chore: update lance dependency to v4.0.0-beta.12

.github/workflows/nodejs.yml

@@ -7,7 +7,6 @@ on:
   pull_request:
     paths:
       - Cargo.toml
-      - Cargo.lock
       - nodejs/**
       - rust/**
       - docs/src/js/**

.github/workflows/npm-publish.yml

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

.github/workflows/pypi-publish.yml

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

.github/workflows/python.yml

@@ -7,7 +7,6 @@ on:
   pull_request:
     paths:
       - Cargo.toml
-      - Cargo.lock
       - python/**
       - rust/**
       - .github/workflows/python.yml

.github/workflows/rust.yml

@@ -7,7 +7,6 @@ on:
   pull_request:
     paths:
       - Cargo.toml
-      - Cargo.lock
       - rust/**
       - .github/workflows/rust.yml
 

Cargo.lock

@@ -3070,9 +3070,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "7ae4126c38f86d37d5479295c135a1b81688b6c799d6c39d44b1855f9a0e712c"
 dependencies = [
  "arrow-array",
  "rand 0.9.2",
@@ -3853,7 +3852,7 @@ dependencies = [
  "libc",
  "percent-encoding",
  "pin-project-lite",
- "socket2 0.6.0",
+ "socket2 0.5.10",
  "system-configuration",
  "tokio",
  "tower-service",
@@ -4242,9 +4241,8 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "45c38e7c7c448a77203b50c05f5bf308cadb3fe074e7dde22e4302206ea44d7a"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4310,9 +4308,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "174bae71821e5535a594f9ecd64b07e6ffe729498a5d27a0ca926b4ff2714664"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4332,9 +4329,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "4494187b4244fa56c8cf911d7358e5322fa1cf7d8f6a213b3155a4139eb556b1"
 dependencies = [
  "arrayref",
  "paste",
@@ -4343,9 +4339,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "ce0a5d4427c42f7d9302771bb2aa474b09316a8919633abad0030c4d58013e89"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4382,9 +4377,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "61c6151ee46a35886ac6c804f870de2992c36de4198da1c64d806529f246d2d7"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4414,9 +4408,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "3d130ec0426173daeb14a6032d18a1eb8c1f8858dca3f42735f0d2c7dde3c47f"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4434,9 +4427,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "965281449dc6b47d4669e11572f7b2a5e0e6b206dc1f21bce0f3b5f7dc533ece"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4473,9 +4465,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "4c8230f9a2e63170eef3d4f8f7576593a73ff8a2f8d5a75400e511e74d4d308f"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4507,9 +4498,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "950a0bc24e01044fc86260c54e810f2d051660d89caa727234f09b252446c425"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4572,9 +4562,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "023188a98822bc87c87726893fbd6c1deea2dccf5c4214051b789b6047bdc2a4"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4615,9 +4604,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "1bc4b0c9892f985dac4d27c058d21b6adfda5c73a7aaf697a92f300f36995ded"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4633,9 +4621,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "9c8aab88d6c91b045ac3d3967c73b547d9fed5559a91a907f3f4586d0f2d6cc6"
 dependencies = [
  "arrow",
  "async-trait",
@@ -4647,9 +4634,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "0beb555ea8ac3bfc220519585ffaea34caa61cc24edce533b98f48474042e3f0"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -4693,9 +4679,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "7511e4e951d3938316b16f1a64360cfae0b44d22d9c5aca971ed7b5bc83caea7"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4734,9 +4719,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "3.0.0"
+version = "4.0.0-beta.12"
-source = "registry+https://github.com/rust-lang/crates.io-index"
+source = "git+https://github.com/lance-format/lance.git?tag=v4.0.0-beta.12#1e7b7252881261f290740d8d5a487c053f05039e"
-checksum = "3de153d46ba1c1fc6dbd4c93ed8b0b99b9001902d5df1159d855ef9fd2613591"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -6459,7 +6443,7 @@ version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
- "heck 0.5.0",
+ "heck 0.4.1",
  "itertools 0.14.0",
  "log",
  "multimap",
@@ -6648,7 +6632,7 @@ dependencies = [
  "quinn-udp",
  "rustc-hash",
  "rustls 0.23.31",
- "socket2 0.6.0",
+ "socket2 0.5.10",
  "thiserror 2.0.17",
  "tokio",
  "tracing",
@@ -6685,7 +6669,7 @@ dependencies = [
  "cfg_aliases",
  "libc",
  "once_cell",
- "socket2 0.6.0",
+ "socket2 0.5.10",
  "tracing",
  "windows-sys 0.60.2",
 ]
@@ -7751,7 +7735,7 @@ version = "0.8.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c1c97747dbf44bb1ca44a561ece23508e99cb592e862f22222dcf42f51d1e451"
 dependencies = [
- "heck 0.5.0",
+ "heck 0.4.1",
  "proc-macro2",
  "quote",
  "syn 2.0.114",
@@ -7763,7 +7747,7 @@ version = "0.9.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "54254b8531cafa275c5e096f62d48c81435d1015405a91198ddb11e967301d40"
 dependencies = [
- "heck 0.5.0",
+ "heck 0.4.1",
  "proc-macro2",
  "quote",
  "syn 2.0.114",

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { version = "=3.0.0", default-features = false }
+lance = { "version" = "=4.0.0-beta.12", default-features = false, "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { version = "=3.0.0" }
+lance-core = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { version = "=3.0.0" }
+lance-datagen = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { version = "=3.0.0" }
+lance-file = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { version = "=3.0.0", default-features = false }
+lance-io = { "version" = "=4.0.0-beta.12", default-features = false, "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { version = "=3.0.0" }
+lance-index = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { version = "=3.0.0" }
+lance-linalg = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { version = "=3.0.0" }
+lance-namespace = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { version = "=3.0.0", default-features = false }
+lance-namespace-impls = { "version" = "=4.0.0-beta.12", default-features = false, "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { version = "=3.0.0" }
+lance-table = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { version = "=3.0.0" }
+lance-testing = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { version = "=3.0.0" }
+lance-datafusion = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { version = "=3.0.0" }
+lance-encoding = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { version = "=3.0.0" }
+lance-arrow = { "version" = "=4.0.0-beta.12", "tag" = "v4.0.0-beta.12", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }

docker-compose.yml

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

docs/src/js/classes/Table.md

@@ -485,7 +485,19 @@ Modeled after ``VACUUM`` in PostgreSQL.
  - Prune: Removes old versions of the dataset
  - Index: Optimizes the indices, adding new data to existing indices
 
- The frequency an application should call optimize is based on the frequency of
+ Experimental API
+ ----------------
+
+ The optimization process is undergoing active development and may change.
+ Our goal with these changes is to improve the performance of optimization and
+ reduce the complexity.
+
+ That being said, it is essential today to run optimize if you want the best
+ performance.  It should be stable and safe to use in production, but it our
+ hope that the API may be simplified (or not even need to be called) in the
+ future.
+
+ The frequency an application shoudl call optimize is based on the frequency of
  data modifications.  If data is frequently added, deleted, or updated then
  optimize should be run frequently.  A good rule of thumb is to run optimize if
  you have added or modified 100,000 or more records or run more than 20 data

docs/src/js/interfaces/OptimizeOptions.md

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

java/pom.xml

@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>3.1.0-beta.2</lance-core.version>
+        <lance-core.version>4.0.0-beta.12</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>

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.30.0"
+current_version = "0.30.0-beta.5"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.30.0"
+version = "0.30.0-beta.5"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/python/tests/test_namespace_integration.py

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