Bump version: 0.37.1-beta.3 → 0.37.1

Bump version: 0.37.1-beta.2 → 0.37.1-beta.3
Bump version: 0.37.1-beta.1 → 0.37.1-beta.2
2026-08-28 17:08:43 +00:00 · 2026-08-10 07:54:42 +00:00 · 2026-08-10 07:53:53 +00:00 · 2026-08-10 06:30:45 +00:00 · 2026-08-10 14:23:41 +08:00 · 2026-08-10 14:23:33 +08:00
37 changed files with 1075 additions and 358 deletions
@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.37.1-beta.0"
+current_version = "0.37.1"
 parse = """(?x)
    (?P<major>0|[1-9]\\d*)\\.
    (?P<minor>0|[1-9]\\d*)\\.
@@ -1,7 +1,8 @@
 name: Create release commit

-# This workflow increments the version, tags it, and pushes it. All SDKs share
-# a single version, so one tag releases all of them.
+# This workflow increments the version, updates lockfiles, tags the final
+# commit, and pushes it. All SDKs share a single version, so one tag releases
+# all of them.
 # When a tag is pushed, another workflow is triggered that creates a GH release
 # and uploads the binaries. This workflow is only for creating the tag.

@@ -63,6 +64,7 @@ jobs:
          pip install bump-my-version PyGithub packaging
          bash ci/bump_version.sh ${{ inputs.type }} ${{ inputs.bump-minor }}
          bash ci/update_lockfiles.sh --amend
+          bash ci/create_release_tag.sh
      - name: Push new version tag
        if: ${{ !inputs.dry_run }}
        uses: ad-m/github-push-action@881a6320fdb16eb5318c5054f31c218aec2b324c # v1.3.0
@@ -775,7 +775,7 @@ dependencies = [
 "http 0.2.12",
 "http 1.5.0",
 "http-body 1.1.0",
- "lru 0.16.4",
+ "lru",
 "percent-encoding",
 "regex-lite",
 "sha2 0.11.0",
@@ -1970,6 +1970,15 @@ dependencies = [
 "spin 0.10.1",
 ]

+[[package]]
+name = "crc32c"
+version = "0.6.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3a47af21622d091a8f0fb295b88bc886ac74efcc613efc19f5d0b21de5c89e47"
+dependencies = [
+ "rustc_version",
+]
+
 [[package]]
 name = "crc32fast"
 version = "1.5.0"
@@ -3441,12 +3450,6 @@ dependencies = [
 "percent-encoding",
 ]

-[[package]]
-name = "frostem"
-version = "1.20260804.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "82eb03a32a1d50555353c85a7b9d3279a6f1e91af9890b789acdf544ed57c8d7"
-
 [[package]]
 name = "fs_extra"
 version = "1.3.0"
@@ -3455,8 +3458,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0981ce90521824089f3cd68a48b1c4c89e9ad96d0eb74f58d6e550a3d604545"
 dependencies = [
 "arrow-array",
 "rand 0.9.5",
@@ -3813,23 +3817,14 @@ dependencies = [

 [[package]]
 name = "goosefs-sdk"
-version = "0.1.9"
+version = "0.1.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e1ea4eee6dcbc31b25ab4fd577adc55b677d2bed3aa3016c44c58fbe1b2298a5"
+checksum = "9ae079b88ffe7772d12cfc5c40a5a324babb357893d95b5e3a22ae857f236c5f"
 dependencies = [
- "arc-swap",
 "async-trait",
 "bytes",
 "dashmap",
- "fastrand",
- "futures",
 "hostname",
- "io-uring",
- "itoa",
- "libc",
- "lru 0.18.2",
- "memmap2 0.9.10",
- "moka",
 "prost",
 "prost-types",
 "rand 0.9.5",
@@ -3842,7 +3837,6 @@ dependencies = [
 "tonic-prost",
 "tracing",
 "uuid",
- "xxhash-rust",
 ]

 [[package]]
@@ -4815,8 +4809,9 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"

 [[package]]
 name = "lance"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830548f9fc92ae74b848a504282d4da06f016f2ee94b663773c2738b9cb61c42"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -4890,8 +4885,9 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24187f972374567bb3573cffd8728f2f4f7f06d644c3c5d4430b79d6b0b67300"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4913,7 +4909,8 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "771f68b04b47f3addf781116f65061808de94b05e1e9411c23c18f32d14ebe79"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4927,17 +4924,20 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd47ec33c90bf29f688fd02118e37d3a5ad5c339caa3163f89e417dc0867001f"
 dependencies = [
 "arrow-array",
 "arrow-schema",
+ "half",
 "lance-arrow-scalar",
 ]

 [[package]]
 name = "lance-bitpacking"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "55fa50ad941e25298afb54eec107c3584f80c16db4adf7a6e4e9c4b6066f4281"
 dependencies = [
 "arrayref",
 "crunchy",
@@ -4947,8 +4947,9 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "21f4fd872bfe948150a6878d983327c4f150dc1b629e94ae7677310fa6a3f35f"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4988,8 +4989,9 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "230770734cd5f6fe1f1cb4a66750acad5c5a862c23c7f587d7def57c9f2c5f6b"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5019,8 +5021,9 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c0c9edcea9dbf154a3baf470595bdcdb7ef6b44dcf2b5a0c28e8815c2d4837c5"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5037,8 +5040,9 @@ dependencies = [

 [[package]]
 name = "lance-derive"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "03ac280ef94d66c2e7a4b0104e60d548f45156f114f02cd0ac57423721ec96ec"
 dependencies = [
 "proc-macro2",
 "quote",
@@ -5047,8 +5051,9 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "65b345fecf1792d4147982e9ded1cf211992a442bcf73dd17a598b1c8c9b53a5"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5074,6 +5079,7 @@ dependencies = [
 "prost",
 "prost-build",
 "rand 0.9.5",
+ "strum 0.26.3",
 "tokio",
 "tracing",
 "xxhash-rust",
@@ -5082,8 +5088,9 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "203400160ecd4ac6f67f6bfdb3c186f94758ff70a6ca76d4f300c327f5c14a11"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -5114,8 +5121,9 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "db67792e22332a7be08d35e60ce9e4c6fb7f75f70ab1566b67b462d1aac21b13"
 dependencies = [
 "arc-swap",
 "arrow",
@@ -5182,8 +5190,9 @@ dependencies = [

 [[package]]
 name = "lance-index-core"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49b5700d71f43e5da2057908f3243a6bc01247b5dd12247313f789c280155aae"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5205,8 +5214,9 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b8a6872b9bff95e75e223e04011feebd990d8784878eaf5df73c86d6acebb47"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5218,6 +5228,7 @@ dependencies = [
 "bytes",
 "chrono",
 "futures",
+ "goosefs-sdk",
 "http 1.5.0",
 "io-uring",
 "lance-arrow",
@@ -5242,8 +5253,9 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a1dd49fdf61da86650dc335fbe1f239803f9d73bc2bc5ffbc0c905dd8809892"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5259,8 +5271,9 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1449221f599147e570bec6e09eaea6ce6b9286f632e00a27f945dd0c6b70ccd8"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5272,8 +5285,9 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c30bff40ab9a9a58313818ab97241cff7bab2b90b8d65039908425a065a797de"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -5303,6 +5317,7 @@ dependencies = [
 "serde",
 "serde_json",
 "sha2 0.10.9",
+ "time",
 "tokio",
 "tower",
 "tower-http 0.5.2",
@@ -5326,8 +5341,9 @@ dependencies = [

 [[package]]
 name = "lance-select"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c66c5cb12ed194c7c8e427a0e90e990cdbc7159edba2bfc7b7e8db2c90c747af"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5342,8 +5358,9 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6cd2a39f2e288d1acecf887cb9cc655711fb67bcf3b24a2034158dbac7a6f60e"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -5353,7 +5370,6 @@ dependencies = [
 "async-trait",
 "aws-credential-types",
 "aws-sdk-dynamodb",
- "blake3",
 "byteorder",
 "bytes",
 "chrono",
@@ -5383,8 +5399,9 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0847352699e869a465b49bd49ecbc467bc5a3dcb168757bf39368362aad05f99"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -5397,13 +5414,14 @@ dependencies = [

 [[package]]
 name = "lance-tokenizer"
-version = "11.0.0-beta.3"
-source = "git+https://github.com/lance-format/lance.git?tag=v11.0.0-beta.3#f7d475539cefbd140cc46a828f3d843e68cd10f1"
+version = "10.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "254c1e9287789c8d744f93f2010a8389a5ea3fcedc0dddf7649c4117ec830c57"
 dependencies = [
- "frostem",
 "icu_segmenter",
 "jieba-rs",
 "lindera",
+ "rust-stemmers",
 "serde",
 "stop-words",
 "unicode-normalization",
@@ -5411,7 +5429,7 @@ dependencies = [

 [[package]]
 name = "lancedb"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 dependencies = [
 "ahash",
 "anyhow",
@@ -5447,7 +5465,6 @@ dependencies = [
 "datafusion-physical-plan",
 "datafusion-sql",
 "futures",
- "goosefs-sdk",
 "half",
 "hf-hub",
 "http 1.5.0",
@@ -5480,6 +5497,7 @@ dependencies = [
 "random_word",
 "regex",
 "reqwest 0.12.28",
+ "roaring",
 "rstest",
 "semver",
 "serde",
@@ -5499,7 +5517,7 @@ dependencies = [

 [[package]]
 name = "lancedb-nodejs"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -5524,7 +5542,7 @@ dependencies = [

 [[package]]
 name = "lancedb-python"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 dependencies = [
 "arrow",
 "async-trait",
@@ -5681,7 +5699,7 @@ dependencies = [
 "serde",
 "serde_json",
 "serde_yaml_ng",
- "strum",
+ "strum 0.28.0",
 "strum_macros 0.28.0",
 "unicode-blocks",
 "unicode-normalization",
@@ -5711,7 +5729,7 @@ dependencies = [
 "rkyv",
 "serde",
 "serde_json",
- "strum",
+ "strum 0.28.0",
 "strum_macros 0.28.0",
 "thiserror 2.0.18",
 ]
@@ -5783,15 +5801,6 @@ dependencies = [
 "hashbrown 0.16.1",
 ]

-[[package]]
-name = "lru"
-version = "0.18.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5d2f2f9b4ba7e6b24d95e7e899329d35be83bcded72c8540cdd5368932d1d90a"
-dependencies = [
- "hashbrown 0.17.1",
-]
-
 [[package]]
 name = "lru-slab"
 version = "0.1.2"
@@ -6429,9 +6438,9 @@ dependencies = [

 [[package]]
 name = "object_store_opendal"
-version = "0.58.0"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "88f165780495c17aa3ce86846600504198c3fffd99073521552751c2430fa6ac"
+checksum = "0eb12a624a41fce745838d0ef3701ff6c47797c13cd18ad3612fd2a3134fdbd8"
 dependencies = [
 "async-trait",
 "bytes",
@@ -6492,13 +6501,12 @@ checksum = "d6790f58c7ff633d8771f42965289203411a5e5c68388703c06e14f24770b41e"

 [[package]]
 name = "opendal"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f20562cc7447fcc915fc5c23df305a412ea80a733c9f2fd9e2d267e2815be6d"
+checksum = "96c9c85ce253ff87225e7669979d877a20c98a06604ec9d6dd5f4473e08f1ae1"
 dependencies = [
 "ctor 1.0.12",
 "opendal-core",
- "opendal-http-transport-reqwest",
 "opendal-layer-concurrent-limit",
 "opendal-layer-logging",
 "opendal-layer-retry",
@@ -6515,22 +6523,24 @@ dependencies = [

 [[package]]
 name = "opendal-core"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec75551ff4cf3e57da98979f6a937aaa9ddb3915bf68cc17d03df733be6646ed"
+checksum = "c4f8607c90e2c963a91467f50fb49fbc7fb3d573f88cea219ca59ccd3740b309"
 dependencies = [
 "anyhow",
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "futures",
 "http 1.5.0",
+ "http-body 1.1.0",
 "jiff",
 "log",
 "md-5 0.11.0",
 "mea",
 "percent-encoding",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-core",
+ "reqwest 0.13.4",
 "serde",
 "serde_json",
 "tokio",
@@ -6539,25 +6549,11 @@ dependencies = [
 "web-time",
 ]

-[[package]]
-name = "opendal-http-transport-reqwest"
-version = "0.58.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ad4d4f19c3ce01126a30611f8e544eaa217104a278c889ac17c9374fe4f9e4ef"
-dependencies = [
- "bytes",
- "futures",
- "http 1.5.0",
- "http-body 1.1.0",
- "opendal-core",
- "reqwest 0.13.4",
-]
-
 [[package]]
 name = "opendal-layer-concurrent-limit"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "249ac5b0aa5a7a6c3737342d10456067937f9c9a6f3f02544271f7908ab91081"
+checksum = "0d6f81ba6960e3fae1882f253b114b21d7e444e1534f209c7737a79f6243eb6f"
 dependencies = [
 "futures",
 "http 1.5.0",
@@ -6567,9 +6563,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-logging"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c75411ab00f77851ff086b686c1e9ca8175ac18c15afa2cb75b9036436cb06c"
+checksum = "58ada45c6d81d1aa4c9305d0c7d4bc317c59c85866a0908a2d75a7a978aa5ee2"
 dependencies = [
 "log",
 "opendal-core",
@@ -6577,9 +6573,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-retry"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "80b7738bd5f233ad8da39af9b9316b9b7a4eaddd91e8e32a1e19b7030688121d"
+checksum = "7b2a25a718afb81fad81cb9a0580a1cb989221fa2317f888c6a37f8dad408eb7"
 dependencies = [
 "backon",
 "log",
@@ -6588,9 +6584,9 @@ dependencies = [

 [[package]]
 name = "opendal-layer-timeout"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a704141924500f3803c05ed871b53305d2a2f11cb5ef20160c3ee688a1857f66"
+checksum = "1e91f731724c213af81e9d03517859c8fc47b4578e64ad61ae4f099f10fe36e3"
 dependencies = [
 "opendal-core",
 "tokio",
@@ -6598,17 +6594,17 @@ dependencies = [

 [[package]]
 name = "opendal-service-azblob"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b3310fbbb48f111c6f590473c2cd15e1b7f8e384444b0d4e328f0464c864d767"
+checksum = "0030644366ef5d8cbe3a4a5822bf99a4aafddc1666e9d24b44d158d9062fc76a"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "http 1.5.0",
 "log",
 "opendal-core",
 "opendal-service-azure-common",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-azure-storage",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6619,18 +6615,17 @@ dependencies = [

 [[package]]
 name = "opendal-service-azdls"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2e3c406729935fe214ce574d68681a1ff7e0b322548f14094912bdbfe50e5c53"
+checksum = "6dea4908d490143a9b0b7f7a790e139ff829b06a023f670455ed3d44f664b361"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
 "http 1.5.0",
 "log",
- "mea",
 "opendal-core",
 "opendal-service-azure-common",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-azure-storage",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6640,9 +6635,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-azure-common"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7348c88edf15af435b7be930077746b569fac5e738c1bf6a363b675e7317c9df"
+checksum = "9b489f13c42e69d69bdd72952b634356ec43a7881a20259b38b540fcecdf4051"
 dependencies = [
 "http 1.5.0",
 "opendal-core",
@@ -6650,15 +6645,15 @@ dependencies = [

 [[package]]
 name = "opendal-service-cos"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d533d4582105d269c8aebeee5f0e8bcf960f41b8aab6197df7012254d9f39bf0"
+checksum = "aa8cafe9729213375c7331019b0cb756ad3e1aff7f45cd32c45eae91ebde8901"
 dependencies = [
 "bytes",
 "http 1.5.0",
 "log",
 "opendal-core",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-core",
 "reqsign-file-read-tokio",
 "reqsign-tencent-cos",
@@ -6667,9 +6662,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-gcs"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "007f3fba63c21e516c956b891e96ff9892d8175662bfb781cdada9d3766a11e6"
+checksum = "48de101aac565ed06af4b47903c24eafd249075553ec1fb18256751c45148d47"
 dependencies = [
 "async-trait",
 "bytes",
@@ -6677,7 +6672,7 @@ dependencies = [
 "log",
 "opendal-core",
 "percent-encoding",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-core",
 "reqsign-file-read-tokio",
 "reqsign-google",
@@ -6688,9 +6683,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-goosefs"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "60871e6386f04d831e6a5bdbc032af4a91aeba49963252d0ef456a2cf36a9b78"
+checksum = "69e43048bde419947ba826fbdc2f134d6c03f44ebf48bd33a03b72f9fc45fcb4"
 dependencies = [
 "bytes",
 "goosefs-sdk",
@@ -6702,9 +6697,9 @@ dependencies = [

 [[package]]
 name = "opendal-service-hf"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b41fd41eb7ed03c5e66cefda61e8e117808ffd2908f2916737cb020a6beb02c7"
+checksum = "c4922661976a1d40794a2adfbdb888cc3c23097690f825a92f773af38908a848"
 dependencies = [
 "bytes",
 "hf-xet",
@@ -6712,21 +6707,22 @@ dependencies = [
 "log",
 "opendal-core",
 "percent-encoding",
+ "reqwest 0.13.4",
 "serde",
 "serde_json",
 ]

 [[package]]
 name = "opendal-service-oss"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cd528ec2d49c5ca69e674ffed7b3e0686fb9cfcfea0596870de381467fda4f1b"
+checksum = "328fa55e8888cbdfe00826bfea2a79042422b720e8369e9e021e46121dea5ace"
 dependencies = [
 "bytes",
 "http 1.5.0",
 "log",
 "opendal-core",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-aliyun-oss",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -6735,18 +6731,18 @@ dependencies = [

 [[package]]
 name = "opendal-service-s3"
-version = "0.58.1"
+version = "0.57.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "58e80cdf192d7eff05feed747894d64f81905ac4eaf132edf7ea270abdd2d663"
+checksum = "313d46c9f5ae70bca26b7c3e3fbb9b639292625f28af73aa016f47e788af9deb"
 dependencies = [
- "base64 0.23.1",
+ "base64 0.22.1",
 "bytes",
- "crc-fast",
+ "crc32c",
 "http 1.5.0",
 "log",
 "md-5 0.11.0",
 "opendal-core",
- "quick-xml 0.41.0",
+ "quick-xml 0.39.4",
 "reqsign-aws-v4",
 "reqsign-core",
 "reqsign-file-read-tokio",
@@ -8679,6 +8675,16 @@ dependencies = [
 "ordered-multimap",
 ]

+[[package]]
+name = "rust-stemmers"
+version = "1.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e46a2036019fdb888131db7a4c847a1063a7493f971ed94ea82c67eada63ca54"
+dependencies = [
+ "serde",
+ "serde_derive",
+]
+
 [[package]]
 name = "rustc-demangle"
 version = "0.1.27"
@@ -9552,6 +9558,15 @@ version = "0.11.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"

+[[package]]
+name = "strum"
+version = "0.26.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fec0f0aef304996cf250b31b5a10dee7980c85da9d759361292b8bca5a18f06"
+dependencies = [
+ "strum_macros 0.26.4",
+]
+
 [[package]]
 name = "strum"
 version = "0.28.0"
@@ -9574,6 +9589,19 @@ dependencies = [
 "syn 2.0.117",
 ]

+[[package]]
+name = "strum_macros"
+version = "0.26.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4c6bee85a5a24955dc440386795aa378cd9cf82acd5f764469152d2270e581be"
+dependencies = [
+ "heck 0.5.0",
+ "proc-macro2",
+ "quote",
+ "rustversion",
+ "syn 2.0.117",
+]
+
 [[package]]
 name = "strum_macros"
 version = "0.28.0"
@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"

 [workspace.dependencies]
-lance = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=11.0.0-beta.3", default-features = false, "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=11.0.0-beta.3", "tag" = "v11.0.0-beta.3", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=10.0.0", default-features = false }
+lance-core = "=10.0.0"
+lance-datagen = "=10.0.0"
+lance-file = "=10.0.0"
+lance-io = { "version" = "=10.0.0", default-features = false }
+lance-index = "=10.0.0"
+lance-linalg = "=10.0.0"
+lance-namespace = "=10.0.0"
+lance-namespace-impls = { "version" = "=10.0.0", default-features = false }
+lance-table = "=10.0.0"
+lance-testing = "=10.0.0"
+lance-datafusion = "=10.0.0"
+lance-encoding = "=10.0.0"
+lance-arrow = "=10.0.0"
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }
@@ -6,16 +6,11 @@ HEAD_SHA=$(git rev-parse HEAD)

 readonly TAG_PREFIX="v"
 readonly SELF_DIR=$(cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )
+readonly BUMP_ARGS="--no-tag"

 PREV_TAG=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
 echo "Found previous tag $PREV_TAG"

-# Initially, we don't want to tag if we are doing stable, because we will bump
-# again later. See comment at end for why.
-if [[ "$RELEASE_TYPE" == 'stable' ]]; then
-  BUMP_ARGS="--no-tag"
-fi
-
 # If last is stable and not bumping minor
 if [[ $PREV_TAG != *beta* ]]; then
    if [[ "$BUMP_MINOR" != "false" ]]; then
@@ -39,12 +34,12 @@ fi
 # a stable version, bump the pre-release level ("pre_l") to make it stable.
 if [[ $RELEASE_TYPE == 'stable' ]]; then
  # X.Y.Z-beta.N -> X.Y.Z
-  bump-my-version bump -vv pre_l
+  bump-my-version bump -vv $BUMP_ARGS pre_l
 fi

 # Validate that we have incremented version appropriately for breaking changes
-NEW_TAG=$(git describe --tags --exact-match HEAD)
-NEW_VERSION=$(echo $NEW_TAG | sed "s/^$TAG_PREFIX//")
+NEW_VERSION=$(python -c 'import tomllib; print(tomllib.load(open(".bumpversion.toml", "rb"))["tool"]["bumpversion"]["current_version"])')
+NEW_TAG="$TAG_PREFIX$NEW_VERSION"
 LAST_STABLE_RELEASE=$(git tag --sort='version:refname' | grep ^$TAG_PREFIX | grep -v beta | grep -vF "$NEW_TAG" | python $SELF_DIR/semver_sort.py $TAG_PREFIX | tail -n 1)
 LAST_STABLE_VERSION=$(echo $LAST_STABLE_RELEASE | sed "s/^$TAG_PREFIX//")

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+RELEASE_VERSION=$(python -c 'import tomllib; print(tomllib.load(open(".bumpversion.toml", "rb"))["tool"]["bumpversion"]["current_version"])')
+RELEASE_TAG="v${RELEASE_VERSION}"
+
+if git rev-parse --quiet --verify "refs/tags/${RELEASE_TAG}" >/dev/null; then
+  echo "Release tag ${RELEASE_TAG} already exists" >&2
+  exit 1
+fi
+
+git tag --annotate "$RELEASE_TAG" --message "Release ${RELEASE_TAG}"
+
+HEAD_SHA=$(git rev-parse HEAD)
+TAG_SHA=$(git rev-parse "refs/tags/${RELEASE_TAG}^{}")
+if [[ "$TAG_SHA" != "$HEAD_SHA" ]]; then
+  echo "Release tag ${RELEASE_TAG} points to ${TAG_SHA}, expected ${HEAD_SHA}" >&2
+  exit 1
+fi
+
+echo "Created ${RELEASE_TAG} at ${HEAD_SHA}"
@@ -0,0 +1,72 @@
+import tempfile
+import unittest
+from pathlib import Path
+
+from validate_stable_lance import validate
+
+
+class ValidateStableLanceTest(unittest.TestCase):
+    def write_fixture(
+        self,
+        root: Path,
+        *,
+        rust: str = "=10.0.0",
+        python: str = "10.0.0",
+        java: str = "10.0.0",
+    ) -> None:
+        (root / "python").mkdir()
+        (root / "java").mkdir()
+        (root / "Cargo.toml").write_text(
+            f'[workspace.dependencies]\nlance = "{rust}"\nlance-core = "{rust}"\n'
+        )
+        (root / "python" / "pyproject.toml").write_text(
+            '[project.optional-dependencies]\ntests = ["pylance==' + python + '"]\n'
+        )
+        (root / "java" / "pom.xml").write_text(
+            "<project><properties><lance-core.version>"
+            + java
+            + "</lance-core.version></properties></project>"
+        )
+
+    def test_accepts_matching_stable_versions(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root)
+            self.assertEqual(validate(root), "10.0.0")
+
+    def test_rejects_prerelease(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root, python="10.0.0rc1")
+            with self.assertRaisesRegex(ValueError, "not stable"):
+                validate(root)
+
+    def test_rejects_sdk_mismatch(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root, java="9.0.0")
+            with self.assertRaisesRegex(ValueError, "do not match across SDKs"):
+                validate(root)
+
+    def test_rejects_non_exact_rust_dependency(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root, rust="10.0.0")
+            with self.assertRaisesRegex(ValueError, "not exact"):
+                validate(root)
+
+    def test_rejects_unpublished_rust_source(self) -> None:
+        with tempfile.TemporaryDirectory() as temp_dir:
+            root = Path(temp_dir)
+            self.write_fixture(root)
+            (root / "Cargo.toml").write_text(
+                "[workspace.dependencies]\n"
+                'lance = { version = "=10.0.0", git = "https://example.com/lance", '
+                'tag = "v10.0.0" }\n'
+            )
+            with self.assertRaisesRegex(ValueError, "unpublished source fields"):
+                validate(root)
+
+
+if __name__ == "__main__":
+    unittest.main()
@@ -1,34 +1,112 @@
+#!/usr/bin/env python3
+"""Validate that every SDK uses the same published stable Lance release."""
+
+from __future__ import annotations
+
+import re
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
 import tomllib

-found_preview_lance = False
+STABLE_VERSION = re.compile(r"[0-9]+\.[0-9]+\.[0-9]+")

-with open("Cargo.toml", "rb") as f:
-    cargo_data = tomllib.load(f)

-    for name, dep in cargo_data["workspace"]["dependencies"].items():
-        if name == "lance" or name.startswith("lance-"):
-            if isinstance(dep, str):
-                version = dep
-            elif isinstance(dep, dict):
-                # Version doesn't have the beta tag in it, so we instead look
-                # at the git tag.
-                version = dep.get('tag', dep.get('version'))
-            else:
-                raise ValueError("Unexpected type for dependency: " + str(dep))
+def _stable_version(raw: str, *, dependency: str, exact: bool = False) -> str:
+    value = raw.strip()
+    if exact and not value.startswith("="):
+        raise ValueError(f"Dependency '{dependency}' is not exact: {raw}")
+    value = value.removeprefix("=").removeprefix("v")
+    if STABLE_VERSION.fullmatch(value) is None:
+        raise ValueError(f"Dependency '{dependency}' is not stable: {raw}")
+    return value

-            if "beta" in version:
-                found_preview_lance = True
-                print(f"Dependency '{name}' is a preview version: {version}")

-with open("python/pyproject.toml", "rb") as f:
-    py_proj_data = tomllib.load(f)
+def rust_lance_version(repo_root: Path) -> str:
+    with (repo_root / "Cargo.toml").open("rb") as cargo_file:
+        dependencies = tomllib.load(cargo_file)["workspace"]["dependencies"]

-    for dep in py_proj_data["project"]["dependencies"]:
-        if dep.startswith("pylance"):
-            if "b" in dep:
-                found_preview_lance = True
-                print(f"Dependency '{dep}' is a preview version")
-            break  # Only one pylance dependency
+    versions: dict[str, str] = {}
+    for name, dependency in dependencies.items():
+        if name != "lance" and not name.startswith("lance-"):
+            continue

-if found_preview_lance:
-    raise ValueError("Found preview version of Lance in dependencies")
+        if isinstance(dependency, str):
+            raw_version = dependency
+        elif isinstance(dependency, dict):
+            forbidden_sources = [
+                source
+                for source in ("git", "path", "branch", "rev", "tag")
+                if source in dependency
+            ]
+            if forbidden_sources:
+                joined = ", ".join(forbidden_sources)
+                raise ValueError(
+                    f"Dependency '{name}' uses unpublished source fields: {joined}"
+                )
+            raw_version = dependency.get("version")
+            if raw_version is None:
+                raise ValueError(f"Dependency '{name}' has no version")
+        else:
+            raise TypeError(f"Dependency '{name}' has an unexpected definition")
+
+        versions[name] = _stable_version(raw_version, dependency=name, exact=True)
+
+    if not versions:
+        raise ValueError("No Rust Lance dependencies found")
+    unique_versions = set(versions.values())
+    if len(unique_versions) != 1:
+        details = ", ".join(f"{name}={version}" for name, version in versions.items())
+        raise ValueError(f"Rust Lance dependency versions do not match: {details}")
+    return unique_versions.pop()
+
+
+def python_lance_version(repo_root: Path) -> str:
+    with (repo_root / "python" / "pyproject.toml").open("rb") as pyproject_file:
+        pyproject = tomllib.load(pyproject_file)
+
+    requirements = pyproject["project"]["optional-dependencies"]["tests"]
+    pylance_requirements = [
+        requirement for requirement in requirements if requirement.startswith("pylance")
+    ]
+    if len(pylance_requirements) != 1:
+        raise ValueError(
+            "Expected exactly one pylance requirement in the Python test dependencies"
+        )
+
+    requirement = pylance_requirements[0]
+    prefix = "pylance=="
+    if not requirement.startswith(prefix):
+        raise ValueError(f"Python test dependency is not exact: {requirement}")
+    return _stable_version(requirement[len(prefix) :], dependency="pylance")
+
+
+def java_lance_version(repo_root: Path) -> str:
+    pom_root = ET.parse(repo_root / "java" / "pom.xml").getroot()
+    versions = [
+        element.text
+        for element in pom_root.iter()
+        if element.tag.rsplit("}", 1)[-1] == "lance-core.version"
+    ]
+    if len(versions) != 1 or versions[0] is None:
+        raise ValueError("Expected exactly one Java lance-core.version property")
+    return _stable_version(versions[0], dependency="Java lance-core")
+
+
+def validate(repo_root: Path) -> str:
+    versions = {
+        "Rust": rust_lance_version(repo_root),
+        "Python": python_lance_version(repo_root),
+        "Java": java_lance_version(repo_root),
+    }
+    if len(set(versions.values())) != 1:
+        details = ", ".join(f"{sdk}={version}" for sdk, version in versions.items())
+        raise ValueError(
+            f"Lance dependency versions do not match across SDKs: {details}"
+        )
+    return versions["Rust"]
+
+
+if __name__ == "__main__":
+    version = validate(Path(__file__).resolve().parents[1])
+    print(f"Validated published stable Lance v{version} across Rust, Python, and Java")
@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-core</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.37.1</version>
 </dependency>
 ```

@@ -44,4 +44,7 @@ The number of rows in the table
 totalBytes: number;
 ```

-The total number of bytes in the table
+The total size, in bytes, of the table's data files, index files, and
+overlay files
+
+Read from the manifest, so this excludes deletion files and manifests.
@@ -8,7 +8,7 @@
    <parent>
      <groupId>com.lancedb</groupId>
      <artifactId>lancedb-parent</artifactId>
-      <version>0.37.1-beta.0</version>
+      <version>0.37.1-final.0</version>
      <relativePath>../pom.xml</relativePath>
    </parent>

@@ -6,7 +6,7 @@

    <groupId>com.lancedb</groupId>
    <artifactId>lancedb-parent</artifactId>
-    <version>0.37.1-beta.0</version>
+    <version>0.37.1-final.0</version>
    <packaging>pom</packaging>
    <name>${project.artifactId}</name>
    <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>11.0.0-beta.3</lance-core.version>
+        <lance-core.version>10.0.0</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>
@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.37.1-beta.0"
+version = "0.37.1"
 publish = false
 license.workspace = true
 description.workspace = true
@@ -6,7 +6,9 @@ import * as arrow17 from "apache-arrow-17";
 import * as arrow18 from "apache-arrow-18";

 import {
+  Vector as CurrentVector,
  convertToTable,
+  tableFromIPC as currentTableFromIPC,
  fromBufferToRecordBatch,
  fromDataToBuffer,
  fromRecordBatchToBuffer,
@@ -19,6 +21,7 @@ import {
  FunctionOptions,
 } from "../lancedb/embedding/embedding_function";
 import { EmbeddingFunctionConfig } from "../lancedb/embedding/registry";
+import { sanitizeTable } from "../lancedb/sanitize";

 // biome-ignore lint/suspicious/noExplicitAny: skip
 function sampleRecords(): Array<Record<string, any>> {
@@ -64,7 +67,11 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
      tableFromIPC,
      DataType,
      Dictionary,
+      RecordBatch: ArrowRecordBatch,
+      Table: ArrowTable,
      Uint8: ArrowUint8,
+      makeData: arrowMakeData,
+      vectorFromArray,
      // biome-ignore lint/suspicious/noExplicitAny: <explanation>
    } = <any>arrow;
    type Schema = ApacheArrow["Schema"];
@@ -1054,6 +1061,114 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
    });

    describe("when using two versions of arrow", function () {
+      it("preserves a dictionary shared by multiple fields", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const batch = new ArrowRecordBatch({
+          first: dictionaryVector.data[0],
+          second: dictionaryVector.data[0],
+        });
+        const table = new ArrowTable([batch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("first")!]).toEqual(values);
+        expect([...sanitized.getChild("second")!]).toEqual(values);
+        const firstType = sanitized.schema.fields[0].type as {
+          dictionary: unknown;
+        };
+        const secondType = sanitized.schema.fields[1].type as {
+          dictionary: unknown;
+        };
+        expect(secondType.dictionary).toBe(firstType.dictionary);
+        expect(sanitized.batches[0].data.children[1].dictionary).toBe(
+          sanitized.batches[0].data.children[0].dictionary,
+        );
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("first")!]).toEqual(values);
+        expect([...actual.getChild("second")!]).toEqual(values);
+      });
+
+      it("preserves shared dictionary data from another Arrow version", async function () {
+        const values = ["alpha", "beta", "alpha"];
+        const dictionaryVector = vectorFromArray(values);
+        const firstBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(0, 2).data[0],
+        });
+        const secondBatch = new ArrowRecordBatch({
+          label: dictionaryVector.slice(2).data[0],
+        });
+        const table = new ArrowTable([firstBatch, secondBatch]);
+
+        const sanitized = sanitizeTable(table);
+        expect([...sanitized.getChild("label")!]).toEqual(values);
+
+        const dictionaries = sanitized.batches.map(
+          (batch) => batch.data.children[0].dictionary,
+        );
+        expect(dictionaries[0]).toBeInstanceOf(CurrentVector);
+        expect(dictionaries[1]).toBe(dictionaries[0]);
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(values);
+      });
+
+      it("preserves shared chunks in growing dictionaries", async function () {
+        const type = new Dictionary(new Utf8(), new Int32(), 42, false);
+        const firstDictionary = vectorFromArray(["alpha", "beta"], new Utf8());
+        const secondDictionary = firstDictionary.concat(
+          vectorFromArray(["gamma"], new Utf8()),
+        );
+        const firstData = arrowMakeData({
+          type,
+          data: Int32Array.from([0, 1]),
+          dictionary: firstDictionary,
+        });
+        const secondData = arrowMakeData({
+          type,
+          data: Int32Array.from([2]),
+          dictionary: secondDictionary,
+        });
+        const table = new ArrowTable([
+          new ArrowRecordBatch({ label: firstData }),
+          new ArrowRecordBatch({ label: secondData }),
+        ]);
+
+        const sanitized = sanitizeTable(table);
+        const expected = ["alpha", "beta", "gamma"];
+        expect([...sanitized.getChild("label")!]).toEqual(expected);
+        const firstLocalDictionary =
+          sanitized.batches[0].data.children[0].dictionary!;
+        const secondLocalDictionary =
+          sanitized.batches[1].data.children[0].dictionary!;
+        expect(secondLocalDictionary.data[0]).toBe(
+          firstLocalDictionary.data[0],
+        );
+
+        const buf = await fromTableToBuffer(sanitized);
+        const actual = currentTableFromIPC(buf);
+        expect([...actual.getChild("label")!]).toEqual(expected);
+      });
+
+      it("can serialize list data from another Arrow version", async function () {
+        const values = [["anime", "action"], [], null];
+        const vector = vectorFromArray(
+          values,
+          new List(new Field("item", new Utf8(), true)),
+        );
+        const table = new ArrowTable({ tags: vector });
+
+        const buf = await fromDataToBuffer(table);
+        const actual = currentTableFromIPC(buf);
+        const actualTags = actual.getChild("tags");
+
+        expect(actualTags?.get(0)?.toJSON()).toEqual(values[0]);
+        expect(actualTags?.get(1)?.toJSON()).toEqual(values[1]);
+        expect(actualTags?.get(2)).toBeNull();
+      });
+
      it("can still import data", async function () {
        const schema = new arrow15.Schema([
          new arrow15.Field("id", new arrow15.Int32()),
@@ -277,8 +277,16 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
        },
        numIndices: 0,
        numRows: 3,
-        totalBytes: 44,
+        // Full on-disk size of the two data files, footers and metadata included.
+        totalBytes: 684,
      });
+
+      // Index files count toward totalBytes too (only deletion files and
+      // manifests are excluded).
+      await table.createIndex("id", { config: Index.btree() });
+      const statsWithIndex = await table.stats();
+      expect(statsWithIndex.numIndices).toBe(1);
+      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
    });

    it("should overwrite data if asked", async () => {
@@ -9,7 +9,7 @@
 // comes from the exact same library instance.  This is not always the case
 // and so we must sanitize the input to ensure that it is compatible.

-import { BufferType, Data } from "apache-arrow";
+import { BufferType, Data, Vector } from "apache-arrow";
 import type { IntBitWidth, TKeys, TimeBitWidth } from "apache-arrow/type";
 import {
  Binary,
@@ -74,6 +74,20 @@ import {
  Utf8,
 } from "./arrow";

+type SanitizationContext = {
+  types: WeakMap<object, DataType>;
+  vectors: WeakMap<object, Vector>;
+  data: WeakMap<object, Data<DataType>>;
+};
+
+function createSanitizationContext(): SanitizationContext {
+  return {
+    types: new WeakMap(),
+    vectors: new WeakMap(),
+    data: new WeakMap(),
+  };
+}
+
 export function sanitizeMetadata(
  metadataLike?: unknown,
 ): Map<string, string> | undefined {
@@ -186,6 +200,13 @@ export function sanitizeInterval(typeLike: object) {
 }

 export function sanitizeList(typeLike: object) {
+  return sanitizeListWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeListWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
    throw Error(
      "Expected a List type to have an array-like `children` property",
@@ -194,19 +215,35 @@ export function sanitizeList(typeLike: object) {
  if (typeLike.children.length !== 1) {
    throw Error("Expected a List type to have exactly one child");
  }
-  return new List(sanitizeField(typeLike.children[0]));
+  return new List(sanitizeFieldWithContext(typeLike.children[0], context));
 }

 export function sanitizeStruct(typeLike: object) {
+  return sanitizeStructWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeStructWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
    throw Error(
      "Expected a Struct type to have an array-like `children` property",
    );
  }
-  return new Struct(typeLike.children.map((child) => sanitizeField(child)));
+  return new Struct(
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
+  );
 }

 export function sanitizeUnion(typeLike: object) {
+  return sanitizeUnionWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeUnionWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (
    !("typeIds" in typeLike) ||
    !("mode" in typeLike) ||
@@ -226,7 +263,7 @@ export function sanitizeUnion(typeLike: object) {
    typeLike.mode,
    // biome-ignore lint/suspicious/noExplicitAny: skip
    typeLike.typeIds as any,
-    typeLike.children.map((child) => sanitizeField(child)),
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
  );
 }

@@ -234,6 +271,19 @@ export function sanitizeTypedUnion(
  typeLike: object,
  // eslint-disable-next-line @typescript-eslint/naming-convention
  UnionType: typeof DenseUnion | typeof SparseUnion,
+) {
+  return sanitizeTypedUnionWithContext(
+    typeLike,
+    UnionType,
+    createSanitizationContext(),
+  );
+}
+
+function sanitizeTypedUnionWithContext(
+  typeLike: object,
+  // eslint-disable-next-line @typescript-eslint/naming-convention
+  UnionType: typeof DenseUnion | typeof SparseUnion,
+  context: SanitizationContext,
 ) {
  if (!("typeIds" in typeLike)) {
    throw Error(
@@ -248,7 +298,7 @@ export function sanitizeTypedUnion(

  return new UnionType(
    typeLike.typeIds as Int32Array | number[],
-    typeLike.children.map((child) => sanitizeField(child)),
+    typeLike.children.map((child) => sanitizeFieldWithContext(child, context)),
  );
 }

@@ -262,6 +312,16 @@ export function sanitizeFixedSizeBinary(typeLike: object) {
 }

 export function sanitizeFixedSizeList(typeLike: object) {
+  return sanitizeFixedSizeListWithContext(
+    typeLike,
+    createSanitizationContext(),
+  );
+}
+
+function sanitizeFixedSizeListWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("listSize" in typeLike) || typeof typeLike.listSize !== "number") {
    throw Error("Expected a FixedSizeList type to have a `listSize` property");
  }
@@ -275,11 +335,18 @@ export function sanitizeFixedSizeList(typeLike: object) {
  }
  return new FixedSizeList(
    typeLike.listSize,
-    sanitizeField(typeLike.children[0]),
+    sanitizeFieldWithContext(typeLike.children[0], context),
  );
 }

 export function sanitizeMap(typeLike: object) {
+  return sanitizeMapWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeMapWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("children" in typeLike) || !Array.isArray(typeLike.children)) {
    throw Error(
      "Expected a Map type to have an array-like `children` property",
@@ -292,7 +359,10 @@ export function sanitizeMap(typeLike: object) {
    throw Error("Expected a Map type to have exactly one child");
  }

-  return new Map_(sanitizeField(typeLike.children[0]), typeLike.keysSorted);
+  return new Map_(
+    sanitizeFieldWithContext(typeLike.children[0], context),
+    typeLike.keysSorted,
+  );
 }

 export function sanitizeDuration(typeLike: object) {
@@ -303,6 +373,13 @@ export function sanitizeDuration(typeLike: object) {
 }

 export function sanitizeDictionary(typeLike: object) {
+  return sanitizeDictionaryWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeDictionaryWithContext(
+  typeLike: object,
+  context: SanitizationContext,
+) {
  if (!("id" in typeLike) || typeof typeLike.id !== "number") {
    throw Error("Expected a Dictionary type to have an `id` property");
  }
@@ -316,8 +393,8 @@ export function sanitizeDictionary(typeLike: object) {
    throw Error("Expected a Dictionary type to have an `isOrdered` property");
  }
  return new Dictionary(
-    sanitizeType(typeLike.dictionary),
-    sanitizeType(typeLike.indices) as TKeys,
+    sanitizeTypeWithContext(typeLike.dictionary, context),
+    sanitizeTypeWithContext(typeLike.indices, context) as TKeys,
    typeLike.id,
    typeLike.isOrdered,
  );
@@ -325,12 +402,23 @@ export function sanitizeDictionary(typeLike: object) {

 // biome-ignore lint/suspicious/noExplicitAny: skip
 export function sanitizeType(typeLike: unknown): DataType<any> {
+  return sanitizeTypeWithContext(typeLike, createSanitizationContext());
+}
+
+function sanitizeTypeWithContext(
+  typeLike: unknown,
+  context: SanitizationContext,
+): DataType {
  if (typeof typeLike === "string") {
    return dataTypeFromName(typeLike);
  }
  if (typeof typeLike !== "object" || typeLike === null) {
    throw Error("Expected a Type but object was null/undefined");
  }
+  const cached = context.types.get(typeLike);
+  if (cached !== undefined) {
+    return cached;
+  }
  if (
    !("typeId" in typeLike) ||
    !(
@@ -349,6 +437,16 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
    throw Error("Type's typeId property was not a function or number");
  }

+  const type = sanitizeTypeById(typeLike, typeId, context);
+  context.types.set(typeLike, type);
+  return type;
+}
+
+function sanitizeTypeById(
+  typeLike: object,
+  typeId: Type,
+  context: SanitizationContext,
+): DataType {
  switch (typeId) {
    case Type.NONE:
      throw Error("Received a Type with a typeId of NONE");
@@ -375,21 +473,21 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
    case Type.Interval:
      return sanitizeInterval(typeLike);
    case Type.List:
-      return sanitizeList(typeLike);
+      return sanitizeListWithContext(typeLike, context);
    case Type.Struct:
-      return sanitizeStruct(typeLike);
+      return sanitizeStructWithContext(typeLike, context);
    case Type.Union:
-      return sanitizeUnion(typeLike);
+      return sanitizeUnionWithContext(typeLike, context);
    case Type.FixedSizeBinary:
      return sanitizeFixedSizeBinary(typeLike);
    case Type.FixedSizeList:
-      return sanitizeFixedSizeList(typeLike);
+      return sanitizeFixedSizeListWithContext(typeLike, context);
    case Type.Map:
-      return sanitizeMap(typeLike);
+      return sanitizeMapWithContext(typeLike, context);
    case Type.Duration:
      return sanitizeDuration(typeLike);
    case Type.Dictionary:
-      return sanitizeDictionary(typeLike);
+      return sanitizeDictionaryWithContext(typeLike, context);
    case Type.Int8:
      return new Int8();
    case Type.Int16:
@@ -433,9 +531,9 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
    case Type.TimestampSecond:
      return sanitizeTypedTimestamp(typeLike, TimestampSecond);
    case Type.DenseUnion:
-      return sanitizeTypedUnion(typeLike, DenseUnion);
+      return sanitizeTypedUnionWithContext(typeLike, DenseUnion, context);
    case Type.SparseUnion:
-      return sanitizeTypedUnion(typeLike, SparseUnion);
+      return sanitizeTypedUnionWithContext(typeLike, SparseUnion, context);
    case Type.IntervalDayTime:
      return new IntervalDayTime();
    case Type.IntervalYearMonth:
@@ -454,6 +552,13 @@ export function sanitizeType(typeLike: unknown): DataType<any> {
 }

 export function sanitizeField(fieldLike: unknown): Field {
+  return sanitizeFieldWithContext(fieldLike, createSanitizationContext());
+}
+
+function sanitizeFieldWithContext(
+  fieldLike: unknown,
+  context: SanitizationContext,
+): Field {
  if (fieldLike instanceof Field) {
    return fieldLike;
  }
@@ -471,7 +576,7 @@ export function sanitizeField(fieldLike: unknown): Field {
  }
  let type: DataType;
  try {
-    type = sanitizeType(fieldLike.type);
+    type = sanitizeTypeWithContext(fieldLike.type, context);
  } catch (error: unknown) {
    throw Error(
      `Unable to sanitize type for field: ${fieldLike.name} due to error: ${error}`,
@@ -501,6 +606,13 @@ export function sanitizeField(fieldLike: unknown): Field {
 * than lancedb is using.
 */
 export function sanitizeSchema(schemaLike: SchemaLike): Schema {
+  return sanitizeSchemaWithContext(schemaLike, createSanitizationContext());
+}
+
+function sanitizeSchemaWithContext(
+  schemaLike: SchemaLike,
+  context: SanitizationContext,
+): Schema {
  if (schemaLike instanceof Schema) {
    return schemaLike;
  }
@@ -522,7 +634,7 @@ export function sanitizeSchema(schemaLike: SchemaLike): Schema {
    );
  }
  const sanitizedFields = schemaLike.fields.map((field) =>
-    sanitizeField(field),
+    sanitizeFieldWithContext(field, context),
  );
  return new Schema(sanitizedFields, metadata);
 }
@@ -544,13 +656,18 @@ export function sanitizeTable(tableLike: TableLike): Table {
      "The table passed in does not appear to be a table (no 'columns' property)",
    );
  }
-  const schema = sanitizeSchema(tableLike.schema);
-
-  const batches = tableLike.batches.map(sanitizeRecordBatch);
+  const context = createSanitizationContext();
+  const schema = sanitizeSchemaWithContext(tableLike.schema, context);
+  const batches = tableLike.batches.map((batch) =>
+    sanitizeRecordBatch(batch, context),
+  );
  return new Table(schema, batches);
 }

-function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
+function sanitizeRecordBatch(
+  batchLike: RecordBatchLike,
+  context: SanitizationContext,
+): RecordBatch {
  if (batchLike instanceof RecordBatch) {
    return batchLike;
  }
@@ -567,19 +684,43 @@ function sanitizeRecordBatch(batchLike: RecordBatchLike): RecordBatch {
      "The record batch passed in does not appear to be a record batch (no 'data' property)",
    );
  }
-  const schema = sanitizeSchema(batchLike.schema);
-  const data = sanitizeData(batchLike.data);
+  const schema = sanitizeSchemaWithContext(batchLike.schema, context);
+  const data = sanitizeData(batchLike.data, context) as Data<Struct>;
  return new RecordBatch(schema, data);
 }
+
+type DictionaryVectorLike = {
+  data: readonly DataLike[];
+};
+
+type DictionaryDataLike = DataLike & {
+  dictionary?: DictionaryVectorLike;
+};
+
 function sanitizeData(
  dataLike: DataLike,
-  // biome-ignore lint/suspicious/noExplicitAny: <explanation>
-): import("apache-arrow").Data<Struct<any>> {
+  context: SanitizationContext,
+): Data<DataType> {
  if (dataLike instanceof Data) {
    return dataLike;
  }
-  return new Data(
-    dataLike.type,
+  const cachedData = context.data.get(dataLike);
+  if (cachedData !== undefined) {
+    return cachedData;
+  }
+  const dictionaryLike = (dataLike as DictionaryDataLike).dictionary;
+  let dictionary: Vector | undefined;
+  if (dictionaryLike !== undefined) {
+    dictionary = context.vectors.get(dictionaryLike);
+    if (dictionary === undefined) {
+      dictionary = new Vector(
+        dictionaryLike.data.map((data) => sanitizeData(data, context)),
+      );
+      context.vectors.set(dictionaryLike, dictionary);
+    }
+  }
+  const data = new Data(
+    sanitizeTypeWithContext(dataLike.type, context),
    dataLike.offset,
    dataLike.length,
    dataLike.nullCount,
@@ -589,7 +730,11 @@ function sanitizeData(
      [BufferType.VALIDITY]: dataLike.nullBitmap,
      [BufferType.TYPE]: dataLike.typeIds,
    },
+    dataLike.children.map((child) => sanitizeData(child, context)),
+    dictionary,
  );
+  context.data.set(dataLike, data);
+  return data;
 }

 const constructorsByTypeName = {
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",
@@ -1,6 +1,6 @@
 {
  "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.37.1-beta.0",
+  "version": "0.37.1",
  "os": [
    "win32"
  ],
@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.37.1-beta.0",
+	"version": "0.37.1",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",
@@ -1,12 +1,12 @@
 {
  "name": "@lancedb/lancedb",
-  "version": "0.37.1-beta.0",
+  "version": "0.37.1",
  "lockfileVersion": 3,
  "requires": true,
  "packages": {
    "": {
      "name": "@lancedb/lancedb",
-      "version": "0.37.1-beta.0",
+      "version": "0.37.1",
      "cpu": [
        "x64",
        "arm64"
@@ -11,7 +11,7 @@
    "ann"
  ],
  "private": false,
-  "version": "0.37.1-beta.0",
+  "version": "0.37.1",
  "main": "dist/index.js",
  "exports": {
    ".": "./dist/index.js",
@@ -1043,7 +1043,10 @@ impl From<lancedb::index::IndexStatistics> for IndexStatistics {

 #[napi(object)]
 pub struct TableStatistics {
-    /// The total number of bytes in the table
+    /// The total size, in bytes, of the table's data files, index files, and
+    /// overlay files
+    ///
+    /// Read from the manifest, so this excludes deletion files and manifests.
    pub total_bytes: i64,

    /// The number of rows in the table
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"
@@ -63,7 +63,7 @@ tests = [
    "polars>=0.19, <=1.32.3",
    "pyarrow<25",
    "pyarrow-stubs>=16.0",
-    "pylance==9.0.0rc1",
+    "pylance==10.0.0",
    "requests>=2.31.0",
    "datafusion>=54,<55",
    "opentelemetry-sdk>=1.30.0",
@@ -87,12 +87,13 @@ class JinaEmbeddings(EmbeddingFunction):
        if isinstance(image, bytes):
            image_dict = {"image": base64.b64encode(image).decode("utf-8")}
        elif isinstance(image, (str, Path)):
-            parsed = urlparse.urlparse(image)
-            # TODO handle drive letter on windows.
+            parsed = urlparse(str(image))
            PIL_Image = attempt_import_or_raise("PIL.Image", "pillow")
            if parsed.scheme == "file":
                pil_image = PIL_Image.open(parsed.path)
-            elif parsed.scheme == "":
+            elif parsed.scheme == "" or (os.name == "nt" and len(parsed.scheme) == 1):
+                # A Windows drive letter parses as a one-character scheme
+                # ("C:\\img.png" -> scheme="c"), so treat it as a local path.
                pil_image = PIL_Image.open(image if os.name == "nt" else parsed.path)
            elif parsed.scheme.startswith("http"):
                pil_image = PIL_Image.open(io.BytesIO(url_retrieve(image)))
@@ -6334,7 +6334,9 @@ class TableStatistics:
    Attributes
    ----------
    total_bytes: int
-        The total number of bytes in the table.
+        The total size, in bytes, of the table's data files, index files, and
+        overlay files. Read from the manifest, so this excludes deletion files
+        and manifests.
    num_rows: int
        The total number of rows in the table.
    num_indices: int
@@ -631,3 +631,23 @@ def test_url_retrieve_downloads_image():
    image_bytes = url_retrieve(image_url)
    img = Image.open(io.BytesIO(image_bytes))
    assert img.size[0] > 0 and img.size[1] > 0
+
+
+def test_jina_generate_image_input_dict_local_path(tmp_path):
+    """
+    JinaEmbeddings._generate_image_input_dict must accept a local image path
+    (str or Path), not just bytes. Previously it crashed with
+    `AttributeError: 'function' object has no attribute 'urlparse'` on any
+    str/Path input because it called `urlparse.urlparse(image)` instead of
+    `urlparse(image)` (urlparse was imported as a function, not a module).
+    """
+    Image = pytest.importorskip("PIL.Image")
+    from lancedb.embeddings.jinaai import JinaEmbeddings
+
+    image_path = tmp_path / "test.png"
+    Image.new("RGB", (4, 4), color="red").save(image_path, format="PNG")
+
+    for image in (str(image_path), image_path):
+        image_dict = JinaEmbeddings._generate_image_input_dict(image)
+        assert "image" in image_dict
+        assert isinstance(image_dict["image"], str) and len(image_dict["image"]) > 0
@@ -3713,7 +3713,8 @@ def test_stats(mem_db: DBConnection):
    stats = table.stats()
    print(f"{stats=}")
    assert stats == {
-        "total_bytes": 60,
+        # Full on-disk size of the data file, footer and metadata included.
+        "total_bytes": 633,
        "num_rows": 2,
        "num_indices": 0,
        "fragment_stats": {
@@ -3731,6 +3732,13 @@ def test_stats(mem_db: DBConnection):
        },
    }

+    # Index files count toward total_bytes too (only deletion files and
+    # manifests are excluded).
+    table.create_index("id", config=BTree())
+    stats_with_index = table.stats()
+    assert stats_with_index["num_indices"] == 1
+    assert stats_with_index["total_bytes"] > stats["total_bytes"]
+

 def test_create_table_empty_list_with_schema(mem_db: DBConnection):
    """Test creating table with empty list data and schema
@@ -799,7 +799,7 @@ name = "cuda-bindings"
 version = "13.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "cuda-pathfinder", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "cuda-pathfinder" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/a9/21/8464d133752951c154feafb3b65c297e7d80f301183d220bec4c830f1441/cuda_bindings-13.3.1-cp310-cp310-manylinux_2_24_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:120fcc53d57903df529c3486962c56528cba5b7d6c57c99537320ed9922c8b86", size = 6073403, upload-time = "2026-05-29T23:11:36.22Z" },
@@ -834,37 +834,37 @@ wheels = [

 [package.optional-dependencies]
 cublas = [
-    { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cublas" },
 ]
 cudart = [
-    { name = "nvidia-cuda-runtime", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cuda-runtime" },
 ]
 cufft = [
-    { name = "nvidia-cufft", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cufft" },
 ]
 cufile = [
-    { name = "nvidia-cufile", marker = "sys_platform == 'linux'" },
+    { name = "nvidia-cufile" },
 ]
 cupti = [
-    { name = "nvidia-cuda-cupti", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cuda-cupti" },
 ]
 curand = [
-    { name = "nvidia-curand", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-curand" },
 ]
 cusolver = [
-    { name = "nvidia-cusolver", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cusolver" },
 ]
 cusparse = [
-    { name = "nvidia-cusparse", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cusparse" },
 ]
 nvjitlink = [
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-nvjitlink" },
 ]
 nvrtc = [
-    { name = "nvidia-cuda-nvrtc", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-cuda-nvrtc" },
 ]
 nvtx = [
-    { name = "nvidia-nvtx", marker = "(python_full_version < '3.14' and sys_platform == 'win32') or sys_platform == 'linux'" },
+    { name = "nvidia-nvtx" },
 ]

 [[package]]
@@ -1023,7 +1023,7 @@ name = "exceptiongroup"
 version = "1.3.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+    { name = "typing-extensions" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/50/79/66800aadf48771f6b62f7eb014e352e5d06856655206165d775e675a02c9/exceptiongroup-1.3.1.tar.gz", hash = "sha256:8b412432c6055b0b7d14c310000ae93352ed6754f70fa8f7c34141f91c4e3219", size = 30371, upload-time = "2025-11-21T23:01:54.787Z" }
 wheels = [
@@ -1440,16 +1440,16 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "cachetools", marker = "python_full_version < '3.11'" },
-    { name = "certifi", marker = "python_full_version < '3.11'" },
-    { name = "httpx", marker = "python_full_version < '3.11'" },
-    { name = "ibm-cos-sdk", marker = "python_full_version < '3.11'" },
-    { name = "lomond", marker = "python_full_version < '3.11'" },
-    { name = "packaging", marker = "python_full_version < '3.11'" },
-    { name = "pandas", version = "2.2.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "requests", marker = "python_full_version < '3.11'" },
-    { name = "tabulate", marker = "python_full_version < '3.11'" },
-    { name = "urllib3", marker = "python_full_version < '3.11'" },
+    { name = "cachetools" },
+    { name = "certifi" },
+    { name = "httpx" },
+    { name = "ibm-cos-sdk" },
+    { name = "lomond" },
+    { name = "packaging" },
+    { name = "pandas", version = "2.2.3", source = { registry = "https://pypi.org/simple" } },
+    { name = "requests" },
+    { name = "tabulate" },
+    { name = "urllib3" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/c7/56/2e3df38a1f13062095d7bde23c87a92f3898982993a15186b1bfecbd206f/ibm_watsonx_ai-1.3.42.tar.gz", hash = "sha256:ee5be59009004245d957ce97d1227355516df95a2640189749487614fef674ff", size = 688651, upload-time = "2025-10-01T13:35:41.527Z" }
 wheels = [
@@ -1468,17 +1468,17 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "cachetools", marker = "python_full_version >= '3.11'" },
-    { name = "certifi", marker = "python_full_version >= '3.11'" },
-    { name = "httpx", marker = "python_full_version >= '3.11'" },
-    { name = "ibm-cos-sdk", marker = "python_full_version >= '3.11'" },
-    { name = "lomond", marker = "python_full_version >= '3.11'" },
-    { name = "packaging", marker = "python_full_version >= '3.11'" },
-    { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
+    { name = "cachetools" },
+    { name = "certifi" },
+    { name = "httpx" },
+    { name = "ibm-cos-sdk" },
+    { name = "lomond" },
+    { name = "packaging" },
+    { name = "pandas", version = "2.3.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.14'" },
    { name = "pandas", version = "3.0.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.14'" },
-    { name = "requests", marker = "python_full_version >= '3.11'" },
-    { name = "tabulate", marker = "python_full_version >= '3.11'" },
-    { name = "urllib3", marker = "python_full_version >= '3.11'" },
+    { name = "requests" },
+    { name = "tabulate" },
+    { name = "urllib3" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/29/a3/c756b534696ab2f3f29882fdb7ca7198b7a5c94e10c0a3a327853d6d6b79/ibm_watsonx_ai-1.5.14.tar.gz", hash = "sha256:a756488bd57e87c0fc51be42dcba871143cfe0ac1e805c497c5047e1e4f13e9d", size = 735804, upload-time = "2026-06-22T12:32:43.85Z" }
 wheels = [
@@ -1554,17 +1554,17 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "colorama", marker = "python_full_version < '3.11' and sys_platform == 'win32'" },
-    { name = "decorator", marker = "python_full_version < '3.11'" },
-    { name = "exceptiongroup", marker = "python_full_version < '3.11'" },
-    { name = "jedi", marker = "python_full_version < '3.11'" },
-    { name = "matplotlib-inline", marker = "python_full_version < '3.11'" },
-    { name = "pexpect", marker = "python_full_version < '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" },
-    { name = "prompt-toolkit", marker = "python_full_version < '3.11'" },
-    { name = "pygments", marker = "python_full_version < '3.11'" },
-    { name = "stack-data", marker = "python_full_version < '3.11'" },
-    { name = "traitlets", marker = "python_full_version < '3.11'" },
-    { name = "typing-extensions", marker = "python_full_version < '3.11'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "decorator" },
+    { name = "exceptiongroup" },
+    { name = "jedi" },
+    { name = "matplotlib-inline" },
+    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit" },
+    { name = "pygments" },
+    { name = "stack-data" },
+    { name = "traitlets" },
+    { name = "typing-extensions" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/40/18/f8598d287006885e7136451fdea0755af4ebcbfe342836f24deefaed1164/ipython-8.39.0.tar.gz", hash = "sha256:4110ae96012c379b8b6db898a07e186c40a2a1ef5d57a7fa83166047d9da7624", size = 5513971, upload-time = "2026-03-27T10:02:13.94Z" }
 wheels = [
@@ -1583,18 +1583,18 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "colorama", marker = "python_full_version >= '3.11' and sys_platform == 'win32'" },
-    { name = "decorator", marker = "python_full_version >= '3.11'" },
-    { name = "ipython-pygments-lexers", marker = "python_full_version >= '3.11'" },
-    { name = "jedi", marker = "python_full_version >= '3.11'" },
-    { name = "matplotlib-inline", marker = "python_full_version >= '3.11'" },
-    { name = "pexpect", marker = "python_full_version >= '3.11' and sys_platform != 'emscripten' and sys_platform != 'win32'" },
-    { name = "prompt-toolkit", marker = "python_full_version >= '3.11'" },
-    { name = "psutil", marker = "python_full_version >= '3.11' and sys_platform != 'cygwin' and sys_platform != 'emscripten'" },
-    { name = "pygments", marker = "python_full_version >= '3.11'" },
-    { name = "stack-data", marker = "python_full_version >= '3.11'" },
-    { name = "traitlets", marker = "python_full_version >= '3.11'" },
-    { name = "typing-extensions", marker = "python_full_version == '3.11.*'" },
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "decorator" },
+    { name = "ipython-pygments-lexers" },
+    { name = "jedi" },
+    { name = "matplotlib-inline" },
+    { name = "pexpect", marker = "sys_platform != 'emscripten' and sys_platform != 'win32'" },
+    { name = "prompt-toolkit" },
+    { name = "psutil", marker = "sys_platform != 'cygwin' and sys_platform != 'emscripten'" },
+    { name = "pygments" },
+    { name = "stack-data" },
+    { name = "traitlets" },
+    { name = "typing-extensions", marker = "python_full_version < '3.12'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/53/59/165d3b4d75cc34add3122c4417ecb229085140ac573103c223cd01dde96f/ipython-9.15.0.tar.gz", hash = "sha256:da2819ce2aa83135257df830660b1176d986c3d2876db24df01974fa955b2756", size = 4442580, upload-time = "2026-06-26T11:03:35.913Z" }
 wheels = [
@@ -1606,7 +1606,7 @@ name = "ipython-pygments-lexers"
 version = "1.1.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "pygments", marker = "python_full_version >= '3.11'" },
+    { name = "pygments" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/ef/4c/5dd1d8af08107f88c7f741ead7a40854b8ac24ddf9ae850afbcf698aa552/ipython_pygments_lexers-1.1.1.tar.gz", hash = "sha256:09c0138009e56b6854f9535736f4171d855c8c08a563a0dcd8022f78355c7e81", size = 8393, upload-time = "2025-01-17T11:24:34.505Z" }
 wheels = [
@@ -2005,7 +2005,7 @@ requires-dist = [
    { name = "pyarrow-stubs", marker = "extra == 'tests'", specifier = ">=16.0" },
    { name = "pydantic", specifier = ">=1.10" },
    { name = "pylance", marker = "extra == 'pylance'", specifier = ">=5.0.0b5" },
-    { name = "pylance", marker = "extra == 'tests'", specifier = "==9.0.0rc1" },
+    { name = "pylance", marker = "extra == 'tests'", specifier = "==10.0.0" },
    { name = "pyright", marker = "extra == 'dev'", specifier = ">=1.1.350" },
    { name = "pytest", marker = "extra == 'tests'", specifier = ">=7.0" },
    { name = "pytest-asyncio", marker = "extra == 'tests'", specifier = ">=0.21" },
@@ -2858,7 +2858,7 @@ name = "nvidia-cudnn-cu13"
 version = "9.19.0.56"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-cublas" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/f1/84/26025437c1e6b61a707442184fa0c03d083b661adf3a3eecfd6d21677740/nvidia_cudnn_cu13-9.19.0.56-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:6ed29ffaee1176c612daf442e4dd6cfeb6a0caa43ddcbeb59da94953030b1be4", size = 433781201, upload-time = "2026-02-03T20:40:53.805Z" },
@@ -2870,7 +2870,7 @@ name = "nvidia-cufft"
 version = "12.0.0.61"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-nvjitlink" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/8b/ae/f417a75c0259e85c1d2f83ca4e960289a5f814ed0cea74d18c353d3e989d/nvidia_cufft-12.0.0.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:2708c852ef8cd89d1d2068bdbece0aa188813a0c934db3779b9b1faa8442e5f5", size = 214053554, upload-time = "2025-09-04T08:31:38.196Z" },
@@ -2900,9 +2900,9 @@ name = "nvidia-cusolver"
 version = "12.0.4.66"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-cublas", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
-    { name = "nvidia-cusparse", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-cublas" },
+    { name = "nvidia-cusparse" },
+    { name = "nvidia-nvjitlink" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/c8/c3/b30c9e935fc01e3da443ec0116ed1b2a009bb867f5324d3f2d7e533e776b/nvidia_cusolver-12.0.4.66-py3-none-manylinux_2_27_aarch64.whl", hash = "sha256:02c2457eaa9e39de20f880f4bd8820e6a1cfb9f9a34f820eb12a155aa5bc92d2", size = 223467760, upload-time = "2025-09-04T08:33:04.222Z" },
@@ -2914,7 +2914,7 @@ name = "nvidia-cusparse"
 version = "12.6.3.3"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "nvidia-nvjitlink", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "nvidia-nvjitlink" },
 ]
 wheels = [
    { url = "https://files.pythonhosted.org/packages/f8/94/5c26f33738ae35276672f12615a64bd008ed5be6d1ebcb23579285d960a9/nvidia_cusparse-12.6.3.3-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:80bcc4662f23f1054ee334a15c72b8940402975e0eab63178fc7e670aa59472c", size = 162155568, upload-time = "2025-09-04T08:33:42.864Z" },
@@ -3091,10 +3091,10 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "python-dateutil", marker = "python_full_version < '3.11'" },
-    { name = "pytz", marker = "python_full_version < '3.11'" },
-    { name = "tzdata", marker = "python_full_version < '3.11'" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } },
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "tzdata" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/9c/d6/9f8431bacc2e19dca897724cd097b1bb224a6ad5433784a44b587c7c13af/pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667", size = 4399213, upload-time = "2024-09-20T13:10:04.827Z" }
 wheels = [
@@ -3143,11 +3143,11 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12' or python_full_version >= '3.14'" },
    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12' and python_full_version < '3.14'" },
-    { name = "python-dateutil", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
-    { name = "pytz", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
-    { name = "tzdata", marker = "python_full_version >= '3.11' and python_full_version < '3.14'" },
+    { name = "python-dateutil" },
+    { name = "pytz" },
+    { name = "tzdata" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/33/01/d40b85317f86cf08d853a4f495195c73815fdf205eef3993821720274518/pandas-2.3.3.tar.gz", hash = "sha256:e05e1af93b977f7eafa636d043f9f94c7ee3ac81af99c13508215942e64c993b", size = 4495223, upload-time = "2025-09-29T23:34:51.853Z" }
 wheels = [
@@ -3210,9 +3210,9 @@ resolution-markers = [
    "python_full_version >= '3.14' and sys_platform != 'emscripten' and sys_platform != 'win32'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.14'" },
-    { name = "python-dateutil", marker = "python_full_version >= '3.14'" },
-    { name = "tzdata", marker = "(python_full_version >= '3.14' and sys_platform == 'emscripten') or (python_full_version >= '3.14' and sys_platform == 'win32')" },
+    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" } },
+    { name = "python-dateutil" },
+    { name = "tzdata", marker = "sys_platform == 'emscripten' or sys_platform == 'win32'" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/f8/87/4341c6252d1c47b08768c3d25ac487362bf403f0313ddae4a2a26c9b1b4c/pandas-3.0.3.tar.gz", hash = "sha256:696a4a00a2a2a35d4e5deb3fc946641b96c944f02230e4f76137fe35d806c4fc", size = 4651414, upload-time = "2026-05-11T18:54:29.21Z" }
 wheels = [
@@ -3320,7 +3320,7 @@ name = "pexpect"
 version = "4.9.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
-    { name = "ptyprocess", marker = "(python_full_version < '3.14' and sys_platform == 'emscripten') or (python_full_version < '3.14' and sys_platform == 'win32') or (sys_platform != 'emscripten' and sys_platform != 'win32')" },
+    { name = "ptyprocess" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/42/92/cc564bf6381ff43ce1f4d06852fc19a2f11d180f23dc32d9588bee2f149d/pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f", size = 166450, upload-time = "2023-11-25T09:07:26.339Z" }
 wheels = [
@@ -3912,7 +3912,7 @@ crypto = [

 [[package]]
 name = "pylance"
-version = "7.0.0"
+version = "10.0.0"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
    { name = "lance-namespace" },
@@ -3922,12 +3922,12 @@ dependencies = [
    { name = "pyarrow" },
 ]
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/ac/ad/2f64921bf346e7075aef24a72595db44821724a3d89a9a92dd24e79632aa/pylance-7.0.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:98422021975be76e72b1572f41b8c9abb3bee5bdc9bfa5e9ce731110a65ed4d1", size = 62134146, upload-time = "2026-05-27T21:59:37.459Z" },
-    { url = "https://files.pythonhosted.org/packages/73/1c/c5a01bee0160b55d9a98895cbd33091d038f0a0995b121ab72e629008d02/pylance-7.0.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4bec86ee5b6fbd8bfc493e653f0a1fba0303cfe5492b9b46fc25ab908edc7183", size = 65373684, upload-time = "2026-05-27T22:04:01.584Z" },
-    { url = "https://files.pythonhosted.org/packages/eb/da/1fe8b8f7dbfe734d76af76acc994fc360a0d0c79a4874ef69f5a72a58fe3/pylance-7.0.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881491432c53184e52f8d1db8d5f872f39a03f36fb104bec77b33d379519d8b5", size = 69458555, upload-time = "2026-05-27T22:16:50.567Z" },
-    { url = "https://files.pythonhosted.org/packages/76/f0/dd505cf3fd0226ab9d94759acd713125af1d3bfacfd80bbd52e3b9f89509/pylance-7.0.0-cp39-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:18453999e7fff4f76b16d6b7882c9df0628bd142ff95e2461bd7dd5ee3fe0af3", size = 65394430, upload-time = "2026-05-27T22:05:30.923Z" },
-    { url = "https://files.pythonhosted.org/packages/17/ba/2357b81034f28eb00790e258ed140289a6a887a7468ca9df6349fd186b27/pylance-7.0.0-cp39-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:04a58051d408c60fe76d41a220dcaf8fea8fb6d1aa0ca78a709b60bc3cc8d19a", size = 69473470, upload-time = "2026-05-27T22:17:18.935Z" },
-    { url = "https://files.pythonhosted.org/packages/1f/ec/5c00b6303a67d787f9475141832cbdc513d674ac3dcaeef8a7b169905e65/pylance-7.0.0-cp39-abi3-win_amd64.whl", hash = "sha256:467d4864af047eaab4e1370e2f1e88e2c6f507c079874421116cb41d78bc3629", size = 74792863, upload-time = "2026-05-27T22:19:23.875Z" },
+    { url = "https://files.pythonhosted.org/packages/82/b2/c81de196076c4c8d768f485324a0043e113ce0950a339977d83fee9783ef/pylance-10.0.0-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:d4bba56ae829202b7e9cdc82c92c00a4b52f03e679dc3edfad1db09d1285be2e", size = 69279797, upload-time = "2026-08-07T18:25:24.812Z" },
+    { url = "https://files.pythonhosted.org/packages/d2/e9/af671a6225740bd70c1e70bd83fa08091d628b960397cbecc477f16aaaf1/pylance-10.0.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:489b944827c0271e16a62b4006f8c75acc3bd7fbc381f35388a2afaaae38d438", size = 72775384, upload-time = "2026-08-07T18:31:29.686Z" },
+    { url = "https://files.pythonhosted.org/packages/5d/22/e07194195bb3bbdf062b0c31690fc92fccb2686d5e768efa1dc379a93350/pylance-10.0.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:018efe7d437d326b9049c1223458bd955e85e48509b4b0bbf8b2d3d94075dbff", size = 76632194, upload-time = "2026-08-07T18:44:29.001Z" },
+    { url = "https://files.pythonhosted.org/packages/f2/71/ed9956cf657e86a5fee5d5ddcfa7bfed0d7c2968bee39ed85d12629d8c93/pylance-10.0.0-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:254bad5d765c14db6c4eddd5323133dee3c76ff6d40c4777afe0b0e91d4c04d2", size = 72804222, upload-time = "2026-08-07T18:31:24.264Z" },
+    { url = "https://files.pythonhosted.org/packages/94/96/de449c246b2892df9d5a0af775b79a061e9897e6942bcee5c4ab6d6071f8/pylance-10.0.0-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:9f0c089e30389d9b7765a4c16f3d9325b05ed4fbf6cc2bbc9418292983472e54", size = 76602015, upload-time = "2026-08-07T18:46:27.724Z" },
+    { url = "https://files.pythonhosted.org/packages/53/81/4a5a9072b6d68c4dbb8c7b5530a381c7a6bea4ba92f9eca58ac885142722/pylance-10.0.0-cp310-abi3-win_amd64.whl", hash = "sha256:9fecf46e6835dc64b2d71767d5eab4f73787543a852432e9ba8ecf8527b3cdab", size = 82799247, upload-time = "2026-08-07T18:47:46.855Z" },
 ]

 [[package]]
@@ -4683,10 +4683,10 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "joblib", marker = "python_full_version < '3.11'" },
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
-    { name = "threadpoolctl", marker = "python_full_version < '3.11'" },
+    { name = "joblib" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } },
+    { name = "scipy", version = "1.15.3", source = { registry = "https://pypi.org/simple" } },
+    { name = "threadpoolctl" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/98/c2/a7855e41c9d285dfe86dc50b250978105dce513d6e459ea66a6aeb0e1e0c/scikit_learn-1.7.2.tar.gz", hash = "sha256:20e9e49ecd130598f1ca38a1d85090e1a600147b9c02fa6f15d69cb53d968fda", size = 7193136, upload-time = "2025-09-09T08:21:29.075Z" }
 wheels = [
@@ -4734,13 +4734,13 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "joblib", marker = "python_full_version >= '3.11'" },
-    { name = "narwhals", marker = "python_full_version >= '3.11'" },
-    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "joblib" },
+    { name = "narwhals" },
+    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" },
    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" },
-    { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "scipy", version = "1.17.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.12'" },
    { name = "scipy", version = "1.18.0", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" },
-    { name = "threadpoolctl", marker = "python_full_version >= '3.11'" },
+    { name = "threadpoolctl" },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/fa/6f/37092bdb25f712817231799fc5674d8e704066a8a70c1d2d40517e18b4ab/scikit_learn-1.9.0.tar.gz", hash = "sha256:8833266989d3a5110178a9fae30783675460724d0e1efb13b14901d2c660c557", size = 7750767, upload-time = "2026-06-02T11:54:32.706Z" }
 wheels = [
@@ -4784,7 +4784,7 @@ resolution-markers = [
    "python_full_version < '3.11'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
+    { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" } },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/0f/37/6964b830433e654ec7485e45a00fc9a27cf868d622838f6b6d9c5ec0d532/scipy-1.15.3.tar.gz", hash = "sha256:eae3cf522bc7df64b42cad3925c876e1b0b6c35c1337c93e12c0f366f55b0eaf", size = 59419214, upload-time = "2025-05-08T16:13:05.955Z" }
 wheels = [
@@ -4843,7 +4843,7 @@ resolution-markers = [
    "python_full_version == '3.11.*'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version == '3.11.*'" },
+    { name = "numpy", version = "2.4.6", source = { registry = "https://pypi.org/simple" } },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/7a/97/5a3609c4f8d58b039179648e62dd220f89864f56f7357f5d4f45c29eb2cc/scipy-1.17.1.tar.gz", hash = "sha256:95d8e012d8cb8816c226aef832200b1d45109ed4464303e997c5b13122b297c0", size = 30573822, upload-time = "2026-02-23T00:26:24.851Z" }
 wheels = [
@@ -4920,7 +4920,7 @@ resolution-markers = [
    "python_full_version >= '3.12' and python_full_version < '3.14'",
 ]
 dependencies = [
-    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version >= '3.12'" },
+    { name = "numpy", version = "2.5.1", source = { registry = "https://pypi.org/simple" } },
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/a7/25/c2700dfaf6442b4effaa91af24ebce5dc9d31bb4a69706313aae70d72cd0/scipy-1.18.0.tar.gz", hash = "sha256:67b2ad2ad54c72ca6d04975a9b2df8c3638c34ddd5b28738e94fc2b57929d378", size = 30774447, upload-time = "2026-06-19T15:01:43.456Z" }
 wheels = [
@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.37.1-beta.0"
+version = "0.37.1"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -49,8 +49,6 @@ lance-namespace = { workspace = true }
 lance-namespace-impls = { workspace = true }
 metrics = { workspace = true, optional = true }
 metrics-util = { workspace = true, optional = true }
-# Pin the GooseFS SDK to the version required by Lance's OpenDAL dependency.
-goosefs-sdk = { version = "=0.1.9", optional = true }
 moka = { workspace = true }
 pin-project = { workspace = true }
 tokio = { version = "1.23", features = ["rt-multi-thread", "sync"] }
@@ -100,6 +98,7 @@ anyhow = "1"
 lance-testing = { workspace = true }
 tempfile = "3.5.0"
 random_word = { version = "0.4.3", features = ["en"] }
+roaring = "0.11.4"
 tokio = { version = "1.23", features = ["io-util", "macros", "net", "rt-multi-thread", "sync", "test-util"] }
 uuid = { version = "1.7.0", features = ["v4"] }
 walkdir = "2"
@@ -135,7 +134,6 @@ azure = [
 ]
 cos = ["lance/tencent", "lance-io/tencent"]
 goosefs = [
-    "dep:goosefs-sdk",
    "lance/goosefs",
    "lance-io/goosefs",
    "lance-namespace-impls/dir-goosefs",
@@ -12,8 +12,7 @@ use lance_encoding::decoder::{DecoderPlugins, FilterExpression};
 use lance_file::{
    reader::{FileReader, FileReaderOptions},
    version::ConcreteFileVersion,
-    versions,
-    writer::FileWriterOptions,
+    writer::{FileWriter, FileWriterOptions},
 };
 use lance_io::{
    ReadBatchParams,
@@ -154,11 +153,13 @@ impl Shuffler {
                    source: None,
                })?;
            let object_writer = object_store.create(&path).await?;
-            let writer = versions::create_writer(
-                ConcreteFileVersion::V2_1,
+            let writer = FileWriter::try_new(
                object_writer,
                schema.clone(),
-                FileWriterOptions::default(),
+                FileWriterOptions {
+                    format_version: Some(ConcreteFileVersion::V2_1.into()),
+                    ..Default::default()
+                },
            )?;
            file_writers.push(writer);
        }
@@ -5955,18 +5955,17 @@ mod tests {
            .await
            .unwrap();

-        // Positions are relative to the first retained token, so dropping the
-        // leading "hello" stop word does not shift the remaining tokens.
+        // Lance 10 retains original token positions after stop-word removal.
        assert_eq!(
            tokens,
            vec![
                FtsToken {
                    text: "こんにちは".to_string(),
-                    position: 0,
+                    position: 1,
                },
                FtsToken {
                    text: "世界".to_string(),
-                    position: 1,
+                    position: 2,
                },
            ]
        );
@@ -95,7 +95,6 @@ pub use delete::DeleteResult;
 use futures::future::join_all;
 pub use lance::dataset::refs::{BranchContents, Ref, TagContents, Tags as LanceTags};
 pub use lance::dataset::scanner::DatasetRecordBatchStream;
-use lance::dataset::statistics::DatasetStatisticsExt;
 pub use lance_index::optimize::OptimizeOptions;
 pub use lsm_stats::{BucketStats, GenerationStats, LsmStats, MemtableStats};
 pub use optimize::{CompactionOptions, OptimizeAction, OptimizeStats};
@@ -3548,9 +3547,24 @@ impl BaseTable for NativeTable {
        let num_rows = self.count_rows(None).await?;
        let num_indices = self.list_indices().await?.len();
        let ds = self.dataset.get().await?;
-        let ds_clone = (*ds).clone();
-        let ds_stats = Arc::new(ds_clone).calculate_data_stats().await?;
-        let total_bytes = ds_stats.fields.iter().map(|f| f.bytes_on_disk).sum::<u64>() as usize;
+        // Sizes come from the manifest. Summing per-field `bytes_on_disk` instead
+        // would open every data file to read its column metadata, which costs one
+        // IO per fragment and reports 0 for legacy v1 storage.
+        //
+        // The manifest summary covers only the fragments' base data files, so
+        // overlay files (recorded on each fragment) and index files (recorded in
+        // the manifest's index section) are added separately.
+        let mut total_bytes = ds.manifest().summary().total_files_size as usize;
+        for frag in ds.manifest().fragments.iter() {
+            for overlay in &frag.overlays {
+                if let Some(size) = overlay.data_file.file_size_bytes.get() {
+                    total_bytes += size.get() as usize;
+                }
+            }
+        }
+        for index in ds.load_indices().await?.iter() {
+            total_bytes += index.total_size_bytes().unwrap_or(0) as usize;
+        }

        let frags = ds.get_fragments();
        let mut sorted_sizes = join_all(
@@ -3622,7 +3636,12 @@ impl BaseTable for NativeTable {
 #[skip_serializing_none]
 #[derive(Debug, Deserialize, PartialEq)]
 pub struct TableStatistics {
-    /// The total number of bytes in the table
+    /// The total size, in bytes, of the table's data files, index files, and
+    /// overlay files
+    ///
+    /// Read from the manifest, so this excludes deletion files and manifests,
+    /// and it excludes any file whose size the manifest does not record
+    /// (tables and indices written before writers persisted file sizes).
    pub total_bytes: usize,

    /// The number of rows in the table
@@ -3683,6 +3702,7 @@ mod tests {
    use super::*;
    use crate::connect;
    use crate::connection::ConnectBuilder;
+    use crate::io::object_store::io_tracking::IoTrackingStore;
    use crate::query::Select;
    use crate::query::{ExecutableQuery, QueryBase};
    use crate::test_utils::connection::new_test_connection;
@@ -5131,12 +5151,16 @@ mod tests {

        let res = table.stats().await.unwrap();
        println!("{:#?}", res);
+        // `total_bytes` is the full on-disk size of the 11 data files (this table
+        // has no index or overlay files), so it is well above the 2000 bytes of
+        // column data these 250 int32 pairs hold: each file carries its own footer
+        // and metadata.
        assert_eq!(
            res,
            TableStatistics {
                num_rows: 250,
                num_indices: 0,
-                total_bytes: 2300,
+                total_bytes: 8925,
                fragment_stats: FragmentStatistics {
                    num_fragments: 11,
                    num_small_fragments: 11,
@@ -5176,4 +5200,198 @@ mod tests {
            }
        )
    }
+
+    /// `total_bytes` counts more than the base data files: index files and
+    /// overlay files recorded in the manifest are included too.
+    #[tokio::test]
+    pub async fn test_stats_includes_index_and_overlay_files() {
+        use lance::dataset::WriteDestination;
+        use lance::dataset::transaction::{DataOverlayGroup, Operation};
+        use lance_file::version::{ConcreteFileVersion, LanceFileVersion};
+        use lance_file::writer::{FileWriter, FileWriterOptions};
+        use lance_io::utils::CachedFileSize;
+        use lance_table::format::DataFile;
+        use lance_table::format::overlay::{DataOverlayFile, OverlayCoverage};
+        use roaring::RoaringBitmap;
+
+        let tmp_dir = tempdir().unwrap();
+        let uri = tmp_dir.path().to_str().unwrap();
+        let conn = ConnectBuilder::new(uri)
+            .read_consistency_interval(Duration::from_secs(0))
+            .execute()
+            .await
+            .unwrap();
+
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("id", DataType::Int32, false),
+            Field::new("foo", DataType::Int32, true),
+        ]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![
+                Arc::new(Int32Array::from_iter_values(0..100)),
+                Arc::new(Int32Array::from_iter_values(0..100)),
+            ],
+        )
+        .unwrap();
+        let table = conn
+            .create_table("test_stats_extra_files", batch)
+            .execute()
+            .await
+            .unwrap();
+
+        let data_only = table.stats().await.unwrap().total_bytes;
+        assert!(data_only > 0);
+
+        // A scalar index adds index files whose sizes are recorded in the
+        // manifest's index section.
+        table
+            .create_index(&["id"], Index::Auto)
+            .execute()
+            .await
+            .unwrap();
+        let with_index = table.stats().await.unwrap().total_bytes;
+        let dataset = {
+            let native = table.as_native().unwrap();
+            (*native.dataset.get().await.unwrap()).clone()
+        };
+        let index_bytes: usize = dataset
+            .load_indices()
+            .await
+            .unwrap()
+            .iter()
+            .map(|idx| idx.total_size_bytes().unwrap_or(0) as usize)
+            .sum();
+        assert!(index_bytes > 0);
+        assert_eq!(with_index, data_only + index_bytes);
+
+        // Commit an overlay file supplying new `foo` values for the first three
+        // rows of fragment 0. There is no high-level API that writes overlays
+        // yet, so write the overlay's data file and commit the `DataOverlay`
+        // operation by hand.
+        let read_version = dataset.version().version;
+        let fragment_id = dataset.get_fragments()[0].id() as u64;
+        let foo_field_id = dataset.schema().field("foo").unwrap().id;
+        let overlay_schema = dataset.schema().project_by_ids(&[foo_field_id], true);
+        let file_version = ConcreteFileVersion::from(LanceFileVersion::Stable);
+
+        let filename = "overlay.lance".to_string();
+        let store = dataset.object_store(None).await.unwrap();
+        let path = dataset.data_dir().child(filename.clone());
+        let obj_writer = store.create(&path).await.unwrap();
+        let mut writer = FileWriter::try_new(
+            obj_writer,
+            overlay_schema,
+            FileWriterOptions {
+                format_version: Some(file_version.into()),
+                ..Default::default()
+            },
+        )
+        .unwrap();
+        writer
+            .write_column(0, Arc::new(Int32Array::from(vec![1000, 1001, 1002])) as _)
+            .await
+            .unwrap();
+        let summary = writer.finish().await.unwrap();
+        let overlay_bytes = summary.size_bytes as usize;
+        assert!(overlay_bytes > 0);
+
+        let mut data_file = DataFile::new_unstarted(filename, file_version);
+        data_file.fields = writer
+            .field_id_to_column_indices()
+            .iter()
+            .map(|(field_id, _)| *field_id as i32)
+            .collect::<Vec<_>>()
+            .into();
+        data_file.column_indices = writer
+            .field_id_to_column_indices()
+            .iter()
+            .map(|(_, column_index)| *column_index as i32)
+            .collect::<Vec<_>>()
+            .into();
+        data_file.file_size_bytes = CachedFileSize::new(summary.size_bytes);
+
+        let overlay = DataOverlayFile {
+            data_file,
+            coverage: OverlayCoverage::dense(RoaringBitmap::from_iter(0..3)),
+            committed_version: 0,
+        };
+        Dataset::commit(
+            WriteDestination::Dataset(Arc::new(dataset)),
+            Operation::DataOverlay {
+                groups: vec![DataOverlayGroup {
+                    fragment_id,
+                    overlays: vec![overlay],
+                }],
+            },
+            Some(read_version),
+            None,
+            None,
+            Arc::new(Default::default()),
+            false,
+        )
+        .await
+        .unwrap();
+
+        table.checkout_latest().await.unwrap();
+        let with_overlay = table.stats().await.unwrap().total_bytes;
+        assert_eq!(with_overlay, with_index + overlay_bytes);
+    }
+
+    /// `stats()` must stay manifest-only. Summing per-field `bytes_on_disk`
+    /// instead opens every data file, so cost would grow with fragment count.
+    #[tokio::test]
+    pub async fn test_stats_does_not_read_data_files() {
+        let tmp_dir = tempdir().unwrap();
+        let uri = tmp_dir.path().to_str().unwrap();
+
+        let conn = ConnectBuilder::new(uri).execute().await.unwrap();
+
+        let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
+        let batch = RecordBatch::try_new(
+            schema.clone(),
+            vec![Arc::new(Int32Array::from_iter_values(0..10))],
+        )
+        .unwrap();
+
+        conn.create_table("test_stats_io", batch.clone())
+            .execute()
+            .await
+            .unwrap();
+        let table = conn.open_table("test_stats_io").execute().await.unwrap();
+        const NUM_APPENDS: usize = 20;
+        for _ in 0..NUM_APPENDS {
+            table.add(batch.clone()).execute().await.unwrap();
+        }
+
+        // Reopen through a tracking store so the counters cover `stats()` alone and
+        // not the writes above.
+        let (wrapper, io_stats) = IoTrackingStore::new_wrapper();
+        let table = conn
+            .open_table("test_stats_io")
+            .lance_read_params(ReadParams {
+                store_options: Some(ObjectStoreParams {
+                    object_store_wrapper: Some(wrapper),
+                    ..Default::default()
+                }),
+                ..Default::default()
+            })
+            .execute()
+            .await
+            .unwrap();
+        io_stats.lock().unwrap().read_iops = 0;
+
+        let stats = table.stats().await.unwrap();
+        let read_iops = io_stats.lock().unwrap().read_iops;
+
+        assert_eq!(stats.fragment_stats.num_fragments, NUM_APPENDS + 1);
+        assert!(stats.total_bytes > 0);
+        // Reading the fragments' data files would take at least one IOP each.
+        assert!(
+            read_iops < stats.fragment_stats.num_fragments as u64,
+            "stats() issued {} read IOPs across {} fragments",
+            read_iops,
+            stats.fragment_stats.num_fragments
+        );
+    }
 }
Author	SHA1	Message	Date
Lance Release	b89f87f206	Bump version: 0.37.1-beta.3 → 0.37.1	2026-08-10 07:54:42 +00:00
Lance Release	a022d3bcb3	Bump version: 0.37.1-beta.2 → 0.37.1-beta.3	2026-08-10 07:53:53 +00:00
Lance Release	8268532d64	Bump version: 0.37.1-beta.1 → 0.37.1-beta.2	2026-08-10 06:30:45 +00:00
Xuanwo	f933ef9b21	fix(ci): tag releases after updating lockfiles	2026-08-10 14:23:41 +08:00
Xuanwo	e885e5dd00	fix(ci): validate stable Lance dependencies	2026-08-10 14:23:33 +08:00
Xuanwo	7c7efa9743	feat: update lance dependency to v10.0.0	2026-08-10 14:23:29 +08:00
ForwardXu	12405a4077	chore: drop explicit goosefs-sdk pin in favor of opendal 0.58.1 transitive dep (#3910 ) ## Summary `opendal 0.58.1` (the version pulled in transitively via Lance) already ships `goosefs-sdk 0.1.9`, which includes the upstream fix for the 0.1.6 compile break. The explicit version pin that lancedb has been carrying since the GooseFS feature was introduced is therefore no longer necessary and is now redundant work to maintain. ## Changes - Remove the direct `goosefs-sdk` dependency from `rust/lancedb/Cargo.toml` (it was pinned to `=0.1.9` with a comment referencing the 0.1.6 compile break). - Remove the `dep:goosefs-sdk` entry from the `goosefs` cargo feature, since no source file in lancedb imports the crate directly. - Refresh `Cargo.lock`; `goosefs-sdk 0.1.9` now resolves transitively through `lance` → `opendal 0.58.1`. ## Verification - `cargo fmt --all` — clean - `cargo check --features remote,goosefs --tests --examples` — passes - `Cargo.lock` confirms `goosefs-sdk 0.1.9` is still resolved (now transitively), so the `goosefs` feature continues to enable the same set of Lance/IOPaths as before. ## Backwards compatibility No public API changes. The `goosefs` cargo feature still activates `lance/goosefs`, `lance-io/goosefs`, and `lance-namespace-impls/dir-goosefs`, and the same `goosefs-sdk 0.1.9` version is selected by the resolver.	2026-08-10 12:16:21 +08:00
lancedb-gatefixer[bot]	36054be576	fix(node): preserve nested Arrow data across versions (#3900 ) <!-- lance-gatekeeper-fix:v1 agent=613a074d606e626c5169d601373a32d8 generation=1 --> ## Root cause When LanceDB accepted an Arrow table created by a different installed Arrow package, its compatibility sanitizer rebuilt each Data node without converting the foreign type or preserving nested children. It also dropped the separate dictionary vector payload and did not preserve identity shared by dictionary schema types, vector wrappers, or growing dictionary chunks. ## Fix Recursively sanitize nested Arrow data types and child data. Use one table-scoped sanitization context to rebuild and memoize source type objects, dictionary vectors, and Data nodes in the local Arrow realm, preserving all identities required by Arrow IPC. Add Arrow 15 through 18 regressions for list serialization, ordinary dictionaries, dictionaries shared across fields and batches, growing dictionaries, and IPC round trips. ## Validation - pnpm test __test__/arrow.test.ts --runInBand (188 passed) - pnpm lint - pnpm build - pnpm test --runInBand (706 passed, 5 skipped) - pnpm run docs Fixes #2256 --------- Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>	2026-08-09 03:34:39 +08:00
Dan Tasse	77a93fee76	fix: get table size from metadata, not files (#3790 ) Some issues: - file_size_bytes is optional in the manifest, so if it's not there (old writer I guess) it'll under-report the table size. - it changes results a little bit from the old way by including per-file footers and metadata (probably not a big difference at real scale) --------- Co-authored-by: Will Jones <willjones127@gmail.com>	2026-08-07 17:41:41 -04:00
Lance Release	7bb501839a	Bump version: 0.37.1-beta.0 → 0.37.1-beta.1	2026-08-07 21:16:07 +00:00
Andrew Chen	5b347afd99	fix: avoid AttributeError in JinaEmbeddings image input for str/Path (#3670 ) ## What `JinaEmbeddings._generate_image_input_dict()` crashes with `AttributeError: 'function' object has no attribute 'urlparse'` on any image given as a URL string, local path string, or `pathlib.Path` — i.e. every documented `jina-clip-v1` image-embedding use case except raw `bytes`. ## Why ```python from urllib.parse import urlparse ... parsed = urlparse.urlparse(image) ``` `urlparse` is imported as a function, then called as if it were the `urllib.parse` module (`urlparse.urlparse(...)`). The module-level `is_valid_url()` a few lines above does it correctly (`urlparse(text)`), which is why this reads as a typo rather than intentional. Fixed to `urlparse(str(image))` — `str()` is needed because `urlparse()` only accepts `str`/`bytes` and raises a different `AttributeError` on a raw `Path`. ## Testing Added `test_jina_generate_image_input_dict_local_path`, which fails with the original `AttributeError` before the fix and passes after, covering both a `str` path and a `pathlib.Path`. Verified locally (built the Rust extension, ran red→green, then the full `test_embeddings.py` file: 15 passed / 8 skipped, no regressions) and with `ruff check`/`ruff format`. --- Disclosure: this PR was drafted with AI assistance (Claude); I reviewed, tested, and take responsibility for the change. --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>	2026-08-07 14:05:45 -07:00
Dan Rammer	706a9c327f	feat: infer maintained indexes when an LsmWriteSpec omits them (#3748 ) ## What `LsmWriteSpec::maintained_indexes` becomes `Option<Vec<String>>`: \| value \| meaning \| \|---\|---\| \| `None` (new default) \| every index the MemWAL supports, resolved when the spec is installed \| \| `Some([])` \| maintain nothing — a scan/filter-only WAL table \| \| `Some([..])` \| exactly these, taken verbatim \| `with_maintained_indexes` keeps its signature; `with_no_maintained_indexes()` is new. Surfaced through the remote path (null on the wire), Python, and Node. ## Why Callers had to state the maintained set by hand every time, which is both tedious and easy to get wrong — the common case is "maintain what I already built." Resolution filters on `IndexConfig::is_memwal_maintainable`, delegating to lance's `is_maintainable_index_type`. This is load-bearing rather than cosmetic: lance does not skip an index type its memtable cannot build, it errors when the shard writer opens, so sweeping up a bitmap index would fail every memtable claim and leave the table unwritable. The inferred set excludes those, and an explicit list naming one is now rejected at spec time instead of at claim time. ## Behavior change A freshly constructed spec used to maintain nothing; it now maintains everything supported. This flipped because napi collapses `undefined` and `null` to `None`, so TypeScript cannot express "absent means nothing, null means all" — any other choice makes the bindings disagree with the wire. The error direction also favors it: an unwanted maintained index costs memory, while a silently unmaintained one degrades FTS to an unscored scan. Three existing tests encoded the old default and are updated rather than worked around. ## Caveat The resolved set is a snapshot, not a subscription. An index created after the spec is installed is not maintained until the spec is unset and set again. `get_lsm_write_spec` therefore always reports a concrete list — `None` never round-trips. ## Dependency Needs a lance release carrying `is_maintainable_index_type` (lance-format/lance#8095) before this builds against the pinned tag. Draft until then. ## Testing 38 Rust LSM tests and 10 Python tests pass against a local lance build, including new coverage that a bitmap index is excluded from inference and rejected when named, and that `[]` stays distinguishable from null on the wire. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>	2026-08-07 14:50:22 -05:00