Bump version: 0.22.1-beta.6 → 0.22.1

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- **Chores**
- Updated workspace dependencies to use a stable release version for
improved consistency and reliability. No changes to application features
or functionality.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.19.1-beta.1"
+current_version = "0.19.1-beta.5"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/rust.yml

@@ -40,6 +40,9 @@ jobs:
         with:
           fetch-depth: 0
           lfs: true
+      - uses: actions-rust-lang/setup-rust-toolchain@v1
+        with:
+          components: rustfmt, clippy
       - uses: Swatinem/rust-cache@v2
         with:
           workspaces: rust

Cargo.lock

@@ -223,7 +223,7 @@ dependencies = [
  "chrono",
  "chrono-tz 0.10.3",
  "half",
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
  "num",
 ]
 
@@ -602,9 +602,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-bedrockruntime"
-version = "1.85.0"
+version = "1.86.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6f6c003cd82739447a18d7616468b047341c125efff11fdafc77a5e777a861c9"
+checksum = "db14a0566037a6c686ef075c406dec4b067537af3d76950522e9e89848ce7a5a"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -628,9 +628,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-dynamodb"
-version = "1.72.1"
+version = "1.73.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b14d5b5d6849d1caa7b404ea57cbe25ed8ba25c3c7d47f45bcbd5b51e098ceac"
+checksum = "8d954f3581bd7254f42bbaa3a21dfd99d40a14d82a324d2012b8f3ea0d15f12b"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -651,9 +651,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-kms"
-version = "1.66.0"
+version = "1.67.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "655097cd83ab1f15575890943135192560f77097413c6dd1733fdbdc453e81ac"
+checksum = "2b650cf9e1e153ab13acd3aa1f73b271dac14e019353ec0b0c176f24a21bad03"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -674,9 +674,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-s3"
-version = "1.83.0"
+version = "1.84.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "51384750334005f40e1a334b0d54eca822a77eacdcf3c50fdf38f583c5eee7a2"
+checksum = "2111975ef21dc06542918479df0df861b273eb8d99e6bb987da469b546dce32c"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -709,9 +709,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-sso"
-version = "1.65.0"
+version = "1.66.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8efec445fb78df585327094fcef4cad895b154b58711e504db7a93c41aa27151"
+checksum = "858007b14d0f1ade2e0124473c2126b24d334dc9486ad12eb7c0ed14757be464"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -732,9 +732,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-ssooidc"
-version = "1.66.0"
+version = "1.67.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5e49cca619c10e7b002dc8e66928ceed66ab7f56c1a3be86c5437bf2d8d89bba"
+checksum = "b83abf3ae8bd10a014933cc2383964a12ca5a3ebbe1948ad26b1b808e7d0d1f2"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -755,9 +755,9 @@ dependencies = [
 
 [[package]]
 name = "aws-sdk-sts"
-version = "1.66.0"
+version = "1.67.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7420479eac0a53f776cc8f0d493841ffe58ad9d9783f3947be7265784471b47a"
+checksum = "74e8e9ac4a837859c8f1d747054172e1e55933f02ed34728b0b34dea0591ec84"
 dependencies = [
  "aws-credential-types",
  "aws-runtime",
@@ -879,7 +879,7 @@ dependencies = [
  "aws-smithy-async",
  "aws-smithy-runtime-api",
  "aws-smithy-types",
- "h2 0.4.9",
+ "h2 0.4.10",
  "http 0.2.12",
  "http 1.3.1",
  "http-body 0.4.6",
@@ -890,7 +890,7 @@ dependencies = [
  "hyper-util",
  "pin-project-lite",
  "rustls 0.21.12",
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.1",
  "rustls-pki-types",
  "tokio",
@@ -1326,9 +1326,9 @@ dependencies = [
 
 [[package]]
 name = "cc"
-version = "1.2.20"
+version = "1.2.21"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "04da6a0d40b948dfc4fa8f5bbf402b0fc1a64a28dbf7d12ffd683550f2c1b63a"
+checksum = "8691782945451c1c383942c4874dbe63814f61cb57ef773cda2972682b7bb3c0"
 dependencies = [
  "jobserver",
  "libc",
@@ -2737,8 +2737,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1b054c0eaa0f92df393e53cb42e3cc01e6f73bc601252f683eb63ddcc552f3ff"
 dependencies = [
  "rand 0.8.5",
 ]
@@ -3065,9 +3066,9 @@ dependencies = [
 
 [[package]]
 name = "h2"
-version = "0.4.9"
+version = "0.4.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "75249d144030531f8dee69fe9cea04d3edf809a017ae445e2abdff6629e86633"
+checksum = "a9421a676d1b147b16b82c9225157dc629087ef8ec4d5e2960f9437a90dac0a5"
 dependencies = [
  "atomic-waker",
  "bytes",
@@ -3115,9 +3116,9 @@ dependencies = [
 
 [[package]]
 name = "hashbrown"
-version = "0.15.2"
+version = "0.15.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bf151400ff0baff5465007dd2f3e717f3fe502074ca563069ce3a6629d07b289"
+checksum = "84b26c544d002229e640969970a2e74021aadf6e2f96372b9c58eff97de08eb3"
 dependencies = [
  "allocator-api2",
  "equivalent",
@@ -3302,7 +3303,7 @@ dependencies = [
  "bytes",
  "futures-channel",
  "futures-util",
- "h2 0.4.9",
+ "h2 0.4.10",
  "http 1.3.1",
  "http-body 1.0.1",
  "httparse",
@@ -3339,7 +3340,7 @@ dependencies = [
  "http 1.3.1",
  "hyper 1.6.0",
  "hyper-util",
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.1",
  "rustls-pki-types",
  "tokio",
@@ -3564,7 +3565,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "cea70ddb795996207ad57735b50c5982d8844f38ba9ee5f1aedcfb708a2aa11e"
 dependencies = [
  "equivalent",
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
  "serde",
 ]
 
@@ -3661,9 +3662,9 @@ checksum = "9028f49264629065d057f340a86acb84867925865f73bbf8d47b4d149a7e88b8"
 
 [[package]]
 name = "jiff"
-version = "0.2.10"
+version = "0.2.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5a064218214dc6a10fbae5ec5fa888d80c45d611aba169222fc272072bf7aef6"
+checksum = "f02000660d30638906021176af16b17498bd0d12813dbfe7b276d8bc7f3c0806"
 dependencies = [
  "jiff-static",
  "log",
@@ -3674,9 +3675,9 @@ dependencies = [
 
 [[package]]
 name = "jiff-static"
-version = "0.2.10"
+version = "0.2.13"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "199b7932d97e325aff3a7030e141eafe7f2c6268e1d1b24859b753a627f45254"
+checksum = "f3c30758ddd7188629c6713fc45d1188af4f44c90582311d0c8d8c9907f60c48"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -3727,8 +3728,9 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4df828dc75fdfc665846a9bb91b882801f2092ac9a5c54cdc99c155b86b97ed"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -3752,6 +3754,7 @@ dependencies = [
  "datafusion-expr",
  "datafusion-functions",
  "datafusion-physical-expr",
+ "datafusion-physical-plan",
  "deepsize",
  "either",
  "futures",
@@ -3790,8 +3793,9 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "270c34ececc4e2603e50dab07ac3ba21a81fe390dcf00ee62b31a844b6cabe25"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3808,8 +3812,9 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8860c76dc32d649cd0460fbc23e612390263de814f5918210166ee6ce26886e9"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3845,8 +3850,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "494e614227a31a01a2a8ca0f151fd53db7f041a856d15514696af63d075867f6"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3875,8 +3881,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "34faee15ed02126597522f36cdc9b5134d1411f512f31ab7ca65e5ab5e111b37"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3891,8 +3898,9 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fb705919e46ea1784c048d798d2e408b2ae703dfdc67e128177e2ee9bb405b31"
 dependencies = [
  "arrayref",
  "arrow",
@@ -3931,8 +3939,9 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "aefcde20c6a27f767072f9239af70da5e744187ec7f3c7bebcb33705b4c01834"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -3966,8 +3975,9 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "82678b7035c9041010c74f789a18a63b192c518699217c69e4a83512b67bcbd5"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4020,8 +4030,9 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e2abb629dab01c7e639d9da2f83b36fb9b8ff7e971312b7363cd49a4d7c67276"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4050,6 +4061,7 @@ dependencies = [
  "pin-project",
  "prost",
  "rand 0.8.5",
+ "serde",
  "shellexpand",
  "snafu",
  "tokio",
@@ -4059,8 +4071,9 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "91f6172d9f7c6105afcee8edd92165d0bfdff68dd6c622a58985eea445f309cb"
 dependencies = [
  "arrow-array",
  "arrow-ord",
@@ -4083,8 +4096,9 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f7831c0d784e2c876dbaf39a041c9174bc888206e2d5ef515bc3917dd78a27ec"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4123,8 +4137,9 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "0.27.0"
+version = "0.27.2"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.27.0-beta.2#cf903b470be1aaff2998830bd0358226f27f4185"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2f37690b1e8dbabedda366803b6481d0b442dd70234406bd746eb0a9aaf25dfb"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4135,7 +4150,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.19.1-beta.1"
+version = "0.19.1-beta.5"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4222,7 +4237,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-node"
-version = "0.19.1-beta.1"
+version = "0.19.1-beta.5"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4247,7 +4262,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.19.1-beta.1"
+version = "0.19.1-beta.5"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4266,7 +4281,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.22.1-beta.1"
+version = "0.22.1-beta.5"
 dependencies = [
  "arrow",
  "env_logger",
@@ -4389,9 +4404,9 @@ dependencies = [
 
 [[package]]
 name = "libm"
-version = "0.2.13"
+version = "0.2.14"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c9627da5196e5d8ed0b0495e61e518847578da83483c37288316d9b2e03a7f72"
+checksum = "a25169bd5913a4b437588a7e3d127cd6e90127b60e0ffbd834a38f1599e016b8"
 
 [[package]]
 name = "libredox"
@@ -4456,7 +4471,7 @@ version = "0.12.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "234cf4f4a04dc1f57e24b96cc0cd600cf2af460d4161ac5ecdd0af8e1f3b2a38"
 dependencies = [
- "hashbrown 0.15.2",
+ "hashbrown 0.15.3",
 ]
 
 [[package]]
@@ -5848,7 +5863,7 @@ dependencies = [
  "quinn-proto",
  "quinn-udp",
  "rustc-hash 2.1.1",
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "socket2",
  "thiserror 2.0.12",
  "tokio",
@@ -5867,7 +5882,7 @@ dependencies = [
  "rand 0.9.1",
  "ring",
  "rustc-hash 2.1.1",
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "rustls-pki-types",
  "slab",
  "thiserror 2.0.12",
@@ -5878,9 +5893,9 @@ dependencies = [
 
 [[package]]
 name = "quinn-udp"
-version = "0.5.11"
+version = "0.5.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "541d0f57c6ec747a90738a52741d3221f7960e8ac2f0ff4b1a63680e033b4ab5"
+checksum = "ee4e529991f949c5e25755532370b8af5d114acae52326361d68d47af64aa842"
 dependencies = [
  "cfg_aliases",
  "libc",
@@ -6086,9 +6101,9 @@ dependencies = [
 
 [[package]]
 name = "redox_syscall"
-version = "0.5.11"
+version = "0.5.12"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d2f103c6d277498fbceb16e84d317e2a400f160f46904d5f5410848c829511a3"
+checksum = "928fca9cf2aa042393a8325b9ead81d2f0df4cb12e1e24cef072922ccd99c5af"
 dependencies = [
  "bitflags 2.9.0",
 ]
@@ -6183,7 +6198,7 @@ dependencies = [
  "encoding_rs",
  "futures-core",
  "futures-util",
- "h2 0.4.9",
+ "h2 0.4.10",
  "http 1.3.1",
  "http-body 1.0.1",
  "http-body-util",
@@ -6199,7 +6214,7 @@ dependencies = [
  "percent-encoding",
  "pin-project-lite",
  "quinn",
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "rustls-native-certs 0.8.1",
  "rustls-pemfile 2.2.0",
  "rustls-pki-types",
@@ -6355,9 +6370,9 @@ dependencies = [
 
 [[package]]
 name = "rustix"
-version = "1.0.5"
+version = "1.0.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d97817398dd4bb2e6da002002db259209759911da105da92bec29ccb12cf58bf"
+checksum = "c71e83d6afe7ff64890ec6b71d6a69bb8a610ab78ce364b3352876bb4c801266"
 dependencies = [
  "bitflags 2.9.0",
  "errno",
@@ -6380,16 +6395,16 @@ dependencies = [
 
 [[package]]
 name = "rustls"
-version = "0.23.26"
+version = "0.23.27"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "df51b5869f3a441595eac5e8ff14d486ff285f7b8c0df8770e49c3b56351f0f0"
+checksum = "730944ca083c1c233a75c09f199e973ca499344a2b7ba9e755c457e86fb4a321"
 dependencies = [
  "aws-lc-rs",
  "log",
  "once_cell",
  "ring",
  "rustls-pki-types",
- "rustls-webpki 0.103.1",
+ "rustls-webpki 0.103.2",
  "subtle",
  "zeroize",
 ]
@@ -6457,9 +6472,9 @@ dependencies = [
 
 [[package]]
 name = "rustls-webpki"
-version = "0.103.1"
+version = "0.103.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fef8b8769aaccf73098557a87cd1816b4f9c7c16811c9c77142aa695c16f2c03"
+checksum = "7149975849f1abb3832b246010ef62ccc80d3a76169517ada7188252b9cfb437"
 dependencies = [
  "aws-lc-rs",
  "ring",
@@ -6712,9 +6727,9 @@ dependencies = [
 
 [[package]]
 name = "sha2"
-version = "0.10.8"
+version = "0.10.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "793db75ad2bcafc3ffa7c68b215fee268f537982cd901d132f89c6343f3a3dc8"
+checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
 dependencies = [
  "cfg-if",
  "cpufeatures",
@@ -7033,9 +7048,9 @@ dependencies = [
 
 [[package]]
 name = "synstructure"
-version = "0.13.1"
+version = "0.13.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
+checksum = "728a70f3dbaf5bab7f0c4b1ac8d7ae5ea60a4b5549c8a5914361c99147a709d2"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -7265,7 +7280,7 @@ dependencies = [
  "fastrand",
  "getrandom 0.3.2",
  "once_cell",
- "rustix 1.0.5",
+ "rustix 1.0.7",
  "windows-sys 0.59.0",
 ]
 
@@ -7460,7 +7475,7 @@ version = "0.26.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8e727b36a1a0e8b74c376ac2211e40c2c8af09fb4013c60d910495810f008e9b"
 dependencies = [
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "tokio",
 ]
 
@@ -7685,7 +7700,7 @@ dependencies = [
  "flate2",
  "log",
  "once_cell",
- "rustls 0.23.26",
+ "rustls 0.23.27",
  "rustls-pki-types",
  "serde",
  "serde_json",
@@ -7905,9 +7920,9 @@ dependencies = [
 
 [[package]]
 name = "webpki-roots"
-version = "0.26.9"
+version = "0.26.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "29aad86cec885cafd03e8305fd727c418e970a521322c91688414d5b8efba16b"
+checksum = "37493cadf42a2a939ed404698ded7fb378bf301b5011f973361779a3a74f8c93"
 dependencies = [
  "rustls-pki-types",
 ]
@@ -8397,9 +8412,9 @@ checksum = "271414315aff87387382ec3d271b52d7ae78726f5d44ac98b4f4030c91880486"
 
 [[package]]
 name = "winnow"
-version = "0.7.7"
+version = "0.7.9"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6cb8234a863ea0e8cd7284fcdd4f145233eb00fee02bbdd9861aec44e6477bc5"
+checksum = "d9fb597c990f03753e08d3c29efbfcf2019a003b4bf4ba19225c158e1549f0f3"
 dependencies = [
  "memchr",
 ]

Cargo.toml

@@ -21,14 +21,14 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.27.0", "features" = ["dynamodb"], tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance = { "version" = "=0.27.2", "features" = ["dynamodb"] }
-lance-io = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-io = { version = "=0.27.2" }
-lance-index = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-index = { version = "=0.27.2" }
-lance-linalg = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-linalg = { version = "=0.27.2" }
-lance-table = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-table = { version = "=0.27.2" }
-lance-testing = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-testing = { version = "=0.27.2" }
-lance-datafusion = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-datafusion = { version = "=0.27.2" }
-lance-encoding = { version = "=0.27.0", tag = "v0.27.0-beta.2", git="https://github.com/lancedb/lance.git" }
+lance-encoding = { version = "=0.27.2" }
 # Note that this one does not include pyarrow
 arrow = { version = "54.1", optional = false }
 arrow-array = "54.1"
@@ -61,15 +61,12 @@ rand = "0.8"
 regex = "1.10"
 lazy_static = "1"
 semver = "1.0.25"
-
 # Temporary pins to work around downstream issues
 # https://github.com/apache/arrow-rs/commit/2fddf85afcd20110ce783ed5b4cdeb82293da30b
 chrono = "=0.4.39"
 # https://github.com/RustCrypto/formats/issues/1684
 base64ct = "=1.6.0"
-
 # Workaround for: https://github.com/eira-fransham/crunchy/issues/13
 crunchy = "=0.2.2"
-
 # Workaround for: https://github.com/Lokathor/bytemuck/issues/306
 bytemuck_derive = ">=1.8.1, <1.9.0"

docs/mkdocs.yml

@@ -205,6 +205,7 @@ nav:
           - PromptTools: integrations/prompttools.md
           - dlt: integrations/dlt.md
           - phidata: integrations/phidata.md
+          - Genkit: integrations/genkit.md
       - 🎯 Examples:
           - Overview: examples/index.md
           - 🐍 Python:
@@ -331,6 +332,7 @@ nav:
       - PromptTools: integrations/prompttools.md
       - dlt: integrations/dlt.md
       - phidata: integrations/phidata.md
+      - Genkit: integrations/genkit.md
   - Examples:
       - examples/index.md
       - 🐍 Python:

docs/src/integrations/genkit.md

@@ -0,0 +1,183 @@
+### genkitx-lancedb
+This is a lancedb plugin for genkit framework. It allows you to use LanceDB for ingesting and rereiving data using genkit framework.
+
+![integration-banner-genkit](https://github.com/user-attachments/assets/a6cc28af-98e9-4425-b87c-7ab139bd7893)
+
+### Installation
+```bash
+pnpm install genkitx-lancedb
+```
+
+### Usage
+
+Adding LanceDB plugin to your genkit instance.
+
+```ts
+import { lancedbIndexerRef, lancedb, lancedbRetrieverRef, WriteMode } from 'genkitx-lancedb';
+import { textEmbedding004, vertexAI } from '@genkit-ai/vertexai';
+import { gemini } from '@genkit-ai/vertexai';
+import { z, genkit } from 'genkit';
+import { Document } from 'genkit/retriever';
+import { chunk } from 'llm-chunk';
+import { readFile } from 'fs/promises';
+import path from 'path';
+import pdf from 'pdf-parse/lib/pdf-parse';
+
+const ai = genkit({
+  plugins: [
+    // vertexAI provides the textEmbedding004 embedder
+    vertexAI(),
+
+    // the local vector store requires an embedder to translate from text to vector
+    lancedb([
+      {
+        dbUri: '.db', // optional lancedb uri, default to .db
+        tableName: 'table', // optional table name, default to table
+        embedder: textEmbedding004,
+      },
+    ]),
+  ],
+});
+```
+
+You can run this app with the following command:
+```bash
+genkit start -- tsx --watch src/index.ts
+```
+
+This'll add LanceDB as a retriever and indexer to the genkit instance. You can see it in the GUI view
+<img width="1710" alt="Screenshot 2025-05-11 at 7 21 05 PM" src="https://github.com/user-attachments/assets/e752f7f4-785b-4797-a11e-72ab06a531b7" />
+
+**Testing retrieval on a sample table**
+Let's see the raw retrieval results
+
+<img width="1710" alt="Screenshot 2025-05-11 at 7 21 05 PM" src="https://github.com/user-attachments/assets/b8d356ed-8421-4790-8fc0-d6af563b9657" />
+On running this query, you'll 5 results fetched from the lancedb table, where each result looks something like this:
+<img width="1417" alt="Screenshot 2025-05-11 at 7 21 18 PM" src="https://github.com/user-attachments/assets/77429525-36e2-4da6-a694-e58c1cf9eb83" />
+
+
+
+## Creating a custom RAG flow
+
+Now that we've seen how you can use LanceDB for in a genkit pipeline, let's refine the flow and create a RAG. A RAG flow will consist of an index and a retreiver with its outputs postprocessed an fed into an LLM for final response
+
+### Creating custom indexer flows
+You can also create custom indexer flows, utilizing more options and features provided by LanceDB.
+
+```ts
+export const menuPdfIndexer = lancedbIndexerRef({
+   // Using all defaults, for dbUri, tableName, and embedder, etc
+});
+
+const chunkingConfig = {
+  minLength: 1000,
+  maxLength: 2000,
+  splitter: 'sentence',
+  overlap: 100,
+  delimiters: '',
+} as any;
+
+
+async function extractTextFromPdf(filePath: string) {
+  const pdfFile = path.resolve(filePath);
+  const dataBuffer = await readFile(pdfFile);
+  const data = await pdf(dataBuffer);
+  return data.text;
+}
+
+export const indexMenu = ai.defineFlow(
+  {
+    name: 'indexMenu',
+    inputSchema: z.string().describe('PDF file path'),
+    outputSchema: z.void(),
+  },
+  async (filePath: string) => {
+    filePath = path.resolve(filePath);
+
+    // Read the pdf.
+    const pdfTxt = await ai.run('extract-text', () =>
+      extractTextFromPdf(filePath)
+    );
+
+    // Divide the pdf text into segments.
+    const chunks = await ai.run('chunk-it', async () =>
+      chunk(pdfTxt, chunkingConfig)
+    );
+
+    // Convert chunks of text into documents to store in the index.
+    const documents = chunks.map((text) => {
+      return Document.fromText(text, { filePath });
+    });
+
+    // Add documents to the index.
+    await ai.index({
+      indexer: menuPdfIndexer,
+      documents,
+      options: {
+        writeMode: WriteMode.Overwrite,
+      } as any
+    });
+  }
+);
+```
+
+<img width="1316" alt="Screenshot 2025-05-11 at 8 35 56 PM" src="https://github.com/user-attachments/assets/e2a20ce4-d1d0-4fa2-9a84-f2cc26e3a29f" />
+
+In your console, you can see the logs
+
+<img width="511" alt="Screenshot 2025-05-11 at 7 19 14 PM" src="https://github.com/user-attachments/assets/243f26c5-ed38-40b6-b661-002f40f0423a" />
+
+### Creating custom retriever flows
+You can also create custom retriever flows, utilizing more options and features provided by LanceDB.
+```ts
+export const menuRetriever = lancedbRetrieverRef({
+  tableName: "table", // Use the same table name as the indexer.
+  displayName: "Menu", // Use a custom display name.
+
+export const menuQAFlow = ai.defineFlow(
+  { name: "Menu", inputSchema: z.string(), outputSchema: z.string() },
+  async (input: string) => {
+    // retrieve relevant documents
+    const docs = await ai.retrieve({
+      retriever: menuRetriever,
+      query: input,
+      options: { 
+        k: 3,
+      },
+    });
+
+    const extractedContent = docs.map(doc => {
+      if (doc.content && Array.isArray(doc.content) && doc.content.length > 0) {
+        if (doc.content[0].media && doc.content[0].media.url) {
+          return doc.content[0].media.url;
+        }
+      }
+      return "No content found";
+    });
+
+    console.log("Extracted content:", extractedContent);
+
+    const { text } = await ai.generate({
+      model: gemini('gemini-2.0-flash'),
+      prompt: `
+You are acting as a helpful AI assistant that can answer 
+questions about the food available on the menu at Genkit Grub Pub.
+
+Use only the context provided to answer the question.
+If you don't know, do not make up an answer.
+Do not add or change items on the menu.
+
+Context:
+${extractedContent.join('\n\n')}
+
+Question: ${input}`,
+      docs,
+    });
+    
+    return text;
+  }
+);
+```
+Now using our retrieval flow, we can ask question about the ingsted PDF
+<img width="1306" alt="Screenshot 2025-05-11 at 7 18 45 PM" src="https://github.com/user-attachments/assets/86c66b13-7c12-4d5f-9d81-ae36bfb1c346" />
+

docs/src/js/classes/MergeInsertBuilder.md

@@ -33,7 +33,7 @@ Construct a MergeInsertBuilder. __Internal use only.__
 ### execute()
 
 ```ts
-execute(data): Promise<MergeResult>
+execute(data, execOptions?): Promise<MergeResult>
 ```
 
 Executes the merge insert operation
@@ -42,6 +42,8 @@ Executes the merge insert operation
 
 * **data**: [`Data`](../type-aliases/Data.md)
 
+* **execOptions?**: `Partial`&lt;[`WriteExecutionOptions`](../interfaces/WriteExecutionOptions.md)&gt;
+
 #### Returns
 
 `Promise`&lt;[`MergeResult`](../interfaces/MergeResult.md)&gt;

docs/src/js/globals.md

@@ -72,6 +72,7 @@
 - [UpdateOptions](interfaces/UpdateOptions.md)
 - [UpdateResult](interfaces/UpdateResult.md)
 - [Version](interfaces/Version.md)
+- [WriteExecutionOptions](interfaces/WriteExecutionOptions.md)
 
 ## Type Aliases
 

docs/src/js/interfaces/WriteExecutionOptions.md

@@ -0,0 +1,26 @@
+[**@lancedb/lancedb**](../README.md) • **Docs**
+
+***
+
+[@lancedb/lancedb](../globals.md) / WriteExecutionOptions
+
+# Interface: WriteExecutionOptions
+
+## Properties
+
+### timeoutMs?
+
+```ts
+optional timeoutMs: number;
+```
+
+Maximum time to run the operation before cancelling it.
+
+By default, there is a 30-second timeout that is only enforced after the
+first attempt. This is to prevent spending too long retrying to resolve
+conflicts. For example, if a write attempt takes 20 seconds and fails,
+the second attempt will be cancelled after 10 seconds, hitting the
+30-second timeout. However, a write that takes one hour and succeeds on the
+first attempt will not be cancelled.
+
+When this is set, the timeout is enforced on all attempts, including the first.

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.19.1-beta.1</version>
+        <version>0.19.1-beta.5</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.19.1-beta.1</version>
+    <version>0.19.1-beta.5</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.19.1-beta.1",
+  "version": "0.19.1-beta.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.1",
+        "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.5",
-        "@lancedb/vectordb-darwin-x64": "0.19.1-beta.1",
+        "@lancedb/vectordb-darwin-x64": "0.19.1-beta.5",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.1",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.5",
-        "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.1",
+        "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.5",
-        "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.1"
+        "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.5"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -327,9 +327,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.1-beta.1.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.1-beta.5.tgz",
-      "integrity": "sha512-Epvel0pF5TM6MtIWQ2KhqezqSSHTL3Wr7a2rGAwz6X/XY23i6DbMPpPs0HyeIDzDrhxNfE3cz3S+SiCA6xpR0g==",
+      "integrity": "sha512-9WcTw67We5HYGayDt5jFquGoyAVzFSt/I65ag8+q7H9q4ZYKxeDhgNyQZJ8BmXEvbJtnYtYBSAtTEdFKYMce6w==",
       "cpu": [
         "arm64"
       ],
@@ -340,9 +340,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.1-beta.1.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.1-beta.5.tgz",
-      "integrity": "sha512-hOiUSlIoISbiXytp46hToi/r6sF5pImAsfbzCsIq8ExDV4TPa8fjbhcIT80vxxOwc2mpSSK4HsVJYod95RSbEQ==",
+      "integrity": "sha512-6Pe3PxEMi0VKGsu5R7IhOxTijUM3b5olRAqhxfcu5ti34gXIPNtu7g+T9lS78LKe+0D0v2BjZEY/JQakIFBNRw==",
       "cpu": [
         "x64"
       ],
@@ -353,9 +353,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.1-beta.1.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.1-beta.5.tgz",
-      "integrity": "sha512-/1JhGVDEngwrlM8o2TNW8G6nJ9U/VgHKAORmj/cTA7O30helJIoo9jfvUAUy+vZ4VoEwRXQbMI+gaYTg0l3MTg==",
+      "integrity": "sha512-VJbBd+Y+6L2SREaOO1OzuUfTPHXyHE4AcsZuM6VMyoeX8k7lPnaA+vNk96o0w4V2KFEAI6o4QPgrRAXmMAzmbg==",
       "cpu": [
         "arm64"
       ],
@@ -366,9 +366,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.1-beta.1.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.1-beta.5.tgz",
-      "integrity": "sha512-zNRGSSUt8nTJMmll4NdxhQjwxR8Rezq3T4dsRoiDts5ienMam5HFjYiZ3FkDZQo16rgq2BcbFuH1G8u1chywlg==",
+      "integrity": "sha512-3wS8Zn5NmHoszXfrY4JzMimHoh5LAmVi3pTX4gD+C9kVGoUJcDBP7/CrAbjnAz7VzzAIPmz8kvBuPz8l9X4hjw==",
       "cpu": [
         "x64"
       ],
@@ -379,9 +379,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.1-beta.1.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.1-beta.5.tgz",
-      "integrity": "sha512-yV550AJGlsIFdm1KoHQPJ1TZx121ZXCIdebBtBZj3wOObIhyB/i0kZAtGvwjkmr7EYyfzt1EHZzbjSGVdehIAA==",
+      "integrity": "sha512-TemM9cvrPa2jFCjvYmKnrL0DTHegi/+LOQ3No9nPDHie2ka2fM9O2q60fAbYsYz+Mo9aV7MvL49ATbNCyl9MLA==",
       "cpu": [
         "x64"
       ],

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.19.1-beta.1",
+  "version": "0.19.1-beta.5",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -89,10 +89,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.19.1-beta.1",
+    "@lancedb/vectordb-darwin-x64": "0.19.1-beta.5",
-    "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.1",
+    "@lancedb/vectordb-darwin-arm64": "0.19.1-beta.5",
-    "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.1",
+    "@lancedb/vectordb-linux-x64-gnu": "0.19.1-beta.5",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.1",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.19.1-beta.5",
-    "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.1"
+    "@lancedb/vectordb-win32-x64-msvc": "0.19.1-beta.5"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.19.1-beta.1"
+version = "0.19.1-beta.5"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/__test__/table.test.ts

@@ -349,7 +349,7 @@ describe("merge insert", () => {
       .mergeInsert("a")
       .whenMatchedUpdateAll()
       .whenNotMatchedInsertAll()
-      .execute(newData);
+      .execute(newData, { timeoutMs: 10_000 });
     expect(mergeInsertRes).toHaveProperty("version");
     expect(mergeInsertRes.version).toBe(2);
     expect(mergeInsertRes.numInsertedRows).toBe(1);
@@ -463,6 +463,20 @@ describe("merge insert", () => {
     res = res.sort((a, b) => a.a - b.a);
     expect(res).toEqual(expected);
   });
+
+  test("timeout", async () => {
+    const newData = [
+      { a: 2, b: "x" },
+      { a: 4, b: "z" },
+    ];
+    await expect(
+      table
+        .mergeInsert("a")
+        .whenMatchedUpdateAll()
+        .whenNotMatchedInsertAll()
+        .execute(newData, { timeoutMs: 0 }),
+    ).rejects.toThrow("merge insert timed out");
+  });
 });
 
 describe("When creating an index", () => {
@@ -1287,6 +1301,32 @@ describe("when dealing with tags", () => {
     await table.checkoutLatest();
     expect(await table.version()).toBe(4);
   });
+
+  it("can checkout and restore tags", async () => {
+    const conn = await connect(tmpDir.name, {
+      readConsistencyInterval: 0,
+    });
+
+    const table = await conn.createTable("my_table", [
+      { id: 1n, vector: [0.1, 0.2] },
+    ]);
+    expect(await table.version()).toBe(1);
+    expect(await table.countRows()).toBe(1);
+    const tagsManager = await table.tags();
+    const tag1 = "tag1";
+    await tagsManager.create(tag1, 1);
+    await table.add([{ id: 2n, vector: [0.3, 0.4] }]);
+    const tag2 = "tag2";
+    await tagsManager.create(tag2, 2);
+    expect(await table.version()).toBe(2);
+    await table.checkout(tag1);
+    expect(await table.version()).toBe(1);
+    await table.restore();
+    expect(await table.version()).toBe(3);
+    expect(await table.countRows()).toBe(1);
+    await table.add([{ id: 3n, vector: [0.5, 0.6] }]);
+    expect(await table.countRows()).toBe(2);
+  });
 });
 
 describe("when optimizing a dataset", () => {

nodejs/lancedb/index.ts

@@ -86,7 +86,7 @@ export {
   ColumnAlteration,
 } from "./table";
 
-export { MergeInsertBuilder } from "./merge";
+export { MergeInsertBuilder, WriteExecutionOptions } from "./merge";
 
 export * as embedding from "./embedding";
 export * as rerankers from "./rerankers";

nodejs/lancedb/merge.ts

@@ -75,7 +75,10 @@ export class MergeInsertBuilder {
    *
    * @returns {Promise<MergeResult>} the merge result
    */
-  async execute(data: Data): Promise<MergeResult> {
+  async execute(
+    data: Data,
+    execOptions?: Partial<WriteExecutionOptions>,
+  ): Promise<MergeResult> {
     let schema: Schema;
     if (this.#schema instanceof Promise) {
       schema = await this.#schema;
@@ -83,7 +86,28 @@ export class MergeInsertBuilder {
     } else {
       schema = this.#schema;
     }
+
+    if (execOptions?.timeoutMs !== undefined) {
+      this.#native.setTimeout(execOptions.timeoutMs);
+    }
+
     const buffer = await fromDataToBuffer(data, undefined, schema);
     return await this.#native.execute(buffer);
   }
 }
+
+export interface WriteExecutionOptions {
+  /**
+   * Maximum time to run the operation before cancelling it.
+   *
+   * By default, there is a 30-second timeout that is only enforced after the
+   * first attempt. This is to prevent spending too long retrying to resolve
+   * conflicts. For example, if a write attempt takes 20 seconds and fails,
+   * the second attempt will be cancelled after 10 seconds, hitting the
+   * 30-second timeout. However, a write that takes one hour and succeeds on the
+   * first attempt will not be cancelled.
+   *
+   * When this is set, the timeout is enforced on all attempts, including the first.
+   */
+  timeoutMs?: number;
+}

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"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": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"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": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"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": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"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": "0.19.1-beta.1",
+  "version": "0.19.1-beta.5",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.19.1-beta.1",
+	"version": "0.19.1-beta.5",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.19.1-beta.1",
+  "version": "0.19.1-beta.5",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.19.1-beta.1",
+      "version": "0.19.1-beta.5",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.19.1-beta.1",
+  "version": "0.19.1-beta.5",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/merge.rs

@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
+use std::time::Duration;
+
 use lancedb::{arrow::IntoArrow, ipc::ipc_file_to_batches, table::merge::MergeInsertBuilder};
 use napi::bindgen_prelude::*;
 use napi_derive::napi;
@@ -36,6 +38,11 @@ impl NativeMergeInsertBuilder {
         this
     }
 
+    #[napi]
+    pub fn set_timeout(&mut self, timeout: u32) {
+        self.inner.timeout(Duration::from_millis(timeout as u64));
+    }
+
     #[napi(catch_unwind)]
     pub async fn execute(&self, buf: Buffer) -> napi::Result<MergeResult> {
         let data = ipc_file_to_batches(buf.to_vec())

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.1-beta.2"
+current_version = "0.22.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.22.1-beta.2"
+version = "0.22.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/python/lancedb/_lancedb.pyi

@@ -51,7 +51,7 @@ class Table:
     async def version(self) -> int: ...
     async def checkout(self, version: Union[int, str]): ...
     async def checkout_latest(self): ...
-    async def restore(self, version: Optional[int] = None): ...
+    async def restore(self, version: Optional[Union[int, str]] = None): ...
     async def list_indices(self) -> list[IndexConfig]: ...
     async def delete(self, filter: str) -> DeleteResult: ...
     async def add_columns(self, columns: list[tuple[str, str]]) -> AddColumnsResult: ...

python/python/lancedb/merge.py

@@ -4,6 +4,7 @@
 
 from __future__ import annotations
 
+from datetime import timedelta
 from typing import TYPE_CHECKING, List, Optional
 
 if TYPE_CHECKING:
@@ -31,6 +32,7 @@ class LanceMergeInsertBuilder(object):
         self._when_not_matched_insert_all = False
         self._when_not_matched_by_source_delete = False
         self._when_not_matched_by_source_condition = None
+        self._timeout = None
 
     def when_matched_update_all(
         self, *, where: Optional[str] = None
@@ -81,6 +83,7 @@ class LanceMergeInsertBuilder(object):
         new_data: DATA,
         on_bad_vectors: str = "error",
         fill_value: float = 0.0,
+        timeout: Optional[timedelta] = None,
     ) -> MergeInsertResult:
         """
         Executes the merge insert operation
@@ -98,10 +101,24 @@ class LanceMergeInsertBuilder(object):
             One of "error", "drop", "fill".
         fill_value: float, default 0.
             The value to use when filling vectors. Only used if on_bad_vectors="fill".
+        timeout: Optional[timedelta], default None
+            Maximum time to run the operation before cancelling it.
+
+            By default, there is a 30-second timeout that is only enforced after the
+            first attempt. This is to prevent spending too long retrying to resolve
+            conflicts. For example, if a write attempt takes 20 seconds and fails,
+            the second attempt will be cancelled after 10 seconds, hitting the
+            30-second timeout. However, a write that takes one hour and succeeds on the
+            first attempt will not be cancelled.
+
+            When this is set, the timeout is enforced on all attempts, including
+            the first.
 
         Returns
         -------
         MergeInsertResult
             version: the new version number of the table after doing merge insert.
         """
+        if timeout is not None:
+            self._timeout = timeout
         return self._table._do_merge(self, new_data, on_bad_vectors, fill_value)

python/python/lancedb/remote/table.py

@@ -47,9 +47,6 @@ class RemoteTable(Table):
     def __repr__(self) -> str:
         return f"RemoteTable({self.db_name}.{self.name})"
 
-    def __len__(self) -> int:
-        self.count_rows(None)
-
     @property
     def schema(self) -> pa.Schema:
         """The [Arrow Schema](https://arrow.apache.org/docs/python/api/datatypes.html#)
@@ -100,7 +97,7 @@ class RemoteTable(Table):
     def checkout_latest(self):
         return LOOP.run(self._table.checkout_latest())
 
-    def restore(self, version: Optional[int] = None):
+    def restore(self, version: Optional[Union[int, str]] = None):
         return LOOP.run(self._table.restore(version))
 
     def list_indices(self) -> Iterable[IndexConfig]:

python/python/lancedb/table.py

@@ -620,6 +620,10 @@ class Table(ABC):
         """
         raise NotImplementedError
 
+    def __len__(self) -> int:
+        """The number of rows in this Table"""
+        return self.count_rows(None)
+
     @property
     @abstractmethod
     def embedding_functions(self) -> Dict[str, EmbeddingFunctionConfig]:
@@ -1470,7 +1474,7 @@ class Table(ABC):
         """
 
     @abstractmethod
-    def restore(self, version: Optional[int] = None):
+    def restore(self, version: Optional[Union[int, str]] = None):
         """Restore a version of the table. This is an in-place operation.
 
         This creates a new version where the data is equivalent to the
@@ -1478,9 +1482,10 @@ class Table(ABC):
 
         Parameters
         ----------
-        version : int, default None
+        version : int or str, default None
-            The version to restore. If unspecified then restores the currently
+            The version number or version tag to restore.
-            checked out version. If the currently checked out version is the
+            If unspecified then restores the currently checked out version.
+            If the currently checked out version is the
             latest version then this is a no-op.
         """
 
@@ -1710,7 +1715,7 @@ class LanceTable(Table):
         """
         LOOP.run(self._table.checkout_latest())
 
-    def restore(self, version: Optional[int] = None):
+    def restore(self, version: Optional[Union[int, str]] = None):
         """Restore a version of the table. This is an in-place operation.
 
         This creates a new version where the data is equivalent to the
@@ -1718,9 +1723,10 @@ class LanceTable(Table):
 
         Parameters
         ----------
-        version : int, default None
+        version : int or str, default None
-            The version to restore. If unspecified then restores the currently
+            The version number or version tag to restore.
-            checked out version. If the currently checked out version is the
+            If unspecified then restores the currently checked out version.
+            If the currently checked out version is the
             latest version then this is a no-op.
 
         Examples
@@ -1738,12 +1744,20 @@ class LanceTable(Table):
         AddResult(version=2)
         >>> table.version
         2
+        >>> table.tags.create("v2", 2)
         >>> table.restore(1)
         >>> table.to_pandas()
                vector    type
         0  [1.1, 0.9]  vector
         >>> len(table.list_versions())
         3
+        >>> table.restore("v2")
+        >>> table.to_pandas()
+               vector    type
+        0  [1.1, 0.9]  vector
+        1  [0.5, 0.2]  vector
+        >>> len(table.list_versions())
+        4
         """
         if version is not None:
             LOOP.run(self._table.checkout(version))
@@ -1752,9 +1766,6 @@ class LanceTable(Table):
     def count_rows(self, filter: Optional[str] = None) -> int:
         return LOOP.run(self._table.count_rows(filter))
 
-    def __len__(self) -> int:
-        return self.count_rows()
-
     def __repr__(self) -> str:
         val = f"{self.__class__.__name__}(name={self.name!r}, version={self.version}"
         if self._conn.read_consistency_interval is not None:
@@ -3705,6 +3716,7 @@ class AsyncTable:
                 when_not_matched_insert_all=merge._when_not_matched_insert_all,
                 when_not_matched_by_source_delete=merge._when_not_matched_by_source_delete,
                 when_not_matched_by_source_condition=merge._when_not_matched_by_source_condition,
+                timeout=merge._timeout,
             ),
         )
 
@@ -3962,7 +3974,7 @@ class AsyncTable:
         """
         await self._inner.checkout_latest()
 
-    async def restore(self, version: Optional[int] = None):
+    async def restore(self, version: Optional[int | str] = None):
         """
         Restore the table to the currently checked out version
 

python/python/tests/test_remote_db.py

@@ -149,6 +149,24 @@ async def test_async_checkout():
         assert await table.count_rows() == 300
 
 
+def test_table_len_sync():
+    def handler(request):
+        if request.path == "/v1/table/test/create/?mode=create":
+            request.send_response(200)
+            request.send_header("Content-Type", "application/json")
+            request.end_headers()
+            request.wfile.write(b"{}")
+
+        request.send_response(200)
+        request.send_header("Content-Type", "application/json")
+        request.end_headers()
+        request.wfile.write(json.dumps(1).encode())
+
+    with mock_lancedb_connection(handler) as db:
+        table = db.create_table("test", [{"id": 1}])
+        assert len(table) == 1
+
+
 @pytest.mark.asyncio
 async def test_http_error():
     request_id_holder = {"request_id": None}

python/python/tests/test_table.py

@@ -769,6 +769,29 @@ def test_restore(mem_db: DBConnection):
         table.restore(0)
 
 
+def test_restore_with_tags(mem_db: DBConnection):
+    table = mem_db.create_table(
+        "my_table",
+        data=[{"vector": [1.1, 0.9], "type": "vector"}],
+    )
+    tag = "tag1"
+    table.tags.create(tag, 1)
+    table.add([{"vector": [0.5, 0.2], "type": "vector"}])
+    table.restore(tag)
+    assert len(table.list_versions()) == 3
+    assert len(table) == 1
+    expected = table.to_arrow()
+
+    table.add([{"vector": [0.3, 0.3], "type": "vector"}])
+    table.checkout("tag1")
+    table.restore()
+    assert len(table.list_versions()) == 5
+    assert table.to_arrow() == expected
+
+    with pytest.raises(ValueError):
+        table.restore("tag_unknown")
+
+
 def test_merge(tmp_db: DBConnection, tmp_path):
     pytest.importorskip("lance")
     import lance
@@ -914,7 +937,7 @@ def test_merge_insert(mem_db: DBConnection):
         table.merge_insert("a")
         .when_matched_update_all()
         .when_not_matched_insert_all()
-        .execute(new_data)
+        .execute(new_data, timeout=timedelta(seconds=10))
     )
     assert merge_insert_res.version == 2
     assert merge_insert_res.num_inserted_rows == 1
@@ -990,6 +1013,12 @@ def test_merge_insert(mem_db: DBConnection):
     expected = pa.table({"a": [2, 4], "b": ["x", "z"]})
     assert table.to_arrow().sort_by("a") == expected
 
+    # timeout
+    with pytest.raises(Exception, match="merge insert timed out"):
+        table.merge_insert("a").when_matched_update_all().execute(
+            new_data, timeout=timedelta(0)
+        )
+
 
 # We vary the data format because there are slight differences in how
 # subschemas are handled in different formats

python/src/table.rs

@@ -17,10 +17,10 @@ use lancedb::table::{
     Table as LanceDbTable,
 };
 use pyo3::{
-    exceptions::{PyIOError, PyKeyError, PyRuntimeError, PyValueError},
+    exceptions::{PyKeyError, PyRuntimeError, PyValueError},
     pyclass, pymethods,
-    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods, PyInt, PyString},
+    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, PyAny, PyObject, PyRef, PyResult, Python,
+    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 
@@ -520,25 +520,15 @@ impl Table {
         })
     }
 
-    pub fn checkout(self_: PyRef<'_, Self>, version: PyObject) -> PyResult<Bound<'_, PyAny>> {
+    pub fn checkout(self_: PyRef<'_, Self>, version: LanceVersion) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.inner_ref()?.clone();
         let py = self_.py();
-        let (is_int, int_value, string_value) = if let Ok(i) = version.downcast_bound::<PyInt>(py) {
-            let num: u64 = i.extract()?;
-            (true, num, String::new())
-        } else if let Ok(s) = version.downcast_bound::<PyString>(py) {
-            let str_value = s.to_string();
-            (false, 0, str_value)
-        } else {
-            return Err(PyIOError::new_err(
-                "version must be an integer or a string.",
-            ));
-        };
         future_into_py(py, async move {
-            if is_int {
+            match version {
-                inner.checkout(int_value).await.infer_error()
+                LanceVersion::Version(version_num) => {
-            } else {
+                    inner.checkout(version_num).await.infer_error()
-                inner.checkout_tag(&string_value).await.infer_error()
+                }
+                LanceVersion::Tag(tag) => inner.checkout_tag(&tag).await.infer_error(),
             }
         })
     }
@@ -551,12 +541,19 @@ impl Table {
     }
 
     #[pyo3(signature = (version=None))]
-    pub fn restore(self_: PyRef<'_, Self>, version: Option<u64>) -> PyResult<Bound<'_, PyAny>> {
+    pub fn restore(
+        self_: PyRef<'_, Self>,
+        version: Option<LanceVersion>,
+    ) -> PyResult<Bound<'_, PyAny>> {
         let inner = self_.inner_ref()?.clone();
+        let py = self_.py();
 
-        future_into_py(self_.py(), async move {
+        future_into_py(py, async move {
             if let Some(version) = version {
-                inner.checkout(version).await.infer_error()?;
+                match version {
+                    LanceVersion::Version(num) => inner.checkout(num).await.infer_error()?,
+                    LanceVersion::Tag(tag) => inner.checkout_tag(&tag).await.infer_error()?,
+                }
             }
             inner.restore().await.infer_error()
         })
@@ -652,6 +649,9 @@ impl Table {
             builder
                 .when_not_matched_by_source_delete(parameters.when_not_matched_by_source_condition);
         }
+        if let Some(timeout) = parameters.timeout {
+            builder.timeout(timeout);
+        }
 
         future_into_py(self_.py(), async move {
             let res = builder.execute(Box::new(batches)).await.infer_error()?;
@@ -795,6 +795,12 @@ impl Table {
     }
 }
 
+#[derive(FromPyObject)]
+pub enum LanceVersion {
+    Version(u64),
+    Tag(String),
+}
+
 #[derive(FromPyObject)]
 #[pyo3(from_item_all)]
 pub struct MergeInsertParams {
@@ -804,6 +810,7 @@ pub struct MergeInsertParams {
     when_not_matched_insert_all: bool,
     when_not_matched_by_source_delete: bool,
     when_not_matched_by_source_condition: Option<String>,
+    timeout: Option<std::time::Duration>,
 }
 
 #[pyclass]

rust-toolchain.toml

@@ -1,2 +1,2 @@
 [toolchain]
-channel = "1.83.0"
+channel = "1.86.0"

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.19.1-beta.1"
+version = "0.19.1-beta.5"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.19.1-beta.1"
+version = "0.19.1-beta.5"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/remote/table.rs

@@ -758,8 +758,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         let (request_id, response) = self.send_streaming(request, data, true).await?;
         let response = self.check_table_response(&request_id, response).await?;
         let body = response.text().await.err_to_http(request_id.clone())?;
-
+        if body.trim().is_empty() {
-        if body.trim().is_empty() || body == "{}" {
             // Backward compatible with old servers
             return Ok(AddResult { version: 0 });
         }
@@ -922,7 +921,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         let response = self.check_table_response(&request_id, response).await?;
         let body = response.text().await.err_to_http(request_id.clone())?;
 
-        if body.trim().is_empty() || body == "{}" {
+        if body.trim().is_empty() {
             // Backward compatible with old servers
             return Ok(UpdateResult {
                 rows_updated: 0,
@@ -950,12 +949,10 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         let (request_id, response) = self.send(request, true).await?;
         let response = self.check_table_response(&request_id, response).await?;
         let body = response.text().await.err_to_http(request_id.clone())?;
-
+        if body.trim().is_empty() {
-        if body == "{}" {
             // Backward compatible with old servers
             return Ok(DeleteResult { version: 0 });
         }
-
         let delete_response: DeleteResult =
             serde_json::from_str(&body).map_err(|e| Error::Http {
                 source: format!("Failed to parse delete response: {}", e).into(),
@@ -1071,19 +1068,28 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
     ) -> Result<MergeResult> {
         self.check_mutable().await?;
 
+        let timeout = params.timeout;
+
         let query = MergeInsertRequest::try_from(params)?;
-        let request = self
+        let mut request = self
             .client
             .post(&format!("/v1/table/{}/merge_insert/", self.name))
             .query(&query)
             .header(CONTENT_TYPE, ARROW_STREAM_CONTENT_TYPE);
 
+        if let Some(timeout) = timeout {
+            // (If it doesn't fit into u64, it's not worth sending anyways.)
+            if let Ok(timeout_ms) = u64::try_from(timeout.as_millis()) {
+                request = request.header(REQUEST_TIMEOUT_HEADER, timeout_ms);
+            }
+        }
+
         let (request_id, response) = self.send_streaming(request, new_data, true).await?;
 
         let response = self.check_table_response(&request_id, response).await?;
         let body = response.text().await.err_to_http(request_id.clone())?;
 
-        if body.trim().is_empty() || body == "{}" {
+        if body.trim().is_empty() {
             // Backward compatible with old servers
             return Ok(MergeResult {
                 version: 0,
@@ -1145,7 +1151,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
                 let response = self.check_table_response(&request_id, response).await?;
                 let body = response.text().await.err_to_http(request_id.clone())?;
 
-                if body.trim().is_empty() || body == "{}" {
+                if body.trim().is_empty() {
                     // Backward compatible with old servers
                     return Ok(AddColumnsResult { version: 0 });
                 }
@@ -1198,7 +1204,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         let response = self.check_table_response(&request_id, response).await?;
         let body = response.text().await.err_to_http(request_id.clone())?;
 
-        if body.trim().is_empty() || body == "{}" {
+        if body.trim().is_empty() {
             // Backward compatible with old servers
             return Ok(AlterColumnsResult { version: 0 });
         }
@@ -1223,7 +1229,7 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
         let response = self.check_table_response(&request_id, response).await?;
         let body = response.text().await.err_to_http(request_id.clone())?;
 
-        if body.trim().is_empty() || body == "{}" {
+        if body.trim().is_empty() {
             // Backward compatible with old servers
             return Ok(DropColumnsResult { version: 0 });
         }
@@ -1328,7 +1334,12 @@ impl<S: HttpSend> BaseTable for RemoteTable<S> {
             self.name, index_name
         ));
         let (request_id, response) = self.send(request, true).await?;
-        self.check_table_response(&request_id, response).await?;
+        if response.status() == StatusCode::NOT_FOUND {
+            return Err(Error::IndexNotFound {
+                name: index_name.to_string(),
+            });
+        };
+        self.client.check_response(&request_id, response).await?;
         Ok(())
     }
 
@@ -1603,16 +1614,21 @@ mod tests {
     }
 
     #[rstest]
-    #[case(true)]
+    #[case("", 0)]
-    #[case(false)]
+    #[case("{}", 0)]
+    #[case(r#"{"request_id": "test-request-id"}"#, 0)]
+    #[case(r#"{"version": 43}"#, 43)]
     #[tokio::test]
-    async fn test_add_append(#[case] old_server: bool) {
+    async fn test_add_append(#[case] response_body: &str, #[case] expected_version: u64) {
         let data = RecordBatch::try_new(
             Arc::new(Schema::new(vec![Field::new("a", DataType::Int32, false)])),
             vec![Arc::new(Int32Array::from(vec![1, 2, 3]))],
         )
         .unwrap();
 
+        // Clone response_body to give it 'static lifetime for the closure
+        let response_body = response_body.to_string();
+
         let (sender, receiver) = std::sync::mpsc::channel();
         let table = Table::new_with_handler("my_table", move |mut request| {
             if request.url().path() == "/v1/table/my_table/insert/" {
@@ -1622,36 +1638,29 @@ mod tests {
                     .query_pairs()
                     .filter(|(k, _)| k == "mode")
                     .all(|(_, v)| v == "append"));
-
                 assert_eq!(
                     request.headers().get("Content-Type").unwrap(),
                     ARROW_STREAM_CONTENT_TYPE
                 );
-
                 let mut body_out = reqwest::Body::from(Vec::new());
                 std::mem::swap(request.body_mut().as_mut().unwrap(), &mut body_out);
                 sender.send(body_out).unwrap();
-
-                if old_server {
-                    http::Response::builder().status(200).body("").unwrap()
-                } else {
                 http::Response::builder()
                     .status(200)
-                        .body(r#"{"version": 43}"#)
+                    .body(response_body.clone())
                     .unwrap()
-                }
             } else {
                 panic!("Unexpected request path: {}", request.url().path());
             }
         });
-
         let result = table
             .add(RecordBatchIterator::new([Ok(data.clone())], data.schema()))
             .execute()
             .await
             .unwrap();
 
-        assert_eq!(result.version, if old_server { 0 } else { 43 });
+        // Check version matches expected value
+        assert_eq!(result.version, expected_version);
 
         let body = receiver.recv().unwrap();
         let body = collect_body(body).await;
@@ -2884,6 +2893,22 @@ mod tests {
         table.drop_index("my_index").await.unwrap();
     }
 
+    #[tokio::test]
+    async fn test_drop_index_not_exists() {
+        let table = Table::new_with_handler("my_table", |request| {
+            assert_eq!(request.method(), "POST");
+            assert_eq!(
+                request.url().path(),
+                "/v1/table/my_table/index/my_index/drop/"
+            );
+            http::Response::builder().status(404).body("{}").unwrap()
+        });
+
+        // Assert that the error is IndexNotFound
+        let e = table.drop_index("my_index").await.unwrap_err();
+        assert!(matches!(e, Error::IndexNotFound { .. }));
+    }
+
     #[tokio::test]
     async fn test_wait_for_index() {
         let table = _make_table_with_indices(0);

rust/lancedb/src/table.rs

@@ -14,7 +14,7 @@ use datafusion_physical_plan::projection::ProjectionExec;
 use datafusion_physical_plan::repartition::RepartitionExec;
 use datafusion_physical_plan::union::UnionExec;
 use datafusion_physical_plan::ExecutionPlan;
-use futures::{StreamExt, TryStreamExt};
+use futures::{FutureExt, StreamExt, TryFutureExt, TryStreamExt};
 use lance::dataset::builder::DatasetBuilder;
 use lance::dataset::cleanup::RemovalStats;
 use lance::dataset::optimize::{compact_files, CompactionMetrics, IndexRemapperOptions};
@@ -80,7 +80,7 @@ pub mod merge;
 
 use crate::index::waiter::wait_for_index;
 pub use chrono::Duration;
-use futures::future::join_all;
+use futures::future::{join_all, Either};
 pub use lance::dataset::optimize::CompactionOptions;
 pub use lance::dataset::refs::{TagContents, Tags as LanceTags};
 pub use lance::dataset::scanner::DatasetRecordBatchStream;
@@ -423,68 +423,79 @@ pub trait Tags: Send + Sync {
     async fn update(&mut self, tag: &str, version: u64) -> Result<()>;
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct UpdateResult {
+    #[serde(default)]
     pub rows_updated: u64,
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct AddResult {
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct DeleteResult {
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct MergeResult {
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
     /// Number of inserted rows (for user statistics)
+    #[serde(default)]
     pub num_inserted_rows: u64,
     /// Number of updated rows (for user statistics)
+    #[serde(default)]
     pub num_updated_rows: u64,
     /// Number of deleted rows (for user statistics)
     /// Note: This is different from internal references to 'deleted_rows', since we technically "delete" updated rows during processing.
     /// However those rows are not shared with the user.
+    #[serde(default)]
     pub num_deleted_rows: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct AddColumnsResult {
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct AlterColumnsResult {
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize, Default)]
 pub struct DropColumnsResult {
     // The commit version associated with the operation.
     // A version of `0` indicates compatibility with legacy servers that do not return
     /// a commit version.
+    #[serde(default)]
     pub version: u64,
 }
 
@@ -2003,7 +2014,7 @@ impl NativeTable {
     /// more information.
     pub async fn uses_v2_manifest_paths(&self) -> Result<bool> {
         let dataset = self.dataset.get().await?;
-        Ok(dataset.manifest_naming_scheme == ManifestNamingScheme::V2)
+        Ok(dataset.manifest_location().naming_scheme == ManifestNamingScheme::V2)
     }
 
     /// Migrate the table to use the new manifest path scheme.
@@ -2464,8 +2475,26 @@ impl BaseTable for NativeTable {
         } else {
             builder.when_not_matched_by_source(WhenNotMatchedBySource::Keep);
         }
+
+        let future = if let Some(timeout) = params.timeout {
+            // The default retry timeout is 30s, so we pass the full timeout down
+            // as well in case it is longer than that.
+            let future = builder
+                .retry_timeout(timeout)
+                .try_build()?
+                .execute_reader(new_data);
+            Either::Left(tokio::time::timeout(timeout, future).map(|res| match res {
+                Ok(Ok((new_dataset, stats))) => Ok((new_dataset, stats)),
+                Ok(Err(e)) => Err(e.into()),
+                Err(_) => Err(Error::Runtime {
+                    message: "merge insert timed out".to_string(),
+                }),
+            }))
+        } else {
             let job = builder.try_build()?;
-        let (new_dataset, stats) = job.execute_reader(new_data).await?;
+            Either::Right(job.execute_reader(new_data).map_err(|e| e.into()))
+        };
+        let (new_dataset, stats) = future.await?;
         let version = new_dataset.manifest().version;
         self.dataset.set_latest(new_dataset.as_ref().clone()).await;
         Ok(MergeResult {

rust/lancedb/src/table/merge.rs

@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::sync::Arc;
+use std::{sync::Arc, time::Duration};
 
 use arrow_array::RecordBatchReader;
 
@@ -21,6 +21,7 @@ pub struct MergeInsertBuilder {
     pub(crate) when_not_matched_insert_all: bool,
     pub(crate) when_not_matched_by_source_delete: bool,
     pub(crate) when_not_matched_by_source_delete_filt: Option<String>,
+    pub(crate) timeout: Option<Duration>,
 }
 
 impl MergeInsertBuilder {
@@ -33,6 +34,7 @@ impl MergeInsertBuilder {
             when_not_matched_insert_all: false,
             when_not_matched_by_source_delete: false,
             when_not_matched_by_source_delete_filt: None,
+            timeout: None,
         }
     }
 
@@ -84,6 +86,21 @@ impl MergeInsertBuilder {
         self
     }
 
+    /// Maximum time to run the operation before cancelling it.
+    ///
+    /// By default, there is a 30-second timeout that is only enforced after the
+    /// first attempt. This is to prevent spending too long retrying to resolve
+    /// conflicts. For example, if a write attempt takes 20 seconds and fails,
+    /// the second attempt will be cancelled after 10 seconds, hitting the
+    /// 30-second timeout. However, a write that takes one hour and succeeds on the
+    /// first attempt will not be cancelled.
+    ///
+    /// When this is set, the timeout is enforced on all attempts, including the first.
+    pub fn timeout(&mut self, timeout: Duration) -> &mut Self {
+        self.timeout = Some(timeout);
+        self
+    }
+
     /// Executes the merge insert operation
     ///
     /// Returns version and statistics about the merge operation including the number of rows