chore: update lance dependency to v11.0.0-rc.2

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.39.0-beta.4"
+current_version = "0.38.0-beta.10"
 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"
+          node-version: "18"
-      - uses: pnpm/action-setup@v6
-        with:
-          version: 11.1.1
       # 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: >
+      - run: npx commitlint --extends @commitlint/config-conventional --verbose <<< $COMMIT_MSG
-          pnpm dlx
-          --package @commitlint/cli@21.2.2
-          --package @commitlint/config-conventional@21.2.2
-          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
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
-        # Node version the library claims to support.
+        # 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
+        # pnpm 11 requires Node >= 22.13; use 24 since 22 hits EOL
-        # are identical across matrix legs; the tests below then run on each
+        # in October. Build/install runs on Node 24; tests run on the
-        # supported Node version.
+        # 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
+      # Invoke jest directly because pnpm 11 itself requires Node 22+
-      # against the build-phase Node, not the version selected above.
+      # while the matrix tests on older Node versions.
-      run: node_modules/.bin/jest --verbose
+      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
+      # Docker builds can use rust-cache too. `target/` already lives on the
-      # `target/` lives on the host and rust-cache's prune keeps the entry
+      # host because the whole workspace is bind-mounted into the container, and
-      # small.
+      # 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
+      # bind-mounted from `.cargo-cache` rather than the host's ~/.cargo, so that
-      # explicitly. And the key uses the *host* rustc version, not the compiler
+      # has to be cached explicitly. And the key is derived from the *host* rustc
-      # that built these artifacts -- safe, since cargo fingerprints the real
+      # version, which is not the compiler that produced these artifacts; that is
-      # one; a base-image bump just costs one cold build.
+      # 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
+        # Invoke jest directly because pnpm 11 itself requires Node 22+
-        # against the install-phase Node, not the version selected above.
+        # while the matrix tests on older Node versions.
-        run: node_modules/.bin/jest --verbose
+        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
+          cargo test --profile ci --features $ALL_FEATURES --locked
-          # 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
 
   windows:
     strategy:

.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

@@ -20,10 +20,7 @@ repos:
     hooks:
       - id: local-biome-check
         name: biome check
-        # Use the biome from nodejs/package.json rather than a separately
+        entry: npx @biomejs/biome@1.8.3 check --config-path nodejs/biome.json nodejs/
-        # 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/
         language: system
         types: [text]
         files: "nodejs/.*"

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.lock

@@ -332,34 +332,6 @@ dependencies = [
  "num-traits",
 ]
 
-[[package]]
-name = "arrow-flight"
-version = "58.4.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b2dbe34824c639e43136af8f106992792ab456540d54b880bc320a3192502d2e"
-dependencies = [
- "arrow-arith",
- "arrow-array",
- "arrow-buffer",
- "arrow-cast",
- "arrow-data",
- "arrow-ipc",
- "arrow-ord",
- "arrow-row",
- "arrow-schema",
- "arrow-select",
- "arrow-string",
- "base64 0.22.1",
- "bytes",
- "futures",
- "once_cell",
- "paste",
- "prost",
- "prost-types",
- "tonic",
- "tonic-prost",
-]
-
 [[package]]
 name = "arrow-ipc"
 version = "58.4.0"
@@ -563,9 +535,9 @@ dependencies = [
 
 [[package]]
 name = "async-trait"
-version = "0.1.92"
+version = "0.1.91"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "82f6aeea286b8eb4dd3431a1be1b59d290ace00f5bfd8e2a159bc2a05e2c1667"
+checksum = "ae36dc4177970ef04fde5178d3e2429882def40e57a451f919c098f72baa6cec"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -1157,7 +1129,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "edca88bc138befd0323b20752846e6587272d3b03b0343c8ea28a6f819e6e71f"
 dependencies = [
  "async-trait",
- "axum-core 0.4.5",
+ "axum-core",
  "bytes",
  "futures-util",
  "http 1.5.0",
@@ -1166,7 +1138,7 @@ dependencies = [
  "hyper 1.9.0",
  "hyper-util",
  "itoa",
- "matchit 0.7.3",
+ "matchit",
  "memchr",
  "mime",
  "percent-encoding",
@@ -1184,31 +1156,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "axum"
-version = "0.8.9"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "31b698c5f9a010f6573133b09e0de5408834d0c82f8d7475a89fc1867a71cd90"
-dependencies = [
- "axum-core 0.5.6",
- "bytes",
- "futures-util",
- "http 1.5.0",
- "http-body 1.1.0",
- "http-body-util",
- "itoa",
- "matchit 0.8.4",
- "memchr",
- "mime",
- "percent-encoding",
- "pin-project-lite",
- "serde_core",
- "sync_wrapper",
- "tower",
- "tower-layer",
- "tower-service",
-]
-
 [[package]]
 name = "axum-core"
 version = "0.4.5"
@@ -1230,24 +1177,6 @@ dependencies = [
  "tracing",
 ]
 
-[[package]]
-name = "axum-core"
-version = "0.5.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "08c78f31d7b1291f7ee735c1c6780ccde7785daae9a9206026862dab7d8792d1"
-dependencies = [
- "bytes",
- "futures-core",
- "http 1.5.0",
- "http-body 1.1.0",
- "http-body-util",
- "mime",
- "pin-project-lite",
- "sync_wrapper",
- "tower-layer",
- "tower-service",
-]
-
 [[package]]
 name = "backoff"
 version = "0.4.0"
@@ -1514,9 +1443,9 @@ checksum = "175812e0be2bccb6abe50bb8d566126198344f707e304f45c648fd8f2cc0365e"
 
 [[package]]
 name = "bytemuck"
-version = "1.25.2"
+version = "1.25.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "95832e849adfb21180ccb6826a99da14e5d266ae5c2e668e1602cf234f153797"
+checksum = "c8efb64bd706a16a1bdde310ae86b351e4d21550d98d056f22f8a7f7a2183fec"
 dependencies = [
  "bytemuck_derive",
 ]
@@ -1668,9 +1597,9 @@ checksum = "613afe47fcd5fac7ccf1db93babcb082c5994d996f20b8b159f2ad1658eb5724"
 
 [[package]]
 name = "chacha20"
-version = "0.10.2"
+version = "0.10.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "65c35e4b699c7e15ccbe7ee35c005e4fc0a278d22238a2857e6ce2dadeda1b06"
+checksum = "6f8d983286843e49675a4b7a2d174efe136dc93a18d69130dd18198a6c167601"
 dependencies = [
  "cfg-if 1.0.4",
  "cpufeatures 0.3.0",
@@ -3526,8 +3455,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "rand 0.9.5",
@@ -4886,8 +4815,8 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
 
 [[package]]
 name = "lance"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -4959,8 +4888,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4982,7 +4911,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4996,7 +4925,7 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5005,8 +4934,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrayref",
  "crunchy",
@@ -5016,8 +4945,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5054,8 +4983,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5071,7 +5000,6 @@ dependencies = [
  "datafusion-functions",
  "datafusion-physical-expr",
  "futures",
- "half",
  "jsonb",
  "lance-arrow",
  "lance-core",
@@ -5085,8 +5013,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5103,8 +5031,8 @@ dependencies = [
 
 [[package]]
 name = "lance-derive"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5113,8 +5041,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5147,8 +5075,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5179,8 +5107,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -5244,8 +5172,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index-core"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5267,8 +5195,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5308,8 +5236,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5323,29 +5251,27 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow",
  "async-trait",
  "bytes",
  "lance-core",
  "lance-namespace-reqwest-client",
- "serde",
- "serde_json",
  "snafu 0.9.0",
 ]
 
 [[package]]
 name = "lance-namespace-impls"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow",
  "arrow-ipc",
  "arrow-schema",
  "async-trait",
- "axum 0.7.9",
+ "axum",
  "base64 0.22.1",
  "bytes",
  "chrono",
@@ -5378,9 +5304,9 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-reqwest-client"
-version = "0.12.0"
+version = "0.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d8d23e54b1634d5bbb434f8dd33dc3c05f6e58d876a9a27b3b4aef58ddbe11af"
+checksum = "0a030196da1c994b63a96a4f0bf5b0cfa459fe6dadc9e962320246ca328da22a"
 dependencies = [
  "reqwest 0.12.28",
  "serde",
@@ -5392,8 +5318,8 @@ dependencies = [
 
 [[package]]
 name = "lance-select"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5407,8 +5333,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5448,8 +5374,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5462,8 +5388,8 @@ dependencies = [
 
 [[package]]
 name = "lance-tokenizer"
-version = "12.0.0-beta.14"
+version = "11.0.0-rc.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v12.0.0-beta.14#a8a101774a1c9647065cc60137094feadbe55296"
+source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-rc.2#20e99c87c3bbf6575109ba6ea9608141495bf608"
 dependencies = [
  "frostem",
  "icu_segmenter",
@@ -5476,7 +5402,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.39.0-beta.4"
+version = "0.38.0-beta.10"
 dependencies = [
  "ahash",
  "anyhow",
@@ -5485,7 +5411,6 @@ dependencies = [
  "arrow-buffer",
  "arrow-cast",
  "arrow-data",
- "arrow-flight",
  "arrow-ipc",
  "arrow-ord",
  "arrow-schema",
@@ -5541,7 +5466,6 @@ dependencies = [
  "polars",
  "polars-arrow",
  "pprof 0.14.1",
- "prost",
  "rand 0.9.5",
  "random_word",
  "regex",
@@ -5558,7 +5482,6 @@ dependencies = [
  "test-log",
  "tokenizers",
  "tokio",
- "tonic",
  "url",
  "urlencoding",
  "uuid",
@@ -5567,7 +5490,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.39.0-beta.4"
+version = "0.38.0-beta.10"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5592,7 +5515,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.39.0-beta.4"
+version = "0.38.0-beta.10"
 dependencies = [
  "arrow",
  "async-trait",
@@ -5616,7 +5539,6 @@ dependencies = [
  "serde_json",
  "snafu 0.8.9",
  "tokio",
- "uuid",
 ]
 
 [[package]]
@@ -5826,9 +5748,9 @@ dependencies = [
 
 [[package]]
 name = "log"
-version = "0.4.34"
+version = "0.4.33"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f9f8bd3e56ce4dfc153cf470fffbfa98c7620958b312ca5c3a4b8d5181fd13c6"
+checksum = "0ceec5bc11778974d1bcb055b18002eba7f4b3518b6a0081b3af5f21666da9ad"
 
 [[package]]
 name = "loom"
@@ -5937,12 +5859,6 @@ version = "0.7.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "0e7465ac9959cc2b1404e8e2367b43684a6d13790fe23056cc8c6c5a6b7bcb94"
 
-[[package]]
-name = "matchit"
-version = "0.8.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "47e1ffaa40ddd1f3ed91f717a33c8c0ee23fff369e3aa8772b9605cc1d22f4c3"
-
 [[package]]
 name = "matrixmultiply"
 version = "0.3.10"
@@ -6085,9 +6001,9 @@ dependencies = [
 
 [[package]]
 name = "moka"
-version = "0.12.16"
+version = "0.12.15"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4293f18e7567a1caf3c584855554377025c65e0aa445344d04171f5ad63d19b9"
+checksum = "957228ad12042ee839f93c8f257b62b4c0ab5eaae1d4fa60de53b27c9d7c5046"
 dependencies = [
  "async-lock",
  "crossbeam-channel",
@@ -6181,15 +6097,14 @@ dependencies = [
 
 [[package]]
 name = "napi"
-version = "3.12.2"
+version = "3.11.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58c5f4d5375213fdb7be2655e152386e82f026f9a5ba36a75556e11359aafe09"
+checksum = "de33522036981030a75c231829566bc63414e08101a6f5ff4ac6cef19c8e0941"
 dependencies = [
  "bitflags 2.11.1",
  "chrono",
  "ctor 1.0.12",
  "futures",
- "libc",
  "napi-build",
  "napi-sys",
  "nohash-hasher",
@@ -6201,15 +6116,15 @@ dependencies = [
 
 [[package]]
 name = "napi-build"
-version = "2.4.1"
+version = "2.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60fdf9b392c50e7c4170fa633bd909490ed7835cea4c046776d1a4dd8d2ae0ab"
+checksum = "5282704fbe8d49b0cf8b08e3f33233416a528658f205c7e5ace63b582de0b11c"
 
 [[package]]
 name = "napi-derive"
-version = "3.6.3"
+version = "3.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fa55ea69990c90b888e9e77044410e304ce7f35de599dc6d0b5c1923d2e59af"
+checksum = "4d5c9c02556ea6dc99dffd36c1ce60141411657438501a125b675776d011ce92"
 dependencies = [
  "convert_case",
  "ctor 1.0.12",
@@ -6221,9 +6136,9 @@ dependencies = [
 
 [[package]]
 name = "napi-derive-backend"
-version = "6.1.2"
+version = "6.1.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df4056ac7c18e4438ccf0edaed4340ca0d269278c8ec19284f7b23cb039fd0ae"
+checksum = "d60b5d773ad46c698c8cc2cd9fde0b283d39cbb7f71c04bee633c7bdba4423bd"
 dependencies = [
  "convert_case",
  "proc-macro2",
@@ -7818,7 +7733,6 @@ dependencies = [
  "pyo3-build-config",
  "pyo3-ffi",
  "pyo3-macros",
- "uuid",
 ]
 
 [[package]]
@@ -8687,9 +8601,9 @@ dependencies = [
 
 [[package]]
 name = "roaring"
-version = "0.11.5"
+version = "0.11.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "18bd8a37d17a58532776dcdf6041ce64929adca78e8489d5cacbafe99229d3e1"
+checksum = "1dedc5658c6ecb3bdb5ef5f3295bb9253f42dcf3fd1402c03f6b1f7659c3c4a9"
 dependencies = [
  "bytemuck",
  "byteorder",
@@ -9149,9 +9063,9 @@ dependencies = [
 
 [[package]]
 name = "serde_with"
-version = "3.22.0"
+version = "3.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ee78f1fbe43ac4a0e47aadb3dbd357b69eb0d3793e948624cd03dd2750ab1c0a"
+checksum = "76a5c54c7310e7b8b9577c286d7e399ddd876c3e12b3ed917a8aabc4b96e9e8c"
 dependencies = [
  "base64 0.22.1",
  "bs58",
@@ -9159,7 +9073,6 @@ dependencies = [
  "hex",
  "indexmap 1.9.3",
  "indexmap 2.14.0",
- "jiff",
  "schemars 0.9.0",
  "schemars 1.2.1",
  "serde_core",
@@ -9170,9 +9083,9 @@ dependencies = [
 
 [[package]]
 name = "serde_with_macros"
-version = "3.22.0"
+version = "3.21.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8705578779c2b6bd90d84d66eb2e206b708b1a4d7b9f17641b293545bf1c7e46"
+checksum = "84d57bc0c8b9a17920c178daa6bb924850d54a9c97ab45194bb8c17ad66bb660"
 dependencies = [
  "darling 0.23.0",
  "proc-macro2",
@@ -10171,7 +10084,6 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ac2a5518c70fa84342385732db33fb3f44bc4cc748936eb5833d2df34d6445ef"
 dependencies = [
  "async-trait",
- "axum 0.8.9",
  "base64 0.22.1",
  "bytes",
  "h2 0.4.16",
@@ -10183,11 +10095,9 @@ dependencies = [
  "hyper-util",
  "percent-encoding",
  "pin-project",
- "rustls-native-certs",
  "socket2 0.6.3",
  "sync_wrapper",
  "tokio",
- "tokio-rustls 0.26.4",
  "tokio-stream",
  "tower",
  "tower-layer",
@@ -10542,9 +10452,9 @@ checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"
 
 [[package]]
 name = "uuid"
-version = "1.26.0"
+version = "1.24.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5772d71c9be8a8a6ac2117d949c5b224c1b72241bb611d9a3012edcf8af7812"
+checksum = "bf3923a6f5c4c6382e0b653c4117f48d631ea17f38ed86e2a828e6f7412f5239"
 dependencies = [
  "getrandom 0.4.2",
  "js-sys",

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=11.0.0-rc.2", default-features = false, "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=11.0.0-rc.2", default-features = false, "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=11.0.0-rc.2", default-features = false, "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=11.0.0-rc.2", "tag" = "v11.0.0-rc.2", "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 }
@@ -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"] }
-uuid = { version = "1.7.0", features = ["v4", "v7"] }
 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
+The `@lancedb/lancedb` package must be built before running the tests:
-built before running the tests. This uses pnpm; see the
-[Typescript contributing guide](../nodejs/CONTRIBUTING.md) for the toolchain setup.
 
 ```shell
 pushd nodejs
-pnpm install
+npm ci
-pnpm build
+npm run build
 popd
 ```
 
-Then you can run the examples by going to the `nodejs/examples` directory, which is a
+Then you can run the examples by going to the `nodejs/examples` directory and
-separate pnpm package with its own lockfile:
+running the tests like a normal npm package:
 
 ```shell
 pushd nodejs/examples
-pnpm install
+npm ci
-pnpm test
+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.
+npm run docs
-pnpm run docs
 popd
 ```

docs/openapi.yml

@@ -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.4</version>
+    <version>0.38.0-beta.10</version>
 </dependency>
 ```
 

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
@@ -586,30 +648,6 @@ A page of table names and an
 
 ***
 
-### 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

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
+### new Job()
-operation returns only a job id, so populating them eagerly would cost an
-extra round trip on every call:
 
-- [Job.refresh](Job.md#refresh) and [Job.status](Job.md#status) fetch the whole record.
+```ts
-- [Job.wait](Job.md#wait) records the terminal state it establishes, but not the
+new Job(): Job
-  rest of the record.
+```
-- Everything is null until one of those runs.
+
+#### 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.
+Identifies the operation on the server that is running it. Operations
-
+that run in this process have no server id. The value is opaque.
-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.
 
 #### 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",
+The operation's current lifecycle state: "running", "finished",
-or "cancelled".
+"failed", or "cancelled".
 
-A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject on a
+A point snapshot; unlike [Job.wait](Job.md#wait) it does not block or reject
-terminal failure state. Also refreshes the getters above.
+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/Table.md

@@ -676,17 +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
 

docs/src/js/globals.md

@@ -96,7 +96,7 @@
 - [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)

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/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/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
@@ -125,10 +72,6 @@ listing a storage directory.
 
 ::: lancedb.functions.UdfDefinition
 
-::: lancedb.secrets.EnvVarSecret
-
-::: lancedb.secrets.SecretInfo
-
 ::: lancedb.functions.FunctionRegistrationRequest
 
 ::: lancedb.functions.FunctionArtifactRequest
@@ -151,8 +94,6 @@ listing a storage directory.
 
 ::: lancedb.functions.OutputMapping
 
-::: lancedb.functions.AssignmentMapping
-
 ::: lancedb.functions.FunctionBinding
 
 ::: lancedb.functions.RefreshColumnResult
@@ -161,18 +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
@@ -294,14 +223,10 @@ 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
@@ -320,12 +245,6 @@ still work. Queries return descriptors. Call
 
 ::: lancedb.exceptions.MissingColumnError
 
-::: lancedb.exceptions.JobNotFoundError
-
-::: lancedb.exceptions.JobFailedError
-
-::: lancedb.exceptions.JobCancelledError
-
 ## Integrations
 
 ## Pydantic

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.4</version>
+      <version>0.38.0-beta.10</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.4</version>
+    <version>0.38.0-beta.10</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.14</lance-core.version>
+        <lance-core.version>11.0.0-rc.2</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.4"
+version = "0.38.0-beta.10"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/__test__/arrow.test.ts

@@ -1,7 +1,5 @@
 // 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";
@@ -42,41 +40,6 @@ 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([

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__/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.engines.node).toBe(">= 18");
-    expect(packageJson.peerDependencies["@types/node"]).toBe(">=22");
+    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
+    server.close();
-    // 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());
-    });
   }
 }
 
@@ -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.
+        const history = await db.jobHistory("job-1");
-        await expect(db.openJob("missing")).rejects.toThrow("not found");
+        expect(history.numRows).toEqual(2);
-        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 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/__test__/table.test.ts

@@ -737,12 +737,11 @@ it("should query documents with LangChain PDF metadata", async () => {
 
 describe("merge insert", () => {
   let tmpDir: tmp.DirResult;
-  let conn: Connection;
   let table: Table;
 
   beforeEach(async () => {
     tmpDir = tmp.dirSync({ unsafeCleanup: true });
-    conn = await connect(tmpDir.name);
+    const conn = await connect(tmpDir.name);
 
     table = await conn.createTable("some_table", [
       { a: 1, b: "a" },
@@ -780,38 +779,6 @@ describe("merge insert", () => {
 
     expect(result.map((row) => ({ ...row }))).toEqual(expected);
   });
-  test("upsert on a composite key", async () => {
-    const composite = await conn.createTable("composite", [
-      { shard: "a", id: 1, val: "x" },
-      { shard: "a", id: 2, val: "y" },
-      { shard: "b", id: 1, val: "z" },
-    ]);
-
-    // ("a", 1) matches an existing row and updates it. ("b", 2) agrees with an
-    // existing row on each key column separately but on neither pair, so it is
-    // an insert.
-    const mergeInsertRes = await composite
-      .mergeInsert(["shard", "id"])
-      .whenMatchedUpdateAll()
-      .whenNotMatchedInsertAll()
-      .execute([
-        { shard: "a", id: 1, val: "X" },
-        { shard: "b", id: 2, val: "W" },
-      ]);
-    expect(mergeInsertRes.numUpdatedRows).toBe(1);
-    expect(mergeInsertRes.numInsertedRows).toBe(1);
-
-    const result = (await composite.toArrow())
-      .toArray()
-      .sort((a, b) => a.shard.localeCompare(b.shard) || a.id - b.id);
-
-    expect(result.map((row) => ({ ...row }))).toEqual([
-      { shard: "a", id: 1, val: "X" },
-      { shard: "a", id: 2, val: "y" },
-      { shard: "b", id: 1, val: "z" },
-      { shard: "b", id: 2, val: "W" },
-    ]);
-  });
   test("conditional update", async () => {
     const newData = [
       { a: 2, b: "x" },

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/.bin/jest --testEnvironment jest-environment-node-single-context --verbose",
-    "test": "node --experimental-vm-modules node_modules/jest/bin/jest.js --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

@@ -72,7 +72,8 @@ 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;
@@ -81,7 +82,6 @@ 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];

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,
@@ -27,6 +27,8 @@ import type {
   CreateNamespaceResponse,
   DescribeNamespaceResponse,
   DropNamespaceResponse,
+  Job,
+  JobDescription,
   JobInfo,
   ListNamespacesResponse,
   ListTablesResponse,
@@ -555,19 +557,24 @@ export abstract class Connection {
   ): Promise<void>;
 
   /**
-   * Open a server-side job by id, returning a handle with its record already
+   * A {@link Job} handle for a server-side job by id.
-   * populated. Rejects when the server has no such job, the way
-   * {@link Connection.openTable} does for a missing table.
    *
-   * The returned {@link Job} answers for its own state, specification,
+   * The handle is constructed without a server round trip; an unknown id
-   * result, failure and event history, so there is no separate
+   * surfaces when the handle is used. Dropping the handle has no effect on
-   * connection-level call for any of them.
+   * 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 +582,13 @@ 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 */
@@ -855,7 +869,7 @@ 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 +928,29 @@ export class LocalConnection extends Connection {
     );
   }
 
-  async openJob(jobId: string): Promise<Job> {
+  job(jobId: string): Job {
-    return new Job(await this.inner.openJob(jobId));
+    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/index.ts

@@ -94,9 +94,13 @@ export {
   RenameTableOptions,
 } from "./connection";
 
-export { JobFailureInfo, JobInfo, Session } from "./native.js";
+export {
-
+  Job,
-export { Job, JobEventsOptions } from "./job";
+  JobDescription,
+  JobFailureInfo,
+  JobInfo,
+  Session,
+} from "./native.js";
 
 export {
   AutoQuery,

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") {
-  if (value.kind !== "select" && value.kind !== "namespaced_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/sanitize.ts

@@ -94,24 +94,17 @@ export function sanitizeMetadata(
   if (metadataLike === undefined || metadataLike === null) {
     return undefined;
   }
-
+  if (!(metadataLike instanceof Map)) {
-  let entries: IterableIterator<[unknown, unknown]>;
-  try {
-    entries = Map.prototype.entries.call(metadataLike);
-  } catch {
     throw Error("Expected metadata, if present, to be a Map<string, string>");
   }
-
+  for (const item of metadataLike) {
-  const metadata = new Map<string, string>();
+    if (typeof item[0] !== "string" || typeof item[1] !== "string") {
-  for (const [key, value] of entries) {
-    if (typeof key !== "string" || typeof value !== "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/table.ts

@@ -19,7 +19,6 @@ import {
 
 import { EmbeddingFunctionConfig, getRegistry } from "./embedding/registry";
 import { IndexOptions } from "./indices";
-import { Job } from "./job";
 import { MergeInsertBuilder } from "./merge";
 import {
   AddColumnsResult,
@@ -31,6 +30,7 @@ import {
   DropColumnsResult,
   IndexConfig,
   IndexStatistics,
+  Job,
   LsmStats,
   Branches as NativeBranches,
   OptimizeStats,
@@ -919,16 +919,6 @@ 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
@@ -1124,15 +1114,13 @@ export class LocalTable extends Table {
   ): Promise<Job> {
     // biome-ignore lint/suspicious/noExplicitAny: skip
     const nativeIndex = (options?.config as any)?.inner;
-    return new Job(
+    return await this.inner.createIndexAsync(
-      await this.inner.createIndexAsync(
+      nativeIndex,
-        nativeIndex,
+      column,
-        column,
+      options?.replace,
-        options?.replace,
+      options?.waitTimeoutSeconds,
-        options?.waitTimeoutSeconds,
+      options?.name,
-        options?.name,
+      options?.train,
-        options?.train,
-      ),
     );
   }
 
@@ -1315,7 +1303,7 @@ 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(

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.39.0-beta.4",
+	"version": "0.38.0-beta.10",
 	"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.4",
+	"version": "0.38.0-beta.10",
 	"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.4",
+	"version": "0.38.0-beta.10",
 	"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.4",
+	"version": "0.38.0-beta.10",
 	"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.4",
+	"version": "0.38.0-beta.10",
 	"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.4",
+  "version": "0.38.0-beta.10",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.39.0-beta.4",
+	"version": "0.38.0-beta.10",
 	"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.4",
+  "version": "0.38.0-beta.10",
   "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/connection.rs

@@ -442,15 +442,13 @@ 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
+    /// A `Job` handle for a server-side job by id.
-    /// already populated. Rejects when the server has no such job.
     ///
-    /// The returned handle answers for its own state, specification, result,
+    /// The handle is constructed without a server round trip; an unknown id
-    /// failure and event history, so there is no separate connection-level
+    /// surfaces when the handle is used.
-    /// call for any of them.
+    #[napi]
-    #[napi(catch_unwind)]
+    pub fn job(&self, job_id: String) -> napi::Result<crate::job::Job> {
-    pub async fn open_job(&self, job_id: String) -> napi::Result<crate::job::Job> {
+        let job = self.get_inner()?.job(job_id).default_error()?;
-        let job = self.get_inner()?.open_job(&job_id).await.default_error()?;
         Ok(crate::job::Job::new(job))
     }
 
@@ -461,6 +459,17 @@ 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 +477,34 @@ 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;
@@ -58,98 +55,12 @@ 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 +91,36 @@ 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/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
+    if let Ok(Some(query)) = query.get::<&JsFullTextQuery>("query") {
-    // 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") {
         Ok(FullTextSearchQuery::new_query(query.inner.clone()))
     } else if let Ok(Some(query_text)) = query.get::<String>("query") {
         let mut query_text = query_text;

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.39.0-beta.4"
+version = "0.38.0-beta.10"
 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

@@ -139,7 +139,6 @@ 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")
 
@@ -20,13 +20,9 @@ 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,
@@ -37,8 +33,6 @@ from .functions import (
     UdfDefinition as UdfDefinition,
     udf as udf,
 )
-from .secrets import EnvVarSecret as EnvVarSecret
-from .secrets import SecretInfo as SecretInfo
 from .materialized_view import (
     AsyncMaterializedView,
     MaterializedView,
@@ -55,19 +49,6 @@ 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:
@@ -107,7 +88,6 @@ 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,
@@ -136,9 +116,6 @@ 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
@@ -280,7 +257,6 @@ 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,
@@ -423,7 +399,6 @@ 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,
         )
@@ -437,7 +412,6 @@ 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,
@@ -460,9 +434,6 @@ 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
@@ -550,7 +521,6 @@ async def connect_async(
             api_key,
             region,
             host_override,
-            sql_host_override,
             read_consistency_interval_secs,
             client_config,
             storage_options,
@@ -573,7 +543,6 @@ __all__ = [
     "connect_namespace_async",
     "AsyncConnection",
     "AsyncJob",
-    "AsyncSqlQuery",
     "AsyncLanceNamespaceDBConnection",
     "AsyncTable",
     "FtsToken",
@@ -588,8 +557,6 @@ __all__ = [
     "vector",
     "DBConnection",
     "Job",
-    "QueryDescription",
-    "SqlQuery",
     "LanceDBConnection",
     "LanceNamespaceDBConnection",
     "LsmWriteSpec",

python/python/lancedb/_blob.py

@@ -12,7 +12,7 @@ from typing import TYPE_CHECKING, Optional, Union
 import pyarrow as pa
 
 from .expr import Expr
-from .schema import row_addressable_blob_v2_paths
+from .schema import blob_v2_column_paths
 from .types import BlobMode, QueryProjection, QueryProjectionSpec
 
 if TYPE_CHECKING:
@@ -119,7 +119,7 @@ def blob_v2_projection_sources(
     schema: pa.Schema,
     projection: QueryProjection,
 ) -> dict[str, str]:
-    blob_columns = row_addressable_blob_v2_paths(schema)
+    blob_columns = blob_v2_column_paths(schema)
     if not blob_columns:
         return {}
     columns = set(blob_columns)
@@ -140,9 +140,7 @@ def v2_projection_needs_row_id(
 ) -> bool:
     if with_row_id:
         return False
-    return projection_includes_blob_column(
+    return projection_includes_blob_column(projection, blob_v2_column_paths(schema))
-        projection, row_addressable_blob_v2_paths(schema)
-    )
 
 
 def blob_auto_row_id_for_scan(
@@ -272,8 +270,7 @@ def _iter_projection_pairs(
             if isinstance(expr, str):
                 yield name, expr
             elif isinstance(expr, Expr):
-                source = expr._column_name()
+                yield name, expr.to_sql()
-                yield name, source if source is not None else expr.to_sql()
         return
     for column in projection:
         if isinstance(column, str):
@@ -283,8 +280,7 @@ def _iter_projection_pairs(
             if isinstance(expr, str):
                 yield name, expr
             elif isinstance(expr, Expr):
-                source = expr._column_name()
+                yield name, expr.to_sql()
-                yield name, source if source is not None else expr.to_sql()
 
 
 def _set_blob_column(tbl: pa.Table, output_name: str, blobs: pa.Array) -> pa.Table:

python/python/lancedb/_lancedb.pyi

@@ -1,7 +1,6 @@
 from datetime import date, datetime, timedelta
 from decimal import Decimal
 from typing import Dict, List, Optional, Tuple, Any, TypedDict, Union, Literal
-from uuid import UUID
 
 import pyarrow as pa
 
@@ -88,7 +87,6 @@ class PyExpr:
     def contains(self, substr: "PyExpr") -> "PyExpr": ...
     def isin(self, values: List["PyExpr"]) -> "PyExpr": ...
     def cast(self, data_type: pa.DataType) -> "PyExpr": ...
-    def column_name(self) -> Optional[str]: ...
     def to_sql(self) -> str: ...
 
 def expr_col(name: str) -> PyExpr: ...
@@ -148,25 +146,15 @@ class Connection(object):
         start_after: Optional[str],
         limit: Optional[int],
     ) -> list[str]: ...  # Deprecated: Use list_tables instead
-    async def open_job(self, job_id: str) -> Job: ...
+    def job(self, job_id: str) -> Job: ...
     async def create_function_async(self, request_json: str) -> Job: ...
     async def get_function(self, name: str, version: str) -> str: ...
-    async def list_functions(self) -> List[str]: ...
-    async def drop_function(self, name: str, version: str) -> bool: ...
-    async def create_secret(self, name: str, value: str) -> None: ...
-    async def alter_secret(self, name: str, value: str) -> None: ...
-    async def list_secrets(self) -> List[str]: ...
-    async def drop_secret(self, name: str) -> None: ...
-    async def describe_secret(self, name: str) -> Dict[str, str]: ...
     async def list_jobs(self) -> List[JobInfo]: ...
+    async def get_job(self, job_id: str) -> Optional[JobDescription]: ...
     async def cancel_job(self, job_id: str) -> bool: ...
-    async def execute_query_async(
+    async def job_history(
-        self,
+        self, job_id: Optional[str] = None
-        query: str,
+    ) -> List[pa.RecordBatch]: ...
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> SqlQuery: ...
-    async def describe_query(self, query_id: UUID) -> QueryDescription: ...
     async def create_table(
         self,
         name: str,
@@ -245,20 +233,9 @@ class BlobFile:
 class Job:
     @property
     def id(self) -> Optional[str]: ...
-    @property
-    def _state(self) -> Optional[str]: ...
-    @property
-    def _description(self) -> Optional[JobDescription]: ...
     async def status(self) -> str: ...
     async def wait(self) -> Optional[str]: ...
     async def cancel(self) -> None: ...
-    async def refresh(self) -> None: ...
-    async def events(
-        self,
-        *,
-        limit: Optional[int] = None,
-        filter: Optional[str] = None,
-    ) -> pa.Table: ...
 
 class JobInfo:
     @property
@@ -290,33 +267,10 @@ class JobDescription:
     @property
     def creation_ms(self) -> int: ...
     @property
-    def _spec_json(self) -> Optional[str]: ...
+    def spec_json(self) -> Optional[str]: ...
-    @property
-    def _result_json(self) -> Optional[str]: ...
-    @property
-    def spec(self) -> Optional[Any]: ...
-    @property
-    def result(self) -> Optional[Any]: ...
     @property
     def failure(self) -> Optional[JobFailureInfo]: ...
 
-class SqlQuery:
-    @property
-    def id(self) -> UUID: ...
-    async def describe(self) -> QueryDescription: ...
-    async def reader(self) -> RecordBatchStream: ...
-    async def cancel(self) -> None: ...
-
-class QueryDescription:
-    @property
-    def id(self) -> UUID: ...
-    @property
-    def status(self) -> str: ...
-    @property
-    def progress(self) -> Optional[float]: ...
-    @property
-    def expires_at(self) -> Optional[datetime]: ...
-
 class Table:
     def name(self) -> str: ...
     def __repr__(self) -> str: ...
@@ -495,7 +449,6 @@ async def connect(
     api_key: Optional[str],
     region: Optional[str],
     host_override: Optional[str],
-    sql_host_override: Optional[str],
     read_consistency_interval: Optional[float],
     client_config: Optional[Union[ClientConfig, Dict[str, Any]]],
     storage_options: Optional[Dict[str, str]],
@@ -652,11 +605,9 @@ class FullTextQuery:
 class PyQueryRequest:
     limit: Optional[int]
     offset: Optional[int]
-    take_offsets: Optional[List[int]]
     filter: Optional[Union[str, bytes]]
     full_text_search: Optional[FullTextQuery]
     select: Optional[Union[str, List[str]]]
-    select_source_columns: Optional[Dict[str, str]]
     fast_search: Optional[bool]
     with_row_id: Optional[bool]
     use_lsm: Optional[bool]

python/python/lancedb/db.py

@@ -17,10 +17,8 @@ from typing import (
     List,
     Literal,
     Optional,
-    Sequence,
     Union,
 )
-from uuid import UUID
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -49,16 +47,12 @@ from . import __version__
 from ._lancedb import connect as lancedb_connect  # type: ignore
 from .functions import FunctionVersion, UdfDefinition
 from .job import AsyncJob, Job, _typed_job
-from .sql import AsyncQuery as AsyncSqlQuery
-from .sql import Query as SqlQuery
-from .sql import QueryDescription
 from .materialized_view import (
     AsyncMaterializedView,
     MaterializedView,
     SelectArg,
     normalize_select,
 )
-from .secrets import EnvVarSecret, SecretInfo, validate_secret_name
 from .table import (
     AsyncTable,
     LanceTable,
@@ -74,11 +68,10 @@ import deprecation
 
 if TYPE_CHECKING:
     import pyarrow as pa
-    from .arrow import AsyncRecordBatchReader
     from .pydantic import LanceModel
 
     from ._lancedb import Connection as LanceDbConnection
-    from ._lancedb import JobInfo
+    from ._lancedb import JobDescription, JobInfo
     from .common import DATA, URI
     from .embeddings import EmbeddingFunctionConfig
     from ._lancedb import Session
@@ -694,47 +687,15 @@ class DBConnection(EnforceOverrides):
         """
         raise NotImplementedError("serialize is not supported for this connection type")
 
-    def create_function(
+    def create_function(self, definition: UdfDefinition) -> FunctionVersion:
-        self,
-        definition: UdfDefinition,
-        *,
-        secrets: Optional[Sequence[EnvVarSecret]] = None,
-    ) -> FunctionVersion:
         """Register a scalar Python UDF and wait for its immutable version.
 
         This is the blocking counterpart of :meth:`create_function_async`.
         Local connections raise ``NotImplementedError``.
-
-        Parameters
-        ----------
-        definition : UdfDefinition
-            A callable decorated with [udf][lancedb.udf].
-        secrets : sequence of EnvVarSecret, optional
-            One [EnvVarSecret][lancedb.secrets.EnvVarSecret] per credential the
-            Function needs, each naming a Secret and the environment variable
-            its value arrives in. The Function's source is unchanged by this;
-            it reads the variable the way it already did.
-
-        Examples
-        --------
-        ```python
-        db.create_secret("openai-prod", os.environ["OPENAI_API_KEY"])
-        db.create_function(
-            analyze_caption,
-            secrets=[
-                EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY")
-            ],
-        )
-        ```
         """
-        return self.create_function_async(definition, secrets=secrets).wait()
+        return self.create_function_async(definition).wait()
 
-    def create_function_async(
+    def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]:
-        self,
-        definition: UdfDefinition,
-        *,
-        secrets: Optional[Sequence[EnvVarSecret]] = None,
-    ) -> Job[FunctionVersion]:
         """Register a scalar Python UDF through the remote Function catalog.
 
         Submission returns a typed job. The immutable Function version becomes
@@ -751,107 +712,26 @@ class DBConnection(EnforceOverrides):
             "Function catalog operations are not supported for this connection type"
         )
 
-    def list_functions(self) -> List[FunctionVersion]:
+    def job(self, job_id: str) -> Job:
-        """List every published immutable Function version.
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
 
-        Results are ordered by Function name then version. Local connections
+        The handle is constructed without a server round trip; an unknown id
-        raise ``NotImplementedError``.
+        surfaces when the handle is used. Dropping the handle has no effect
-
+        on the job itself.
-        Examples
-        --------
-        List the identities available to use in Function-backed columns:
-
-        ```python
-        [(function.name, function.version) for function in db.list_functions()]
-        ```
         """
-        raise NotImplementedError(
+        raise NotImplementedError("job is not supported for this connection type")
-            "Function catalog operations are not supported for this connection type"
-        )
-
-    def drop_function(self, name: str, *, version: str) -> bool:
-        """Drop one exact immutable Function version from the remote catalog.
-
-        Returns True when the version changed to Dropped and False for an
-        idempotent replay. Local connections raise NotImplementedError.
-        """
-        raise NotImplementedError(
-            "Function catalog operations are not supported for this connection type"
-        )
-
-    def create_secret(self, name: str, value: str) -> None:
-        """Create a named Secret in this database.
-
-        Fails if the name is taken, so a create never silently becomes a
-        rotation. Nothing reads the value back: it is bound to a Function by
-        name and resolved by the service when that Function runs. Local
-        connections raise ``NotImplementedError``.
-        """
-        raise NotImplementedError(
-            "Secret operations are not supported for this connection type"
-        )
-
-    def alter_secret(self, name: str, value: str) -> None:
-        """Replace the credential behind an existing Secret.
-
-        Fails if it does not exist. Every Function bound to the Secret uses the
-        new value from its next job, and no new Function version is created --
-        which is how a rotation reaches columns pinned to a version registered
-        before it. Local connections raise ``NotImplementedError``.
-        """
-        raise NotImplementedError(
-            "Secret operations are not supported for this connection type"
-        )
-
-    def list_secrets(self) -> List[str]:
-        """The names of every Secret in this database.
-
-        Names only. No method returns a stored credential, by construction
-        rather than by policy. Local connections raise ``NotImplementedError``.
-        """
-        raise NotImplementedError(
-            "Secret operations are not supported for this connection type"
-        )
-
-    def drop_secret(self, name: str) -> None:
-        """Drop a Secret.
-
-        Functions bound to it fail at their next job, naming the Secret; that
-        is the revocation path. The name becomes free to reuse, and a new
-        Secret under it is picked up by everything still bound to that name.
-        Local connections raise ``NotImplementedError``.
-        """
-        raise NotImplementedError(
-            "Secret operations are not supported for this connection type"
-        )
-
-    def describe_secret(self, name: str) -> SecretInfo:
-        """What this database records about a Secret: name and timestamps.
-
-        Never the value -- there is no code path that could return one. Local
-        connections raise ``NotImplementedError``.
-        """
-        raise NotImplementedError(
-            "Secret operations are not supported for this connection type"
-        )
-
-    def open_job(self, job_id: str) -> Job:
-        """Open a server-side job by id, returning a handle with its record
-        already populated.
-
-        The returned [Job][lancedb.job.Job] answers for its own state,
-        specification, result, failure and event history, so there is no
-        separate connection-level call for any of them.
-
-        Raises `JobNotFoundError` when the server has no such job, the way
-        `open_table` does for a missing table.
-        """
-        raise NotImplementedError("open_job is not supported for this connection type")
 
     def list_jobs(self) -> List[JobInfo]:
         """List server-side jobs across the database's tables."""
         raise NotImplementedError("list_jobs is not supported for this connection type")
 
+    def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        raise NotImplementedError("get_job is not supported for this connection type")
+
     def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
 
@@ -863,38 +743,14 @@ class DBConnection(EnforceOverrides):
             "cancel_job is not supported for this connection type"
         )
 
-    def execute_query(
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
-        self,
+        """The lifecycle event history of a server-side job, as Arrow batches.
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> pa.RecordBatchReader:
-        """Execute SQL and return a blocking Arrow reader.
 
-        This submits through :meth:`execute_query_async` and waits until the
+        Lists history across all jobs when `job_id` is None.
-        initial result stream is readable. It does not wait for the full query
-        to finish.
         """
-        return self.execute_query_async(
+        raise NotImplementedError(
-            query,
+            "job_history is not supported for this connection type"
-            default_namespace_path=default_namespace_path,
+        )
-        ).reader()
-
-    def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> SqlQuery:
-        """Start executing SQL and return its query handle.
-
-        Local connections do not support SQL.
-        """
-        raise NotImplementedError("SQL is not supported for this connection type")
-
-    def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query by its connection-scoped id."""
-        raise NotImplementedError("SQL is not supported for this connection type")
 
 
 class LanceDBConnection(DBConnection):
@@ -991,7 +847,6 @@ class LanceDBConnection(DBConnection):
                 None,
                 None,
                 None,
-                None,
                 read_consistency_interval_secs,
                 None,
                 storage_options,
@@ -1540,59 +1395,37 @@ class LanceDBConnection(DBConnection):
         )
 
     @override
-    def open_job(self, job_id: str) -> Job:
+    def job(self, job_id: str) -> Job:
-        """Open a server-side job by id. See
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
-        [DBConnection.open_job][lancedb.db.DBConnection.open_job].
+
+        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.
         """
-        return Job(LOOP.run(self._conn.open_job(job_id)))
+        return Job(self._conn.job(job_id))
 
     @override
-    def create_function_async(
+    def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]:
-        self,
+        job = LOOP.run(self._conn.create_function_async(definition))
-        definition: UdfDefinition,
-        *,
-        secrets: Optional[Sequence[EnvVarSecret]] = None,
-    ) -> Job[FunctionVersion]:
-        job = LOOP.run(self._conn.create_function_async(definition, secrets=secrets))
         return Job(job)
 
     @override
     def get_function(self, name: str, *, version: str) -> FunctionVersion:
         return LOOP.run(self._conn.get_function(name, version=version))
 
-    @override
-    def list_functions(self) -> List[FunctionVersion]:
-        return LOOP.run(self._conn.list_functions())
-
-    @override
-    def drop_function(self, name: str, *, version: str) -> bool:
-        return LOOP.run(self._conn.drop_function(name, version=version))
-
-    @override
-    def create_secret(self, name: str, value: str) -> None:
-        LOOP.run(self._conn.create_secret(name, value))
-
-    @override
-    def alter_secret(self, name: str, value: str) -> None:
-        LOOP.run(self._conn.alter_secret(name, value))
-
-    @override
-    def list_secrets(self) -> List[str]:
-        return LOOP.run(self._conn.list_secrets())
-
-    @override
-    def drop_secret(self, name: str) -> None:
-        LOOP.run(self._conn.drop_secret(name))
-
-    @override
-    def describe_secret(self, name: str) -> SecretInfo:
-        return LOOP.run(self._conn.describe_secret(name))
-
     @override
     def list_jobs(self) -> List[JobInfo]:
         """List server-side jobs across the database's tables."""
         return LOOP.run(self._conn.list_jobs())
 
+    @override
+    def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return LOOP.run(self._conn.get_job(job_id))
+
     @override
     def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
@@ -1603,6 +1436,14 @@ class LanceDBConnection(DBConnection):
         """
         return LOOP.run(self._conn.cancel_job(job_id))
 
+    @override
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
+        """The lifecycle event history of a server-side job, as Arrow batches.
+
+        Lists history across all jobs when `job_id` is None.
+        """
+        return LOOP.run(self._conn.job_history(job_id))
+
     @override
     def namespace_client(self) -> LanceNamespace:
         """Get the equivalent namespace client for this connection.
@@ -2373,85 +2214,46 @@ class AsyncConnection(object):
             namespace_path = []
         await self._inner.drop_all_tables(namespace_path=namespace_path)
 
-    async def open_job(self, job_id: str) -> AsyncJob:
+    def job(self, job_id: str) -> AsyncJob:
-        """Open a server-side job by id. See
+        """An [AsyncJob][lancedb.job.AsyncJob] handle for a server-side job
-        [DBConnection.open_job][lancedb.db.DBConnection.open_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.
         """
-        return AsyncJob(await self._inner.open_job(job_id))
+        return AsyncJob(self._inner.job(job_id))
 
     async def create_function_async(
-        self,
+        self, definition: UdfDefinition
-        definition: UdfDefinition,
-        *,
-        secrets: Optional[Sequence[EnvVarSecret]] = None,
     ) -> AsyncJob[FunctionVersion]:
         """Register a scalar Python UDF through the remote Function catalog.
 
         The returned typed job resolves to the immutable Function version.
-        ``secrets`` is a sequence of
+        Local connections raise ``NotImplementedError``.
-        [EnvVarSecret][lancedb.secrets.EnvVarSecret], each naming a Secret and
-        the environment variable its value arrives in. Local connections raise
-        ``NotImplementedError``.
         """
         if not isinstance(definition, UdfDefinition):
             raise TypeError("create_function_async requires a @udf definition")
-        request = definition.bind_secrets(secrets)
+        inner = await self._inner.create_function_async(
-        inner = await self._inner.create_function_async(request.to_canonical_json())
+            definition.registration_request.to_canonical_json()
+        )
         return _typed_job(inner, FunctionVersion.from_json)
 
     async def get_function(self, name: str, *, version: str) -> FunctionVersion:
         """Open one exact immutable Function version from the remote catalog."""
         return FunctionVersion.from_json(await self._inner.get_function(name, version))
 
-    async def list_functions(self) -> List[FunctionVersion]:
-        """List every published immutable Function version.
-
-        Results are ordered by Function name then version. Local connections
-        raise ``NotImplementedError``.
-        """
-        return [
-            FunctionVersion.from_json(value)
-            for value in await self._inner.list_functions()
-        ]
-
-    async def drop_function(self, name: str, *, version: str) -> bool:
-        """Drop one exact immutable Function version from the remote catalog."""
-        return await self._inner.drop_function(name, version)
-
-    async def create_secret(self, name: str, value: str) -> None:
-        """Create a named Secret in this database.
-
-        Fails if the name is taken, so a create never silently becomes a
-        rotation. Nothing reads the value back.
-        """
-        await self._inner.create_secret(validate_secret_name(name), value)
-
-    async def alter_secret(self, name: str, value: str) -> None:
-        """Replace the credential behind an existing Secret.
-
-        Fails if it does not exist. Bound Functions use the new value from
-        their next job, with no new Function version.
-        """
-        await self._inner.alter_secret(validate_secret_name(name), value)
-
-    async def list_secrets(self) -> List[str]:
-        """The names of every Secret in this database. Names only."""
-        return await self._inner.list_secrets()
-
-    async def drop_secret(self, name: str) -> None:
-        """Drop a Secret. Bound Functions fail at their next job."""
-        await self._inner.drop_secret(validate_secret_name(name))
-
-    async def describe_secret(self, name: str) -> SecretInfo:
-        """What this database records about a Secret. Never the value."""
-        return SecretInfo.from_json(
-            await self._inner.describe_secret(validate_secret_name(name))
-        )
-
     async def list_jobs(self) -> List[JobInfo]:
         """List server-side jobs across the database's tables."""
         return await self._inner.list_jobs()
 
+    async def get_job(self, job_id: str) -> Optional[JobDescription]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return await self._inner.get_job(job_id)
+
     async def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
 
@@ -2461,46 +2263,12 @@ class AsyncConnection(object):
         """
         return await self._inner.cancel_job(job_id)
 
-    async def execute_query(
+    async def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
-        self,
+        """The lifecycle event history of a server-side job, as Arrow batches.
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncRecordBatchReader:
-        """Execute SQL and return an asynchronous Arrow reader.
 
-        This submits through :meth:`execute_query_async` and waits until the
+        Lists history across all jobs when `job_id` is None.
-        initial result stream is readable. It does not wait for the full query
-        to finish.
         """
-        submitted = await self.execute_query_async(
+        return await self._inner.job_history(job_id)
-            query,
-            default_namespace_path=default_namespace_path,
-        )
-        return await submitted.reader()
-
-    async def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncSqlQuery:
-        """Start executing SQL and return its query handle.
-
-        The database from ``connect_async`` is used for unqualified database
-        references. The namespace defaults to ``["public"]``. Local
-        connections raise ``NotImplementedError``.
-        """
-        return AsyncSqlQuery(
-            await self._inner.execute_query_async(
-                query,
-                default_namespace_path=default_namespace_path,
-            )
-        )
-
-    async def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query by its connection-scoped id."""
-        return await self._inner.describe_query(query_id)
 
     async def namespace_client(self) -> LanceNamespace:
         """Get the equivalent namespace client for this connection.

python/python/lancedb/exceptions.py

@@ -35,9 +35,3 @@ class JobCancelledError(RuntimeError):
     """Exception raised when an asynchronous job was cancelled."""
 
     pass
-
-
-class JobNotFoundError(ValueError):
-    """Exception raised when opening a job the server does not have."""
-
-    pass

python/python/lancedb/expr.py

@@ -249,10 +249,6 @@ class Expr:
 
     # ── utilities ────────────────────────────────────────────────────────────
 
-    def _column_name(self) -> str | None:
-        """Return the source name when this is a bare column expression."""
-        return self._inner.column_name()
-
     def to_sql(self) -> str:
         """Render the expression as a SQL string (useful for debugging)."""
         return self._inner.to_sql()
@@ -316,7 +312,7 @@ def func(name: str, *args: ExprLike) -> Expr:
     --------
     >>> from lancedb.expr import col, func
     >>> func("lower", col("name"))
-    Expr(lower(`name`))
+    Expr(lower(name))
     """
     inner_args = [_coerce(a)._inner for a in args]
     return Expr(expr_func(name, inner_args))

python/python/lancedb/functions.py

@@ -4,7 +4,7 @@
 """Canonical Function values exchanged with LanceDB Enterprise services.
 
 These immutable models contain client/wire state only. Catalog persistence,
-environment bake, secret resolution, and execution are owned by Sophon.
+environment bake, and execution are owned by Sophon.
 ``RefreshColumnResult`` is also the backend-neutral result of a local
 expression-backed refresh job.
 """
@@ -25,7 +25,7 @@ import re
 import sys
 import textwrap
 import types
-from collections.abc import Mapping, Sequence
+from collections.abc import Mapping
 from datetime import date, datetime
 from typing import (
     Annotated,
@@ -49,26 +49,11 @@ from pydantic import (
     model_validator,
 )
 
-from .schema import is_blob_v2_field as _is_blob_v2_field
-from .secrets import EnvVarSecret
-
 _Int32 = conint(strict=True, ge=-(2**31), le=2**31 - 1)
 _UInt32 = conint(strict=True, ge=0, le=2**32 - 1)
 _UInt64 = conint(strict=True, ge=0, le=2**64 - 1)
 
 
-def _validate_gpu_wire_marker(value: Any) -> bool:
-    if value is not True:
-        raise ValueError("runtime.gpu must be true")
-    return True
-
-
-def _normalize_gpu_marker(value: bool) -> Optional[bool]:
-    if not isinstance(value, bool):
-        raise ValueError("gpu must be a boolean")
-    return True if value else None
-
-
 class _FrozenDict(dict):
     def _immutable(self, *args, **kwargs):
         raise TypeError("remote canonical values are immutable")
@@ -254,23 +239,6 @@ class PythonRuntimeSpec(_RemoteValue):
     python_version: Optional[str] = None
     environment: Optional[PythonEnvironmentSpec] = None
     env: Optional[Mapping[str, str]] = None
-    gpu: Optional[bool] = None
-
-    @model_validator(mode="before")
-    @classmethod
-    def _discard_unknown_runtime_payload(cls, value):
-        if isinstance(value, Mapping):
-            kind = value.get("kind")
-            if isinstance(kind, str) and kind not in {"python", "python_v2"}:
-                return {"kind": kind}
-        return value
-
-    @field_validator("gpu", mode="before")
-    @classmethod
-    def _validate_gpu_marker(cls, value):
-        if value is None:
-            return None
-        return _validate_gpu_wire_marker(value)
 
     @model_validator(mode="after")
     def _validate_runtime_kind(self):
@@ -279,28 +247,18 @@ class PythonRuntimeSpec(_RemoteValue):
                 raise ValueError("python runtime requires python_version")
             if self.environment is None:
                 raise ValueError("python runtime requires environment")
-            if self.gpu is not None:
-                raise ValueError("python runtime with gpu requires kind='python_v2'")
-        elif self.kind == "python_v2":
-            if self.python_version is None:
-                raise ValueError("python_v2 runtime requires python_version")
-            if self.environment is None:
-                raise ValueError("python_v2 runtime requires environment")
-            if self.gpu is None:
-                raise ValueError("python_v2 runtime requires gpu")
         else:
             object.__setattr__(self, "python_version", None)
             object.__setattr__(self, "environment", None)
             object.__setattr__(self, "env", None)
-            object.__setattr__(self, "gpu", None)
         return self
 
 
 class FunctionVersion(_RemoteValue):
     """An exact immutable Function version returned by Enterprise.
 
-    The GPU execution requirement is part of this identity. CPU and memory sizing,
+    Scheduling resources, priority, concurrency, and retry policy belong to
-    priority, concurrency, and retry policy belong to the execution platform.
+    the submitting Job and are not part of this identity.
     """
 
     name: str
@@ -310,7 +268,6 @@ class FunctionVersion(_RemoteValue):
     runtime: PythonRuntimeSpec
     runtime_digest: str
     environment_digest: str
-    secret_env_bindings: Mapping[str, str] = {}
     created_at: str
 
     def __call__(self, **inputs: Any) -> FunctionApplication:
@@ -372,18 +329,12 @@ class FunctionVersion(_RemoteValue):
 
 
 class FunctionRegistrationRequest(_RemoteValue):
-    """Stable remote registration envelope produced by :func:`udf`.
+    """Stable remote registration envelope produced by :func:`udf`."""
-
-    Credential values deliberately have no field here. The only secret-shaped
-    thing a client sends is ``secret_env_bindings``: the name of a Secret the
-    database already holds, which the remote service resolves at execution.
-    """
 
     name: str
     artifact: FunctionArtifactRequest
     signature: FunctionSignature
     runtime: PythonRuntimeSpec
-    secret_env_bindings: Mapping[str, str] = {}
 
 
 class FunctionVersionRef(_OpenRemoteValue):
@@ -478,7 +429,11 @@ class InputBinding(_RemoteValue):
 
 
 class OutputMapping(_RemoteValue):
-    """One stable result-field mapping."""
+    """One stable result-field mapping.
+
+    Assignment state is outside the Slice 1 client contract. During the NULL
+    transition Lance exposes no public cell-flag identifier to persist here.
+    """
 
     result_field: str
     output_name: str
@@ -488,13 +443,6 @@ class OutputMapping(_RemoteValue):
     nullable: bool
 
 
-class AssignmentMapping(_RemoteValue):
-    """Internal physical column preserving flattened struct validity."""
-
-    output_name: str
-    output_field_id: _Int32
-
-
 class FunctionBinding(_RemoteValue):
     """Immutable Function binding persisted by the Enterprise table service."""
 
@@ -502,7 +450,6 @@ class FunctionBinding(_RemoteValue):
     function: FunctionVersionRef
     inputs: tuple[InputBinding, ...]
     outputs: tuple[OutputMapping, ...]
-    assignment: Optional[AssignmentMapping] = None
     input_schema: Optional[Mapping[str, Any]] = None
     output_schema: Optional[Mapping[str, Any]] = None
 
@@ -532,15 +479,6 @@ class RefreshColumnResult(_RemoteValue):
 
 
 _FUNCTION_NAME = re.compile(r"^[A-Za-z_][A-Za-z0-9_.-]*$")
-_DECLARED_SECRET = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
-
-_FUNCTION_BLOB_V2_TYPE = "blob_v2"
-_ARROW_EXTENSION_NAME_KEY = "ARROW:extension:name"
-_BLOB_V2_EXTENSION_NAME = "lance.blob.v2"
-_NESTED_BLOB_COLLECTION_ERROR = (
-    "unsupported Arrow type for Function signature: Blob v2 fields nested under "
-    "collection types are not supported"
-)
 
 
 _GRAMMAR_PRIMITIVES = (
@@ -557,7 +495,6 @@ _GRAMMAR_PRIMITIVES = (
     (pa.float32(), "float32"),
     (pa.float64(), "float64"),
     (pa.string(), "utf8"),
-    (pa.large_string(), "large_utf8"),
     (pa.binary(), "binary"),
     (pa.date32(), "date32"),
     (pa.date64(), "date64"),
@@ -565,258 +502,31 @@ _GRAMMAR_PRIMITIVES = (
 
 
 def _canonical_arrow_type(data_type: pa.DataType) -> str:
-    """The compact Function grammar, or canonical exact JSON for nested types."""
+    """The server's V1 Function type grammar. Anything outside it is rejected
-    grammar = _grammar_arrow_type(data_type)
+    here rather than at registration."""
-    if grammar is not None:
-        return grammar
-    exact = _exact_arrow_type(data_type)
-    return json.dumps(exact, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
-
-
-def _grammar_arrow_type(data_type: pa.DataType) -> Optional[str]:
     for candidate, name in _GRAMMAR_PRIMITIVES:
         if data_type == candidate:
             return name
     if pa.types.is_list(data_type) or pa.types.is_large_list(data_type):
-        item = _grammar_list_item(data_type)
-        if item is None:
-            return None
         prefix = "list" if pa.types.is_list(data_type) else "large_list"
-        return f"{prefix}<{item}>"
+        return f"{prefix}<{_canonical_list_item(data_type)}>"
     if pa.types.is_fixed_size_list(data_type) and data_type.list_size > 0:
-        item = _grammar_list_item(data_type)
+        return (
-        if item is not None:
+            f"fixed_size_list<{_canonical_list_item(data_type)}, {data_type.list_size}>"
-            return f"fixed_size_list<{item}, {data_type.list_size}>"
+        )
-    return None
+    raise TypeError(f"unsupported Arrow type for Function signature: {data_type}")
 
 
-def _grammar_list_item(data_type: pa.DataType) -> Optional[str]:
+def _canonical_list_item(data_type: pa.DataType) -> str:
     """The grammar names only the item type; it always means a non-nullable
-    child called `item`, so other child properties require exact JSON."""
+    child called `item`, so any other child metadata cannot be represented."""
     child = data_type.value_field
     if child.name != "item" or child.nullable or child.metadata:
-        return None
-    return _grammar_arrow_type(child.type)
-
-
-def _validate_exact_arrow_field(field: pa.Field) -> None:
-    if not field.name:
         raise TypeError(
-            "unsupported Arrow type for Function signature: field names "
+            "unsupported Arrow type for Function signature: list items must be a "
-            "must not be empty"
+            f"non-nullable field named 'item', got {child}"
         )
-    if _is_blob_v2_field(field):
+    return _canonical_arrow_type(child.type)
-        if not _has_supported_blob_v2_layout(field):
-            raise TypeError(
-                "unsupported Arrow type for Function signature: lance.blob.v2 "
-                f"requires a supported Blob storage layout, got {field}"
-            )
-        metadata = {
-            (key.decode() if isinstance(key, bytes) else key): (
-                value.decode() if isinstance(value, bytes) else value
-            )
-            for key, value in (field.metadata or {}).items()
-        }
-        if metadata and metadata != {
-            _ARROW_EXTENSION_NAME_KEY: _BLOB_V2_EXTENSION_NAME
-        }:
-            raise TypeError(
-                "unsupported Arrow type for Function signature: lance.blob.v2 "
-                "field metadata must contain only its canonical extension marker"
-            )
-    elif field.metadata:
-        raise TypeError(
-            "unsupported Arrow type for Function signature: field metadata "
-            f"is not supported, got {field}"
-        )
-
-
-def _has_supported_blob_v2_layout(field: pa.Field) -> bool:
-    data_type = field.type
-    if isinstance(data_type, pa.ExtensionType):
-        data_type = data_type.storage_type
-    if not pa.types.is_struct(data_type):
-        return False
-
-    fields = tuple(data_type)
-
-    def matches(spec, compare_nullable) -> bool:
-        return len(fields) == len(spec) and all(
-            actual.name == name
-            and actual.type == expected_type
-            and (not check_nullable or actual.nullable == nullable)
-            for actual, (name, expected_type, nullable), check_nullable in zip(
-                fields, spec, compare_nullable
-            )
-        )
-
-    logical_minimal = (
-        ("data", pa.large_binary(), True),
-        ("uri", pa.utf8(), True),
-    )
-    logical_full = logical_minimal + (
-        ("position", pa.uint64(), True),
-        ("size", pa.uint64(), True),
-    )
-    prepared = (
-        ("kind", pa.uint8(), True),
-        ("data", pa.large_binary(), True),
-        ("uri", pa.utf8(), True),
-        ("blob_id", pa.uint32(), True),
-        ("blob_size", pa.uint64(), True),
-        ("position", pa.uint64(), True),
-    )
-    descriptor = (
-        ("kind", pa.uint8(), False),
-        ("position", pa.uint64(), False),
-        ("size", pa.uint64(), False),
-        ("blob_id", pa.uint32(), False),
-        ("blob_uri", pa.utf8(), False),
-    )
-    return (
-        matches(logical_minimal, (True, True))
-        or matches(logical_full, (True, True, False, False))
-        or matches(prepared, (True,) * len(prepared))
-        or matches(descriptor, (False,) * len(descriptor))
-    )
-
-
-def _canonical_arrow_field(field: pa.Field) -> str:
-    _validate_exact_arrow_field(field)
-    if _is_blob_v2_field(field):
-        return _FUNCTION_BLOB_V2_TYPE
-    return _canonical_arrow_type(field.type)
-
-
-def _blob_storage_type(field: pa.Field) -> pa.DataType:
-    data_type = field.type
-    if isinstance(data_type, pa.ExtensionType):
-        return data_type.storage_type
-    return data_type
-
-
-def _exact_blob_storage_type(field: pa.Field) -> dict[str, Any]:
-    storage = _blob_storage_type(field)
-    if not pa.types.is_struct(storage):
-        raise TypeError(
-            "unsupported Arrow type for Function signature: lance.blob.v2 "
-            "requires struct storage"
-        )
-    return {
-        "type": "struct",
-        "fields": [
-            {
-                "name": child.name,
-                "nullable": child.nullable,
-                "type": (
-                    {"type": "large_binary"}
-                    if pa.types.is_large_binary(child.type)
-                    else _exact_arrow_type(child.type)
-                ),
-            }
-            for child in storage
-        ],
-    }
-
-
-def _data_type_has_blob_v2(data_type: pa.DataType) -> bool:
-    if pa.types.is_struct(data_type):
-        return any(
-            _is_blob_v2_field(field) or _data_type_has_blob_v2(field.type)
-            for field in data_type
-        )
-    if (
-        pa.types.is_list(data_type)
-        or pa.types.is_large_list(data_type)
-        or pa.types.is_fixed_size_list(data_type)
-    ):
-        field = data_type.value_field
-        return _is_blob_v2_field(field) or _data_type_has_blob_v2(field.type)
-    if pa.types.is_map(data_type):
-        return any(
-            _is_blob_v2_field(field) or _data_type_has_blob_v2(field.type)
-            for field in (data_type.key_field, data_type.item_field)
-        )
-    return False
-
-
-def _exact_arrow_field(
-    field: pa.Field, *, inside_collection: bool = False
-) -> dict[str, Any]:
-    _validate_exact_arrow_field(field)
-    if _is_blob_v2_field(field):
-        if inside_collection:
-            raise TypeError(_NESTED_BLOB_COLLECTION_ERROR)
-        return {
-            "name": field.name,
-            "nullable": field.nullable,
-            "type": _exact_blob_storage_type(field),
-            "metadata": {
-                _ARROW_EXTENSION_NAME_KEY: _BLOB_V2_EXTENSION_NAME,
-            },
-        }
-    value = {
-        "name": field.name,
-        "nullable": field.nullable,
-        "type": _exact_arrow_type(field.type, inside_collection=inside_collection),
-    }
-    return value
-
-
-def _exact_arrow_type(
-    data_type: pa.DataType, *, inside_collection: bool = False
-) -> dict[str, Any]:
-    for candidate, name in _GRAMMAR_PRIMITIVES:
-        if data_type == candidate:
-            return {"type": name}
-    if pa.types.is_struct(data_type):
-        fields = list(data_type)
-        names = [field.name for field in fields]
-        if not fields or len(set(names)) != len(names):
-            raise TypeError(
-                "unsupported Arrow type for Function signature: structs must have "
-                "non-empty, uniquely named fields"
-            )
-        return {
-            "type": "struct",
-            "fields": [
-                _exact_arrow_field(field, inside_collection=inside_collection)
-                for field in fields
-            ],
-        }
-    if (
-        pa.types.is_list(data_type)
-        or pa.types.is_large_list(data_type)
-        or pa.types.is_fixed_size_list(data_type)
-    ):
-        if pa.types.is_fixed_size_list(data_type):
-            if data_type.value_field.name != "item":
-                raise TypeError(
-                    "unsupported Arrow type for Function signature: fixed-size list "
-                    "items must be named 'item'"
-                )
-            if data_type.list_size <= 0:
-                raise TypeError(
-                    f"unsupported Arrow type for Function signature: {data_type}"
-                )
-        value: dict[str, Any] = {
-            "type": (
-                "list"
-                if pa.types.is_list(data_type)
-                else "large_list"
-                if pa.types.is_large_list(data_type)
-                else "fixed_size_list"
-            ),
-            "fields": [
-                _exact_arrow_field(data_type.value_field, inside_collection=True)
-            ],
-        }
-        if pa.types.is_fixed_size_list(data_type):
-            value["length"] = data_type.list_size
-        return value
-    if pa.types.is_map(data_type) and _data_type_has_blob_v2(data_type):
-        raise TypeError(_NESTED_BLOB_COLLECTION_ERROR)
-    raise TypeError(f"unsupported Arrow type for Function signature: {data_type}")
 
 
 def _list_of(item: pa.DataType) -> pa.DataType:
@@ -890,15 +600,8 @@ def _callable_parameters(function: Callable[..., Any]) -> tuple[inspect.Paramete
 
 def _function_output(output: pa.DataType | pa.Field | pa.Schema) -> FunctionOutput:
     if isinstance(output, pa.Schema):
-        if output.metadata:
-            raise TypeError("Function output schema metadata is not supported")
         fields = tuple(output)
-    elif (
+    elif isinstance(output, pa.Field) and pa.types.is_struct(output.type):
-        isinstance(output, pa.Field)
-        and not _is_blob_v2_field(output)
-        and pa.types.is_struct(output.type)
-    ):
-        _validate_exact_arrow_field(output)
         if output.nullable:
             raise ValueError("Function output must be non-nullable")
         fields = tuple(output.type)
@@ -914,19 +617,18 @@ def _function_output(output: pa.DataType | pa.Field | pa.Schema) -> FunctionOutp
             raise TypeError(
                 "output_schema must be a PyArrow DataType, Field, or Schema"
             )
-        _validate_exact_arrow_field(field)
         if field.nullable:
             raise ValueError("Function output must be non-nullable")
         return FunctionOutput(
             kind="scalar",
-            arrow_type=_canonical_arrow_field(field),
+            arrow_type=_canonical_arrow_type(field.type),
             nullable=False,
         )
 
     if not fields:
         raise ValueError("named-struct Function output must contain at least one field")
-    for field in fields:
+    if any(field.nullable for field in fields):
-        _validate_exact_arrow_field(field)
+        raise ValueError("Function output fields must be non-nullable")
     names = [field.name for field in fields]
     if len(set(names)) != len(names):
         raise ValueError("Function output field names must be unique")
@@ -935,8 +637,8 @@ def _function_output(output: pa.DataType | pa.Field | pa.Schema) -> FunctionOutp
         fields=tuple(
             FunctionResultField(
                 name=field.name,
-                arrow_type=_canonical_arrow_field(field),
+                arrow_type=_canonical_arrow_type(field.type),
-                nullable=field.nullable,
+                nullable=False,
             )
             for field in fields
         ),
@@ -955,10 +657,6 @@ def _infer_signature(
     if input_schema is not None:
         if not isinstance(input_schema, pa.Schema):
             raise TypeError("input_schema must be a PyArrow Schema")
-        if input_schema.metadata:
-            raise TypeError("Function input schema metadata is not supported")
-        for field in input_schema:
-            _validate_exact_arrow_field(field)
         expected = tuple(parameter.name for parameter in parameters)
         actual = tuple(input_schema.names)
         if actual != expected:
@@ -969,7 +667,7 @@ def _infer_signature(
         inputs = tuple(
             FunctionParameter(
                 name=field.name,
-                arrow_type=_canonical_arrow_field(field),
+                arrow_type=_canonical_arrow_type(field.type),
                 nullable=field.nullable,
             )
             for field in input_schema
@@ -992,9 +690,7 @@ def _infer_signature(
         inputs.append(
             FunctionParameter(
                 name=parameter.name,
-                arrow_type=_canonical_arrow_field(
+                arrow_type=_canonical_arrow_type(data_type),
-                    pa.field(parameter.name, data_type, nullable=nullable)
-                ),
                 nullable=nullable,
             )
         )
@@ -1214,7 +910,6 @@ class UdfDefinition:
         pip: tuple[str, ...],
         env: Mapping[str, str],
         python_version: Optional[str],
-        gpu: bool = False,
         conda: tuple[str, ...] = (),
         conda_channels: tuple[str, ...] = (),
     ):
@@ -1243,14 +938,12 @@ class UdfDefinition:
         signature = _infer_signature(function, input_schema, output_schema)
         source = _package_source(function)
         digest = f"sha256:{hashlib.sha256(source).hexdigest()}"
-        gpu_marker = _normalize_gpu_marker(gpu)
         runtime = PythonRuntimeSpec(
-            kind="python_v2" if gpu_marker is not None else "python",
+            kind="python",
             python_version=python_version
             or f"{sys.version_info.major}.{sys.version_info.minor}",
             environment=environment_spec,
             env=environment,
-            gpu=gpu_marker,
         )
         self._function = function
         self._request = FunctionRegistrationRequest(
@@ -1275,56 +968,9 @@ class UdfDefinition:
 
     @property
     def registration_request(self) -> FunctionRegistrationRequest:
-        """The immutable request sent by ``create_function_async``.
+        """The immutable request sent by ``create_function_async``."""
-
-        Carries no secret bindings. Binding is a registration-time decision,
-        so a Function bound to Secrets is registered through :meth:`bind_secrets`,
-        which is what ``create_function`` calls.
-        """
         return self._request
 
-    def bind_secrets(
-        self, secrets: Optional[Sequence[EnvVarSecret]]
-    ) -> FunctionRegistrationRequest:
-        """The registration request for this definition bound to ``secrets``.
-
-        Binding does not change the Function's source: each
-        [EnvVarSecret][lancedb.secrets.EnvVarSecret] names a Secret and the
-        environment variable its value should arrive in, and the Function reads
-        that variable the way it already did. Whether the named Secrets exist is
-        the server's answer, not this one.
-        """
-        bindings = () if secrets is None else tuple(secrets)
-        wrong_type = [
-            binding for binding in bindings if not isinstance(binding, EnvVarSecret)
-        ]
-        if wrong_type:
-            kinds = sorted({type(binding).__name__ for binding in wrong_type})
-            raise TypeError(
-                f"Function secrets must be EnvVarSecret values, not {kinds!r}; a "
-                "credential value is never sent to this API"
-            )
-        variables = [binding.env_variable for binding in bindings]
-        duplicates = sorted({name for name in variables if variables.count(name) > 1})
-        if duplicates:
-            raise ValueError(
-                "a Function binds each environment variable once; duplicated: "
-                f"{duplicates!r}"
-            )
-        # `env` is ordinary configuration carried in the definition, so a name in
-        # both would have a value visible in the Function's record and a value
-        # that is not. Refuse rather than pick.
-        environment = self._request.runtime.env or {}
-        overlap = sorted(set(environment) & set(variables))
-        if overlap:
-            raise ValueError(
-                f"Function env and secret bindings must be disjoint: {overlap!r}"
-            )
-        if not bindings:
-            return self._request
-        resolved = {binding.env_variable: binding.secret for binding in bindings}
-        return self._request._copy(update={"secret_env_bindings": resolved})
-
     def __call__(self, *args, **kwargs):
         return self._function(*args, **kwargs)
 
@@ -1343,7 +989,6 @@ def udf(
     pip: tuple[str, ...] | list[str] = (),
     env: Optional[Mapping[str, str]] = None,
     python_version: Optional[str] = None,
-    gpu: bool = False,
     conda: tuple[str, ...] | list[str] = (),
     conda_channels: tuple[str, ...] | list[str] = (),
 ) -> Callable[[Callable[..., Any]], UdfDefinition]: ...
@@ -1358,7 +1003,6 @@ def udf(
     pip: tuple[str, ...] | list[str] = (),
     env: Optional[Mapping[str, str]] = None,
     python_version: Optional[str] = None,
-    gpu: bool = False,
     conda: tuple[str, ...] | list[str] = (),
     conda_channels: tuple[str, ...] | list[str] = (),
 ):
@@ -1366,9 +1010,8 @@ def udf(
 
     Input and output signatures are inferred from supported annotations. For
     Arrow types annotations cannot express precisely, pass ``input_schema``
-    and ``output_schema`` together. Scalar outputs must be non-nullable. Every
+    and ``output_schema`` together. Nullable outputs are rejected because V1
-    named-struct field may be nullable; Enterprise preserves the struct's
+    uses physical NULL to represent unassigned computed-column rows.
-    validity when the result is expanded into sibling columns.
 
     Parameters
     ----------
@@ -1380,8 +1023,8 @@ def udf(
         Explicit input fields in the exact order of the callable parameters.
         Must be provided together with ``output_schema``.
     output_schema : pyarrow.DataType, pyarrow.Field, or pyarrow.Schema, optional
-        Explicit scalar or named-struct output. Scalar outputs must be
+        Explicit scalar or named-struct output. Must be non-nullable and be
-        non-nullable. Must be provided together with ``input_schema``.
+        provided together with ``input_schema``.
     pip : sequence of str, optional
         Pip requirements for the remote environment.
     conda : sequence of str, optional
@@ -1389,15 +1032,9 @@ def udf(
     conda_channels : sequence of str, optional
         Conda channels in priority order; requires ``conda``.
     env : mapping of str to str, optional
-        Environment variables included in the Function definition. Not for
+        Environment variables included in the Function definition.
-        credentials -- these are ordinary configuration, stored with the
-        Function and visible wherever it is.
     python_version : str, optional
         Remote Python major/minor version. Defaults to the client version.
-    gpu : bool, default False
-        Whether every remote execution requires a GPU. The execution platform
-        selects one compatible GPU for each worker. The requirement is part of
-        the immutable Function version.
 
     The packaged artifact is a snapshot: the function source plus exactly
     the module-level names it references (modules as imports, importable
@@ -1422,11 +1059,6 @@ def udf(
     ...     return value * 2
     >>> score(1.5)
     3.0
-    >>> @udf(pip=["cupy-cuda12x"], gpu=True)
-    ... def gpu_score(value: int) -> int:
-    ...     return value * 2
-    >>> gpu_score.registration_request.runtime.gpu
-    True
     """
 
     def decorate(target: Callable[..., Any]) -> UdfDefinition:
@@ -1438,7 +1070,6 @@ def udf(
             pip=tuple(pip),
             env={} if env is None else env,
             python_version=python_version,
-            gpu=gpu,
             conda=tuple(conda),
             conda_channels=tuple(conda_channels),
         )
@@ -1449,7 +1080,6 @@ def udf(
 
 
 __all__ = [
-    "AssignmentMapping",
     "ApplicationInput",
     "FunctionApplication",
     "FunctionArtifact",

python/python/lancedb/job.py

@@ -4,27 +4,15 @@
 """Handles to operations a server may run asynchronously."""
 
 import asyncio
-import json
 from datetime import timedelta
 from typing import Any, Callable, Generic, Optional, TypeVar, cast
 
-import pyarrow as pa
-
 from lancedb.background_loop import LOOP
 
 from . import _lancedb
-from ._lancedb import JobDescription, JobFailureInfo, JobInfo
 
 T = TypeVar("T")
 
-__all__ = [
-    "AsyncJob",
-    "Job",
-    "JobDescription",
-    "JobFailureInfo",
-    "JobInfo",
-]
-
 
 class AsyncJob(Generic[T]):
     """A handle to an operation that may still be running.
@@ -90,149 +78,6 @@ class AsyncJob(Generic[T]):
             return
         await self._inner.cancel()
 
-    async def refresh(self) -> None:
-        """Ask the backend for this job's current state, and for a server-side
-        job its full record, then cache it for the properties below.
-
-        The properties are all `None` until this runs, because submitting an
-        operation returns only a job id. `status` fetches the whole record too;
-        `wait` records only the terminal state it establishes.
-        """
-        if self._inner is None:
-            return
-        await self._inner.refresh()
-
-    @property
-    def state(self) -> Optional[str]:
-        """The last observed lifecycle state, without contacting the backend.
-
-        `None` until the handle has talked to it. See :meth:`AsyncJob.refresh`.
-        """
-        if self._inner is None:
-            return "finished"
-        return self._inner._state
-
-    @property
-    def job_type(self) -> Optional[str]:
-        """The job's type, as the server names it.
-
-        `None` for an in-process job, which has no server-side record.
-        """
-        return self._field("job_type")
-
-    @property
-    def creation_ms(self) -> Optional[int]:
-        """When the job was created, in milliseconds since the epoch."""
-        return self._field("creation_ms")
-
-    @property
-    def spec(self) -> Optional[Any]:
-        """The job-type-specific specification it was submitted with."""
-        return self._field("spec")
-
-    @property
-    def result(self) -> Optional[Any]:
-        """The job-type-specific terminal result, as reported data rather than
-        the typed model :meth:`AsyncJob.wait` returns.
-
-        `None` until the job succeeds, so a job that never terminates reports
-        its progress through :meth:`AsyncJob.events` instead.
-        """
-        return self._field("result")
-
-    @property
-    def failure(self) -> Optional[JobFailureInfo]:
-        """Why the job failed, when it failed and the server reports a reason."""
-        return self._field("failure")
-
-    @property
-    def _spec_json(self) -> Optional[str]:
-        return self._field("_spec_json")
-
-    @property
-    def _result_json(self) -> Optional[str]:
-        return self._field("_result_json")
-
-    def _field(self, name: str) -> Optional[Any]:
-        description = self._inner._description if self._inner is not None else None
-        return getattr(description, name) if description is not None else None
-
-    async def events(
-        self,
-        *,
-        limit: Optional[int] = None,
-        filter: Optional[str] = None,
-    ) -> "pa.Table":
-        """This job's recorded lifecycle events.
-
-        Where the properties 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.
-
-        Parameters
-        ----------
-        limit: int, optional
-            Maximum event rows to return. The server caps results at 1000 by
-            default and 10,000 at most, and truncates without saying so, so
-            pass this for a job that emits an event per fragment.
-        filter: str, optional
-            SQL-like expression over the `state`, `updated_by`, `emitted_from`,
-            `emitted_by`, and `claim_entity` columns, such as
-            ``state = 'claim_complete'``.
-        """
-        if self._inner is None:
-            raise NotImplementedError(
-                "job event history is only available for server-side jobs"
-            )
-        return await self._inner.events(limit=limit, filter=filter)
-
-    def __repr__(self) -> str:
-        return _job_repr("AsyncJob", self)
-
-
-_REPR_INDENT = " " * 4
-
-
-def _repr_payload(value: Any) -> str:
-    """Render a job payload as indented JSON, aligned under its field."""
-    try:
-        rendered = json.dumps(value, indent=4)
-    except TypeError:
-        return repr(value)
-    return rendered.replace("\n", "\n" + _REPR_INDENT)
-
-
-def _job_repr(kind: str, job: Any) -> str:
-    """Render every field the handle currently knows, omitting the rest.
-
-    One field per line, with the JSON payloads indented, because a refresh
-    job's spec and result are the point of printing it.
-    """
-    state = job.state
-    if state is None:
-        # Nothing has been fetched yet, so there is nothing to lay out.
-        known = f"id={job.id!r}, " if job.id is not None else ""
-        return f"{kind}({known}not refreshed)"
-
-    fields = []
-    if job.id is not None:
-        fields.append(f"id={job.id!r}")
-    fields.append(f"state={state!r}")
-    for name in ("job_type", "creation_ms"):
-        value = getattr(job, name)
-        if value is not None:
-            fields.append(f"{name}={value!r}")
-    for name in ("spec", "result"):
-        value = getattr(job, name)
-        if value is not None:
-            fields.append(f"{name}={_repr_payload(value)}")
-    if job.failure is not None:
-        fields.append(f"failure={job.failure!r}")
-    body = "".join(f"\n{_REPR_INDENT}{field}," for field in fields)
-    return f"{kind}({body}\n)"
-
 
 class Job(Generic[T]):
     """Synchronous counterpart of `AsyncJob` with the same result type."""
@@ -277,75 +122,6 @@ class Job(Generic[T]):
             return
         LOOP.run(self._inner.cancel())
 
-    def refresh(self) -> None:
-        """Ask the backend for this job's current state and record.
-
-        See :meth:`AsyncJob.refresh`.
-        """
-        if self._inner is None:
-            return
-        LOOP.run(self._inner.refresh())
-
-    @property
-    def state(self) -> Optional[str]:
-        """The last observed lifecycle state. See :attr:`AsyncJob.state`."""
-        return self._inner.state if self._inner is not None else "finished"
-
-    @property
-    def job_type(self) -> Optional[str]:
-        """The job's type. See :attr:`AsyncJob.job_type`."""
-        return self._field("job_type")
-
-    @property
-    def creation_ms(self) -> Optional[int]:
-        """When the job was created. See :attr:`AsyncJob.creation_ms`."""
-        return self._field("creation_ms")
-
-    @property
-    def spec(self) -> Optional[Any]:
-        """The job's specification. See :attr:`AsyncJob.spec`."""
-        return self._field("spec")
-
-    @property
-    def result(self) -> Optional[Any]:
-        """The job's terminal result. See :attr:`AsyncJob.result`."""
-        return self._field("result")
-
-    @property
-    def failure(self) -> Optional[JobFailureInfo]:
-        """Why the job failed. See :attr:`AsyncJob.failure`."""
-        return self._field("failure")
-
-    @property
-    def _spec_json(self) -> Optional[str]:
-        return self._field("_spec_json")
-
-    @property
-    def _result_json(self) -> Optional[str]:
-        return self._field("_result_json")
-
-    def _field(self, name: str) -> Optional[Any]:
-        return getattr(self._inner, name) if self._inner is not None else None
-
-    def events(
-        self,
-        *,
-        limit: Optional[int] = None,
-        filter: Optional[str] = None,
-    ) -> "pa.Table":
-        """This job's recorded lifecycle events.
-
-        See :meth:`AsyncJob.events`.
-        """
-        if self._inner is None:
-            raise NotImplementedError(
-                "job event history is only available for server-side jobs"
-            )
-        return LOOP.run(self._inner.events(limit=limit, filter=filter))
-
-    def __repr__(self) -> str:
-        return _job_repr("Job", self)
-
 
 def _typed_job(
     inner: "_lancedb.Job", result_decoder: Callable[[str], T]

python/python/lancedb/materialized_view.py

@@ -42,8 +42,6 @@ class MaterializedViewDefinition:
     """Cap on the number of rows the view holds."""
     inputs: List[str] = field(default_factory=list)
     """Source columns the projections and filter read."""
-    source_namespace: List[str] = field(default_factory=list)
-    """Namespace holding the source table; empty is the root namespace."""
 
 
 def _definition_from_schema(
@@ -55,8 +53,7 @@ def _definition_from_schema(
         raise ValueError(f"Table '{name}' is not a materialized view")
     value = json.loads(raw)
     kind = value.get("kind")
-    # "namespaced_select" keeps older readers from resolving the source at root.
+    if kind != "select":
-    if kind not in ("select", "namespaced_select"):
         raise NotImplementedError(
             f"materialized view '{name}' is defined by '{kind}', which this "
             "version of lancedb cannot refresh"
@@ -69,7 +66,6 @@ def _definition_from_schema(
         filter=value.get("filter"),
         limit=value.get("limit"),
         inputs=value.get("inputs", []),
-        source_namespace=value.get("source_namespace", []),
     )
 
 

python/python/lancedb/namespace.py

@@ -12,7 +12,6 @@ from __future__ import annotations
 
 import sys
 from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
-from uuid import UUID
 
 if sys.version_info >= (3, 12):
     from typing import override
@@ -49,11 +48,8 @@ from lancedb._lancedb import (
     connect_namespace_client as _connect_namespace_client,
 )
 from lancedb.background_loop import LOOP
-from lancedb.arrow import AsyncRecordBatchReader
 from lancedb.db import AsyncConnection, DBConnection
 from lancedb.job import AsyncJob, Job
-from lancedb.sql import AsyncQuery as AsyncSqlQuery
-from lancedb.sql import QueryDescription
 from lance_namespace import (
     LanceNamespace,
     connect as namespace_connect,
@@ -1451,37 +1447,6 @@ class AsyncLanceNamespaceDBConnection:
             namespace_path=namespace_path, page_token=page_token, limit=limit
         )
 
-    async def execute_query(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncRecordBatchReader:
-        """Execute SQL when supported by the underlying connection."""
-        return await self._inner.execute_query(
-            query,
-            default_namespace_path=default_namespace_path,
-        )
-
-    async def execute_query_async(
-        self,
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> AsyncSqlQuery:
-        """Start executing SQL when supported by the underlying connection.
-
-        Namespace-backed local connections do not support SQL.
-        """
-        return await self._inner.execute_query_async(
-            query,
-            default_namespace_path=default_namespace_path,
-        )
-
-    async def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query when supported."""
-        return await self._inner.describe_query(query_id)
-
     async def namespace_client(self) -> LanceNamespace:
         """Get the namespace client for this connection.
 

python/python/lancedb/query.py

@@ -109,7 +109,6 @@ def _query_is_plain_scan(query: Query) -> bool:
     return (
         query.vector is None
         and query.full_text_query is None
-        and query.take_offsets is None
         and not query.postfilter
         and not query.order_by
     )
@@ -168,12 +167,6 @@ def _projection_to_scanner_kwargs(columns: QueryProjection) -> Dict[str, Any]:
     return {"columns": projection}
 
 
-def _query_request_projection(req: "PyQueryRequest") -> QueryProjection:
-    if req.select_source_columns is not None:
-        return req.select_source_columns
-    return req.select
-
-
 def _scanner_kwargs_for_query(
     query: Query,
     blob_mode: BlobMode,
@@ -805,10 +798,6 @@ class Query(pydantic.BaseModel):
     # offset to start fetching results from
     offset: Optional[int] = None
 
-    # Dataset offsets whose duplicate occurrences must be restored after lookup.
-    # This is populated when a take query is converted to this serializable form.
-    take_offsets: Optional[List[int]] = None
-
     # if true, will only search the indexed data
     fast_search: Optional[bool] = None
 
@@ -830,7 +819,6 @@ class Query(pydantic.BaseModel):
         query = cls()
         query.limit = req.limit
         query.offset = req.offset
-        query.take_offsets = req.take_offsets
         query.filter = req.filter
         query.full_text_query = req.full_text_search
         query.columns = req.select
@@ -2811,16 +2799,15 @@ class AsyncQueryBase(object):
 
         req = self._inner.to_query_request()
         schema = await self._table.schema()
-        projection = _query_request_projection(req)
         self._blob_auto_row_id = blob_auto_row_id_for_scan(
             schema,
-            projection,
+            req.select,
             with_row_id=self._with_row_id,
         )
         if not self._blob_auto_row_id:
             self._blob_paths = ()
             return
-        self._blob_paths = tuple(blob_v2_projection_sources(schema, projection).keys())
+        self._blob_paths = tuple(blob_v2_projection_sources(schema, req.select).keys())
         self._inner.with_row_id()
 
     def select(self, columns: Union[List[str], dict[str, str]]) -> Self:
@@ -3907,15 +3894,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         blob_paths: tuple[str, ...] = ()
         if self._table is not None:
             schema = await self._table.schema()
-            projection = _query_request_projection(req)
             blob_auto_row_id = blob_auto_row_id_for_scan(
                 schema,
-                projection,
+                req.select,
                 with_row_id=self._with_row_id,
             )
             if blob_auto_row_id:
                 blob_paths = tuple(
-                    blob_v2_projection_sources(schema, projection).keys()
+                    blob_v2_projection_sources(schema, req.select).keys()
                 )
         self._blob_auto_row_id = blob_auto_row_id
         self._blob_paths = blob_paths

python/python/lancedb/remote/db.py

@@ -7,18 +7,8 @@ import json
 import logging
 from concurrent.futures import ThreadPoolExecutor
 import sys
-from typing import (
+from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
-    TYPE_CHECKING,
-    Any,
-    Dict,
-    Iterable,
-    List,
-    Optional,
-    Sequence,
-    Union,
-)
 from urllib.parse import urlparse
-from uuid import UUID
 import warnings
 
 if sys.version_info >= (3, 12):
@@ -35,13 +25,10 @@ from ..common import DATA
 from ..db import DBConnection, LOOP
 from ..functions import FunctionVersion, UdfDefinition
 from ..job import AsyncJob, Job
-from ..sql import Query as SqlQuery
-from ..sql import QueryDescription
 from ..materialized_view import MaterializedView, SelectArg
-from ..secrets import EnvVarSecret, SecretInfo
 
 if TYPE_CHECKING:
-    from .._lancedb import JobInfo
+    from .._lancedb import JobDescription, JobInfo
 from ..embeddings import EmbeddingFunctionConfig
 from lance_namespace import (
     LanceNamespace,
@@ -129,7 +116,6 @@ class RemoteDBConnection(DBConnection):
         read_timeout: Optional[float] = None,
         storage_options: Optional[Dict[str, str]] = None,
         read_consistency_interval: Optional[timedelta] = None,
-        sql_host_override: Optional[str] = None,
     ):
         """Connect to a remote LanceDB database."""
         if isinstance(client_config, dict):
@@ -175,7 +161,6 @@ class RemoteDBConnection(DBConnection):
         self.api_key = api_key
         self.region = region
         self.host_override = host_override
-        self.sql_host_override = sql_host_override
         self.storage_options = storage_options
         self.db_name = parsed.netloc
 
@@ -190,7 +175,6 @@ class RemoteDBConnection(DBConnection):
                 api_key=api_key,
                 region=region,
                 host_override=host_override,
-                sql_host_override=sql_host_override,
                 client_config=client_config,
                 storage_options=storage_options,
                 read_consistency_interval=read_consistency_interval,
@@ -209,7 +193,6 @@ class RemoteDBConnection(DBConnection):
                 "api_key": self.api_key,
                 "region": self.region,
                 "host_override": self.host_override,
-                "sql_host_override": self.sql_host_override,
                 "client_config": _client_config_to_dict(self.client_config),
                 "storage_options": self.storage_options,
             }
@@ -749,59 +732,36 @@ class RemoteDBConnection(DBConnection):
         )
 
     @override
-    def open_job(self, job_id: str) -> Job:
+    def job(self, job_id: str) -> Job:
-        """Open a server-side job by id. See
+        """A [Job][lancedb.job.Job] handle for a server-side job by id.
-        [DBConnection.open_job][lancedb.db.DBConnection.open_job].
+
+        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.
         """
-        return Job(LOOP.run(self._conn.open_job(job_id)))
+        return Job(self._conn.job(job_id))
 
     @override
-    def create_function_async(
+    def create_function_async(self, definition: UdfDefinition) -> Job[FunctionVersion]:
-        self,
+        return Job(LOOP.run(self._conn.create_function_async(definition)))
-        definition: UdfDefinition,
-        *,
-        secrets: Optional[Sequence[EnvVarSecret]] = None,
-    ) -> Job[FunctionVersion]:
-        job = LOOP.run(self._conn.create_function_async(definition, secrets=secrets))
-        return Job(job)
 
     @override
     def get_function(self, name: str, *, version: str) -> FunctionVersion:
         return LOOP.run(self._conn.get_function(name, version=version))
 
-    @override
-    def list_functions(self) -> List[FunctionVersion]:
-        return LOOP.run(self._conn.list_functions())
-
-    @override
-    def drop_function(self, name: str, *, version: str) -> bool:
-        return LOOP.run(self._conn.drop_function(name, version=version))
-
-    @override
-    def create_secret(self, name: str, value: str) -> None:
-        LOOP.run(self._conn.create_secret(name, value))
-
-    @override
-    def alter_secret(self, name: str, value: str) -> None:
-        LOOP.run(self._conn.alter_secret(name, value))
-
-    @override
-    def describe_secret(self, name: str) -> SecretInfo:
-        return LOOP.run(self._conn.describe_secret(name))
-
-    @override
-    def list_secrets(self) -> List[str]:
-        return LOOP.run(self._conn.list_secrets())
-
-    @override
-    def drop_secret(self, name: str) -> None:
-        LOOP.run(self._conn.drop_secret(name))
-
     @override
     def list_jobs(self) -> List["JobInfo"]:
         """List server-side jobs across the database's tables."""
         return LOOP.run(self._conn.list_jobs())
 
+    @override
+    def get_job(self, job_id: str) -> Optional["JobDescription"]:
+        """Describe a single server-side job by id.
+
+        Returns None when the server has no such job.
+        """
+        return LOOP.run(self._conn.get_job(job_id))
+
     @override
     def cancel_job(self, job_id: str) -> bool:
         """Request cancellation of a server-side job by id.
@@ -813,35 +773,12 @@ class RemoteDBConnection(DBConnection):
         return LOOP.run(self._conn.cancel_job(job_id))
 
     @override
-    def execute_query_async(
+    def job_history(self, job_id: Optional[str] = None) -> List[pa.RecordBatch]:
-        self,
+        """The lifecycle event history of a server-side job, as Arrow batches.
-        query: str,
-        *,
-        default_namespace_path: Optional[List[str]] = None,
-    ) -> SqlQuery:
-        """Start executing SQL through this remote connection.
 
-        Unqualified tables use this connection's database and the
+        Lists history across all jobs when `job_id` is None.
-        ``["public"]`` namespace by default. Fully qualified table names may
-        reference other databases available to the same deployment.
         """
-        return SqlQuery(
+        return LOOP.run(self._conn.job_history(job_id))
-            LOOP.run(
-                self._conn.execute_query_async(
-                    query,
-                    default_namespace_path=default_namespace_path,
-                )
-            )
-        )
-
-    @override
-    def describe_query(self, query_id: UUID) -> QueryDescription:
-        """Describe a submitted SQL query by its connection-scoped id."""
-        return LOOP.run(
-            self._conn.describe_query(
-                query_id,
-            )
-        )
 
     @override
     def namespace_client(self) -> LanceNamespace:

python/python/lancedb/remote/header.py

@@ -177,7 +177,4 @@ class OAuthProvider(HeaderProvider):
         if not self._current_token:
             raise RuntimeError("Failed to obtain OAuth token")
 
-        return {
+        return {"Authorization": f"Bearer {self._current_token}"}
-            "Authorization": f"Bearer {self._current_token}",
-            "x-lancedb-credential-type": "oidc",
-        }

python/python/lancedb/remote/table.py

@@ -36,7 +36,6 @@ from lancedb._lancedb import (
     UpdateResult,
 )
 from lancedb.embeddings.base import EmbeddingFunctionConfig
-from lancedb.expr import Expr
 from lancedb.index import (
     FTS,
     BTree,
@@ -67,15 +66,7 @@ from ..query import (
     LanceTakeQueryBuilder,
     LanceVectorQueryBuilder,
 )
-from ..table import (
+from ..table import AsyncTable, BlobMode, Branches, IndexStatistics, Query, Table, Tags
-    AsyncTable,
-    BlobMode,
-    Branches,
-    IndexStatistics,
-    Query,
-    Table,
-    Tags,
-)
 from ..types import BaseTokenizerType
 
 
@@ -548,7 +539,6 @@ class RemoteTable(Table):
         LOOP.run(
             self._table.create_index(
                 column,
-                replace=replace,
                 config=config,
                 wait_timeout=wait_timeout,
                 name=name,
@@ -873,7 +863,7 @@ class RemoteTable(Table):
 
     def update(
         self,
-        where: Optional[Union[str, Expr]] = None,
+        where: Optional[str] = None,
         values: Optional[dict] = None,
         *,
         values_sql: Optional[Dict[str, str]] = None,
@@ -884,11 +874,9 @@ class RemoteTable(Table):
 
         Parameters
         ----------
-        where: str or [Expr][lancedb.expr.Expr], optional
+        where: str, optional
-            The filter condition. Can be a SQL string or a type-safe
+            The SQL where clause to use when updating rows. For example, 'x = 2'
-            [Expr][lancedb.expr.Expr] built with [col][lancedb.expr.col] and
+            or 'x IN (1, 2, 3)'. The filter must not be empty, or it will error.
-            [lit][lancedb.expr.lit]. The filter must not be empty, or it will
-            error.
         values: dict, optional
             The values to update. The keys are the column names and the values
             are the values to set.

python/python/lancedb/schema.py

@@ -4,34 +4,30 @@
 
 """Schema helpers for Lance blob columns."""
 
-import importlib
-from typing import TYPE_CHECKING
-
 import pyarrow as pa
-import pyarrow.ipc
-
-if TYPE_CHECKING:
-    from lance.blob import BlobType as BlobType
 
 _BLOB_EXTENSION_NAME = "lance.blob.v2"
 _BLOB_V1_KEY = "lance-encoding:blob"
 _ARROW_EXT_NAME_KEY = "ARROW:extension:name"
-_BLOB_V2_STORAGE_TYPE = pa.struct(
-    [
-        pa.field("data", pa.large_binary(), nullable=True),
-        pa.field("uri", pa.utf8(), nullable=True),
-        pa.field("position", pa.uint64(), nullable=True),
-        pa.field("size", pa.uint64(), nullable=True),
-    ]
-)
-_resolved_blob_type = None
 
 
-class _FallbackBlobType(pa.ExtensionType):
+class BlobType(pa.ExtensionType):
-    """lance.blob.v2 extension type used when pylance is not installed."""
+    """PyArrow extension type for a Lance blob v2 column.
+
+    Queries return descriptors; call :meth:`~lancedb.table.Table.fetch_blob_files`
+    for lazy reads or :meth:`~lancedb.table.Table.fetch_blobs` for eager bytes.
+    """
 
     def __init__(self) -> None:
-        pa.ExtensionType.__init__(self, _BLOB_V2_STORAGE_TYPE, _BLOB_EXTENSION_NAME)
+        storage_type = pa.struct(
+            [
+                pa.field("data", pa.large_binary(), nullable=True),
+                pa.field("uri", pa.utf8(), nullable=True),
+                pa.field("position", pa.uint64(), nullable=True),
+                pa.field("size", pa.uint64(), nullable=True),
+            ]
+        )
+        super().__init__(storage_type, _BLOB_EXTENSION_NAME)
 
     def __arrow_ext_serialize__(self) -> bytes:
         return b""
@@ -39,16 +35,23 @@ class _FallbackBlobType(pa.ExtensionType):
     @classmethod
     def __arrow_ext_deserialize__(
         cls, storage_type: pa.DataType, serialized: bytes
-    ) -> "_FallbackBlobType":
+    ) -> "BlobType":
         return cls()
 
     def __reduce__(self):
+        # Ensure pickle round-trips on older pyarrow (apache/arrow#35599).
         return type(self).__arrow_ext_deserialize__, (
             self.storage_type,
             self.__arrow_ext_serialize__(),
         )
 
 
+try:
+    pa.register_extension_type(BlobType())  # type: ignore[arg-type]
+except pa.ArrowKeyError:
+    pass
+
+
 def _metadata_value(metadata: dict, key: str):
     return metadata.get(key.encode()) or metadata.get(key)
 
@@ -89,105 +92,43 @@ def is_blob_like_field(field: pa.Field) -> bool:
     return is_blob_v2_field(field) or _metadata_marks_legacy_blob(field.metadata or {})
 
 
-def _collect_blob_paths(schema: pa.Schema, is_blob) -> list[tuple[str, bool]]:
+def _collect_blob_paths(schema: pa.Schema, is_blob) -> list[str]:
-    """Walk the schema and return (path, has_list_ancestor) for each blob field."""
+    paths: list[str] = []
-    paths: list[tuple[str, bool]] = []
 
-    def walk(fields, prefix: str, has_list_ancestor: bool) -> None:
+    def walk(fields, prefix: str) -> None:
         for field in fields:
             path = f"{prefix}.{field.name}" if prefix else field.name
             if is_blob(field):
-                paths.append((path, has_list_ancestor))
+                paths.append(path)
             elif pa.types.is_struct(field.type):
-                walk(field.type, path, has_list_ancestor)
+                walk(field.type, path)
             elif (
                 pa.types.is_list(field.type)
                 or pa.types.is_large_list(field.type)
                 or pa.types.is_fixed_size_list(field.type)
             ):
-                walk([field.type.value_field], path, True)
+                walk([field.type.value_field], path)
 
-    walk(schema, "", False)
+    walk(schema, "")
     return paths
 
 
 def blob_column_paths(schema: pa.Schema) -> list[str]:
     """Dotted paths of blob-like columns (v2 extension or legacy metadata)."""
-    return [path for path, _ in _collect_blob_paths(schema, is_blob_like_field)]
+    return _collect_blob_paths(schema, is_blob_like_field)
 
 
 def blob_v2_column_paths(schema: pa.Schema) -> list[str]:
-    return [path for path, _ in _collect_blob_paths(schema, is_blob_v2_field)]
+    return _collect_blob_paths(schema, is_blob_v2_field)
-
-
-def row_addressable_blob_v2_paths(schema: pa.Schema) -> list[str]:
-    """Blob v2 paths with one blob addressable by table row id.
-
-    ``fetch_blobs`` and the descriptor row-id ride-along address one blob per
-    row, so a blob inside a list container has no row-id slot and no fetch
-    path. Those columns still store and query as raw descriptors.
-    """
-    return [
-        path
-        for path, has_list_ancestor in _collect_blob_paths(schema, is_blob_v2_field)
-        if not has_list_ancestor
-    ]
 
 
 def schema_has_blob_field(schema: pa.Schema) -> bool:
     return bool(blob_column_paths(schema))
 
 
-def _deserialize_registered_type(extension_type: pa.ExtensionType) -> pa.DataType:
-    """Return the type Arrow reconstructs for this extension name."""
-    schema = pa.schema([pa.field("value", extension_type)])
-    restored = pa.ipc.read_schema(schema.serialize())
-    return restored.field("value").type
-
-
-def _resolve_blob_type():
-    """Return the BlobType class this process should use.
-
-    pylance's class when it owns the lance.blob.v2 registry entry,
-    otherwise LanceDB's fallback. A different registered class is an error.
-    """
-    global _resolved_blob_type
-    if _resolved_blob_type is not None:
-        return _resolved_blob_type
-    try:
-        blob_module = importlib.import_module("lance.blob")
-    except ModuleNotFoundError as err:
-        if err.name not in ("lance", "lance.blob"):
-            raise
-    else:
-        blob_type = getattr(blob_module, "BlobType", None)
-        if blob_type is not None:
-            registered_type = _deserialize_registered_type(blob_type())
-            if type(registered_type) is not blob_type:
-                registered_cls = type(registered_type)
-                raise ValueError(
-                    "lance.blob.v2 is already registered by "
-                    f"{registered_cls.__module__}.{registered_cls.__qualname__}"
-                )
-            _resolved_blob_type = blob_type
-            return blob_type
-    try:
-        pa.register_extension_type(_FallbackBlobType())  # type: ignore[arg-type]
-    except pa.ArrowKeyError as err:
-        raise ValueError(
-            "lance.blob.v2 is already registered by another extension class"
-        ) from err
-    _resolved_blob_type = _FallbackBlobType
-    return _resolved_blob_type
-
-
 def blob(name: str, nullable: bool = True) -> pa.Field:
-    """Create a Lance blob v2 column field.
+    """Create a Lance blob v2 column field."""
-
+    return pa.field(name, BlobType(), nullable=nullable)
-    When pylance is installed this is ``lance.blob.BlobType``.
-    """
-    blob_type = _resolve_blob_type()
-    return pa.field(name, blob_type(), nullable=nullable)
 
 
 def vector(dimension: int, value_type: pa.DataType = pa.float32()) -> pa.DataType:
@@ -214,11 +155,3 @@ def vector(dimension: int, value_type: pa.DataType = pa.float32()) -> pa.DataTyp
     ... ])
     """
     return pa.list_(value_type, dimension)
-
-
-def __getattr__(name: str):
-    if name == "BlobType":
-        blob_type = _resolve_blob_type()
-        globals()["BlobType"] = blob_type
-        return blob_type
-    raise AttributeError(f"module {__name__!r} has no attribute {name!r}")

python/python/lancedb/secrets.py

@@ -1,169 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Named Secrets, and the bindings that deliver them to Functions.
-
-A Secret is a database-scoped named credential. Nothing in this module holds a
-value: :class:`EnvVarSecret` names one and says which environment variable it
-should arrive in, and the value is resolved by the remote service when a
-Function bound to it runs. No API returns a stored credential, by construction
-rather than by policy -- there is no code path that could.
-"""
-
-from __future__ import annotations
-
-import re
-
-# The same characters LanceDB already admits in a namespace or table name, and
-# no positional rule on top of them: a segment may begin with `_`, `-` or `.`
-# today, so anything narrower would put Secrets out of reach inside namespaces
-# that already exist. Matches the service, which admits the same set.
-_SECRET_NAME = re.compile(r"^[A-Za-z0-9_.-]{1,255}$")
-_ENV_VARIABLE = re.compile(r"^[A-Za-z_][A-Za-z0-9_]*$")
-
-
-def validate_secret_name(name: str) -> str:
-    """Check a Secret name locally and return it unchanged."""
-    if not isinstance(name, str):
-        raise TypeError(f"Secret name must be a string, not {type(name).__name__}")
-    if not _SECRET_NAME.fullmatch(name):
-        raise ValueError(f"invalid Secret name: {name!r}")
-    return name
-
-
-def validate_env_variable(name: str) -> str:
-    """Check an environment variable name locally and return it unchanged."""
-    if not isinstance(name, str):
-        raise TypeError(
-            f"environment variable name must be a string, not {type(name).__name__}"
-        )
-    if not _ENV_VARIABLE.fullmatch(name):
-        raise ValueError(f"invalid environment variable name: {name!r}")
-    return name
-
-
-class EnvVarSecret:
-    """A Secret bound to the environment variable a Function's library reads.
-
-    Pass these in the ``secrets`` sequence of
-    [DBConnection.create_function][lancedb.db.DBConnection.create_function]. The
-    Function's source is unchanged by binding: it reads ``OPENAI_API_KEY`` the
-    way it always did, and the binding is what puts a value there.
-
-    This is a local value. Constructing it contacts no server, so it always
-    succeeds and says nothing about whether the Secret exists; that is checked
-    at registration, where a mistyped Secret name surfaces as a clear "does not
-    exist" naming both the Secret and the variable bound to it. A mistyped
-    *variable* name cannot be caught anywhere -- nothing knows which variables a
-    Function reads -- so it surfaces on the first rows instead.
-
-    The type exists so a credential cannot be passed by accident. A bare string
-    in the same position is a plausible-looking mistake with the opposite
-    meaning, and it reads identically in a diff.
-
-    Parameters
-    ----------
-    secret : str
-        The Secret's database-scoped name.
-    env_variable : str
-        The environment variable the Function reads it from.
-
-    Examples
-    --------
-    >>> from lancedb import EnvVarSecret
-    >>> binding = EnvVarSecret(secret="openai-prod", env_variable="OPENAI_API_KEY")
-    >>> binding.secret, binding.env_variable
-    ('openai-prod', 'OPENAI_API_KEY')
-    """
-
-    __slots__ = ("_secret", "_env_variable")
-
-    def __init__(self, secret: str, env_variable: str):
-        self._secret = validate_secret_name(secret)
-        self._env_variable = validate_env_variable(env_variable)
-
-    @property
-    def secret(self) -> str:
-        """The Secret's database-scoped name."""
-        return self._secret
-
-    @property
-    def env_variable(self) -> str:
-        """The environment variable the value is delivered in."""
-        return self._env_variable
-
-    def __repr__(self) -> str:
-        return (
-            f"EnvVarSecret(secret={self._secret!r}, "
-            f"env_variable={self._env_variable!r})"
-        )
-
-    def __eq__(self, other: object) -> bool:
-        return (
-            isinstance(other, EnvVarSecret)
-            and other._secret == self._secret
-            and other._env_variable == self._env_variable
-        )
-
-    def __hash__(self) -> int:
-        return hash((EnvVarSecret, self._secret, self._env_variable))
-
-
-class SecretInfo:
-    """What a database records about a Secret. Never its value.
-
-    Returned by
-    [DBConnection.describe_secret][lancedb.db.DBConnection.describe_secret].
-    """
-
-    __slots__ = ("_name", "_created_at", "_updated_at")
-
-    def __init__(self, name: str, created_at: str, updated_at: str):
-        self._name = name
-        self._created_at = created_at
-        self._updated_at = updated_at
-
-    @property
-    def name(self) -> str:
-        """The Secret's database-scoped name."""
-        return self._name
-
-    @property
-    def created_at(self) -> str:
-        """When the Secret was created, as an RFC 3339 timestamp."""
-        return self._created_at
-
-    @property
-    def updated_at(self) -> str:
-        """When the Secret's value was last rotated, as an RFC 3339 timestamp."""
-        return self._updated_at
-
-    @classmethod
-    def from_json(cls, value: dict) -> "SecretInfo":
-        return cls(
-            name=value["name"],
-            created_at=value["created_at"],
-            updated_at=value["updated_at"],
-        )
-
-    def __repr__(self) -> str:
-        return (
-            f"SecretInfo(name={self._name!r}, created_at={self._created_at!r}, "
-            f"updated_at={self._updated_at!r})"
-        )
-
-    def __eq__(self, other: object) -> bool:
-        return (
-            isinstance(other, SecretInfo)
-            and other._name == self._name
-            and other._created_at == self._created_at
-            and other._updated_at == self._updated_at
-        )
-
-
-__all__ = [
-    "EnvVarSecret",
-    "SecretInfo",
-    "validate_env_variable",
-    "validate_secret_name",
-]

python/python/lancedb/sql.py

@@ -1,88 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Handles to SQL queries running on a remote database."""
-
-from uuid import UUID
-
-import pyarrow as pa
-
-from lancedb.background_loop import LOOP
-
-from . import _lancedb
-from .arrow import AsyncRecordBatchReader
-
-QueryDescription = _lancedb.QueryDescription
-
-
-class AsyncQuery:
-    """A handle to a submitted SQL query on an asynchronous connection."""
-
-    def __init__(self, inner: "_lancedb.SqlQuery"):
-        self._inner = inner
-
-    @property
-    def id(self) -> UUID:
-        """The stable identifier scoped to the connection that submitted it."""
-        return self._inner.id
-
-    async def describe(self) -> QueryDescription:
-        """Get a point-in-time description of the query."""
-        return await self._inner.describe()
-
-    async def reader(self) -> AsyncRecordBatchReader:
-        """Wait for the initial result stream and return its Arrow reader.
-
-        Results are single-consumer. Calling this method more than once on the
-        same query raises an error. Later batches are streamed as they become
-        available without waiting for the full query to finish.
-        """
-        return AsyncRecordBatchReader(await self._inner.reader())
-
-    async def cancel(self) -> None:
-        """Request cancellation of the query."""
-        await self._inner.cancel()
-
-
-class Query:
-    """Synchronous counterpart of :class:`AsyncQuery`."""
-
-    def __init__(self, inner: AsyncQuery):
-        self._inner = inner
-
-    @property
-    def id(self) -> UUID:
-        """The stable identifier scoped to the connection that submitted it."""
-        return self._inner.id
-
-    def describe(self) -> QueryDescription:
-        """Get a point-in-time description of the query."""
-        return LOOP.run(self._inner.describe())
-
-    def reader(self) -> pa.RecordBatchReader:
-        """Wait for the initial result stream and return a blocking reader.
-
-        Results are single-consumer. Calling this method more than once on the
-        same query raises an error. Later batches block only until they become
-        available, without waiting for the full query to finish.
-        """
-        reader = LOOP.run(self._inner.reader())
-
-        def next_batch():
-            try:
-                return LOOP.run(reader.__anext__())
-            except StopAsyncIteration:
-                return None
-
-        def batches():
-            while (batch := next_batch()) is not None:
-                yield batch
-
-        return pa.RecordBatchReader.from_batches(reader.schema, batches())
-
-    def cancel(self) -> None:
-        """Request cancellation of the query."""
-        LOOP.run(self._inner.cancel())
-
-
-__all__ = ["AsyncQuery", "Query", "QueryDescription"]

python/python/lancedb/table.py

@@ -104,12 +104,7 @@ from .util import (
     value_to_sql,
 )
 from .index import lang_mapping
-from .schema import (
+from .schema import blob_v2_column_paths, schema_has_blob_field
-    blob_v2_column_paths,
-    is_blob_v2_field,
-    row_addressable_blob_v2_paths,
-    schema_has_blob_field,
-)
 
 
 def _should_push_down_query_table(
@@ -431,7 +426,6 @@ def _cast_to_target_schema(
 
     def gen():
         for batch in reader:
-            batch = _coerce_blob_write_columns(batch, reordered_schema)
             # Table but not RecordBatch has cast.
             cast_batches = (
                 pa.Table.from_batches([batch]).cast(reordered_schema).to_batches()
@@ -444,166 +438,6 @@ def _cast_to_target_schema(
     return pa.RecordBatchReader.from_batches(reordered_schema, gen())
 
 
-def _coerce_blob_write_columns(
-    batch: pa.RecordBatch, target_schema: pa.Schema
-) -> pa.RecordBatch:
-    """Materialize blob storage structs before the stream leaves Python.
-
-    merge_insert requires its source reader to already match the table's
-    physical schema. Unlike add and insert, it does not pass through
-    LanceDB's Rust blob coercion, so preserving binary input here would
-    reach Lance as binary and fail the schema check.
-    """
-    columns = []
-    fields = []
-    changed = False
-    for field, column in zip(batch.schema, batch.columns):
-        target_field = target_schema.field(field.name)
-        coerced = _coerce_blob_value(column, target_field)
-        if coerced is not column:
-            column = coerced
-            field = pa.field(
-                field.name,
-                coerced.type,
-                field.nullable,
-                target_field.metadata,
-            )
-            changed = True
-        columns.append(column)
-        fields.append(field)
-    if not changed:
-        return batch
-    return pa.RecordBatch.from_arrays(
-        columns, schema=pa.schema(fields, metadata=batch.schema.metadata)
-    )
-
-
-def _coerce_blob_value(column: pa.Array, target_field: pa.Field) -> pa.Array:
-    if is_blob_v2_field(target_field) and _can_coerce_to_blob(column.type):
-        return _coerce_value_to_blob(column, target_field)
-
-    target_type = target_field.type
-    if pa.types.is_struct(target_type) and pa.types.is_struct(column.type):
-        children = []
-        fields = []
-        changed = False
-        for source_field in column.type:
-            source_column = column.field(source_field.name)
-            nested_target = next(
-                (field for field in target_type if field.name == source_field.name),
-                None,
-            )
-            if nested_target is None:
-                children.append(source_column)
-                fields.append(source_field)
-                continue
-            coerced = _coerce_blob_value(source_column, nested_target)
-            if coerced is not source_column:
-                changed = True
-            child_array, child_type = _physical_array_and_type(coerced)
-            children.append(child_array)
-            fields.append(
-                pa.field(
-                    source_field.name,
-                    child_type,
-                    source_field.nullable,
-                    nested_target.metadata,
-                )
-            )
-        if not changed:
-            return column
-        return pa.StructArray.from_arrays(
-            children,
-            fields=fields,
-            mask=column.is_null() if column.null_count else None,
-        )
-
-    if _is_list_like(target_type) and _is_list_like(column.type):
-        return _coerce_blob_list_values(column, target_type.value_field)
-
-    return column
-
-
-def _coerce_blob_list_values(
-    column: pa.Array, target_value_field: pa.Field
-) -> pa.Array:
-    """Coerce blob values inside a list column, preserving offsets and nulls.
-
-    Works on the raw child values window instead of ``pc.list_flatten`` because
-    flatten drops values spanned by null slots, which would misalign offsets.
-    """
-    mask = column.is_null() if column.null_count else None
-    if pa.types.is_fixed_size_list(column.type):
-        list_size = column.type.list_size
-        values = column.values.slice(column.offset * list_size, len(column) * list_size)
-        coerced = _coerce_blob_value(values, target_value_field)
-        if coerced is values:
-            return column
-        physical_values, _ = _physical_array_and_type(coerced)
-        return pa.FixedSizeListArray.from_arrays(physical_values, list_size, mask=mask)
-    offsets = column.offsets
-    first_offset = offsets[0].as_py()
-    values = column.values.slice(
-        first_offset,
-        offsets[-1].as_py() - first_offset,
-    )
-    coerced = _coerce_blob_value(values, target_value_field)
-    if coerced is values:
-        return column
-    physical_values, _ = _physical_array_and_type(coerced)
-    if first_offset:
-        offsets = pc.subtract(offsets, pa.scalar(first_offset, offsets.type))
-    if pa.types.is_large_list(column.type):
-        return pa.LargeListArray.from_arrays(offsets, physical_values, mask=mask)
-    return pa.ListArray.from_arrays(offsets, physical_values, mask=mask)
-
-
-def _coerce_value_to_blob(values: pa.Array, target_field: pa.Field) -> pa.Array:
-    if pa.types.is_null(values.type):
-        data = pa.nulls(len(values), type=pa.large_binary())
-    elif pa.types.is_large_binary(values.type):
-        data = values
-    else:
-        data = values.cast(pa.large_binary())
-    length = len(values)
-    storage_type = target_field.type
-    if isinstance(storage_type, pa.ExtensionType):
-        storage_type = storage_type.storage_type
-    storage_fields = list(storage_type)
-    children = []
-    for storage_field in storage_fields:
-        if storage_field.name == "data":
-            children.append(data)
-        else:
-            children.append(pa.nulls(length, type=storage_field.type))
-    storage = pa.StructArray.from_arrays(
-        children,
-        fields=storage_fields,
-        mask=values.is_null() if values.null_count else None,
-    )
-    if isinstance(target_field.type, pa.ExtensionType):
-        return pa.ExtensionArray.from_storage(target_field.type, storage)
-    return storage
-
-
-def _physical_array_and_type(array: pa.Array) -> tuple[pa.Array, pa.DataType]:
-    if isinstance(array.type, pa.ExtensionType):
-        return array.storage, array.type.storage_type
-    return array, array.type
-
-
-def _can_coerce_to_blob(data_type: pa.DataType) -> bool:
-    return _is_binary_like(data_type) or pa.types.is_null(data_type)
-
-
-def _is_binary_like(data_type: pa.DataType) -> bool:
-    return (
-        pa.types.is_binary(data_type)
-        or pa.types.is_large_binary(data_type)
-        or pa.types.is_binary_view(data_type)
-    )
-
-
 def _field_extension_name(field: pa.Field) -> Optional[str]:
     extension_name = getattr(field.type, "extension_name", None)
     if extension_name is not None:
@@ -630,73 +464,65 @@ def _align_field_types(
         target_field = next((f for f in target_fields if f.name == field.name), None)
         if target_field is None:
             raise ValueError(f"Field '{field.name}' not found in target schema")
-        new_fields.append(_align_field(field, target_field))
+        # Preserve arrow.json input until it reaches Lance. LanceDB exposes stored
+        # JSON columns as lance.json (JSONB-backed LargeBinary), but casting the
+        # input to that storage type here merely relabels the raw JSON bytes as
+        # JSONB. Lance must see arrow.json so it can perform the JSONB encoding.
+        if (
+            _field_extension_name(field) == "arrow.json"
+            and _field_extension_name(target_field) == "lance.json"
+        ):
+            new_fields.append(field)
+            continue
+        if pa.types.is_struct(target_field.type):
+            if pa.types.is_struct(field.type):
+                new_type = pa.struct(
+                    _align_field_types(
+                        field.type.fields,
+                        target_field.type.fields,
+                    )
+                )
+            else:
+                new_type = target_field.type
+        elif pa.types.is_list(target_field.type):
+            if _is_list_like(field.type):
+                new_type = pa.list_(
+                    _align_field_types(
+                        [field.type.value_field],
+                        [target_field.type.value_field],
+                    )[0]
+                )
+            else:
+                new_type = target_field.type
+        elif pa.types.is_large_list(target_field.type):
+            if _is_list_like(field.type):
+                new_type = pa.large_list(
+                    _align_field_types(
+                        [field.type.value_field],
+                        [target_field.type.value_field],
+                    )[0]
+                )
+            else:
+                new_type = target_field.type
+        elif pa.types.is_fixed_size_list(target_field.type):
+            if _is_list_like(field.type):
+                new_type = pa.list_(
+                    _align_field_types(
+                        [field.type.value_field],
+                        [target_field.type.value_field],
+                    )[0],
+                    target_field.type.list_size,
+                )
+            else:
+                new_type = target_field.type
+        else:
+            new_type = target_field.type
+        new_fields.append(
+            pa.field(field.name, new_type, field.nullable, target_field.metadata)
+        )
     return new_fields
 
 
-def _align_list_value_field(
-    value_field: pa.Field, target_value_field: pa.Field
-) -> pa.Field:
-    # A list has exactly one child, so the inferred child name ("item") aligns
-    # positionally and adopts the table's child name; pa.Table.cast renames it.
-    return _align_field(value_field, target_value_field).with_name(
-        target_value_field.name
-    )
-
-
-def _align_field(field: pa.Field, target_field: pa.Field) -> pa.Field:
-    # Preserve arrow.json input until it reaches Lance. LanceDB exposes stored
-    # JSON columns as lance.json (JSONB-backed LargeBinary), but casting the
-    # input to that storage type here merely relabels the raw JSON bytes as
-    # JSONB. Lance must see arrow.json so it can perform the JSONB encoding.
-    if (
-        _field_extension_name(field) == "arrow.json"
-        and _field_extension_name(target_field) == "lance.json"
-    ):
-        return field
-    if pa.types.is_struct(target_field.type):
-        if pa.types.is_struct(field.type):
-            new_type = pa.struct(
-                _align_field_types(
-                    field.type.fields,
-                    target_field.type.fields,
-                )
-            )
-        else:
-            new_type = target_field.type
-    elif pa.types.is_list(target_field.type):
-        if _is_list_like(field.type):
-            new_type = pa.list_(
-                _align_list_value_field(
-                    field.type.value_field, target_field.type.value_field
-                )
-            )
-        else:
-            new_type = target_field.type
-    elif pa.types.is_large_list(target_field.type):
-        if _is_list_like(field.type):
-            new_type = pa.large_list(
-                _align_list_value_field(
-                    field.type.value_field, target_field.type.value_field
-                )
-            )
-        else:
-            new_type = target_field.type
-    elif pa.types.is_fixed_size_list(target_field.type):
-        if _is_list_like(field.type):
-            new_type = pa.list_(
-                _align_list_value_field(
-                    field.type.value_field, target_field.type.value_field
-                ),
-                target_field.type.list_size,
-            )
-        else:
-            new_type = target_field.type
-    else:
-        new_type = target_field.type
-    return pa.field(field.name, new_type, field.nullable, target_field.metadata)
-
-
 def _infer_subschema(
     schema: List[pa.Field],
     reference_fields: List[pa.Field],
@@ -763,7 +589,7 @@ def sanitize_create_table(
         schema = data.schema
     else:
         if schema is not None:
-            data = pa.Table.from_batches([], schema=schema)
+            data = pa.Table.from_pylist([], schema)
     if schema is None:
         if data is None:
             raise ValueError("Either data or schema must be provided")
@@ -1547,9 +1373,7 @@ class Table(ABC):
         on: Union[str, Iterable[str]]
             A column (or columns) to join on.  This is how records from the
             source table and target table are matched.  Typically this is some
-            kind of key or id column.  Passing several columns matches on the
+            kind of key or id column.
-            composite key: a source row updates a target row only when it
-            agrees on every one of them.
 
         Examples
         --------
@@ -1680,9 +1504,9 @@ class Table(ABC):
         Offsets are mostly useful for sampling as the set of all valid offsets is easily
         known in advance to be [0, len(table)).
 
-        No guarantees are made regarding the order in which results are returned.
+        No guarantees are made regarding the order in which results are returned.  If
-        Repeated offsets produce repeated rows, which makes this method suitable for
+        you desire an output order that matches the order of the given offsets, you will
-        sampling with replacement.
+        need to add the row offset column to the output and align it yourself.
 
         Parameters
         ----------
@@ -1793,9 +1617,6 @@ class Table(ABC):
         The result has the same length and order as ``row_ids``. Null blobs
         produce null slots; valid empty blobs produce ``b""``.
 
-        ``_rowid`` values stay valid after compaction when the table has stable
-        row ids.
-
         Convenience for small payloads. For large values use
         :meth:`fetch_blob_files`.
         """
@@ -1813,9 +1634,6 @@ class Table(ABC):
         The result has the same length and order as ``requests``; null blobs
         produce null slots and empty ranges on non-null blobs produce ``b""``.
 
-        ``_rowid`` values stay valid after compaction when the table has stable
-        row ids.
-
         Row IDs can be obtained from a query with ``with_row_id(True)``. This
         API is currently supported only by local tables.
         """
@@ -1831,9 +1649,6 @@ class Table(ABC):
         ``_rowid`` or a ``_lance_row_id`` field on the blob descriptor. Null
         rows are ``None``. Remote tables require LanceDB Cloud server 0.5.0 or
         newer.
-
-        ``_rowid`` values stay valid after compaction when the table has stable
-        row ids.
         """
 
     @abstractmethod
@@ -1929,7 +1744,7 @@ class Table(ABC):
     @abstractmethod
     def update(
         self,
-        where: Optional[Union[str, Expr]] = None,
+        where: Optional[str] = None,
         values: Optional[dict] = None,
         *,
         values_sql: Optional[Dict[str, str]] = None,
@@ -1944,11 +1759,9 @@ class Table(ABC):
 
         Parameters
         ----------
-        where: str or [Expr][lancedb.expr.Expr], optional
+        where: str, optional
-            The filter condition. Can be a SQL string or a type-safe
+            The SQL where clause to use when updating rows. For example, 'x = 2'
-            [Expr][lancedb.expr.Expr] built with [col][lancedb.expr.col] and
+            or 'x IN (1, 2, 3)'. The filter must not be empty, or it will error.
-            [lit][lancedb.expr.lit]. The filter must not be empty, or it will
-            error.
         values: dict, optional
             The values to update. The keys are the column names and the values
             are the values to set.
@@ -1966,7 +1779,6 @@ class Table(ABC):
         Examples
         --------
         >>> import lancedb
-        >>> from lancedb.expr import col
         >>> import pandas as pd
         >>> data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1.0, 2], [3, 4], [5, 6]]})
         >>> db = lancedb.connect("./.lancedb")
@@ -1976,7 +1788,7 @@ class Table(ABC):
         0  1  [1.0, 2.0]
         1  2  [3.0, 4.0]
         2  3  [5.0, 6.0]
-        >>> table.update(where=col("x") == 2, values={"vector": [10.0, 10]})
+        >>> table.update(where="x = 2", values={"vector": [10.0, 10]})
         UpdateResult(rows_updated=1, version=2)
         >>> table.to_pandas()
            x        vector
@@ -2176,11 +1988,9 @@ class Table(ABC):
             Function columns are supported only on LanceDB Cloud and
             Enterprise.
         computed: Dict[str, str], optional
-            A mapping from output column names to SQL expressions derives each
+            A map of column name to a SQL expression defining the column. The
-            output field from its expression. A direct projection of a Blob v2
+            column's type and inputs are derived from the expression, so no
-            field inherits Blob v2 semantics; other expressions derive their
+            data type is supplied.
-            ordinary Arrow type. Mapping order is declaration and dependency
-            order.
 
             Unlike ``transforms``, the expression is stored rather than
             evaluated now: the column is committed with no values, and rows get
@@ -2885,7 +2695,7 @@ class LanceTable(Table):
             arrow_tbl = self.to_arrow()
             if blob_mode == "descriptions":
                 arrow_tbl = strip_auto_row_ids(
-                    arrow_tbl, row_addressable_blob_v2_paths(self.schema)
+                    arrow_tbl, blob_v2_column_paths(self.schema)
                 )
             return arrow_tbl.to_pandas(**kwargs)
 
@@ -4031,7 +3841,7 @@ class LanceTable(Table):
 
     def update(
         self,
-        where: Optional[Union[str, Expr]] = None,
+        where: Optional[str] = None,
         values: Optional[dict] = None,
         *,
         values_sql: Optional[Dict[str, str]] = None,
@@ -4042,11 +3852,9 @@ class LanceTable(Table):
 
         Parameters
         ----------
-        where: str or [Expr][lancedb.expr.Expr], optional
+        where: str, optional
-            The filter condition. Can be a SQL string or a type-safe
+            The SQL where clause to use when updating rows. For example, 'x = 2'
-            [Expr][lancedb.expr.Expr] built with [col][lancedb.expr.col] and
+            or 'x IN (1, 2, 3)'. The filter must not be empty, or it will error.
-            [lit][lancedb.expr.lit]. The filter must not be empty, or it will
-            error.
         values: dict, optional
             The values to update. The keys are the column names and the values
             are the values to set.
@@ -4064,7 +3872,6 @@ class LanceTable(Table):
         Examples
         --------
         >>> import lancedb
-        >>> from lancedb.expr import col
         >>> import pandas as pd
         >>> data = pd.DataFrame({"x": [1, 2, 3], "vector": [[1.0, 2], [3, 4], [5, 6]]})
         >>> db = lancedb.connect("./.lancedb")
@@ -4074,7 +3881,7 @@ class LanceTable(Table):
         0  1  [1.0, 2.0]
         1  2  [3.0, 4.0]
         2  3  [5.0, 6.0]
-        >>> table.update(where=col("x") == 2, values={"vector": [10.0, 10]})
+        >>> table.update(where="x = 2", values={"vector": [10.0, 10]})
         UpdateResult(rows_updated=1, version=2)
         >>> table.to_pandas()
            x        vector
@@ -4101,7 +3908,6 @@ class LanceTable(Table):
             )
             and not self._route_pushdown_to_rust
             and self.current_branch() is None
-            and query.take_offsets is None
         ):
             from lancedb.namespace import _execute_server_side_query
 
@@ -5290,9 +5096,7 @@ class AsyncTable:
         if blob_mode == "descriptions" or not schema_has_blob_field(schema):
             arrow_tbl = await self.to_arrow()
             if blob_mode == "descriptions":
-                arrow_tbl = strip_auto_row_ids(
+                arrow_tbl = strip_auto_row_ids(arrow_tbl, blob_v2_column_paths(schema))
-                    arrow_tbl, row_addressable_blob_v2_paths(schema)
-                )
             return arrow_tbl.to_pandas(**kwargs)
 
         if blob_mode == "lazy" and get_uri_scheme(await self.uri()) == "memory":
@@ -5712,9 +5516,7 @@ class AsyncTable:
         on: Union[str, Iterable[str]]
             A column (or columns) to join on.  This is how records from the
             source table and target table are matched.  Typically this is some
-            kind of key or id column.  Passing several columns matches on the
+            kind of key or id column.
-            composite key: a source row updates a target row only when it
-            agrees on every one of them.
 
         Examples
         --------
@@ -5997,23 +5799,7 @@ class AsyncTable:
 
     def _sync_query_to_async(
         self, query: Query
-    ) -> (
+    ) -> AsyncHybridQuery | AsyncFTSQuery | AsyncVectorQuery | AsyncQuery:
-        AsyncHybridQuery
-        | AsyncFTSQuery
-        | AsyncVectorQuery
-        | AsyncQuery
-        | AsyncTakeQuery
-    ):
-        if query.take_offsets is not None:
-            take_query = self.take_offsets(query.take_offsets)
-            if query.columns:
-                take_query = take_query.select(query.columns)
-            if query.use_lsm is not None:
-                take_query = take_query.use_lsm(query.use_lsm)
-            if query.with_row_id:
-                take_query = take_query.with_row_id()
-            return take_query
-
         async_query = self.query()
         if query.limit is not None:
             async_query = async_query.limit(query.limit)
@@ -6078,7 +5864,6 @@ class AsyncTable:
                 self._namespace_client, self._pushdown_operations
             )
             and not self._route_pushdown_to_rust
-            and query.take_offsets is None
         ):
             from lancedb.namespace import _execute_server_side_query
 
@@ -6210,7 +5995,7 @@ class AsyncTable:
         self,
         updates: Optional[Dict[str, Any]] = None,
         *,
-        where: Optional[Union[str, Expr]] = None,
+        where: Optional[str] = None,
         updates_sql: Optional[Dict[str, str]] = None,
     ) -> UpdateResult:
         """
@@ -6225,11 +6010,9 @@ class AsyncTable:
             The updates to apply.  The keys should be the name of the column to
             update.  The values should be the new values to assign.  This is
             required unless updates_sql is supplied.
-        where: str or [Expr][lancedb.expr.Expr], optional
+        where: str, optional
-            The filter condition. Can be a SQL string or a type-safe
+            An SQL filter that controls which rows are updated. For example, 'x = 2'
-            [Expr][lancedb.expr.Expr] built with [col][lancedb.expr.col] and
+            or 'x IN (1, 2, 3)'.  Only rows that satisfy this filter will be udpated.
-            [lit][lancedb.expr.lit]. Only rows that satisfy this filter will
-            be updated.
         updates_sql: dict, optional
             The updates to apply, expressed as SQL expression strings.  The keys should
             be column names. The values should be SQL expressions.  These can be SQL
@@ -6247,14 +6030,13 @@ class AsyncTable:
         --------
         >>> import asyncio
         >>> import lancedb
-        >>> from lancedb.expr import col
         >>> import pandas as pd
         >>> async def demo_update():
         ...     data = pd.DataFrame({"x": [1, 2], "vector": [[1, 2], [3, 4]]})
         ...     db = await lancedb.connect_async("./.lancedb")
         ...     table = await db.create_table("my_table", data)
         ...     # x is [1, 2], vector is [[1, 2], [3, 4]]
-        ...     await table.update({"vector": [10, 10]}, where=col("x") == 2)
+        ...     await table.update({"vector": [10, 10]}, where="x = 2")
         ...     # x is [1, 2], vector is [[1, 2], [10, 10]]
         ...     await table.update(updates_sql={"x": "x + 1"})
         ...     # x is [2, 3], vector is [[1, 2], [10, 10]]
@@ -6268,8 +6050,7 @@ class AsyncTable:
         if updates is not None:
             updates_sql = {k: value_to_sql(v) for k, v in updates.items()}
 
-        predicate = where.to_sql() if isinstance(where, Expr) else where
+        return await self._inner.update(updates_sql, where)
-        return await self._inner.update(updates_sql, predicate)
 
     async def add_columns(
         self,
@@ -6301,11 +6082,8 @@ class AsyncTable:
             Function columns are supported only on LanceDB Cloud and
             Enterprise.
         computed: Dict[str, str], optional
-            A mapping from output column names to SQL expressions derives each
+            A map of column name to a SQL expression defining the column. The
-            output field from its expression. A direct projection of a Blob v2
+            column's type and inputs are derived from the expression.
-            field inherits Blob v2 semantics; other expressions derive their
-            ordinary Arrow type. Mapping order is declaration and dependency
-            order.
 
             Unlike ``transforms``, the expression is stored rather than
             evaluated now: the column is committed with no values, and rows get
@@ -6576,9 +6354,6 @@ class AsyncTable:
         Offsets are mostly useful for sampling as the set of all valid offsets is easily
         known in advance to be [0, len(table)).
 
-        No guarantees are made regarding the order in which results are returned.
-        Repeated offsets produce repeated rows.
-
         Parameters
         ----------
         offsets: list[int]

python/python/tests/test_blob.py

@@ -2,41 +2,17 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 import io
-import subprocess
-import sys
-import textwrap
 
-import lance
 import pyarrow as pa
 import pyarrow.compute as pc
 import pytest
-from lance.blob import BlobType as LanceBlobType
 
 import lancedb
-from lancedb._blob import (
+from lancedb._blob import read_row_ids_from_hits, stash_auto_row_ids
-    blob_v2_projection_sources,
-    read_row_ids_from_hits,
-    stash_auto_row_ids,
-)
-from lancedb.expr import col
 from lancedb.index import FTS
 from lancedb.schema import blob_column_paths, blob_v2_column_paths
 
 
-_HIDE_LANCE_BLOB = """\
-import importlib.abc
-import sys
-
-class _MissingLanceBlob(importlib.abc.MetaPathFinder):
-    def find_spec(self, fullname, path, target=None):
-        if fullname == "lance.blob" or fullname.startswith("lance.blob."):
-            raise ModuleNotFoundError(fullname, name="lance.blob")
-
-sys.modules.pop("lance.blob", None)
-sys.meta_path.insert(0, _MissingLanceBlob())
-"""
-
-
 def _blob_table(name, rows):
     db = lancedb.connect("memory:///")
     schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
@@ -66,204 +42,10 @@ def _row_ids_by_id(table):
     return dict(zip(hits["id"].to_pylist(), hits["_rowid"].to_pylist()))
 
 
-def _assert_missing_blob_row_ids(exc_info):
-    message = str(exc_info.value)
-    assert "row ids" in message
-    assert "rowaddr" not in message
-    assert "fragment" not in message
-
-
-def _assert_fetch_apis_reject_missing_row_ids(table, row_ids):
-    with pytest.raises(ValueError) as exc_info:
-        table.fetch_blobs("image", row_ids)
-    _assert_missing_blob_row_ids(exc_info)
-    with pytest.raises(ValueError) as exc_info:
-        table.fetch_blob_files("image", row_ids)
-    _assert_missing_blob_row_ids(exc_info)
-    with pytest.raises(ValueError) as exc_info:
-        table.fetch_blob_ranges("image", [(row_id, 0, 1) for row_id in row_ids])
-    _assert_missing_blob_row_ids(exc_info)
-
-
 def test_blob_factory_declares_v2_field():
     field = lancedb.blob("image")
     assert isinstance(field.type, pa.ExtensionType)
     assert field.type.extension_name == "lance.blob.v2"
-    assert lancedb.BlobType is LanceBlobType
-    assert type(field.type) is LanceBlobType
-
-
-def test_blob_type_works_without_pylance():
-    script = _HIDE_LANCE_BLOB + textwrap.dedent(
-        """\
-        import lancedb
-        import pyarrow as pa
-
-        field = lancedb.blob("image")
-        if not isinstance(field.type, pa.ExtensionType):
-            raise SystemExit("expected an extension type")
-        if field.type.extension_name != "lance.blob.v2":
-            raise SystemExit(field.type.extension_name)
-        if lancedb.BlobType is not type(field.type):
-            raise SystemExit("BlobType is not the field type class")
-        if lancedb.BlobType.__module__ != "lancedb.schema":
-            raise SystemExit(lancedb.BlobType.__module__)
-
-        db = lancedb.connect("memory:///")
-        table = db.create_table(
-            "images",
-            schema=pa.schema([pa.field("id", pa.int64()), field]),
-        )
-        table.add([{"id": 1, "image": b"hello"}])
-        result = (
-            table.merge_insert("id")
-            .when_matched_update_all()
-            .when_not_matched_insert_all()
-            .execute([{"id": 1, "image": b"updated"}, {"id": 2, "image": b"inserted"}])
-        )
-        if result.num_updated_rows != 1 or result.num_inserted_rows != 1:
-            raise SystemExit(
-                f"merge_insert rows updated={result.num_updated_rows} "
-                f"inserted={result.num_inserted_rows}"
-            )
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
-
-
-def test_blob_resolves_pylance_type_without_eager_import():
-    script = textwrap.dedent(
-        """\
-        import sys
-        import lancedb
-
-        if "lance.blob" in sys.modules:
-            raise SystemExit("import lancedb imported lance.blob")
-        field = lancedb.blob("image")
-        from lance.blob import BlobType
-
-        if type(field.type) is not BlobType:
-            raise SystemExit(f"{type(field.type)} is not {BlobType}")
-        import lance
-
-        image = lance.blob_array([b"x"])
-        if type(image.type) is not BlobType:
-            raise SystemExit("blob_array used a different class")
-        if type(image.type) is not type(field.type):
-            raise SystemExit("field and array classes differ")
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
-
-
-def test_blob_fallback_fails_if_name_already_registered():
-    script = _HIDE_LANCE_BLOB + textwrap.dedent(
-        """\
-        import pyarrow as pa
-
-        class OtherBlobType(pa.ExtensionType):
-            def __init__(self):
-                super().__init__(
-                    pa.struct([pa.field("data", pa.large_binary())]),
-                    "lance.blob.v2",
-                )
-
-            def __arrow_ext_serialize__(self):
-                return b""
-
-            @classmethod
-            def __arrow_ext_deserialize__(cls, storage_type, serialized):
-                return cls()
-
-        pa.register_extension_type(OtherBlobType())
-        import lancedb
-
-        try:
-            lancedb.blob("image")
-        except ValueError as err:
-            if "already registered" not in str(err):
-                raise SystemExit(err)
-        else:
-            raise SystemExit("expected ValueError")
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
-
-
-def test_blob_type_rejects_competing_registration_with_pylance():
-    script = textwrap.dedent(
-        """\
-        import pyarrow as pa
-        import pyarrow.ipc
-
-        class OtherBlobType(pa.ExtensionType):
-            def __init__(self):
-                super().__init__(
-                    pa.struct(
-                        [
-                            pa.field("data", pa.large_binary()),
-                            pa.field("uri", pa.utf8()),
-                            pa.field("position", pa.uint64()),
-                            pa.field("size", pa.uint64()),
-                        ]
-                    ),
-                    "lance.blob.v2",
-                )
-
-            def __arrow_ext_serialize__(self):
-                return b""
-
-            @classmethod
-            def __arrow_ext_deserialize__(cls, storage_type, serialized):
-                return cls()
-
-        pa.register_extension_type(OtherBlobType())
-
-        from lance.blob import BlobType
-
-        if BlobType is OtherBlobType:
-            raise SystemExit("pylance BlobType was replaced")
-        schema = pa.schema([pa.field("value", BlobType())])
-        restored = pa.ipc.read_schema(schema.serialize())
-        if type(restored.field("value").type) is not OtherBlobType:
-            raise SystemExit(type(restored.field("value").type))
-
-        import lancedb
-
-        try:
-            lancedb.blob("image")
-        except ValueError as err:
-            if "__main__.OtherBlobType" not in str(err):
-                raise SystemExit(err)
-        else:
-            raise SystemExit("expected ValueError")
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
 
 
 def test_blob_v2_column_paths_include_list_children():
@@ -288,14 +70,6 @@ def test_blob_v2_column_paths_include_list_children():
     ]
 
 
-def test_blob_v2_projection_sources_use_typed_column_name():
-    schema = pa.schema([lancedb.blob("blob")])
-
-    assert blob_v2_projection_sources(schema, {"blob_alias": col("blob")}) == {
-        "blob_alias": "blob"
-    }
-
-
 def _legacy_v1_table(name):
     db = lancedb.connect("memory:///")
     schema = pa.schema(
@@ -392,20 +166,6 @@ async def test_async_table_to_pandas_descriptions_mode_omits_row_id():
     assert set(descriptor.keys()) == {"kind", "position", "size", "blob_id", "blob_uri"}
 
 
-@pytest.mark.asyncio
-async def test_async_typed_blob_projection_preserves_source_column():
-    db = await lancedb.connect_async("memory:///typed_blob_projection")
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("blob")])
-    table = await db.create_table("typed_blob_projection", schema=schema)
-    await table.add([{"id": 1, "blob": b"alpha"}])
-
-    hits = await table.query().select({"blob_alias": col("blob")}).to_arrow()
-
-    assert "_lance_row_id" in hits.schema.field("blob_alias").type.names
-    blobs = await table.fetch_blobs("blob", hits)
-    assert blobs.to_pylist() == [b"alpha"]
-
-
 def test_fetch_blobs_round_trip():
     table = _blob_table(
         "round_trip",
@@ -416,292 +176,6 @@ def test_fetch_blobs_round_trip():
     assert [blobs[0].as_py(), blobs[1].as_py()] == [b"alpha", b"beta"]
 
 
-def test_merge_insert_writes_python_bytes():
-    table = _blob_table("merge_bytes", [{"id": 1, "image": b"before"}])
-    result = (
-        table.merge_insert("id")
-        .when_matched_update_all()
-        .when_not_matched_insert_all()
-        .execute([{"id": 1, "image": b"updated"}, {"id": 2, "image": b"inserted"}])
-    )
-    assert result.num_updated_rows == 1
-    assert result.num_inserted_rows == 1
-    by_id = _row_ids_by_id(table)
-    blobs = table.fetch_blobs("image", [by_id[1], by_id[2]])
-    assert blobs.to_pylist() == [b"updated", b"inserted"]
-
-
-def test_merge_insert_bytes_after_reopen_without_touching_blob_type(tmp_path):
-    db = lancedb.connect(tmp_path)
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    table = db.create_table("images", schema=schema)
-    table.add([{"id": 1, "image": b"hello"}])
-
-    script = textwrap.dedent(
-        f"""\
-        import lancedb
-
-        db = lancedb.connect({str(tmp_path)!r})
-        table = db.open_table("images")
-        image_type = table.schema.field("image").type
-        if type(image_type).__name__ != "StructType":
-            raise SystemExit(f"expected StructType, got {{type(image_type)}}")
-        result = (
-            table.merge_insert("id")
-            .when_matched_update_all()
-            .when_not_matched_insert_all()
-            .execute(
-                [{{"id": 1, "image": b"updated"}}, {{"id": 2, "image": b"inserted"}}]
-            )
-        )
-        if result.num_updated_rows != 1 or result.num_inserted_rows != 1:
-            raise SystemExit(
-                f"rows updated={{result.num_updated_rows}} "
-                f"inserted={{result.num_inserted_rows}}"
-            )
-        hits = table.search().with_row_id(True).limit(10).to_arrow()
-        by_id = dict(zip(hits["id"].to_pylist(), hits["_rowid"].to_pylist()))
-        blobs = table.fetch_blobs("image", [by_id[1], by_id[2]])
-        if blobs.to_pylist() != [b"updated", b"inserted"]:
-            raise SystemExit(blobs.to_pylist())
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
-
-
-def test_merge_insert_bytes_after_reopen_without_pylance(tmp_path):
-    db = lancedb.connect(tmp_path)
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    table = db.create_table("images", schema=schema)
-    table.add([{"id": 1, "image": b"hello"}])
-
-    script = _HIDE_LANCE_BLOB + textwrap.dedent(
-        f"""\
-        import lancedb
-
-        db = lancedb.connect({str(tmp_path)!r})
-        table = db.open_table("images")
-        image_type = table.schema.field("image").type
-        if type(image_type).__name__ != "StructType":
-            raise SystemExit(f"expected StructType, got {{type(image_type)}}")
-        result = (
-            table.merge_insert("id")
-            .when_matched_update_all()
-            .when_not_matched_insert_all()
-            .execute(
-                [{{"id": 1, "image": b"updated"}}, {{"id": 2, "image": b"inserted"}}]
-            )
-        )
-        if result.num_updated_rows != 1 or result.num_inserted_rows != 1:
-            raise SystemExit(
-                f"rows updated={{result.num_updated_rows}} "
-                f"inserted={{result.num_inserted_rows}}"
-            )
-        hits = table.search().with_row_id(True).limit(10).to_arrow()
-        by_id = dict(zip(hits["id"].to_pylist(), hits["_rowid"].to_pylist()))
-        blobs = table.fetch_blobs("image", [by_id[1], by_id[2]])
-        if blobs.to_pylist() != [b"updated", b"inserted"]:
-            raise SystemExit(blobs.to_pylist())
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
-
-
-def test_merge_insert_blob_array_into_reopened_unregistered_table(tmp_path):
-    db = lancedb.connect(tmp_path)
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    table = db.create_table("images", schema=schema)
-    table.add([{"id": 1, "image": b"before"}])
-
-    script = textwrap.dedent(
-        f"""\
-        import pyarrow as pa
-        import lancedb
-
-        db = lancedb.connect({str(tmp_path)!r})
-        table = db.open_table("images")
-        image_type = table.schema.field("image").type
-        if type(image_type).__name__ != "StructType":
-            raise SystemExit(
-                f"expected StructType before lance import, got {{type(image_type)}}"
-            )
-
-        import lance
-
-        updates = pa.Table.from_arrays(
-            [
-                pa.array([1, 2], type=pa.int64()),
-                lance.blob_array([b"updated", b"inserted"]),
-            ],
-            names=["id", "image"],
-        )
-        result = (
-            table.merge_insert("id")
-            .when_matched_update_all()
-            .when_not_matched_insert_all()
-            .execute(updates)
-        )
-        if result.num_updated_rows != 1 or result.num_inserted_rows != 1:
-            raise SystemExit(
-                f"rows updated={{result.num_updated_rows}} "
-                f"inserted={{result.num_inserted_rows}}"
-            )
-        hits = table.search().with_row_id(True).limit(10).to_arrow()
-        by_id = dict(zip(hits["id"].to_pylist(), hits["_rowid"].to_pylist()))
-        blobs = table.fetch_blobs("image", [by_id[1], by_id[2]])
-        if blobs.to_pylist() != [b"updated", b"inserted"]:
-            raise SystemExit(blobs.to_pylist())
-        """
-    )
-    result = subprocess.run(
-        [sys.executable, "-c", script],
-        capture_output=True,
-        text=True,
-        check=False,
-    )
-    assert result.returncode == 0, result.stderr
-
-
-def test_add_all_null_blob_column():
-    db = lancedb.connect("memory:///")
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    table = db.create_table("all_null", schema=schema)
-    table.add([{"id": 1, "image": None}, {"id": 2, "image": None}])
-    by_id = _row_ids_by_id(table)
-    blobs = table.fetch_blobs("image", [by_id[1], by_id[2]])
-    assert blobs.to_pylist() == [None, None]
-
-
-def test_create_table_nested_blob_schema_without_rows():
-    db = lancedb.connect("memory:///")
-    schema = pa.schema(
-        [
-            pa.field("id", pa.int64()),
-            pa.field("info", pa.struct([lancedb.blob("blob")])),
-            pa.field("images", pa.list_(lancedb.blob("image"))),
-        ]
-    )
-    table = db.create_table("nested_empty", schema=schema)
-    assert table.count_rows() == 0
-
-
-def test_merge_insert_nested_blob_dicts():
-    db = lancedb.connect("memory:///")
-    info = pa.StructArray.from_arrays(
-        [
-            pa.array(["first"], type=pa.string()),
-            _blob_array("blob", [b"before"]),
-        ],
-        names=["name", "blob"],
-    )
-    data = pa.Table.from_arrays(
-        [pa.array([1], type=pa.int64()), info],
-        names=["id", "info"],
-    )
-    table = db.create_table("nested_merge", data=data)
-    result = (
-        table.merge_insert("id")
-        .when_matched_update_all()
-        .execute([{"id": 1, "info": {"name": "first", "blob": b"after"}}])
-    )
-    assert result.num_updated_rows == 1
-    by_id = _row_ids_by_id(table)
-    blobs = table.fetch_blobs("info.blob", [by_id[1]])
-    assert blobs.to_pylist() == [b"after"]
-
-
-def _list_blob_table(name):
-    db = lancedb.connect("memory:///")
-    blob_field = lancedb.blob("image")
-    images = pa.ListArray.from_arrays(
-        pa.array([0, 1], type=pa.int32()), _blob_array("image", [b"before"])
-    )
-    data = pa.Table.from_arrays(
-        [pa.array([1], type=pa.int64()), images],
-        schema=pa.schema(
-            [pa.field("id", pa.int64()), pa.field("images", pa.list_(blob_field))]
-        ),
-    )
-    return db.create_table(name, data=data)
-
-
-def test_merge_insert_list_blob_dicts():
-    table = _list_blob_table("list_merge")
-    result = (
-        table.merge_insert("id")
-        .when_matched_update_all()
-        .when_not_matched_insert_all()
-        .execute([{"id": 1, "images": [b"one", b"two"]}, {"id": 2, "images": None}])
-    )
-    assert result.num_updated_rows == 1
-    assert result.num_inserted_rows == 1
-    hits = table.search().limit(10).to_arrow()
-    sizes = {
-        row["id"]: None if row["images"] is None else [d["size"] for d in row["images"]]
-        for row in hits.to_pylist()
-    }
-    assert sizes == {1: [3, 3], 2: None}
-
-
-def test_list_blob_column_queries_as_raw_descriptors():
-    table = _list_blob_table("list_query")
-    hits = table.search().limit(10).to_arrow()
-    element = hits.schema.field("images").type.value_type
-    assert pa.types.is_struct(element)
-    assert "_lance_row_id" not in element.names
-    with pytest.raises(ValueError, match="expected struct before segment"):
-        table.fetch_blobs("images.image", [0])
-
-
-def test_row_addressable_paths_exclude_list_children():
-    from lancedb.schema import row_addressable_blob_v2_paths
-
-    schema = pa.schema(
-        [
-            pa.field("id", pa.int64()),
-            pa.field("info", pa.struct([lancedb.blob("blob")])),
-            pa.field("images", pa.list_(lancedb.blob("image"))),
-        ]
-    )
-    assert blob_v2_column_paths(schema) == ["info.blob", "images.image"]
-    assert row_addressable_blob_v2_paths(schema) == ["info.blob"]
-
-
-def test_merge_insert_writes_pylance_blob_array():
-    table = _blob_table("merge_pylance", [{"id": 1, "image": b"before"}])
-    image = lance.blob_array([b"updated", b"inserted"])
-    assert type(image.type) is LanceBlobType
-    assert type(image.type) is type(lancedb.BlobType())
-    updates = pa.Table.from_arrays(
-        [pa.array([1, 2], type=pa.int64()), image], names=["id", "image"]
-    )
-
-    result = (
-        table.merge_insert("id")
-        .when_matched_update_all()
-        .when_not_matched_insert_all()
-        .execute(updates)
-    )
-
-    assert result.num_updated_rows == 1
-    assert result.num_inserted_rows == 1
-    by_id = _row_ids_by_id(table)
-    blobs = table.fetch_blobs("image", [by_id[1], by_id[2]])
-    assert blobs.to_pylist() == [b"updated", b"inserted"]
-
-
 def test_fetch_blobs_accepts_query_result():
     table = _blob_table("from_result", [{"id": 1, "image": b"gamma"}])
     hits = table.search().limit(10).to_arrow()
@@ -710,25 +184,6 @@ def test_fetch_blobs_accepts_query_result():
     assert {blobs[i].as_py() for i in range(len(blobs))} == {b"gamma"}
 
 
-def test_fetch_blobs_after_compact_with_stable_row_ids(tmp_path):
-    db = lancedb.connect(
-        tmp_path, storage_options={"new_table_enable_stable_row_ids": "true"}
-    )
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    table = db.create_table("t", schema=schema)
-    table.add([{"id": 1, "image": b"frag-one"}])
-    table.add([{"id": 2, "image": b"frag-two"}])
-    by_id = _row_ids_by_id(table)
-    ids = [by_id[1], by_id[2]]
-
-    table.optimize()
-
-    blobs = table.fetch_blobs("image", ids)
-    assert blobs.to_pylist() == [b"frag-one", b"frag-two"]
-    ranges = table.fetch_blob_ranges("image", [(ids[0], 5, 3), (ids[1], 5, 3)])
-    assert ranges.to_pylist() == [b"one", b"two"]
-
-
 def test_fetch_blobs_preserves_null_and_empty_values():
     table = _blob_table(
         "nulls",
@@ -777,25 +232,8 @@ def test_fetch_blob_ranges_validates_requests():
     with pytest.raises(ValueError, match="offset \\+ length overflowed"):
         table.fetch_blob_ranges("image", [(row_id, 2**64 - 1, 1)])
 
-    with pytest.raises(ValueError) as exc_info:
+    with pytest.raises(ValueError, match="row IDs"):
         table.fetch_blob_ranges("image", [(2**64 - 1, 0, 1)])
-    _assert_missing_blob_row_ids(exc_info)
-
-
-def test_fetch_blob_apis_reject_missing_fragment_row_addr():
-    table = _blob_table("missing_frag", [{"id": 1, "image": b"x"}])
-    live = _row_ids_by_id(table)[1]
-    _assert_fetch_apis_reject_missing_row_ids(table, [1 << 32, live])
-
-
-def test_fetch_blob_apis_reject_deleted_row_ids():
-    table = _blob_table(
-        "deleted_rows",
-        [{"id": 1, "image": b"one"}, {"id": 2, "image": b"two"}],
-    )
-    by_id = _row_ids_by_id(table)
-    table.delete("id = 2")
-    _assert_fetch_apis_reject_missing_row_ids(table, [by_id[2], by_id[1]])
 
 
 def test_fetch_blob_ranges_empty_requests_returns_empty_array():
@@ -965,50 +403,6 @@ async def test_blob_v2_hybrid_fetch_blobs_async():
     assert {blobs[i].as_py() for i in range(len(blobs))} == {b"alpha", b"beta"}
 
 
-@pytest.mark.asyncio
-async def test_async_hybrid_typed_blob_projection_preserves_source_column():
-    db = await lancedb.connect_async("memory:///hybrid_typed_blob")
-    schema = pa.schema(
-        [
-            pa.field("id", pa.int64()),
-            pa.field("text", pa.utf8()),
-            pa.field("vector", pa.list_(pa.float32(), list_size=2)),
-            lancedb.blob("blob"),
-        ]
-    )
-    table = await db.create_table("hybrid_typed_blob", schema=schema)
-    await table.add(
-        [
-            {
-                "id": 1,
-                "text": "hello alpha",
-                "vector": [1.0, 0.0],
-                "blob": b"alpha",
-            },
-            {
-                "id": 2,
-                "text": "hello beta",
-                "vector": [0.9, 0.1],
-                "blob": b"beta",
-            },
-        ]
-    )
-    await table.create_index("text", config=FTS(with_position=False))
-
-    hits = await (
-        table.query()
-        .nearest_to([1.0, 0.0])
-        .nearest_to_text("hello")
-        .select({"blob_alias": col("blob")})
-        .limit(2)
-        .to_arrow()
-    )
-
-    assert "_lance_row_id" in hits.schema.field("blob_alias").type.names
-    blobs = await table.fetch_blobs("blob", hits)
-    assert {blobs[i].as_py() for i in range(len(blobs))} == {b"alpha", b"beta"}
-
-
 def test_blob_file_seek_read_and_read_range():
     payload = _identifiable_payload(1024)
     table = _blob_table("seek_read", [{"id": 1, "image": payload}])

python/python/tests/test_expr.py

@@ -52,7 +52,7 @@ class TestExprConstruction:
     def test_func(self):
         e = func("lower", col("name"))
         assert isinstance(e, Expr)
-        assert e.to_sql() == "lower(`name`)"
+        assert e.to_sql() == "lower(name)"
 
     def test_func_unknown_raises(self):
         with pytest.raises(Exception):
@@ -115,7 +115,7 @@ class TestExprOperators:
     def test_and_operator(self):
         e = (col("age") > lit(18)) & (col("status") == lit("active"))
         assert isinstance(e, Expr)
-        assert e.to_sql() == "((age > 18) AND (`status` = 'active'))"
+        assert e.to_sql() == "((age > 18) AND (status = 'active'))"
 
     def test_or_operator(self):
         e = (col("a") == lit(1)) | (col("b") == lit(2))
@@ -166,7 +166,7 @@ class TestExprOperators:
     def test_coerce_plain_str(self):
         e = col("name") == "alice"
         assert isinstance(e, Expr)
-        assert e.to_sql() == "(`name` = 'alice')"
+        assert e.to_sql() == "(name = 'alice')"
 
     def test_reflexive_comparisons(self):
         # 10 < col("age") swaps to col("age") > 10
@@ -198,85 +198,85 @@ class TestExprBytesLiteral:
 
     def test_bytes_equality_expr_sql(self):
         e = col("data") == lit(b"\xca\xfe")
-        assert e.to_sql() == "(`data` = X'CAFE')"
+        assert e.to_sql() == "(data = X'CAFE')"
 
     def test_bytes_ne_expr_sql(self):
         e = col("data") != lit(b"\xff")
-        assert e.to_sql() == "(`data` <> X'FF')"
+        assert e.to_sql() == "(data <> X'FF')"
 
     def test_bytes_compound_expr_sql(self):
         e = (col("data") == lit(b"\x01")) & (col("id") > lit(5))
-        assert e.to_sql() == "((`data` = X'01') AND (id > 5))"
+        assert e.to_sql() == "((data = X'01') AND (id > 5))"
 
     def test_bytes_in_function_call(self):
         # Regression test: binary literals inside scalar function calls
         # used to fail because DataFusion's unparser does not support Binary
         # scalars.  Now handled via a placeholder-substitution rewrite.
         e = func("contains", col("data"), lit(b"\xff"))
-        assert e.to_sql() == "contains(`data`, X'FF')"
+        assert e.to_sql() == "contains(data, X'FF')"
 
     def test_bytes_in_not(self):
         e = ~(col("data") == lit(b"\xff"))
-        assert e.to_sql() == "NOT (`data` = X'FF')"
+        assert e.to_sql() == "NOT (data = X'FF')"
 
 
 class TestExprStringMethods:
     def test_lower(self):
         e = col("name").lower()
         assert isinstance(e, Expr)
-        assert e.to_sql() == "lower(`name`)"
+        assert e.to_sql() == "lower(name)"
 
     def test_upper(self):
         e = col("name").upper()
         assert isinstance(e, Expr)
-        assert e.to_sql() == "upper(`name`)"
+        assert e.to_sql() == "upper(name)"
 
     def test_contains(self):
         e = col("text").contains(lit("hello"))
         assert isinstance(e, Expr)
-        assert e.to_sql() == "contains(`text`, 'hello')"
+        assert e.to_sql() == "contains(text, 'hello')"
 
     def test_contains_with_str_coerce(self):
         e = col("text").contains("hello")
         assert isinstance(e, Expr)
-        assert e.to_sql() == "contains(`text`, 'hello')"
+        assert e.to_sql() == "contains(text, 'hello')"
 
     def test_chained_lower_eq(self):
         e = col("name").lower() == lit("alice")
         assert isinstance(e, Expr)
-        assert e.to_sql() == "(lower(`name`) = 'alice')"
+        assert e.to_sql() == "(lower(name) = 'alice')"
 
 
 class TestExprCast:
     def test_cast_string(self):
         e = col("id").cast("string")
         assert isinstance(e, Expr)
-        assert e.to_sql() == "arrow_cast(id, 'Utf8')"
+        assert e.to_sql() == "CAST(id AS VARCHAR)"
 
     def test_cast_int32(self):
         e = col("score").cast("int32")
         assert isinstance(e, Expr)
-        assert e.to_sql() == "arrow_cast(score, 'Int32')"
+        assert e.to_sql() == "CAST(score AS INTEGER)"
 
     def test_cast_float64(self):
         e = col("val").cast("float64")
         assert isinstance(e, Expr)
-        assert e.to_sql() == "arrow_cast(val, 'Float64')"
+        assert e.to_sql() == "CAST(val AS DOUBLE)"
 
     def test_cast_pyarrow_type(self):
         e = col("score").cast(pa.int32())
         assert isinstance(e, Expr)
-        assert e.to_sql() == "arrow_cast(score, 'Int32')"
+        assert e.to_sql() == "CAST(score AS INTEGER)"
 
     def test_cast_pyarrow_float64(self):
         e = col("val").cast(pa.float64())
         assert isinstance(e, Expr)
-        assert e.to_sql() == "arrow_cast(val, 'Float64')"
+        assert e.to_sql() == "CAST(val AS DOUBLE)"
 
     def test_cast_pyarrow_string(self):
         e = col("id").cast(pa.string())
         assert isinstance(e, Expr)
-        assert e.to_sql() == "arrow_cast(id, 'Utf8')"
+        assert e.to_sql() == "CAST(id AS VARCHAR)"
 
     def test_cast_pyarrow_and_string_equivalent(self):
         # pa.int32() and "int32" should produce equivalent SQL
@@ -597,14 +597,14 @@ class TestExprIsin:
     def test_isin_strs(self):
         assert (
             col("status").isin(["active", "pending"]).to_sql()
-            == "`status` IN ('active', 'pending')"
+            == "status IN ('active', 'pending')"
         )
 
     def test_isin_coerces_and_mixes(self):
         assert col("id").isin([lit(1), 2]).to_sql() == "id IN (1, 2)"
 
     def test_isin_empty(self):
-        assert col("id").isin([]).to_sql() == "false"
+        assert col("id").isin([]).to_sql() == "id IN ()"
 
     def test_isin_filter(self, simple_table):
         result = simple_table.search().where(col("id").isin([1, 3, 5])).to_arrow()

python/python/tests/test_first_class_function_slice1.py

@@ -37,22 +37,6 @@ def job_result(name: str) -> dict:
     return json.loads(fixture(name))["result"]
 
 
-def assert_no_secret_values(value):
-    """No client value models a resolved credential, at any nesting depth."""
-    if isinstance(value, dict):
-        for key, child in value.items():
-            assert key not in {
-                "secret_value",
-                "secret_values",
-                "resolved_secret",
-                "resolved_secrets",
-            }
-            assert_no_secret_values(child)
-    elif isinstance(value, list):
-        for child in value:
-            assert_no_secret_values(child)
-
-
 def test_public_function_values_are_in_api_reference():
     docs = Path(__file__).parents[3] / "docs" / "src" / "python" / "python.md"
     rendered = docs.read_text()
@@ -110,7 +94,6 @@ def test_function_version_identity_is_immutable_and_exact():
     version = FunctionVersion.from_json(json.dumps(value))
     assert version.name == "embed"
     assert version.version == "fv_01K3EXACT"
-    assert dict(version.secret_env_bindings) == {"HF_TOKEN": "hf-prod"}
 
     with pytest.raises((TypeError, ValueError)):
         version.version = "fv_changed"
@@ -293,25 +276,6 @@ def test_refresh_result_rejects_non_u64_values(field):
         RefreshColumnResult.from_json(json.dumps(value))
 
 
-def test_canonical_client_values_carry_bindings_and_no_credentials():
-    """A binding names a Secret; the credential behind it has no client field."""
-    version = FunctionVersion.from_json(
-        json.dumps(job_result("remote_function_job.json"))
-    )
-    canonical = json.loads(version.to_canonical_json())
-    assert canonical["secret_env_bindings"] == {"HF_TOKEN": "hf-prod"}
-    assert_no_secret_values(canonical)
-
-
-def test_a_version_without_bindings_keeps_the_original_wire_shape():
-    """Every Function registered before Secrets existed serializes unchanged."""
-    value = job_result("remote_function_job.json")
-    del value["secret_env_bindings"]
-    version = FunctionVersion.from_json(json.dumps(value))
-    assert dict(version.secret_env_bindings) == {}
-    assert "secret_env_bindings" not in json.loads(version.to_canonical_json())
-
-
 class _FunctionDeclarationInner:
     def __init__(self):
         self.calls = []

python/python/tests/test_header_provider.py

@@ -54,10 +54,7 @@ class TestOAuthProvider:
         provider = OAuthProvider(fetcher)
         headers = provider.get_headers()
 
-        assert headers == {
+        assert headers == {"Authorization": "Bearer token123"}
-            "Authorization": "Bearer token123",
-            "x-lancedb-credential-type": "oidc",
-        }
         assert provider._current_token == "token123"
         assert provider._token_expires_at is not None
 
@@ -76,20 +73,14 @@ class TestOAuthProvider:
 
         # First call
         headers1 = provider.get_headers()
-        assert headers1 == {
+        assert headers1 == {"Authorization": "Bearer token1"}
-            "Authorization": "Bearer token1",
-            "x-lancedb-credential-type": "oidc",
-        }
 
         # Wait for token to expire
         time.sleep(1.1)
 
         # Second call should refresh
         headers2 = provider.get_headers()
-        assert headers2 == {
+        assert headers2 == {"Authorization": "Bearer token2"}
-            "Authorization": "Bearer token2",
-            "x-lancedb-credential-type": "oidc",
-        }
         assert call_count == 2
 
     def test_no_expiry_info(self):
@@ -101,18 +92,12 @@ class TestOAuthProvider:
         provider = OAuthProvider(fetcher)
         headers = provider.get_headers()
 
-        assert headers == {
+        assert headers == {"Authorization": "Bearer permanent_token"}
-            "Authorization": "Bearer permanent_token",
-            "x-lancedb-credential-type": "oidc",
-        }
         assert provider._token_expires_at is None
 
         # Should not refresh on second call
         headers2 = provider.get_headers()
-        assert headers2 == {
+        assert headers2 == {"Authorization": "Bearer permanent_token"}
-            "Authorization": "Bearer permanent_token",
-            "x-lancedb-credential-type": "oidc",
-        }
 
     def test_missing_access_token(self):
         """Test error handling when access_token is missing."""
@@ -136,10 +121,7 @@ class TestOAuthProvider:
         provider = OAuthProvider(fetcher)
         headers = provider.get_headers()
 
-        assert headers == {
+        assert headers == {"Authorization": "Bearer sync_token"}
-            "Authorization": "Bearer sync_token",
-            "x-lancedb-credential-type": "oidc",
-        }
 
 
 class TestClientConfigIntegration:

python/python/tests/test_materialized_views.py

@@ -266,38 +266,3 @@ async def test_async_namespace_connection_materialized_views(tmp_path):
             handle._route_pushdown_to_rust == through_namespace._route_pushdown_to_rust
         )
         assert handle._namespace_path == through_namespace._namespace_path
-
-
-def test_namespaced_select_kind_is_read_and_unknown_kinds_are_refused():
-    import json
-
-    import pyarrow as pa
-
-    from lancedb.materialized_view import _definition_from_schema
-
-    def schema_with(definition: dict) -> pa.Schema:
-        return pa.schema([pa.field("id", pa.int32())]).with_metadata(
-            {b"mv.definition": json.dumps(definition).encode()}
-        )
-
-    # "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.
-    definition = _definition_from_schema(
-        schema_with(
-            {
-                "kind": "namespaced_select",
-                "source_table": "people",
-                "source_namespace": ["ns"],
-                "projections": [{"output": "name", "expression": "name"}],
-            }
-        ),
-        "v",
-    )
-    assert definition.source_table == "people"
-    assert definition.source_namespace == ["ns"]
-
-    with pytest.raises(NotImplementedError, match="cannot refresh"):
-        _definition_from_schema(
-            schema_with({"kind": "select_v3", "source_table": "people"}), "v"
-        )

python/python/tests/test_query.py

@@ -675,21 +675,6 @@ def test_distance_range(table: lancedb.table.Table):
     assert res["_distance"].to_pylist() == [min_dist, max_dist]
 
 
-@pytest.mark.parametrize("expression", ["1 - _distance", "1.0 - _distance"])
-def test_select_arithmetic_with_distance(table, expression):
-    result = (
-        table.search([10, 10])
-        .select({"similarity": expression, "_distance": "_distance"})
-        .distance_type("cosine")
-        .to_arrow()
-    )
-
-    assert result.schema.field("similarity").type == pa.float32()
-    assert result["similarity"].to_pylist() == pytest.approx(
-        [1 - distance for distance in result["_distance"].to_pylist()]
-    )
-
-
 @pytest.mark.asyncio
 async def test_distance_range_async(table_async: AsyncTable):
     q = [0, 0]
@@ -1923,21 +1908,6 @@ def test_take_queries(tmp_path):
         17,
     ]
 
-    # Duplicate offsets are occurrences, not set members. Ordering is unspecified.
-    assert sorted(table.take_offsets([5, 2, 5, 17]).to_pandas()["idx"].to_list()) == [
-        2,
-        5,
-        5,
-        17,
-    ]
-
-    # Converting a take builder to its serializable query representation must
-    # retain occurrence metadata and execute with the same multiplicity.
-    query = table.take_offsets([5, 2, 5, 17]).select(["idx"]).to_query_object()
-    assert query.take_offsets == [5, 2, 5, 17]
-    converted = table._execute_query(query).read_all()
-    assert sorted(converted["idx"].to_pylist()) == [2, 5, 5, 17]
-
     # Take by row id
     assert list(
         sorted(table.take_row_ids([5, 2, 17]).to_pandas()["idx"].to_list())

python/python/tests/test_remote_db.py

@@ -479,49 +479,24 @@ def test_remote_permutation_is_picklable():
                 match = re.search(
                     r"_rowoffset\s+in\s+\((.*?)\)", body["filter"], re.IGNORECASE
                 )
-                offsets = list(
+                offsets = [int(o.strip()) for o in match.group(1).split(",")]
-                    dict.fromkeys(int(o.strip()) for o in match.group(1).split(","))
-                )
             else:
                 offsets = list(range(len(rows)))
-            columns = body.get("columns") or ["a"]
+            table = pa.table({"a": [rows[offset] for offset in offsets]})
-            table = pa.table(
-                {
-                    column: (
-                        [rows[offset] for offset in offsets]
-                        if column == "a"
-                        else offsets
-                    )
-                    for column in columns
-                }
-            )
 
             request.send_response(200)
             request.send_header("Content-Type", "application/vnd.apache.arrow.file")
             request.end_headers()
             with pa.ipc.new_file(request.wfile, schema=table.schema) as writer:
-                writer.write_table(table, max_chunksize=2)
+                writer.write_table(table)
         else:
             request.send_response(404)
             request.end_headers()
 
     with mock_lancedb_connection(handler) as db:
-        table = db.open_table("test")
+        permutation = Permutation.identity(db.open_table("test"))
-        assert table.take_offsets([0, 2, 0, 4]).to_list() == [
-            {"a": 0},
-            {"a": 0},
-            {"a": 2},
-            {"a": 4},
-        ]
-
-        permutation = Permutation.identity(table)
         restored = pickle.loads(pickle.dumps(permutation))
-        assert restored.__getitems__([0, 2, 0, 4]) == [
+        assert restored.__getitems__([0, 2, 4]) == [{"a": 0}, {"a": 2}, {"a": 4}]
-            {"a": 0},
-            {"a": 2},
-            {"a": 0},
-            {"a": 4},
-        ]
 
 
 def test_create_table_exist_ok():
@@ -820,13 +795,11 @@ def test_table_create_indices():
         scalar_req = received_requests[0]
         assert "name" in scalar_req
         assert scalar_req["name"] == "custom_scalar_idx"
-        assert scalar_req["replace"] is False
 
         # Check FTS index request has custom name
         fts_req = received_requests[1]
         assert "name" in fts_req
         assert fts_req["name"] == "custom_fts_idx"
-        assert fts_req["replace"] is False
         assert fts_req["block_size"] == 256
         assert fts_req["custom_stop_words"] == ["cloud"]
 
@@ -834,7 +807,6 @@ def test_table_create_indices():
         vector_req = received_requests[2]
         assert "name" in vector_req
         assert vector_req["name"] == "custom_vector_idx"
-        assert "replace" not in vector_req
 
         table.wait_for_index(["custom_scalar_idx"], timedelta(seconds=2))
         table.wait_for_index(
@@ -1107,9 +1079,6 @@ def test_remote_create_index_new_api():
             table.create_index("text", config=FTS(block_size=256))
             # IvfRq via new API
             table.create_index("vector", config=IvfRq(distance_type="l2"))
-            table.create_index(
-                "vector", config=IvfPq(distance_type="l2"), replace=False
-            )
 
         # Legacy index_type="IVF_RQ" routes to IvfRq config under the hood.
         with pytest.warns(DeprecationWarning, match="create_index"):
@@ -1119,17 +1088,15 @@ def test_remote_create_index_new_api():
                 num_partitions=8,
             )
 
-        assert len(received_requests) == 6
+        assert len(received_requests) == 5
         assert [req["column"] for req in received_requests] == [
             "vector",
             "category",
             "text",
             "vector",
             "vector",
-            "vector",
         ]
         assert received_requests[2]["block_size"] == 256
-        assert received_requests[4]["replace"] is False
 
 
 def test_table_wait_for_index_timeout():
@@ -2467,7 +2434,7 @@ def test_remote_blob_byte_apis_not_supported_on_old_server():
 
 
 def test_remote_connection_jobs_surface():
-    from lancedb.exceptions import JobFailedError, JobNotFoundError
+    from lancedb.exceptions import JobFailedError
 
     schema = pa.schema([("state", pa.string())])
     batch = pa.record_batch([pa.array(["created", "done"])], schema=schema)
@@ -2475,7 +2442,6 @@ def test_remote_connection_jobs_surface():
     with pa.ipc.new_stream(sink, schema) as writer:
         writer.write_batch(batch)
     events_body = sink.getvalue().to_pybytes()
-    query_events_payloads = []
 
     def handler(request):
         content_len = int(request.headers.get("Content-Length", 0))
@@ -2513,22 +2479,6 @@ def test_remote_connection_jobs_surface():
             request.end_headers()
             request.wfile.write(json.dumps(rsp).encode())
         elif request.path == "/v1/jobs/describe":
-            if payload["job_id"] == "job-2":
-                request.send_response(200)
-                request.send_header("Content-Type", "application/json")
-                request.end_headers()
-                request.wfile.write(
-                    json.dumps(
-                        dict(
-                            job_id="job-2",
-                            job_type="refresh_column",
-                            job_state="DONE",
-                            creation_ms=2000,
-                            result=dict(rows_assigned=1000000, rows_failed=0),
-                        )
-                    ).encode()
-                )
-                return
             if payload["job_id"] != "job-1":
                 request.send_response(404)
                 request.end_headers()
@@ -2560,7 +2510,7 @@ def test_remote_connection_jobs_surface():
             request.end_headers()
             request.wfile.write(b'{"job_id": "job-1"}')
         elif request.path == "/v1/jobs/query_events":
-            query_events_payloads.append(payload)
+            assert payload["job_id"] == "job-1"
             request.send_response(200)
             request.send_header("Content-Type", "application/vnd.apache.arrow.stream")
             request.end_headers()
@@ -2576,109 +2526,24 @@ def test_remote_connection_jobs_surface():
         assert jobs[0].table == "t1"
         assert jobs[1].state == "finished"
 
+        description = db.get_job("job-1")
+        assert description.job_type == "create_index"
+        assert description.state == "failed"
+        assert json.loads(description.spec_json) == {"column": "vec"}
+        assert description.failure.message == "worker died"
+        assert description.failure.retryable is True
+        assert db.get_job("missing") is None
+
         assert db.cancel_job("job-1") is True
         assert db.cancel_job("missing") is False
 
-        # Opening a job hands back a populated handle; a missing one fails.
+        batches = db.job_history("job-1")
-        with pytest.raises(JobNotFoundError, match="missing"):
+        assert len(batches) == 1
-            db.open_job("missing")
+        assert batches[0].num_rows == 2
-        finished = db.open_job("job-2")
+        assert batches[0].column("state").to_pylist() == ["created", "done"]
-        assert finished.state == "finished"
-        assert finished.result == {"rows_assigned": 1000000, "rows_failed": 0}
 
-        job = db.open_job("job-1")
+        job = db.job("job-1")
         assert job.id == "job-1"
-        # Opening already populated the handle.
-        assert job.state == "failed"
-        assert job.spec == {"column": "vec"}
-        assert job.failure.message == "worker died"
         assert job.status() == "failed"
         with pytest.raises(JobFailedError, match="worker died"):
             job.wait(timeout=timedelta(seconds=5))
-
-
-def test_remote_job_handle_reports_its_own_detail():
-    schema = pa.schema([("state", pa.string())])
-    batch = pa.record_batch([pa.array(["claim_complete"])], schema=schema)
-    sink = pa.BufferOutputStream()
-    with pa.ipc.new_stream(sink, schema) as writer:
-        writer.write_batch(batch)
-    events_body = sink.getvalue().to_pybytes()
-    event_payloads = []
-
-    def handler(request):
-        content_len = int(request.headers.get("Content-Length", 0))
-        body = request.rfile.read(content_len) if content_len > 0 else b""
-        payload = json.loads(body) if body else {}
-        if request.path == "/v1/jobs/describe":
-            request.send_response(200)
-            request.send_header("Content-Type", "application/json")
-            request.end_headers()
-            request.wfile.write(
-                json.dumps(
-                    dict(
-                        job_id="job-1",
-                        job_type="refresh_column",
-                        job_state="DONE",
-                        creation_ms=2000,
-                        spec=dict(column="vec"),
-                        result=dict(rows_assigned=1000000),
-                    )
-                ).encode()
-            )
-        elif request.path == "/v1/jobs/query_events":
-            event_payloads.append(payload)
-            request.send_response(200)
-            request.send_header("Content-Type", "application/vnd.apache.arrow.stream")
-            request.end_headers()
-            request.wfile.write(events_body)
-        else:
-            request.send_response(404)
-            request.end_headers()
-
-    with mock_lancedb_connection(handler) as db:
-        job = db.open_job("job-1")
-
-        # Opening populates the handle in the same round trip.
-        assert job.state == "finished"
-        job.refresh()
-        assert job.job_type == "refresh_column"
-        assert job.creation_ms == 2000
-        assert job.spec == {"column": "vec"}
-        assert job.result == {"rows_assigned": 1000000}
-        assert job.failure is None
-        # The JSON payloads stay reachable, but as internal APIs.
-        assert json.loads(job._spec_json) == {"column": "vec"}
-        assert json.loads(job._result_json) == {"rows_assigned": 1000000}
-
-        # print() shows everything the handle knows and nothing it does not.
-        # print() lays every known field out on its own line, with the JSON
-        # payloads indented rather than crammed onto one line.
-        assert repr(job) == "\n".join(
-            [
-                "Job(",
-                "    id='job-1',",
-                "    state='finished',",
-                "    job_type='refresh_column',",
-                "    creation_ms=2000,",
-                "    spec={",
-                '        "column": "vec"',
-                "    },",
-                "    result={",
-                '        "rows_assigned": 1000000',
-                "    },",
-                ")",
-            ]
-        )
-        # Nothing it does not know shows up.
-        assert "failure" not in repr(job)
-
-        events = job.events(filter="state = 'claim_complete'", limit=500)
-        assert isinstance(events, pa.Table)
-        assert events.column("state").to_pylist() == ["claim_complete"]
-        # The handle supplies job_id; the caller only narrows the query.
-        assert event_payloads[-1] == {
-            "job_id": "job-1",
-            "limit": 500,
-            "filter": "state = 'claim_complete'",
-        }

python/python/tests/test_sql.py

@@ -1,162 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-from uuid import UUID
-
-import pytest
-import pyarrow as pa
-
-import lancedb
-from lancedb import _lancedb
-from lancedb.arrow import AsyncRecordBatchReader
-from lancedb.db import AsyncConnection
-from lancedb.remote.db import RemoteDBConnection
-from lancedb.sql import AsyncQuery, Query
-
-NIL_QUERY_ID = UUID(int=0)
-
-
-class FakeNativeQuery:
-    id = UUID("0198f1b2-c3d4-7e5f-8123-456789abcdef")
-
-    async def reader(self):
-        return pa.table({"value": [1, 2]})
-
-
-class FakeNativeConnection:
-    async def execute_query_async(self, query, *, default_namespace_path=None):
-        return FakeNativeQuery()
-
-
-class FakeAsyncConnection:
-    async def execute_query_async(self, query, *, default_namespace_path=None):
-        return AsyncQuery(FakeNativeQuery())
-
-
-def remote_connection(sql_host_override=None):
-    return lancedb.connect(
-        "db://analytics",
-        api_key="test-key",
-        host_override="http://localhost:10024",
-        sql_host_override=sql_host_override,
-    )
-
-
-def test_sql_is_connection_scoped():
-    assert hasattr(lancedb, "sql")
-    assert not callable(lancedb.sql)
-    assert not hasattr(_lancedb, "sql")
-    assert not hasattr(remote_connection(), "sql")
-    assert hasattr(remote_connection(), "execute_query")
-    assert hasattr(remote_connection(), "execute_query_async")
-    assert hasattr(remote_connection(), "describe_query")
-
-
-def test_query_id_is_uuid():
-    query = AsyncQuery(FakeNativeQuery())
-    assert isinstance(query.id, UUID)
-    assert Query(query).id == query.id
-
-
-def test_connection_serializes_sql_host_override():
-    endpoint = "grpc+tls://sql.example.com:10026"
-    restored = lancedb.deserialize_conn(
-        remote_connection(sql_host_override=endpoint).serialize()
-    )
-    assert restored.sql_host_override == endpoint
-
-
-@pytest.mark.asyncio
-async def test_async_sql_reader_is_record_batch_stream():
-    reader = await AsyncQuery(FakeNativeQuery()).reader()
-    assert isinstance(reader, AsyncRecordBatchReader)
-    assert (await reader.read_all())[0].column(0).to_pylist() == [1, 2]
-
-
-def test_sync_sql_reader_is_record_batch_reader():
-    reader = Query(AsyncQuery(FakeNativeQuery())).reader()
-    assert isinstance(reader, pa.RecordBatchReader)
-    assert reader.read_all().column(0).to_pylist() == [1, 2]
-
-
-def test_execute_query_returns_blocking_reader():
-    connection = RemoteDBConnection.__new__(RemoteDBConnection)
-    connection._conn = FakeAsyncConnection()
-    reader = connection.execute_query("SELECT 1")
-    assert isinstance(reader, pa.RecordBatchReader)
-    assert reader.read_all().column(0).to_pylist() == [1, 2]
-
-
-@pytest.mark.asyncio
-async def test_async_execute_query_returns_async_reader():
-    connection = AsyncConnection(FakeNativeConnection())
-    reader = await connection.execute_query("SELECT 1")
-    assert isinstance(reader, AsyncRecordBatchReader)
-    assert (await reader.read_all())[0].column(0).to_pylist() == [1, 2]
-
-
-def test_local_connection_rejects_sql(tmp_path):
-    connection = lancedb.connect(tmp_path)
-    with pytest.raises(NotImplementedError, match="SQL"):
-        connection.execute_query("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        connection.execute_query_async("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        connection.describe_query(NIL_QUERY_ID)
-
-
-@pytest.mark.asyncio
-async def test_local_async_connection_rejects_sql(tmp_path):
-    connection = await lancedb.connect_async(tmp_path)
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query_async("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.describe_query(NIL_QUERY_ID)
-
-
-@pytest.mark.asyncio
-async def test_async_namespace_connection_rejects_sql(tmp_path):
-    connection = lancedb.connect_namespace_async("dir", {"root": str(tmp_path)})
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.execute_query_async("SELECT 1")
-    with pytest.raises(NotImplementedError, match="SQL"):
-        await connection.describe_query(NIL_QUERY_ID)
-
-
-def test_describe_query_requires_uuid():
-    with pytest.raises(TypeError, match="UUID"):
-        remote_connection().describe_query(str(NIL_QUERY_ID))
-
-
-@pytest.mark.parametrize(
-    "default_namespace_path",
-    ["public", ("public",), [1]],
-)
-def test_execute_query_async_requires_namespace_path_list(default_namespace_path):
-    with pytest.raises(ValueError, match="default_namespace_path"):
-        remote_connection().execute_query_async(
-            "SELECT 1", default_namespace_path=default_namespace_path
-        )
-
-
-def test_execute_query_async_rejects_invalid_endpoint():
-    connection = remote_connection(sql_host_override="invalid://localhost")
-    with pytest.raises(ValueError, match="sql_host_override"):
-        connection.execute_query_async("SELECT 1")
-
-
-@pytest.mark.parametrize(
-    "default_namespace_path",
-    [[""], ["café"], ["pub\tlic"], ["events$raw"]],
-)
-def test_execute_query_async_rejects_invalid_namespace_components(
-    default_namespace_path,
-):
-    with pytest.raises(ValueError, match="default_namespace_path"):
-        remote_connection().execute_query_async(
-            "SELECT 1", default_namespace_path=default_namespace_path
-        )

python/python/tests/test_table.py

@@ -11,7 +11,6 @@ import warnings
 import weakref
 from concurrent.futures import ThreadPoolExecutor
 from datetime import date, datetime, timedelta
-from decimal import Decimal
 from time import sleep
 from typing import List
 from unittest.mock import patch
@@ -337,21 +336,6 @@ async def test_update_async(mem_db_async: AsyncConnection):
     assert await table.count_rows("id == 10") == 1
 
 
-@pytest.mark.asyncio
-async def test_update_expr_filter_literals_async(mem_db_async: AsyncConnection):
-    values = ["5", "4.66e-84", "it's"]
-    table = await mem_db_async.create_table(
-        "update_expr_literals",
-        data=[{"field": value, "result": "original"} for value in values],
-    )
-
-    for value in values:
-        update_res = await table.update({"result": value}, where=col("field") == value)
-        assert update_res.rows_updated == 1
-
-    assert (await table.to_arrow())["result"].to_pylist() == values
-
-
 def test_create_table(mem_db: DBConnection):
     schema = pa.schema(
         {
@@ -2359,148 +2343,6 @@ def test_update(mem_db: DBConnection):
     assert np.allclose(v, np.array([[1.2, 1.9], [1.1, 1.1]]))
 
 
-def test_update_expr_filter_literals(mem_db: DBConnection):
-    values = ["5", "4.66e-84", "it's"]
-    table = mem_db.create_table(
-        "update_expr_literals",
-        data=[{"field": value, "result": "original"} for value in values],
-    )
-
-    for value in values:
-        update_res = table.update(where=col("field") == value, values={"result": value})
-        assert update_res.rows_updated == 1
-
-    assert table.to_arrow()["result"].to_pylist() == values
-
-
-def test_update_expr_filter_preserves_typed_semantics(mem_db: DBConnection):
-    low = Decimal("1.234567890123456789")
-    high = Decimal("1.234567890123456790")
-    decimal_schema = pa.schema(
-        [("val", pa.decimal128(19, 18)), ("result", pa.string())]
-    )
-    decimal_table = mem_db.create_table(
-        "update_expr_decimal",
-        pa.table(
-            {"val": [low, high], "result": ["old", "old"]},
-            schema=decimal_schema,
-        ),
-    )
-    predicate = col("val") < lit(high)
-    assert decimal_table.search().where(predicate).to_arrow().num_rows == 1
-    result = decimal_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 1
-
-    keyword_table = mem_db.create_table(
-        "update_expr_keyword", [{"null": 1, "result": "old"}]
-    )
-    predicate = col("null") == 1
-    assert keyword_table.search().where(predicate).to_arrow().num_rows == 1
-    result = keyword_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 1
-
-    empty_in_table = mem_db.create_table(
-        "update_expr_empty_in", [{"id": 1, "result": "old"}]
-    )
-    predicate = col("id").isin([])
-    assert empty_in_table.search().where(predicate).to_arrow().num_rows == 0
-    result = empty_in_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 0
-
-    marker = "__lancedb_binary_placeholder_0__"
-    binary_schema = pa.schema(
-        [("payload", pa.binary()), ("text", pa.string()), ("result", pa.string())]
-    )
-    binary_table = mem_db.create_table(
-        "update_expr_binary",
-        pa.table(
-            {
-                "payload": [b"\x01", b"\x02"],
-                "text": ["other", marker],
-                "result": ["old", "old"],
-            },
-            schema=binary_schema,
-        ),
-    )
-    predicate = (col("payload") == lit(b"\x01")) | (col("text") == marker)
-    assert binary_table.search().where(predicate).to_arrow().num_rows == 2
-    result = binary_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 2
-
-    nonfinite_table = mem_db.create_table(
-        "update_expr_nonfinite",
-        [{"x": 1.0, "result": "old"}, {"x": 2.0, "result": "old"}],
-    )
-    predicate = col("x") < float("inf")
-    assert nonfinite_table.search().where(predicate).to_arrow().num_rows == 2
-    result = nonfinite_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 2
-
-    float16_table = mem_db.create_table(
-        "update_expr_float16",
-        [{"x": 1.0, "result": "old"}, {"x": 3.0, "result": "old"}],
-    )
-    predicate = col("x").cast(pa.float16()) < 2.0
-    assert float16_table.search().where(predicate).to_arrow().num_rows == 1
-    result = float16_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 1
-
-    string_cast_table = mem_db.create_table(
-        "update_expr_string_cast",
-        [{"x": 1, "result": "old"}, {"x": 2, "result": "old"}],
-    )
-    predicate = col("x").cast("string") == "1"
-    assert string_cast_table.search().where(predicate).to_arrow().num_rows == 1
-    result = string_cast_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 1
-
-    quoted_identifier_schema = pa.schema(
-        [("payload", pa.binary()), ("odd'name", pa.int64()), ("result", pa.string())]
-    )
-    quoted_identifier_table = mem_db.create_table(
-        "update_expr_quoted_identifier",
-        pa.table(
-            {"payload": [b"\x01"], "odd'name": [1], "result": ["old"]},
-            schema=quoted_identifier_schema,
-        ),
-    )
-    predicate = (col("payload") == lit(b"\x01")) & (col("odd'name") == 1)
-    assert quoted_identifier_table.search().where(predicate).to_arrow().num_rows == 1
-    result = quoted_identifier_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 1
-
-    decimal256_schema = pa.schema(
-        [("val", pa.decimal256(40, 2)), ("result", pa.string())]
-    )
-    decimal256_table = mem_db.create_table(
-        "update_expr_decimal256",
-        pa.table(
-            {
-                "val": [Decimal("1.00"), Decimal("3.00")],
-                "result": ["old", "old"],
-            },
-            schema=decimal256_schema,
-        ),
-    )
-    predicate = col("val") < lit(Decimal("2.00")).cast(pa.decimal256(40, 2))
-    assert decimal256_table.search().where(predicate).to_arrow().num_rows == 1
-    result = decimal256_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 1
-
-    binary_empty_table = mem_db.create_table(
-        "update_expr_binary_empty",
-        pa.table(
-            {"payload": [b"\x01", b"\x02"], "result": ["old", "old"]},
-            schema=pa.schema([("payload", pa.binary()), ("result", pa.string())]),
-        ),
-    )
-    predicate = (col("payload") == lit(b"\x01")).isin([])
-    assert binary_empty_table.search().where(predicate).to_arrow().num_rows == 0
-    assert predicate.to_sql() == "false"
-    result = binary_empty_table.update(where=predicate, values={"result": "new"})
-    assert result.rows_updated == 0
-
-
 def test_update_with_arrow_scalar(mem_db: DBConnection):
     schema = pa.schema({"id": pa.int64(), "vector": pa.list_(pa.float32(), 4)})
     table = mem_db.create_table("my_table", schema=schema)
@@ -2682,43 +2524,6 @@ def test_merge_insert(mem_db: DBConnection):
         )
 
 
-def test_merge_insert_composite_key(mem_db: DBConnection):
-    table = mem_db.create_table(
-        "my_table",
-        data=pa.table(
-            {
-                "shard": ["a", "a", "b"],
-                "id": [1, 2, 1],
-                "val": ["x", "y", "z"],
-            }
-        ),
-    )
-
-    # ("a", 1) matches an existing row and updates it. ("b", 2) agrees with an
-    # existing row on each key column separately but on neither pair, so it is
-    # an insert.
-    new_data = pa.table({"shard": ["a", "b"], "id": [1, 2], "val": ["X", "W"]})
-    res = (
-        table.merge_insert(["shard", "id"])
-        .when_matched_update_all()
-        .when_not_matched_insert_all()
-        .execute(new_data)
-    )
-    assert res.num_updated_rows == 1
-    assert res.num_inserted_rows == 1
-
-    expected = pa.table(
-        {
-            "shard": ["a", "a", "b", "b"],
-            "id": [1, 2, 1, 2],
-            "val": ["X", "y", "z", "W"],
-        }
-    )
-    assert table.to_arrow().sort_by([("shard", "ascending"), ("id", "ascending")]) == (
-        expected
-    )
-
-
 def test_merge_insert_nullable_pandas_into_pydantic_schema(mem_db: DBConnection):
     # Regression test for https://github.com/lancedb/lancedb/issues/2366
     pd = pytest.importorskip("pandas")
@@ -4124,29 +3929,6 @@ def test_computed_column_rejects_transforms_and_computed_together(tmp_path):
         table.add_columns({"a": "x + 1"}, computed={"b": "x * 2"})
 
 
-def test_computed_column_blob_projection_inherits_semantics(tmp_path):
-    schema = pa.schema([pa.field("id", pa.int64()), lancedb.blob("image")])
-    db = lancedb.connect(tmp_path)
-    table = db.create_table("computed_column_blob", schema=schema)
-    table.add(
-        [
-            {"id": 1, "image": b"hello"},
-            {"id": 2, "image": b""},
-            {"id": 3, "image": None},
-        ]
-    )
-
-    table.add_columns(computed={"image_copy": "image", "second_copy": "image_copy"})
-    assert table.refresh_column("image_copy").rows_filled == 2
-    assert table.refresh_column("second_copy").rows_filled == 2
-    assert table.blob_columns() == ["image", "image_copy", "second_copy"]
-
-    hits = table.search().with_row_id(True).limit(10).to_arrow()
-    rows = sorted(zip(hits["id"].to_pylist(), hits["_rowid"].to_pylist()))
-    copied = table.fetch_blobs("second_copy", [row_id for _, row_id in rows])
-    assert copied.to_pylist() == [b"hello", b"", None]
-
-
 @pytest.mark.asyncio
 async def test_computed_column_async(tmp_path):
     db = await lancedb.connect_async(tmp_path)

python/python/tests/test_util.py

@@ -7,7 +7,6 @@ import pathlib
 from typing import Optional
 
 import lance
-from lance.blob import BlobType as LanceBlobType
 from lancedb.conftest import MockTextEmbeddingFunction
 from lancedb.embeddings.base import EmbeddingFunctionConfig
 from lancedb.embeddings.registry import EmbeddingFunctionRegistry
@@ -908,165 +907,6 @@ def test_cast_to_target_schema():
     assert output == expected
 
 
-def test_cast_to_target_schema_coerces_binary_to_blob_v2():
-    data = pa.table({"image": pa.array([b"hello", None], type=pa.binary())})
-    target = pa.schema([lancedb.blob("image")])
-
-    output = _cast_to_target_schema(data.to_reader(), target).read_all()
-
-    image = output["image"].chunk(0)
-    assert type(image.type) is lancedb.BlobType
-    assert image.storage.to_pylist() == [
-        {"data": b"hello", "uri": None, "position": None, "size": None},
-        None,
-    ]
-
-
-def test_cast_to_target_schema_coerces_binary_to_metadata_blob_struct():
-    storage = lancedb.blob("image").type.storage_type
-    target = pa.schema(
-        [
-            pa.field(
-                "image",
-                storage,
-                metadata={
-                    b"ARROW:extension:name": b"lance.blob.v2",
-                    b"ARROW:extension:metadata": b"",
-                },
-            )
-        ]
-    )
-    data = pa.table({"image": pa.array([b"hello", None], type=pa.binary())})
-
-    output = _cast_to_target_schema(data.to_reader(), target).read_all()
-
-    image = output["image"].chunk(0)
-    assert not isinstance(image.type, pa.ExtensionType)
-    assert image.to_pylist() == [
-        {"data": b"hello", "uri": None, "position": None, "size": None},
-        None,
-    ]
-
-
-def test_cast_to_target_schema_coerces_nested_binary_blob():
-    data = pa.table(
-        {
-            "info": pa.array(
-                [{"blob": b"hello"}, {"blob": None}],
-                type=pa.struct([pa.field("blob", pa.binary())]),
-            )
-        }
-    )
-    target = pa.schema([pa.field("info", pa.struct([lancedb.blob("blob")]))])
-
-    output = _cast_to_target_schema(data.to_reader(), target).read_all()
-
-    blob = output["info"].chunk(0).field("blob")
-    assert type(blob.type) is lancedb.BlobType
-    assert blob.storage.to_pylist() == [
-        {"data": b"hello", "uri": None, "position": None, "size": None},
-        None,
-    ]
-
-
-def test_cast_to_target_schema_coerces_list_binary_blob_with_inferred_child_name():
-    data = pa.table(
-        {"images": pa.array([[b"a", b"b"], None], type=pa.list_(pa.binary()))}
-    )
-    target = pa.schema([pa.field("images", pa.list_(lancedb.blob("image")))])
-
-    output = _cast_to_target_schema(data.to_reader(), target).read_all()
-
-    images = output["images"].chunk(0)
-    assert images.type.value_field.name == "image"
-    assert type(images.type.value_type) is lancedb.BlobType
-    assert images.to_pylist()[1] is None
-    assert images.values.storage.to_pylist() == [
-        {"data": b"a", "uri": None, "position": None, "size": None},
-        {"data": b"b", "uri": None, "position": None, "size": None},
-    ]
-
-
-def test_list_blob_coercion_preserves_null_slots_with_nonzero_extent():
-    child = pa.field("image", pa.binary())
-    source = pa.ListArray.from_arrays(
-        pa.array([0, 2, 4], type=pa.int32()),
-        pa.array([b"a", b"b", b"dead", b"beef"], type=pa.binary()),
-        mask=pa.array([False, True]),
-    ).cast(pa.list_(child))
-    target = pa.schema([pa.field("images", pa.list_(lancedb.blob("image")))])
-
-    output = _cast_to_target_schema(
-        pa.table({"images": source}).to_reader(), target
-    ).read_all()
-
-    images = output["images"].chunk(0)
-    assert images.to_pylist()[1] is None
-    assert [b["data"] for b in images.to_pylist()[0]] == [b"a", b"b"]
-
-
-def test_fixed_size_list_blob_coercion_keeps_null_rows():
-    child = pa.field("frame", pa.binary())
-    source = (
-        pa.FixedSizeListArray.from_arrays(
-            pa.array([b"a", b"b", b"c", b"d"], type=pa.binary()), 2
-        )
-        .take(pa.array([0, None], type=pa.int32()))
-        .cast(pa.list_(child, 2))
-    )
-    target = pa.schema([pa.field("frames", pa.list_(lancedb.blob("frame"), 2))])
-
-    output = _cast_to_target_schema(
-        pa.table({"frames": source}).to_reader(), target
-    ).read_all()
-
-    frames = output["frames"].chunk(0)
-    assert frames.to_pylist()[1] is None
-    assert [b["data"] for b in frames.to_pylist()[0]] == [b"a", b"b"]
-
-
-def test_cast_to_target_schema_accepts_pylance_blob_v2():
-    target_type = lancedb.BlobType()
-    source = lance.blob_array([b"hello", None])
-    assert type(source.type) is LanceBlobType
-    assert type(source.type) is type(target_type)
-    data = pa.table({"image": source})
-    target = pa.schema([pa.field("image", target_type)])
-
-    output = _cast_to_target_schema(data.to_reader(), target).read_all()
-
-    image = output["image"].chunk(0)
-    assert type(image.type) is LanceBlobType
-    assert image.type == target_type
-    assert image.storage.to_pylist() == [
-        {"data": b"hello", "uri": None, "position": None, "size": None},
-        None,
-    ]
-
-
-def test_cast_to_target_schema_rejects_different_blob_v2_class():
-    class OtherBlobType(pa.ExtensionType):
-        def __init__(self):
-            super().__init__(lancedb.BlobType().storage_type, "lance.blob.v2")
-
-        def __arrow_ext_serialize__(self) -> bytes:
-            return b""
-
-        @classmethod
-        def __arrow_ext_deserialize__(
-            cls, storage_type: pa.DataType, serialized: bytes
-        ) -> "OtherBlobType":
-            return cls()
-
-    storage = lance.blob_array([b"hello"]).storage
-    source = pa.ExtensionArray.from_storage(OtherBlobType(), storage)
-    data = pa.table({"image": source})
-    target = pa.schema([lancedb.blob("image")])
-
-    with pytest.raises(pa.ArrowTypeError, match="different extension type"):
-        _cast_to_target_schema(data.to_reader(), target).read_all()
-
-
 def test_sanitize_data_stream():
     # Make sure we don't collect the whole stream when running sanitize_data
     schema = pa.schema({"a": pa.int32()})

python/src/connection.rs

@@ -13,7 +13,11 @@ use crate::{
     runtime::future_into_py,
     table::Table,
 };
-use arrow::{datatypes::Schema, ffi_stream::ArrowArrayStreamReader, pyarrow::FromPyArrow};
+use arrow::{
+    datatypes::Schema,
+    ffi_stream::ArrowArrayStreamReader,
+    pyarrow::{FromPyArrow, ToPyArrow},
+};
 use lancedb::{
     connection::Connection as LanceConnection,
     connection::NamespaceClientPushdownOperation,
@@ -24,7 +28,7 @@ use pyo3::{
     Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
     exceptions::{PyRuntimeError, PyValueError},
     pyclass, pyfunction, pymethods,
-    types::{PyAnyMethods, PyDict, PyDictMethods, PyList},
+    types::{PyDict, PyDictMethods, PyList, PyListMethods},
 };
 
 #[pyclass]
@@ -82,24 +86,6 @@ impl Connection {
     }
 }
 
-fn parse_default_namespace_path(path: Option<Bound<'_, PyAny>>) -> PyResult<Vec<String>> {
-    match path {
-        Some(path) => {
-            if !path.is_instance_of::<PyList>() {
-                return Err(PyValueError::new_err(
-                    "Connection.execute_query_async default_namespace_path must be a list",
-                ));
-            }
-            path.extract::<Vec<String>>().map_err(|_| {
-                PyValueError::new_err(
-                    "Connection.execute_query_async default_namespace_path components must be strings",
-                )
-            })
-        }
-        None => Ok(vec!["public".to_string()]),
-    }
-}
-
 #[pymethods]
 impl Connection {
     fn __repr__(&self) -> String {
@@ -122,40 +108,6 @@ impl Connection {
         self.get_inner().map(|inner| inner.uri().to_string())
     }
 
-    #[pyo3(signature = (query, *, default_namespace_path=None))]
-    pub fn execute_query_async<'a>(
-        self_: PyRef<'a, Self>,
-        query: String,
-        default_namespace_path: Option<Bound<'_, PyAny>>,
-    ) -> PyResult<Bound<'a, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        let default_namespace_path = parse_default_namespace_path(default_namespace_path)?;
-        future_into_py(self_.py(), async move {
-            let operation = inner
-                .execute_query_async(query)
-                .default_namespace_path(default_namespace_path);
-            operation
-                .execute()
-                .await
-                .map(crate::sql::Query::new)
-                .infer_error()
-        })
-    }
-
-    pub fn describe_query<'a>(
-        self_: PyRef<'a, Self>,
-        query_id: uuid::Uuid,
-    ) -> PyResult<Bound<'a, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner
-                .describe_query(query_id)
-                .await
-                .map(crate::sql::QueryDescription::from)
-                .infer_error()
-        })
-    }
-
     #[pyo3(signature = ())]
     pub fn get_read_consistency_interval(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
@@ -640,12 +592,9 @@ impl Connection {
         })
     }
 
-    pub fn open_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {
+    pub fn job(&self, job_id: String) -> PyResult<crate::job::Job> {
-        let inner = self_.get_inner()?.clone();
+        let inner = self.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
+        Ok(crate::job::Job::new(inner.job(job_id).infer_error()?))
-            let job = inner.open_job(&job_id).await.infer_error()?;
-            Ok(crate::job::Job::new(job))
-        })
     }
 
     pub fn create_function_async(
@@ -680,80 +629,6 @@ impl Connection {
         })
     }
 
-    pub fn list_functions(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner
-                .list_functions()
-                .await
-                .infer_error()?
-                .into_iter()
-                .map(|function| function.to_canonical_json().infer_error())
-                .collect::<PyResult<Vec<_>>>()
-        })
-    }
-
-    pub fn drop_function(
-        self_: PyRef<'_, Self>,
-        name: String,
-        version: String,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.drop_function(name, version).await.infer_error()
-        })
-    }
-
-    pub fn create_secret(
-        self_: PyRef<'_, Self>,
-        name: String,
-        value: String,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.create_secret(name, value).await.infer_error()
-        })
-    }
-
-    pub fn alter_secret(
-        self_: PyRef<'_, Self>,
-        name: String,
-        value: String,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.alter_secret(name, value).await.infer_error()
-        })
-    }
-
-    pub fn list_secrets(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.list_secrets().await.infer_error()
-        })
-    }
-
-    pub fn drop_secret(self_: PyRef<'_, Self>, name: String) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            inner.drop_secret(name).await.infer_error()
-        })
-    }
-
-    /// Name and timestamps as a plain mapping. `SecretInfo` carries no value,
-    /// so there is none to filter out here.
-    pub fn describe_secret(self_: PyRef<'_, Self>, name: String) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.get_inner()?.clone();
-        future_into_py(self_.py(), async move {
-            let info = inner.describe_secret(name).await.infer_error()?;
-            Ok(HashMap::from([
-                ("name".to_string(), info.name),
-                ("created_at".to_string(), info.created_at),
-                ("updated_at".to_string(), info.updated_at),
-            ]))
-        })
-    }
-
     pub fn list_jobs(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
         future_into_py(self_.py(), async move {
@@ -765,16 +640,42 @@ impl Connection {
         })
     }
 
+    pub fn get_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let description = inner.get_job(&job_id).await.infer_error()?;
+            Ok(description.map(crate::job::JobDescription::from))
+        })
+    }
+
     pub fn cancel_job(self_: PyRef<'_, Self>, job_id: String) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.get_inner()?.clone();
         future_into_py(self_.py(), async move {
             inner.cancel_job(&job_id).await.infer_error()
         })
     }
+
+    #[pyo3(signature = (job_id=None))]
+    pub fn job_history(
+        self_: PyRef<'_, Self>,
+        job_id: Option<String>,
+    ) -> PyResult<Bound<'_, PyAny>> {
+        let inner = self_.get_inner()?.clone();
+        future_into_py(self_.py(), async move {
+            let batches = inner.job_history(job_id.as_deref()).await.infer_error()?;
+            Python::attach(|py| {
+                let list = PyList::empty(py);
+                for batch in batches {
+                    list.append(batch.to_pyarrow(py)?)?;
+                }
+                Ok(list.unbind())
+            })
+        })
+    }
 }
 
 #[pyfunction]
-#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, sql_host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None, oauth_config=None))]
+#[pyo3(signature = (uri, api_key=None, region=None, host_override=None, read_consistency_interval=None, client_config=None, storage_options=None, session=None, manifest_enabled=false, namespace_client_properties=None, oauth_config=None))]
 #[allow(clippy::too_many_arguments)]
 pub fn connect(
     py: Python<'_>,
@@ -782,7 +683,6 @@ pub fn connect(
     api_key: Option<String>,
     region: Option<String>,
     host_override: Option<String>,
-    sql_host_override: Option<String>,
     read_consistency_interval: Option<f64>,
     client_config: Option<PyClientConfig>,
     storage_options: Option<HashMap<String, String>>,
@@ -802,12 +702,6 @@ pub fn connect(
         if let Some(host_override) = host_override {
             builder = builder.host_override(&host_override);
         }
-        #[cfg(feature = "remote")]
-        if let Some(sql_host_override) = sql_host_override {
-            builder = builder.sql_host_override(&sql_host_override);
-        }
-        #[cfg(not(feature = "remote"))]
-        let _ = sql_host_override;
         if let Some(read_consistency_interval) = read_consistency_interval {
             let read_consistency_interval = Duration::from_secs_f64(read_consistency_interval);
             builder = builder.read_consistency_interval(read_consistency_interval);

python/src/error.rs

@@ -114,12 +114,6 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                         .getattr(intern!(py, "JobCancelledError"))?;
                     Err(PyErr::from_value(cls.call1((err.to_string(),))?))
                 }),
-                LanceError::JobNotFound { .. } => Python::attach(|py| {
-                    let cls = py
-                        .import(intern!(py, "lancedb.exceptions"))?
-                        .getattr(intern!(py, "JobNotFoundError"))?;
-                    Err(PyErr::from_value(cls.call1((err.to_string(),))?))
-                }),
                 _ => self.runtime_error(),
             },
         }

python/src/expr.rs

@@ -130,14 +130,6 @@ impl PyExpr {
 
     // ── utilities ────────────────────────────────────────────────────────────
 
-    /// Return the referenced column name for a bare column expression.
-    fn column_name(&self) -> Option<String> {
-        match &self.0 {
-            DfExpr::Column(column) if column.relation.is_none() => Some(column.name.clone()),
-            _ => None,
-        }
-    }
-
     /// Render the expression as a SQL string (useful for debugging).
     fn to_sql(&self) -> PyResult<String> {
         lancedb::expr::expr_to_sql_string(&self.0).map_err(|e| PyValueError::new_err(e.to_string()))

python/src/job.rs

@@ -4,50 +4,11 @@
 use std::sync::Arc;
 
 use crate::runtime::future_into_py;
-use arrow::{
+use pyo3::{Bound, PyAny, PyRef, PyResult, pyclass, pymethods};
-    datatypes::Schema,
-    pyarrow::{IntoPyArrow, Table as PyArrowTable},
-};
-use lancedb::job::JobEventsRequest;
-use pyo3::{
-    Bound, PyAny, PyRef, PyResult, Python,
-    exceptions::PyValueError,
-    pyclass, pymethods,
-    types::{PyAnyMethods, PyDict, PyDictMethods},
-};
 use serde::Serialize;
 
 use crate::error::PythonErrorExt;
 
-const REPR_INDENT: &str = "    ";
-
-/// Parse a stored JSON payload into Python data. The bindings carry these as
-/// strings because that is what crosses the boundary cheaply; the public
-/// Python surface is the parsed form.
-fn parse_json_payload<'py>(
-    py: Python<'py>,
-    raw: Option<&str>,
-) -> PyResult<Option<Bound<'py, PyAny>>> {
-    match raw {
-        None => Ok(None),
-        Some(raw) => Ok(Some(py.import("json")?.call_method1("loads", (raw,))?)),
-    }
-}
-
-/// A payload rendered as indented JSON, aligned under the field that holds it.
-fn pretty_json_payload(py: Python<'_>, raw: Option<&str>) -> PyResult<Option<String>> {
-    let Some(parsed) = parse_json_payload(py, raw)? else {
-        return Ok(None);
-    };
-    let kwargs = PyDict::new(py);
-    kwargs.set_item("indent", 4)?;
-    let rendered: String = py
-        .import("json")?
-        .call_method("dumps", (parsed,), Some(&kwargs))?
-        .extract()?;
-    Ok(Some(rendered.replace('\n', &format!("\n{REPR_INDENT}"))))
-}
-
 #[pyclass]
 pub struct Job {
     inner: Arc<lancedb::Job<std::result::Result<Option<String>, String>>>,
@@ -106,48 +67,6 @@ impl Job {
             Ok(())
         })
     }
-
-    pub fn refresh(self_: PyRef<'_, Self>) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        future_into_py(self_.py(), async move {
-            inner.refresh().await.infer_error()?;
-            Ok(())
-        })
-    }
-
-    /// The last observed lifecycle state, without contacting the backend.
-    #[getter]
-    pub fn _state(&self) -> Option<String> {
-        self.inner.state()
-    }
-
-    /// The last observed server-side record. `None` for an in-process job.
-    #[getter]
-    pub fn _description(&self) -> Option<JobDescription> {
-        self.inner.description().map(JobDescription::from)
-    }
-
-    #[pyo3(signature = (*, limit=None, filter=None))]
-    pub fn events(
-        self_: PyRef<'_, Self>,
-        limit: Option<u32>,
-        filter: Option<String>,
-    ) -> PyResult<Bound<'_, PyAny>> {
-        let inner = self_.inner.clone();
-        let request = JobEventsRequest { limit, filter };
-        future_into_py(self_.py(), async move {
-            let batches = inner.events(request).await.infer_error()?;
-            Python::attach(|py| {
-                let schema = batches
-                    .first()
-                    .map(|batch| batch.schema())
-                    .unwrap_or_else(|| Arc::new(Schema::empty()));
-                let table = PyArrowTable::try_new(batches, schema)
-                    .map_err(|err| PyValueError::new_err(err.to_string()))?;
-                table.into_pyarrow(py).map(|table| table.unbind())
-            })
-        })
-    }
 }
 
 /// A row from `Connection.list_jobs`: one server-side job.
@@ -202,7 +121,7 @@ impl JobFailureInfo {
     }
 }
 
-/// The server-side record behind a `Job` handle.
+/// A described job from `Connection.get_job`.
 #[pyclass(get_all, skip_from_py_object)]
 #[derive(Clone)]
 pub struct JobDescription {
@@ -210,49 +129,17 @@ pub struct JobDescription {
     job_type: String,
     state: String,
     creation_ms: i64,
-    /// Internal: the wire form behind the `spec` property.
+    spec_json: Option<String>,
-    _spec_json: Option<String>,
-    /// Internal: the wire form behind the `result` property.
-    _result_json: Option<String>,
     failure: Option<JobFailureInfo>,
 }
 
 #[pymethods]
 impl JobDescription {
-    /// The job-type-specific specification it was submitted with.
+    fn __repr__(&self) -> String {
-    #[getter]
+        format!(
-    fn spec<'py>(&self, py: Python<'py>) -> PyResult<Option<Bound<'py, PyAny>>> {
+            "JobDescription(job_id={:?}, job_type={:?}, state={:?}, creation_ms={})",
-        parse_json_payload(py, self._spec_json.as_deref())
+            self.job_id, self.job_type, self.state, self.creation_ms
-    }
+        )
-
-    /// The job-type-specific terminal result. `None` until the job succeeds.
-    #[getter]
-    fn result<'py>(&self, py: Python<'py>) -> PyResult<Option<Bound<'py, PyAny>>> {
-        parse_json_payload(py, self._result_json.as_deref())
-    }
-
-    fn __repr__(&self, py: Python<'_>) -> PyResult<String> {
-        let mut fields = vec![
-            format!("job_id={:?}", self.job_id),
-            format!("job_type={:?}", self.job_type),
-            format!("state={:?}", self.state),
-            format!("creation_ms={}", self.creation_ms),
-        ];
-        // Lay the payloads out as indented JSON, the same way the `Job` repr
-        // does, so the two agree on how the same data looks.
-        for (name, payload) in [("spec", &self._spec_json), ("result", &self._result_json)] {
-            if let Some(rendered) = pretty_json_payload(py, payload.as_deref())? {
-                fields.push(format!("{name}={rendered}"));
-            }
-        }
-        if let Some(failure) = &self.failure {
-            fields.push(format!("failure={}", failure.__repr__()));
-        }
-        let body = fields
-            .iter()
-            .map(|field| format!("\n{REPR_INDENT}{field},"))
-            .collect::<String>();
-        Ok(format!("JobDescription({body}\n)"))
     }
 }
 
@@ -263,11 +150,7 @@ impl From<lancedb::database::JobDescription> for JobDescription {
             job_type: description.job_type,
             state: description.state,
             creation_ms: description.creation_ms,
-            _spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
+            spec_json: (!description.spec.is_null()).then(|| description.spec.to_string()),
-            _result_json: description
-                .result
-                .filter(|result| !result.is_null())
-                .map(|result| result.to_string()),
             failure: description.failure.map(|failure| JobFailureInfo {
                 phase: failure.phase,
                 message: failure.message,

python/src/lib.rs

@@ -34,7 +34,6 @@ pub mod permutation;
 pub mod query;
 pub mod runtime;
 pub mod session;
-pub mod sql;
 pub mod table;
 pub mod util;
 
@@ -51,8 +50,6 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<crate::job::JobInfo>()?;
     m.add_class::<crate::job::JobDescription>()?;
     m.add_class::<crate::job::JobFailureInfo>()?;
-    m.add_class::<crate::sql::Query>()?;
-    m.add_class::<crate::sql::QueryDescription>()?;
     m.add_class::<PyBlobFile>()?;
     m.add_class::<IndexConfig>()?;
     m.add_class::<Query>()?;

python/src/query.rs

@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::collections::HashMap;
 use std::sync::Arc;
 use std::time::Duration;
 
@@ -323,11 +322,9 @@ impl<'py> IntoPyObject<'py> for PyQueryVectors {
 pub struct PyQueryRequest {
     pub limit: Option<usize>,
     pub offset: Option<usize>,
-    pub take_offsets: Option<Vec<u64>>,
     pub filter: Option<PyQueryFilter>,
     pub full_text_search: Option<PyLanceDB<FtsQuery>>,
     pub select: PySelect,
-    pub select_source_columns: Option<HashMap<String, String>>,
     pub fast_search: Option<bool>,
     pub with_row_id: Option<bool>,
     pub use_lsm: Option<bool>,
@@ -354,12 +351,10 @@ impl From<AnyQuery> for PyQueryRequest {
             AnyQuery::Query(query_request) => Self {
                 limit: query_request.limit,
                 offset: query_request.offset,
-                take_offsets: query_request.take_offsets,
                 filter: query_request.filter.map(PyQueryFilter),
                 full_text_search: query_request
                     .full_text_search
                     .map(|fts| PyLanceDB(fts.query)),
-                select_source_columns: PySelect::source_columns(&query_request.select),
                 select: PySelect(query_request.select),
                 fast_search: Some(query_request.fast_search),
                 with_row_id: Some(query_request.with_row_id),
@@ -383,10 +378,8 @@ impl From<AnyQuery> for PyQueryRequest {
             AnyQuery::VectorQuery(vector_query) => Self {
                 limit: vector_query.base.limit,
                 offset: vector_query.base.offset,
-                take_offsets: vector_query.base.take_offsets,
                 filter: vector_query.base.filter.map(PyQueryFilter),
                 full_text_search: None,
-                select_source_columns: PySelect::source_columns(&vector_query.base.select),
                 select: PySelect(vector_query.base.select),
                 fast_search: Some(vector_query.base.fast_search),
                 with_row_id: Some(vector_query.base.with_row_id),
@@ -419,25 +412,6 @@ impl From<AnyQuery> for PyQueryRequest {
 #[derive(Clone)]
 pub struct PySelect(Select);
 
-impl PySelect {
-    fn source_columns(select: &Select) -> Option<HashMap<String, String>> {
-        match select {
-            Select::Expr(pairs) => Some(
-                pairs
-                    .iter()
-                    .filter_map(|(output, expr)| match expr {
-                        lancedb::expr::DfExpr::Column(column) if column.relation.is_none() => {
-                            Some((output.clone(), column.name.clone()))
-                        }
-                        _ => None,
-                    })
-                    .collect(),
-            ),
-            _ => None,
-        }
-    }
-}
-
 impl<'py> IntoPyObject<'py> for PySelect {
     type Target = PyAny;
     type Output = Bound<'py, Self::Target>;