Add skip_merge option for FTS indexes

chore: update lance dependency to v2.0.0-beta.8 (#2907 )
## Summary - bump Lance crates to v2.0.0-beta.8 and align arrow/datafusion/regex/half and PyO3 dependencies - update Rust/Python bindings for upstream API changes (namespace/table requests, query select columns, storage option providers) - verified with cargo clippy --workspace --tests --all-features -D warnings and cargo fmt --all Triggered by refs/tags/v2.0.0-beta.8. --------- Signed-off-by: BubbleCal <bubble-cal@outlook.com> Co-authored-by: BubbleCal <bubble-cal@outlook.com>
2026-09-08 06:18:59 +00:00 · 2026-01-20 21:32:41 +08:00 · 2026-01-16 01:46:52 +08:00 · 2026-01-13 11:23:14 -08:00 · 2026-01-13 20:42:11 +05:30 · 2026-01-12 12:28:07 -08:00
28 changed files with 349 additions and 257 deletions
@@ -167,13 +167,13 @@ jobs:
      - name: Build
        run: |
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo build --profile ci --features remote --tests --locked --target ${{ matrix.target }}
+          cargo build --profile ci --features aws,remote --tests --locked --target ${{ matrix.target }}
      - name: Run tests
        # Can only run tests when target matches host
        if: ${{ matrix.target == 'x86_64-pc-windows-msvc' }}
        run: |
          $env:VCPKG_ROOT = $env:VCPKG_INSTALLATION_ROOT
-          cargo test --profile ci --features remote --locked
+          cargo test --profile ci --features aws,remote --locked

  msrv:
    # Check the minimum supported Rust version
@@ -181,9 +181,9 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"

 [[package]]
 name = "arrow"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cb372a7cbcac02a35d3fb7b3fc1f969ec078e871f9bb899bf00a2e1809bec8a3"
+checksum = "2a2b10dcb159faf30d3f81f6d56c1211a5bea2ca424eabe477648a44b993320e"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -203,9 +203,9 @@ dependencies = [

 [[package]]
 name = "arrow-arith"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0f377dcd19e440174596d83deb49cd724886d91060c07fec4f67014ef9d54049"
+checksum = "288015089e7931843c80ed4032c5274f02b37bcb720c4a42096d50b390e70372"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -217,9 +217,9 @@ dependencies = [

 [[package]]
 name = "arrow-array"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a23eaff85a44e9fa914660fb0d0bb00b79c4a3d888b5334adb3ea4330c84f002"
+checksum = "65ca404ea6191e06bf30956394173337fa9c35f445bd447fe6c21ab944e1a23c"
 dependencies = [
 "ahash",
 "arrow-buffer",
@@ -236,9 +236,9 @@ dependencies = [

 [[package]]
 name = "arrow-buffer"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a2819d893750cb3380ab31ebdc8c68874dd4429f90fd09180f3c93538bd21626"
+checksum = "36356383099be0151dacc4245309895f16ba7917d79bdb71a7148659c9206c56"
 dependencies = [
 "bytes",
 "half",
@@ -248,9 +248,9 @@ dependencies = [

 [[package]]
 name = "arrow-cast"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e3d131abb183f80c450d4591dc784f8d7750c50c6e2bc3fcaad148afc8361271"
+checksum = "9c8e372ed52bd4ee88cc1e6c3859aa7ecea204158ac640b10e187936e7e87074"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -270,9 +270,9 @@ dependencies = [

 [[package]]
 name = "arrow-csv"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2275877a0e5e7e7c76954669366c2aa1a829e340ab1f612e647507860906fb6b"
+checksum = "8e4100b729fe656f2e4fb32bc5884f14acf9118d4ad532b7b33c1132e4dce896"
 dependencies = [
 "arrow-array",
 "arrow-cast",
@@ -285,9 +285,9 @@ dependencies = [

 [[package]]
 name = "arrow-data"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "05738f3d42cb922b9096f7786f606fcb8669260c2640df8490533bb2fa38c9d3"
+checksum = "bf87f4ff5fc13290aa47e499a8b669a82c5977c6a1fedce22c7f542c1fd5a597"
 dependencies = [
 "arrow-buffer",
 "arrow-schema",
@@ -298,9 +298,9 @@ dependencies = [

 [[package]]
 name = "arrow-ipc"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3d09446e8076c4b3f235603d9ea7c5494e73d441b01cd61fb33d7254c11964b3"
+checksum = "eb3ca63edd2073fcb42ba112f8ae165df1de935627ead6e203d07c99445f2081"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -314,9 +314,9 @@ dependencies = [

 [[package]]
 name = "arrow-json"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "371ffd66fa77f71d7628c63f209c9ca5341081051aa32f9c8020feb0def787c0"
+checksum = "a36b2332559d3310ebe3e173f75b29989b4412df4029a26a30cc3f7da0869297"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -338,9 +338,9 @@ dependencies = [

 [[package]]
 name = "arrow-ord"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cbc94fc7adec5d1ba9e8cd1b1e8d6f72423b33fe978bf1f46d970fafab787521"
+checksum = "13c4e0530272ca755d6814218dffd04425c5b7854b87fa741d5ff848bf50aa39"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -351,9 +351,9 @@ dependencies = [

 [[package]]
 name = "arrow-pyarrow"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fbd810e3997bae72f58cda57231ccb0a2fda07911ca1b0a5718cbf9379abb297"
+checksum = "f45c7989cb70214b2f362eaa10266d15e1a433692f2ea1514018be3aace679f4"
 dependencies = [
 "arrow-array",
 "arrow-data",
@@ -363,9 +363,9 @@ dependencies = [

 [[package]]
 name = "arrow-row"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "169676f317157dc079cc5def6354d16db63d8861d61046d2f3883268ced6f99f"
+checksum = "b07f52788744cc71c4628567ad834cadbaeb9f09026ff1d7a4120f69edf7abd3"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -376,9 +376,9 @@ dependencies = [

 [[package]]
 name = "arrow-schema"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d27609cd7dd45f006abae27995c2729ef6f4b9361cde1ddd019dc31a5aa017e0"
+checksum = "6bb63203e8e0e54b288d0d8043ca8fa1013820822a27692ef1b78a977d879f2c"
 dependencies = [
 "bitflags 2.9.4",
 "serde_core",
@@ -387,9 +387,9 @@ dependencies = [

 [[package]]
 name = "arrow-select"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ae980d021879ea119dd6e2a13912d81e64abed372d53163e804dfe84639d8010"
+checksum = "c96d8a1c180b44ecf2e66c9a2f2bbcb8b1b6f14e165ce46ac8bde211a363411b"
 dependencies = [
 "ahash",
 "arrow-array",
@@ -401,9 +401,9 @@ dependencies = [

 [[package]]
 name = "arrow-string"
-version = "57.1.0"
+version = "57.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cf35e8ef49dcf0c5f6d175edee6b8af7b45611805333129c541a8b89a0fc0534"
+checksum = "a8ad6a81add9d3ea30bf8374ee8329992c7fd246ffd8b7e2f48a3cea5aa0cc9a"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -2446,7 +2446,7 @@ dependencies = [
 "itertools 0.14.0",
 "parking_lot",
 "paste",
- "petgraph 0.8.3",
+ "petgraph",
 ]

 [[package]]
@@ -3072,8 +3072,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"

 [[package]]
 name = "fsst"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-array",
 "rand 0.9.2",
@@ -4404,8 +4404,8 @@ dependencies = [

 [[package]]
 name = "lance"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4470,8 +4470,8 @@ dependencies = [

 [[package]]
 name = "lance-arrow"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4490,8 +4490,8 @@ dependencies = [

 [[package]]
 name = "lance-bitpacking"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrayref",
 "paste",
@@ -4500,8 +4500,8 @@ dependencies = [

 [[package]]
 name = "lance-core"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4538,8 +4538,8 @@ dependencies = [

 [[package]]
 name = "lance-datafusion"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4569,8 +4569,8 @@ dependencies = [

 [[package]]
 name = "lance-datagen"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4588,8 +4588,8 @@ dependencies = [

 [[package]]
 name = "lance-encoding"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4626,8 +4626,8 @@ dependencies = [

 [[package]]
 name = "lance-file"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-arith",
 "arrow-array",
@@ -4659,8 +4659,8 @@ dependencies = [

 [[package]]
 name = "lance-geo"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "datafusion",
 "geo-traits",
@@ -4674,8 +4674,8 @@ dependencies = [

 [[package]]
 name = "lance-index"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4742,8 +4742,8 @@ dependencies = [

 [[package]]
 name = "lance-io"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-arith",
@@ -4783,8 +4783,8 @@ dependencies = [

 [[package]]
 name = "lance-linalg"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-array",
 "arrow-buffer",
@@ -4800,8 +4800,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "async-trait",
@@ -4813,8 +4813,8 @@ dependencies = [

 [[package]]
 name = "lance-namespace-impls"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-ipc",
@@ -4857,8 +4857,8 @@ dependencies = [

 [[package]]
 name = "lance-table"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow",
 "arrow-array",
@@ -4897,8 +4897,8 @@ dependencies = [

 [[package]]
 name = "lance-testing"
-version = "2.0.0-beta.6"
-source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.6#450ddc26061e8e73039c3771c3055328488b8b7c"
+version = "2.0.0-beta.8"
+source = "git+https://github.com/lance-format/lance.git?tag=v2.0.0-beta.8#5bffcfc3f9716fd6eb069579eb5027ed9c69feb7"
 dependencies = [
 "arrow-array",
 "arrow-schema",
@@ -6004,16 +6004,6 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "df202b0b0f5b8e389955afd5f27b007b00fb948162953f1db9c70d2c7e3157d7"

-[[package]]
-name = "petgraph"
-version = "0.7.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "3672b37090dbd86368a4145bc067582552b29c27377cad4e0a306c97f9bd7772"
-dependencies = [
- "fixedbitset",
- "indexmap 2.12.0",
-]
-
 [[package]]
 name = "petgraph"
 version = "0.8.3"
@@ -6595,9 +6585,9 @@ dependencies = [

 [[package]]
 name = "prost"
-version = "0.14.1"
+version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7231bd9b3d3d33c86b58adbac74b5ec0ad9f496b19d22801d773636feaa95f3d"
+checksum = "d2ea70524a2f82d518bce41317d0fae74151505651af45faf1ffbd6fd33f0568"
 dependencies = [
 "bytes",
 "prost-derive",
@@ -6605,16 +6595,15 @@ dependencies = [

 [[package]]
 name = "prost-build"
-version = "0.14.1"
+version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ac6c3320f9abac597dcbc668774ef006702672474aad53c6d596b62e487b40b1"
+checksum = "343d3bd7056eda839b03204e68deff7d1b13aba7af2b2fd16890697274262ee7"
 dependencies = [
 "heck 0.5.0",
 "itertools 0.14.0",
 "log",
 "multimap",
- "once_cell",
- "petgraph 0.7.1",
+ "petgraph",
 "prettyplease",
 "prost",
 "prost-types",
@@ -6625,9 +6614,9 @@ dependencies = [

 [[package]]
 name = "prost-derive"
-version = "0.14.1"
+version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9120690fafc389a67ba3803df527d0ec9cbbc9cc45e4cc20b332996dfb672425"
+checksum = "27c6023962132f4b30eb4c172c91ce92d933da334c59c23cddee82358ddafb0b"
 dependencies = [
 "anyhow",
 "itertools 0.14.0",
@@ -6638,9 +6627,9 @@ dependencies = [

 [[package]]
 name = "prost-types"
-version = "0.14.1"
+version = "0.14.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b9b4db3d6da204ed77bb26ba83b6122a73aeb2e87e25fbf7ad2e84c4ccbf8f72"
+checksum = "8991c4cbdb8bc5b11f0b074ffe286c30e523de90fee5ba8132f1399f23cb3dd7"
 dependencies = [
 "prost",
 ]
@@ -15,30 +15,30 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"

 [workspace.dependencies]
-lance = { "version" = "=2.0.0-beta.6", default-features = false, "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=2.0.0-beta.6", default-features = false, "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=2.0.0-beta.6", default-features = false, "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=2.0.0-beta.6", "tag" = "v2.0.0-beta.6", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=2.0.0-beta.8", default-features = false, "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=2.0.0-beta.8", "tag" = "v2.0.0-beta.8", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
-arrow = { version = "57.1", optional = false }
-arrow-array = "57.1"
-arrow-data = "57.1"
-arrow-ipc = "57.1"
-arrow-ord = "57.1"
-arrow-schema = "57.1"
-arrow-select = "57.1"
-arrow-cast = "57.1"
+arrow = { version = "57.2", optional = false }
+arrow-array = "57.2"
+arrow-data = "57.2"
+arrow-ipc = "57.2"
+arrow-ord = "57.2"
+arrow-schema = "57.2"
+arrow-select = "57.2"
+arrow-cast = "57.2"
 async-trait = "0"
 datafusion = { version = "51.0", default-features = false }
 datafusion-catalog = "51.0"
@@ -59,7 +59,7 @@ rand = "0.9"
 snafu = "0.8"
 url = "2"
 num-traits = "0.2"
-regex = "1.10"
+regex = "1.12"
 lazy_static = "1"
 semver = "1.0.25"
 chrono = "0.4"
@@ -36,6 +36,6 @@ aws-lc-rs = "=1.13.0"
 napi-build = "2.1"

 [features]
-default = ["remote", "lancedb/default"]
+default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]
@@ -558,6 +558,12 @@ export interface FtsOptions {
   * whether to only index the prefix of the token for ngram tokenizer
   */
  prefixOnly?: boolean;
+
+  /**
+   * Whether to skip the partition merge stage after indexing.
+   * Useful for distributed indexing where merges are handled separately.
+   */
+  skipMerge?: boolean;
 }

 export class Index {
@@ -726,6 +732,7 @@ export class Index {
        options?.ngramMinLength,
        options?.ngramMaxLength,
        options?.prefixOnly,
+        options?.skipMerge,
      ),
    );
  }
@@ -157,6 +157,7 @@ impl Index {
        ngram_min_length: Option<u32>,
        ngram_max_length: Option<u32>,
        prefix_only: Option<bool>,
+        skip_merge: Option<bool>,
    ) -> Self {
        let mut opts = FtsIndexBuilder::default();
        if let Some(with_position) = with_position {
@@ -192,6 +193,9 @@ impl Index {
        if let Some(prefix_only) = prefix_only {
            opts = opts.ngram_prefix_only(prefix_only);
        }
+        if let Some(skip_merge) = skip_merge {
+            opts = opts.skip_merge(skip_merge);
+        }

        Self {
            inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
@@ -14,7 +14,7 @@ name = "_lancedb"
 crate-type = ["cdylib"]

 [dependencies]
-arrow = { workspace = true, features = ["pyarrow"] }
+arrow = { version = "57.2", features = ["pyarrow"] }
 async-trait = "0.1"
 lancedb = { path = "../rust/lancedb", default-features = false }
 lance-core.workspace = true
@@ -38,6 +38,6 @@ pyo3-build-config = { version = "0.26", features = [
 ] }

 [features]
-default = ["remote", "lancedb/default"]
+default = ["remote",  "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface"]
 fp16kernels = ["lancedb/fp16kernels"]
 remote = ["lancedb/remote"]
@@ -127,6 +127,9 @@ class FTS:
    ascii_folding : bool, default True
        Whether to fold ASCII characters. This converts accented characters to
        their ASCII equivalent. For example, "café" would be converted to "cafe".
+    skip_merge : bool, default False
+        Whether to skip the partition merge stage after indexing. This can be
+        useful for distributed indexing where merges are handled separately.
    """

    with_position: bool = False
@@ -140,6 +143,7 @@ class FTS:
    ngram_min_length: int = 3
    ngram_max_length: int = 3
    prefix_only: bool = False
+    skip_merge: bool = False


@dataclass
@@ -961,22 +961,27 @@ class LanceQueryBuilder(ABC):
        >>> query = [100, 100]
        >>> plan = table.search(query).analyze_plan()
        >>> print(plan)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-        AnalyzeExec verbose=true, metrics=[], cumulative_cpu=...
-          TracedExec, metrics=[], cumulative_cpu=...
-            ProjectionExec: expr=[...], metrics=[...], cumulative_cpu=...
-              GlobalLimitExec: skip=0, fetch=10, metrics=[...], cumulative_cpu=...
-                FilterExec: _distance@2 IS NOT NULL,
-                metrics=[output_rows=..., elapsed_compute=...], cumulative_cpu=...
-                  SortExec: TopK(fetch=10), expr=[...],
+        AnalyzeExec verbose=true, elapsed=..., metrics=...
+          TracedExec, elapsed=..., metrics=...
+            ProjectionExec: elapsed=..., expr=[...],
+            metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
+              GlobalLimitExec: elapsed=..., skip=0, fetch=10,
+              metrics=[output_rows=..., elapsed_compute=..., output_bytes=...]
+                FilterExec: elapsed=..., _distance@2 IS NOT NULL, metrics=[...]
+                  SortExec: elapsed=..., TopK(fetch=10), expr=[...],
                  preserve_partitioning=[...],
-                  metrics=[output_rows=..., elapsed_compute=..., row_replacements=...],
-                  cumulative_cpu=...
-                    KNNVectorDistance: metric=l2,
-                    metrics=[output_rows=..., elapsed_compute=..., output_batches=...],
-                    cumulative_cpu=...
-                      LanceRead: uri=..., projection=[vector], ...
-                      metrics=[output_rows=..., elapsed_compute=...,
-                      bytes_read=..., iops=..., requests=...], cumulative_cpu=...
+                  metrics=[output_rows=..., elapsed_compute=...,
+                  output_bytes=..., row_replacements=...]
+                    KNNVectorDistance: elapsed=..., metric=l2,
+                    metrics=[output_rows=..., elapsed_compute=...,
+                    output_bytes=..., output_batches=...]
+                      LanceRead: elapsed=..., uri=..., projection=[vector],
+                      num_fragments=..., range_before=None, range_after=None,
+                      row_id=true, row_addr=false,
+                      full_filter=--, refine_filter=--,
+                      metrics=[output_rows=..., elapsed_compute=..., output_bytes=...,
+                      fragments_scanned=..., ranges_scanned=1, rows_scanned=1,
+                      bytes_read=..., iops=..., requests=..., task_wait_time=...]

        Returns
        -------
@@ -176,6 +176,7 @@ class RemoteTable(Table):
        ngram_min_length: int = 3,
        ngram_max_length: int = 3,
        prefix_only: bool = False,
+        skip_merge: bool = False,
        name: Optional[str] = None,
    ):
        config = FTS(
@@ -190,6 +191,7 @@ class RemoteTable(Table):
            ngram_min_length=ngram_min_length,
            ngram_max_length=ngram_max_length,
            prefix_only=prefix_only,
+            skip_merge=skip_merge,
        )
        LOOP.run(
            self._table.create_index(
@@ -892,6 +892,7 @@ class Table(ABC):
        ngram_min_length: int = 3,
        ngram_max_length: int = 3,
        prefix_only: bool = False,
+        skip_merge: bool = False,
        wait_timeout: Optional[timedelta] = None,
        name: Optional[str] = None,
    ):
@@ -956,6 +957,9 @@ class Table(ABC):
            The maximum length of an n-gram.
        prefix_only: bool, default False
            Whether to only index the prefix of the token for ngram tokenizer.
+        skip_merge: bool, default False
+            Only available with use_tantivy=False.
+            If True, skip the partition merge stage after indexing.
        wait_timeout: timedelta, optional
            The timeout to wait if indexing is asynchronous.
        name: str, optional
@@ -2259,6 +2263,7 @@ class LanceTable(Table):
        ngram_min_length: int = 3,
        ngram_max_length: int = 3,
        prefix_only: bool = False,
+        skip_merge: bool = False,
        name: Optional[str] = None,
    ):
        if not use_tantivy:
@@ -2282,6 +2287,8 @@ class LanceTable(Table):
            else:
                tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)

+            tokenizer_configs["skip_merge"] = skip_merge
+
            config = FTS(
                **tokenizer_configs,
            )
@@ -405,7 +405,10 @@ def test_table_create_indices():

        # Test create_fts_index with custom name
        table.create_fts_index(
-            "text", wait_timeout=timedelta(seconds=2), name="custom_fts_idx"
+            "text",
+            wait_timeout=timedelta(seconds=2),
+            name="custom_fts_idx",
+            skip_merge=True,
        )

        # Test create_index with custom name
@@ -427,6 +430,7 @@ def test_table_create_indices():
        fts_req = received_requests[1]
        assert "name" in fts_req
        assert fts_req["name"] == "custom_fts_idx"
+        assert fts_req["skip_merge"] is True

        # Check vector index request has custom name
        vector_req = received_requests[2]
@@ -39,7 +39,7 @@ impl RecordBatchStream {
        (*self.schema)
            .clone()
            .into_pyarrow(py)
-            .map(|bound| bound.unbind())
+            .map(|obj| obj.unbind())
    }

    pub fn __aiter__(self_: PyRef<'_, Self>) -> PyRef<'_, Self> {
@@ -55,12 +55,12 @@ impl RecordBatchStream {
                .next()
                .await
                .ok_or_else(|| PyStopAsyncIteration::new_err(""))?;
-            Python::attach(|py| {
-                inner_next
-                    .infer_error()?
-                    .to_pyarrow(py)
-                    .map(|bound| bound.unbind())
-            })
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = inner_next.infer_error()?.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }
 }
@@ -307,6 +307,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_namespaces(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("namespaces", response.namespaces)?;
@@ -327,11 +328,11 @@ impl Connection {
        let py = self_.py();
        future_into_py(py, async move {
            use lance_namespace::models::CreateNamespaceRequest;
-            let mode_enum = mode.map(|m| match m.to_lowercase().as_str() {
-                "create" => "Create".to_string(),
-                "exist_ok" => "ExistOk".to_string(),
-                "overwrite" => "Overwrite".to_string(),
-                other => other.to_string(),
+            let mode_enum = mode.and_then(|m| match m.to_lowercase().as_str() {
+                "create" => Some("Create".to_string()),
+                "exist_ok" => Some("ExistOk".to_string()),
+                "overwrite" => Some("Overwrite".to_string()),
+                _ => None,
            });
            let request = CreateNamespaceRequest {
                id: if namespace.is_empty() {
@@ -344,6 +345,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.create_namespace(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
@@ -363,15 +365,15 @@ impl Connection {
        let py = self_.py();
        future_into_py(py, async move {
            use lance_namespace::models::DropNamespaceRequest;
-            let mode_enum = mode.map(|m| match m.to_uppercase().as_str() {
-                "SKIP" => "Skip".to_string(),
-                "FAIL" => "Fail".to_string(),
-                other => other.to_string(),
+            let mode_enum = mode.and_then(|m| match m.to_uppercase().as_str() {
+                "SKIP" => Some("Skip".to_string()),
+                "FAIL" => Some("Fail".to_string()),
+                _ => None,
            });
-            let behavior_enum = behavior.map(|b| match b.to_uppercase().as_str() {
-                "RESTRICT" => "Restrict".to_string(),
-                "CASCADE" => "Cascade".to_string(),
-                other => other.to_string(),
+            let behavior_enum = behavior.and_then(|b| match b.to_uppercase().as_str() {
+                "RESTRICT" => Some("Restrict".to_string()),
+                "CASCADE" => Some("Cascade".to_string()),
+                _ => None,
            });
            let request = DropNamespaceRequest {
                id: if namespace.is_empty() {
@@ -384,6 +386,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.drop_namespace(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
@@ -411,6 +414,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.describe_namespace(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("properties", response.properties)?;
@@ -441,6 +445,7 @@ impl Connection {
                ..Default::default()
            };
            let response = inner.list_tables(request).await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| -> PyResult<Py<PyDict>> {
                let dict = PyDict::new(py);
                dict.set_item("tables", response.tables)?;
@@ -40,31 +40,34 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    request_id,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
-                    let message = err.to_string();
-                    let http_err_cls = py
-                        .import(intern!(py, "lancedb.remote.errors"))?
-                        .getattr(intern!(py, "HttpError"))?;
-                    let err = http_err_cls.call1((
-                        message,
-                        request_id,
-                        status_code.map(|s| s.as_u16()),
-                    ))?;
-
-                    if let Some(cause) = source.source() {
-                        // The HTTP error already includes the first cause. But
-                        // we can add the rest of the chain if there is any more.
-                        let cause_err = http_from_rust_error(
-                            py,
-                            cause,
+                } => {
+                    #[allow(deprecated)]
+                    Python::with_gil(|py| {
+                        let message = err.to_string();
+                        let http_err_cls = py
+                            .import(intern!(py, "lancedb.remote.errors"))?
+                            .getattr(intern!(py, "HttpError"))?;
+                        let err = http_err_cls.call1((
+                            message,
                            request_id,
                            status_code.map(|s| s.as_u16()),
-                        )?;
-                        err.setattr(intern!(py, "__cause__"), cause_err)?;
-                    }
+                        ))?;

-                    Err(PyErr::from_value(err))
-                }),
+                        if let Some(cause) = source.source() {
+                            // The HTTP error already includes the first cause. But
+                            // we can add the rest of the chain if there is any more.
+                            let cause_err = http_from_rust_error(
+                                py,
+                                cause,
+                                request_id,
+                                status_code.map(|s| s.as_u16()),
+                            )?;
+                            err.setattr(intern!(py, "__cause__"), cause_err)?;
+                        }
+
+                        Err(PyErr::from_value(err))
+                    })
+                }
                LanceError::Retry {
                    request_id,
                    request_failures,
@@ -75,33 +78,37 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                    max_read_failures,
                    source,
                    status_code,
-                } => Python::with_gil(|py| {
-                    let cause_err = http_from_rust_error(
-                        py,
-                        source.as_ref(),
-                        request_id,
-                        status_code.map(|s| s.as_u16()),
-                    )?;
+                } =>
+                {
+                    #[allow(deprecated)]
+                    Python::with_gil(|py| {
+                        let cause_err = http_from_rust_error(
+                            py,
+                            source.as_ref(),
+                            request_id,
+                            status_code.map(|s| s.as_u16()),
+                        )?;

-                    let message = err.to_string();
-                    let retry_error_cls = py
-                        .import(intern!(py, "lancedb.remote.errors"))?
-                        .getattr("RetryError")?;
-                    let err = retry_error_cls.call1((
-                        message,
-                        request_id,
-                        *request_failures,
-                        *connect_failures,
-                        *read_failures,
-                        *max_request_failures,
-                        *max_connect_failures,
-                        *max_read_failures,
-                        status_code.map(|s| s.as_u16()),
-                    ))?;
+                        let message = err.to_string();
+                        let retry_error_cls = py
+                            .import(intern!(py, "lancedb.remote.errors"))?
+                            .getattr("RetryError")?;
+                        let err = retry_error_cls.call1((
+                            message,
+                            request_id,
+                            *request_failures,
+                            *connect_failures,
+                            *read_failures,
+                            *max_request_failures,
+                            *max_connect_failures,
+                            *max_read_failures,
+                            status_code.map(|s| s.as_u16()),
+                        ))?;

-                    err.setattr(intern!(py, "__cause__"), cause_err)?;
-                    Err(PyErr::from_value(err))
-                }),
+                        err.setattr(intern!(py, "__cause__"), cause_err)?;
+                        Err(PyErr::from_value(err))
+                    })
+                }
                _ => self.runtime_error(),
            },
        }
@@ -12,6 +12,7 @@ pub struct PyHeaderProvider {

 impl Clone for PyHeaderProvider {
    fn clone(&self) -> Self {
+        #[allow(deprecated)]
        Python::with_gil(|py| Self {
            provider: self.provider.clone_ref(py),
        })
@@ -25,6 +26,7 @@ impl PyHeaderProvider {

    /// Get headers from the Python provider (internal implementation)
    fn get_headers_internal(&self) -> Result<HashMap<String, String>, String> {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Call the get_headers method
            let result = self.provider.call_method0(py, "get_headers");
@@ -50,7 +50,8 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                    .ascii_folding(params.ascii_folding)
                    .ngram_min_length(params.ngram_min_length)
                    .ngram_max_length(params.ngram_max_length)
-                    .ngram_prefix_only(params.prefix_only);
+                    .ngram_prefix_only(params.prefix_only)
+                    .skip_merge(params.skip_merge);
                Ok(LanceDbIndex::FTS(inner_opts))
            },
            "IvfFlat" => {
@@ -179,6 +180,7 @@ struct FtsParams {
    ngram_min_length: u32,
    ngram_max_length: u32,
    prefix_only: bool,
+    skip_merge: bool,
 }

 #[derive(FromPyObject)]
@@ -1,4 +1,3 @@
-#![allow(deprecated)]
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors

@@ -19,7 +19,7 @@ use pyo3::{
    exceptions::PyRuntimeError,
    pyclass, pymethods,
    types::{PyAnyMethods, PyDict, PyDictMethods, PyType},
-    Bound, PyAny, PyRef, PyRefMut, PyResult, Python,
+    Bound, Py, PyAny, PyRef, PyRefMut, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -281,7 +281,12 @@ impl PyPermutationReader {
        let reader = slf.reader.clone();
        future_into_py(slf.py(), async move {
            let schema = reader.output_schema(selection).await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -29,6 +29,7 @@ use pyo3::types::PyList;
 use pyo3::types::{PyDict, PyString};
 use pyo3::Bound;
 use pyo3::IntoPyObject;
+use pyo3::Py;
 use pyo3::PyAny;
 use pyo3::PyRef;
 use pyo3::PyResult;
@@ -216,7 +217,7 @@ impl<'py> IntoPyObject<'py> for PyQueryVectors {
        let py_objs = self
            .0
            .into_iter()
-            .map(|v| v.to_data().into_pyarrow(py).map(|bound| bound.unbind()))
+            .map(|v| v.to_data().into_pyarrow(py))
            .collect::<Result<Vec<_>, _>>()?;
        PyList::new(py, py_objs)
    }
@@ -453,7 +454,12 @@ impl Query {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -532,7 +538,12 @@ impl TakeQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -627,7 +638,12 @@ impl FTSQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -806,7 +822,12 @@ impl VectorQuery {
        let inner = self_.inner.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.output_schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -22,6 +22,7 @@ pub struct PyStorageOptionsProvider {

 impl Clone for PyStorageOptionsProvider {
    fn clone(&self) -> Self {
+        #[allow(deprecated)]
        Python::with_gil(|py| Self {
            inner: self.inner.clone_ref(py),
        })
@@ -30,6 +31,7 @@ impl Clone for PyStorageOptionsProvider {

 impl PyStorageOptionsProvider {
    pub fn new(obj: Py<PyAny>) -> PyResult<Self> {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Verify the object has a fetch_storage_options method
            if !obj.bind(py).hasattr("fetch_storage_options")? {
@@ -37,7 +39,9 @@ impl PyStorageOptionsProvider {
                    "StorageOptionsProvider must implement fetch_storage_options() method",
                ));
            }
-            Ok(Self { inner: obj })
+            Ok(Self {
+                inner: obj.clone_ref(py),
+            })
        })
    }
 }
@@ -60,6 +64,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
        let py_provider = self.py_provider.clone();

        tokio::task::spawn_blocking(move || {
+            #[allow(deprecated)]
            Python::with_gil(|py| {
                // Call the Python fetch_storage_options method
                let result = py_provider
@@ -119,6 +124,7 @@ impl StorageOptionsProvider for PyStorageOptionsProviderWrapper {
    }

    fn provider_id(&self) -> String {
+        #[allow(deprecated)]
        Python::with_gil(|py| {
            // Call provider_id() method on the Python object
            let obj = self.py_provider.inner.bind(py);
@@ -21,7 +21,7 @@ use pyo3::{
    exceptions::{PyKeyError, PyRuntimeError, PyValueError},
    pyclass, pymethods,
    types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
+    Bound, FromPyObject, Py, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;

@@ -287,7 +287,12 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let schema = inner.schema().await.infer_error()?;
-            Python::with_gil(|py| schema.to_pyarrow(py).map(|bound| bound.unbind()))
+            #[allow(deprecated)]
+            let py_obj: Py<PyAny> = Python::with_gil(|py| -> PyResult<Py<PyAny>> {
+                let bound = schema.to_pyarrow(py)?;
+                Ok(bound.unbind())
+            })?;
+            Ok(py_obj)
        })
    }

@@ -437,6 +442,7 @@ impl Table {
        future_into_py(self_.py(), async move {
            let stats = inner.index_stats(&index_name).await.infer_error()?;
            if let Some(stats) = stats {
+                #[allow(deprecated)]
                Python::with_gil(|py| {
                    let dict = PyDict::new(py);
                    dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
@@ -467,6 +473,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let stats = inner.stats().await.infer_error()?;
+            #[allow(deprecated)]
            Python::with_gil(|py| {
                let dict = PyDict::new(py);
                dict.set_item("total_bytes", stats.total_bytes)?;
@@ -516,6 +523,7 @@ impl Table {
        let inner = self_.inner_ref()?.clone();
        future_into_py(self_.py(), async move {
            let versions = inner.list_versions().await.infer_error()?;
+            #[allow(deprecated)]
            let versions_as_dict = Python::with_gil(|py| {
                versions
                    .iter()
@@ -867,6 +875,7 @@ impl Tags {
            let tags = inner.tags().await.infer_error()?;
            let res = tags.list().await.infer_error()?;

+            #[allow(deprecated)]
            Python::with_gil(|py| {
                let py_dict = PyDict::new(py);
                for (key, contents) in res {
@@ -104,11 +104,16 @@ test-log = "0.2"


 [features]
-default = ["aws", "gcs", "azure", "dynamodb", "oss"]
+default = []
 aws = ["lance/aws", "lance-io/aws", "lance-namespace-impls/dir-aws"]
 oss = ["lance/oss", "lance-io/oss", "lance-namespace-impls/dir-oss"]
 gcs = ["lance/gcp", "lance-io/gcp", "lance-namespace-impls/dir-gcp"]
 azure = ["lance/azure", "lance-io/azure", "lance-namespace-impls/dir-azure"]
+huggingface = [
+    "lance/huggingface",
+    "lance-io/huggingface",
+    "lance-namespace-impls/dir-huggingface",
+]
 dynamodb = ["lance/dynamodb", "aws"]
 remote = ["dep:reqwest", "dep:http", "lance-namespace-impls/rest", "lance-namespace-impls/rest-adapter"]
 fp16kernels = ["lance-linalg/fp16kernels"]
@@ -148,3 +153,6 @@ name = "ivf_pq"
 [[example]]
 name = "hybrid_search"
 required-features = ["sentence-transformers"]
+
+[package.metadata.docs.rs]
+all-features = true
@@ -205,24 +205,26 @@ impl Database for LanceNamespaceDatabase {
        let mut table_id = request.namespace.clone();
        table_id.push(request.name.clone());

-        let declare_request = DeclareTableRequest {
+        let create_empty_request = DeclareTableRequest {
            id: Some(table_id.clone()),
            location: None,
            vend_credentials: None,
            ..Default::default()
        };

-        let declare_response = self
+        let create_empty_response = self
            .namespace
-            .declare_table(declare_request)
+            .declare_table(create_empty_request)
            .await
            .map_err(|e| Error::Runtime {
                message: format!("Failed to declare table: {}", e),
            })?;

-        let location = declare_response.location.ok_or_else(|| Error::Runtime {
-            message: "Table location is missing from declare_table response".to_string(),
-        })?;
+        let location = create_empty_response
+            .location
+            .ok_or_else(|| Error::Runtime {
+                message: "Table location is missing from create_empty_table response".to_string(),
+            })?;

        let native_table = NativeTable::create_from_namespace(
            self.namespace.clone(),
@@ -53,5 +53,8 @@ pub struct LabelListIndexBuilder {}

 pub use lance_index::scalar::inverted::query::*;
 pub use lance_index::scalar::FullTextSearchQuery;
+/// Builder for full text search (FTS) index parameters.
+///
+/// Use [`FtsIndexBuilder::skip_merge`] to skip the partition merge stage after indexing.
 pub use lance_index::scalar::InvertedIndexParams as FtsIndexBuilder;
 pub use lance_index::scalar::InvertedIndexParams;
@@ -25,13 +25,14 @@
 //!
 //! ## Crate Features
 //!
-//! ### Experimental Features
-//!
-//! These features are not enabled by default.  They are experimental or in-development features that
-//! are not yet ready to be released.
-//!
-//! - `remote` - Enable remote client to connect to LanceDB cloud.  This is not yet fully implemented
-//!   and should not be enabled.
+//! - `aws` - Enable AWS S3 object store support.
+//! - `dynamodb` - Enable DynamoDB manifest store support.
+//! - `azure` - Enable Azure Blob Storage object store support.
+//! - `gcs` - Enable Google Cloud Storage object store support.
+//! - `oss` - Enable Alibaba Cloud OSS object store support.
+//! - `remote` - Enable remote client to connect to LanceDB cloud.
+//! - `huggingface` - Enable HuggingFace Hub integration for loading datasets from the Hub.
+//! - `fp16kernels` - Enable FP16 kernels for faster vector search on CPU.
 //!
 //! ### Quick Start
 //!
@@ -53,6 +54,8 @@
 //! You can also use [`ConnectOptions`] to configure the connection to the database.
 //!
 //! ```rust
+//! # #[cfg(feature = "aws")]
+//! # {
 //! use object_store::aws::AwsCredential;
 //! # tokio::runtime::Runtime::new().unwrap().block_on(async {
 //! let db = lancedb::connect("data/sample-lancedb")
@@ -65,6 +68,7 @@
 //!     .await
 //!     .unwrap();
 //! # });
+//! # }
 //! ```
 //!
 //! LanceDB uses [arrow-rs](https://github.com/apache/arrow-rs) to define schema, data types and array itself.
@@ -2624,6 +2624,11 @@ mod tests {
                serde_json::to_value(InvertedIndexParams::default()).unwrap(),
                Index::FTS(Default::default()),
            ),
+            (
+                "FTS",
+                serde_json::to_value(InvertedIndexParams::default().skip_merge(true)).unwrap(),
+                Index::FTS(InvertedIndexParams::default().skip_merge(true)),
+            ),
        ];

        for (index_type, expected_body, index) in cases {
@@ -1424,7 +1424,9 @@ impl Table {
            })
            .collect::<Vec<_>>();

-        let unioned = UnionExec::try_new(projected_plans).unwrap();
+        let unioned = UnionExec::try_new(projected_plans).map_err(|e| Error::Runtime {
+            message: format!("Failed to build union plan: {e}"),
+        })?;
        // We require 1 partition in the final output
        let repartitioned = RepartitionExec::try_new(
            unioned,
@@ -2332,18 +2334,6 @@ impl NativeTable {
        }
    }

-    /// Convert selected columns into the namespace request format.
-    fn namespace_columns(&self, columns: &[String]) -> Option<Box<QueryTableRequestColumns>> {
-        if columns.is_empty() {
-            None
-        } else {
-            Some(Box::new(QueryTableRequestColumns {
-                column_names: Some(columns.to_vec()),
-                column_aliases: None,
-            }))
-        }
-    }
-
    /// Convert an AnyQuery to the namespace QueryTableRequest format.
    fn convert_to_namespace_query(&self, query: &AnyQuery) -> Result<NsQueryTableRequest> {
        match query {
@@ -2358,9 +2348,12 @@ impl NativeTable {
                };

                // Convert select to columns list
-                let columns = match &vq.base.select {
+                let columns: Option<Box<QueryTableRequestColumns>> = match &vq.base.select {
                    Select::All => None,
-                    Select::Columns(cols) => self.namespace_columns(cols),
+                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
+                        column_names: Some(cols.clone()),
+                        column_aliases: None,
+                    })),
                    Select::Dynamic(_) => {
                        return Err(Error::NotSupported {
                            message:
@@ -2395,8 +2388,6 @@ impl NativeTable {
                });

                Ok(NsQueryTableRequest {
-                    identity: None,
-                    context: None,
                    id: None, // Will be set in namespace_query
                    k: vq.base.limit.unwrap_or(10) as i32,
                    vector: Box::new(vector),
@@ -2416,6 +2407,7 @@ impl NativeTable {
                    bypass_vector_index: Some(!vq.use_index),
                    full_text_query,
                    version: None,
+                    ..Default::default()
                })
            }
            AnyQuery::Query(q) => {
@@ -2433,9 +2425,12 @@ impl NativeTable {
                    .map(|f| self.filter_to_sql(f))
                    .transpose()?;

-                let columns = match &q.select {
+                let columns: Option<Box<QueryTableRequestColumns>> = match &q.select {
                    Select::All => None,
-                    Select::Columns(cols) => self.namespace_columns(cols),
+                    Select::Columns(cols) => Some(Box::new(QueryTableRequestColumns {
+                        column_names: Some(cols.clone()),
+                        column_aliases: None,
+                    })),
                    Select::Dynamic(_) => {
                        return Err(Error::NotSupported {
                            message: "Dynamic columns are not supported for server-side query"
@@ -2467,8 +2462,6 @@ impl NativeTable {
                });

                Ok(NsQueryTableRequest {
-                    identity: None,
-                    context: None,
                    id: None, // Will be set by caller
                    vector,
                    k: q.limit.unwrap_or(10) as i32,
@@ -2488,6 +2481,7 @@ impl NativeTable {
                    fast_search: None,
                    lower_bound: None,
                    upper_bound: None,
+                    ..Default::default()
                })
            }
        }
@@ -5159,16 +5153,15 @@ mod tests {
        let any_query = AnyQuery::VectorQuery(vq);
        let ns_request = table.convert_to_namespace_query(&any_query).unwrap();

-        assert_eq!(ns_request.k, 10);
-        assert_eq!(ns_request.offset, Some(5));
-        assert_eq!(ns_request.filter, Some("id > 0".to_string()));
        let column_names = ns_request
            .columns
            .as_ref()
-            .and_then(|c| c.column_names.as_ref())
-            .cloned()
-            .unwrap();
-        assert_eq!(column_names, vec!["id".to_string()]);
+            .and_then(|cols| cols.column_names.clone());
+
+        assert_eq!(ns_request.k, 10);
+        assert_eq!(ns_request.offset, Some(5));
+        assert_eq!(ns_request.filter, Some("id > 0".to_string()));
+        assert_eq!(column_names, Some(vec!["id".to_string()]));
        assert_eq!(ns_request.vector_column, Some("vector".to_string()));
        assert_eq!(ns_request.distance_type, Some("l2".to_string()));
        assert!(ns_request.vector.single_vector.is_some());
@@ -5205,17 +5198,16 @@ mod tests {
        let any_query = AnyQuery::Query(q);
        let ns_request = table.convert_to_namespace_query(&any_query).unwrap();

+        let column_names = ns_request
+            .columns
+            .as_ref()
+            .and_then(|cols| cols.column_names.clone());
+
        // Plain queries should pass an empty vector
        assert_eq!(ns_request.k, 20);
        assert_eq!(ns_request.offset, Some(5));
        assert_eq!(ns_request.filter, Some("id > 5".to_string()));
-        let column_names = ns_request
-            .columns
-            .as_ref()
-            .and_then(|c| c.column_names.as_ref())
-            .cloned()
-            .unwrap();
-        assert_eq!(column_names, vec!["id".to_string()]);
+        assert_eq!(column_names, Some(vec!["id".to_string()]));
        assert_eq!(ns_request.with_row_id, Some(true));
        assert_eq!(ns_request.bypass_vector_index, Some(true));
        assert!(ns_request.vector_column.is_none()); // No vector column for plain queries
Author	SHA1	Message	Date
BubbleCal	4b24e28539	Add skip_merge option for FTS indexes	2026-01-20 21:32:41 +08:00
LanceDB RobotandBubbleCal	4da01a0e65	chore: update lance dependency to v2.0.0-beta.8 (#2907 ) ## Summary - bump Lance crates to v2.0.0-beta.8 and align arrow/datafusion/regex/half and PyO3 dependencies - update Rust/Python bindings for upstream API changes (namespace/table requests, query select columns, storage option providers) - verified with cargo clippy --workspace --tests --all-features -D warnings and cargo fmt --all Triggered by refs/tags/v2.0.0-beta.8. --------- Signed-off-by: BubbleCal <bubble-cal@outlook.com> Co-authored-by: BubbleCal <bubble-cal@outlook.com>	2026-01-16 01:46:52 +08:00
Will Jones	1840aa7edc	feat(rust)!: remove default features (#2912 ) BREAKING CHANGE: removes `aws`, `dynamodb`, `azure`, `gcs`, `oss`, `huggingface` from default Rust features. They can be enabled by users as needed. They are still enabled for Python and NodeJS, since those users don't control the compilation of artifacts. Closes #2911	2026-01-13 11:23:14 -08:00
Xuanwo	489c91c5d6	feat: enable huggingface feature by default (#2910 )	2026-01-13 20:42:11 +05:30
LanceDB Robot	f0c3fe5c6d	chore: update lance dependency to v1.0.2-rc.2 (#2908 ) ## Summary - bump Lance dependencies to v1.0.2-rc.2 using ci/set_lance_version.py - verified cargo clippy --workspace --tests --all-features -D warnings - ran cargo fmt --all Tag: https://github.com/lance-format/lance/releases/tag/v1.0.2-rc.2	2026-01-12 12:28:07 -08:00