Bump version: 0.38.0-beta.5 → 0.38.0-beta.6

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.39.0-beta.6"
+current_version = "0.38.0-beta.6"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/dependabot.yml

@@ -44,27 +44,3 @@ updates:
       python-deps:
         patterns:
           - "*"
-
-  # The npm ecosystem covers pnpm lockfiles. There are two separate installs:
-  # the bindings themselves and the examples, which have their own lockfile.
-  # As with cargo and pip above, only bump the lockfile — the version ranges
-  # in package.json are our consumers' constraints, not ours.
-  - package-ecosystem: npm
-    directory: /nodejs
-    schedule:
-      interval: weekly
-    versioning-strategy: lockfile-only
-    groups:
-      nodejs-deps:
-        patterns:
-          - "*"
-
-  - package-ecosystem: npm
-    directory: /nodejs/examples
-    schedule:
-      interval: weekly
-    versioning-strategy: lockfile-only
-    groups:
-      nodejs-examples-deps:
-        patterns:
-          - "*"

.github/workflows/dev.yml

@@ -29,14 +29,12 @@ jobs:
     steps:
       - uses: actions/setup-node@v6
         with:
-          node-version: "24"
-      - uses: pnpm/action-setup@v6
-        with:
-          version: 11.1.1
+          node-version: "18"
       # These rules are disabled because Github will always ensure there
       # is a blank line between the title and the body and Github will
       # word wrap the description field to ensure a reasonable max line
       # length.
+      - run: npm install @commitlint/config-conventional
       - run: >
           echo 'module.exports = {
             "rules": {
@@ -45,11 +43,7 @@ jobs:
               "body-leading-blank": [0, "always"]
             }
           }' > .commitlintrc.js
-      - run: >
-          pnpm dlx
-          --package @commitlint/cli@21.2.2
-          --package @commitlint/config-conventional@21.2.2
-          commitlint --extends @commitlint/config-conventional --verbose <<< $COMMIT_MSG
+      - run: npx commitlint --extends @commitlint/config-conventional --verbose <<< $COMMIT_MSG
         env:
           COMMIT_MSG: >
             ${{ github.event.pull_request.title }}
@@ -60,7 +54,7 @@ jobs:
         with:
           script: |
             const message = `**ACTION NEEDED**
-
+              
               Lance follows the [Conventional Commits specification](https://www.conventionalcommits.org/en/v1.0.0/) for release automation.
 
               The PR title and description are used as the merge commit message.\

.github/workflows/docs-link-check.yml

@@ -56,7 +56,7 @@ jobs:
         uses: lycheeverse/lychee-action@e7477775783ea5526144ba13e8db5eec57747ce8 # v2.9.0
         with:
           # Restricted to http(s) on purpose. Much of docs/src is generated
-          # API reference (the js/ tree comes from `pnpm run docs` in nodejs)
+          # API reference (the js/ tree comes from `npm run docs` in nodejs)
           # and the hand-written pages use mkdocstrings cross-references and
           # nav-relative paths that only resolve in the site mkdocs builds,
           # not in this checkout, so relative links would be reported as

.github/workflows/docs.yml

@@ -55,7 +55,9 @@ jobs:
       - name: Set up node
         uses: actions/setup-node@v6
         with:
-          node-version: 24
+          node-version: 20
+          cache: 'npm'
+          cache-dependency-path: docs/package-lock.json
       - name: Install node dependencies
         working-directory: nodejs
         run: |

.github/workflows/nodejs.yml

@@ -47,8 +47,9 @@ jobs:
         version: 11.1.1
     - uses: actions/setup-node@v6
       with:
-        # Build on a supported LTS; the matrix job below covers every
-        # Node version the library claims to support.
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # in October. The library itself still supports Node >= 18
+        # (see test matrix below).
         node-version: 24
         cache: 'pnpm'
         cache-dependency-path: nodejs/pnpm-lock.yaml
@@ -83,7 +84,7 @@ jobs:
     timeout-minutes: 30
     strategy:
       matrix:
-        node-version: [ "22", "24", "26" ]
+        node-version: [ "18", "20" ]
     runs-on: "ubuntu-22.04"
     defaults:
       run:
@@ -100,9 +101,9 @@ jobs:
     - uses: actions/setup-node@v6
       name: Setup Node.js 24 for build
       with:
-        # Build and install once on a fixed version so the generated docs
-        # are identical across matrix legs; the tests below then run on each
-        # supported Node version.
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # in October. Build/install runs on Node 24; tests run on the
+        # matrix version below using direct jest invocation.
         node-version: 24
         cache: 'pnpm'
         cache-dependency-path: nodejs/pnpm-lock.yaml
@@ -151,9 +152,9 @@ jobs:
         S3_TEST: "1"
         # Newer @smithy/core uses dynamic ESM imports.
         NODE_OPTIONS: "--experimental-vm-modules"
-      # Invoke the installed jest binary directly; the pnpm shim is set up
-      # against the build-phase Node, not the version selected above.
-      run: node_modules/.bin/jest --verbose
+      # Invoke jest directly because pnpm 11 itself requires Node 22+
+      # while the matrix tests on older Node versions.
+      run: npx jest --verbose
     - name: Test examples
       working-directory: ./
       env:
@@ -163,7 +164,7 @@ jobs:
       run: |
         python ci/mock_openai.py &
         cd nodejs/examples
-        node_modules/.bin/jest --testEnvironment jest-environment-node-single-context --verbose
+        npx jest --testEnvironment jest-environment-node-single-context --verbose
   macos:
     timeout-minutes: 30
     # macos-15 ships a newer linker; the older macos-14 linker fails to insert
@@ -184,7 +185,8 @@ jobs:
         version: 11.1.1
     - uses: actions/setup-node@v6
       with:
-        # pnpm 11 requires Node >= 22.13.
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+        # in October.
         node-version: 24
         cache: 'pnpm'
         cache-dependency-path: nodejs/pnpm-lock.yaml

.github/workflows/npm-publish.yml

@@ -40,31 +40,40 @@ jobs:
           - target: aarch64-apple-darwin
             host: macos-latest
             features: fp16kernels
-            # Fat LTO was ~111 of this job's ~113 minutes.
-            lto: thin
-            codegen_units: 16
             pre_build: |-
               brew install protobuf
+              # Fat LTO (the workspace default in .cargo/config.toml) is
+              # single-threaded and is the peak-memory step of the build. On
+              # this runner it accounted for ~111 of the job's ~113 minutes,
+              # making it the critical path of the entire publish pipeline.
+              # ThinLTO parallelizes it across the runner's cores, for a few
+              # percent of runtime performance.
+              export CARGO_PROFILE_RELEASE_LTO=thin
+              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
           - target: x86_64-pc-windows-msvc
             host: windows-2025
             features: ","
-            # The lower peak also keeps this on the standard 4-core runner.
-            lto: thin
-            codegen_units: 16
             pre_build: |-
               choco install --no-progress protoc ninja nasm
               tail -n 1000 /c/ProgramData/chocolatey/logs/chocolatey.log
               # There is an issue where choco doesn't add nasm to the path
               export PATH="$PATH:/c/Program Files/NASM"
               nasm -v
+              # See the ThinLTO note on aarch64-apple-darwin above. Keeping
+              # peak memory down is also what lets this run on the standard
+              # 4-core runner: the 8-core larger runner was only needed to
+              # stop fat LTO from OOMing rustc-LLVM.
+              export CARGO_PROFILE_RELEASE_LTO=thin
+              export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
           - target: aarch64-pc-windows-msvc
             host: windows-2025
             features: ","
-            lto: thin
-            codegen_units: 16
             pre_build: |-
                 choco install --no-progress protoc
                 rustup target add aarch64-pc-windows-msvc
+                # See the ThinLTO note on aarch64-apple-darwin above.
+                export CARGO_PROFILE_RELEASE_LTO=thin
+                export CARGO_PROFILE_RELEASE_CODEGEN_UNITS=16
           - target: x86_64-unknown-linux-gnu
             host: ubuntu-latest
             features: fp16kernels
@@ -94,14 +103,6 @@ jobs:
             # https://github.com/napi-rs/napi-rs/blob/main/debian-aarch64.Dockerfile
             docker: ghcr.io/napi-rs/napi-rs/nodejs-rust:lts-debian-aarch64
             features: "fp16kernels"
-            # Fat LTO OOM-killed rustc every nightly; even with lld it peaked
-            # at 31391 MiB of the runner's 32 GiB.
-            lto: thin
-            codegen_units: 16
-            # arm64 Linux links through GNU `ld` where x86_64 defaults to
-            # `rust-lld`, which is why only arm64 OOM'd. lld cut the largest
-            # linker process 7.0 -> 4.0 GiB (lancedb/sophon#7313).
-            linker: /tmp/aarch64-lld-clang
             pre_build: |-
               set -e &&
               apt-get update &&
@@ -111,30 +112,9 @@ jobs:
               # AT_HWCAP2 (added in Linux 3.17). Define it for aws-lc-sys.
               export CFLAGS="$CFLAGS -DAT_HWCAP2=26" &&
               rustup target add aarch64-unknown-linux-gnu
-              # Not `&&`-chained: in dash, errexit does not fire for a
-              # non-final command in an `&&` list, so failures were ignored.
-              #
-              # A wrapper rather than `-C link-arg` because the per-target
-              # rustflags variable does not reach every unit that links, while
-              # the linker variable does. `clang` because GCC silently ignores
-              # `-fuse-ld=lld` unless built with lld support. Two echoes
-              # because printf's newline escape gets rewritten to `;` between
-              # here and the container.
-              echo '#!/bin/sh' > /tmp/aarch64-lld-clang
-              echo 'exec clang --target=aarch64-unknown-linux-gnu --sysroot=/usr/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/sysroot --gcc-toolchain=/usr/aarch64-unknown-linux-gnu -fuse-ld=lld "$@"' >> /tmp/aarch64-lld-clang
-              chmod 0755 /tmp/aarch64-lld-clang
-              # Fail now, not at the cdylib link ~30 minutes later. Linking at
-              # all also proves lld resolved; clang errors out when it cannot.
-              echo 'int main(void){return 0;}' > /tmp/probe.c
-              /tmp/aarch64-lld-clang /tmp/probe.c -o /tmp/probe
-              readelf -h /tmp/probe | grep AArch64
           - target: aarch64-unknown-linux-musl
             host: ubuntu-2404-8x-x64
             features: ","
-            # Fat LTO took the whole runner down. lld cannot help: it died
-            # inside rustc's LLVM, before any linker was spawned.
-            lto: thin
-            codegen_units: 16
             pre_build: |-
               set -e &&
               sudo apt-get update &&
@@ -143,19 +123,6 @@ jobs:
               export EXTRA_ARGS="-x"
     name: build - ${{ matrix.settings.target }}
     runs-on: ${{ matrix.settings.host }}
-    # On the job, not exported from `pre_build`: `Swatinem/rust-cache` hashes
-    # `CARGO_*` into its cache key before any step runs, so a step-local export
-    # leaves the key unchanged while cargo still rebuilds cold. The ThinLTO
-    # legs had been doing that every run.
-    #
-    # Not `RUSTFLAGS`: setting it, even to "", discards every config-file
-    # rustflag, silently dropping .cargo/config.toml's `target-cpu` and
-    # `target-feature` from the published binaries.
-    env:
-      CARGO_PROFILE_RELEASE_LTO: ${{ matrix.settings.lto || 'fat' }}
-      CARGO_PROFILE_RELEASE_CODEGEN_UNITS: ${{ matrix.settings.codegen_units || '1' }}
-      # Empty elsewhere: a per-target variable is only read for that triple.
-      CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER: ${{ matrix.settings.linker }}
     defaults:
       run:
         working-directory: nodejs
@@ -168,7 +135,8 @@ jobs:
       - name: Setup node
         uses: actions/setup-node@v6
         with:
-          # pnpm 11 requires Node >= 22.13.
+          # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
+          # in October.
           node-version: 24
           cache: pnpm
           cache-dependency-path: nodejs/pnpm-lock.yaml
@@ -201,15 +169,19 @@ jobs:
           # creating ref). The nightly cadence also keeps entries inside
           # GitHub's 7-day eviction window, which a tag-only trigger would not.
           save-if: ${{ github.ref == 'refs/heads/main' }}
-      # Docker builds can use rust-cache too: the workspace is bind-mounted, so
-      # `target/` lives on the host and rust-cache's prune keeps the entry
-      # small.
+      # Docker builds can use rust-cache too. `target/` already lives on the
+      # host because the whole workspace is bind-mounted into the container, and
+      # rust-cache's prune and save run host-side, so they can manage it -- which
+      # is what keeps the entry to dependency artifacts rather than a multi-GB
+      # copy of everything.
       #
       # Two differences from the native builds. The container's CARGO_HOME is
-      # bind-mounted from `.cargo-cache` rather than ~/.cargo, so that is cached
-      # explicitly. And the key uses the *host* rustc version, not the compiler
-      # that built these artifacts -- safe, since cargo fingerprints the real
-      # one; a base-image bump just costs one cold build.
+      # bind-mounted from `.cargo-cache` rather than the host's ~/.cargo, so that
+      # has to be cached explicitly. And the key is derived from the *host* rustc
+      # version, which is not the compiler that produced these artifacts; that is
+      # safe because cargo fingerprints the real compiler and rebuilds on a
+      # mismatch, it just means a base-image toolchain bump costs one cold build
+      # instead of invalidating the key.
       - name: Cache cargo (docker builds)
         uses: Swatinem/rust-cache@v2
         if: ${{ matrix.settings.docker }}
@@ -238,19 +210,14 @@ jobs:
           # cache step above saves. Previously the registry mounts pointed at
           # `.cargo/...`, a path nothing cached, so the container re-downloaded
           # the whole crate registry on every run.
-          #
-          # `docker run` inherits nothing; `-e NAME` carries the job's `env:` in.
           options: "--user 0:0 -v ${{ github.workspace }}/.cargo-cache/git/db:/usr/local/cargo/git/db \
                     -v ${{ github.workspace }}/.cargo-cache/registry/cache:/usr/local/cargo/registry/cache \
                     -v ${{ github.workspace }}/.cargo-cache/registry/index:/usr/local/cargo/registry/index \
-                    -e CARGO_PROFILE_RELEASE_LTO \
-                    -e CARGO_PROFILE_RELEASE_CODEGEN_UNITS \
-                    -e CARGO_TARGET_AARCH64_UNKNOWN_LINUX_GNU_LINKER \
                     -v ${{ github.workspace }}:/build -w /build/nodejs"
           run: |
             set -e
             ${{ matrix.settings.pre_build }}
-            node_modules/.bin/napi build --platform --release \
+            npx napi build --platform --release \
               --features ${{ matrix.settings.features }} \
               --target ${{ matrix.settings.target }} \
               --dts ../lancedb/native.d.ts \
@@ -270,7 +237,7 @@ jobs:
       - name: Build
         run: |
           ${{ matrix.settings.pre_build }}
-          node_modules/.bin/napi build --platform --release \
+          npx napi build --platform --release \
               --features ${{ matrix.settings.features }} \
               --target ${{ matrix.settings.target }} \
               --dts ../lancedb/native.d.ts \
@@ -289,18 +256,6 @@ jobs:
         if: always()
         run: df -h
         shell: bash
-      - name: Report peak memory
-        if: always() && runner.os == 'Linux'
-        shell: bash
-        run: |
-          peak=$(find /sys/fs/cgroup -name memory.peak -readable \
-                 -exec cat {} + 2>/dev/null | sort -n | tail -1)
-          if [ -n "$peak" ]; then
-            echo "peak memory: $((peak / 1024 / 1024)) MiB"
-          else
-            echo "peak memory: unavailable (no readable cgroup v2 memory.peak)"
-          fi
-          free -g || true
       - name: Upload artifact
         uses: actions/upload-artifact@v7
         with:
@@ -338,7 +293,7 @@ jobs:
           - target: aarch64-unknown-linux-gnu
             host: ubuntu-2404-8x-arm64
         node:
-          - '22'
+          - '20'
     runs-on: ${{ matrix.settings.host }}
     defaults:
       run:
@@ -384,9 +339,9 @@ jobs:
       - name: Move built files
         run: cp dist/native.d.ts dist/native.js dist/*.node lancedb/
       - name: Test bindings
-        # Invoke the installed jest binary directly; the pnpm shim is set up
-        # against the install-phase Node, not the version selected above.
-        run: node_modules/.bin/jest --verbose
+        # Invoke jest directly because pnpm 11 itself requires Node 22+
+        # while the matrix tests on older Node versions.
+        run: npx jest --verbose
   publish:
     name: Publish
     runs-on: ubuntu-latest

.github/workflows/rust.yml

@@ -232,10 +232,7 @@ jobs:
           ALL_FEATURES=`cargo metadata --format-version=1 --no-deps \
             | jq -r '.packages[] | .features | keys | .[]' \
             | grep -v s3-test | sort | uniq | paste -s -d "," -`
-          # Run doctests before test binaries fill the runner disk. Examples are
-          # already built by the Linux job, so avoid retaining them here.
-          cargo test --profile ci --features $ALL_FEATURES --locked --doc
-          cargo test --profile ci --features $ALL_FEATURES --locked --lib --tests
+          cargo test --profile ci --features $ALL_FEATURES --locked
 
   windows:
     strategy:

.github/workflows/typos.yml

@@ -1,20 +0,0 @@
-name: Typo checker
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-
-permissions:
-  contents: read
-
-jobs:
-  run:
-    name: Spell Check with Typos
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Check spelling of the entire repository
-        uses: crate-ci/typos@6802cc60d4e7f78b9d5454f6cf3935c042d5e1e3 # v1.26.0

.github/workflows/update_package_lock_run.yml

@@ -0,0 +1,22 @@
+name: Update package-lock.json
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          ref: main
+          persist-credentials: false
+          fetch-depth: 0
+          lfs: true
+      - uses: ./.github/workflows/update_package_lock
+        with:
+          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}

.github/workflows/update_package_lock_run_nodejs.yml

@@ -0,0 +1,22 @@
+name: Update NodeJs package-lock.json
+
+on:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  publish:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v6
+        with:
+          ref: main
+          persist-credentials: false
+          fetch-depth: 0
+          lfs: true
+      - uses: ./.github/workflows/update_package_lock_nodejs
+        with:
+          github_token: ${{ secrets.LANCEDB_RELEASE_TOKEN }}

.pre-commit-config.yaml

@@ -10,10 +10,6 @@ repos:
     rev: v0.9.9
     hooks:
       - id: ruff
-  - repo: https://github.com/crate-ci/typos
-    rev: v1.26.0
-    hooks:
-      - id: typos
   # - repo: https://github.com/RobertCraigie/pyright-python
   #   rev: v1.1.395
   #   hooks:
@@ -24,10 +20,7 @@ repos:
     hooks:
       - id: local-biome-check
         name: biome check
-        # Use the biome from nodejs/package.json rather than a separately
-        # pinned one: the two drifted apart and disagreed on formatting, so
-        # this hook rejected code that `pnpm lint` accepted.
-        entry: nodejs/node_modules/.bin/biome check --config-path nodejs/biome.json nodejs/
+        entry: npx @biomejs/biome@1.8.3 check --config-path nodejs/biome.json nodejs/
         language: system
         types: [text]
         files: "nodejs/.*"

.typos.toml

@@ -1,19 +0,0 @@
-[default]
-extend-ignore-re = ["(?Rm)^.*(#|//)\\s*spellchecker:disable-line$"]
-
-[default.extend-words]
-# Azure Kubernetes Service, mentioned in rust/lancedb/src/remote/oauth.rs.
-AKS = "AKS"
-# RabitQ is the name of a vector quantization algorithm, not a typo of "Rabbit".
-Rabit = "Rabit"
-# `VarBuilder::from_mmaped_safetensors` is the real (if oddly-spelled) name of
-# the candle-core API we call in rust/lancedb/src/embeddings/sentence_transformers.rs.
-mmaped = "mmaped"
-# `WriteableBuffer` is the real name of a type from Python's `_typeshed` stubs,
-# used in python/python/lancedb/_blob.py.
-Writeable = "Writeable"
-
-[files]
-extend-exclude = [
-    "*_THIRD_PARTY_LICENSES.*",
-]

AGENTS.md

@@ -38,7 +38,7 @@ Before committing changes, run formatting for every language you touched. At min
 * Rust changes: run `cargo fmt --all`.
 * Python changes: run `ruff format .` and `ruff check .` from the repository root,
   and run targeted tests through `cd python && uv run ...`.
-* TypeScript changes: run the relevant `pnpm` lint, format, build, and docs commands in `nodejs`.
+* TypeScript changes: run the relevant `npm`/`pnpm` lint, format, build, and docs commands in `nodejs`.
 
 Before creating a PR, the exact value passed to `gh pr create --title` must follow
 Conventional Commits, such as `fix: support nested field paths in native index creation`
@@ -101,12 +101,12 @@ Python bindings changes:
 TypeScript bindings changes:
 
 1. Add napi-rs method binding on `Table` in `nodejs/src/table.rs`.
-2. Run `pnpm build` to generate TypeScript definitions.
+2. Run `npm run build` to generate TypeScript definitions.
 3. Add typescript method on abstract class `Table` in `nodejs/src/table.ts`.
 4. Add concrete method on `LocalTable` class in `nodejs/src/native_table.ts`.
     * Note: despite the name, this class is also used for remote tables.
 5. Add test in `nodejs/__test__/table.test.ts`.
-6. Run `pnpm run docs` to generate TypeScript documentation.
+6. Run `npm run docs` to generate TypeScript documentation.
 
 ## Python API reference
 

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=12.0.0-beta.18", default-features = false, "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=12.0.0-beta.18", default-features = false, "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=12.0.0-beta.18", default-features = false, "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=12.0.0-beta.18", "tag" = "v12.0.0-beta.18", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=11.0.0-beta.22", default-features = false, "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=11.0.0-beta.22", default-features = false, "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=11.0.0-beta.22", default-features = false, "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=11.0.0-beta.22", "tag" = "v11.0.0-beta.22", "git" = "https://github.com/lance-format/lance.git" }
 lancedb = { path = "rust/lancedb", default-features = false }
 ahash = "0.8"
 # Note that this one does not include pyarrow
@@ -39,7 +39,6 @@ arrow-ord = "58.0.0"
 arrow-schema = "58.0.0"
 arrow-select = "58.0.0"
 arrow-cast = "58.0.0"
-arrow-flight = { version = "58.0.0", features = ["flight-sql-experimental"] }
 async-trait = "0"
 bytes = "1"
 datafusion = { version = "54.0.0", default-features = false }
@@ -60,7 +59,7 @@ log = "0.4"
 metrics = "0.24"
 metrics-util = "0.19"
 moka = { version = "0.12", features = ["future"] }
-object_store = "0.14.1"
+object_store = "0.13.2"
 pin-project = "1.0.7"
 rand = "0.9"
 snafu = "0.8"
@@ -72,8 +71,7 @@ serde = "1"
 serde_json = "1"
 tempfile = "3.5.0"
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
-tonic = { version = "0.14", features = ["tls-native-roots", "tls-ring"] }
-uuid = { version = "1.7.0", features = ["v4", "v7"] }
+uuid = { version = "1.7.0", features = ["v4"] }
 chrono = { version = "0.4", default-features = false, features = ["clock"] }
 
 [profile.ci]

Makefile

@@ -5,5 +5,5 @@ licenses:
 	cd python && cargo about generate ../about.hbs -o RUST_THIRD_PARTY_LICENSES.html -c ../about.toml
 	cd python && uv sync --all-extras && uv tool run pip-licenses --python .venv/bin/python --format=markdown --with-urls --output-file=PYTHON_THIRD_PARTY_LICENSES.md
 	cd nodejs && cargo about generate ../about.hbs -o RUST_THIRD_PARTY_LICENSES.html -c ../about.toml
-	cd nodejs && pnpm dlx license-checker@25 --markdown --out NODEJS_THIRD_PARTY_LICENSES.md
+	cd nodejs && npx license-checker --markdown --out NODEJS_THIRD_PARTY_LICENSES.md
 	cd java && ./mvnw license:aggregate-add-third-party -q

ci/update_lockfiles.sh

@@ -12,12 +12,16 @@ done
 # This updates the lockfile without building
 cargo metadata --quiet > /dev/null
 
+pushd nodejs || exit 1
+npm install --package-lock-only --silent
+popd
+
 if git diff --quiet --exit-code; then
   echo "No lockfile changes to commit; skipping amend."
 elif $AMEND; then
-  git add Cargo.lock
+  git add Cargo.lock nodejs/package-lock.json
   git commit --amend --no-edit
 else
-  git add Cargo.lock
+  git add Cargo.lock nodejs/package-lock.json
   git commit -m "Update lockfiles"
 fi

deny.toml

@@ -131,13 +131,18 @@ allow = [
     "BSD-3-Clause",
     "ISC",
     "Unicode-3.0",
+    "Unicode-DFS-2016",
     "Zlib",
     "CC0-1.0",
     "MPL-2.0",
     "BSL-1.0",
+    "OpenSSL",
     # 0BSD ("BSD Zero Clause") is effectively public domain — no attribution
     # required. Pulled in by `mock_instant`.
     "0BSD",
+    # bzip2-1.0.6 is the permissive upstream bzip2 license (BSD-like). Pulled
+    # in by `libbz2-rs-sys`, the pure-Rust bzip2 implementation.
+    "bzip2-1.0.6",
     # CDLA-Permissive-2.0 is a permissive data license used by `webpki-roots`
     # for the Mozilla CA root bundle. Data-only, distribution-compatible.
     "CDLA-Permissive-2.0",
@@ -145,7 +150,12 @@ allow = [
 confidence-threshold = 0.8
 # Per-crate license exceptions: allow a license for a specific crate only,
 # rather than globally via the `allow` list above.
-exceptions = []
+exceptions = [
+    # CDDL-1.0 (copyleft) is pulled in only as a dev/profiling dependency via
+    # `inferno` -> `pprof` -> `lance-testing`; it is a test dependency that we
+    # do not distribute, so scope the allowance to `inferno` alone.
+    { allow = ["CDDL-1.0"], crate = "inferno" },
+]
 # Crates whose license cannot be determined from Cargo metadata but whose
 # license we've manually confirmed from upstream. Keep this list minimal.
 [[licenses.clarify]]

docs/README.md

@@ -47,24 +47,22 @@ pytest -vv python/tests/docs
 
 ### Checking typescript examples
 
-The examples depend on `@lancedb/lancedb` at `file:../dist`, so the package must be
-built before running the tests. This uses pnpm; see the
-[Typescript contributing guide](../nodejs/CONTRIBUTING.md) for the toolchain setup.
+The `@lancedb/lancedb` package must be built before running the tests:
 
 ```shell
 pushd nodejs
-pnpm install
-pnpm build
+npm ci
+npm run build
 popd
 ```
 
-Then you can run the examples by going to the `nodejs/examples` directory, which is a
-separate pnpm package with its own lockfile:
+Then you can run the examples by going to the `nodejs/examples` directory and
+running the tests like a normal npm package:
 
 ```shell
 pushd nodejs/examples
-pnpm install
-pnpm test
+npm ci
+npm test
 popd
 ```
 
@@ -86,7 +84,6 @@ The new files should be checked into the repository.
 
 ```shell
 pushd nodejs
-# `pnpm docs` would invoke pnpm's built-in `docs` command, not the script.
-pnpm run docs
+npm run docs
 popd
 ```

docs/openapi.yml

@@ -155,7 +155,7 @@ paths:
                 vector:
                   type: FixedSizeList
                   description: |
-                    The targeted vector to search for. Required.
+                    The targetted vector to search for. Required.
                 vector_column:
                   type: string
                   description: |
@@ -446,15 +446,6 @@ paths:
               properties:
                 column:
                   type: string
-                name:
-                  type: string
-                  description: Optional name for the created index.
-                replace:
-                  type: boolean
-                  default: true
-                  description: |
-                    Whether to replace an existing index with the same resolved
-                    name. Defaults to true.
                 metric_type:
                   type: string
                   nullable: false

docs/package-lock.json

@@ -0,0 +1,135 @@
+{
+  "name": "lancedb-docs-test",
+  "version": "1.0.0",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "lancedb-docs-test",
+      "version": "1.0.0",
+      "license": "Apache 2",
+      "dependencies": {
+        "apache-arrow": "file:../node/node_modules/apache-arrow",
+        "vectordb": "file:../node"
+      },
+      "devDependencies": {
+        "@types/node": "^20.11.8",
+        "typescript": "^5.3.3"
+      }
+    },
+    "../node": {
+      "name": "vectordb",
+      "version": "0.21.2-beta.0",
+      "cpu": [
+        "x64",
+        "arm64"
+      ],
+      "license": "Apache-2.0",
+      "os": [
+        "darwin",
+        "linux",
+        "win32"
+      ],
+      "dependencies": {
+        "@neon-rs/load": "^0.0.74",
+        "axios": "^1.4.0"
+      },
+      "devDependencies": {
+        "@neon-rs/cli": "^0.0.160",
+        "@types/chai": "^4.3.4",
+        "@types/chai-as-promised": "^7.1.5",
+        "@types/mocha": "^10.0.1",
+        "@types/node": "^18.16.2",
+        "@types/sinon": "^10.0.15",
+        "@types/temp": "^0.9.1",
+        "@types/uuid": "^9.0.3",
+        "@typescript-eslint/eslint-plugin": "^5.59.1",
+        "apache-arrow-old": "npm:apache-arrow@13.0.0",
+        "cargo-cp-artifact": "^0.1",
+        "chai": "^4.3.7",
+        "chai-as-promised": "^7.1.1",
+        "eslint": "^8.39.0",
+        "eslint-config-standard-with-typescript": "^34.0.1",
+        "eslint-plugin-import": "^2.26.0",
+        "eslint-plugin-n": "^15.7.0",
+        "eslint-plugin-promise": "^6.1.1",
+        "mocha": "^10.2.0",
+        "openai": "^4.24.1",
+        "sinon": "^15.1.0",
+        "temp": "^0.9.4",
+        "ts-node": "^10.9.1",
+        "ts-node-dev": "^2.0.0",
+        "typedoc": "^0.24.7",
+        "typedoc-plugin-markdown": "^3.15.3",
+        "typescript": "^5.1.0",
+        "uuid": "^9.0.0"
+      },
+      "optionalDependencies": {
+        "@lancedb/vectordb-darwin-arm64": "0.21.2-beta.0",
+        "@lancedb/vectordb-darwin-x64": "0.21.2-beta.0",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.21.2-beta.0",
+        "@lancedb/vectordb-linux-x64-gnu": "0.21.2-beta.0",
+        "@lancedb/vectordb-win32-x64-msvc": "0.21.2-beta.0"
+      },
+      "peerDependencies": {
+        "@apache-arrow/ts": "^14.0.2",
+        "apache-arrow": "^14.0.2"
+      }
+    },
+    "../node/node_modules/apache-arrow": {
+      "version": "14.0.2",
+      "license": "Apache-2.0",
+      "dependencies": {
+        "@types/command-line-args": "5.2.0",
+        "@types/command-line-usage": "5.0.2",
+        "@types/node": "20.3.0",
+        "@types/pad-left": "2.1.1",
+        "command-line-args": "5.2.1",
+        "command-line-usage": "7.0.1",
+        "flatbuffers": "23.5.26",
+        "json-bignum": "^0.0.3",
+        "pad-left": "^2.1.0",
+        "tslib": "^2.5.3"
+      },
+      "bin": {
+        "arrow2csv": "bin/arrow2csv.js"
+      }
+    },
+    "node_modules/@types/node": {
+      "version": "20.11.8",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-20.11.8.tgz",
+      "integrity": "sha512-i7omyekpPTNdv4Jb/Rgqg0RU8YqLcNsI12quKSDkRXNfx7Wxdm6HhK1awT3xTgEkgxPn3bvnSpiEAc7a7Lpyow==",
+      "dev": true,
+      "dependencies": {
+        "undici-types": "~5.26.4"
+      }
+    },
+    "node_modules/apache-arrow": {
+      "resolved": "../node/node_modules/apache-arrow",
+      "link": true
+    },
+    "node_modules/typescript": {
+      "version": "5.3.3",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.3.3.tgz",
+      "integrity": "sha512-pXWcraxM0uxAS+tN0AG/BF2TyqmHO014Z070UsJ+pFvYuRSq8KH8DmWpnbXe0pEPDHXZV3FcAbJkijJ5oNEnWw==",
+      "dev": true,
+      "bin": {
+        "tsc": "bin/tsc",
+        "tsserver": "bin/tsserver"
+      },
+      "engines": {
+        "node": ">=14.17"
+      }
+    },
+    "node_modules/undici-types": {
+      "version": "5.26.5",
+      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-5.26.5.tgz",
+      "integrity": "sha512-JlCMO+ehdEIKqlFxk6IfVoAUVmgz7cU7zD/h9XZ0qzeosSHmUJVOzSQvvYSYWXkFXC+IfLKSIffhv0sVZup6pA==",
+      "dev": true
+    },
+    "node_modules/vectordb": {
+      "resolved": "../node",
+      "link": true
+    }
+  }
+}

docs/package.json

@@ -0,0 +1,20 @@
+{
+  "name": "lancedb-docs-test",
+  "version": "1.0.0",
+  "description": "auto-generated tests from doc",
+  "author": "dev@lancedb.com",
+  "license": "Apache 2",
+  "dependencies": {
+    "apache-arrow": "file:../node/node_modules/apache-arrow",
+    "vectordb": "file:../node"
+  },
+  "scripts": {
+    "build": "tsc -b && cd ../node && npm run build-release",
+    "example": "npm run build && node",
+    "test": "npm run build && ls dist/*.js | xargs -n 1 node"
+  },
+  "devDependencies": {
+    "@types/node": "^20.11.8",
+    "typescript": "^5.3.3"
+  }
+}

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>0.39.0-beta.6</version>
+    <version>0.38.0-beta.6</version>
 </dependency>
 ```
 

docs/src/js/classes/AutoQuery.md

@@ -1,518 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / AutoQuery
-
-# Class: AutoQuery
-
-A builder for automatic string searches.
-
-Automatic search determines whether to use full-text or vector search from
-the table revision selected for each execution. This builder exposes the
-common operations supported by both query families.
-
-## Extends
-
-- `StandardQueryBase`<`NativeQuery` \| `NativeVectorQuery`>
-
-## Properties
-
-### inner
-
-```ts
-protected inner: Query | VectorQuery | Promise<Query | VectorQuery>;
-```
-
-#### Inherited from
-
-`StandardQueryBase.inner`
-
-## Methods
-
-### analyzePlan()
-
-```ts
-analyzePlan(distributedMetrics?): Promise<string>
-```
-
-Executes the query and returns the physical query plan annotated with runtime metrics.
-
-This is useful for debugging and performance analysis, as it shows how the query was executed
-and includes metrics such as elapsed time, rows processed, and I/O statistics.
-
-#### Parameters
-
-* **distributedMetrics?**: [`AnalyzePlanDistributedMetrics`](../type-aliases/AnalyzePlanDistributedMetrics.md)
-    How distributed worker metrics are displayed for remote query plans.
-    Defaults to `"aggregate"`.
-
-#### Returns
-
-`Promise`&lt;`string`&gt;
-
-A query execution plan with runtime metrics for each step.
-
-#### Example
-
-```ts
-import * as lancedb from "@lancedb/lancedb"
-
-const db = await lancedb.connect("./.lancedb");
-const table = await db.createTable("my_table", [
-  { vector: [1.1, 0.9], id: "1" },
-]);
-
-const plan = await table.query().nearestTo([0.5, 0.2]).analyzePlan();
-
-Example output (with runtime metrics inlined):
-AnalyzeExec verbose=true, metrics=[]
- ProjectionExec: expr=[id@3 as id, vector@0 as vector, _distance@2 as _distance], metrics=[output_rows=1, elapsed_compute=3.292µs]
-  Take: columns="vector, _rowid, _distance, (id)", metrics=[output_rows=1, elapsed_compute=66.001µs, batches_processed=1, bytes_read=8, iops=1, requests=1]
-   CoalesceBatchesExec: target_batch_size=1024, metrics=[output_rows=1, elapsed_compute=3.333µs]
-    GlobalLimitExec: skip=0, fetch=10, metrics=[output_rows=1, elapsed_compute=167ns]
-     FilterExec: _distance@2 IS NOT NULL, metrics=[output_rows=1, elapsed_compute=8.542µs]
-      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST], metrics=[output_rows=1, elapsed_compute=63.25µs, row_replacements=1]
-       KNNVectorDistance: metric=l2, metrics=[output_rows=1, elapsed_compute=114.333µs, output_batches=1]
-        LanceScan: uri=/path/to/data, projection=[vector], row_id=true, row_addr=false, ordered=false, metrics=[output_rows=1, elapsed_compute=103.626µs, bytes_read=549, iops=2, requests=2]
-```
-
-#### Inherited from
-
-`StandardQueryBase.analyzePlan`
-
-***
-
-### execute()
-
-```ts
-protected execute(options?): AsyncGenerator<RecordBatch<any>, void, unknown>
-```
-
-Execute the query and return the results as an
-
-#### Parameters
-
-* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
-
-#### Returns
-
-`AsyncGenerator`&lt;`RecordBatch`&lt;`any`&gt;, `void`, `unknown`&gt;
-
-#### See
-
- - AsyncIterator
-of
- - RecordBatch.
-
-By default, LanceDb will use many threads to calculate results and, when
-the result set is large, multiple batches will be processed at one time.
-This readahead is limited however and backpressure will be applied if this
-stream is consumed slowly (this constrains the maximum memory used by a
-single query)
-
-#### Inherited from
-
-`StandardQueryBase.execute`
-
-***
-
-### explainPlan()
-
-```ts
-explainPlan(verbose): Promise<string>
-```
-
-Generates an explanation of the query execution plan.
-
-#### Parameters
-
-* **verbose**: `boolean` = `false`
-    If true, provides a more detailed explanation. Defaults to false.
-
-#### Returns
-
-`Promise`&lt;`string`&gt;
-
-A Promise that resolves to a string containing the query execution plan explanation.
-
-#### Example
-
-```ts
-import * as lancedb from "@lancedb/lancedb"
-const db = await lancedb.connect("./.lancedb");
-const table = await db.createTable("my_table", [
-  { vector: [1.1, 0.9], id: "1" },
-]);
-const plan = await table.query().nearestTo([0.5, 0.2]).explainPlan();
-```
-
-#### Inherited from
-
-`StandardQueryBase.explainPlan`
-
-***
-
-### fastSearch()
-
-```ts
-fastSearch(): this
-```
-
-Skip searching un-indexed data. This can make search faster, but will miss
-any data that is not yet indexed.
-
-Use [Table#optimize](Table.md#optimize) to index all un-indexed data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.fastSearch`
-
-***
-
-### ~~filter()~~
-
-```ts
-filter(predicate): this
-```
-
-A filter statement to be applied to this query.
-
-#### Parameters
-
-* **predicate**: `string`
-
-#### Returns
-
-`this`
-
-#### See
-
-where
-
-#### Deprecated
-
-Use `where` instead
-
-#### Inherited from
-
-`StandardQueryBase.filter`
-
-***
-
-### fullTextSearch()
-
-```ts
-fullTextSearch(query, options?): this
-```
-
-#### Parameters
-
-* **query**: `string` \| [`FullTextQuery`](../interfaces/FullTextQuery.md)
-
-* **options?**: `Partial`&lt;[`FullTextSearchOptions`](../interfaces/FullTextSearchOptions.md)&gt;
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.fullTextSearch`
-
-***
-
-### limit()
-
-```ts
-limit(limit): this
-```
-
-Set the maximum number of results to return.
-
-By default, a plain search has no limit.  If this method is not
-called then every valid row from the table will be returned.
-
-#### Parameters
-
-* **limit**: `number`
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.limit`
-
-***
-
-### offset()
-
-```ts
-offset(offset): this
-```
-
-Set the number of rows to skip before returning results.
-
-This is useful for pagination.
-
-#### Parameters
-
-* **offset**: `number`
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.offset`
-
-***
-
-### orderBy()
-
-```ts
-orderBy(ordering): this
-```
-
-Sort the results by the specified column(s).
-
-#### Parameters
-
-* **ordering**: [`ColumnOrdering`](../interfaces/ColumnOrdering.md) \| [`ColumnOrdering`](../interfaces/ColumnOrdering.md)[]
-
-#### Returns
-
-`this`
-
-This query builder.
-
-#### Inherited from
-
-`StandardQueryBase.orderBy`
-
-***
-
-### outputSchema()
-
-```ts
-outputSchema(): Promise<Schema<any>>
-```
-
-Returns the schema of the output that will be returned by this query.
-
-This can be used to inspect the types and names of the columns that will be
-returned by the query before executing it.
-
-#### Returns
-
-`Promise`&lt;`Schema`&lt;`any`&gt;&gt;
-
-An Arrow Schema describing the output columns.
-
-#### Inherited from
-
-`StandardQueryBase.outputSchema`
-
-***
-
-### select()
-
-```ts
-select(columns): this
-```
-
-Return only the specified columns.
-
-By default a query will return all columns from the table.  However, this can have
-a very significant impact on latency.  LanceDb stores data in a columnar fashion.  This
-means we can finely tune our I/O to select exactly the columns we need.
-
-As a best practice you should always limit queries to the columns that you need.  If you
-pass in an array of column names then only those columns will be returned.
-
-You can also use this method to create new "dynamic" columns based on your existing columns.
-For example, you may not care about "a" or "b" but instead simply want "a + b".  This is often
-seen in the SELECT clause of an SQL query (e.g. `SELECT a+b FROM my_table`).
-
-To create dynamic columns you can pass in a Map<string, string>.  A column will be returned
-for each entry in the map.  The key provides the name of the column.  The value is
-an SQL string used to specify how the column is calculated.
-
-For example, an SQL query might state `SELECT a + b AS combined, c`.  The equivalent
-input to this method would be:
-
-#### Parameters
-
-* **columns**: `string` \| `string`[] \| `Record`&lt;`string`, `string`&gt; \| `Map`&lt;`string`, `string`&gt;
-
-#### Returns
-
-`this`
-
-#### Example
-
-```ts
-new Map([["combined", "a + b"], ["c", "c"]])
-
-Columns will always be returned in the order given, even if that order is different than
-the order used when adding the data.
-
-Note that you can pass in a `Record<string, string>` (e.g. an object literal). This method
-uses `Object.entries` which should preserve the insertion order of the object.  However,
-object insertion order is easy to get wrong and `Map` is more foolproof.
-```
-
-#### Inherited from
-
-`StandardQueryBase.select`
-
-***
-
-### toArray()
-
-```ts
-toArray(options?): Promise<any[]>
-```
-
-Collect the results as an array of objects.
-
-#### Parameters
-
-* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
-
-#### Returns
-
-`Promise`&lt;`any`[]&gt;
-
-#### Inherited from
-
-`StandardQueryBase.toArray`
-
-***
-
-### toArrow()
-
-```ts
-toArrow(options?): Promise<Table<any>>
-```
-
-Collect the results as an Arrow
-
-#### Parameters
-
-* **options?**: `Partial`&lt;[`QueryExecutionOptions`](../interfaces/QueryExecutionOptions.md)&gt;
-
-#### Returns
-
-`Promise`&lt;`Table`&lt;`any`&gt;&gt;
-
-#### See
-
-ArrowTable.
-
-#### Inherited from
-
-`StandardQueryBase.toArrow`
-
-***
-
-### useLsm()
-
-```ts
-useLsm(enable): this
-```
-
-Control MemWAL read routing for this query.
-
-By default (unset), when the table carries a MemWAL write spec (see
-[Table#setLsmWriteSpec](Table.md#setlsmwritespec)), reads are routed through the LSM scanner so
-they also return data written via the `mergeInsert` LSM path that has not yet
-been compacted into the base table (the active/frozen in-memory memtables and
-the flushed generations), deduplicated by primary key; a table without a spec
-reads the base table.
-
-#### Parameters
-
-* **enable**: `boolean`
-    `true` forces the LSM scanner and errors if the table has no
-    MemWAL write spec. `false` bypasses the MemWAL and reads the base table only,
-    even when a spec is present.
-    Note: the LSM scanner does not support every query shape (e.g. reranking,
-    hybrid search, `orderBy`). On a MemWAL table those shapes error unless
-    `useLsm(false)` is set, because a base-only read would silently exclude
-    un-compacted MemWAL data.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.useLsm`
-
-***
-
-### where()
-
-```ts
-where(predicate): this
-```
-
-A filter statement to be applied to this query.
-
-The filter should be supplied as an SQL query string.  For example:
-
-#### Parameters
-
-* **predicate**: `string`
-
-#### Returns
-
-`this`
-
-#### Example
-
-```ts
-x > 10
-y > 0 AND y < 100
-x > 5 OR y = 'test'
-
-Filtering performance can often be improved by creating a scalar index
-on the filter column(s).
-
-Calling this multiple times combines the filters with a logical AND rather
-than replacing the previous filter.
-```
-
-#### Inherited from
-
-`StandardQueryBase.where`
-
-***
-
-### withRowId()
-
-```ts
-withRowId(): this
-```
-
-Whether to return the row id in the results.
-
-This column can be used to match results between different queries. For
-example, to match results from a full text search and a vector search in
-order to perform hybrid search.
-
-#### Returns
-
-`this`
-
-#### Inherited from
-
-`StandardQueryBase.withRowId`

docs/src/js/classes/BlobFile.md

@@ -1,62 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BlobFile
-
-# Class: BlobFile
-
-A lazy handle to blob bytes. Create one with [Table.fetchBlobFiles](Table.md#fetchblobfiles).
-
-## Methods
-
-### read()
-
-```ts
-read(): Promise<Buffer>
-```
-
-Reads from the cursor to the end and advances the cursor.
-
-A second call returns an empty buffer. [BlobFile.readRange](BlobFile.md#readrange) does
-not move the cursor.
-
-#### Returns
-
-`Promise`&lt;`Buffer`&gt;
-
-***
-
-### readRange()
-
-```ts
-readRange(start, end): Promise<Buffer>
-```
-
-Reads the half-open byte range `[start, end)`.
-
-Fails when `end` is past the blob size. Does not move the cursor.
-
-#### Parameters
-
-* **start**: `bigint`
-
-* **end**: `bigint`
-
-#### Returns
-
-`Promise`&lt;`Buffer`&gt;
-
-***
-
-### size()
-
-```ts
-size(): bigint
-```
-
-Returns the blob size in bytes.
-
-#### Returns
-
-`bigint`

docs/src/js/classes/Connection.md

@@ -448,6 +448,26 @@ on the returned job to know when cleanup has finished.
 
 ***
 
+### getJob()
+
+```ts
+abstract getJob(jobId): Promise<null | JobDescription>
+```
+
+Describe a single server-side job by id.
+
+Resolves to `null` when the server has no such job.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+`Promise`&lt;`null` \| [`JobDescription`](../interfaces/JobDescription.md)&gt;
+
+***
+
 ### isOpen()
 
 ```ts
@@ -462,6 +482,48 @@ Return true if the connection has not been closed
 
 ***
 
+### job()
+
+```ts
+abstract job(jobId): Job
+```
+
+A [Job](Job.md) handle for a server-side job by id.
+
+The handle is constructed without a server round trip; an unknown id
+surfaces when the handle is used. Dropping the handle has no effect on
+the job itself.
+
+#### Parameters
+
+* **jobId**: `string`
+
+#### Returns
+
+[`Job`](Job.md)
+
+***
+
+### jobHistory()
+
+```ts
+abstract jobHistory(jobId?): Promise<Table<any>>
+```
+
+The lifecycle event history of a server-side job, as an Arrow table.
+
+Lists history across all jobs when `jobId` is omitted.
+
+#### Parameters
+
+* **jobId?**: `string`
+
+#### Returns
+
+`Promise`&lt;`Table`&lt;`any`&gt;&gt;
+
+***
+
 ### listJobs()
 
 ```ts
@@ -522,94 +584,6 @@ Child namespace names and
 
 ***
 
-### listTables()
-
-#### listTables(options)
-
-```ts
-abstract listTables(options?): Promise<ListTablesResponse>
-```
-
-List a page of the tables in this database.
-
-To retrieve the tables after the page, pass the `pageToken` the response
-carries back in. A page can be shorter than `limit` without being the last
-one, so walk until a response carries no page token:
-
-```ts
-const names = [];
-let pageToken = undefined;
-do {
-  const page = await conn.listTables({ pageToken, limit: 100 });
-  names.push(...page.tables);
-  pageToken = page.pageToken;
-} while (pageToken);
-```
-
-##### Parameters
-
-* **options?**: `Partial`&lt;[`ListTablesOptions`](../interfaces/ListTablesOptions.md)&gt;
-    Pagination options
-    (`pageToken`, `limit`).
-
-##### Returns
-
-`Promise`&lt;[`ListTablesResponse`](../interfaces/ListTablesResponse.md)&gt;
-
-A page of table names and an
-  optional token for the tables after it.
-
-#### listTables(namespacePath, options)
-
-```ts
-abstract listTables(namespacePath?, options?): Promise<ListTablesResponse>
-```
-
-List a page of the tables in this database.
-
-##### Parameters
-
-* **namespacePath?**: `string`[]
-    The namespace path to list tables from
-    (defaults to root namespace)
-
-* **options?**: `Partial`&lt;[`ListTablesOptions`](../interfaces/ListTablesOptions.md)&gt;
-    Pagination options
-    (`pageToken`, `limit`).
-
-##### Returns
-
-`Promise`&lt;[`ListTablesResponse`](../interfaces/ListTablesResponse.md)&gt;
-
-A page of table names and an
-  optional token for the tables after it.
-
-***
-
-### openJob()
-
-```ts
-abstract openJob(jobId): Promise<Job>
-```
-
-Open a server-side job by id, returning a handle with its record already
-populated. Rejects when the server has no such job, the way
-[Connection.openTable](Connection.md#opentable) does for a missing table.
-
-The returned [Job](Job.md) answers for its own state, specification,
-result, failure and event history, so there is no separate
-connection-level call for any of them.
-
-#### Parameters
-
-* **jobId**: `string`
-
-#### Returns
-
-`Promise`&lt;[`Job`](Job.md)&gt;
-
-***
-
 ### openMaterializedView()
 
 ```ts
@@ -686,7 +660,7 @@ a "not supported" error.
 
 ***
 
-### ~~tableNames()~~
+### tableNames()
 
 #### tableNames(options)
 
@@ -708,10 +682,6 @@ Tables will be returned in lexicographical order.
 
 `Promise`&lt;`string`[]&gt;
 
-##### Deprecated
-
-Use [Connection.listTables](Connection.md#listtables) instead.
-
 #### tableNames(namespacePath, options)
 
 ```ts
@@ -734,7 +704,3 @@ Tables will be returned in lexicographical order.
 ##### Returns
 
 `Promise`&lt;`string`[]&gt;
-
-##### Deprecated
-
-Use [Connection.listTables](Connection.md#listtables) instead.

docs/src/js/classes/Job.md

@@ -8,116 +8,28 @@
 
 A handle to an operation that may still be running.
 
-The operation may already be complete when the handle is created.
+## Constructors
 
-The detail getters read what the handle last observed. Submitting an
-operation returns only a job id, so populating them eagerly would cost an
-extra round trip on every call:
+### new Job()
 
-- [Job.refresh](Job.md#refresh) and [Job.status](Job.md#status) fetch the whole record.
-- [Job.wait](Job.md#wait) records the terminal state it establishes, but not the
-  rest of the record.
-- Everything is null until one of those runs.
+```ts
+new Job(): Job
+```
+
+#### Returns
+
+[`Job`](Job.md)
 
 ## Accessors
 
-### creationMs
-
-```ts
-get creationMs(): null | number
-```
-
-When the job was created, in milliseconds since the epoch.
-
-#### Returns
-
-`null` \| `number`
-
-***
-
-### failure
-
-```ts
-get failure(): null | JobFailureInfo
-```
-
-Why the job failed, when it failed and the server reports a reason.
-
-#### Returns
-
-`null` \| [`JobFailureInfo`](../interfaces/JobFailureInfo.md)
-
-***
-
 ### id
 
 ```ts
 get id(): null | string
 ```
 
-Identifies the operation on the server that is running it.
-
-Operations that run in this process have no server id. The value is
-opaque: parsing it or storing it to resume the job later is not supported.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
-### jobType
-
-```ts
-get jobType(): null | string
-```
-
-The job's type, as the server names it. Null for an in-process job, which
-has no server-side record.
-
-#### Returns
-
-`null` \| `string`
-
-***
-
-### result
-
-```ts
-get result(): any
-```
-
-The job-type-specific terminal result. Null until the job succeeds, so a
-job that never terminates reports its progress through [Job.events](Job.md#events)
-instead.
-
-#### Returns
-
-`any`
-
-***
-
-### spec
-
-```ts
-get spec(): any
-```
-
-The job-type-specific specification it was submitted with.
-
-#### Returns
-
-`any`
-
-***
-
-### state
-
-```ts
-get state(): null | string
-```
-
-The last observed lifecycle state, without contacting the backend.
+Identifies the operation on the server that is running it. Operations
+that run in this process have no server id. The value is opaque.
 
 #### Returns
 
@@ -139,61 +51,18 @@ Request cancellation. Cancelling a finished operation is a no-op.
 
 ***
 
-### events()
-
-```ts
-events(options?): Promise<Table<any>>
-```
-
-This job's recorded lifecycle events.
-
-Where the getters above report a terminal result only once the job reaches
-one, events are written as the job runs and outlive the workers that
-produced them. A distributed job records a `claim`/`claim_complete` pair
-per unit of work, each carrying `rows_processed`, so a job that never
-finishes still accounts for what it did.
-
-The server caps results at 1000 rows by default and 10,000 at most, and
-truncates without saying so, so pass `limit` for a job that emits an event
-per fragment. `filter` is a SQL-like expression over the `state`,
-`updated_by`, `emitted_from`, `emitted_by`, and `claim_entity` columns.
-
-#### Parameters
-
-* **options?**: [`JobEventsOptions`](../interfaces/JobEventsOptions.md)
-
-#### Returns
-
-`Promise`&lt;`Table`&lt;`any`&gt;&gt;
-
-***
-
-### refresh()
-
-```ts
-refresh(): Promise<void>
-```
-
-Ask the backend for this job's current state, and for a server-side job
-its full record, then cache it for the getters above.
-
-#### Returns
-
-`Promise`&lt;`void`&gt;
-
-***
-
 ### status()
 
 ```ts
 status(): Promise<string>
 ```
 
-The operation's current lifecycle state: "running", "finished", "failed",
-or "cancelled".
+The operation's current lifecycle state: "running", "finished",
+"failed", or "cancelled".
 
-A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject on a
-terminal failure state. Also refreshes the getters above.
+A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject
+on a terminal failure state. States a newer server reports that this
+client version does not know pass through as-is.
 
 #### Returns
 
@@ -201,22 +70,6 @@ terminal failure state. Also refreshes the getters above.
 
 ***
 
-### toString()
-
-```ts
-toString(): string
-```
-
-Every field the handle currently knows, one per line, with the JSON
-payloads indented -- a refresh job's spec and result are the point of
-printing it.
-
-#### Returns
-
-`string`
-
-***
-
 ### wait()
 
 ```ts

docs/src/js/classes/MergeInsertBuilder.md

@@ -141,7 +141,7 @@ Currently this causes multiple copies of the row to be created
 but that behavior is subject to change.
 
 An optional condition may be specified.  If it is, then only
-matched rows that satisfy the condition will be updated.  Any
+matched rows that satisfy the condtion will be updated.  Any
 rows that do not satisfy the condition will be left as they
 are.  Failing to satisfy the condition does not cause a
 "matched row" to become a "not matched" row.

docs/src/js/classes/Table.md

@@ -137,20 +137,6 @@ containing the new version number of the table after altering the columns.
 
 ***
 
-### blobColumns()
-
-```ts
-abstract blobColumns(): Promise<string[]>
-```
-
-Blob v2 columns, including nested dotted paths.
-
-#### Returns
-
-`Promise`&lt;`string`[]&gt;
-
-***
-
 ### branches()
 
 ```ts
@@ -513,54 +499,6 @@ Drop an index from the table.
 
 ***
 
-### fetchBlobFiles()
-
-```ts
-abstract fetchBlobFiles(column, rowIds): Promise<(null | BlobFile)[]>
-```
-
-Opens lazy blob handles for `column` at the given row IDs using the
-table's current checkout.
-
-Preserves input order, duplicates, and nulls. Use this for large payloads.
-See [Table.fetchBlobs](Table.md#fetchblobs) for row-ID validity across versions.
-
-#### Parameters
-
-* **column**: `string`
-
-* **rowIds**: readonly (`number` \| `bigint`)[]
-
-#### Returns
-
-`Promise`&lt;(`null` \| [`BlobFile`](BlobFile.md))[]&gt;
-
-***
-
-### fetchBlobs()
-
-```ts
-abstract fetchBlobs(column, rowIds): Promise<(null | Buffer)[]>
-```
-
-Bytes for `column` at row IDs from [Query.withRowId](Query.md#withrowid).
-
-Reads the table's current checkout. IDs from another version can fail after
-compaction unless stable row ids are enabled. Results keep input order and
-duplicates. Null blobs are `null`. Empty blobs are empty buffers.
-
-#### Parameters
-
-* **column**: `string`
-
-* **rowIds**: readonly (`number` \| `bigint`)[]
-
-#### Returns
-
-`Promise`&lt;(`null` \| `Buffer`)[]&gt;
-
-***
-
 ### flushLsm()
 
 ```ts
@@ -738,17 +676,9 @@ List all the versions of the table
 abstract mergeInsert(on): MergeInsertBuilder
 ```
 
-Create a [MergeInsertBuilder](MergeInsertBuilder.md), which combines new data with the
-existing table in a single transaction — inserting, updating and deleting
-rows depending on how they match.
-
 #### Parameters
 
 * **on**: `string` \| `string`[]
-    The column, or columns, to match source rows against target
-    rows on. Typically a key or id column. Several columns match on the
-    composite key: a source row updates a target row only when it agrees on
-    every one of them.
 
 #### Returns
 
@@ -1012,7 +942,7 @@ Get the schema of the table.
 abstract search(
    query,
    queryType?,
-   ftsColumns?): Query | VectorQuery | AutoQuery
+   ftsColumns?): Query | VectorQuery
 ```
 
 Create a search query to find the nearest neighbors
@@ -1034,7 +964,7 @@ of the given query
 
 #### Returns
 
-[`Query`](Query.md) \| [`VectorQuery`](VectorQuery.md) \| [`AutoQuery`](AutoQuery.md)
+[`Query`](Query.md) \| [`VectorQuery`](VectorQuery.md)
 
 ***
 
@@ -1328,7 +1258,7 @@ value is 0")
 Note: if your condition is something like "some_id_column == 7" and
 you are updating many rows (with different ids) then you will get
 better performance with a single [`merge_insert`] call instead of
-repeatedly calling this method.
+repeatedly calilng this method.
 
 ##### Parameters
 
@@ -1362,18 +1292,6 @@ abstract updateFieldMetadata(updates): Promise<UpdateFieldMetadataResult>
 
 Update per-field (column) metadata.
 
-The following keys are treated specially, by convention, and should be
-used when appropriate:
-
-- `lancedb:description`: for a human-readable description of a field.
-- `lancedb:tag:<name>`: for a user-defined key-value tag, where the suffix
-  names the tag category; e.g. `lancedb:tag:model: "clip"`.
-- `lancedb:logical-column`: for a column grouping; e.g. `feature_v1` and
-  `feature_v2` might be in the same logical column.
-- `lancedb:status`: for status options (`production`, `candidate`,
-  `deprecated`, `archived`) to designate the current life cycle state of
-  this column.
-
 #### Parameters
 
 * **updates**: [`FieldMetadataUpdate`](../interfaces/FieldMetadataUpdate.md)[]

docs/src/js/functions/blob.md

@@ -1,55 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / blob
-
-# Function: blob()
-
-```ts
-function blob(name, options): Field
-```
-
-Declares a `lance.blob.v2` column.
-
-Query results are descriptors, not payload bytes. Use [Table.fetchBlobs](../classes/Table.md#fetchblobs)
-or [Table.fetchBlobFiles](../classes/Table.md#fetchblobfiles) to read bytes.
-
-## Parameters
-
-* **name**: `string`
-
-* **options**: [`BlobOptions`](../type-aliases/BlobOptions.md) = `{}`
-
-## Returns
-
-`Field`
-
-## Example
-
-```ts
-import { readFile } from "node:fs/promises";
-import { Field, Int64, Schema } from "apache-arrow";
-import { blob, connect } from "@lancedb/lancedb";
-
-const db = await connect("./data");
-const video = await readFile("clip.mp4");
-const table = await db.createTable(
-  "videos",
-  [{ id: 1n, video }],
-  {
-    schema: new Schema([
-      new Field("id", new Int64()),
-      blob("video"),
-    ]),
-  },
-);
-
-const rows = await table.query().select(["id"]).withRowId().toArray();
-const rowIds = rows.map((row) => row._rowid as bigint);
-const bytes = await table.fetchBlobs("video", rowIds);
-
-const [handle] = await table.fetchBlobFiles("video", rowIds);
-const size = handle!.size();
-const header = await handle!.readRange(0n, size < 65536n ? size : 65536n);
-```

docs/src/js/functions/isBlobField.md

@@ -1,22 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / isBlobField
-
-# Function: isBlobField()
-
-```ts
-function isBlobField(field): boolean
-```
-
-Checks for the `lance.blob.v2` extension marker. Does not validate the
-field's storage type.
-
-## Parameters
-
-* **field**: `Field`<`any`>
-
-## Returns
-
-`boolean`

docs/src/js/globals.md

@@ -18,8 +18,6 @@
 
 ## Classes
 
-- [AutoQuery](classes/AutoQuery.md)
-- [BlobFile](classes/BlobFile.md)
 - [BooleanQuery](classes/BooleanQuery.md)
 - [BoostQuery](classes/BoostQuery.md)
 - [BranchContents](classes/BranchContents.md)
@@ -97,13 +95,11 @@
 - [IvfFlatOptions](interfaces/IvfFlatOptions.md)
 - [IvfPqOptions](interfaces/IvfPqOptions.md)
 - [IvfRqOptions](interfaces/IvfRqOptions.md)
-- [JobEventsOptions](interfaces/JobEventsOptions.md)
+- [JobDescription](interfaces/JobDescription.md)
 - [JobFailureInfo](interfaces/JobFailureInfo.md)
 - [JobInfo](interfaces/JobInfo.md)
 - [ListNamespacesOptions](interfaces/ListNamespacesOptions.md)
 - [ListNamespacesResponse](interfaces/ListNamespacesResponse.md)
-- [ListTablesOptions](interfaces/ListTablesOptions.md)
-- [ListTablesResponse](interfaces/ListTablesResponse.md)
 - [LsmStats](interfaces/LsmStats.md)
 - [LsmWriteSpec](interfaces/LsmWriteSpec.md)
 - [MaterializedViewDefinition](interfaces/MaterializedViewDefinition.md)
@@ -144,7 +140,6 @@
 
 - [AnalyzePlanDistributedMetrics](type-aliases/AnalyzePlanDistributedMetrics.md)
 - [BaseTokenizer](type-aliases/BaseTokenizer.md)
-- [BlobOptions](type-aliases/BlobOptions.md)
 - [Data](type-aliases/Data.md)
 - [DataLike](type-aliases/DataLike.md)
 - [FieldLike](type-aliases/FieldLike.md)
@@ -160,11 +155,9 @@
 ## Functions
 
 - [RecordBatchIterator](functions/RecordBatchIterator.md)
-- [blob](functions/blob.md)
 - [connect](functions/connect.md)
 - [connectNamespace](functions/connectNamespace.md)
 - [instrumentLanceDbMetrics](functions/instrumentLanceDbMetrics.md)
-- [isBlobField](functions/isBlobField.md)
 - [makeArrowTable](functions/makeArrowTable.md)
 - [packBits](functions/packBits.md)
 - [permutationBuilder](functions/permutationBuilder.md)

docs/src/js/interfaces/FieldMetadataUpdate.md

@@ -17,8 +17,7 @@ metadata: Record<string, null | string>;
 ```
 
 Metadata key/value pairs. Merged into the field's existing metadata by
-default; a value of `null` deletes that key. See
-[Table.updateFieldMetadata](../classes/Table.md#updatefieldmetadata) for the conventional `lancedb:*` keys.
+default; a value of `null` deletes that key.
 
 ***
 

docs/src/js/interfaces/HnswPqOptions.md

@@ -118,7 +118,7 @@ Number of sub-vectors of PQ.
 This value controls how much the vector is compressed during the quantization step.
 The more sub vectors there are the less the vector is compressed.  The default is
 the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divided by 8.
+by 16 we use the dimension divded by 8.
 
 The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
 us to use efficient SIMD instructions.

docs/src/js/interfaces/IndexOptions.md

@@ -16,7 +16,7 @@ optional config: Index;
 
 Advanced index configuration
 
-This option allows you to specify a specific index to create and also
+This option allows you to specify a specfic index to create and also
 allows you to pass in configuration for training the index.
 
 See the static methods on Index for details on the various index types.

docs/src/js/interfaces/IvfPqOptions.md

@@ -112,7 +112,7 @@ Number of sub-vectors of PQ.
 This value controls how much the vector is compressed during the quantization step.
 The more sub vectors there are the less the vector is compressed.  The default is
 the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divided by 8.
+by 16 we use the dimension divded by 8.
 
 The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
 us to use efficient SIMD instructions.

docs/src/js/interfaces/JobDescription.md

@@ -0,0 +1,66 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / JobDescription
+
+# Interface: JobDescription
+
+A described job from `Connection.getJob`.
+
+## Properties
+
+### creationMs
+
+```ts
+creationMs: number;
+```
+
+When the job was created, in milliseconds since the epoch.
+
+***
+
+### failure?
+
+```ts
+optional failure: JobFailureInfo;
+```
+
+Why the job failed, when the job is failed and the server reports a
+reason.
+
+***
+
+### jobId
+
+```ts
+jobId: string;
+```
+
+***
+
+### jobType
+
+```ts
+jobType: string;
+```
+
+***
+
+### specJson?
+
+```ts
+optional specJson: string;
+```
+
+The job-type-specific specification as a JSON string, when present.
+
+***
+
+### state
+
+```ts
+state: string;
+```
+
+Lifecycle state: "running", "finished", "failed", or "cancelled".

docs/src/js/interfaces/JobEventsOptions.md

@@ -1,29 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / JobEventsOptions
-
-# Interface: JobEventsOptions
-
-Which of a job's events [Job.events](../classes/Job.md#events) returns.
-
-## Properties
-
-### filter?
-
-```ts
-optional filter: string;
-```
-
-SQL-like filter over the event columns.
-
-***
-
-### limit?
-
-```ts
-optional limit: number;
-```
-
-Maximum event rows to return, up to the server maximum of 10,000.

docs/src/js/interfaces/JobInfo.md

@@ -26,7 +26,7 @@ When the job was created, in milliseconds since the epoch.
 jobId: string;
 ```
 
-The job id -- what `Connection.openJob` and `Connection.cancelJob`
+The job id -- what `Connection.getJob` and `Connection.cancelJob`
 accept.
 
 ***

docs/src/js/interfaces/ListTablesOptions.md

@@ -1,34 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / ListTablesOptions
-
-# Interface: ListTablesOptions
-
-## Properties
-
-### limit?
-
-```ts
-optional limit: number;
-```
-
-An upper bound on how many tables to return.
-
-A page may hold fewer than this and still not be the last one, so keep
-going while the response carries a page token rather than while pages are
-full.
-
-***
-
-### pageToken?
-
-```ts
-optional pageToken: string;
-```
-
-Token from a previous response, to resume listing where it left off.
-
-The token is opaque: it carries whatever the database needs to resume, and
-callers should not construct or interpret one.

docs/src/js/interfaces/ListTablesResponse.md

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

docs/src/js/interfaces/MaterializedViewDefinition.md

@@ -50,16 +50,6 @@ projections: [string, string][];
 
 ***
 
-### sourceNamespace
-
-```ts
-sourceNamespace: string[];
-```
-
-Namespace holding the source table; empty is the root namespace.
-
-***
-
 ### sourceTable
 
 ```ts

docs/src/js/interfaces/TableNamesOptions.md

@@ -4,16 +4,11 @@
 
 [@lancedb/lancedb](../globals.md) / TableNamesOptions
 
-# Interface: ~~TableNamesOptions~~
-
-## Deprecated
-
-Use [ListTablesOptions](ListTablesOptions.md) with [Connection.listTables](../classes/Connection.md#listtables)
-instead.
+# Interface: TableNamesOptions
 
 ## Properties
 
-### ~~limit?~~
+### limit?
 
 ```ts
 optional limit: number;
@@ -23,7 +18,7 @@ An optional limit to the number of results to return.
 
 ***
 
-### ~~startAfter?~~
+### startAfter?
 
 ```ts
 optional startAfter: string;

docs/src/js/namespaces/embedding/functions/getRegistry.md

@@ -10,12 +10,16 @@
 function getRegistry(): EmbeddingFunctionRegistry
 ```
 
-Get the global embedding function registry.
-
-LanceDB built-in providers are initialized when this public API is first
-used, so importing the root package does not change automatic search
-selection for tables without embedding metadata.
+Utility function to get the global instance of the registry
 
 ## Returns
 
 [`EmbeddingFunctionRegistry`](../classes/EmbeddingFunctionRegistry.md)
+
+`EmbeddingFunctionRegistry` The global instance of the registry
+
+## Example
+
+```ts
+const registry = getRegistry();
+const openai = registry.get("openai").create();

docs/src/js/type-aliases/BlobOptions.md

@@ -1,48 +0,0 @@
-[**@lancedb/lancedb**](../README.md) • **Docs**
-
-***
-
-[@lancedb/lancedb](../globals.md) / BlobOptions
-
-# Type Alias: BlobOptions
-
-```ts
-type BlobOptions: object;
-```
-
-## Type declaration
-
-### dedicatedSizeThreshold?
-
-```ts
-optional dedicatedSizeThreshold: number;
-```
-
-Max payload bytes stored in a packed sidecar before a dedicated file. Must
-be a positive safe integer.
-
-### inlineSizeThreshold?
-
-```ts
-optional inlineSizeThreshold: number;
-```
-
-Max payload bytes kept inline in the data file. Zero is allowed. Must be a
-safe integer.
-
-### nullable?
-
-```ts
-optional nullable: boolean;
-```
-
-Defaults to true.
-
-### packFileSizeThreshold?
-
-```ts
-optional packFileSizeThreshold: number;
-```
-
-Max bytes in one packed sidecar before starting another. Must be a positive
-safe integer.

docs/src/python/python.md

@@ -28,59 +28,6 @@ is also an [asynchronous API client](#connections-asynchronous).
 
 ::: lancedb.Session
 
-## Remote SQL
-
-Submit SQL against a remote LanceDB database through the connection.
-The connected database and `default_namespace_path=["public"]` are used for
-unqualified tables. Fully qualified references can still query other databases
-and namespaces available to the same deployment. `execute_query` returns a
-reader as soon as its initial result stream is available. `execute_query_async`
-returns a query handle immediately; use it to inspect progress, open a reader,
-or cancel the query. The SQL client is initialized by the first query and
-retained for the lifetime of the remote connection. Query ids are random,
-connection-scoped references rather than encoded SQL or durable resume tokens:
-
-```python
-import lancedb
-
-db = lancedb.connect(
-    "db://analytics",
-    api_key="ldb_...",
-    host_override="https://api.example.com",
-    sql_host_override="grpc+tls://sql.example.com:10026",
-)
-reader = db.execute_query(
-    """
-    SELECT events.id, accounts.name
-    FROM analytics.public.events AS events
-    JOIN users.public.accounts AS accounts ON events.user_id = accounts.id
-    """,
-    default_namespace_path=["public"],
-)
-for batch in reader:
-    print(batch.num_rows)
-
-query = db.execute_query_async("SELECT * FROM events")
-print(query.id)
-print(query.describe().status)
-for batch in query.reader():
-    print(batch.num_rows)
-
-# The async connection exposes the same lifecycle without blocking:
-# async_db = await lancedb.connect_async(
-#     "db://analytics",
-#     api_key="ldb_...",
-#     host_override="https://api.example.com",
-#     sql_host_override="grpc+tls://sql.example.com:10026",
-# )
-# reader = await async_db.execute_query("SELECT * FROM events")
-# query = await async_db.execute_query_async("SELECT * FROM events")
-# description = await async_db.describe_query(query.id)
-# async for batch in await query.reader():
-#     print(batch.num_rows)
-# await query.cancel()
-```
-
 ## Namespaces (Synchronous)
 
 A namespace-backed connection resolves tables through a
@@ -147,8 +94,6 @@ listing a storage directory.
 
 ::: lancedb.functions.OutputMapping
 
-::: lancedb.functions.AssignmentMapping
-
 ::: lancedb.functions.FunctionBinding
 
 ::: lancedb.functions.RefreshColumnResult
@@ -157,18 +102,6 @@ listing a storage directory.
 
 ::: lancedb.job.AsyncJob
 
-::: lancedb.job.JobInfo
-
-::: lancedb.job.JobDescription
-
-::: lancedb.job.JobFailureInfo
-
-::: lancedb.sql.Query
-
-::: lancedb.sql.AsyncQuery
-
-::: lancedb.sql.QueryDescription
-
 ## Materialized Views (Synchronous)
 
 ::: lancedb.materialized_view.MaterializedView
@@ -226,8 +159,6 @@ and combined with [BooleanQuery][lancedb.query.BooleanQuery].
 
 ::: lancedb.query.FullTextOperator
 
-::: lancedb.query.DocumentGranularity
-
 ::: lancedb.query.Occur
 
 ## Embeddings
@@ -290,14 +221,10 @@ tokens = list(
 Blob columns store large binary values out of line so they can be read lazily
 instead of being materialized with the rest of the row.
 
-`lancedb.BlobType` is `lance.blob.BlobType` when pylance is installed. Without
-pylance, LanceDB uses a matching `lance.blob.v2` extension type so blob columns
-still work. Queries return descriptors. Call
-[`fetch_blob_files`][lancedb.table.Table.fetch_blob_files] for lazy reads or
-[`fetch_blobs`][lancedb.table.Table.fetch_blobs] for eager bytes.
-
 ::: lancedb.blob
 
+::: lancedb.BlobType
+
 ::: lancedb._blob.BlobFile
     options:
       show_root_full_path: false
@@ -316,12 +243,6 @@ still work. Queries return descriptors. Call
 
 ::: lancedb.exceptions.MissingColumnError
 
-::: lancedb.exceptions.JobNotFoundError
-
-::: lancedb.exceptions.JobFailedError
-
-::: lancedb.exceptions.JobCancelledError
-
 ## Integrations
 
 ## Pydantic
@@ -340,8 +261,6 @@ still work. Queries return descriptors. Call
 
 ::: lancedb.streaming.StreamingDataset
 
-::: lancedb.streaming.StreamingDataLoader
-
 ::: lancedb.permutation.permutation_builder
 
 ::: lancedb.permutation.PermutationBuilder

docs/tsconfig.json

@@ -0,0 +1,17 @@
+{
+  "include": [
+    "src/*.ts",
+  ],
+  "compilerOptions": {
+    "target": "es2022",
+    "module": "nodenext",
+    "declaration": true,
+    "outDir": "./dist",
+    "strict": true,
+    "allowJs": true,
+    "resolveJsonModule": true,
+  },
+  "exclude": [
+    "./dist/*",
+  ]
+}

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.39.0-beta.6</version>
+      <version>0.38.0-beta.6</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.39.0-beta.6</version>
+    <version>0.38.0-beta.6</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>12.0.0-beta.18</lance-core.version>
+        <lance-core.version>11.0.0-beta.22</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.39.0-beta.6"
+version = "0.38.0-beta.6"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/__test__/arrow.test.ts

@@ -1,16 +1,11 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
-import * as fs from "node:fs";
-import * as vm from "node:vm";
 import * as arrow15 from "apache-arrow-15";
 import * as arrow16 from "apache-arrow-16";
 import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";
 
 import {
-  Field as CurrentField,
-  LargeBinary as CurrentLargeBinary,
-  Schema as CurrentSchema,
   Vector as CurrentVector,
   convertToTable,
   tableFromIPC as currentTableFromIPC,
@@ -41,59 +36,6 @@ function sampleRecords(): Array<Record<string, any>> {
     },
   ];
 }
-
-it("serializes an Arrow Table created in another JavaScript realm", async () => {
-  const context = vm.createContext({
-    TextDecoder,
-    TextEncoder,
-    console,
-    setTimeout,
-    clearTimeout,
-  });
-  vm.runInContext(
-    fs.readFileSync(
-      require.resolve("apache-arrow-15/Arrow.es2015.min"),
-      "utf8",
-    ),
-    context,
-  );
-  const foreignTable: unknown = vm.runInContext(
-    "Arrow.tableFromArrays({ id: new Int32Array([1, 2, 3]), text: ['foo', 'bar', 'baz'] })",
-    context,
-  );
-
-  const foreignMetadata = (
-    foreignTable as { schema: { metadata: Map<string, string> } }
-  ).schema.metadata;
-  expect(foreignMetadata).not.toBeInstanceOf(Map);
-
-  const buf = await fromDataToBuffer(
-    foreignTable as Parameters<typeof fromDataToBuffer>[0],
-  );
-  const actual = currentTableFromIPC(buf);
-
-  expect(actual.numRows).toBe(3);
-  expect(actual.getChild("id")?.toJSON()).toEqual([1, 2, 3]);
-  expect(actual.getChild("text")?.toJSON()).toEqual(["foo", "bar", "baz"]);
-});
-
-it("preserves field metadata from a provided schema", async function () {
-  const jsonMetadata = new Map([["ARROW:extension:name", "lance.json"]]);
-  const schema = new CurrentSchema([
-    new CurrentField("meta", new CurrentLargeBinary(), true, jsonMetadata),
-  ]);
-
-  const table = makeArrowTable(
-    [{ meta: Buffer.from(JSON.stringify({ source: "test" })) }],
-    { schema },
-  );
-
-  expect(table.schema.fields[0].metadata).toEqual(jsonMetadata);
-
-  const roundTripped = currentTableFromIPC(await fromTableToBuffer(table));
-  expect(roundTripped.schema.fields[0].metadata).toEqual(jsonMetadata);
-});
-
 describe.each([arrow15, arrow16, arrow17, arrow18])(
   "Arrow",
   (
@@ -573,137 +515,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         );
       });
 
-      it("will allow matching inferred types across records", function () {
-        expect(() =>
-          makeArrowTable([{ value: 1 }, { value: 2 }]),
-        ).not.toThrow();
-      });
-
-      it("will reject mismatched inferred types across records", function () {
-        expect(() => makeArrowTable([{ value: 1 }, { value: "two" }])).toThrow(
-          "Failed to infer schema for data. Previously inferred type Float64 but found Utf8 for field value at row 1. Consider providing an explicit schema.",
-        );
-      });
-
-      it("will ignore generated dictionary IDs when comparing inferred types", function () {
-        const table = makeArrowTable([{ str: "a" }, { str: "b" }], {
-          dictionaryEncodeStrings: true,
-        });
-
-        expect(table.getChild("str")?.toJSON()).toEqual(["a", "b"]);
-      });
-
-      it("will preserve null values without treating them as type mismatches", function () {
-        for (const records of [
-          [{ vector: [1, 2, 3] }, { vector: null }],
-          [{ vector: null }, { vector: [1, 2, 3] }],
-        ]) {
-          const table = makeArrowTable(records);
-
-          expect(table.numRows).toBe(2);
-          expect(table.getChild("vector")?.nullCount).toBe(1);
-        }
-      });
-
-      it("will preserve empty variable-size lists", function () {
-        for (const records of [
-          [{ items: [1] }, { items: [] }],
-          [{ items: [] }, { items: [1] }],
-        ]) {
-          const table = makeArrowTable(records);
-          expect(
-            table
-              .getChild("items")
-              ?.toJSON()
-              .map((value) => value.toJSON()),
-          ).toEqual(records.map((record) => record.items));
-        }
-      });
-
-      it("will propagate deferred evidence through nested lists", function () {
-        for (const records of [
-          [{ items: [1] }, { items: [null] }],
-          [{ items: [null] }, { items: [1] }],
-          [{ items: [null, 1] }, { items: [2, null] }],
-        ]) {
-          const table = makeArrowTable(records);
-          expect(
-            table
-              .getChild("items")
-              ?.toJSON()
-              .map((value) => value.toJSON()),
-          ).toEqual(records.map((record) => record.items));
-        }
-
-        const nestedRecords = [{ items: [[1]] }, { items: [[null]] }];
-        const nestedTable = makeArrowTable(nestedRecords);
-        expect(
-          nestedTable
-            .getChild("items")
-            ?.toJSON()
-            .map((value) =>
-              value
-                .toJSON()
-                .map((nestedValue: { toJSON: () => unknown[] }) =>
-                  nestedValue.toJSON(),
-                ),
-            ),
-        ).toEqual(nestedRecords.map((record) => record.items));
-      });
-
-      it("will reject incompatible deferred evidence within a list", function () {
-        for (const items of [
-          [[], 1],
-          [1, []],
-          [[null], 1],
-          [1, [null]],
-        ]) {
-          expect(() => makeArrowTable([{ items }])).toThrow(
-            "Failed to infer data type for field items at row 0.",
-          );
-        }
-      });
-
-      it("will reject empty fixed-size lists", function () {
-        expect(() =>
-          makeArrowTable([{ vector: [1, 2, 3] }, { vector: [] }]),
-        ).toThrow(
-          "Failed to infer schema for data. Previously inferred type FixedSizeList[3]<Float32> but found List[0] for field vector at row 1.",
-        );
-      });
-
-      it("will reject inferred leaf and branch shape changes", function () {
-        expect(() =>
-          makeArrowTable([{ value: 1 }, { value: { nested: 2 } }]),
-        ).toThrow(
-          "Failed to infer schema for data. Previously inferred type Float64 but found Struct for field value at row 1.",
-        );
-        expect(() =>
-          makeArrowTable([{ value: { nested: 1 } }, { value: 2 }]),
-        ).toThrow(
-          "Failed to infer schema for data. Previously inferred type Struct but found Float64 for field value at row 1.",
-        );
-      });
-
-      it("will allow null values around inferred struct values", function () {
-        for (const { records, nullIndex } of [
-          {
-            records: [{ value: null }, { value: { nested: 2 } }],
-            nullIndex: 0,
-          },
-          {
-            records: [{ value: { nested: 1 } }, { value: null }],
-            nullIndex: 1,
-          },
-        ]) {
-          const table = makeArrowTable(records);
-          const values = table.getChild("value");
-
-          expect(values?.nullCount).toBe(1);
-          expect(values?.get(nullIndex)).toBeNull();
-        }
-      });
-
       it("will allow a schema to be provided", async function () {
         await checkTableCreation(
           async (records, _, schema) =>

nodejs/__test__/blob.test.ts

@@ -1,185 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import { Field, Int64, List, Schema, Struct, Utf8 } from "apache-arrow";
-import { makeArrowTable } from "../lancedb/arrow";
-import { BlobFile, blob, coerceBlobValue, isBlobField } from "../lancedb/blob";
-
-describe("blob()", () => {
-  it("marks the field as lance.blob.v2", () => {
-    const field = blob("image", { nullable: false });
-    expect(field.nullable).toBe(false);
-    expect(isBlobField(field)).toBe(true);
-    expect(field.metadata.get("ARROW:extension:name")).toBe("lance.blob.v2");
-  });
-
-  it("writes encoding thresholds as field metadata", () => {
-    const field = blob("video", {
-      inlineSizeThreshold: 1024,
-      dedicatedSizeThreshold: 2 * 1024 * 1024,
-      packFileSizeThreshold: 64 * 1024 * 1024,
-    });
-    expect(
-      field.metadata.get("lance-encoding:blob-inline-size-threshold"),
-    ).toBe("1024");
-    expect(
-      field.metadata.get("lance-encoding:blob-dedicated-size-threshold"),
-    ).toBe(String(2 * 1024 * 1024));
-    expect(
-      field.metadata.get("lance-encoding:blob-pack-file-size-threshold"),
-    ).toBe(String(64 * 1024 * 1024));
-  });
-
-  it("rejects invalid thresholds", () => {
-    expect(() => blob("image", { inlineSizeThreshold: -1 })).toThrow(
-      /inlineSizeThreshold must be non-negative/,
-    );
-    expect(() => blob("image", { dedicatedSizeThreshold: 0 })).toThrow(
-      /dedicatedSizeThreshold must be positive/,
-    );
-    expect(() => blob("image", { packFileSizeThreshold: 1.5 })).toThrow(
-      /packFileSizeThreshold must be a safe integer/,
-    );
-    expect(() =>
-      blob("image", { dedicatedSizeThreshold: Number.MAX_SAFE_INTEGER + 1 }),
-    ).toThrow(/dedicatedSizeThreshold must be a safe integer/);
-  });
-});
-
-describe("coerceBlobValue", () => {
-  it.each([
-    ["Buffer", Buffer.from("x"), { data: Buffer.from("x"), uri: null }],
-    [
-      "Uint8Array",
-      new Uint8Array([120]),
-      { data: new Uint8Array([120]), uri: null },
-    ],
-    ["URI string", "s3://bucket/key", { data: null, uri: "s3://bucket/key" }],
-    [
-      "data struct",
-      { data: Buffer.from("y") },
-      { data: Buffer.from("y"), uri: null },
-    ],
-    [
-      "uri struct",
-      { uri: "s3://bucket/key" },
-      { data: null, uri: "s3://bucket/key" },
-    ],
-    ["null", null, null],
-  ])("accepts %s", (_name, input, expected) => {
-    expect(coerceBlobValue(input)).toEqual(expected);
-  });
-
-  it.each([
-    ["empty URI", "", /uri cannot be empty/],
-    ["object without data or uri", { position: 0 }, /data' or 'uri/],
-    [
-      "Int16Array",
-      new Int16Array([1]),
-      /Blob data must be Buffer or Uint8Array/,
-    ],
-    [
-      "both data and uri",
-      { data: Buffer.from("y"), uri: "s3://bucket/key" },
-      /exactly one of 'data' or 'uri'/,
-    ],
-    [
-      "neither data nor uri",
-      { data: null, uri: null },
-      /exactly one of 'data' or 'uri'/,
-    ],
-  ])("rejects %s", (_name, input, message) => {
-    expect(() => coerceBlobValue(input)).toThrow(message);
-  });
-});
-
-describe("BlobFile", () => {
-  it("rejects constructing BlobFile without a native handle", () => {
-    expect(() => new (BlobFile as unknown as { new (): BlobFile })()).toThrow(
-      /fetchBlobFiles/,
-    );
-  });
-});
-
-describe("makeArrowTable blob columns", () => {
-  it("coerces Buffer input onto a blob field", () => {
-    const schema = new Schema([
-      new Field("id", new Int64(), true),
-      blob("image"),
-    ]);
-    const table = makeArrowTable([{ id: 1n, image: Buffer.from("hello") }], {
-      schema,
-    });
-    expect(isBlobField(table.schema.fields[1])).toBe(true);
-    const image = table.getChild("image")!;
-    expect(image.nullCount).toBe(0);
-    expect(image.getChild("uri")!.get(0)).toBeNull();
-    expect(image.getChild("data")!.nullCount).toBe(0);
-    expect(Buffer.from(image.getChild("data")!.get(0)!).toString()).toBe(
-      "hello",
-    );
-  });
-
-  it("coerces Buffer elements inside a list and keeps null slots", () => {
-    const schema = new Schema([
-      new Field("id", new Int64(), true),
-      new Field("images", new List(blob("image")), true),
-    ]);
-    const table = makeArrowTable(
-      [
-        { id: 1n, images: [Buffer.from("a"), Buffer.from("bb")] },
-        { id: 2n, images: null },
-        { id: 3n, images: [Buffer.from("c"), null] },
-        { id: 4n, images: [] },
-      ],
-      { schema },
-    );
-    const images = table.getChild("images")!;
-    expect(images.nullCount).toBe(1);
-    const rows = images.toArray();
-    expect(rows[1]).toBeNull();
-    expect(Array.from(rows[3] as Iterable<unknown>)).toHaveLength(0);
-    const first = Array.from(rows[0] as Iterable<{ data: Uint8Array | null }>);
-    expect(Buffer.from(first[0].data!).toString()).toBe("a");
-    expect(Buffer.from(first[1].data!).toString()).toBe("bb");
-    const third = Array.from(
-      rows[2] as Iterable<{ data: Uint8Array | null } | null>,
-    );
-    expect(Buffer.from(third[0]!.data!).toString()).toBe("c");
-    expect(third[1]).toBeNull();
-  });
-
-  it("coerces Buffer fields inside list structs", () => {
-    const schema = new Schema([
-      new Field("id", new Int64(), true),
-      new Field(
-        "items",
-        new List(
-          new Field(
-            "item",
-            new Struct([new Field("name", new Utf8(), true), blob("image")]),
-            true,
-          ),
-        ),
-        true,
-      ),
-    ]);
-    const table = makeArrowTable(
-      [
-        {
-          id: 1n,
-          items: [{ name: "one", image: Buffer.from("alpha") }],
-        },
-      ],
-      { schema },
-    );
-    const items = Array.from(
-      table.getChild("items")!.toArray()[0] as Iterable<{
-        name: string;
-        image: { data: Uint8Array | null };
-      }>,
-    );
-    expect(items[0].name).toBe("one");
-    expect(Buffer.from(items[0].image.data!).toString()).toBe("alpha");
-  });
-});

nodejs/__test__/connection.test.ts

@@ -4,13 +4,7 @@
 import { readdirSync } from "fs";
 import { Field, Float64, Schema } from "apache-arrow";
 import * as tmp from "tmp";
-import {
-  Connection,
-  ListTablesResponse,
-  Table,
-  connect,
-  connectNamespace,
-} from "../lancedb";
+import { Connection, Table, connect, connectNamespace } from "../lancedb";
 import { LocalTable } from "../lancedb/table";
 
 describe("when connecting", () => {
@@ -53,7 +47,6 @@ describe("given a connection", () => {
     await db.close();
     expect(db.isOpen()).toBe(false);
     await expect(db.tableNames()).rejects.toThrow("Connection is closed");
-    await expect(db.listTables()).rejects.toThrow("Connection is closed");
     await expect(db.renameTable("a", "b")).rejects.toThrow(
       "Connection is closed",
     );
@@ -136,66 +129,6 @@ describe("given a connection", () => {
     expect(tables).toEqual(["b", "c"]);
   });
 
-  it("should respect limit and page token when listing tables", async () => {
-    const db = await connect(tmpDir.name);
-
-    await db.createTable("b", [{ id: 1 }]);
-    await db.createTable("a", [{ id: 1 }]);
-    await db.createTable("c", [{ id: 1 }]);
-
-    const all = await db.listTables();
-    expect(all.tables).toEqual(["a", "b", "c"]);
-    expect(all.pageToken).toBeUndefined();
-
-    const first = await db.listTables({ limit: 1 });
-    expect(first.tables).toEqual(["a"]);
-    expect(first.pageToken).toBeDefined();
-
-    const second = await db.listTables({
-      limit: 1,
-      pageToken: first.pageToken,
-    });
-    expect(second.tables).toEqual(["b"]);
-  });
-
-  it("should visit every table exactly once when walking pages", async () => {
-    const db = await connect(tmpDir.name);
-
-    const created = ["a", "b", "c", "d", "e"];
-    for (const name of created) {
-      await db.createTable(name, [{ id: 1 }]);
-    }
-
-    const seen: string[] = [];
-    let pageToken: string | undefined = undefined;
-    do {
-      const page: ListTablesResponse = await db.listTables({
-        limit: 2,
-        pageToken,
-      });
-      seen.push(...page.tables);
-      pageToken = page.pageToken;
-    } while (pageToken);
-
-    expect(seen).toEqual(created);
-  });
-
-  it("should list tables in a namespace", async () => {
-    const db = await connect(tmpDir.name, {
-      // biome-ignore lint/style/useNamingConvention: opaque backend property key, must match Rust
-      namespaceClientProperties: { manifest_enabled: "true" },
-    });
-    await db.createNamespace(["child"]);
-    await db.createTable("nested", [{ id: 1 }], ["child"]);
-
-    await expect(db.listTables(["child"])).resolves.toEqual(
-      expect.objectContaining({ tables: ["nested"] }),
-    );
-    await expect(db.listTables()).resolves.toEqual(
-      expect.objectContaining({ tables: [] }),
-    );
-  });
-
   it("should create tables in v2 mode", async () => {
     const db = await connect(tmpDir.name);
     const data = [...Array(10000).keys()].map((i) => ({ id: i }));

nodejs/__test__/embedding.test.ts

@@ -187,58 +187,6 @@ describe("embedding functions", () => {
     const vector0 = JSON.parse(JSON.stringify(arr[0].vector));
     expect(vector0).toEqual([1, 2, 3]);
   });
-  it("should append multiple Python embeddings with the same alias", async () => {
-    @register("python-mock")
-    // biome-ignore lint/correctness/noUnusedVariables: the decorator registers this class
-    class MockEmbeddingFunction extends EmbeddingFunction<string> {
-      ndims() {
-        return 3;
-      }
-      embeddingDataType(): Float {
-        return new Float32();
-      }
-      async computeQueryEmbeddings(_data: string) {
-        return [1, 2, 3];
-      }
-      async computeSourceEmbeddings(data: string[]) {
-        return data.map((value) =>
-          value === "hello world" ? [1, 2, 3] : [4, 5, 6],
-        );
-      }
-    }
-
-    const metadata = new Map([
-      [
-        "embedding_functions",
-        '[{"source_column":"text1","vector_column":"vector1","name":"python-mock","model":{}},{"source_column":"text2","vector_column":"vector2","name":"python-mock","model":{}}]',
-      ],
-    ]);
-    const schema = new Schema(
-      [
-        new Field("text1", new Utf8(), true),
-        new Field("text2", new Utf8(), true),
-        new Field(
-          "vector1",
-          new FixedSizeList(3, new Field("item", new Float32(), true)),
-          true,
-        ),
-        new Field(
-          "vector2",
-          new FixedSizeList(3, new Field("item", new Float32(), true)),
-          true,
-        ),
-      ],
-      metadata,
-    );
-
-    const db = await connect(tmpDir.name);
-    const table = await db.createEmptyTable("test", schema);
-    await table.add([{ text1: "hello world", text2: "goodbye world" }]);
-
-    const rows = await table.query().toArray();
-    expect(JSON.parse(JSON.stringify(rows[0].vector1))).toEqual([1, 2, 3]);
-    expect(JSON.parse(JSON.stringify(rows[0].vector2))).toEqual([4, 5, 6]);
-  });
 
   it("should append generated vectors to a non-nullable schema", async () => {
     @register("non_nullable_schema_test")

nodejs/__test__/embedding_registry.test.ts

@@ -1,95 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import { execFileSync } from "node:child_process";
-import { resolve } from "node:path";
-
-import type { OpenAIEmbeddingFunction } from "../lancedb/embedding/openai";
-import type { EmbeddingFunctionRegistry } from "../lancedb/embedding/registry";
-
-type EmbeddingModule = typeof import("../lancedb/embedding");
-type OpenAIModule = typeof import("../lancedb/embedding/openai");
-type RegistryModule = typeof import("../lancedb/embedding/registry");
-
-describe("embedding function registry", () => {
-  const registries: EmbeddingFunctionRegistry[] = [];
-
-  afterEach(() => {
-    for (const registry of registries) {
-      registry.reset();
-    }
-    registries.length = 0;
-  });
-
-  it("defers built-in providers until the public registry API is used", () => {
-    jest.isolateModules(() => {
-      const embedding = require("../lancedb/embedding") as EmbeddingModule;
-      const { getRegistry: getInternalRegistry } =
-        require("../lancedb/embedding/registry") as RegistryModule;
-      const registry = getInternalRegistry();
-      registries.push(registry);
-
-      expect(registry.length()).toBe(0);
-      expect(embedding.getRegistry()).toBe(registry);
-      expect(registry.get("openai")).toBeDefined();
-      expect(registry.get("huggingface")).toBeDefined();
-    });
-  });
-
-  it("preserves automatic FTS search in a fresh process", () => {
-    execFileSync(
-      process.execPath,
-      [resolve(__dirname, "fixtures", "auto_fts_search.cjs")],
-      { stdio: "pipe" },
-    );
-  });
-
-  it("shares registrations across duplicated provider module graphs", () => {
-    let registeringRegistry: EmbeddingFunctionRegistry | undefined;
-    let latestOpenAIConstructor: typeof OpenAIEmbeddingFunction | undefined;
-
-    jest.isolateModules(() => {
-      require("../lancedb/embedding/openai");
-      const { getRegistry } =
-        require("../lancedb/embedding/registry") as RegistryModule;
-      registeringRegistry = getRegistry();
-      registries.push(registeringRegistry);
-      expect(registeringRegistry.get("openai")).toBeDefined();
-    });
-
-    expect(() => {
-      jest.isolateModules(() => {
-        const { OpenAIEmbeddingFunction } =
-          require("../lancedb/embedding/openai") as OpenAIModule;
-        latestOpenAIConstructor = OpenAIEmbeddingFunction;
-        const { getRegistry } =
-          require("../lancedb/embedding/registry") as RegistryModule;
-        registries.push(getRegistry());
-      });
-    }).not.toThrow();
-
-    const previousApiKey = process.env.OPENAI_API_KEY;
-    process.env.OPENAI_API_KEY = "test";
-    try {
-      const latestOpenAI = registeringRegistry!
-        .get<OpenAIEmbeddingFunction>("openai")!
-        .create();
-      expect(latestOpenAI).toBeInstanceOf(latestOpenAIConstructor!);
-    } finally {
-      if (previousApiKey === undefined) {
-        delete process.env.OPENAI_API_KEY;
-      } else {
-        process.env.OPENAI_API_KEY = previousApiKey;
-      }
-    }
-
-    jest.isolateModules(() => {
-      const { getRegistry } =
-        require("../lancedb/embedding") as EmbeddingModule;
-      const publicRegistry = getRegistry();
-      registries.push(publicRegistry);
-      expect(publicRegistry).toBe(registeringRegistry);
-      expect(publicRegistry.get("openai")).toBeDefined();
-    });
-  });
-});

nodejs/__test__/fixtures/auto_fts_search.cjs

@@ -1,33 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-const assert = require("node:assert/strict");
-const tmp = require("tmp");
-const { connect, embedding, Index } = require("../../dist");
-const { getRegistry } = require("../../dist/embedding/registry");
-
-async function main() {
-  assert.equal(typeof embedding.getRegistry, "function");
-  assert.equal(getRegistry().length(), 0);
-  assert.equal(embedding.getRegistry(), getRegistry());
-  assert.equal(getRegistry().length(), 2);
-
-  const dir = tmp.dirSync({ unsafeCleanup: true });
-  let db;
-  try {
-    db = await connect(dir.name);
-    const table = await db.createTable("docs", [{ text: "hello world" }]);
-    await table.createIndex("text", { config: Index.fts() });
-
-    const rows = await table.search("hello").toArray();
-    assert.equal(rows[0].text, "hello world");
-  } finally {
-    db?.close();
-    dir.removeCallback();
-  }
-}
-
-main().catch((error) => {
-  console.error(error);
-  process.exitCode = 1;
-});

nodejs/__test__/materialized_view.test.ts

@@ -48,28 +48,6 @@ describe("materialized views", () => {
     expect(definitionFromMetadata(safe, "v").limit).toBe(42);
   });
 
-  it("reads the namespaced select kind and refuses unknown kinds", () => {
-    // "namespaced_select" is the namespaced form of "select": same shape, a
-    // separate kind so readers that predate it refuse instead of resolving
-    // the source at the root.
-    const namespaced = new Map([
-      [
-        DEFINITION_META_KEY,
-        '{"kind":"namespaced_select","source_table":"people","source_namespace":["ns"]}',
-      ],
-    ]);
-    const definition = definitionFromMetadata(namespaced, "v");
-    expect(definition.sourceTable).toBe("people");
-    expect(definition.sourceNamespace).toEqual(["ns"]);
-
-    const unknown = new Map([
-      [DEFINITION_META_KEY, '{"kind":"select_v3","source_table":"people"}'],
-    ]);
-    expect(() => definitionFromMetadata(unknown, "v")).toThrow(
-      /cannot refresh/,
-    );
-  });
-
   it("creates, refreshes and queries a view", async () => {
     const view = await db.createMaterializedView("adults", "people", {
       select: ["name", ["shout", "upper(name)"]],

nodejs/__test__/package.test.ts

@@ -5,8 +5,8 @@ import packageJson = require("../package.json");
 
 describe("package metadata", () => {
   it("requires Node.js type declarations compatible with the runtime", () => {
-    expect(packageJson.engines.node).toBe(">= 22");
-    expect(packageJson.peerDependencies["@types/node"]).toBe(">=22");
+    expect(packageJson.engines.node).toBe(">= 18");
+    expect(packageJson.peerDependencies["@types/node"]).toBe(">=18");
     expect(packageJson.peerDependenciesMeta["@types/node"]).toEqual({
       optional: true,
     });

nodejs/__test__/remote.test.ts

@@ -3,7 +3,6 @@
 
 import * as http from "http";
 import { RequestListener } from "http";
-import packageJson = require("../package.json");
 import {
   ClientConfig,
   Connection,
@@ -71,13 +70,7 @@ async function withMockDatabase(
   try {
     await callback(db);
   } finally {
-    // `close()` alone leaves the port bound until keep-alive sockets drain, so
-    // a single failing test would cascade into EADDRINUSE for every test after
-    // it. Destroy the connections and wait for the port to actually be free.
-    await new Promise<void>((resolve) => {
-      server.closeAllConnections();
-      server.close(() => resolve());
-    });
+    server.close();
   }
 }
 
@@ -138,7 +131,7 @@ describe("remote connection", () => {
       (req, res) => {
         expect(req.headers["x-api-key"]).toEqual("fake");
         expect(req.headers["user-agent"]).toEqual(
-          `LanceDB-Node-Client/${packageJson.version}`,
+          `LanceDB-Node-Client/${process.env.npm_package_version}`,
         );
 
         const body = JSON.stringify({ tables: [] });
@@ -939,7 +932,6 @@ describe("remote connection jobs surface", () => {
     const { tableFromArrays, tableToIPC } = await import("apache-arrow");
     const eventsTable = tableFromArrays({ state: ["created", "succeeded"] });
     const eventsBody = Buffer.from(tableToIPC(eventsTable, "stream"));
-    const queryEventsPayloads: Record<string, unknown>[] = [];
 
     await withMockDatabase(
       (req, res) => {
@@ -968,16 +960,6 @@ describe("remote connection jobs surface", () => {
                 );
             }
           } else if (req.url === "/v1/jobs/describe") {
-            if (payload["job_id"] === "job-2") {
-              res
-                .writeHead(200, { "Content-Type": "application/json" })
-                .end(
-                  '{"job_id": "job-2", "job_type": "refresh_column", ' +
-                    '"job_state": "DONE", "creation_ms": 2000, ' +
-                    '"result": {"rows_assigned": 1000000}}',
-                );
-              return;
-            }
             if (payload["job_id"] !== "job-1") {
               res.writeHead(404).end("no such job");
               return;
@@ -999,7 +981,6 @@ describe("remote connection jobs surface", () => {
               .writeHead(200, { "Content-Type": "application/json" })
               .end('{"job_id": "job-1"}');
           } else if (req.url === "/v1/jobs/query_events") {
-            queryEventsPayloads.push(payload);
             res
               .writeHead(200, {
                 "Content-Type": "application/vnd.apache.arrow.stream",
@@ -1016,65 +997,22 @@ describe("remote connection jobs surface", () => {
         expect(jobs[0].state).toEqual("running");
         expect(jobs[1].state).toEqual("finished");
 
+        const description = await db.getJob("job-1");
+        expect(description?.state).toEqual("failed");
+        expect(JSON.parse(description?.specJson ?? "")).toEqual({
+          column: "vec",
+        });
+        expect(description?.failure?.message).toEqual("worker died");
+        expect(await db.getJob("missing")).toBeNull();
+
         expect(await db.cancelJob("job-1")).toBe(true);
         expect(await db.cancelJob("missing")).toBe(false);
 
-        // Opening a job hands back a populated handle; a missing one rejects.
-        await expect(db.openJob("missing")).rejects.toThrow("not found");
-        const finished = await db.openJob("job-2");
-        expect(finished.state).toEqual("finished");
-        expect(finished.result).toEqual({
-          // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-          rows_assigned: 1000000,
-        });
+        const history = await db.jobHistory("job-1");
+        expect(history.numRows).toEqual(2);
 
-        const job = await db.openJob("job-1");
+        const job = db.job("job-1");
         expect(job.id).toEqual("job-1");
-
-        // openJob already populated the handle; refresh() re-reads it.
-        expect(job.state).toEqual("failed");
-        await job.refresh();
-        expect(job.state).toEqual("failed");
-        expect(job.jobType).toEqual("create_index");
-        expect(job.creationMs).toEqual(1000);
-        expect(job.spec).toEqual({ column: "vec" });
-        expect(job.result).toBeNull();
-        expect(job.failure?.message).toEqual("worker died");
-
-        // The handle reaches its own events, supplying its job id.
-        const jobEvents = await job.events({
-          limit: 500,
-          filter: "state = 'claim_complete'",
-        });
-        expect(jobEvents.numRows).toEqual(2);
-        expect(queryEventsPayloads.pop()).toEqual({
-          // biome-ignore lint/style/useNamingConvention: snake_case mandated by the server wire format
-          job_id: "job-1",
-          limit: 500,
-          filter: "state = 'claim_complete'",
-        });
-
-        // Printing lays every known field out on its own line, with the JSON
-        // payloads indented rather than crammed onto one line.
-        expect(`${job}`).toEqual(
-          [
-            "Job(",
-            '    id="job-1",',
-            '    state="failed",',
-            '    jobType="create_index",',
-            "    creationMs=1000,",
-            "    spec={",
-            '        "column": "vec"',
-            "    },",
-            "    failure={",
-            '        "phase": "execute",',
-            '        "message": "worker died",',
-            '        "retryable": true',
-            "    },",
-            ")",
-          ].join("\n"),
-        );
-
         expect(await job.status()).toEqual("failed");
         await expect(job.wait()).rejects.toThrow("worker died");
       },

nodejs/examples/basic.test.ts

@@ -170,7 +170,7 @@ test("basic table examples", async () => {
     // --8<-- [end:create_index]
 
     // --8<-- [start:delete_rows]
-    await tbl.delete("item = 'fizz'");
+    await tbl.delete('item = "fizz"');
     // --8<-- [end:delete_rows]
 
     // --8<-- [start:drop_table]

nodejs/examples/package.json

@@ -8,8 +8,7 @@
     "//1": "--experimental-vm-modules is needed to run jest with sentence-transformers",
     "//2": "--testEnvironment is needed to run jest with sentence-transformers",
     "//3": "See: https://github.com/huggingface/transformers.js/issues/57",
-    "//4": "jest is invoked by its JS entry, not node_modules/.bin/jest: under pnpm that path is a shell shim, which `node` cannot execute",
-    "test": "node --experimental-vm-modules node_modules/jest/bin/jest.js --testEnvironment jest-environment-node-single-context --verbose",
+    "test": "node --experimental-vm-modules node_modules/.bin/jest --testEnvironment jest-environment-node-single-context --verbose",
     "lint": "biome check *.ts && biome format *.ts",
     "lint-ci": "biome ci .",
     "lint-fix": "biome check --write *.ts && pnpm format",

nodejs/lancedb/arrow.ts

@@ -5,6 +5,7 @@ import {
   Data as ArrowData,
   Table as ArrowTable,
   Binary,
+  Bool,
   BufferType,
   DataType,
   DateUnit,
@@ -17,7 +18,12 @@ import {
   FixedSizeList,
   Float,
   Float32,
+  Float64,
   Int,
+  Int8,
+  Int16,
+  Int32,
+  Int64,
   LargeBinary,
   List,
   Null,
@@ -30,17 +36,17 @@ import {
   Struct,
   Timestamp,
   Type,
+  Uint8,
+  Uint16,
+  Uint32,
   Utf8,
   Vector,
   makeVector as arrowMakeVector,
-  util as arrowUtil,
   vectorFromArray as badVectorFromArray,
   makeBuilder,
   makeData,
 } from "apache-arrow";
 import { Buffers } from "apache-arrow/data";
-import { typedArrayToArrowType } from "./arrow_type";
-import { coerceBlobValue, isBlobField } from "./blob";
 import { type EmbeddingFunction } from "./embedding/embedding_function";
 import {
   EmbeddingFunctionConfig,
@@ -53,7 +59,14 @@ import {
   sanitizeTable,
   sanitizeType,
 } from "./sanitize";
-import { inferSchema } from "./schema";
+
+/**
+ * Check if a field name indicates a vector column.
+ */
+function nameSuggestsVectorColumn(fieldName: string): boolean {
+  const nameLower = fieldName.toLowerCase();
+  return nameLower.includes("vector") || nameLower.includes("embedding");
+}
 
 export * from "apache-arrow";
 export type SchemaLike =
@@ -73,7 +86,8 @@ export type FieldLike =
     };
 
 export type DataLike =
-  | import("apache-arrow").Data
+  // biome-ignore lint/suspicious/noExplicitAny: <explanation>
+  | import("apache-arrow").Data<Struct<any>>
   | {
       // biome-ignore lint/suspicious/noExplicitAny: <explanation>
       type: any;
@@ -82,7 +96,6 @@ export type DataLike =
       stride: number;
       nullable: boolean;
       children: DataLike[];
-      dictionary?: { data: readonly DataLike[] };
       get nullCount(): number;
       // biome-ignore lint/suspicious/noExplicitAny: <explanation>
       values: Buffers<any>[BufferType.DATA];
@@ -431,14 +444,12 @@ export function makeArrowTable(
       throw new Error("A schema must be provided if data is empty");
     } else {
       schema = new Schema(schema.fields, schemaMetadata);
-      validateBlobSchema(schema);
       return new ArrowTable(schema);
     }
   }
 
   let inferredSchema = inferSchema(data, schema, opt);
   inferredSchema = new Schema(inferredSchema.fields, schemaMetadata);
-  validateBlobSchema(inferredSchema);
 
   const finalColumns: Record<string, Vector> = {};
   for (const field of inferredSchema.fields) {
@@ -448,33 +459,108 @@ export function makeArrowTable(
   return new ArrowTable(inferredSchema, finalColumns);
 }
 
-function validateBlobSchema(schema: Schema): void {
-  for (const field of schema.fields) {
-    validateBlobField(field);
+function inferSchema(
+  data: Array<Record<string, unknown>>,
+  schema: Schema | undefined,
+  opts: MakeArrowTableOptions,
+): Schema {
+  // We will collect all fields we see in the data.
+  const pathTree = new PathTree<DataType>();
+
+  for (const [rowI, row] of data.entries()) {
+    for (const [path, value] of rowPathsAndValues(row)) {
+      if (!pathTree.has(path)) {
+        // First time seeing this field.
+        if (schema !== undefined) {
+          const field = getFieldForPath(schema, path);
+          if (field === undefined) {
+            throw new Error(
+              `Found field not in schema: ${path.join(".")} at row ${rowI}`,
+            );
+          } else {
+            pathTree.set(path, field.type);
+          }
+        } else {
+          const inferredType = inferType(value, path, opts);
+          if (inferredType === undefined) {
+            throw new Error(`Failed to infer data type for field ${path.join(
+              ".",
+            )} at row ${rowI}. \
+                             Consider providing an explicit schema.`);
+          }
+          pathTree.set(path, inferredType);
+        }
+      } else if (schema === undefined) {
+        const currentType = pathTree.get(path);
+        const newType = inferType(value, path, opts);
+        if (currentType !== newType) {
+          new Error(`Failed to infer schema for data. Previously inferred type \
+                     ${currentType} but found ${newType} at row ${rowI}. Consider \
+                     providing an explicit schema.`);
+        }
+      }
+    }
+  }
+
+  if (schema === undefined) {
+    function fieldsFromPathTree(pathTree: PathTree<DataType>): Field[] {
+      const fields = [];
+      for (const [name, value] of pathTree.map.entries()) {
+        if (value instanceof PathTree) {
+          const children = fieldsFromPathTree(value);
+          fields.push(new Field(name, new Struct(children), true));
+        } else {
+          fields.push(new Field(name, value, true));
+        }
+      }
+      return fields;
+    }
+    const fields = fieldsFromPathTree(pathTree);
+    return new Schema(fields);
+  } else {
+    function takeMatchingFields(
+      fields: Field[],
+      pathTree: PathTree<DataType>,
+    ): Field[] {
+      const outFields = [];
+      for (const field of fields) {
+        if (pathTree.map.has(field.name)) {
+          const value = pathTree.get([field.name]);
+          if (value instanceof PathTree) {
+            const struct = field.type as Struct;
+            const children = takeMatchingFields(struct.children, value);
+            outFields.push(
+              new Field(field.name, new Struct(children), field.nullable),
+            );
+          } else {
+            outFields.push(
+              new Field(field.name, value as DataType, field.nullable),
+            );
+          }
+        }
+      }
+      return outFields;
+    }
+    const fields = takeMatchingFields(schema.fields, pathTree);
+    return new Schema(fields);
   }
 }
 
-function validateBlobField(field: Field): void {
-  if (
-    isFixedSizeList(field.type) &&
-    containsBlobField(field.type.children[0])
-  ) {
-    throw new Error(
-      "Blob fields inside FixedSizeList are not supported. Use List instead.",
-    );
+function* rowPathsAndValues(
+  row: Record<string, unknown>,
+  basePath: string[] = [],
+): Generator<[string[], unknown]> {
+  for (const [key, value] of Object.entries(row)) {
+    if (isObject(value)) {
+      yield* rowPathsAndValues(value, [...basePath, key]);
+    } else {
+      // Skip undefined values - they should be treated the same as missing fields
+      // for embedding function purposes
+      if (value !== undefined) {
+        yield [[...basePath, key], value];
+      }
+    }
   }
-  for (const child of field.type.children ?? []) {
-    validateBlobField(child);
-  }
-}
-
-function containsBlobField(field: Field): boolean {
-  if (isBlobField(field)) {
-    return true;
-  }
-  return (field.type.children ?? []).some((child: Field) =>
-    containsBlobField(child),
-  );
 }
 
 function isObject(value: unknown): value is Record<string, unknown> {
@@ -491,19 +577,146 @@ function isObject(value: unknown): value is Record<string, unknown> {
   );
 }
 
-function valueAtPath(datum: Record<string, unknown>, path: string[]): unknown {
-  let current: unknown = datum;
+function getFieldForPath(schema: Schema, path: string[]): Field | undefined {
+  let current: Field | Schema = schema;
   for (const key of path) {
-    if (current == null) {
-      return null;
-    }
-    if (isObject(current) && (Object.hasOwn(current, key) || key in current)) {
-      current = current[key];
+    if (current instanceof Schema) {
+      const field: Field | undefined = current.fields.find(
+        (f) => f.name === key,
+      );
+      if (field === undefined) {
+        return undefined;
+      }
+      current = field;
+    } else if (current instanceof Field && DataType.isStruct(current.type)) {
+      const struct: Struct = current.type;
+      const field = struct.children.find((f) => f.name === key);
+      if (field === undefined) {
+        return undefined;
+      }
+      current = field;
     } else {
       return undefined;
     }
   }
-  return current;
+  if (current instanceof Field) {
+    return current;
+  } else {
+    return undefined;
+  }
+}
+
+/**
+ * Try to infer which Arrow type to use for a given value.
+ *
+ * May return undefined if the type cannot be inferred.
+ */
+function inferType(
+  value: unknown,
+  path: string[],
+  opts: MakeArrowTableOptions,
+): DataType | undefined {
+  if (typeof value === "bigint") {
+    return new Int64();
+  } else if (typeof value === "number") {
+    // Even if it's an integer, it's safer to assume Float64. Users can
+    // always provide an explicit schema or use BigInt if they mean integer.
+    return new Float64();
+  } else if (typeof value === "string") {
+    if (opts.dictionaryEncodeStrings) {
+      return new Dictionary(new Utf8(), new Int32());
+    } else {
+      return new Utf8();
+    }
+  } else if (typeof value === "boolean") {
+    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
+    }
+    if (path.length === 1 && Object.hasOwn(opts.vectorColumns, path[0])) {
+      const floatType = sanitizeType(opts.vectorColumns[path[0]].type);
+      return new FixedSizeList(
+        value.length,
+        new Field("item", floatType, true),
+      );
+    }
+    const valueType = inferType(value[0], path, opts);
+    if (valueType === undefined) {
+      return undefined;
+    }
+    // Try to automatically detect embedding columns.
+    if (nameSuggestsVectorColumn(path[path.length - 1])) {
+      // Check if value is a Uint8Array for integer vector type determination
+      if (value instanceof Uint8Array) {
+        // For integer vectors, we default to Uint8 (matching Python implementation)
+        const child = new Field("item", new Uint8(), true);
+        return new FixedSizeList(value.length, child);
+      } else {
+        // For float vectors, we default to Float32
+        const child = new Field("item", new Float32(), true);
+        return new FixedSizeList(value.length, child);
+      }
+    } else {
+      const child = new Field("item", valueType, true);
+      return new List(child);
+    }
+  } else {
+    // TODO: timestamp
+    return undefined;
+  }
+}
+
+class PathTree<V> {
+  map: Map<string, V | PathTree<V>>;
+
+  constructor(entries?: [string[], V][]) {
+    this.map = new Map();
+    if (entries !== undefined) {
+      for (const [path, value] of entries) {
+        this.set(path, value);
+      }
+    }
+  }
+  has(path: string[]): boolean {
+    let ref: PathTree<V> = this;
+    for (const part of path) {
+      if (!(ref instanceof PathTree) || !ref.map.has(part)) {
+        return false;
+      }
+      ref = ref.map.get(part) as PathTree<V>;
+    }
+    return true;
+  }
+  get(path: string[]): V | undefined {
+    let ref: PathTree<V> = this;
+    for (const part of path) {
+      if (!(ref instanceof PathTree) || !ref.map.has(part)) {
+        return undefined;
+      }
+      ref = ref.map.get(part) as PathTree<V>;
+    }
+    return ref as V;
+  }
+  set(path: string[], value: V): void {
+    let ref: PathTree<V> = this;
+    for (const part of path.slice(0, path.length - 1)) {
+      if (!ref.map.has(part)) {
+        ref.map.set(part, new PathTree<V>());
+      }
+      ref = ref.map.get(part) as PathTree<V>;
+    }
+    ref.map.set(path[path.length - 1], value);
+  }
 }
 
 function transposeData(
@@ -511,98 +724,41 @@ function transposeData(
   field: Field,
   path: string[] = [],
 ): Vector {
-  const valuesPath = [...path, field.name];
-  if (isBlobField(field) && field.type instanceof Struct) {
-    const blobRows = data.map((datum) =>
-      coerceBlobValue(valueAtPath(datum, valuesPath)),
-    );
-    const childVectors = field.type.children.map((child) => {
-      const values = blobRows.map((row) =>
-        row == null ? null : (row[child.name as "data" | "uri"] ?? null),
-      );
-      return makeVector(values, child.type, undefined, child.nullable);
-    });
-    const nullCount = blobRows.filter((row) => row === null).length;
-    const structData = makeData({
-      type: field.type,
-      length: blobRows.length,
-      nullCount,
-      nullBitmap:
-        nullCount > 0
-          ? arrowUtil.packBools(blobRows.map((row) => row !== null))
-          : undefined,
-      children: childVectors.map((v) => v.data[0]),
-    });
-    return arrowMakeVector(structData);
-  }
-  if (isList(field.type) && containsBlobField(field.type.children[0])) {
-    return transposeListData(data, field, valuesPath);
-  }
-  const values = data.map((datum) => valueAtPath(datum, valuesPath));
   if (field.type instanceof Struct) {
     const childFields = field.type.children;
+    const fullPath = [...path, field.name];
     const childVectors = childFields.map((child) => {
-      return transposeData(data, child, valuesPath);
+      return transposeData(data, child, fullPath);
     });
-    const nullCount = values.filter((value) => value === null).length;
     const structData = makeData({
       type: field.type,
-      length: values.length,
-      nullCount,
-      nullBitmap:
-        nullCount > 0
-          ? arrowUtil.packBools(values.map((value) => value !== null))
-          : undefined,
-      children: childVectors.map((v) => v.data[0]),
+      children: childVectors as unknown as ArrowData<DataType>[],
     });
     return arrowMakeVector(structData);
   } else {
+    const valuesPath = [...path, field.name];
+    const values = data.map((datum) => {
+      let current: unknown = datum;
+      for (const key of valuesPath) {
+        if (current == null) {
+          return null;
+        }
+
+        if (
+          isObject(current) &&
+          (Object.hasOwn(current, key) || key in current)
+        ) {
+          current = current[key];
+        } else {
+          return null;
+        }
+      }
+      return current;
+    });
     return makeVector(values, field.type, undefined, field.nullable);
   }
 }
 
-function transposeListData(
-  data: Record<string, unknown>[],
-  field: Field,
-  valuesPath: string[],
-): Vector {
-  const listType = field.type as List;
-  const childField = listType.children[0];
-  const lists = data.map((datum) => valueAtPath(datum, valuesPath));
-  const flattened: Record<string, unknown>[] = [];
-  const validity: boolean[] = [];
-  const offsets: number[] = [0];
-
-  for (const list of lists) {
-    if (list == null) {
-      validity.push(false);
-      offsets.push(flattened.length);
-      continue;
-    }
-    if (!Array.isArray(list)) {
-      throw new Error(`expected an array for list field '${field.name}'`);
-    }
-    validity.push(true);
-    for (const element of list) {
-      flattened.push({ [childField.name]: element });
-    }
-    offsets.push(flattened.length);
-  }
-
-  const childVector = transposeData(flattened, childField, []);
-  const nullCount = validity.filter((valid) => !valid).length;
-  return arrowMakeVector(
-    makeData({
-      type: listType,
-      length: lists.length,
-      nullCount,
-      nullBitmap: nullCount > 0 ? arrowUtil.packBools(validity) : undefined,
-      valueOffsets: Int32Array.from(offsets),
-      child: childVector.data[0],
-    }),
-  );
-}
-
 /**
  * Create an empty Arrow table with the provided schema
  */
@@ -641,6 +797,32 @@ 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[],
@@ -700,7 +882,7 @@ function makeVector(
   }
   if (values.length === 0) {
     throw Error(
-      "makeVector requires at least one value or the type must be specified",
+      "makeVector requires at least one value or the type must be specfied",
     );
   }
   const sampleValue = values.find((val) => val !== null && val !== undefined);
@@ -958,7 +1140,7 @@ async function applyEmbeddings<T>(
  * customized by the `embeddingDataType` property of the embedding function.
  *
  * If a schema is provided in `makeTableOptions` then it should include the
- * embedding columns.  If no schema is provided then embedding columns will
+ * embedding columns.  If no schema is provded then embedding columns will
  * be placed at the end of the table, after all of the input columns.
  */
 export async function convertToTable(
@@ -1052,7 +1234,6 @@ export async function fromTableToBuffer(
     schema = sanitizeSchema(schema);
   }
   const tableWithEmbeddings = await applyEmbeddings(table, embeddings, schema);
-  validateBlobSchema(tableWithEmbeddings.schema);
   const writer = RecordBatchFileWriter.writeAll(tableWithEmbeddings);
   return Buffer.from(await writer.toUint8Array());
 }
@@ -1281,12 +1462,8 @@ export function ensureNestedFieldsExist(
           completeRow[field.name] = row[field.name];
         }
       } else {
-        // Keep a missing struct valid while filling each of its children with
-        // null. This is distinct from an explicitly null struct value.
-        completeRow[field.name] =
-          field.type.constructor.name === "Struct"
-            ? ensureStructFieldsExist({}, field.type as Struct)
-            : null;
+        // Field is missing from the data - set to null
+        completeRow[field.name] = null;
       }
     }
 
@@ -1321,12 +1498,8 @@ function ensureStructFieldsExist(
         completeStruct[childField.name] = data[childField.name];
       }
     } else {
-      // Keep a missing struct valid while filling each of its children with
-      // null. This is distinct from an explicitly null struct value.
-      completeStruct[childField.name] =
-        childField.type.constructor.name === "Struct"
-          ? ensureStructFieldsExist({}, childField.type as Struct)
-          : null;
+      // Field is missing - set to null
+      completeStruct[childField.name] = null;
     }
   }
 

nodejs/lancedb/arrow_type.ts

@@ -1,40 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  type DataType,
-  Float32,
-  Float64,
-  Int8,
-  Int16,
-  Int32,
-  Uint8,
-  Uint16,
-  Uint32,
-} from "apache-arrow";
-
-/**
- * Map a JS TypedArray instance to the corresponding Arrow element type and
- * length. Returns undefined when the view is not a supported TypedArray.
- */
-export 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;
-}

nodejs/lancedb/blob.ts

@@ -1,236 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import { Field, LargeBinary, Struct, Utf8 } from "apache-arrow";
-import { BlobFile as NativeBlobFile } from "./native";
-
-const BLOB_V2_EXTENSION_NAME = "lance.blob.v2";
-
-const INLINE_SIZE_THRESHOLD_KEY = "lance-encoding:blob-inline-size-threshold";
-const DEDICATED_SIZE_THRESHOLD_KEY =
-  "lance-encoding:blob-dedicated-size-threshold";
-const PACK_FILE_SIZE_THRESHOLD_KEY =
-  "lance-encoding:blob-pack-file-size-threshold";
-
-export type BlobInput = {
-  data: Buffer | Uint8Array | null;
-  uri: string | null;
-};
-
-export type BlobOptions = {
-  /** Defaults to true. */
-  nullable?: boolean;
-  /**
-   * Max payload bytes kept inline in the data file. Zero is allowed. Must be a
-   * safe integer.
-   */
-  inlineSizeThreshold?: number;
-  /**
-   * Max payload bytes stored in a packed sidecar before a dedicated file. Must
-   * be a positive safe integer.
-   */
-  dedicatedSizeThreshold?: number;
-  /**
-   * Max bytes in one packed sidecar before starting another. Must be a positive
-   * safe integer.
-   */
-  packFileSizeThreshold?: number;
-};
-
-/**
- * Declares a `lance.blob.v2` column.
- *
- * Query results are descriptors, not payload bytes. Use {@link Table.fetchBlobs}
- * or {@link Table.fetchBlobFiles} to read bytes.
- *
- * @example
- * ```ts
- * import { readFile } from "node:fs/promises";
- * import { Field, Int64, Schema } from "apache-arrow";
- * import { blob, connect } from "@lancedb/lancedb";
- *
- * const db = await connect("./data");
- * const video = await readFile("clip.mp4");
- * const table = await db.createTable(
- *   "videos",
- *   [{ id: 1n, video }],
- *   {
- *     schema: new Schema([
- *       new Field("id", new Int64()),
- *       blob("video"),
- *     ]),
- *   },
- * );
- *
- * const rows = await table.query().select(["id"]).withRowId().toArray();
- * const rowIds = rows.map((row) => row._rowid as bigint);
- * const bytes = await table.fetchBlobs("video", rowIds);
- *
- * const [handle] = await table.fetchBlobFiles("video", rowIds);
- * const size = handle!.size();
- * const header = await handle!.readRange(0n, size < 65536n ? size : 65536n);
- * ```
- */
-export function blob(name: string, options: BlobOptions = {}): Field {
-  const metadata = new Map<string, string>([
-    ["ARROW:extension:name", BLOB_V2_EXTENSION_NAME],
-  ]);
-  setThreshold(
-    metadata,
-    INLINE_SIZE_THRESHOLD_KEY,
-    "inlineSizeThreshold",
-    options.inlineSizeThreshold,
-    0,
-  );
-  setThreshold(
-    metadata,
-    DEDICATED_SIZE_THRESHOLD_KEY,
-    "dedicatedSizeThreshold",
-    options.dedicatedSizeThreshold,
-    1,
-  );
-  setThreshold(
-    metadata,
-    PACK_FILE_SIZE_THRESHOLD_KEY,
-    "packFileSizeThreshold",
-    options.packFileSizeThreshold,
-    1,
-  );
-  return new Field(
-    name,
-    new Struct([
-      new Field("data", new LargeBinary(), true),
-      new Field("uri", new Utf8(), true),
-    ]),
-    options.nullable ?? true,
-    metadata,
-  );
-}
-
-/**
- * Checks for the `lance.blob.v2` extension marker. Does not validate the
- * field's storage type.
- */
-export function isBlobField(field: Field): boolean {
-  return field.metadata?.get("ARROW:extension:name") === BLOB_V2_EXTENSION_NAME;
-}
-
-/**
- * A lazy handle to blob bytes. Create one with {@link Table.fetchBlobFiles}.
- *
- * @hideconstructor
- */
-export class BlobFile {
-  private readonly inner: NativeBlobFile;
-
-  private constructor(inner: NativeBlobFile) {
-    if (!(inner instanceof NativeBlobFile)) {
-      throw new Error("BlobFile handles come from Table.fetchBlobFiles");
-    }
-    this.inner = inner;
-  }
-
-  /** @ignore */
-  static fromNative(inner: NativeBlobFile): BlobFile {
-    return new BlobFile(inner);
-  }
-
-  /** Returns the blob size in bytes. */
-  size(): bigint {
-    return this.inner.size();
-  }
-
-  /**
-   * Reads from the cursor to the end and advances the cursor.
-   *
-   * A second call returns an empty buffer. {@link BlobFile.readRange} does
-   * not move the cursor.
-   */
-  read(): Promise<Buffer> {
-    return this.inner.read();
-  }
-
-  /**
-   * Reads the half-open byte range `[start, end)`.
-   *
-   * Fails when `end` is past the blob size. Does not move the cursor.
-   */
-  readRange(start: bigint, end: bigint): Promise<Buffer> {
-    return this.inner.readRange(start, end);
-  }
-}
-
-export function coerceBlobValue(value: unknown): BlobInput | null {
-  if (value == null) {
-    return null;
-  }
-  if (isBlobBytes(value)) {
-    return { data: value, uri: null };
-  }
-  if (ArrayBuffer.isView(value)) {
-    throw new Error("Blob data must be Buffer or Uint8Array");
-  }
-  if (typeof value === "string") {
-    if (value === "") {
-      throw new Error("Blob uri cannot be empty");
-    }
-    return { data: null, uri: value };
-  }
-  if (typeof value === "object") {
-    const record = value as Record<string, unknown>;
-    if (!("data" in record) && !("uri" in record)) {
-      throw new Error(
-        "Blob struct values must include a 'data' or 'uri' field",
-      );
-    }
-    const uri = record.uri;
-    if (uri === "") {
-      throw new Error("Blob uri cannot be empty");
-    }
-    if (uri != null && typeof uri !== "string") {
-      throw new Error(`Blob uri must be a string or null, got ${typeof uri}`);
-    }
-    const data = record.data;
-    if (data != null && !isBlobBytes(data)) {
-      throw new Error("Blob data must be Buffer, Uint8Array, or null");
-    }
-    const bytes = (data as Buffer | Uint8Array | null | undefined) ?? null;
-    const uriValue = uri ?? null;
-    if ((bytes == null) === (uriValue == null)) {
-      throw new Error(
-        "Blob struct values must set exactly one of 'data' or 'uri'",
-      );
-    }
-    return { data: bytes, uri: uriValue };
-  }
-  throw new Error(
-    "Blob column values must be Buffer, Uint8Array, a URI string, null, or { data?, uri? }",
-  );
-}
-
-function isBlobBytes(value: unknown): value is Buffer | Uint8Array {
-  return Buffer.isBuffer(value) || value instanceof Uint8Array;
-}
-
-function setThreshold(
-  metadata: Map<string, string>,
-  key: string,
-  optionName: string,
-  value: number | undefined,
-  minimum: number,
-): void {
-  if (value === undefined) {
-    return;
-  }
-  if (!Number.isSafeInteger(value)) {
-    throw new Error(`${optionName} must be a safe integer`);
-  }
-  if (value < minimum) {
-    throw new Error(
-      minimum <= 0
-        ? `${optionName} must be non-negative`
-        : `${optionName} must be positive`,
-    );
-  }
-  metadata.set(key, String(value));
-}

nodejs/lancedb/connection.ts

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
+import { tableFromIPC } from "apache-arrow";
 import {
   Data,
   SchemaLike,
@@ -15,7 +16,6 @@ import {
   makeEmptyTable,
 } from "./arrow";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
-import { Job } from "./job";
 import {
   MaterializedView,
   MaterializedViewSelect,
@@ -27,16 +27,16 @@ import type {
   CreateNamespaceResponse,
   DescribeNamespaceResponse,
   DropNamespaceResponse,
+  Job,
+  JobDescription,
   JobInfo,
   ListNamespacesResponse,
-  ListTablesResponse,
 } from "./native";
 export type {
   CreateNamespaceResponse,
   DescribeNamespaceResponse,
   DropNamespaceResponse,
   ListNamespacesResponse,
-  ListTablesResponse,
 };
 import { sanitizeTable } from "./sanitize";
 import { LocalTable, Table } from "./table";
@@ -134,10 +134,6 @@ export interface OpenTableOptions {
   indexCacheSize?: number;
 }
 
-/**
- * @deprecated Use {@link ListTablesOptions} with {@link Connection.listTables}
- * instead.
- */
 export interface TableNamesOptions {
   /**
    * If present, only return names that come lexicographically after the
@@ -151,24 +147,6 @@ export interface TableNamesOptions {
   limit?: number;
 }
 
-export interface ListTablesOptions {
-  /**
-   * Token from a previous response, to resume listing where it left off.
-   *
-   * The token is opaque: it carries whatever the database needs to resume, and
-   * callers should not construct or interpret one.
-   */
-  pageToken?: string;
-  /**
-   * An upper bound on how many tables to return.
-   *
-   * A page may hold fewer than this and still not be the last one, so keep
-   * going while the response carries a page token rather than while pages are
-   * full.
-   */
-  limit?: number;
-}
-
 export interface ListNamespacesOptions {
   /** Token from a previous response for pagination. */
   pageToken?: string;
@@ -253,7 +231,6 @@ export abstract class Connection {
    * @param {Partial<TableNamesOptions>} options - options to control the
    * paging / start point (backwards compatibility)
    *
-   * @deprecated Use {@link Connection.listTables} instead.
    */
   abstract tableNames(options?: Partial<TableNamesOptions>): Promise<string[]>;
   /**
@@ -264,53 +241,12 @@ export abstract class Connection {
    * @param {Partial<TableNamesOptions>} options - options to control the
    * paging / start point
    *
-   * @deprecated Use {@link Connection.listTables} instead.
    */
   abstract tableNames(
     namespacePath?: string[],
     options?: Partial<TableNamesOptions>,
   ): Promise<string[]>;
 
-  /**
-   * List a page of the tables in this database.
-   *
-   * To retrieve the tables after the page, pass the `pageToken` the response
-   * carries back in. A page can be shorter than `limit` without being the last
-   * one, so walk until a response carries no page token:
-   *
-   * ```ts
-   * const names = [];
-   * let pageToken = undefined;
-   * do {
-   *   const page = await conn.listTables({ pageToken, limit: 100 });
-   *   names.push(...page.tables);
-   *   pageToken = page.pageToken;
-   * } while (pageToken);
-   * ```
-   *
-   * @param {Partial<ListTablesOptions>} options - Pagination options
-   *   (`pageToken`, `limit`).
-   * @returns {Promise<ListTablesResponse>} A page of table names and an
-   *   optional token for the tables after it.
-   */
-  abstract listTables(
-    options?: Partial<ListTablesOptions>,
-  ): Promise<ListTablesResponse>;
-  /**
-   * List a page of the tables in this database.
-   *
-   * @param {string[]} namespacePath - The namespace path to list tables from
-   *   (defaults to root namespace)
-   * @param {Partial<ListTablesOptions>} options - Pagination options
-   *   (`pageToken`, `limit`).
-   * @returns {Promise<ListTablesResponse>} A page of table names and an
-   *   optional token for the tables after it.
-   */
-  abstract listTables(
-    namespacePath?: string[],
-    options?: Partial<ListTablesOptions>,
-  ): Promise<ListTablesResponse>;
-
   /**
    * Open a table in the database.
    * @param {string} name - The name of the table
@@ -555,19 +491,24 @@ export abstract class Connection {
   ): Promise<void>;
 
   /**
-   * Open a server-side job by id, returning a handle with its record already
-   * populated. Rejects when the server has no such job, the way
-   * {@link Connection.openTable} does for a missing table.
+   * A {@link Job} handle for a server-side job by id.
    *
-   * The returned {@link Job} answers for its own state, specification,
-   * result, failure and event history, so there is no separate
-   * connection-level call for any of them.
+   * The handle is constructed without a server round trip; an unknown id
+   * surfaces when the handle is used. Dropping the handle has no effect on
+   * the job itself.
    */
-  abstract openJob(jobId: string): Promise<Job>;
+  abstract job(jobId: string): Job;
 
   /** List server-side jobs across the database's tables. */
   abstract listJobs(): Promise<JobInfo[]>;
 
+  /**
+   * Describe a single server-side job by id.
+   *
+   * Resolves to `null` when the server has no such job.
+   */
+  abstract getJob(jobId: string): Promise<JobDescription | null>;
+
   /**
    * Request cancellation of a server-side job by id.
    *
@@ -575,6 +516,13 @@ export abstract class Connection {
    * such job exists. Cancelling an already-terminal job is a no-op success.
    */
   abstract cancelJob(jobId: string): Promise<boolean>;
+
+  /**
+   * The lifecycle event history of a server-side job, as an Arrow table.
+   *
+   * Lists history across all jobs when `jobId` is omitted.
+   */
+  abstract jobHistory(jobId?: string): Promise<ArrowTable>;
 }
 
 /** @hideconstructor */
@@ -653,25 +601,6 @@ export class LocalConnection extends Connection {
     return await this.inner.listMaterializedViews();
   }
 
-  async listTables(
-    namespacePathOrOptions?: string[] | Partial<ListTablesOptions>,
-    options?: Partial<ListTablesOptions>,
-  ): Promise<ListTablesResponse> {
-    // Detect if first argument is namespacePath array or options object
-    const namespacePath = Array.isArray(namespacePathOrOptions)
-      ? namespacePathOrOptions
-      : undefined;
-    const listTablesOptions = Array.isArray(namespacePathOrOptions)
-      ? options
-      : namespacePathOrOptions;
-
-    return this.inner.listTables(
-      namespacePath ?? [],
-      listTablesOptions?.pageToken,
-      listTablesOptions?.limit,
-    );
-  }
-
   async openTable(
     name: string,
     namespacePath?: string[],
@@ -855,7 +784,7 @@ export class LocalConnection extends Connection {
   }
 
   async dropTableAsync(name: string, namespacePath?: string[]): Promise<Job> {
-    return new Job(await this.inner.dropTableAsync(name, namespacePath ?? []));
+    return this.inner.dropTableAsync(name, namespacePath ?? []);
   }
 
   async dropAllTables(namespacePath?: string[]): Promise<void> {
@@ -914,17 +843,29 @@ export class LocalConnection extends Connection {
     );
   }
 
-  async openJob(jobId: string): Promise<Job> {
-    return new Job(await this.inner.openJob(jobId));
+  job(jobId: string): Job {
+    return this.inner.job(jobId);
   }
 
   async listJobs(): Promise<JobInfo[]> {
     return this.inner.listJobs();
   }
 
+  async getJob(jobId: string): Promise<JobDescription | null> {
+    return this.inner.getJob(jobId);
+  }
+
   async cancelJob(jobId: string): Promise<boolean> {
     return this.inner.cancelJob(jobId);
   }
+
+  async jobHistory(jobId?: string): Promise<ArrowTable> {
+    const buf = await this.inner.jobHistory(jobId);
+    if (buf.length === 0) {
+      return new ArrowTable();
+    }
+    return tableFromIPC(buf);
+  }
 }
 
 /**

nodejs/lancedb/embedding/index.ts

@@ -4,15 +4,7 @@
 import { Field, Schema } from "../arrow";
 import { sanitizeType } from "../sanitize";
 import { EmbeddingFunction } from "./embedding_function";
-import {
-  EmbeddingFunctionConfig,
-  EmbeddingFunctionRegistry,
-  getRegistry as getGlobalRegistry,
-  registerBuiltIn,
-} from "./registry";
-
-type OpenAIModule = typeof import("./openai");
-type TransformersModule = typeof import("./transformers");
+import { EmbeddingFunctionConfig, getRegistry } from "./registry";
 
 export {
   FieldOptions,
@@ -22,39 +14,7 @@ export {
   EmbeddingFunctionConstructor,
 } from "./embedding_function";
 
-export {
-  EmbeddingFunctionRegistry,
-  parseEmbeddingMetadata,
-  register,
-} from "./registry";
-export type {
-  CreateReturnType,
-  EmbeddingFunctionConfig,
-  EmbeddingFunctionCreate,
-  EmbeddingMetadataEntry,
-  ResolvedEmbeddingFunctionConfig,
-} from "./registry";
-
-function initializeBuiltInProviders() {
-  const { OpenAIEmbeddingFunction } = require("./openai") as OpenAIModule;
-  const { TransformersEmbeddingFunction } =
-    require("./transformers") as TransformersModule;
-
-  registerBuiltIn("openai", OpenAIEmbeddingFunction);
-  registerBuiltIn("huggingface", TransformersEmbeddingFunction);
-}
-
-/**
- * Get the global embedding function registry.
- *
- * LanceDB built-in providers are initialized when this public API is first
- * used, so importing the root package does not change automatic search
- * selection for tables without embedding metadata.
- */
-export function getRegistry(): EmbeddingFunctionRegistry {
-  initializeBuiltInProviders();
-  return getGlobalRegistry();
-}
+export * from "./registry";
 
 /**
  * Create a schema with embedding functions.

nodejs/lancedb/embedding/openai.ts

@@ -5,13 +5,14 @@ import type OpenAI from "openai";
 import type { EmbeddingCreateParams } from "openai/resources/index";
 import { Float, Float32 } from "../arrow";
 import { EmbeddingFunction } from "./embedding_function";
-import { registerBuiltIn } from "./registry";
+import { register } from "./registry";
 
 export type OpenAIOptions = {
   apiKey: string;
   model: EmbeddingCreateParams["model"];
 };
 
+@register("openai")
 export class OpenAIEmbeddingFunction extends EmbeddingFunction<
   string,
   Partial<OpenAIOptions>
@@ -99,5 +100,3 @@ export class OpenAIEmbeddingFunction extends EmbeddingFunction<
     return response.data[0].embedding;
   }
 }
-
-registerBuiltIn("openai", OpenAIEmbeddingFunction);

nodejs/lancedb/embedding/registry.ts

@@ -7,10 +7,6 @@ import {
 } from "./embedding_function";
 import "reflect-metadata";
 
-const builtInFunctionsKey = Symbol.for(
-  "@lancedb/lancedb::embedding-built-in-functions::v1",
-);
-
 export type CreateReturnType<T> = T extends { init: () => Promise<void> }
   ? Promise<T>
   : T;
@@ -63,15 +59,6 @@ export class EmbeddingFunctionRegistry {
     };
   }
 
-  /** @ignore */
-  setBuiltIn<
-    T extends EmbeddingFunctionConstructor = EmbeddingFunctionConstructor,
-  >(name: string, ctor: T): T {
-    this.#functions.set(name, ctor);
-    Reflect.defineMetadata("lancedb::embedding::name", name, ctor);
-    return ctor;
-  }
-
   get<T extends EmbeddingFunction<unknown>>(
     name: string,
   ): EmbeddingFunctionCreate<T> | undefined;
@@ -109,7 +96,6 @@ export class EmbeddingFunctionRegistry {
    */
   reset(this: EmbeddingFunctionRegistry) {
     this.#functions.clear();
-    getBuiltInFunctions(this).clear();
   }
 
   /**
@@ -197,56 +183,12 @@ export class EmbeddingFunctionRegistry {
   }
 }
 
-function getBuiltInFunctions(registry: EmbeddingFunctionRegistry): Set<string> {
-  const registryWithBuiltIns = registry as EmbeddingFunctionRegistry & {
-    [key: symbol]: Set<string> | undefined;
-  };
-  let builtInFunctions = registryWithBuiltIns[builtInFunctionsKey];
-  if (builtInFunctions === undefined) {
-    builtInFunctions = new Set<string>();
-    registryWithBuiltIns[builtInFunctionsKey] = builtInFunctions;
-  }
-  return builtInFunctions;
-}
-
-// Server bundlers can load the side-effect embedding entry points and the public
-// embedding API from separate module graphs. Keep their registry shared.
-const registryKey = Symbol.for(
-  "@lancedb/lancedb::embedding-function-registry::v1",
-);
-const registryGlobal = globalThis as typeof globalThis & {
-  [key: symbol]: EmbeddingFunctionRegistry | undefined;
-};
-
-function getGlobalRegistry(): EmbeddingFunctionRegistry {
-  const existingRegistry = registryGlobal[registryKey];
-  if (existingRegistry !== undefined) {
-    return existingRegistry;
-  }
-  const registry = new EmbeddingFunctionRegistry();
-  registryGlobal[registryKey] = registry;
-  return registry;
-}
-
-const _REGISTRY = getGlobalRegistry();
+const _REGISTRY = new EmbeddingFunctionRegistry();
 
 export function register(name?: string) {
   return _REGISTRY.register(name);
 }
 
-/** @ignore */
-export function registerBuiltIn<
-  T extends EmbeddingFunctionConstructor = EmbeddingFunctionConstructor,
->(name: string, ctor: T): T {
-  const builtInFunctions = getBuiltInFunctions(_REGISTRY);
-  if (builtInFunctions.has(name)) {
-    return _REGISTRY.setBuiltIn(name, ctor);
-  }
-  _REGISTRY.register(name)(ctor);
-  builtInFunctions.add(name);
-  return ctor;
-}
-
 /**
  * Utility function to get the global instance of the registry
  * @returns `EmbeddingFunctionRegistry` The global instance of the registry

nodejs/lancedb/embedding/transformers.ts

@@ -3,7 +3,7 @@
 
 import { Float, Float32 } from "../arrow";
 import { EmbeddingFunction } from "./embedding_function";
-import { registerBuiltIn } from "./registry";
+import { register } from "./registry";
 
 export type XenovaTransformerOptions = {
   /** The wasm compatible model to use */
@@ -31,6 +31,7 @@ export type XenovaTransformerOptions = {
   };
 };
 
+@register("huggingface")
 export class TransformersEmbeddingFunction extends EmbeddingFunction<
   string,
   Partial<XenovaTransformerOptions>
@@ -157,8 +158,6 @@ export class TransformersEmbeddingFunction extends EmbeddingFunction<
   }
 }
 
-registerBuiltIn("huggingface", TransformersEmbeddingFunction);
-
 const tensorDiv = (
   src: import("@huggingface/transformers").Tensor,
   divBy: number,

nodejs/lancedb/index.ts

@@ -77,32 +77,30 @@ export {
   VectorColumnOptions,
 } from "./arrow";
 
-export { blob, isBlobField, BlobFile } from "./blob";
-export type { BlobOptions } from "./blob";
-
 export {
   Connection,
   CreateTableOptions,
   TableNamesOptions,
-  ListTablesOptions,
   OpenTableOptions,
   ListNamespacesOptions,
   CreateNamespaceOptions,
   DropNamespaceOptions,
   ListNamespacesResponse,
-  ListTablesResponse,
   CreateNamespaceResponse,
   DropNamespaceResponse,
   DescribeNamespaceResponse,
   RenameTableOptions,
 } from "./connection";
 
-export { JobFailureInfo, JobInfo, Session } from "./native.js";
-
-export { Job, JobEventsOptions } from "./job";
+export {
+  Job,
+  JobDescription,
+  JobFailureInfo,
+  JobInfo,
+  Session,
+} from "./native.js";
 
 export {
-  AutoQuery,
   ExecutableQuery,
   Query,
   QueryBase,

nodejs/lancedb/indices.ts

@@ -26,7 +26,7 @@ export interface IvfPqOptions {
    * This value controls how much the vector is compressed during the quantization step.
    * The more sub vectors there are the less the vector is compressed.  The default is
    * the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-   * by 16 we use the dimension divided by 8.
+   * by 16 we use the dimension divded by 8.
    *
    * The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
    * us to use efficient SIMD instructions.
@@ -228,7 +228,7 @@ export interface HnswPqOptions {
    * This value controls how much the vector is compressed during the quantization step.
    * The more sub vectors there are the less the vector is compressed.  The default is
    * the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-   * by 16 we use the dimension divided by 8.
+   * by 16 we use the dimension divded by 8.
    *
    * The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
    * us to use efficient SIMD instructions.
@@ -825,7 +825,7 @@ export interface IndexOptions {
   /**
    * Advanced index configuration
    *
-   * This option allows you to specify a specific index to create and also
+   * This option allows you to specify a specfic index to create and also
    * allows you to pass in configuration for training the index.
    *
    * See the static methods on Index for details on the various index types.

nodejs/lancedb/job.ts

@@ -1,188 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import { Table as ArrowTable, tableFromIPC } from "apache-arrow";
-import { JobFailureInfo, Job as NativeJob } from "./native";
-
-/** Which of a job's events {@link Job.events} returns. */
-export interface JobEventsOptions {
-  /** Maximum event rows to return, up to the server maximum of 10,000. */
-  limit?: number;
-  /** SQL-like filter over the event columns. */
-  filter?: string;
-}
-
-/**
- * A handle to an operation that may still be running.
- *
- * The operation may already be complete when the handle is created.
- *
- * The detail getters read what the handle last observed. Submitting an
- * operation returns only a job id, so populating them eagerly would cost an
- * extra round trip on every call:
- *
- * - {@link Job.refresh} and {@link Job.status} fetch the whole record.
- * - {@link Job.wait} records the terminal state it establishes, but not the
- *   rest of the record.
- * - Everything is null until one of those runs.
- *
- * @hideconstructor
- */
-export class Job {
-  private readonly inner: NativeJob;
-
-  constructor(inner: NativeJob) {
-    this.inner = inner;
-  }
-
-  /**
-   * Identifies the operation on the server that is running it.
-   *
-   * Operations that run in this process have no server id. The value is
-   * opaque: parsing it or storing it to resume the job later is not supported.
-   */
-  get id(): string | null {
-    return this.inner.id ?? null;
-  }
-
-  /** The last observed lifecycle state, without contacting the backend. */
-  get state(): string | null {
-    return this.inner.state ?? null;
-  }
-
-  /**
-   * The job's type, as the server names it. Null for an in-process job, which
-   * has no server-side record.
-   */
-  get jobType(): string | null {
-    return this.inner.jobType ?? null;
-  }
-
-  /** When the job was created, in milliseconds since the epoch. */
-  get creationMs(): number | null {
-    return this.inner.creationMs ?? null;
-  }
-
-  /** The job-type-specific specification it was submitted with. */
-  // biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-  get spec(): any | null {
-    return parseJson(this.inner.specJson);
-  }
-
-  /**
-   * The job-type-specific terminal result. Null until the job succeeds, so a
-   * job that never terminates reports its progress through {@link Job.events}
-   * instead.
-   */
-  // biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-  get result(): any | null {
-    return parseJson(this.inner.resultJson);
-  }
-
-  /** Why the job failed, when it failed and the server reports a reason. */
-  get failure(): JobFailureInfo | null {
-    return this.inner.failure ?? null;
-  }
-
-  /**
-   * The operation's current lifecycle state: "running", "finished", "failed",
-   * or "cancelled".
-   *
-   * A point snapshot; unlike {@link Job.wait} it does not block or reject on a
-   * terminal failure state. Also refreshes the getters above.
-   */
-  async status(): Promise<string> {
-    return this.inner.status();
-  }
-
-  /** Wait until the operation reaches a terminal state. */
-  async wait(): Promise<void> {
-    return this.inner.wait();
-  }
-
-  /** Request cancellation. Cancelling a finished operation is a no-op. */
-  async cancel(): Promise<void> {
-    return this.inner.cancel();
-  }
-
-  /**
-   * Ask the backend for this job's current state, and for a server-side job
-   * its full record, then cache it for the getters above.
-   */
-  async refresh(): Promise<void> {
-    return this.inner.refresh();
-  }
-
-  /**
-   * This job's recorded lifecycle events.
-   *
-   * Where the getters above report a terminal result only once the job reaches
-   * one, events are written as the job runs and outlive the workers that
-   * produced them. A distributed job records a `claim`/`claim_complete` pair
-   * per unit of work, each carrying `rows_processed`, so a job that never
-   * finishes still accounts for what it did.
-   *
-   * The server caps results at 1000 rows by default and 10,000 at most, and
-   * truncates without saying so, so pass `limit` for a job that emits an event
-   * per fragment. `filter` is a SQL-like expression over the `state`,
-   * `updated_by`, `emitted_from`, `emitted_by`, and `claim_entity` columns.
-   */
-  async events(options?: JobEventsOptions): Promise<ArrowTable> {
-    const buf = await this.inner.events(options?.limit, options?.filter);
-    if (buf.length === 0) {
-      return new ArrowTable();
-    }
-    return tableFromIPC(buf);
-  }
-
-  /**
-   * Every field the handle currently knows, one per line, with the JSON
-   * payloads indented -- a refresh job's spec and result are the point of
-   * printing it.
-   */
-  toString(): string {
-    if (this.state === null) {
-      const known = this.id === null ? "" : `id=${JSON.stringify(this.id)}, `;
-      return `Job(${known}not refreshed)`;
-    }
-    const fields: string[] = [];
-    if (this.id !== null) {
-      fields.push(`id=${JSON.stringify(this.id)}`);
-    }
-    fields.push(`state=${JSON.stringify(this.state)}`);
-    if (this.jobType !== null) {
-      fields.push(`jobType=${JSON.stringify(this.jobType)}`);
-    }
-    if (this.creationMs !== null) {
-      fields.push(`creationMs=${this.creationMs}`);
-    }
-    for (const [name, value] of [
-      ["spec", this.spec],
-      ["result", this.result],
-    ] as const) {
-      if (value !== null) {
-        fields.push(`${name}=${indentJson(value)}`);
-      }
-    }
-    if (this.failure !== null) {
-      fields.push(`failure=${indentJson(this.failure)}`);
-    }
-    return `Job(${fields.map((field) => `\n${REPR_INDENT}${field},`).join("")}\n)`;
-  }
-
-  [Symbol.for("nodejs.util.inspect.custom")](): string {
-    return this.toString();
-  }
-}
-
-const REPR_INDENT = "    ";
-
-// biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-function indentJson(value: any): string {
-  return JSON.stringify(value, null, 4).replace(/\n/g, `\n${REPR_INDENT}`);
-}
-
-// biome-ignore lint/suspicious/noExplicitAny: shape varies by job type
-function parseJson(raw: string | null | undefined): any | null {
-  return raw === null || raw === undefined ? null : JSON.parse(raw);
-}

nodejs/lancedb/materialized_view.ts

@@ -19,8 +19,6 @@ export interface MaterializedViewDefinition {
   limit?: number;
   /** Source columns the projections and filter read. */
   inputs: string[];
-  /** Namespace holding the source table; empty is the root namespace. */
-  sourceNamespace: string[];
 }
 
 /**
@@ -80,8 +78,7 @@ export function definitionFromMetadata(
   }
   // biome-ignore lint/suspicious/noExplicitAny: raw JSON
   const value: any = JSON.parse(raw);
-  // "namespaced_select" keeps older readers from resolving the source at root.
-  if (value.kind !== "select" && value.kind !== "namespaced_select") {
+  if (value.kind !== "select") {
     throw new Error(
       `materialized view '${name}' is defined by '${value.kind}', which this ` +
         "version of lancedb cannot refresh",
@@ -106,7 +103,6 @@ export function definitionFromMetadata(
     filter: value.filter ?? undefined,
     limit,
     inputs: value.inputs ?? [],
-    sourceNamespace: value.source_namespace ?? [],
   };
 }
 

nodejs/lancedb/merge.ts

@@ -27,7 +27,7 @@ export class MergeInsertBuilder {
    * but that behavior is subject to change.
    *
    * An optional condition may be specified.  If it is, then only
-   * matched rows that satisfy the condition will be updated.  Any
+   * matched rows that satisfy the condtion will be updated.  Any
    * rows that do not satisfy the condition will be left as they
    * are.  Failing to satisfy the condition does not cause a
    * "matched row" to become a "not matched" row.

nodejs/lancedb/query.ts

@@ -100,29 +100,6 @@ export interface FullTextSearchOptions {
   columns?: string | string[];
 }
 
-function nearestToNative(
-  inner: NativeQuery,
-  vector: Awaited<IntoVector>,
-): NativeVectorQuery {
-  const raw = Array.isArray(vector) ? null : extractVectorBuffer(vector);
-  if (raw) {
-    return inner.nearestToRaw(raw.data, raw.dtype);
-  }
-  return inner.nearestTo(Float32Array.from(vector as number[]));
-}
-
-function addQueryVectorToNative(
-  inner: NativeVectorQuery,
-  vector: Awaited<IntoVector>,
-) {
-  const raw = Array.isArray(vector) ? null : extractVectorBuffer(vector);
-  if (raw) {
-    inner.addQueryVectorRaw(raw.data, raw.dtype);
-  } else {
-    inner.addQueryVector(Float32Array.from(vector as number[]));
-  }
-}
-
 /** Common methods supported by all query types
  *
  * @see {@link Query}
@@ -134,15 +111,13 @@ export class QueryBase<
   NativeQueryType extends NativeQuery | NativeVectorQuery | NativeTakeQuery,
 > implements AsyncIterable<RecordBatch>
 {
-  protected inner!: NativeQueryType | Promise<NativeQueryType>;
-
   /**
    * @hidden
    */
-  protected constructor(inner?: NativeQueryType | Promise<NativeQueryType>) {
-    if (inner !== undefined) {
-      this.inner = inner;
-    }
+  protected constructor(
+    protected inner: NativeQueryType | Promise<NativeQueryType>,
+  ) {
+    // intentionally empty
   }
 
   // call a function on the inner (either a promise or the actual object)
@@ -160,15 +135,6 @@ export class QueryBase<
     }
   }
 
-  /**
-   * Return the native query used by the next terminal operation.
-   *
-   * @hidden
-   */
-  protected async getInner(): Promise<NativeQueryType> {
-    return this.inner;
-  }
-
   /**
    * Return only the specified columns.
    *
@@ -241,11 +207,16 @@ export class QueryBase<
   /**
    * @hidden
    */
-  protected async nativeExecute(
+  protected nativeExecute(
     options?: Partial<QueryExecutionOptions>,
   ): Promise<NativeBatchIterator> {
-    const inner = await this.getInner();
-    return inner.execute(options?.maxBatchLength, options?.timeoutMs);
+    if (this.inner instanceof Promise) {
+      return this.inner.then((inner) =>
+        inner.execute(options?.maxBatchLength, options?.timeoutMs),
+      );
+    } else {
+      return this.inner.execute(options?.maxBatchLength, options?.timeoutMs);
+    }
   }
 
   /**
@@ -274,7 +245,12 @@ export class QueryBase<
   /** Collect the results as an Arrow @see {@link ArrowTable}. */
   async toArrow(options?: Partial<QueryExecutionOptions>): Promise<ArrowTable> {
     const batches = [];
-    const inner = await this.getInner();
+    let inner;
+    if (this.inner instanceof Promise) {
+      inner = await this.inner;
+    } else {
+      inner = this.inner;
+    }
     for await (const batch of new RecordBatchIterable(inner, options)) {
       batches.push(batch);
     }
@@ -303,8 +279,11 @@ export class QueryBase<
    * @returns A Promise that resolves to a string containing the query execution plan explanation.
    */
   async explainPlan(verbose = false): Promise<string> {
-    const inner = await this.getInner();
-    return inner.explainPlan(verbose);
+    if (this.inner instanceof Promise) {
+      return this.inner.then((inner) => inner.explainPlan(verbose));
+    } else {
+      return this.inner.explainPlan(verbose);
+    }
   }
 
   /**
@@ -342,8 +321,13 @@ export class QueryBase<
     distributedMetrics?: AnalyzePlanDistributedMetrics,
   ): Promise<string> {
     const distributedMetricsMode = distributedMetrics ?? "aggregate";
-    const inner = await this.getInner();
-    return inner.analyzePlan(distributedMetricsMode);
+    if (this.inner instanceof Promise) {
+      return this.inner.then((inner) =>
+        inner.analyzePlan(distributedMetricsMode),
+      );
+    } else {
+      return this.inner.analyzePlan(distributedMetricsMode);
+    }
   }
 
   /**
@@ -355,8 +339,12 @@ export class QueryBase<
    * @returns An Arrow Schema describing the output columns.
    */
   async outputSchema(): Promise<import("./arrow").Schema> {
-    const inner = await this.getInner();
-    const schemaBuffer = await inner.outputSchema();
+    let schemaBuffer: Buffer;
+    if (this.inner instanceof Promise) {
+      schemaBuffer = await this.inner.then((inner) => inner.outputSchema());
+    } else {
+      schemaBuffer = await this.inner.outputSchema();
+    }
     const schema = tableFromIPC(schemaBuffer).schema;
     return schema;
   }
@@ -368,7 +356,7 @@ export class StandardQueryBase<
   extends QueryBase<NativeQueryType>
   implements ExecutableQuery
 {
-  constructor(inner?: NativeQueryType | Promise<NativeQueryType>) {
+  constructor(inner: NativeQueryType | Promise<NativeQueryType>) {
     super(inner);
   }
 
@@ -522,13 +510,6 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
     super(inner);
   }
 
-  /**
-   * @hidden
-   */
-  protected doVectorCall(fn: (inner: NativeVectorQuery) => void) {
-    super.doCall(fn);
-  }
-
   /**
    * Set the number of partitions to search (probe)
    *
@@ -556,7 +537,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * the minimum and maximum to the same value.
    */
   nprobes(nprobes: number): VectorQuery {
-    this.doVectorCall((inner) => inner.nprobes(nprobes));
+    super.doCall((inner) => inner.nprobes(nprobes));
 
     return this;
   }
@@ -570,7 +551,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * but will also increase latency.
    */
   minimumNprobes(minimumNprobes: number): VectorQuery {
-    this.doVectorCall((inner) => inner.minimumNprobes(minimumNprobes));
+    super.doCall((inner) => inner.minimumNprobes(minimumNprobes));
     return this;
   }
 
@@ -584,7 +565,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * potential false negatives.
    */
   maximumNprobes(maximumNprobes: number): VectorQuery {
-    this.doVectorCall((inner) => inner.maximumNprobes(maximumNprobes));
+    super.doCall((inner) => inner.maximumNprobes(maximumNprobes));
     return this;
   }
 
@@ -597,7 +578,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * `undefined` means no lower or upper bound.
    */
   distanceRange(lowerBound?: number, upperBound?: number): VectorQuery {
-    this.doVectorCall((inner) => inner.distanceRange(lowerBound, upperBound));
+    super.doCall((inner) => inner.distanceRange(lowerBound, upperBound));
     return this;
   }
 
@@ -611,7 +592,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * also increase the latency of your query. The default value is 1.5*limit.
    */
   ef(ef: number): VectorQuery {
-    this.doVectorCall((inner) => inner.ef(ef));
+    super.doCall((inner) => inner.ef(ef));
     return this;
   }
 
@@ -625,7 +606,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * whose data type is a fixed-size-list of floats.
    */
   column(column: string): VectorQuery {
-    this.doVectorCall((inner) => inner.column(column));
+    super.doCall((inner) => inner.column(column));
     return this;
   }
 
@@ -646,7 +627,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
   distanceType(
     distanceType: Required<IvfPqOptions>["distanceType"],
   ): VectorQuery {
-    this.doVectorCall((inner) => inner.distanceType(distanceType));
+    super.doCall((inner) => inner.distanceType(distanceType));
     return this;
   }
 
@@ -680,7 +661,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * distance between the query vector and the actual uncompressed vector.
    */
   refineFactor(refineFactor: number): VectorQuery {
-    this.doVectorCall((inner) => inner.refineFactor(refineFactor));
+    super.doCall((inner) => inner.refineFactor(refineFactor));
     return this;
   }
 
@@ -705,7 +686,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * factor can often help restore some of the results lost by post filtering.
    */
   postfilter(): VectorQuery {
-    this.doVectorCall((inner) => inner.postfilter());
+    super.doCall((inner) => inner.postfilter());
     return this;
   }
 
@@ -719,7 +700,7 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * calculate your recall to select an appropriate value for nprobes.
    */
   bypassVectorIndex(): VectorQuery {
-    this.doVectorCall((inner) => inner.bypassVectorIndex());
+    super.doCall((inner) => inner.bypassVectorIndex());
     return this;
   }
 
@@ -727,39 +708,43 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
    * Add a query vector to the search
    *
    * This method can be called multiple times to add multiple query vectors
-   * to the search. A column called `query_index` will be added to indicate the index
-   * of the query vector that produced the result. Flat searches share one table scan
-   * across the query vectors, avoiding the scan and memory amplification of running
-   * multiple queries concurrently. Indexed searches may still perform per-vector
-   * index work.
+   * to the search. If multiple query vectors are added, then they will be searched
+   * in parallel, and the results will be concatenated. A column called `query_index`
+   * will be added to indicate the index of the query vector that produced the result.
+   *
+   * Performance wise, this is equivalent to running multiple queries concurrently.
    */
   addQueryVector(vector: IntoVector): VectorQuery {
     if (vector instanceof Promise) {
-      // Observe the promise as soon as it is accepted. The existing native
-      // query may still be pending, and delaying observation until it resolves
-      // can otherwise surface a fast rejection as unhandled.
-      const settledVector = vector.then(
-        (value) => ({ status: "fulfilled" as const, value }),
-        (reason) => ({ status: "rejected" as const, reason }),
-      );
       const res = (async () => {
-        const inner = await this.getInner();
-        const outcome = await settledVector;
-        if (outcome.status === "rejected") {
-          throw outcome.reason;
+        try {
+          const v = await vector;
+          // biome-ignore lint/suspicious/noExplicitAny: we need to get the `inner`, but js has no package scoping
+          const value: any = this.addQueryVector(v);
+          const inner = value.inner as
+            | NativeVectorQuery
+            | Promise<NativeVectorQuery>;
+          return inner;
+        } catch (e) {
+          return Promise.reject(e);
         }
-        addQueryVectorToNative(inner, outcome.value);
-        return inner;
       })();
       return new VectorQuery(res);
     } else {
-      this.doVectorCall((inner) => addQueryVectorToNative(inner, vector));
+      super.doCall((inner) => {
+        const raw = Array.isArray(vector) ? null : extractVectorBuffer(vector);
+        if (raw) {
+          inner.addQueryVectorRaw(raw.data, raw.dtype);
+        } else {
+          inner.addQueryVector(Float32Array.from(vector as number[]));
+        }
+      });
       return this;
     }
   }
 
   rerank(reranker: Reranker): VectorQuery {
-    this.doVectorCall((inner) =>
+    super.doCall((inner) =>
       inner.rerank(async (args) => {
         const vecResults = await fromBufferToRecordBatch(args.vecResults);
         const ftsResults = await fromBufferToRecordBatch(args.ftsResults);
@@ -778,71 +763,6 @@ export class VectorQuery extends StandardQueryBase<NativeVectorQuery> {
   }
 }
 
-/**
- * Create a string query whose vector/FTS routing is resolved against the active
- * table schema when the query executes.
- *
- * @hidden
- */
-export function createAutoQuery(
-  table: NativeTable,
-  query: string,
-  columns: string[] | null,
-  getVector: (metadata: string) => Promise<Awaited<IntoVector>>,
-): AutoQuery {
-  type RouteSnapshot = {
-    table: NativeTable;
-    embeddingMetadata: string | undefined;
-  };
-  type CachedPreparation = {
-    metadata: string;
-    vector: Promise<Awaited<IntoVector>>;
-  };
-
-  let cachedPreparation: CachedPreparation | undefined;
-
-  const snapshotRoute = async (): Promise<RouteSnapshot> => {
-    const snapshot = await table.querySnapshot();
-    const schema = tableFromIPC(await snapshot.schema()).schema;
-    return {
-      table: snapshot,
-      embeddingMetadata: schema.metadata.get("embedding_functions"),
-    };
-  };
-
-  const createInner = async (): Promise<NativeQuery | NativeVectorQuery> => {
-    const route = await snapshotRoute();
-    if (route.embeddingMetadata === undefined) {
-      const inner = route.table.query();
-      inner.fullTextSearch({ query, columns });
-      return inner;
-    }
-
-    const metadata = route.embeddingMetadata;
-    if (cachedPreparation?.metadata !== metadata) {
-      cachedPreparation = {
-        metadata,
-        vector: Promise.resolve().then(() => getVector(metadata)),
-      };
-    }
-
-    const preparation = cachedPreparation;
-    let vector: Awaited<IntoVector>;
-    try {
-      vector = await preparation.vector;
-    } catch (error) {
-      if (cachedPreparation === preparation) {
-        cachedPreparation = undefined;
-      }
-      throw error;
-    }
-
-    return nearestToNative(route.table.query(), vector);
-  };
-
-  return new AutoQuery(createInner);
-}
-
 /**
  * A query that returns a subset of the rows in the table.
  *
@@ -868,51 +788,6 @@ export class TakeQuery extends QueryBase<NativeTakeQuery> {
   }
 }
 
-/**
- * A builder for automatic string searches.
- *
- * Automatic search determines whether to use full-text or vector search from
- * the table revision selected for each execution. This builder exposes the
- * common operations supported by both query families.
- *
- * @hideconstructor
- */
-export class AutoQuery extends StandardQueryBase<
-  NativeQuery | NativeVectorQuery
-> {
-  private readonly calls: Array<
-    (inner: NativeQuery | NativeVectorQuery) => void
-  > = [];
-
-  /** @hidden */
-  constructor(
-    private readonly createInner: () => Promise<
-      NativeQuery | NativeVectorQuery
-    >,
-  ) {
-    super();
-  }
-
-  /** @hidden */
-  protected override doCall(
-    fn: (inner: NativeQuery | NativeVectorQuery) => void,
-  ) {
-    this.calls.push(fn);
-  }
-
-  /** @hidden */
-  protected override async getInner(): Promise<
-    NativeQuery | NativeVectorQuery
-  > {
-    const calls = [...this.calls];
-    const inner = await this.createInner();
-    for (const call of calls) {
-      call(inner);
-    }
-    return inner;
-  }
-}
-
 /** A builder for LanceDB queries.
  *
  * @see {@link Table#query}, {@link Table#search}
@@ -965,19 +840,45 @@ export class Query extends StandardQueryBase<NativeQuery> {
    * a default `limit` of 10 will be used.  @see {@link Query#limit}
    */
   nearestTo(vector: IntoVector): VectorQuery {
-    const inner = this.inner;
-    if (inner instanceof Promise) {
-      const nativeQuery = inner.then(async (resolvedInner) =>
-        nearestToNative(resolvedInner, await vector),
-      );
+    const callNearestTo = (
+      inner: NativeQuery,
+      resolved: Float32Array | Float64Array | Uint8Array | number[],
+    ): NativeVectorQuery => {
+      const raw = Array.isArray(resolved)
+        ? null
+        : extractVectorBuffer(resolved);
+      if (raw) {
+        return inner.nearestToRaw(raw.data, raw.dtype);
+      }
+      return inner.nearestTo(Float32Array.from(resolved as number[]));
+    };
+
+    if (this.inner instanceof Promise) {
+      const nativeQuery = this.inner.then(async (inner) => {
+        const resolved = vector instanceof Promise ? await vector : vector;
+        return callNearestTo(inner, resolved);
+      });
       return new VectorQuery(nativeQuery);
     }
     if (vector instanceof Promise) {
-      return new VectorQuery(
-        vector.then((resolvedVector) => nearestToNative(inner, resolvedVector)),
-      );
+      const res = (async () => {
+        try {
+          const v = await vector;
+          // biome-ignore lint/suspicious/noExplicitAny: we need to get the `inner`, but js has no package scoping
+          const value: any = this.nearestTo(v);
+          const inner = value.inner as
+            | NativeVectorQuery
+            | Promise<NativeVectorQuery>;
+          return inner;
+        } catch (e) {
+          return Promise.reject(e);
+        }
+      })();
+      return new VectorQuery(res);
+    } else {
+      const vectorQuery = callNearestTo(this.inner, vector);
+      return new VectorQuery(vectorQuery);
     }
-    return new VectorQuery(nearestToNative(inner, vector));
   }
 
   nearestToText(query: string | FullTextQuery, columns?: string[]): Query {

nodejs/lancedb/sanitize.ts

@@ -3,7 +3,7 @@
 
 // The utilities in this file help sanitize data from the user's arrow
 // library into the types expected by vectordb's arrow library.  Node
-// generally allows for multiple versions of the same library (and sometimes
+// generally allows for mulitple versions of the same library (and sometimes
 // even multiple copies of the same version) to be installed at the same
 // time.  However, arrow-js uses instanceof which expected that the input
 // comes from the exact same library instance.  This is not always the case
@@ -94,24 +94,17 @@ export function sanitizeMetadata(
   if (metadataLike === undefined || metadataLike === null) {
     return undefined;
   }
-
-  let entries: IterableIterator<[unknown, unknown]>;
-  try {
-    entries = Map.prototype.entries.call(metadataLike);
-  } catch {
+  if (!(metadataLike instanceof Map)) {
     throw Error("Expected metadata, if present, to be a Map<string, string>");
   }
-
-  const metadata = new Map<string, string>();
-  for (const [key, value] of entries) {
-    if (typeof key !== "string" || typeof value !== "string") {
+  for (const item of metadataLike) {
+    if (typeof item[0] !== "string" || typeof item[1] !== "string") {
       throw Error(
         "Expected metadata, if present, to be a Map<string, string> but it had non-string keys or values",
       );
     }
-    metadata.set(key, value);
   }
-  return metadata;
+  return metadataLike as Map<string, string>;
 }
 
 export function sanitizeInt(typeLike: object) {

nodejs/lancedb/schema.ts

@@ -1,567 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-import {
-  Binary,
-  Bool,
-  DataType,
-  Dictionary,
-  Field,
-  FixedSizeList,
-  Float32,
-  Float64,
-  Int32,
-  Int64,
-  List,
-  Schema,
-  Struct,
-  Utf8,
-  util as arrowUtil,
-} from "apache-arrow";
-import { typedArrayToArrowType } from "./arrow_type";
-import { sanitizeType } from "./sanitize";
-
-type InferenceOptions = {
-  dictionaryEncodeStrings: boolean;
-  vectorColumns: Record<string, { type: unknown }>;
-};
-
-/**
- * Infer the Arrow schema represented by a set of records.
- *
- * This is the intentionally small interface to schema inference. The stateful
- * details of combining partial type evidence are encapsulated below so callers
- * only need to provide records, an optional schema, and inference options.
- */
-export function inferSchema(
-  data: Array<Record<string, unknown>>,
-  schema: Schema | undefined,
-  options: InferenceOptions,
-): Schema {
-  return new SchemaInferrer(schema, options).infer(data);
-}
-
-class SchemaInferrer {
-  private readonly fields = new FieldTree();
-
-  constructor(
-    private readonly providedSchema: Schema | undefined,
-    private readonly options: InferenceOptions,
-  ) {}
-
-  infer(data: Array<Record<string, unknown>>): Schema {
-    for (const [row, record] of data.entries()) {
-      for (const [path, value] of recordPathsAndValues(record)) {
-        this.observe(path, value, row);
-      }
-    }
-
-    return this.providedSchema === undefined
-      ? new Schema(fieldsFromTree(this.fields))
-      : new Schema(matchingFields(this.providedSchema.fields, this.fields));
-  }
-
-  private observe(path: string[], value: unknown, row: number): void {
-    const current = this.fields.get(path);
-    if (current === undefined) {
-      this.addField(path, value, row);
-    } else if (this.providedSchema === undefined) {
-      this.updateInferredField(path, value, row, current);
-    }
-  }
-
-  private addField(path: string[], value: unknown, row: number): void {
-    if (this.providedSchema !== undefined) {
-      this.addSchemaField(this.providedSchema, path, row);
-      return;
-    }
-
-    const evidence =
-      this.inferType(value, path) ?? DeferredTypeEvidence.from(value, row);
-    if (evidence === undefined) {
-      throw typeInferenceError(path, row);
-    }
-
-    const conflict = this.fields.set(
-      path,
-      evidence,
-      (existing) =>
-        existing instanceof DeferredTypeEvidence && existing.isOnlyNulls(),
-    );
-    if (conflict !== undefined) {
-      throw branchConflictError(conflict, row, "Struct");
-    }
-  }
-
-  private addSchemaField(schema: Schema, path: string[], row: number): void {
-    const field = fieldAtPath(schema, path);
-    if (field === undefined) {
-      throw new Error(
-        `Found field not in schema: ${path.join(".")} at row ${row}`,
-      );
-    }
-
-    const conflict = this.fields.set(path, field.type);
-    if (conflict !== undefined) {
-      throw branchConflictError(conflict, row, "Struct");
-    }
-  }
-
-  private updateInferredField(
-    path: string[],
-    value: unknown,
-    row: number,
-    current: FieldNode,
-  ): void {
-    const newType = this.inferType(value, path);
-    const deferred = DeferredTypeEvidence.from(value, row);
-
-    if (current instanceof FieldTree) {
-      if (deferred?.isOnlyNulls()) {
-        return;
-      }
-      throw schemaInferenceError(
-        path,
-        row,
-        "Struct",
-        describeEvidence(newType ?? deferred),
-      );
-    }
-
-    if (current instanceof DeferredTypeEvidence) {
-      this.resolveDeferredField(path, row, current, newType, deferred);
-      return;
-    }
-
-    if (newType !== undefined) {
-      if (!inferredTypesEqual(current, newType)) {
-        throw schemaInferenceError(
-          path,
-          row,
-          describeEvidence(current),
-          describeEvidence(newType),
-        );
-      }
-      return;
-    }
-
-    if (deferred === undefined || !deferred.matches(current)) {
-      throw schemaInferenceError(
-        path,
-        row,
-        describeEvidence(current),
-        describeEvidence(deferred),
-      );
-    }
-  }
-
-  private resolveDeferredField(
-    path: string[],
-    row: number,
-    current: DeferredTypeEvidence,
-    newType: DataType | undefined,
-    deferred: DeferredTypeEvidence | undefined,
-  ): void {
-    if (newType !== undefined) {
-      if (!current.matches(newType)) {
-        throw schemaInferenceError(
-          path,
-          row,
-          current.describe(),
-          describeEvidence(newType),
-        );
-      }
-      this.fields.set(path, newType);
-      return;
-    }
-
-    if (deferred !== undefined) {
-      this.fields.set(path, current.merge(deferred));
-      return;
-    }
-
-    throw schemaInferenceError(
-      path,
-      row,
-      current.describe(),
-      describeEvidence(newType),
-    );
-  }
-
-  private inferType(value: unknown, path: string[]): DataType | undefined {
-    if (typeof value === "bigint") {
-      return new Int64();
-    }
-    if (typeof value === "number") {
-      return new Float64();
-    }
-    if (typeof value === "string") {
-      return this.options.dictionaryEncodeStrings
-        ? new Dictionary(new Utf8(), new Int32())
-        : new Utf8();
-    }
-    if (typeof value === "boolean") {
-      return new Bool();
-    }
-    if (value instanceof Buffer) {
-      return new Binary();
-    }
-    if (ArrayBuffer.isView(value) && !(value instanceof DataView)) {
-      const typedArray = typedArrayToArrowType(value);
-      return typedArray === undefined
-        ? undefined
-        : new FixedSizeList(
-            typedArray.length,
-            new Field("item", typedArray.elementType, true),
-          );
-    }
-    if (!Array.isArray(value) || value.length === 0) {
-      return undefined;
-    }
-
-    const configuredVector =
-      path.length === 1 ? this.options.vectorColumns[path[0]] : undefined;
-    if (configuredVector !== undefined) {
-      return new FixedSizeList(
-        value.length,
-        new Field("item", sanitizeType(configuredVector.type), true),
-      );
-    }
-
-    const itemType = this.inferArrayItemType(value, path);
-    if (itemType === undefined) {
-      return undefined;
-    }
-
-    return nameSuggestsVectorColumn(path[path.length - 1])
-      ? new FixedSizeList(value.length, new Field("item", new Float32(), true))
-      : new List(new Field("item", itemType, true));
-  }
-
-  private inferArrayItemType(
-    values: unknown[],
-    path: string[],
-  ): DataType | undefined {
-    let itemType: DataType | undefined;
-    const deferredItems: unknown[] = [];
-
-    for (const value of values) {
-      const candidate = this.inferType(value, path);
-      if (candidate === undefined) {
-        if (!isDeferredValue(value)) {
-          return undefined;
-        }
-        deferredItems.push(value);
-      } else if (itemType === undefined) {
-        itemType = candidate;
-      } else if (!inferredTypesEqual(itemType, candidate)) {
-        return undefined;
-      }
-    }
-
-    if (itemType === undefined) {
-      return undefined;
-    }
-    return deferredItems.every((value) =>
-      deferredValueMatchesType(value, itemType),
-    )
-      ? itemType
-      : undefined;
-  }
-}
-
-/** Nulls and empty/all-null lists that do not determine a type by themselves. */
-class DeferredTypeEvidence {
-  private constructor(
-    private readonly values: Array<{ value: unknown; row: number }>,
-  ) {}
-
-  static from(value: unknown, row: number): DeferredTypeEvidence | undefined {
-    return isDeferredValue(value)
-      ? new DeferredTypeEvidence([{ value, row }])
-      : undefined;
-  }
-
-  isOnlyNulls(): boolean {
-    return this.values.every(({ value }) => value == null);
-  }
-
-  matches(type: DataType): boolean {
-    return this.values.every(({ value }) =>
-      deferredValueMatchesType(value, type),
-    );
-  }
-
-  merge(other: DeferredTypeEvidence): DeferredTypeEvidence {
-    return new DeferredTypeEvidence([...this.values, ...other.values]);
-  }
-
-  describe(): string {
-    const list = this.values.find(({ value }) => Array.isArray(value));
-    return list === undefined
-      ? "null"
-      : `List[${(list.value as unknown[]).length}]`;
-  }
-
-  firstRow(): number {
-    return this.values[0].row;
-  }
-}
-
-type FieldNode = DataType | DeferredTypeEvidence | FieldTree;
-type LeafNode = Exclude<FieldNode, FieldTree>;
-type FieldConflict = { path: string[]; value: FieldNode };
-
-/** Nested field state, kept separate from Arrow's eventual Struct types. */
-class FieldTree {
-  private readonly children = new Map<string, FieldNode>();
-
-  get(path: string[]): FieldNode | undefined {
-    let current: FieldNode = this;
-    for (const part of path) {
-      if (!(current instanceof FieldTree)) {
-        return undefined;
-      }
-      const child = current.children.get(part);
-      if (child === undefined) {
-        return undefined;
-      }
-      current = child;
-    }
-    return current;
-  }
-
-  set(
-    path: string[],
-    value: LeafNode,
-    canReplaceLeaf: (value: LeafNode) => boolean = () => false,
-  ): FieldConflict | undefined {
-    let branch: FieldTree = this;
-    for (const [index, part] of path.slice(0, -1).entries()) {
-      const child = branch.children.get(part);
-      if (child === undefined || (isLeaf(child) && canReplaceLeaf(child))) {
-        const nextBranch = new FieldTree();
-        branch.children.set(part, nextBranch);
-        branch = nextBranch;
-      } else if (child instanceof FieldTree) {
-        branch = child;
-      } else {
-        return { path: path.slice(0, index + 1), value: child };
-      }
-    }
-
-    const name = path[path.length - 1];
-    const current = branch.children.get(name);
-    if (current instanceof FieldTree) {
-      return { path, value: current };
-    }
-    branch.children.set(name, value);
-    return undefined;
-  }
-
-  entries(): IterableIterator<[string, FieldNode]> {
-    return this.children.entries();
-  }
-
-  has(name: string): boolean {
-    return this.children.has(name);
-  }
-}
-
-function isLeaf(value: FieldNode): value is LeafNode {
-  return !(value instanceof FieldTree);
-}
-
-function fieldsFromTree(tree: FieldTree, path: string[] = []): Field[] {
-  const fields: Field[] = [];
-  for (const [name, value] of tree.entries()) {
-    if (value instanceof FieldTree) {
-      fields.push(
-        new Field(
-          name,
-          new Struct(fieldsFromTree(value, [...path, name])),
-          true,
-        ),
-      );
-    } else if (value instanceof DeferredTypeEvidence) {
-      throw typeInferenceError([...path, name], value.firstRow());
-    } else {
-      fields.push(new Field(name, value, true));
-    }
-  }
-  return fields;
-}
-
-function matchingFields(fields: Field[], tree: FieldTree): Field[] {
-  const matches: Field[] = [];
-  for (const field of fields) {
-    if (!tree.has(field.name)) {
-      continue;
-    }
-    const value = tree.get([field.name]);
-    if (value instanceof FieldTree) {
-      const struct = field.type as Struct;
-      matches.push(
-        new Field(
-          field.name,
-          new Struct(matchingFields(struct.children, value)),
-          field.nullable,
-          field.metadata,
-        ),
-      );
-    } else {
-      matches.push(field);
-    }
-  }
-  return matches;
-}
-
-function* recordPathsAndValues(
-  record: Record<string, unknown>,
-  path: string[] = [],
-): Generator<[string[], unknown]> {
-  for (const [name, value] of Object.entries(record)) {
-    if (isRecord(value)) {
-      yield* recordPathsAndValues(value, [...path, name]);
-    } else if (value !== undefined) {
-      yield [[...path, name], value];
-    }
-  }
-}
-
-function isRecord(value: unknown): value is Record<string, unknown> {
-  return (
-    typeof value === "object" &&
-    value !== null &&
-    !Array.isArray(value) &&
-    !(value instanceof RegExp) &&
-    !(value instanceof Date) &&
-    !(value instanceof Set) &&
-    !(value instanceof Map) &&
-    !(value instanceof Buffer) &&
-    !ArrayBuffer.isView(value)
-  );
-}
-
-function fieldAtPath(schema: Schema, path: string[]): Field | undefined {
-  let fields = schema.fields;
-  let field: Field | undefined;
-  for (const [index, name] of path.entries()) {
-    field = fields.find((candidate) => candidate.name === name);
-    if (field === undefined || index === path.length - 1) {
-      return field;
-    }
-    if (!DataType.isStruct(field.type)) {
-      return undefined;
-    }
-    fields = field.type.children;
-  }
-  return field;
-}
-
-function isDeferredValue(value: unknown): boolean {
-  return (
-    value == null || (Array.isArray(value) && value.every(isDeferredValue))
-  );
-}
-
-function deferredValueMatchesType(value: unknown, type: DataType): boolean {
-  if (value == null) {
-    return true;
-  }
-  if (!Array.isArray(value)) {
-    return false;
-  }
-  if (DataType.isList(type)) {
-    return value.every((item) =>
-      deferredValueMatchesType(item, type.valueType),
-    );
-  }
-  if (DataType.isFixedSizeList(type)) {
-    return (
-      value.length === type.listSize &&
-      value.every((item) => deferredValueMatchesType(item, type.valueType))
-    );
-  }
-  return false;
-}
-
-function inferredTypesEqual(current: DataType, candidate: DataType): boolean {
-  if (DataType.isDictionary(current)) {
-    return (
-      DataType.isDictionary(candidate) &&
-      current.isOrdered === candidate.isOrdered &&
-      inferredTypesEqual(current.indices, candidate.indices) &&
-      inferredTypesEqual(current.dictionary, candidate.dictionary)
-    );
-  }
-  if (DataType.isList(current)) {
-    return (
-      DataType.isList(candidate) &&
-      current.valueField.name === candidate.valueField.name &&
-      current.valueField.nullable === candidate.valueField.nullable &&
-      inferredTypesEqual(current.valueType, candidate.valueType)
-    );
-  }
-  if (DataType.isFixedSizeList(current)) {
-    return (
-      DataType.isFixedSizeList(candidate) &&
-      current.listSize === candidate.listSize &&
-      current.valueField.name === candidate.valueField.name &&
-      current.valueField.nullable === candidate.valueField.nullable &&
-      inferredTypesEqual(current.valueType, candidate.valueType)
-    );
-  }
-  return arrowUtil.compareTypes(current, candidate);
-}
-
-function describeEvidence(
-  evidence: DataType | DeferredTypeEvidence | undefined,
-): string {
-  if (evidence === undefined) {
-    return "an unsupported value";
-  }
-  return evidence instanceof DeferredTypeEvidence
-    ? evidence.describe()
-    : evidence.toString();
-}
-
-function branchConflictError(
-  conflict: FieldConflict,
-  row: number,
-  candidate: string,
-): Error {
-  return schemaInferenceError(
-    conflict.path,
-    row,
-    conflict.value instanceof FieldTree
-      ? "Struct"
-      : describeEvidence(conflict.value),
-    candidate,
-  );
-}
-
-function schemaInferenceError(
-  path: string[],
-  row: number,
-  currentType: string,
-  newType: string,
-): Error {
-  return new Error(
-    `Failed to infer schema for data. Previously inferred type ${currentType} ` +
-      `but found ${newType} for field ${path.join(".")} at row ${row}. ` +
-      "Consider providing an explicit schema.",
-  );
-}
-
-function typeInferenceError(path: string[], row: number): Error {
-  return new Error(
-    `Failed to infer data type for field ${path.join(".")} at row ${row}. ` +
-      "Consider providing an explicit schema.",
-  );
-}
-
-function nameSuggestsVectorColumn(name: string): boolean {
-  const normalized = name.toLowerCase();
-  return normalized.includes("vector") || normalized.includes("embedding");
-}

nodejs/lancedb/table.ts

@@ -17,10 +17,8 @@ import {
   tableFromIPC,
 } from "./arrow";
 
-import { BlobFile } from "./blob";
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { IndexOptions } from "./indices";
-import { Job } from "./job";
 import { MergeInsertBuilder } from "./merge";
 import {
   AddColumnsResult,
@@ -32,6 +30,7 @@ import {
   DropColumnsResult,
   IndexConfig,
   IndexStatistics,
+  Job,
   LsmStats,
   Branches as NativeBranches,
   OptimizeStats,
@@ -44,12 +43,10 @@ import {
   Table as _NativeTable,
 } from "./native";
 import {
-  AutoQuery,
   FullTextQuery,
   Query,
   TakeQuery,
   VectorQuery,
-  createAutoQuery,
   instanceOfFullTextQuery,
 } from "./query";
 import { sanitizeType } from "./sanitize";
@@ -314,7 +311,7 @@ export abstract class Table {
    * Note: if your condition is something like "some_id_column == 7" and
    * you are updating many rows (with different ids) then you will get
    * better performance with a single [`merge_insert`] call instead of
-   * repeatedly calling this method.
+   * repeatedly calilng this method.
    * @param {Map<string, string> | Record<string, string>} updates - the
    * columns to update
    * @returns {Promise<UpdateResult>} A promise that resolves to an object
@@ -511,35 +508,6 @@ export abstract class Table {
    */
   abstract takeRowIds(rowIds: readonly (bigint | number)[]): TakeQuery;
 
-  /**
-   * Blob v2 columns, including nested dotted paths.
-   */
-  abstract blobColumns(): Promise<string[]>;
-
-  /**
-   * Bytes for `column` at row IDs from {@link Query.withRowId}.
-   *
-   * Reads the table's current checkout. IDs from another version can fail after
-   * compaction unless stable row ids are enabled. Results keep input order and
-   * duplicates. Null blobs are `null`. Empty blobs are empty buffers.
-   */
-  abstract fetchBlobs(
-    column: string,
-    rowIds: readonly (bigint | number)[],
-  ): Promise<(Buffer | null)[]>;
-
-  /**
-   * Opens lazy blob handles for `column` at the given row IDs using the
-   * table's current checkout.
-   *
-   * Preserves input order, duplicates, and nulls. Use this for large payloads.
-   * See {@link Table.fetchBlobs} for row-ID validity across versions.
-   */
-  abstract fetchBlobFiles(
-    column: string,
-    rowIds: readonly (bigint | number)[],
-  ): Promise<(BlobFile | null)[]>;
-
   /**
    * Create a search query to find the nearest neighbors
    * of the given query
@@ -555,7 +523,7 @@ export abstract class Table {
     query: string | IntoVector | MultiVector | FullTextQuery,
     queryType?: string,
     ftsColumns?: string | string[],
-  ): VectorQuery | Query | AutoQuery;
+  ): VectorQuery | Query;
   /**
    * Search the table with a given query vector.
    *
@@ -660,18 +628,6 @@ export abstract class Table {
 
   /**
    * Update per-field (column) metadata.
-   *
-   * The following keys are treated specially, by convention, and should be
-   * used when appropriate:
-   *
-   * - `lancedb:description`: for a human-readable description of a field.
-   * - `lancedb:tag:<name>`: for a user-defined key-value tag, where the suffix
-   *   names the tag category; e.g. `lancedb:tag:model: "clip"`.
-   * - `lancedb:logical-column`: for a column grouping; e.g. `feature_v1` and
-   *   `feature_v2` might be in the same logical column.
-   * - `lancedb:status`: for status options (`production`, `candidate`,
-   *   `deprecated`, `archived`) to designate the current life cycle state of
-   *   this column.
    * @param {FieldMetadataUpdate[]} updates One or more per-field updates. Each
    * update's metadata is merged into the field's existing metadata by default;
    * a value of `null` deletes that key, and `replace: true` swaps the whole map.
@@ -949,16 +905,6 @@ export abstract class Table {
   /** Return the table as an arrow table */
   abstract toArrow(): Promise<ArrowTable>;
 
-  /**
-   * Create a {@link MergeInsertBuilder}, which combines new data with the
-   * existing table in a single transaction — inserting, updating and deleting
-   * rows depending on how they match.
-   *
-   * @param on - The column, or columns, to match source rows against target
-   * rows on. Typically a key or id column. Several columns match on the
-   * composite key: a source row updates a target row only when it agrees on
-   * every one of them.
-   */
   abstract mergeInsert(on: string | string[]): MergeInsertBuilder;
 
   /** List all the stats of a specified index
@@ -1029,11 +975,10 @@ export class LocalTable extends Table {
     return this.inner.display();
   }
 
-  private async getEmbeddingFunctions(
-    inner: _NativeTable = this.inner,
-  ): Promise<Map<string, EmbeddingFunctionConfig>> {
-    const schemaBuf = await inner.schema();
-    const schema = tableFromIPC(schemaBuf).schema;
+  private async getEmbeddingFunctions(): Promise<
+    Map<string, EmbeddingFunctionConfig>
+  > {
+    const schema = await this.schema();
     const registry = getRegistry();
     return registry.parseFunctions(schema.metadata);
   }
@@ -1154,15 +1099,13 @@ export class LocalTable extends Table {
   ): Promise<Job> {
     // biome-ignore lint/suspicious/noExplicitAny: skip
     const nativeIndex = (options?.config as any)?.inner;
-    return new Job(
-      await this.inner.createIndexAsync(
-        nativeIndex,
-        column,
-        options?.replace,
-        options?.waitTimeoutSeconds,
-        options?.name,
-        options?.train,
-      ),
+    return await this.inner.createIndexAsync(
+      nativeIndex,
+      column,
+      options?.replace,
+      options?.waitTimeoutSeconds,
+      options?.name,
+      options?.train,
     );
   }
 
@@ -1190,34 +1133,23 @@ export class LocalTable extends Table {
   }
 
   takeRowIds(rowIds: readonly (bigint | number)[]): TakeQuery {
-    return new TakeQuery(this.inner.takeRowIds(rowIdsToBigInts(rowIds)));
-  }
+    const ids = rowIds.map((id) => {
+      if (typeof id === "bigint") {
+        return id;
+      }
+      if (!Number.isInteger(id)) {
+        throw new Error("Row id must be an integer (or bigint)");
+      }
+      if (id < 0) {
+        throw new Error("Row id cannot be negative");
+      }
+      if (!Number.isSafeInteger(id)) {
+        throw new Error("Row id is too large for number; use bigint instead");
+      }
+      return BigInt(id);
+    });
 
-  blobColumns(): Promise<string[]> {
-    return this.inner.blobColumns();
-  }
-
-  async fetchBlobs(
-    column: string,
-    rowIds: readonly (bigint | number)[],
-  ): Promise<(Buffer | null)[]> {
-    const values = await this.inner.fetchBlobs(column, rowIdsToBigInts(rowIds));
-    // N-API Option maps missing values to undefined. Collapse those to null.
-    return values.map((value) => value ?? null);
-  }
-
-  async fetchBlobFiles(
-    column: string,
-    rowIds: readonly (bigint | number)[],
-  ): Promise<(BlobFile | null)[]> {
-    const files = await this.inner.fetchBlobFiles(
-      column,
-      rowIdsToBigInts(rowIds),
-    );
-    // N-API Option maps missing values to undefined. Collapse those to null.
-    return files.map((file) =>
-      file == null ? null : BlobFile.fromNative(file),
-    );
+    return new TakeQuery(this.inner.takeRowIds(ids));
   }
 
   query(): Query {
@@ -1228,7 +1160,7 @@ export class LocalTable extends Table {
     query: string | IntoVector | MultiVector | FullTextQuery,
     queryType: string = "auto",
     ftsColumns?: string | string[],
-  ): VectorQuery | Query | AutoQuery {
+  ): VectorQuery | Query {
     if (typeof query !== "string" && !instanceOfFullTextQuery(query)) {
       if (queryType === "fts") {
         throw new Error("Cannot perform full text search on a vector query");
@@ -1243,28 +1175,14 @@ export class LocalTable extends Table {
       });
     }
 
-    if (queryType === "auto") {
-      if (instanceOfFullTextQuery(query)) {
-        return this.query().fullTextSearch(query, {
-          columns: ftsColumns,
-        });
-      }
-
-      const columns =
-        typeof ftsColumns === "string" ? [ftsColumns] : (ftsColumns ?? null);
-      return createAutoQuery(this.inner, query, columns, async (metadata) => {
-        const functions = await getRegistry().parseFunctions(
-          new Map([["embedding_functions", metadata]]),
-        );
-        // TODO: Support multiple embedding functions
-        const embeddingFunc: EmbeddingFunctionConfig | undefined = functions
-          .values()
-          .next().value;
-        // The route only calls this callback when embedding metadata exists.
-        // parseFunctions either yields a provider or reports malformed metadata.
-        if (!embeddingFunc)
-          throw new Error("Invalid embedding function metadata");
-        return await embeddingFunc.function.computeQueryEmbeddings(query);
+    // The query type is auto or vector
+    // fall back to full text search if no embedding functions are defined and the query is a string
+    if (
+      queryType === "auto" &&
+      (getRegistry().length() === 0 || instanceOfFullTextQuery(query))
+    ) {
+      return this.query().fullTextSearch(query, {
+        columns: ftsColumns,
       });
     }
 
@@ -1356,7 +1274,7 @@ export class LocalTable extends Table {
   }
 
   async refreshColumnAsync(column: string): Promise<Job> {
-    return new Job(await this.inner.refreshColumnAsync(column));
+    return await this.inner.refreshColumnAsync(column);
   }
 
   async refreshMaterializedView(
@@ -1620,8 +1538,7 @@ export interface FieldMetadataUpdate {
   path: string;
   /**
    * Metadata key/value pairs. Merged into the field's existing metadata by
-   * default; a value of `null` deletes that key. See
-   * {@link Table.updateFieldMetadata} for the conventional `lancedb:*` keys.
+   * default; a value of `null` deletes that key.
    */
   metadata: Record<string, string | null>;
   /** If true, replace the field's entire metadata map instead of merging. */
@@ -1774,21 +1691,3 @@ export class Branches {
     )) as unknown as CherryPickResult;
   }
 }
-
-function rowIdsToBigInts(rowIds: readonly (bigint | number)[]): bigint[] {
-  return rowIds.map((id) => {
-    if (typeof id === "bigint") {
-      return id;
-    }
-    if (!Number.isInteger(id)) {
-      throw new Error("Row id must be an integer (or bigint)");
-    }
-    if (id < 0) {
-      throw new Error("Row id cannot be negative");
-    }
-    if (!Number.isSafeInteger(id)) {
-      throw new Error("Row id is too large for number; use bigint instead");
-    }
-    return BigInt(id);
-  });
-}

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0-beta.6",
 	"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": "0.39.0-beta.6",
+	"version": "0.38.0-beta.6",
 	"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": "0.39.0-beta.6",
+	"version": "0.38.0-beta.6",
 	"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": "0.39.0-beta.6",
+	"version": "0.38.0-beta.6",
 	"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": "0.39.0-beta.6",
+	"version": "0.38.0-beta.6",
 	"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": "0.39.0-beta.6",
+  "version": "0.38.0-beta.6",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.39.0-beta.6",
+	"version": "0.38.0-beta.6",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.39.0-beta.6",
+  "version": "0.38.0-beta.6",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",
@@ -44,7 +44,7 @@
     "@biomejs/biome": "^1.7.3",
     "@jest/globals": "^29.7.0",
     "@napi-rs/cli": "3.7.0",
-    "@opentelemetry/sdk-metrics": "^2.10.0",
+    "@opentelemetry/sdk-metrics": "^1.30.0",
     "@types/axios": "^0.14.0",
     "@types/jest": "^29.1.2",
     "@types/node": "22.7.4",
@@ -56,7 +56,7 @@
     "eslint": "^8.57.0",
     "jest": "^29.7.0",
     "shx": "^0.3.4",
-    "tmp": "^0.2.7",
+    "tmp": "^0.2.3",
     "ts-jest": "^29.1.2",
     "typedoc": "0.26.4",
     "typedoc-plugin-markdown": "4.2.1",
@@ -67,7 +67,7 @@
     "timeout": "3m"
   },
   "engines": {
-    "node": ">= 22"
+    "node": ">= 18"
   },
   "packageManager": "pnpm@11.1.1",
   "cpu": ["x64", "arm64"],
@@ -101,7 +101,7 @@
     "openai": "4.29.2"
   },
   "peerDependencies": {
-    "@types/node": ">=22",
+    "@types/node": ">=18",
     "apache-arrow": ">=15.0.0 <=18.1.0"
   },
   "peerDependenciesMeta": {

nodejs/pnpm-workspace.yaml

@@ -16,41 +16,3 @@ allowBuilds:
   onnxruntime-node: true
   protobufjs: true
   sharp: true
-
-minimumReleaseAgeExclude:
-  - protobufjs@7.5.8
-  - tmp@0.2.6
-  - form-data@4.0.6
-  - tar@7.5.16
-  - markdown-it@14.1.2
-  - linkify-it@5.0.1
-  - js-yaml@3.15.0
-  - js-yaml@4.1.2
-  - protobufjs@7.6.1
-  - protobufjs@7.6.3
-  - '@babel/core@7.29.1'
-  - axios@1.18.0
-  - brace-expansion@2.1.2
-  - brace-expansion@1.1.16
-  - js-yaml@4.3.0
-  - tar@7.5.18
-  - tar@7.5.19
-  - tar@7.5.17
-  - protobufjs@7.6.5
-  - linkify-it@5.0.2
-  - sharp@0.35.0
-  - brace-expansion@1.1.17
-  - brace-expansion@2.1.3
-  - brace-expansion@2.1.4
-  - brace-expansion@1.1.18
-  - js-yaml@3.15.1
-  - js-yaml@4.3.1
-  - tar@7.5.21
-  - '@opentelemetry/core@2.8.0'
-
-# @huggingface/transformers pins sharp ^0.33.5 and no released version has moved
-# past ^0.34.5, all of which inherit the libvips CVEs in GHSA-f88m-g3jw-g9cj.
-# Force the patched line. sharp is only reached by transformers' image pipeline,
-# which LanceDB's text embedding function never uses.
-overrides:
-  sharp: ^0.35.4

nodejs/src/blob.rs

@@ -1,95 +0,0 @@
-// SPDX-License-Identifier: Apache-2.0
-// SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-use std::ops::Range;
-use std::sync::Arc;
-
-use arrow_array::{Array, LargeBinaryArray};
-use lancedb::blob::BlobFile as LanceBlobFile;
-use napi::bindgen_prelude::*;
-use napi_derive::napi;
-
-use crate::error::convert_error;
-
-#[napi]
-pub struct BlobFile {
-    inner: Arc<LanceBlobFile>,
-}
-
-impl BlobFile {
-    pub(crate) fn new(inner: LanceBlobFile) -> Self {
-        Self {
-            inner: Arc::new(inner),
-        }
-    }
-}
-
-#[napi]
-impl BlobFile {
-    #[napi]
-    pub fn size(&self) -> BigInt {
-        BigInt::from(self.inner.size())
-    }
-
-    #[napi]
-    pub async fn read(&self) -> napi::Result<Buffer> {
-        let bytes = self.inner.read().await.map_err(|err| convert_error(&err))?;
-        Ok(Buffer::from(bytes.as_ref()))
-    }
-
-    #[napi]
-    pub async fn read_range(&self, start: BigInt, end: BigInt) -> napi::Result<Buffer> {
-        let range = bigint_range(start, end)?;
-        let bytes = self
-            .inner
-            .read_range(range)
-            .await
-            .map_err(|err| convert_error(&err))?;
-        Ok(Buffer::from(bytes.as_ref()))
-    }
-}
-
-fn bigint_range(start: BigInt, end: BigInt) -> napi::Result<Range<u64>> {
-    let start = parse_u64(start, "start")?;
-    let end = parse_u64(end, "end")?;
-    if start > end {
-        return Err(napi::Error::from_reason(format!(
-            "invalid blob range: start ({start}) > end ({end})"
-        )));
-    }
-    Ok(start..end)
-}
-
-fn parse_u64(value: BigInt, name: &str) -> napi::Result<u64> {
-    let (negative, value, lossless) = value.get_u64();
-    if negative {
-        return Err(napi::Error::from_reason(format!(
-            "{name} cannot be negative"
-        )));
-    }
-    if !lossless {
-        return Err(napi::Error::from_reason(format!(
-            "{name} is too large to fit in u64"
-        )));
-    }
-    Ok(value)
-}
-
-pub fn parse_row_ids(row_ids: Vec<BigInt>) -> napi::Result<Vec<u64>> {
-    row_ids
-        .into_iter()
-        .map(|id| parse_u64(id, "row id"))
-        .collect()
-}
-
-pub fn copy_blob_buffers(array: LargeBinaryArray) -> Vec<Option<Buffer>> {
-    (0..array.len())
-        .map(|i| {
-            if array.is_null(i) {
-                None
-            } else {
-                Some(Buffer::from(array.value(i).to_vec()))
-            }
-        })
-        .collect()
-}

nodejs/src/connection.rs

@@ -17,7 +17,6 @@ use lancedb::connection::{ConnectBuilder, Connection as LanceDBConnection, conne
 
 use lance_namespace::models::{
     CreateNamespaceRequest, DescribeNamespaceRequest, DropNamespaceRequest, ListNamespacesRequest,
-    ListTablesRequest,
 };
 use lancedb::ipc::{ipc_file_to_batches, ipc_file_to_schema};
 
@@ -37,12 +36,6 @@ pub struct ListNamespacesResponse {
     pub page_token: Option<String>,
 }
 
-#[napi(object)]
-pub struct ListTablesResponse {
-    pub tables: Vec<String>,
-    pub page_token: Option<String>,
-}
-
 #[napi(object)]
 pub struct CreateNamespaceResponse {
     pub properties: Option<HashMap<String, String>>,
@@ -213,33 +206,6 @@ impl Connection {
         op.execute().await.default_error()
     }
 
-    /// List a page of tables in the database.
-    #[napi(catch_unwind)]
-    pub async fn list_tables(
-        &self,
-        namespace_path: Option<Vec<String>>,
-        page_token: Option<String>,
-        limit: Option<u32>,
-    ) -> napi::Result<ListTablesResponse> {
-        let request = ListTablesRequest {
-            // The root namespace is an empty path, not an absent one: a namespace-backed
-            // database rejects a request that names no namespace.
-            id: Some(namespace_path.unwrap_or_default()),
-            page_token,
-            limit: limit.map(|limit| i32::try_from(limit).unwrap_or(i32::MAX)),
-            ..Default::default()
-        };
-        let response = self
-            .get_inner()?
-            .list_tables(request)
-            .await
-            .default_error()?;
-        Ok(ListTablesResponse {
-            tables: response.tables,
-            page_token: response.page_token,
-        })
-    }
-
     /// Create table from a Apache Arrow IPC (file) buffer.
     ///
     /// Parameters:
@@ -442,15 +408,13 @@ impl Connection {
         self.get_inner()?.drop_all_tables(&ns).await.default_error()
     }
 
-    /// Open a server-side job by id, returning a handle with its record
-    /// already populated. Rejects when the server has no such job.
+    /// A `Job` handle for a server-side job by id.
     ///
-    /// The returned handle answers for its own state, specification, result,
-    /// failure and event history, so there is no separate connection-level
-    /// call for any of them.
-    #[napi(catch_unwind)]
-    pub async fn open_job(&self, job_id: String) -> napi::Result<crate::job::Job> {
-        let job = self.get_inner()?.open_job(&job_id).await.default_error()?;
+    /// The handle is constructed without a server round trip; an unknown id
+    /// surfaces when the handle is used.
+    #[napi]
+    pub fn job(&self, job_id: String) -> napi::Result<crate::job::Job> {
+        let job = self.get_inner()?.job(job_id).default_error()?;
         Ok(crate::job::Job::new(job))
     }
 
@@ -461,6 +425,17 @@ impl Connection {
         Ok(jobs.into_iter().map(Into::into).collect())
     }
 
+    /// Describe a single server-side job by id. `null` when the server has
+    /// no such job.
+    #[napi(catch_unwind)]
+    pub async fn get_job(
+        &self,
+        job_id: String,
+    ) -> napi::Result<Option<crate::job::JobDescription>> {
+        let description = self.get_inner()?.get_job(&job_id).await.default_error()?;
+        Ok(description.map(Into::into))
+    }
+
     /// Request cancellation of a server-side job by id. Returns true if the
     /// server accepted the cancellation, false if no such job exists.
     #[napi(catch_unwind)]
@@ -468,6 +443,34 @@ impl Connection {
         self.get_inner()?.cancel_job(&job_id).await.default_error()
     }
 
+    /// The lifecycle event history of a server-side job (all jobs when
+    /// `job_id` is null), as an Arrow IPC stream buffer. Empty when there is
+    /// no history.
+    #[napi(catch_unwind)]
+    pub async fn job_history(&self, job_id: Option<String>) -> napi::Result<Buffer> {
+        let batches = self
+            .get_inner()?
+            .job_history(job_id.as_deref())
+            .await
+            .default_error()?;
+        let Some(first) = batches.first() else {
+            return Ok(Buffer::from(Vec::<u8>::new()));
+        };
+        let mut out = Vec::new();
+        let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        for batch in &batches {
+            writer
+                .write(batch)
+                .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        }
+        writer
+            .finish()
+            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
+        drop(writer);
+        Ok(Buffer::from(out))
+    }
+
     #[napi(catch_unwind)]
     /// Describe a namespace and return its properties.
     pub async fn describe_namespace(

nodejs/src/job.rs

@@ -3,9 +3,6 @@
 
 use std::sync::Arc;
 
-use arrow_array::RecordBatch;
-use lancedb::job::JobEventsRequest;
-use napi::bindgen_prelude::Buffer;
 use napi_derive::napi;
 
 use crate::error::NapiErrorExt;
@@ -17,12 +14,9 @@ pub struct Job {
 }
 
 impl Job {
-    pub(crate) fn new<T>(inner: lancedb::Job<T>) -> Self
-    where
-        T: Clone + Send + Sync + 'static,
-    {
+    pub(crate) fn new(inner: lancedb::Job) -> Self {
         Self {
-            inner: Arc::new(inner.map(|_| ())),
+            inner: Arc::new(inner),
         }
     }
 }
@@ -58,98 +52,12 @@ impl Job {
     pub async fn cancel(&self) -> napi::Result<()> {
         self.inner.cancel().await.default_error()
     }
-
-    /// Ask the backend for this job's current state, and for a server-side job
-    /// its full record, then cache it for the getters below.
-    ///
-    /// They are all null until this runs, because submitting an operation
-    /// returns only a job id. {@link Job.status} fetches the whole record too;
-    /// {@link Job.wait} records only the terminal state it establishes.
-    #[napi(catch_unwind)]
-    pub async fn refresh(&self) -> napi::Result<()> {
-        self.inner.refresh().await.default_error()
-    }
-
-    /// The last observed lifecycle state, without contacting the backend.
-    #[napi(getter)]
-    pub fn state(&self) -> Option<String> {
-        self.inner.state()
-    }
-
-    /// The job's type, as the server names it. Null for an in-process job,
-    /// which has no server-side record.
-    #[napi(getter)]
-    pub fn job_type(&self) -> Option<String> {
-        self.inner.job_type()
-    }
-
-    /// When the job was created, in milliseconds since the epoch.
-    #[napi(getter)]
-    pub fn creation_ms(&self) -> Option<i64> {
-        self.inner.creation_ms()
-    }
-
-    /// The job-type-specific specification as a JSON string, when present.
-    #[napi(getter)]
-    pub fn spec_json(&self) -> Option<String> {
-        self.inner.spec().map(|spec| spec.to_string())
-    }
-
-    /// The job-type-specific terminal result as a JSON string. Null until the
-    /// job succeeds, so a job that never terminates reports its progress
-    /// through {@link Job.events} instead.
-    #[napi(getter)]
-    pub fn result_json(&self) -> Option<String> {
-        self.inner.result().map(|result| result.to_string())
-    }
-
-    /// Why the job failed, when it failed and the server reports a reason.
-    #[napi(getter)]
-    pub fn failure(&self) -> Option<JobFailureInfo> {
-        self.inner.failure().map(|failure| JobFailureInfo {
-            phase: failure.phase,
-            message: failure.message,
-            retryable: failure.retryable,
-        })
-    }
-
-    /// This job's recorded lifecycle events, as an Arrow IPC stream buffer.
-    /// The TypeScript wrapper turns it into an Arrow table.
-    #[napi(catch_unwind)]
-    pub async fn events(&self, limit: Option<u32>, filter: Option<String>) -> napi::Result<Buffer> {
-        let batches = self
-            .inner
-            .events(JobEventsRequest { limit, filter })
-            .await
-            .default_error()?;
-        batches_to_ipc_buffer(&batches)
-    }
-}
-
-/// Serialise Arrow batches as a single IPC stream for the TypeScript layer.
-fn batches_to_ipc_buffer(batches: &[RecordBatch]) -> napi::Result<Buffer> {
-    let Some(first) = batches.first() else {
-        return Ok(Buffer::from(Vec::<u8>::new()));
-    };
-    let mut out = Vec::new();
-    let mut writer = arrow_ipc::writer::StreamWriter::try_new(&mut out, &first.schema())
-        .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-    for batch in batches {
-        writer
-            .write(batch)
-            .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-    }
-    writer
-        .finish()
-        .map_err(|e| napi::Error::from_reason(e.to_string()))?;
-    drop(writer);
-    Ok(Buffer::from(out))
 }
 
 /// A row from `Connection.listJobs`: one server-side job.
 #[napi(object)]
 pub struct JobInfo {
-    /// The job id -- what `Connection.openJob` and `Connection.cancelJob`
+    /// The job id -- what `Connection.getJob` and `Connection.cancelJob`
     /// accept.
     pub job_id: String,
     /// The table the job runs against, without URI or namespace.
@@ -180,3 +88,36 @@ pub struct JobFailureInfo {
     pub message: Option<String>,
     pub retryable: Option<bool>,
 }
+
+/// A described job from `Connection.getJob`.
+#[napi(object)]
+pub struct JobDescription {
+    pub job_id: String,
+    pub job_type: String,
+    /// Lifecycle state: "running", "finished", "failed", or "cancelled".
+    pub state: String,
+    /// When the job was created, in milliseconds since the epoch.
+    pub creation_ms: i64,
+    /// The job-type-specific specification as a JSON string, when present.
+    pub spec_json: Option<String>,
+    /// Why the job failed, when the job is failed and the server reports a
+    /// reason.
+    pub failure: Option<JobFailureInfo>,
+}
+
+impl From<lancedb::database::JobDescription> for JobDescription {
+    fn from(description: lancedb::database::JobDescription) -> Self {
+        Self {
+            job_id: description.job_id,
+            job_type: description.job_type,
+            state: description.state,
+            creation_ms: description.creation_ms,
+            spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
+            failure: description.failure.map(|failure| JobFailureInfo {
+                phase: failure.phase,
+                message: failure.message,
+                retryable: failure.retryable,
+            }),
+        }
+    }
+}

nodejs/src/lib.rs

@@ -10,7 +10,6 @@ use std::collections::HashMap;
 use env_logger::Env;
 use napi_derive::*;
 
-mod blob;
 mod connection;
 mod error;
 mod header;

nodejs/src/query.rs

@@ -664,11 +664,7 @@ impl JsFullTextQuery {
 }
 
 fn parse_fts_query(query: Object) -> napi::Result<FullTextSearchQuery> {
-    // `&JsFullTextQuery` recovers a native class reference through napi's borrow-tracked
-    // path, which is only usable from generated `#[napi]` argument conversion. This is a
-    // manual lookup on a nested `Object` property instead, so use `ClassInstance`, which
-    // unwraps the class without requiring a borrow scope.
-    if let Ok(Some(query)) = query.get::<ClassInstance<JsFullTextQuery>>("query") {
+    if let Ok(Some(query)) = query.get::<&JsFullTextQuery>("query") {
         Ok(FullTextSearchQuery::new_query(query.inner.clone()))
     } else if let Ok(Some(query_text)) = query.get::<String>("query") {
         let mut query_text = query_text;

nodejs/src/table.rs

@@ -15,7 +15,6 @@ use napi::bindgen_prelude::*;
 use napi::threadsafe_function::{ThreadsafeFunction, ThreadsafeFunctionCallMode};
 use napi_derive::napi;
 
-use crate::blob::{BlobFile, copy_blob_buffers, parse_row_ids};
 use crate::error::NapiErrorExt;
 use crate::index::Index;
 use crate::merge::NativeMergeInsertBuilder;
@@ -279,13 +278,6 @@ impl Table {
         Ok(Query::new(self.inner_ref()?.query()))
     }
 
-    /// Return a read-only table handle pinned to the current query revision.
-    #[napi(catch_unwind)]
-    pub async fn query_snapshot(&self) -> napi::Result<Self> {
-        let snapshot = self.inner_ref()?.query_snapshot().await.default_error()?;
-        Ok(Self::new(snapshot))
-    }
-
     #[napi(catch_unwind)]
     pub fn take_offsets(&self, offsets: Vec<i64>) -> napi::Result<TakeQuery> {
         Ok(TakeQuery::new(
@@ -330,44 +322,6 @@ impl Table {
         ))
     }
 
-    #[napi(catch_unwind)]
-    pub async fn blob_columns(&self) -> napi::Result<Vec<String>> {
-        self.inner_ref()?.blob_columns().await.default_error()
-    }
-
-    #[napi(catch_unwind)]
-    pub async fn fetch_blobs(
-        &self,
-        column: String,
-        row_ids: Vec<BigInt>,
-    ) -> napi::Result<Vec<Option<Buffer>>> {
-        let row_ids = parse_row_ids(row_ids)?;
-        let array = self
-            .inner_ref()?
-            .fetch_blobs(column.as_str(), &row_ids)
-            .await
-            .default_error()?;
-        Ok(copy_blob_buffers(array))
-    }
-
-    #[napi(catch_unwind)]
-    pub async fn fetch_blob_files(
-        &self,
-        column: String,
-        row_ids: Vec<BigInt>,
-    ) -> napi::Result<Vec<Option<BlobFile>>> {
-        let row_ids = parse_row_ids(row_ids)?;
-        let files = self
-            .inner_ref()?
-            .fetch_blob_files(column.as_str(), &row_ids)
-            .await
-            .default_error()?;
-        Ok(files
-            .into_iter()
-            .map(|file| file.map(BlobFile::new))
-            .collect())
-    }
-
     #[napi(catch_unwind)]
     pub fn vector_search(&self, vector: Float32Array) -> napi::Result<VectorQuery> {
         self.query()?.nearest_to(vector)
@@ -600,12 +554,6 @@ impl Table {
             .default_error()
     }
 
-    #[napi(catch_unwind)]
-    pub async fn checkout_current(&self) -> napi::Result<Self> {
-        let table = self.inner_ref()?.checkout_current().await.default_error()?;
-        Ok(Self::new(table))
-    }
-
     #[napi(catch_unwind)]
     pub async fn checkout(&self, version: i64) -> napi::Result<()> {
         self.inner_ref()?

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.39.0-beta.6"
+version = "0.38.0-beta.6"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -28,7 +28,7 @@ env_logger.workspace = true
 log.workspace = true
 # Maturin enables extension-module mode for Python builds. Keeping it out of
 # Cargo features lets Rust unit tests link against libpython.
-pyo3 = { version = "0.28", features = ["abi3-py310", "chrono", "uuid"] }
+pyo3 = { version = "0.28", features = ["abi3-py310", "chrono"] }
 chrono.workspace = true
 pyo3-async-runtimes = { version = "0.28", features = [
     "attributes",
@@ -40,7 +40,6 @@ serde.workspace = true
 serde_json.workspace = true
 snafu.workspace = true
 tokio.workspace = true
-uuid.workspace = true
 libc = "0.2"
 
 [build-dependencies]

python/pyproject.toml

@@ -101,12 +101,9 @@ azure = ["adlfs>=2024.2.0"]
 [tool.maturin]
 python-source = "python"
 module-name = "lancedb._lancedb"
-# uv installs the project as an editable package before `uv run`, so keep that
-# bootstrap build consistent with `maturin develop`.
-editable-profile = "dev"
 
 [build-system]
-requires = ["maturin>=1.10"]
+requires = ["maturin>=1.9.4"]
 build-backend = "maturin"
 
 [tool.ruff.lint]
@@ -139,7 +136,6 @@ include = [
     "python/lancedb/exceptions.py",
     "python/lancedb/background_loop.py",
     "python/lancedb/schema.py",
-    "python/lancedb/sql.py",
     "python/lancedb/remote/__init__.py",
     "python/lancedb/remote/errors.py",
     "python/lancedb/embeddings/__init__.py",

python/python/lancedb/__init__.py

@@ -6,7 +6,7 @@ import importlib.metadata
 import os
 from concurrent.futures import ThreadPoolExecutor
 from datetime import timedelta
-from typing import Dict, Optional, Union, Any, List, Iterable, TYPE_CHECKING
+from typing import Dict, Optional, Union, Any, List, Iterable
 
 __version__ = importlib.metadata.version("lancedb")
 
@@ -20,20 +20,15 @@ from .db import AsyncConnection, DBConnection, LanceDBConnection
 from .remote import ClientConfig
 from .remote.db import RemoteDBConnection
 from .expr import Expr, col, lit, func
-from .schema import blob, vector
+from .schema import blob, vector, BlobType
 from .job import AsyncJob, Job
-from .sql import AsyncQuery as AsyncSqlQuery
-from .sql import Query as SqlQuery
-from .sql import QueryDescription
 from .functions import (
-    AssignmentMapping as AssignmentMapping,
     FunctionArtifactRequest as FunctionArtifactRequest,
     FunctionApplication as FunctionApplication,
     FunctionBinding as FunctionBinding,
     FunctionRegistrationRequest as FunctionRegistrationRequest,
     FunctionVersion as FunctionVersion,
     PythonRuntimeSpec as PythonRuntimeSpec,
-    RefreshColumnResult as RefreshColumnResult,
     UdfDefinition as UdfDefinition,
     udf as udf,
 )
@@ -53,19 +48,6 @@ from .namespace import (
 )
 
 
-if TYPE_CHECKING:
-    from lance.blob import BlobType as BlobType
-
-
-def __getattr__(name: str):
-    if name == "BlobType":
-        from .schema import BlobType
-
-        globals()["BlobType"] = BlobType
-        return BlobType
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
-
-
 def _check_s3_bucket_with_dots(
     uri: str, storage_options: Optional[Dict[str, str]]
 ) -> None:
@@ -105,7 +87,6 @@ def connect(
     api_key: Optional[str] = None,
     region: str = "us-east-1",
     host_override: Optional[str] = None,
-    sql_host_override: Optional[str] = None,
     read_consistency_interval: Optional[timedelta] = None,
     request_thread_pool: Optional[Union[int, ThreadPoolExecutor]] = None,
     client_config: Union[ClientConfig, Dict[str, Any], None] = None,
@@ -134,9 +115,6 @@ def connect(
         The region to use for LanceDB Cloud.
     host_override: str, optional
         The override url for LanceDB Cloud.
-    sql_host_override: str, optional
-        The remote SQL service endpoint override. The client connects lazily when SQL
-        is first executed and retains that connection.
     read_consistency_interval: timedelta, default None
         The interval at which to check for updates to the table from other
         processes. If None, then consistency is not checked. For performance
@@ -200,18 +178,6 @@ def connect(
     ...     },
     ... )
 
-    For Azure Blob Storage, credentials can be passed directly without setting
-    environment variables:
-
-    >>> azure_storage_options = {
-    ...     "account_name": "some-account",
-    ...     "account_key": "some-key",
-    ... }
-    >>> db = lancedb.connect(  # doctest: +SKIP
-    ...     "az://my-container/my-database",
-    ...     storage_options=azure_storage_options,
-    ... )
-
     For tests and temporary data, use an in-memory database:
 
     >>> db = lancedb.connect("memory://")
@@ -278,7 +244,6 @@ def connect(
             api_key,
             region,
             host_override,
-            sql_host_override=sql_host_override,
             # TODO: remove this (deprecation warning downstream)
             request_thread_pool=request_thread_pool,
             client_config=client_config,
@@ -421,7 +386,6 @@ def deserialize_conn(
             parsed["api_key"],
             parsed.get("region", "us-east-1"),
             host_override=parsed.get("host_override"),
-            sql_host_override=parsed.get("sql_host_override"),
             client_config=parsed.get("client_config"),
             storage_options=storage_options,
         )
@@ -435,7 +399,6 @@ async def connect_async(
     api_key: Optional[str] = None,
     region: str = "us-east-1",
     host_override: Optional[str] = None,
-    sql_host_override: Optional[str] = None,
     read_consistency_interval: Optional[timedelta] = None,
     client_config: Optional[Union[ClientConfig, Dict[str, Any]]] = None,
     storage_options: Optional[Dict[str, str]] = None,
@@ -458,9 +421,6 @@ async def connect_async(
         The region to use for LanceDB Cloud.
     host_override: str, optional
         The override url for LanceDB Cloud.
-    sql_host_override: str, optional
-        The remote SQL service endpoint override. The client connects lazily when SQL
-        is first executed and retains that connection.
     read_consistency_interval: timedelta, default None
         The interval at which to check for updates to the table from other
         processes. If None, then consistency is not checked. For performance
@@ -504,10 +464,6 @@ async def connect_async(
     --------
 
     >>> import lancedb
-    >>> azure_storage_options = {
-    ...     "account_name": "some-account",
-    ...     "account_key": "some-key",
-    ... }
     >>> async def doctest_example():
     ...     # For a local directory, provide a path to the database
     ...     db = await lancedb.connect_async("~/.lancedb")
@@ -515,11 +471,6 @@ async def connect_async(
     ...     db = await lancedb.connect_async("s3://my-bucket/lancedb",
     ...                                      storage_options={
     ...                                          "aws_access_key_id": "***"})
-    ...     # Azure credentials can also be passed directly
-    ...     db = await lancedb.connect_async(
-    ...         "az://my-container/my-database",
-    ...         storage_options=azure_storage_options,
-    ...     )
     ...     # For tests and temporary data, use an in-memory database
     ...     db = await lancedb.connect_async("memory://")
     ...     # Connect to LanceDB cloud
@@ -548,7 +499,6 @@ async def connect_async(
             api_key,
             region,
             host_override,
-            sql_host_override,
             read_consistency_interval_secs,
             client_config,
             storage_options,
@@ -571,7 +521,6 @@ __all__ = [
     "connect_namespace_async",
     "AsyncConnection",
     "AsyncJob",
-    "AsyncSqlQuery",
     "AsyncLanceNamespaceDBConnection",
     "AsyncTable",
     "FtsToken",
@@ -586,8 +535,6 @@ __all__ = [
     "vector",
     "DBConnection",
     "Job",
-    "QueryDescription",
-    "SqlQuery",
     "LanceDBConnection",
     "LanceNamespaceDBConnection",
     "LsmWriteSpec",