+
+
+def test_hybrid_prefilter_explain_plan(table_with_id: Table):
+    """
+    Verify that the prefilter logic is not inverted in LanceHybridQueryBuilder.
+    """
+    plan_prefilter = (
+        table_with_id.search(query_type="hybrid")
+        .vector([0.0, 0.0])
+        .text("dog")
+        .where("id = 1", prefilter=True)
+        .limit(2)
+        .explain_plan(verbose=True)
+    )
+
+    plan_postfilter = (
+        table_with_id.search(query_type="hybrid")
+        .vector([0.0, 0.0])
+        .text("dog")
+        .where("id = 1", prefilter=False)
+        .limit(2)
+        .explain_plan(verbose=True)
+    )
+
+    # prefilter=True: filter is pushed into the LanceRead scan.
+    # The FTS sub-plan exposes this as "full_filter=id = Int64(1)" inside LanceRead.
+    assert "full_filter=id = Int64(1)" in plan_prefilter, (
+        f"Should push the filter into the scan.\nPlan:\n{plan_prefilter}"
+    )
+
+    # prefilter=False: filter is applied as a separate FilterExec after the search.
+    # The filter must NOT be embedded in the scan.
+    assert "full_filter=id = Int64(1)" not in plan_postfilter, (
+        f"Should NOT push the filter into the scan.\nPlan:\n{plan_postfilter}"
+    )
+
+
 def test_normalize_scores():
     cases = [
         (pa.array([0.1, 0.4]), pa.array([0.0, 1.0])),

python/python/tests/test_index.py

@@ -3,6 +3,7 @@
 
 from datetime import timedelta
 import random
+from typing import get_args, get_type_hints
 
 import pyarrow as pa
 import pytest
@@ -22,6 +23,7 @@ from lancedb.index import (
     HnswSq,
     FTS,
 )
+from lancedb.table import IndexStatistics
 
 
 @pytest_asyncio.fixture
@@ -283,3 +285,23 @@ async def test_create_index_with_binary_vectors(binary_table: AsyncTable):
     for v in range(256):
         res = await binary_table.query().nearest_to([v] * 128).to_arrow()
         assert res["id"][0].as_py() == v
+
+
+def test_index_statistics_index_type_lists_all_supported_values():
+    expected_index_types = {
+        "IVF_FLAT",
+        "IVF_SQ",
+        "IVF_PQ",
+        "IVF_RQ",
+        "IVF_HNSW_SQ",
+        "IVF_HNSW_PQ",
+        "FTS",
+        "BTREE",
+        "BITMAP",
+        "LABEL_LIST",
+    }
+
+    assert (
+        set(get_args(get_type_hints(IndexStatistics)["index_type"]))
+        == expected_index_types
+    )

python/python/tests/test_namespace_integration.py

@@ -147,7 +147,12 @@ class TrackingNamespace(LanceNamespace):
         This simulates a credential rotation system where each call returns
         new credentials that expire after credential_expires_in_seconds.
         """
-        modified = copy.deepcopy(storage_options) if storage_options else {}
+        # Start from base storage options (endpoint, region, allow_http, etc.)
+        # because DirectoryNamespace returns None for storage_options from
+        # describe_table/declare_table when no credential vendor is configured.
+        modified = copy.deepcopy(self.base_storage_options)
+        if storage_options:
+            modified.update(storage_options)
 
         # Increment credentials to simulate rotation
         modified["aws_access_key_id"] = f"AKID_{count}"

python/python/tests/test_table.py

@@ -326,6 +326,24 @@ def test_add_struct(mem_db: DBConnection):
     table = mem_db.create_table("test2", schema=schema)
     table.add(data)
 
+    struct_type = pa.struct(
+        [
+            ("b", pa.int64()),
+            ("a", pa.int64()),
+        ]
+    )
+    expected = pa.table(
+        {
+            "s_list": [
+                [
+                    pa.scalar({"b": 1, "a": 2}, type=struct_type),
+                    pa.scalar({"b": 4, "a": None}, type=struct_type),
+                ]
+            ],
+        }
+    )
+    assert table.to_arrow() == expected
+
 
 def test_add_subschema(mem_db: DBConnection):
     schema = pa.schema(
@@ -509,6 +527,102 @@ async def test_add_async(mem_db_async: AsyncConnection):
     assert await table.count_rows() == 3
 
 
+def test_add_progress_callback(mem_db: DBConnection):
+    table = mem_db.create_table(
+        "test",
+        data=[{"id": 1}, {"id": 2}],
+    )
+
+    updates = []
+    table.add([{"id": 3}, {"id": 4}], progress=lambda p: updates.append(dict(p)))
+
+    assert len(table) == 4
+    # The done callback always fires, so we should always get at least one.
+    assert len(updates) >= 1, "expected at least one progress callback"
+    for p in updates:
+        assert "output_rows" in p
+        assert "output_bytes" in p
+        assert "total_rows" in p
+        assert "elapsed_seconds" in p
+        assert "active_tasks" in p
+        assert "total_tasks" in p
+        assert "done" in p
+    # The last callback should have done=True.
+    assert updates[-1]["done"] is True
+
+
+def test_add_progress_tqdm_like(mem_db: DBConnection):
+    """Test that a tqdm-like object gets total set and update() called."""
+
+    class FakeBar:
+        def __init__(self):
+            self.total = None
+            self.n = 0
+            self.postfix = None
+
+        def update(self, n):
+            self.n += n
+
+        def set_postfix_str(self, s):
+            self.postfix = s
+
+        def refresh(self):
+            pass
+
+    table = mem_db.create_table(
+        "test",
+        data=[{"id": 1}, {"id": 2}],
+    )
+
+    bar = FakeBar()
+    table.add([{"id": 3}, {"id": 4}], progress=bar)
+
+    assert len(table) == 4
+    # Postfix should contain throughput and worker count
+    if bar.postfix is not None:
+        assert "MB/s" in bar.postfix
+        assert "workers" in bar.postfix
+
+
+def test_add_progress_bool(mem_db: DBConnection):
+    """Test that progress=True creates and closes a tqdm bar automatically."""
+    table = mem_db.create_table(
+        "test",
+        data=[{"id": 1}, {"id": 2}],
+    )
+
+    table.add([{"id": 3}, {"id": 4}], progress=True)
+    assert len(table) == 4
+
+    # progress=False should be the same as None
+    table.add([{"id": 5}], progress=False)
+    assert len(table) == 5
+
+
+@pytest.mark.asyncio
+async def test_add_progress_callback_async(mem_db_async: AsyncConnection):
+    """Progress callbacks work through the async path too."""
+    table = await mem_db_async.create_table("test", data=[{"id": 1}, {"id": 2}])
+
+    updates = []
+    await table.add([{"id": 3}, {"id": 4}], progress=lambda p: updates.append(dict(p)))
+
+    assert await table.count_rows() == 4
+    assert len(updates) >= 1
+    assert updates[-1]["done"] is True
+
+
+def test_add_progress_callback_error(mem_db: DBConnection):
+    """A failing callback must not prevent the write from succeeding."""
+    table = mem_db.create_table("test", data=[{"id": 1}, {"id": 2}])
+
+    def bad_callback(p):
+        raise RuntimeError("boom")
+
+    table.add([{"id": 3}, {"id": 4}], progress=bad_callback)
+    assert len(table) == 4
+
+
 def test_polars(mem_db: DBConnection):
     data = {
         "vector": [[3.1, 4.1], [5.9, 26.5]],

python/python/tests/test_util.py

@@ -121,6 +121,32 @@ def test_value_to_sql_string(tmp_path):
         assert table.to_pandas().query("search == @value")["replace"].item() == value
 
 
+def test_value_to_sql_dict():
+    # Simple flat struct
+    assert value_to_sql({"a": 1, "b": "hello"}) == "named_struct('a', 1, 'b', 'hello')"
+
+    # Nested struct
+    assert (
+        value_to_sql({"outer": {"inner": 1}})
+        == "named_struct('outer', named_struct('inner', 1))"
+    )
+
+    # List inside struct
+    assert value_to_sql({"a": [1, 2]}) == "named_struct('a', [1, 2])"
+
+    # Mixed types
+    assert (
+        value_to_sql({"name": "test", "count": 42, "rate": 3.14, "active": True})
+        == "named_struct('name', 'test', 'count', 42, 'rate', 3.14, 'active', TRUE)"
+    )
+
+    # Null value inside struct
+    assert value_to_sql({"a": None}) == "named_struct('a', NULL)"
+
+    # Empty dict
+    assert value_to_sql({}) == "named_struct()"
+
+
 def test_append_vector_columns():
     registry = EmbeddingFunctionRegistry.get_instance()
     registry.register("test")(MockTextEmbeddingFunction)

python/src/arrow.rs

@@ -10,7 +10,7 @@ use arrow::{
 use futures::stream::StreamExt;
 use lancedb::arrow::SendableRecordBatchStream;
 use pyo3::{
-    exceptions::PyStopAsyncIteration, pyclass, pymethods, Bound, Py, PyAny, PyRef, PyResult, Python,
+    Bound, Py, PyAny, PyRef, PyResult, Python, exceptions::PyStopAsyncIteration, pyclass, pymethods,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 

python/src/connection.rs

@@ -9,15 +9,16 @@ use lancedb::{
     database::{CreateTableMode, Database, ReadConsistency},
 };
 use pyo3::{
+    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
     exceptions::{PyRuntimeError, PyValueError},
     pyclass, pyfunction, pymethods,
     types::{PyDict, PyDictMethods},
-    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::{
-    error::PythonErrorExt, storage_options::py_object_to_storage_options_provider, table::Table,
+    error::PythonErrorExt, namespace::extract_namespace_arc,
+    storage_options::py_object_to_storage_options_provider, table::Table,
 };
 
 #[pyclass]
@@ -182,7 +183,8 @@ impl Connection {
         })
     }
 
-    #[pyo3(signature = (name, namespace=vec![], storage_options = None, storage_options_provider=None, index_cache_size = None, location=None))]
+    #[allow(clippy::too_many_arguments)]
+    #[pyo3(signature = (name, namespace=vec![], storage_options = None, storage_options_provider=None, index_cache_size = None, location=None, namespace_client=None, managed_versioning=None))]
     pub fn open_table(
         self_: PyRef<'_, Self>,
         name: String,
@@ -191,11 +193,13 @@ impl Connection {
         storage_options_provider: Option<Py<PyAny>>,
         index_cache_size: Option<u32>,
         location: Option<String>,
+        namespace_client: Option<Py<PyAny>>,
+        managed_versioning: Option<bool>,
     ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
 
         let mut builder = inner.open_table(name);
-        builder = builder.namespace(namespace);
+        builder = builder.namespace(namespace.clone());
         if let Some(storage_options) = storage_options {
             builder = builder.storage_options(storage_options);
         }
@@ -209,6 +213,20 @@ impl Connection {
         if let Some(location) = location {
             builder = builder.location(location);
         }
+        // Extract namespace client from Python object if provided
+        let ns_client = if let Some(ns_obj) = namespace_client {
+            let py = self_.py();
+            Some(extract_namespace_arc(py, ns_obj)?)
+        } else {
+            None
+        };
+        if let Some(ns_client) = ns_client {
+            builder = builder.namespace_client(ns_client);
+        }
+        // Pass managed_versioning if provided to avoid redundant describe_table call
+        if let Some(enabled) = managed_versioning {
+            builder = builder.managed_versioning(enabled);
+        }
 
         future_into_py(self_.py(), async move {
             let table = builder.execute().await.infer_error()?;

python/src/error.rs

@@ -2,10 +2,10 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use pyo3::{
+    PyErr, PyResult, Python,
     exceptions::{PyIOError, PyNotImplementedError, PyOSError, PyRuntimeError, PyValueError},
     intern,
     types::{PyAnyMethods, PyNone},
-    PyErr, PyResult, Python,
 };
 
 use lancedb::error::Error as LanceError;

python/src/index.rs

@@ -3,17 +3,17 @@
 
 use lancedb::index::vector::{IvfFlatIndexBuilder, IvfRqIndexBuilder, IvfSqIndexBuilder};
 use lancedb::index::{
+    Index as LanceDbIndex,
     scalar::{BTreeIndexBuilder, FtsIndexBuilder},
     vector::{IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder},
-    Index as LanceDbIndex,
 };
-use pyo3::types::PyStringMethods;
 use pyo3::IntoPyObject;
+use pyo3::types::PyStringMethods;
 use pyo3::{
+    Bound, FromPyObject, PyAny, PyResult, Python,
     exceptions::{PyKeyError, PyValueError},
     intern, pyclass, pymethods,
     types::PyAnyMethods,
-    Bound, FromPyObject, PyAny, PyResult, Python,
 };
 
 use crate::util::parse_distance_type;
@@ -41,7 +41,12 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                 let inner_opts = FtsIndexBuilder::default()
                     .base_tokenizer(params.base_tokenizer)
                     .language(&params.language)
-                    .map_err(|_| PyValueError::new_err(format!("LanceDB does not support the requested language: '{}'", params.language)))?
+                    .map_err(|_| {
+                        PyValueError::new_err(format!(
+                            "LanceDB does not support the requested language: '{}'",
+                            params.language
+                        ))
+                    })?
                     .with_position(params.with_position)
                     .lower_case(params.lower_case)
                     .max_token_length(params.max_token_length)
@@ -52,7 +57,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     .ngram_max_length(params.ngram_max_length)
                     .ngram_prefix_only(params.prefix_only);
                 Ok(LanceDbIndex::FTS(inner_opts))
-            },
+            }
             "IvfFlat" => {
                 let params = source.extract::<IvfFlatParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -64,10 +69,11 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     ivf_flat_builder = ivf_flat_builder.num_partitions(num_partitions);
                 }
                 if let Some(target_partition_size) = params.target_partition_size {
-                    ivf_flat_builder = ivf_flat_builder.target_partition_size(target_partition_size);
+                    ivf_flat_builder =
+                        ivf_flat_builder.target_partition_size(target_partition_size);
                 }
                 Ok(LanceDbIndex::IvfFlat(ivf_flat_builder))
-            },
+            }
             "IvfPq" => {
                 let params = source.extract::<IvfPqParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -86,7 +92,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     ivf_pq_builder = ivf_pq_builder.num_sub_vectors(num_sub_vectors);
                 }
                 Ok(LanceDbIndex::IvfPq(ivf_pq_builder))
-            },
+            }
             "IvfSq" => {
                 let params = source.extract::<IvfSqParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -101,7 +107,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     ivf_sq_builder = ivf_sq_builder.target_partition_size(target_partition_size);
                 }
                 Ok(LanceDbIndex::IvfSq(ivf_sq_builder))
-            },
+            }
             "IvfRq" => {
                 let params = source.extract::<IvfRqParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -117,7 +123,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     ivf_rq_builder = ivf_rq_builder.target_partition_size(target_partition_size);
                 }
                 Ok(LanceDbIndex::IvfRq(ivf_rq_builder))
-            },
+            }
             "HnswPq" => {
                 let params = source.extract::<IvfHnswPqParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -138,7 +144,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     hnsw_pq_builder = hnsw_pq_builder.num_sub_vectors(num_sub_vectors);
                 }
                 Ok(LanceDbIndex::IvfHnswPq(hnsw_pq_builder))
-            },
+            }
             "HnswSq" => {
                 let params = source.extract::<IvfHnswSqParams>()?;
                 let distance_type = parse_distance_type(params.distance_type)?;
@@ -155,7 +161,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     hnsw_sq_builder = hnsw_sq_builder.target_partition_size(target_partition_size);
                 }
                 Ok(LanceDbIndex::IvfHnswSq(hnsw_sq_builder))
-            },
+            }
             not_supported => Err(PyValueError::new_err(format!(
                 "Invalid index type '{}'.  Must be one of BTree, Bitmap, LabelList, FTS, IvfPq, IvfSq, IvfHnswPq, or IvfHnswSq",
                 not_supported

python/src/lib.rs

@@ -2,14 +2,14 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use arrow::RecordBatchStream;
-use connection::{connect, Connection};
+use connection::{Connection, connect};
 use env_logger::Env;
 use index::IndexConfig;
 use permutation::{PyAsyncPermutationBuilder, PyPermutationReader};
 use pyo3::{
-    pymodule,
+    Bound, PyResult, Python, pymodule,
     types::{PyModule, PyModuleMethods},
-    wrap_pyfunction, Bound, PyResult, Python,
+    wrap_pyfunction,
 };
 use query::{FTSQuery, HybridQuery, Query, VectorQuery};
 use session::Session;
@@ -23,6 +23,7 @@ pub mod connection;
 pub mod error;
 pub mod header;
 pub mod index;
+pub mod namespace;
 pub mod permutation;
 pub mod query;
 pub mod session;

python/src/namespace.rs

@@ -0,0 +1,696 @@
+// SPDX-License-Identifier: Apache-2.0
+// SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+//! Namespace utilities for Python bindings
+
+use std::collections::HashMap;
+use std::sync::Arc;
+
+use async_trait::async_trait;
+use bytes::Bytes;
+use lance_namespace::LanceNamespace as LanceNamespaceTrait;
+use lance_namespace::models::*;
+use pyo3::prelude::*;
+use pyo3::types::PyDict;
+
+/// Wrapper that allows any Python object implementing LanceNamespace protocol
+/// to be used as a Rust LanceNamespace.
+///
+/// This is similar to PyLanceNamespace in lance's Python bindings - it wraps a Python
+/// object and calls back into Python when namespace methods are invoked.
+pub struct PyLanceNamespace {
+    py_namespace: Arc<Py<PyAny>>,
+    namespace_id: String,
+}
+
+impl PyLanceNamespace {
+    /// Create a new PyLanceNamespace wrapper around a Python namespace object.
+    pub fn new(_py: Python<'_>, py_namespace: &Bound<'_, PyAny>) -> PyResult<Self> {
+        let namespace_id = py_namespace
+            .call_method0("namespace_id")?
+            .extract::<String>()?;
+
+        Ok(Self {
+            py_namespace: Arc::new(py_namespace.clone().unbind()),
+            namespace_id,
+        })
+    }
+
+    /// Create an Arc<dyn LanceNamespace> from a Python namespace object.
+    pub fn create_arc(
+        py: Python<'_>,
+        py_namespace: &Bound<'_, PyAny>,
+    ) -> PyResult<Arc<dyn LanceNamespaceTrait>> {
+        let wrapper = Self::new(py, py_namespace)?;
+        Ok(Arc::new(wrapper))
+    }
+}
+
+impl std::fmt::Debug for PyLanceNamespace {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        write!(f, "PyLanceNamespace {{ id: {} }}", self.namespace_id)
+    }
+}
+
+/// Get or create the DictWithModelDump class in Python.
+/// This class acts like a dict but also has model_dump() method.
+/// This allows it to work with both:
+/// - depythonize (which expects a dict/Mapping)
+/// - Python code that calls .model_dump() (like DirectoryNamespace wrapper)
+fn get_dict_with_model_dump_class(py: Python<'_>) -> PyResult<Bound<'_, PyAny>> {
+    // Use a module-level cache via __builtins__
+    let builtins = py.import("builtins")?;
+    if builtins.hasattr("_DictWithModelDump")? {
+        return builtins.getattr("_DictWithModelDump");
+    }
+
+    // Create the class using exec
+    let locals = PyDict::new(py);
+    py.run(
+        c"class DictWithModelDump(dict):
+    def model_dump(self):
+        return dict(self)",
+        None,
+        Some(&locals),
+    )?;
+    let class = locals.get_item("DictWithModelDump")?.ok_or_else(|| {
+        pyo3::exceptions::PyRuntimeError::new_err("Failed to create DictWithModelDump class")
+    })?;
+
+    // Cache it
+    builtins.setattr("_DictWithModelDump", &class)?;
+    Ok(class)
+}
+
+/// Helper to call a Python namespace method with JSON serialization.
+/// For methods that take a request and return a response.
+/// Uses DictWithModelDump to pass a dict that also has model_dump() method,
+/// making it compatible with both depythonize and Python wrappers.
+async fn call_py_method<Req, Resp>(
+    py_namespace: Arc<Py<PyAny>>,
+    method_name: &'static str,
+    request: Req,
+) -> lance_core::Result<Resp>
+where
+    Req: serde::Serialize + Send + 'static,
+    Resp: serde::de::DeserializeOwned + Send + 'static,
+{
+    let request_json = serde_json::to_string(&request).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to serialize request for {}: {}",
+            method_name, e
+        ))
+    })?;
+
+    let response_json = tokio::task::spawn_blocking(move || {
+        Python::attach(|py| {
+            let json_module = py.import("json")?;
+            let request_dict = json_module.call_method1("loads", (&request_json,))?;
+
+            // Wrap dict in DictWithModelDump so it works with both depythonize and .model_dump()
+            let dict_class = get_dict_with_model_dump_class(py)?;
+            let request_arg = dict_class.call1((request_dict,))?;
+
+            // Call the Python method
+            let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
+
+            // Convert response to dict, then to JSON
+            // Pydantic models have model_dump() method
+            let result_dict = if result.bind(py).hasattr("model_dump")? {
+                result.call_method0(py, "model_dump")?
+            } else {
+                result
+            };
+            let response_json: String = json_module
+                .call_method1("dumps", (result_dict,))?
+                .extract()?;
+            Ok::<_, PyErr>(response_json)
+        })
+    })
+    .await
+    .map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
+    .map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))?;
+
+    serde_json::from_str(&response_json).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to deserialize response from {}: {}",
+            method_name, e
+        ))
+    })
+}
+
+/// Helper for methods that return () on success
+async fn call_py_method_unit<Req>(
+    py_namespace: Arc<Py<PyAny>>,
+    method_name: &'static str,
+    request: Req,
+) -> lance_core::Result<()>
+where
+    Req: serde::Serialize + Send + 'static,
+{
+    let request_json = serde_json::to_string(&request).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to serialize request for {}: {}",
+            method_name, e
+        ))
+    })?;
+
+    tokio::task::spawn_blocking(move || {
+        Python::attach(|py| {
+            let json_module = py.import("json")?;
+            let request_dict = json_module.call_method1("loads", (&request_json,))?;
+
+            // Wrap dict in DictWithModelDump
+            let dict_class = get_dict_with_model_dump_class(py)?;
+            let request_arg = dict_class.call1((request_dict,))?;
+
+            // Call the Python method
+            py_namespace.call_method1(py, method_name, (request_arg,))?;
+            Ok::<_, PyErr>(())
+        })
+    })
+    .await
+    .map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
+    .map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))
+}
+
+/// Helper for methods that return a primitive type
+async fn call_py_method_primitive<Req, Resp>(
+    py_namespace: Arc<Py<PyAny>>,
+    method_name: &'static str,
+    request: Req,
+) -> lance_core::Result<Resp>
+where
+    Req: serde::Serialize + Send + 'static,
+    Resp: for<'py> pyo3::FromPyObject<'py> + Send + 'static,
+{
+    let request_json = serde_json::to_string(&request).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to serialize request for {}: {}",
+            method_name, e
+        ))
+    })?;
+
+    tokio::task::spawn_blocking(move || {
+        Python::attach(|py| {
+            let json_module = py.import("json")?;
+            let request_dict = json_module.call_method1("loads", (&request_json,))?;
+
+            // Wrap dict in DictWithModelDump
+            let dict_class = get_dict_with_model_dump_class(py)?;
+            let request_arg = dict_class.call1((request_dict,))?;
+
+            // Call the Python method
+            let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
+            let value: Resp = result.extract(py)?;
+            Ok::<_, PyErr>(value)
+        })
+    })
+    .await
+    .map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
+    .map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))
+}
+
+/// Helper for methods that return Bytes
+async fn call_py_method_bytes<Req>(
+    py_namespace: Arc<Py<PyAny>>,
+    method_name: &'static str,
+    request: Req,
+) -> lance_core::Result<Bytes>
+where
+    Req: serde::Serialize + Send + 'static,
+{
+    let request_json = serde_json::to_string(&request).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to serialize request for {}: {}",
+            method_name, e
+        ))
+    })?;
+
+    tokio::task::spawn_blocking(move || {
+        Python::attach(|py| {
+            let json_module = py.import("json")?;
+            let request_dict = json_module.call_method1("loads", (&request_json,))?;
+
+            // Wrap dict in DictWithModelDump
+            let dict_class = get_dict_with_model_dump_class(py)?;
+            let request_arg = dict_class.call1((request_dict,))?;
+
+            // Call the Python method
+            let result = py_namespace.call_method1(py, method_name, (request_arg,))?;
+            let bytes_data: Vec<u8> = result.extract(py)?;
+            Ok::<_, PyErr>(Bytes::from(bytes_data))
+        })
+    })
+    .await
+    .map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
+    .map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))
+}
+
+/// Helper for methods that take request + data and return a response
+async fn call_py_method_with_data<Req, Resp>(
+    py_namespace: Arc<Py<PyAny>>,
+    method_name: &'static str,
+    request: Req,
+    data: Bytes,
+) -> lance_core::Result<Resp>
+where
+    Req: serde::Serialize + Send + 'static,
+    Resp: serde::de::DeserializeOwned + Send + 'static,
+{
+    let request_json = serde_json::to_string(&request).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to serialize request for {}: {}",
+            method_name, e
+        ))
+    })?;
+
+    let response_json = tokio::task::spawn_blocking(move || {
+        Python::attach(|py| {
+            let json_module = py.import("json")?;
+            let request_dict = json_module.call_method1("loads", (&request_json,))?;
+
+            // Wrap dict in DictWithModelDump
+            let dict_class = get_dict_with_model_dump_class(py)?;
+            let request_arg = dict_class.call1((request_dict,))?;
+
+            // Pass request and bytes to Python method
+            let py_bytes = pyo3::types::PyBytes::new(py, &data);
+            let result = py_namespace.call_method1(py, method_name, (request_arg, py_bytes))?;
+
+            // Convert response dict to JSON
+            let response_json: String = json_module.call_method1("dumps", (result,))?.extract()?;
+            Ok::<_, PyErr>(response_json)
+        })
+    })
+    .await
+    .map_err(|e| lance_core::Error::io(format!("Task join error for {}: {}", method_name, e)))?
+    .map_err(|e: PyErr| lance_core::Error::io(format!("Python error in {}: {}", method_name, e)))?;
+
+    serde_json::from_str(&response_json).map_err(|e| {
+        lance_core::Error::io(format!(
+            "Failed to deserialize response from {}: {}",
+            method_name, e
+        ))
+    })
+}
+
+#[async_trait]
+impl LanceNamespaceTrait for PyLanceNamespace {
+    fn namespace_id(&self) -> String {
+        self.namespace_id.clone()
+    }
+
+    async fn list_namespaces(
+        &self,
+        request: ListNamespacesRequest,
+    ) -> lance_core::Result<ListNamespacesResponse> {
+        call_py_method(self.py_namespace.clone(), "list_namespaces", request).await
+    }
+
+    async fn describe_namespace(
+        &self,
+        request: DescribeNamespaceRequest,
+    ) -> lance_core::Result<DescribeNamespaceResponse> {
+        call_py_method(self.py_namespace.clone(), "describe_namespace", request).await
+    }
+
+    async fn create_namespace(
+        &self,
+        request: CreateNamespaceRequest,
+    ) -> lance_core::Result<CreateNamespaceResponse> {
+        call_py_method(self.py_namespace.clone(), "create_namespace", request).await
+    }
+
+    async fn drop_namespace(
+        &self,
+        request: DropNamespaceRequest,
+    ) -> lance_core::Result<DropNamespaceResponse> {
+        call_py_method(self.py_namespace.clone(), "drop_namespace", request).await
+    }
+
+    async fn namespace_exists(&self, request: NamespaceExistsRequest) -> lance_core::Result<()> {
+        call_py_method_unit(self.py_namespace.clone(), "namespace_exists", request).await
+    }
+
+    async fn list_tables(
+        &self,
+        request: ListTablesRequest,
+    ) -> lance_core::Result<ListTablesResponse> {
+        call_py_method(self.py_namespace.clone(), "list_tables", request).await
+    }
+
+    async fn describe_table(
+        &self,
+        request: DescribeTableRequest,
+    ) -> lance_core::Result<DescribeTableResponse> {
+        call_py_method(self.py_namespace.clone(), "describe_table", request).await
+    }
+
+    async fn register_table(
+        &self,
+        request: RegisterTableRequest,
+    ) -> lance_core::Result<RegisterTableResponse> {
+        call_py_method(self.py_namespace.clone(), "register_table", request).await
+    }
+
+    async fn table_exists(&self, request: TableExistsRequest) -> lance_core::Result<()> {
+        call_py_method_unit(self.py_namespace.clone(), "table_exists", request).await
+    }
+
+    async fn drop_table(&self, request: DropTableRequest) -> lance_core::Result<DropTableResponse> {
+        call_py_method(self.py_namespace.clone(), "drop_table", request).await
+    }
+
+    async fn deregister_table(
+        &self,
+        request: DeregisterTableRequest,
+    ) -> lance_core::Result<DeregisterTableResponse> {
+        call_py_method(self.py_namespace.clone(), "deregister_table", request).await
+    }
+
+    async fn count_table_rows(&self, request: CountTableRowsRequest) -> lance_core::Result<i64> {
+        call_py_method_primitive(self.py_namespace.clone(), "count_table_rows", request).await
+    }
+
+    async fn create_table(
+        &self,
+        request: CreateTableRequest,
+        request_data: Bytes,
+    ) -> lance_core::Result<CreateTableResponse> {
+        call_py_method_with_data(
+            self.py_namespace.clone(),
+            "create_table",
+            request,
+            request_data,
+        )
+        .await
+    }
+
+    async fn declare_table(
+        &self,
+        request: DeclareTableRequest,
+    ) -> lance_core::Result<DeclareTableResponse> {
+        call_py_method(self.py_namespace.clone(), "declare_table", request).await
+    }
+
+    async fn insert_into_table(
+        &self,
+        request: InsertIntoTableRequest,
+        request_data: Bytes,
+    ) -> lance_core::Result<InsertIntoTableResponse> {
+        call_py_method_with_data(
+            self.py_namespace.clone(),
+            "insert_into_table",
+            request,
+            request_data,
+        )
+        .await
+    }
+
+    async fn merge_insert_into_table(
+        &self,
+        request: MergeInsertIntoTableRequest,
+        request_data: Bytes,
+    ) -> lance_core::Result<MergeInsertIntoTableResponse> {
+        call_py_method_with_data(
+            self.py_namespace.clone(),
+            "merge_insert_into_table",
+            request,
+            request_data,
+        )
+        .await
+    }
+
+    async fn update_table(
+        &self,
+        request: UpdateTableRequest,
+    ) -> lance_core::Result<UpdateTableResponse> {
+        call_py_method(self.py_namespace.clone(), "update_table", request).await
+    }
+
+    async fn delete_from_table(
+        &self,
+        request: DeleteFromTableRequest,
+    ) -> lance_core::Result<DeleteFromTableResponse> {
+        call_py_method(self.py_namespace.clone(), "delete_from_table", request).await
+    }
+
+    async fn query_table(&self, request: QueryTableRequest) -> lance_core::Result<Bytes> {
+        call_py_method_bytes(self.py_namespace.clone(), "query_table", request).await
+    }
+
+    async fn create_table_index(
+        &self,
+        request: CreateTableIndexRequest,
+    ) -> lance_core::Result<CreateTableIndexResponse> {
+        call_py_method(self.py_namespace.clone(), "create_table_index", request).await
+    }
+
+    async fn list_table_indices(
+        &self,
+        request: ListTableIndicesRequest,
+    ) -> lance_core::Result<ListTableIndicesResponse> {
+        call_py_method(self.py_namespace.clone(), "list_table_indices", request).await
+    }
+
+    async fn describe_table_index_stats(
+        &self,
+        request: DescribeTableIndexStatsRequest,
+    ) -> lance_core::Result<DescribeTableIndexStatsResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "describe_table_index_stats",
+            request,
+        )
+        .await
+    }
+
+    async fn describe_transaction(
+        &self,
+        request: DescribeTransactionRequest,
+    ) -> lance_core::Result<DescribeTransactionResponse> {
+        call_py_method(self.py_namespace.clone(), "describe_transaction", request).await
+    }
+
+    async fn alter_transaction(
+        &self,
+        request: AlterTransactionRequest,
+    ) -> lance_core::Result<AlterTransactionResponse> {
+        call_py_method(self.py_namespace.clone(), "alter_transaction", request).await
+    }
+
+    async fn create_table_scalar_index(
+        &self,
+        request: CreateTableIndexRequest,
+    ) -> lance_core::Result<CreateTableScalarIndexResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "create_table_scalar_index",
+            request,
+        )
+        .await
+    }
+
+    async fn drop_table_index(
+        &self,
+        request: DropTableIndexRequest,
+    ) -> lance_core::Result<DropTableIndexResponse> {
+        call_py_method(self.py_namespace.clone(), "drop_table_index", request).await
+    }
+
+    async fn list_all_tables(
+        &self,
+        request: ListTablesRequest,
+    ) -> lance_core::Result<ListTablesResponse> {
+        call_py_method(self.py_namespace.clone(), "list_all_tables", request).await
+    }
+
+    async fn restore_table(
+        &self,
+        request: RestoreTableRequest,
+    ) -> lance_core::Result<RestoreTableResponse> {
+        call_py_method(self.py_namespace.clone(), "restore_table", request).await
+    }
+
+    async fn rename_table(
+        &self,
+        request: RenameTableRequest,
+    ) -> lance_core::Result<RenameTableResponse> {
+        call_py_method(self.py_namespace.clone(), "rename_table", request).await
+    }
+
+    async fn list_table_versions(
+        &self,
+        request: ListTableVersionsRequest,
+    ) -> lance_core::Result<ListTableVersionsResponse> {
+        call_py_method(self.py_namespace.clone(), "list_table_versions", request).await
+    }
+
+    async fn create_table_version(
+        &self,
+        request: CreateTableVersionRequest,
+    ) -> lance_core::Result<CreateTableVersionResponse> {
+        call_py_method(self.py_namespace.clone(), "create_table_version", request).await
+    }
+
+    async fn describe_table_version(
+        &self,
+        request: DescribeTableVersionRequest,
+    ) -> lance_core::Result<DescribeTableVersionResponse> {
+        call_py_method(self.py_namespace.clone(), "describe_table_version", request).await
+    }
+
+    async fn batch_delete_table_versions(
+        &self,
+        request: BatchDeleteTableVersionsRequest,
+    ) -> lance_core::Result<BatchDeleteTableVersionsResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "batch_delete_table_versions",
+            request,
+        )
+        .await
+    }
+
+    async fn update_table_schema_metadata(
+        &self,
+        request: UpdateTableSchemaMetadataRequest,
+    ) -> lance_core::Result<UpdateTableSchemaMetadataResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "update_table_schema_metadata",
+            request,
+        )
+        .await
+    }
+
+    async fn get_table_stats(
+        &self,
+        request: GetTableStatsRequest,
+    ) -> lance_core::Result<GetTableStatsResponse> {
+        call_py_method(self.py_namespace.clone(), "get_table_stats", request).await
+    }
+
+    async fn explain_table_query_plan(
+        &self,
+        request: ExplainTableQueryPlanRequest,
+    ) -> lance_core::Result<String> {
+        call_py_method_primitive(
+            self.py_namespace.clone(),
+            "explain_table_query_plan",
+            request,
+        )
+        .await
+    }
+
+    async fn analyze_table_query_plan(
+        &self,
+        request: AnalyzeTableQueryPlanRequest,
+    ) -> lance_core::Result<String> {
+        call_py_method_primitive(
+            self.py_namespace.clone(),
+            "analyze_table_query_plan",
+            request,
+        )
+        .await
+    }
+
+    async fn alter_table_add_columns(
+        &self,
+        request: AlterTableAddColumnsRequest,
+    ) -> lance_core::Result<AlterTableAddColumnsResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "alter_table_add_columns",
+            request,
+        )
+        .await
+    }
+
+    async fn alter_table_alter_columns(
+        &self,
+        request: AlterTableAlterColumnsRequest,
+    ) -> lance_core::Result<AlterTableAlterColumnsResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "alter_table_alter_columns",
+            request,
+        )
+        .await
+    }
+
+    async fn alter_table_drop_columns(
+        &self,
+        request: AlterTableDropColumnsRequest,
+    ) -> lance_core::Result<AlterTableDropColumnsResponse> {
+        call_py_method(
+            self.py_namespace.clone(),
+            "alter_table_drop_columns",
+            request,
+        )
+        .await
+    }
+
+    async fn list_table_tags(
+        &self,
+        request: ListTableTagsRequest,
+    ) -> lance_core::Result<ListTableTagsResponse> {
+        call_py_method(self.py_namespace.clone(), "list_table_tags", request).await
+    }
+
+    async fn create_table_tag(
+        &self,
+        request: CreateTableTagRequest,
+    ) -> lance_core::Result<CreateTableTagResponse> {
+        call_py_method(self.py_namespace.clone(), "create_table_tag", request).await
+    }
+
+    async fn delete_table_tag(
+        &self,
+        request: DeleteTableTagRequest,
+    ) -> lance_core::Result<DeleteTableTagResponse> {
+        call_py_method(self.py_namespace.clone(), "delete_table_tag", request).await
+    }
+
+    async fn update_table_tag(
+        &self,
+        request: UpdateTableTagRequest,
+    ) -> lance_core::Result<UpdateTableTagResponse> {
+        call_py_method(self.py_namespace.clone(), "update_table_tag", request).await
+    }
+
+    async fn get_table_tag_version(
+        &self,
+        request: GetTableTagVersionRequest,
+    ) -> lance_core::Result<GetTableTagVersionResponse> {
+        call_py_method(self.py_namespace.clone(), "get_table_tag_version", request).await
+    }
+}
+
+/// Convert Python dict to HashMap<String, String>
+#[allow(dead_code)]
+fn dict_to_hashmap(dict: &Bound<'_, PyDict>) -> PyResult<HashMap<String, String>> {
+    let mut map = HashMap::new();
+    for (key, value) in dict.iter() {
+        let key_str: String = key.extract()?;
+        let value_str: String = value.extract()?;
+        map.insert(key_str, value_str);
+    }
+    Ok(map)
+}
+
+/// Extract an Arc<dyn LanceNamespace> from a Python namespace object.
+///
+/// This function wraps any Python namespace object with PyLanceNamespace.
+/// The PyLanceNamespace wrapper uses DictWithModelDump to pass requests,
+/// which works with both:
+/// - Native namespaces (DirectoryNamespace, RestNamespace) that use depythonize (expects dict)
+/// - Custom Python implementations that call .model_dump() on the request
+pub fn extract_namespace_arc(
+    py: Python<'_>,
+    ns: Py<PyAny>,
+) -> PyResult<Arc<dyn LanceNamespaceTrait>> {
+    let ns_ref = ns.bind(py);
+    PyLanceNamespace::create_arc(py, ns_ref)
+}

python/src/permutation.rs

@@ -16,10 +16,10 @@ use lancedb::{
     query::Select,
 };
 use pyo3::{
+    Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
     exceptions::PyRuntimeError,
     pyclass, pymethods,
     types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
-    Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 

python/src/query.rs

@@ -4,9 +4,9 @@
 use std::sync::Arc;
 use std::time::Duration;
 
-use arrow::array::make_array;
 use arrow::array::Array;
 use arrow::array::ArrayData;
+use arrow::array::make_array;
 use arrow::pyarrow::FromPyArrow;
 use arrow::pyarrow::IntoPyArrow;
 use arrow::pyarrow::ToPyArrow;
@@ -22,23 +22,23 @@ use lancedb::query::{
     VectorQuery as LanceDbVectorQuery,
 };
 use lancedb::table::AnyQuery;
-use pyo3::prelude::{PyAnyMethods, PyDictMethods};
-use pyo3::pyfunction;
-use pyo3::pymethods;
-use pyo3::types::PyList;
-use pyo3::types::{PyDict, PyString};
 use pyo3::Bound;
 use pyo3::IntoPyObject;
 use pyo3::PyAny;
 use pyo3::PyRef;
 use pyo3::PyResult;
 use pyo3::Python;
-use pyo3::{exceptions::PyRuntimeError, FromPyObject};
+use pyo3::prelude::{PyAnyMethods, PyDictMethods};
+use pyo3::pyfunction;
+use pyo3::pymethods;
+use pyo3::types::PyList;
+use pyo3::types::{PyDict, PyString};
+use pyo3::{FromPyObject, exceptions::PyRuntimeError};
+use pyo3::{PyErr, pyclass};
 use pyo3::{
     exceptions::{PyNotImplementedError, PyValueError},
     intern,
 };
-use pyo3::{pyclass, PyErr};
 use pyo3_async_runtimes::tokio::future_into_py;
 
 use crate::util::parse_distance_type;
@@ -316,6 +316,19 @@ impl<'py> IntoPyObject<'py> for PySelect {
             Select::All => Ok(py.None().into_bound(py).into_any()),
             Select::Columns(columns) => Ok(columns.into_pyobject(py)?.into_any()),
             Select::Dynamic(columns) => Ok(columns.into_pyobject(py)?.into_any()),
+            Select::Expr(pairs) => {
+                // Serialize DataFusion Expr -> SQL string so Python sees the same
+                // format as Select::Dynamic: a list of (name, sql_string) tuples.
+                let sql_pairs: PyResult<Vec<(String, String)>> = pairs
+                    .into_iter()
+                    .map(|(name, expr)| {
+                        lancedb::expr::expr_to_sql_string(&expr)
+                            .map(|sql| (name, sql))
+                            .map_err(|e| PyRuntimeError::new_err(e.to_string()))
+                    })
+                    .collect();
+                Ok(sql_pairs?.into_pyobject(py)?.into_any())
+            }
         }
     }
 }

python/src/session.rs

@@ -4,7 +4,7 @@
 use std::sync::Arc;
 
 use lancedb::{ObjectStoreRegistry, Session as LanceSession};
-use pyo3::{pyclass, pymethods, PyResult};
+use pyo3::{PyResult, pyclass, pymethods};
 
 /// A session for managing caches and object stores across LanceDB operations.
 ///

python/src/storage_options.rs

@@ -66,13 +66,10 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
                     .inner
                     .bind(py)
                     .call_method0("fetch_storage_options")
-                    .map_err(|e| lance_core::Error::IO {
-                        source: Box::new(std::io::Error::other(format!(
-                            "Failed to call fetch_storage_options: {}",
-                            e
-                        ))),
-                        location: snafu::location!(),
-                    })?;
+                    .map_err(|e| lance_core::Error::io_source(Box::new(std::io::Error::other(format!(
+                        "Failed to call fetch_storage_options: {}",
+                        e
+                    )))))?;
 
                 // If result is None, return None
                 if result.is_none() {
@@ -81,26 +78,19 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
 
                 // Extract the result dict - should be a flat Map<String, String>
                 let result_dict = result.downcast::<PyDict>().map_err(|_| {
-                    lance_core::Error::InvalidInput {
-                        source: "fetch_storage_options() must return None or a dict of string key-value pairs".into(),
-                        location: snafu::location!(),
-                    }
+                    lance_core::Error::invalid_input(
+                        "fetch_storage_options() must return a dict of string key-value pairs or None",
+                    )
                 })?;
 
                 // Convert all entries to HashMap<String, String>
                 let mut storage_options = HashMap::new();
                 for (key, value) in result_dict.iter() {
                     let key_str: String = key.extract().map_err(|e| {
-                        lance_core::Error::InvalidInput {
-                            source: format!("Storage option key must be a string: {}", e).into(),
-                            location: snafu::location!(),
-                        }
+                        lance_core::Error::invalid_input(format!("Storage option key must be a string: {}", e))
                     })?;
                     let value_str: String = value.extract().map_err(|e| {
-                        lance_core::Error::InvalidInput {
-                            source: format!("Storage option value must be a string: {}", e).into(),
-                            location: snafu::location!(),
-                        }
+                        lance_core::Error::invalid_input(format!("Storage option value must be a string: {}", e))
                     })?;
                     storage_options.insert(key_str, value_str);
                 }
@@ -109,13 +99,10 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
             })
         })
         .await
-        .map_err(|e| lance_core::Error::IO {
-            source: Box::new(std::io::Error::other(format!(
-                "Task join error: {}",
-                e
-            ))),
-            location: snafu::location!(),
-        })?
+        .map_err(|e| lance_core::Error::io_source(Box::new(std::io::Error::other(format!(
+            "Task join error: {}",
+            e
+        )))))?
     }
 
     fn provider_id(&self) -> String {

python/src/table.rs

@@ -5,7 +5,7 @@ use std::{collections::HashMap, sync::Arc};
 use crate::{
     connection::Connection,
     error::PythonErrorExt,
-    index::{extract_index_params, IndexConfig},
+    index::{IndexConfig, extract_index_params},
     query::{Query, TakeQuery},
     table::scannable::PyScannable,
 };
@@ -19,10 +19,10 @@ use lancedb::table::{
     Table as LanceDbTable,
 };
 use pyo3::{
+    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
     exceptions::{PyKeyError, PyRuntimeError, PyValueError},
     pyclass, pymethods,
     types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
@@ -112,19 +112,24 @@ impl From<lancedb::table::AddResult> for AddResult {
 #[pyclass(get_all)]
 #[derive(Clone, Debug)]
 pub struct DeleteResult {
+    pub num_deleted_rows: u64,
     pub version: u64,
 }
 
 #[pymethods]
 impl DeleteResult {
     pub fn __repr__(&self) -> String {
-        format!("DeleteResult(version={})", self.version)
+        format!(
+            "DeleteResult(num_deleted_rows={}, version={})",
+            self.num_deleted_rows, self.version
+        )
     }
 }
 
 impl From<lancedb::table::DeleteResult> for DeleteResult {
     fn from(result: lancedb::table::DeleteResult) -> Self {
         Self {
+            num_deleted_rows: result.num_deleted_rows,
             version: result.version,
         }
     }
@@ -294,10 +299,12 @@ impl Table {
         })
     }
 
+    #[pyo3(signature = (data, mode, progress=None))]
     pub fn add<'a>(
         self_: PyRef<'a, Self>,
         data: PyScannable,
         mode: String,
+        progress: Option<Py<PyAny>>,
     ) -> PyResult<Bound<'a, PyAny>> {
         let mut op = self_.inner_ref()?.add(data);
         if mode == "append" {
@@ -307,6 +314,81 @@ impl Table {
         } else {
             return Err(PyValueError::new_err(format!("Invalid mode: {}", mode)));
         }
+        if let Some(progress_obj) = progress {
+            let is_callable = Python::attach(|py| progress_obj.bind(py).is_callable());
+            if is_callable {
+                // Callback: call with a dict of progress info.
+                op = op.progress(move |p| {
+                    Python::attach(|py| {
+                        let dict = PyDict::new(py);
+                        if let Err(e) = dict
+                            .set_item("output_rows", p.output_rows())
+                            .and_then(|_| dict.set_item("output_bytes", p.output_bytes()))
+                            .and_then(|_| dict.set_item("total_rows", p.total_rows()))
+                            .and_then(|_| {
+                                dict.set_item("elapsed_seconds", p.elapsed().as_secs_f64())
+                            })
+                            .and_then(|_| dict.set_item("active_tasks", p.active_tasks()))
+                            .and_then(|_| dict.set_item("total_tasks", p.total_tasks()))
+                            .and_then(|_| dict.set_item("done", p.done()))
+                        {
+                            log::warn!("progress dict error: {e}");
+                            return;
+                        }
+                        if let Err(e) = progress_obj.call1(py, (dict,)) {
+                            log::warn!("progress callback error: {e}");
+                        }
+                    });
+                });
+            } else {
+                // tqdm-like: has update() method.
+                let mut last_rows: usize = 0;
+                let mut total_set = false;
+                op = op.progress(move |p| {
+                    let current = p.output_rows();
+                    let prev = last_rows;
+                    last_rows = current;
+                    Python::attach(|py| {
+                        if let Some(total) = p.total_rows()
+                            && !total_set
+                        {
+                            if let Err(e) = progress_obj.setattr(py, "total", total) {
+                                log::warn!("progress setattr error: {e}");
+                            }
+                            total_set = true;
+                        }
+                        let delta = current.saturating_sub(prev);
+                        if delta > 0 {
+                            if let Err(e) = progress_obj.call_method1(py, "update", (delta,)) {
+                                log::warn!("progress update error: {e}");
+                            }
+                            // Show throughput and active workers in tqdm postfix.
+                            let elapsed = p.elapsed().as_secs_f64();
+                            if elapsed > 0.0 {
+                                let mb_per_sec = p.output_bytes() as f64 / elapsed / 1_000_000.0;
+                                let postfix = format!(
+                                    "{:.1} MB/s | {}/{} workers",
+                                    mb_per_sec,
+                                    p.active_tasks(),
+                                    p.total_tasks()
+                                );
+                                if let Err(e) =
+                                    progress_obj.call_method1(py, "set_postfix_str", (postfix,))
+                                {
+                                    log::warn!("progress set_postfix_str error: {e}");
+                                }
+                            }
+                        }
+                        if p.done() {
+                            // Force a final refresh so the bar shows completion.
+                            if let Err(e) = progress_obj.call_method0(py, "refresh") {
+                                log::warn!("progress refresh error: {e}");
+                            }
+                        }
+                    });
+                });
+            }
+        }
 
         future_into_py(self_.py(), async move {
             let result = op.execute().await.infer_error()?;
@@ -421,6 +503,17 @@ impl Table {
         })
     }
 
+    pub fn prewarm_data(
+        self_: PyRef<'_, Self>,
+        columns: Option<Vec<String>>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.inner_ref()?.clone();
+        future_into_py(self_.py(), async move {
+            inner.prewarm_data(columns).await.infer_error()?;
+            Ok(())
+        })
+    }
+
     pub fn list_indices(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
@@ -537,7 +630,7 @@ impl Table {
         let inner = self_.inner_ref()?.clone();
         future_into_py(self_.py(), async move {
             let versions = inner.list_versions().await.infer_error()?;
-            let versions_as_dict = Python::attach(|py| {
+            Python::attach(|py| {
                 versions
                     .iter()
                     .map(|v| {
@@ -554,9 +647,7 @@ impl Table {
                         Ok(dict.unbind())
                     })
                     .collect::<PyResult<Vec<_>>>()
-            });
-
-            versions_as_dict
+            })
         })
     }
 

python/src/table/scannable.rs

@@ -10,11 +10,11 @@ use arrow::{
 };
 use futures::StreamExt;
 use lancedb::{
+    Error,
     arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
     data::scannable::Scannable,
-    Error,
 };
-use pyo3::{types::PyAnyMethods, FromPyObject, Py, PyAny, Python};
+use pyo3::{FromPyObject, Py, PyAny, Python, types::PyAnyMethods};
 
 /// Adapter that implements Scannable for a Python reader factory callable.
 ///
@@ -99,15 +99,15 @@ impl Scannable for PyScannable {
                         // Channel closed. Check if the task panicked — a panic
                         // drops the sender without sending an error, so without
                         // this check we'd silently return a truncated stream.
-                        if let Some(handle) = join_handle {
-                            if let Err(join_err) = handle.await {
-                                return Some((
-                                    Err(Error::Runtime {
-                                        message: format!("Reader task panicked: {}", join_err),
-                                    }),
-                                    (rx, None),
-                                ));
-                            }
+                        if let Some(handle) = join_handle
+                            && let Err(join_err) = handle.await
+                        {
+                            return Some((
+                                Err(Error::Runtime {
+                                    message: format!("Reader task panicked: {}", join_err),
+                                }),
+                                (rx, None),
+                            ));
                         }
                         None
                     }

python/src/util.rs

@@ -5,8 +5,9 @@ use std::sync::Mutex;
 
 use lancedb::DistanceType;
 use pyo3::{
+    PyResult,
     exceptions::{PyRuntimeError, PyValueError},
-    pyfunction, PyResult,
+    pyfunction,
 };
 
 /// A wrapper around a rust builder

python/uv.lock

@@ -2006,7 +2006,7 @@ requires-dist = [
     { name = "botocore", marker = "extra == 'embeddings'", specifier = ">=1.31.57" },
     { name = "cohere", marker = "extra == 'embeddings'" },
     { name = "colpali-engine", marker = "extra == 'embeddings'", specifier = ">=0.3.10" },
-    { name = "datafusion", marker = "extra == 'tests'" },
+    { name = "datafusion", marker = "extra == 'tests'", specifier = "<52" },
     { name = "deprecation" },
     { name = "duckdb", marker = "extra == 'tests'" },
     { name = "google-generativeai", marker = "extra == 'embeddings'" },
@@ -2035,7 +2035,7 @@ requires-dist = [
     { name = "pyarrow-stubs", marker = "extra == 'tests'" },
     { name = "pydantic", specifier = ">=1.10" },
     { name = "pylance", marker = "extra == 'pylance'", specifier = ">=1.0.0b14" },
-    { name = "pylance", marker = "extra == 'tests'", specifier = ">=1.0.0b14" },
+    { name = "pylance", marker = "extra == 'tests'", specifier = ">=1.0.0b14,<3.0.0" },
     { name = "pyright", marker = "extra == 'dev'" },
     { name = "pytest", marker = "extra == 'tests'" },
     { name = "pytest-asyncio", marker = "extra == 'tests'" },

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.27.0-beta.2"
+version = "0.27.2-beta.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/README.md

@@ -1,4 +1,4 @@
-# LanceDB Rust
+# LanceDB Rust SDK
 
 <a href="https://crates.io/crates/vectordb">![img](https://img.shields.io/crates/v/vectordb)</a>
 <a href="https://docs.rs/vectordb/latest/vectordb/">![Docs.rs](https://img.shields.io/docsrs/vectordb)</a>

rust/lancedb/examples/bedrock.rs

@@ -9,10 +9,9 @@ use aws_config::Region;
 use aws_sdk_bedrockruntime::Client;
 use futures::StreamExt;
 use lancedb::{
-    connect,
-    embeddings::{bedrock::BedrockEmbeddingFunction, EmbeddingDefinition, EmbeddingFunction},
+    Result, connect,
+    embeddings::{EmbeddingDefinition, EmbeddingFunction, bedrock::BedrockEmbeddingFunction},
     query::{ExecutableQuery, QueryBase},
-    Result,
 };
 
 #[tokio::main]

rust/lancedb/examples/full_text_search.rs

@@ -10,10 +10,10 @@ use futures::TryStreamExt;
 use lance_index::scalar::FullTextSearchQuery;
 use lancedb::connection::Connection;
 
-use lancedb::index::scalar::FtsIndexBuilder;
 use lancedb::index::Index;
+use lancedb::index::scalar::FtsIndexBuilder;
 use lancedb::query::{ExecutableQuery, QueryBase};
-use lancedb::{connect, Result, Table};
+use lancedb::{Result, Table, connect};
 use rand::random;
 
 #[tokio::main]
@@ -46,19 +46,21 @@ fn create_some_records() -> Result<Box<dyn arrow_array::RecordBatchReader + Send
         .collect::<Vec<_>>();
     let n_terms = 3;
     let batches = RecordBatchIterator::new(
-        vec![RecordBatch::try_new(
-            schema.clone(),
-            vec![
-                Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
-                Arc::new(StringArray::from_iter_values((0..TOTAL).map(|_| {
-                    (0..n_terms)
-                        .map(|_| words[random::<u32>() as usize % words.len()])
-                        .collect::<Vec<_>>()
-                        .join(" ")
-                }))),
-            ],
-        )
-        .unwrap()]
+        vec![
+            RecordBatch::try_new(
+                schema.clone(),
+                vec![
+                    Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
+                    Arc::new(StringArray::from_iter_values((0..TOTAL).map(|_| {
+                        (0..n_terms)
+                            .map(|_| words[random::<u32>() as usize % words.len()])
+                            .collect::<Vec<_>>()
+                            .join(" ")
+                    }))),
+                ],
+            )
+            .unwrap(),
+        ]
         .into_iter()
         .map(Ok),
         schema.clone(),

rust/lancedb/examples/hybrid_search.rs

@@ -5,16 +5,15 @@ use arrow_array::{RecordBatch, StringArray};
 use arrow_schema::{DataType, Field, Schema};
 use futures::TryStreamExt;
 use lance_index::scalar::FullTextSearchQuery;
-use lancedb::index::scalar::FtsIndexBuilder;
 use lancedb::index::Index;
+use lancedb::index::scalar::FtsIndexBuilder;
 use lancedb::{
-    connect,
+    Result, Table, connect,
     embeddings::{
-        sentence_transformers::SentenceTransformersEmbeddings, EmbeddingDefinition,
-        EmbeddingFunction,
+        EmbeddingDefinition, EmbeddingFunction,
+        sentence_transformers::SentenceTransformersEmbeddings,
     },
     query::{QueryBase, QueryExecutionOptions},
-    Result, Table,
 };
 use std::{iter::once, sync::Arc};
 

rust/lancedb/examples/ivf_pq.rs

@@ -14,10 +14,10 @@ use arrow_schema::{DataType, Field, Schema};
 use futures::TryStreamExt;
 use lancedb::connection::Connection;
 
-use lancedb::index::vector::IvfPqIndexBuilder;
 use lancedb::index::Index;
+use lancedb::index::vector::IvfPqIndexBuilder;
 use lancedb::query::{ExecutableQuery, QueryBase};
-use lancedb::{connect, DistanceType, Result, Table};
+use lancedb::{DistanceType, Result, Table, connect};
 
 #[tokio::main]
 async fn main() -> Result<()> {
@@ -51,19 +51,21 @@ fn create_some_records() -> Result<Box<dyn arrow_array::RecordBatchReader + Send
 
     // Create a RecordBatch stream.
     let batches = RecordBatchIterator::new(
-        vec![RecordBatch::try_new(
-            schema.clone(),
-            vec![
-                Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
-                Arc::new(
-                    FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(
-                        (0..TOTAL).map(|_| Some(vec![Some(1.0); DIM])),
-                        DIM as i32,
+        vec![
+            RecordBatch::try_new(
+                schema.clone(),
+                vec![
+                    Arc::new(Int32Array::from_iter_values(0..TOTAL as i32)),
+                    Arc::new(
+                        FixedSizeListArray::from_iter_primitive::<Float32Type, _, _>(
+                            (0..TOTAL).map(|_| Some(vec![Some(1.0); DIM])),
+                            DIM as i32,
+                        ),
                     ),
-                ),
-            ],
-        )
-        .unwrap()]
+                ],
+            )
+            .unwrap(),
+        ]
         .into_iter()
         .map(Ok),
         schema.clone(),

rust/lancedb/examples/openai.rs

@@ -8,10 +8,9 @@ use std::{iter::once, sync::Arc};
 use arrow_array::{RecordBatch, StringArray};
 use futures::StreamExt;
 use lancedb::{
-    connect,
-    embeddings::{openai::OpenAIEmbeddingFunction, EmbeddingDefinition, EmbeddingFunction},
+    Result, connect,
+    embeddings::{EmbeddingDefinition, EmbeddingFunction, openai::OpenAIEmbeddingFunction},
     query::{ExecutableQuery, QueryBase},
-    Result,
 };
 
 // --8<-- [end:imports]

rust/lancedb/examples/sentence_transformers.rs

@@ -7,13 +7,12 @@ use arrow_array::{RecordBatch, StringArray};
 use arrow_schema::{DataType, Field, Schema};
 use futures::StreamExt;
 use lancedb::{
-    connect,
+    Result, connect,
     embeddings::{
-        sentence_transformers::SentenceTransformersEmbeddings, EmbeddingDefinition,
-        EmbeddingFunction,
+        EmbeddingDefinition, EmbeddingFunction,
+        sentence_transformers::SentenceTransformersEmbeddings,
     },
     query::{ExecutableQuery, QueryBase},
-    Result,
 };
 
 #[tokio::main]

rust/lancedb/examples/simple.rs

@@ -14,7 +14,7 @@ use futures::TryStreamExt;
 use lancedb::connection::Connection;
 use lancedb::index::Index;
 use lancedb::query::{ExecutableQuery, QueryBase};
-use lancedb::{connect, Result, Table as LanceDbTable};
+use lancedb::{Result, Table as LanceDbTable, connect};
 
 #[tokio::main]
 async fn main() -> Result<()> {

rust/lancedb/src/arrow.rs

@@ -12,7 +12,7 @@ use lance_datagen::{BatchCount, BatchGeneratorBuilder, RowCount};
 #[cfg(feature = "polars")]
 use {crate::polars_arrow_convertors, polars::frame::ArrowChunk, polars::prelude::DataFrame};
 
-use crate::{error::Result, Error};
+use crate::{Error, error::Result};
 
 /// An iterator of batches that also has a schema
 pub trait RecordBatchReader: Iterator<Item = Result<arrow_array::RecordBatch>> {

rust/lancedb/src/connection.rs

@@ -17,6 +17,7 @@ use lance_namespace::models::{
 #[cfg(feature = "aws")]
 use object_store::aws::AwsCredential;
 
+use crate::Table;
 use crate::connection::create_table::CreateTableBuilder;
 use crate::data::scannable::Scannable;
 use crate::database::listing::ListingDatabase;
@@ -31,7 +32,6 @@ use crate::remote::{
     client::ClientConfig,
     db::{OPT_REMOTE_API_KEY, OPT_REMOTE_HOST_OVERRIDE, OPT_REMOTE_REGION},
 };
-use crate::Table;
 use lance::io::ObjectStoreParams;
 pub use lance_encoding::version::LanceFileVersion;
 #[cfg(feature = "remote")]
@@ -136,6 +136,7 @@ impl OpenTableBuilder {
                 lance_read_params: None,
                 location: None,
                 namespace_client: None,
+                managed_versioning: None,
             },
             embedding_registry,
         }
@@ -235,6 +236,29 @@ impl OpenTableBuilder {
         self
     }
 
+    /// Set a namespace client for managed versioning support.
+    ///
+    /// When a namespace client is provided and the table has `managed_versioning` enabled,
+    /// the table will use the namespace's commit handler to notify the namespace of
+    /// version changes. This enables features like event emission for table modifications.
+    pub fn namespace_client(mut self, client: Arc<dyn lance_namespace::LanceNamespace>) -> Self {
+        self.request.namespace_client = Some(client);
+        self
+    }
+
+    /// Set whether managed versioning is enabled for this table.
+    ///
+    /// When set to `Some(true)`, the table will use namespace-managed commits.
+    /// When set to `Some(false)`, the table will use local commits even if namespace_client is set.
+    /// When set to `None` (default), the value will be fetched from the namespace if namespace_client is set.
+    ///
+    /// This is typically set when the caller has already queried the namespace and knows the
+    /// managed_versioning status, avoiding a redundant describe_table call.
+    pub fn managed_versioning(mut self, enabled: bool) -> Self {
+        self.request.managed_versioning = Some(enabled);
+        self
+    }
+
     /// Open the table
     pub async fn execute(self) -> Result<Table> {
         let table = self.parent.open_table(self.request).await?;
@@ -294,6 +318,12 @@ impl CloneTableBuilder {
         self
     }
 
+    /// Set a namespace client for managed versioning support.
+    pub fn namespace_client(mut self, client: Arc<dyn lance_namespace::LanceNamespace>) -> Self {
+        self.request.namespace_client = Some(client);
+        self
+    }
+
     /// Execute the clone operation
     pub async fn execute(self) -> Result<Table> {
         let parent = self.parent.clone();
@@ -758,10 +788,10 @@ impl ConnectBuilder {
         options: &mut HashMap<String, String>,
     ) {
         for (env_key, opt_key) in env_var_to_remote_storage_option {
-            if let Ok(env_value) = std::env::var(env_key) {
-                if !options.contains_key(*opt_key) {
-                    options.insert((*opt_key).to_string(), env_value);
-                }
+            if let Ok(env_value) = std::env::var(env_key)
+                && !options.contains_key(*opt_key)
+            {
+                options.insert((*opt_key).to_string(), env_value);
             }
         }
     }
@@ -1011,14 +1041,13 @@ mod tests {
     #[cfg(feature = "remote")]
     #[test]
     fn test_apply_env_defaults() {
-        let env_key = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_KEY";
-        let env_val = "TEST_APPLY_ENV_DEFAULTS_ENVIRONMENT_VARIABLE_ENV_VAL";
+        let env_key = "PATH";
+        let env_val = std::env::var(env_key).expect("PATH should be set in test environment");
         let opts_key = "test_apply_env_defaults_environment_variable_opts_key";
-        std::env::set_var(env_key, env_val);
 
         let mut options = HashMap::new();
         ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);
-        assert_eq!(Some(&env_val.to_string()), options.get(opts_key));
+        assert_eq!(Some(&env_val), options.get(opts_key));
 
         options.insert(opts_key.to_string(), "EXPLICIT-VALUE".to_string());
         ConnectBuilder::apply_env_defaults(&[(env_key, opts_key)], &mut options);

rust/lancedb/src/connection/create_table.rs

@@ -6,12 +6,12 @@ use std::sync::Arc;
 use lance_io::object_store::StorageOptionsProvider;
 
 use crate::{
+    Error, Result, Table,
     connection::{merge_storage_options, set_storage_options_provider},
     data::scannable::{Scannable, WithEmbeddingsScannable},
     database::{CreateTableMode, CreateTableRequest, Database},
     embeddings::{EmbeddingDefinition, EmbeddingFunction, EmbeddingRegistry},
     table::WriteOptions,
-    Error, Result, Table,
 };
 
 pub struct CreateTableBuilder {
@@ -167,7 +167,7 @@ impl CreateTableBuilder {
 #[cfg(test)]
 mod tests {
     use arrow_array::{
-        record_batch, Array, FixedSizeListArray, Float32Array, RecordBatch, RecordBatchIterator,
+        Array, FixedSizeListArray, Float32Array, RecordBatch, RecordBatchIterator, record_batch,
     };
     use arrow_schema::{ArrowError, DataType, Field, Schema};
     use futures::TryStreamExt;
@@ -380,11 +380,12 @@ mod tests {
             .await
             .unwrap();
         let other_schema = Arc::new(Schema::new(vec![Field::new("y", DataType::Int32, false)]));
-        assert!(db
-            .create_empty_table("test", other_schema.clone())
-            .execute()
-            .await
-            .is_err()); // TODO: assert what this error is
+        assert!(
+            db.create_empty_table("test", other_schema.clone())
+                .execute()
+                .await
+                .is_err()
+        ); // TODO: assert what this error is
         let overwritten = db
             .create_empty_table("test", other_schema.clone())
             .mode(CreateTableMode::Overwrite)

rust/lancedb/src/data/inspect.rs

@@ -5,9 +5,9 @@ use std::collections::HashMap;
 
 use arrow::compute::kernels::{aggregate::bool_and, length::length};
 use arrow_array::{
+    Array, GenericListArray, OffsetSizeTrait, PrimitiveArray, RecordBatchReader,
     cast::AsArray,
     types::{ArrowPrimitiveType, Int32Type, Int64Type},
-    Array, GenericListArray, OffsetSizeTrait, PrimitiveArray, RecordBatchReader,
 };
 use arrow_ord::cmp::eq;
 use arrow_schema::DataType;
@@ -78,7 +78,7 @@ pub fn infer_vector_columns(
                 _ => {
                     return Err(Error::Schema {
                         message: format!("Column {} is not a list", col_name),
-                    })
+                    });
                 }
             } {
                 if let Some(Some(prev_dim)) = columns_to_infer.get(&col_name) {
@@ -102,8 +102,8 @@ mod tests {
     use super::*;
 
     use arrow_array::{
-        types::{Float32Type, Float64Type},
         FixedSizeListArray, Float32Array, ListArray, RecordBatch, RecordBatchIterator, StringArray,
+        types::{Float32Type, Float64Type},
     };
     use arrow_schema::{DataType, Field, Schema};
     use std::{sync::Arc, vec};

rust/lancedb/src/data/sanitize.rs

@@ -4,10 +4,10 @@
 use std::{iter::repeat_with, sync::Arc};
 
 use arrow_array::{
-    cast::AsArray,
-    types::{Float16Type, Float32Type, Float64Type, Int32Type, Int64Type},
     Array, ArrowNumericType, FixedSizeListArray, PrimitiveArray, RecordBatch, RecordBatchIterator,
     RecordBatchReader,
+    cast::AsArray,
+    types::{Float16Type, Float32Type, Float64Type, Int32Type, Int64Type},
 };
 use arrow_cast::{can_cast_types, cast};
 use arrow_schema::{ArrowError, DataType, Field, Schema};
@@ -184,7 +184,7 @@ mod tests {
     use std::sync::Arc;
 
     use arrow_array::{
-        FixedSizeListArray, Float16Array, Float32Array, Float64Array, Int32Array, Int8Array,
+        FixedSizeListArray, Float16Array, Float32Array, Float64Array, Int8Array, Int32Array,
         RecordBatch, RecordBatchIterator, StringArray,
     };
     use arrow_schema::Field;

rust/lancedb/src/data/scannable.rs

@@ -13,16 +13,16 @@ use crate::arrow::{
     SendableRecordBatchStream, SendableRecordBatchStreamExt, SimpleRecordBatchStream,
 };
 use crate::embeddings::{
-    compute_embeddings_for_batch, compute_output_schema, EmbeddingDefinition, EmbeddingFunction,
-    EmbeddingRegistry,
+    EmbeddingDefinition, EmbeddingFunction, EmbeddingRegistry, compute_embeddings_for_batch,
+    compute_output_schema,
 };
 use crate::table::{ColumnDefinition, ColumnKind, TableDefinition};
 use crate::{Error, Result};
 use arrow_array::{ArrayRef, RecordBatch, RecordBatchIterator, RecordBatchReader};
 use arrow_schema::{ArrowError, SchemaRef};
 use async_trait::async_trait;
-use futures::stream::once;
 use futures::StreamExt;
+use futures::stream::once;
 use lance_datafusion::utils::StreamingWriteSource;
 
 pub trait Scannable: Send {

rust/lancedb/src/database.rs

@@ -19,12 +19,12 @@ use std::sync::Arc;
 use std::time::Duration;
 
 use lance::dataset::ReadParams;
+use lance_namespace::LanceNamespace;
 use lance_namespace::models::{
     CreateNamespaceRequest, CreateNamespaceResponse, DescribeNamespaceRequest,
     DescribeNamespaceResponse, DropNamespaceRequest, DropNamespaceResponse, ListNamespacesRequest,
     ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
 };
-use lance_namespace::LanceNamespace;
 
 use crate::data::scannable::Scannable;
 use crate::error::Result;
@@ -66,6 +66,10 @@ pub struct OpenTableRequest {
     /// Optional namespace client for server-side query execution.
     /// When set, queries will be executed on the namespace server instead of locally.
     pub namespace_client: Option<Arc<dyn LanceNamespace>>,
+    /// Whether managed versioning is enabled for this table.
+    /// When Some(true), the table will use namespace-managed commits instead of local commits.
+    /// When None and namespace_client is provided, the value will be fetched from the namespace.
+    pub managed_versioning: Option<bool>,
 }
 
 impl std::fmt::Debug for OpenTableRequest {
@@ -77,6 +81,7 @@ impl std::fmt::Debug for OpenTableRequest {
             .field("lance_read_params", &self.lance_read_params)
             .field("location", &self.location)
             .field("namespace_client", &self.namespace_client)
+            .field("managed_versioning", &self.managed_versioning)
             .finish()
     }
 }
@@ -161,6 +166,9 @@ pub struct CloneTableRequest {
     /// Whether to perform a shallow clone (true) or deep clone (false). Defaults to true.
     /// Currently only shallow clone is supported.
     pub is_shallow: bool,
+    /// Optional namespace client for managed versioning support.
+    /// When set, enables the commit handler to track table versions through the namespace.
+    pub namespace_client: Option<Arc<dyn LanceNamespace>>,
 }
 
 impl CloneTableRequest {
@@ -172,6 +180,7 @@ impl CloneTableRequest {
             source_version: None,
             source_tag: None,
             is_shallow: true,
+            namespace_client: None,
         }
     }
 }

rust/lancedb/src/database/listing.rs

@@ -8,7 +8,7 @@ use std::path::Path;
 use std::{collections::HashMap, sync::Arc};
 
 use lance::dataset::refs::Ref;
-use lance::dataset::{builder::DatasetBuilder, ReadParams, WriteMode};
+use lance::dataset::{ReadParams, WriteMode, builder::DatasetBuilder};
 use lance::io::{ObjectStore, ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
 use lance_encoding::version::LanceFileVersion;
@@ -669,6 +669,7 @@ impl ListingDatabase {
                     lance_read_params: None,
                     location: None,
                     namespace_client: None,
+                    managed_versioning: None,
                 };
                 let req = (callback)(req);
                 let table = self.open_table(req).await?;
@@ -869,6 +870,7 @@ impl Database for ListingDatabase {
             Some(write_params),
             self.read_consistency_interval,
             request.namespace_client,
+            false, // server_side_query_enabled - listing database doesn't support server-side queries
         )
         .await
         {
@@ -946,7 +948,9 @@ impl Database for ListingDatabase {
             self.store_wrapper.clone(),
             None,
             self.read_consistency_interval,
-            None,
+            request.namespace_client,
+            false, // server_side_query_enabled - listing database doesn't support server-side queries
+            None,  // managed_versioning - will be queried if namespace_client is provided
         )
         .await?;
 
@@ -1022,6 +1026,8 @@ impl Database for ListingDatabase {
                 Some(read_params),
                 self.read_consistency_interval,
                 request.namespace_client,
+                false, // server_side_query_enabled - listing database doesn't support server-side queries
+                request.managed_versioning, // Pass through managed_versioning from request
             )
             .await?,
         );
@@ -1097,11 +1103,11 @@ impl Database for ListingDatabase {
 #[cfg(test)]
 mod tests {
     use super::*;
+    use crate::Table;
     use crate::connection::ConnectRequest;
     use crate::data::scannable::Scannable;
     use crate::database::{CreateTableMode, CreateTableRequest};
     use crate::table::WriteOptions;
-    use crate::Table;
     use arrow_array::{Int32Array, RecordBatch, StringArray};
     use arrow_schema::{DataType, Field, Schema};
     use std::path::PathBuf;
@@ -1162,6 +1168,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1222,6 +1229,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1281,6 +1289,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await;
 
@@ -1317,6 +1326,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: false, // Request deep clone
+                namespace_client: None,
             })
             .await;
 
@@ -1357,6 +1367,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await;
 
@@ -1397,6 +1408,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await;
 
@@ -1416,6 +1428,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await;
 
@@ -1452,6 +1465,7 @@ mod tests {
                 source_version: Some(1),
                 source_tag: Some("v1.0".to_string()),
                 is_shallow: true,
+                namespace_client: None,
             })
             .await;
 
@@ -1525,6 +1539,7 @@ mod tests {
                 source_version: Some(initial_version),
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1603,6 +1618,7 @@ mod tests {
                 source_version: None,
                 source_tag: Some("v1.0".to_string()),
                 is_shallow: true,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1654,6 +1670,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await
             .unwrap();
@@ -1746,6 +1763,7 @@ mod tests {
                 source_version: None,
                 source_tag: None,
                 is_shallow: true,
+                namespace_client: None,
             })
             .await
             .unwrap();

rust/lancedb/src/database/namespace.rs

@@ -7,18 +7,20 @@ use std::collections::HashMap;
 use std::sync::Arc;
 
 use async_trait::async_trait;
+use lance::io::commit::namespace_manifest::LanceNamespaceExternalManifestStore;
 use lance_io::object_store::{ObjectStoreParams, StorageOptionsAccessor};
 use lance_namespace::{
-    models::{
-        CreateEmptyTableRequest, CreateNamespaceRequest, CreateNamespaceResponse,
-        DeclareTableRequest, DescribeNamespaceRequest, DescribeNamespaceResponse,
-        DescribeTableRequest, DropNamespaceRequest, DropNamespaceResponse, DropTableRequest,
-        ListNamespacesRequest, ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
-    },
     LanceNamespace,
+    models::{
+        CreateNamespaceRequest, CreateNamespaceResponse, DeclareTableRequest,
+        DescribeNamespaceRequest, DescribeNamespaceResponse, DescribeTableRequest,
+        DropNamespaceRequest, DropNamespaceResponse, DropTableRequest, ListNamespacesRequest,
+        ListNamespacesResponse, ListTablesRequest, ListTablesResponse,
+    },
 };
 use lance_namespace_impls::ConnectBuilder;
-use log::warn;
+use lance_table::io::commit::CommitHandler;
+use lance_table::io::commit::external_manifest::ExternalManifestCommitHandler;
 
 use crate::database::ReadConsistency;
 use crate::error::{Error, Result};
@@ -206,83 +208,48 @@ impl Database for LanceNamespaceDatabase {
         let mut table_id = request.namespace.clone();
         table_id.push(request.name.clone());
 
-        // Try declare_table first, falling back to create_empty_table for backwards
-        // compatibility with older namespace clients that don't support declare_table
         let declare_request = DeclareTableRequest {
             id: Some(table_id.clone()),
             ..Default::default()
         };
 
-        let (location, initial_storage_options) =
-            match self.namespace.declare_table(declare_request).await {
-                Ok(response) => {
-                    let loc = response.location.ok_or_else(|| Error::Runtime {
-                        message: "Table location is missing from declare_table response"
-                            .to_string(),
-                    })?;
-                    // Use storage options from response, fall back to self.storage_options
-                    let opts = response
-                        .storage_options
-                        .or_else(|| Some(self.storage_options.clone()))
-                        .filter(|o| !o.is_empty());
-                    (loc, opts)
-                }
-                Err(e) => {
-                    // Check if the error is "not supported" and try create_empty_table as fallback
-                    let err_str = e.to_string().to_lowercase();
-                    if err_str.contains("not supported") || err_str.contains("not implemented") {
-                        warn!(
-                            "declare_table is not supported by the namespace client, \
-                        falling back to deprecated create_empty_table. \
-                        create_empty_table is deprecated and will be removed in Lance 3.0.0. \
-                        Please upgrade your namespace client to support declare_table."
-                        );
-                        #[allow(deprecated)]
-                        let create_empty_request = CreateEmptyTableRequest {
-                            id: Some(table_id.clone()),
-                            ..Default::default()
-                        };
+        let (location, initial_storage_options, managed_versioning) = {
+            let response = self.namespace.declare_table(declare_request).await?;
+            let loc = response.location.ok_or_else(|| Error::Runtime {
+                message: "Table location is missing from declare_table response".to_string(),
+            })?;
+            // Use storage options from response, fall back to self.storage_options
+            let opts = response
+                .storage_options
+                .or_else(|| Some(self.storage_options.clone()))
+                .filter(|o| !o.is_empty());
+            (loc, opts, response.managed_versioning)
+        };
 
-                        #[allow(deprecated)]
-                        let create_response = self
-                            .namespace
-                            .create_empty_table(create_empty_request)
-                            .await
-                            .map_err(|e| Error::Runtime {
-                                message: format!("Failed to create empty table: {}", e),
-                            })?;
+        // Build write params with storage options and commit handler
+        let mut params = request.write_options.lance_write_params.unwrap_or_default();
 
-                        let loc = create_response.location.ok_or_else(|| Error::Runtime {
-                            message: "Table location is missing from create_empty_table response"
-                                .to_string(),
-                        })?;
-                        // For deprecated path, use self.storage_options
-                        let opts = if self.storage_options.is_empty() {
-                            None
-                        } else {
-                            Some(self.storage_options.clone())
-                        };
-                        (loc, opts)
-                    } else {
-                        return Err(Error::Runtime {
-                            message: format!("Failed to declare table: {}", e),
-                        });
-                    }
-                }
-            };
-
-        let write_params = if let Some(storage_opts) = initial_storage_options {
-            let mut params = request.write_options.lance_write_params.unwrap_or_default();
+        // Set up storage options if provided
+        if let Some(storage_opts) = initial_storage_options {
             let store_params = params
                 .store_params
                 .get_or_insert_with(ObjectStoreParams::default);
             store_params.storage_options_accessor = Some(Arc::new(
                 StorageOptionsAccessor::with_static_options(storage_opts),
             ));
-            Some(params)
-        } else {
-            request.write_options.lance_write_params
-        };
+        }
+
+        // Set up commit handler when managed_versioning is enabled
+        if managed_versioning == Some(true) {
+            let external_store =
+                LanceNamespaceExternalManifestStore::new(self.namespace.clone(), table_id.clone());
+            let commit_handler: Arc<dyn CommitHandler> = Arc::new(ExternalManifestCommitHandler {
+                external_manifest_store: Arc::new(external_store),
+            });
+            params.commit_handler = Some(commit_handler);
+        }
+
+        let write_params = Some(params);
 
         let native_table = NativeTable::create_from_namespace(
             self.namespace.clone(),

rust/lancedb/src/dataloader/permutation/builder.rs

@@ -11,16 +11,16 @@ use lance_core::ROW_ID;
 use lance_datafusion::exec::SessionContextExt;
 
 use crate::{
+    Error, Result, Table,
     arrow::{SendableRecordBatchStream, SendableRecordBatchStreamExt, SimpleRecordBatchStream},
     connect,
     database::{CreateTableRequest, Database},
     dataloader::permutation::{
         shuffle::{Shuffler, ShufflerConfig},
-        split::{SplitStrategy, Splitter, SPLIT_ID_COLUMN},
-        util::{rename_column, TemporaryDirectory},
+        split::{SPLIT_ID_COLUMN, SplitStrategy, Splitter},
+        util::{TemporaryDirectory, rename_column},
     },
     query::{ExecutableQuery, QueryBase, Select},
-    Error, Result, Table,
 };
 
 pub const SRC_ROW_ID_COL: &str = "row_id";

rust/lancedb/src/dataloader/permutation/reader.rs

@@ -25,8 +25,8 @@ use futures::{StreamExt, TryStreamExt};
 use lance::dataset::scanner::DatasetRecordBatchStream;
 use lance::io::RecordBatchStream;
 use lance_arrow::RecordBatchExt;
-use lance_core::error::LanceOptionExt;
 use lance_core::ROW_ID;
+use lance_core::error::LanceOptionExt;
 use std::collections::HashMap;
 use std::sync::Arc;
 
@@ -339,6 +339,12 @@ impl PermutationReader {
                 }
                 Ok(false)
             }
+            Select::Expr(columns) => {
+                // For Expr projections, we check if any alias is _rowid.
+                // We can't validate the expression itself (it may differ from _rowid)
+                // but we allow it through; the column will be included.
+                Ok(columns.iter().any(|(alias, _)| alias == ROW_ID))
+            }
         }
     }
 
@@ -500,10 +506,10 @@ mod tests {
     use rand::seq::SliceRandom;
 
     use crate::{
+        Table,
         arrow::SendableRecordBatchStream,
         query::{ExecutableQuery, QueryBase},
-        test_utils::datagen::{virtual_table, LanceDbDatagenExt},
-        Table,
+        test_utils::datagen::{LanceDbDatagenExt, virtual_table},
     };
 
     use super::*;

rust/lancedb/src/dataloader/permutation/shuffle.rs

@@ -18,12 +18,12 @@ use lance_io::{
     scheduler::{ScanScheduler, SchedulerConfig},
     utils::CachedFileSize,
 };
-use rand::{seq::SliceRandom, Rng, RngCore};
+use rand::{Rng, RngCore, seq::SliceRandom};
 
 use crate::{
-    arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
-    dataloader::permutation::util::{non_crypto_rng, TemporaryDirectory},
     Error, Result,
+    arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
+    dataloader::permutation::util::{TemporaryDirectory, non_crypto_rng},
 };
 
 #[derive(Debug, Clone)]
@@ -281,7 +281,7 @@ mod tests {
     use datafusion_expr::col;
     use futures::TryStreamExt;
     use lance_datagen::{BatchCount, BatchGeneratorBuilder, ByteCount, RowCount, Seed};
-    use rand::{rngs::SmallRng, SeedableRng};
+    use rand::{SeedableRng, rngs::SmallRng};
 
     fn test_gen() -> BatchGeneratorBuilder {
         lance_datagen::gen_batch()

rust/lancedb/src/dataloader/permutation/split.rs

@@ -2,8 +2,8 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use std::sync::{
-    atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
     Arc,
+    atomic::{AtomicBool, AtomicU64, AtomicUsize, Ordering},
 };
 
 use arrow_array::{Array, BooleanArray, RecordBatch, UInt64Array};
@@ -15,13 +15,13 @@ use lance_arrow::SchemaExt;
 use lance_core::ROW_ID;
 
 use crate::{
+    Error, Result,
     arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
     dataloader::{
         permutation::shuffle::{Shuffler, ShufflerConfig},
         permutation::util::TemporaryDirectory,
     },
     query::{Query, QueryBase, Select},
-    Error, Result,
 };
 
 pub const SPLIT_ID_COLUMN: &str = "split_id";

rust/lancedb/src/dataloader/permutation/util.rs

@@ -7,12 +7,12 @@ use arrow_array::RecordBatch;
 use arrow_schema::{Fields, Schema};
 use datafusion_execution::disk_manager::DiskManagerMode;
 use futures::TryStreamExt;
-use rand::{rngs::SmallRng, RngCore, SeedableRng};
+use rand::{RngCore, SeedableRng, rngs::SmallRng};
 use tempfile::TempDir;
 
 use crate::{
-    arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
     Error, Result,
+    arrow::{SendableRecordBatchStream, SimpleRecordBatchStream},
 };
 
 /// Directory to use for temporary files

rust/lancedb/src/embeddings.rs

@@ -23,9 +23,9 @@ use arrow_schema::{DataType, Field, SchemaBuilder, SchemaRef};
 use serde::{Deserialize, Serialize};
 
 use crate::{
+    Error,
     error::Result,
     table::{ColumnDefinition, ColumnKind, TableDefinition},
-    Error,
 };
 
 /// Trait for embedding functions