Bump version: 0.21.1-beta.0 → 0.21.1

We attempted to make pylance optional in
https://github.com/lancedb/lancedb/pull/2156 but it appears this did not
quite work. Users are unable to use lancedb from a fresh install. This
reverts the optional-ness so we can get back in a working state while we
fix the issue.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.18.0-beta.0"
+current_version = "0.18.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/python.yml

@@ -33,11 +33,41 @@ jobs:
           python-version: "3.12"
       - name: Install ruff
         run: |
-          pip install ruff==0.8.4
+          pip install ruff==0.9.9
       - name: Format check
         run: ruff format --check .
       - name: Lint
         run: ruff check .
+
+  type-check:
+    name: "Type Check"
+    timeout-minutes: 30
+    runs-on: "ubuntu-22.04"
+    defaults:
+      run:
+        shell: bash
+        working-directory: python
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.12"
+      - name: Install protobuf compiler
+        run: |
+          sudo apt update
+          sudo apt install -y protobuf-compiler
+          pip install toml
+      - name: Install dependencies
+        run: |
+          python ../ci/parse_requirements.py pyproject.toml --extras dev,tests,embeddings > requirements.txt
+          pip install -r requirements.txt
+      - name: Run pyright
+        run: pyright
+
   doctest:
     name: "Doctest"
     timeout-minutes: 30

.pre-commit-config.yaml

@@ -1,16 +1,22 @@
 repos:
--   repo: https://github.com/pre-commit/pre-commit-hooks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v3.2.0
     hooks:
       - id: check-yaml
       - id: end-of-file-fixer
       - id: trailing-whitespace
--   repo: https://github.com/astral-sh/ruff-pre-commit
+  - repo: https://github.com/astral-sh/ruff-pre-commit
     # Ruff version.
-    rev: v0.8.4
+    rev: v0.9.9
     hooks:
       - id: ruff
-- repo: local
+  # - repo: https://github.com/RobertCraigie/pyright-python
+  #   rev: v1.1.395
+  #   hooks:
+  #     - id: pyright
+  #       args: ["--project", "python"]
+  #       additional_dependencies: [pyarrow-stubs]
+  - repo: local
     hooks:
       - id: local-biome-check
         name: biome check

Cargo.lock

@@ -176,9 +176,9 @@ checksum = "7c02d123df017efcdfbd739ef81735b36c5ba83ec3c59c80a9d7ecc718f92e50"
 
 [[package]]
 name = "arrow"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eaf3437355979f1e93ba84ba108c38be5767713051f3c8ffbf07c094e2e61f9f"
+checksum = "dc208515aa0151028e464cc94a692156e945ce5126abd3537bb7fd6ba2143ed1"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -198,24 +198,23 @@ dependencies = [
 
 [[package]]
 name = "arrow-arith"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "31dce77d2985522288edae7206bffd5fc4996491841dda01a13a58415867e681"
+checksum = "e07e726e2b3f7816a85c6a45b6ec118eeeabf0b2a8c208122ad949437181f49a"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
  "arrow-data",
  "arrow-schema",
  "chrono",
- "half",
  "num",
 ]
 
 [[package]]
 name = "arrow-array"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2d45fe6d3faed0435b7313e59a02583b14c6c6339fa7729e94c32a20af319a79"
+checksum = "a2262eba4f16c78496adfd559a29fe4b24df6088efc9985a873d58e92be022d5"
 dependencies = [
  "ahash",
  "arrow-buffer",
@@ -230,9 +229,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-buffer"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2b02656a35cc103f28084bc80a0159668e0a680d919cef127bd7e0aaccb06ec1"
+checksum = "4e899dade2c3b7f5642eb8366cfd898958bcca099cde6dfea543c7e8d3ad88d4"
 dependencies = [
  "bytes",
  "half",
@@ -241,9 +240,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-cast"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c73c6233c5b5d635a56f6010e6eb1ab9e30e94707db21cea03da317f67d84cf3"
+checksum = "4103d88c5b441525ed4ac23153be7458494c2b0c9a11115848fdb9b81f6f886a"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -262,28 +261,25 @@ dependencies = [
 
 [[package]]
 name = "arrow-csv"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ec222848d70fea5a32af9c3602b08f5d740d5e2d33fbd76bf6fd88759b5b13a7"
+checksum = "43d3cb0914486a3cae19a5cad2598e44e225d53157926d0ada03c20521191a65"
 dependencies = [
  "arrow-array",
- "arrow-buffer",
  "arrow-cast",
- "arrow-data",
  "arrow-schema",
  "chrono",
  "csv",
  "csv-core",
  "lazy_static",
- "lexical-core",
  "regex",
 ]
 
 [[package]]
 name = "arrow-data"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b7f2861ffa86f107b8ab577d86cff7c7a490243eabe961ba1e1af4f27542bb79"
+checksum = "0a329fb064477c9ec5f0870d2f5130966f91055c7c5bce2b3a084f116bc28c3b"
 dependencies = [
  "arrow-buffer",
  "arrow-schema",
@@ -293,13 +289,12 @@ dependencies = [
 
 [[package]]
 name = "arrow-ipc"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0270dc511f11bb5fa98a25020ad51a99ca5b08d8a8dfbd17503bb9dba0388f0b"
+checksum = "ddecdeab02491b1ce88885986e25002a3da34dd349f682c7cfe67bab7cc17b86"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
- "arrow-cast",
  "arrow-data",
  "arrow-schema",
  "flatbuffers",
@@ -309,9 +304,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-json"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0eff38eeb8a971ad3a4caf62c5d57f0cff8a48b64a55e3207c4fd696a9234aad"
+checksum = "d03b9340013413eb84868682ace00a1098c81a5ebc96d279f7ebf9a4cac3c0fd"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -329,26 +324,23 @@ dependencies = [
 
 [[package]]
 name = "arrow-ord"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c6f202a879d287099139ff0d121e7f55ae5e0efe634b8cf2106ebc27a8715dee"
+checksum = "f841bfcc1997ef6ac48ee0305c4dfceb1f7c786fe31e67c1186edf775e1f1160"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
  "arrow-data",
  "arrow-schema",
  "arrow-select",
- "half",
- "num",
 ]
 
 [[package]]
 name = "arrow-row"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a8f936954991c360ba762dff23f5dda16300774fafd722353d9683abd97630ae"
+checksum = "1eeb55b0a0a83851aa01f2ca5ee5648f607e8506ba6802577afdda9d75cdedcd"
 dependencies = [
- "ahash",
  "arrow-array",
  "arrow-buffer",
  "arrow-data",
@@ -358,18 +350,18 @@ dependencies = [
 
 [[package]]
 name = "arrow-schema"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9579b9d8bce47aa41389fe344f2c6758279983b7c0ebb4013e283e3e91bb450e"
+checksum = "85934a9d0261e0fa5d4e2a5295107d743b543a6e0484a835d4b8db2da15306f9"
 dependencies = [
  "bitflags 2.8.0",
 ]
 
 [[package]]
 name = "arrow-select"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "7471ba126d0b0aaa24b50a36bc6c25e4e74869a1fd1a5553357027a0b1c8d1f1"
+checksum = "7e2932aece2d0c869dd2125feb9bd1709ef5c445daa3838ac4112dcfa0fda52c"
 dependencies = [
  "ahash",
  "arrow-array",
@@ -381,9 +373,9 @@ dependencies = [
 
 [[package]]
 name = "arrow-string"
-version = "53.4.0"
+version = "54.2.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72993b01cb62507b06f1fb49648d7286c8989ecfabdb7b77a750fcb54410731b"
+checksum = "912e38bd6a7a7714c1d9b61df80315685553b7455e8a6045c27531d8ecd5b458"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -1708,9 +1700,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "014fc8c384ecacedaabb3bc8359c2a6c6e9d8f7bea65be3434eccacfc37f52d9"
+checksum = "eae420e7a5b0b7f1c39364cc76cbcd0f5fdc416b2514ae3847c2676bbd60702a"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -1719,7 +1711,6 @@ dependencies = [
  "async-trait",
  "bytes",
  "chrono",
- "dashmap",
  "datafusion-catalog",
  "datafusion-common",
  "datafusion-common-runtime",
@@ -1738,7 +1729,7 @@ dependencies = [
  "datafusion-sql",
  "futures",
  "glob",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "log",
  "object_store",
  "parking_lot",
@@ -1753,30 +1744,38 @@ dependencies = [
 
 [[package]]
 name = "datafusion-catalog"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ee60d33e210ef96070377ae667ece7caa0e959c8387496773d4a1a72f1a5012e"
+checksum = "6f27987bc22b810939e8dfecc55571e9d50355d6ea8ec1c47af8383a76a6d0e1"
 dependencies = [
- "arrow-schema",
+ "arrow",
  "async-trait",
+ "dashmap",
  "datafusion-common",
  "datafusion-execution",
  "datafusion-expr",
  "datafusion-physical-plan",
+ "datafusion-sql",
+ "futures",
+ "itertools 0.14.0",
+ "log",
  "parking_lot",
+ "sqlparser 0.53.0",
 ]
 
 [[package]]
 name = "datafusion-common"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b42b7d720fe21ed9cca2ebb635f3f13a12cfab786b41e0fba184fb2e620525b"
+checksum = "e3f6d5b8c9408cc692f7c194b8aa0c0f9b253e065a8d960ad9cdc2a13e697602"
 dependencies = [
  "ahash",
  "arrow",
  "arrow-array",
  "arrow-buffer",
+ "arrow-ipc",
  "arrow-schema",
+ "base64 0.22.1",
  "half",
  "hashbrown 0.14.5",
  "indexmap 2.7.1",
@@ -1791,9 +1790,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-common-runtime"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "72fbf14d4079f7ce5306393084fe5057dddfdc2113577e0049310afa12e94281"
+checksum = "0d4603c8e8a4baf77660ab7074cc66fc15cc8a18f2ce9dfadb755fc6ee294e48"
 dependencies = [
  "log",
  "tokio",
@@ -1801,15 +1800,15 @@ dependencies = [
 
 [[package]]
 name = "datafusion-doc"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c278dbd64860ed0bb5240fc1f4cb6aeea437153910aea69bcf7d5a8d6d0454f3"
+checksum = "e5bf4bc68623a5cf231eed601ed6eb41f46a37c4d15d11a0bff24cbc8396cd66"
 
 [[package]]
 name = "datafusion-execution"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e22cb02af47e756468b3cbfee7a83e3d4f2278d452deb4b033ba933c75169486"
+checksum = "88b491c012cdf8e051053426013429a76f74ee3c2db68496c79c323ca1084d27"
 dependencies = [
  "arrow",
  "dashmap",
@@ -1826,9 +1825,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-expr"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "62298eadb1d15b525df1315e61a71519ffc563d41d5c3b2a30fda2d70f77b93c"
+checksum = "e5a181408d4fc5dc22f9252781a8f39f2d0e5d1b33ec9bde242844980a2689c1"
 dependencies = [
  "arrow",
  "chrono",
@@ -1846,20 +1845,21 @@ dependencies = [
 
 [[package]]
 name = "datafusion-expr-common"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dda7f73c5fc349251cd3dcb05773c5bf55d2505a698ef9d38dfc712161ea2f55"
+checksum = "d1129b48e8534d8c03c6543bcdccef0b55c8ac0c1272a15a56c67068b6eb1885"
 dependencies = [
  "arrow",
  "datafusion-common",
- "itertools 0.13.0",
+ "itertools 0.14.0",
+ "paste",
 ]
 
 [[package]]
 name = "datafusion-functions"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fd197f3b2975424d3a4898ea46651be855a46721a56727515dbd5c9e2fb597da"
+checksum = "6125874e4856dfb09b59886784fcb74cde5cfc5930b3a80a1a728ef7a010df6b"
 dependencies = [
  "arrow",
  "arrow-buffer",
@@ -1875,7 +1875,7 @@ dependencies = [
  "datafusion-macros",
  "hashbrown 0.14.5",
  "hex",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "log",
  "md-5",
  "rand",
@@ -1887,12 +1887,13 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aabbe48fba18f9981b134124381bee9e46f93518b8ad2f9721ee296cef5affb9"
+checksum = "f3add7b1d3888e05e7c95f2b281af900ca69ebdcb21069ba679b33bde8b3b9d6"
 dependencies = [
  "ahash",
  "arrow",
+ "arrow-buffer",
  "arrow-schema",
  "datafusion-common",
  "datafusion-doc",
@@ -1909,9 +1910,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-aggregate-common"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d7a3fefed9c8c11268d446d924baca8cabf52fe32f73fdaa20854bac6473590c"
+checksum = "6e18baa4cfc3d2f144f74148ed68a1f92337f5072b6dde204a0dbbdf3324989c"
 dependencies = [
  "ahash",
  "arrow",
@@ -1922,9 +1923,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-nested"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6360f27464fab857bec698af39b2ae331dc07c8bf008fb4de387a19cdc6815a5"
+checksum = "3ec5ee8cecb0dc370291279673097ddabec03a011f73f30d7f1096457127e03e"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -1932,21 +1933,23 @@ dependencies = [
  "arrow-ord",
  "arrow-schema",
  "datafusion-common",
+ "datafusion-doc",
  "datafusion-execution",
  "datafusion-expr",
  "datafusion-functions",
  "datafusion-functions-aggregate",
+ "datafusion-macros",
  "datafusion-physical-expr-common",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "log",
  "paste",
 ]
 
 [[package]]
 name = "datafusion-functions-table"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "5c35c070eb705c12795dab399c3809f4dfbc290678c624d3989490ca9b8449c1"
+checksum = "2c403ddd473bbb0952ba880008428b3c7febf0ed3ce1eec35a205db20efb2a36"
 dependencies = [
  "arrow",
  "async-trait",
@@ -1960,9 +1963,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "52229bca26b590b140900752226c829f15fc1a99840e1ca3ce1a9534690b82a8"
+checksum = "1ab18c2fb835614d06a75f24a9e09136d3a8c12a92d97c95a6af316a1787a9c5"
 dependencies = [
  "datafusion-common",
  "datafusion-doc",
@@ -1977,9 +1980,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-functions-window-common"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "367befc303b64a668a10ae6988a064a9289e1999e71a7f8e526b6e14d6bdd9d6"
+checksum = "a77b73bc15e7d1967121fdc7a55d819bfb9d6c03766a6c322247dce9094a53a4"
 dependencies = [
  "datafusion-common",
  "datafusion-physical-expr-common",
@@ -1987,19 +1990,20 @@ dependencies = [
 
 [[package]]
 name = "datafusion-macros"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f5de3c8f386ea991696553afe241a326ecbc3c98a12c562867e4be754d3a060c"
+checksum = "09369b8d962291e808977cf94d495fd8b5b38647232d7ef562c27ac0f495b0af"
 dependencies = [
+ "datafusion-expr",
  "quote",
  "syn 2.0.98",
 ]
 
 [[package]]
 name = "datafusion-optimizer"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "53b520413906f755910422b016fb73884ae6e9e1b376de4f9584b6c0e031da75"
+checksum = "2403a7e4a84637f3de7d8d4d7a9ccc0cc4be92d89b0161ba3ee5be82f0531c54"
 dependencies = [
  "arrow",
  "chrono",
@@ -2007,7 +2011,7 @@ dependencies = [
  "datafusion-expr",
  "datafusion-physical-expr",
  "indexmap 2.7.1",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "log",
  "regex",
  "regex-syntax 0.8.5",
@@ -2015,9 +2019,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-physical-expr"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "acd6ddc378f6ad19af95ccd6790dec8f8e1264bc4c70e99ddc1830c1a1c78ccd"
+checksum = "86ff72ac702b62dbf2650c4e1d715ebd3e4aab14e3885e72e8549e250307347c"
 dependencies = [
  "ahash",
  "arrow",
@@ -2032,47 +2036,53 @@ dependencies = [
  "half",
  "hashbrown 0.14.5",
  "indexmap 2.7.1",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "log",
  "paste",
- "petgraph 0.6.5",
+ "petgraph",
 ]
 
 [[package]]
 name = "datafusion-physical-expr-common"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "06e6c05458eccd74b4c77ed6a1fe63d52434240711de7f6960034794dad1caf5"
+checksum = "60982b7d684e25579ee29754b4333057ed62e2cc925383c5f0bd8cab7962f435"
 dependencies = [
  "ahash",
  "arrow",
+ "arrow-buffer",
  "datafusion-common",
  "datafusion-expr-common",
  "hashbrown 0.14.5",
- "itertools 0.13.0",
+ "itertools 0.14.0",
 ]
 
 [[package]]
 name = "datafusion-physical-optimizer"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9dc3a82190f49c37d377f31317e07ab5d7588b837adadba8ac367baad5dc2351"
+checksum = "ac5e85c189d5238a5cf181a624e450c4cd4c66ac77ca551d6f3ff9080bac90bb"
 dependencies = [
  "arrow",
+ "arrow-schema",
  "datafusion-common",
  "datafusion-execution",
+ "datafusion-expr",
  "datafusion-expr-common",
  "datafusion-physical-expr",
+ "datafusion-physical-expr-common",
  "datafusion-physical-plan",
- "itertools 0.13.0",
+ "futures",
+ "itertools 0.14.0",
  "log",
+ "url",
 ]
 
 [[package]]
 name = "datafusion-physical-plan"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a6608bc9844b4ddb5ed4e687d173e6c88700b1d0482f43894617d18a1fe75da"
+checksum = "c36bf163956d7e2542657c78b3383fdc78f791317ef358a359feffcdb968106f"
 dependencies = [
  "ahash",
  "arrow",
@@ -2093,7 +2103,7 @@ dependencies = [
  "half",
  "hashbrown 0.14.5",
  "indexmap 2.7.1",
- "itertools 0.13.0",
+ "itertools 0.14.0",
  "log",
  "parking_lot",
  "pin-project-lite",
@@ -2102,9 +2112,9 @@ dependencies = [
 
 [[package]]
 name = "datafusion-sql"
-version = "44.0.0"
+version = "45.0.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6a884061c79b33d0c8e84a6f4f4be8bdc12c0f53f5af28ddf5d6d95ac0b15fdc"
+checksum = "e13caa4daede211ecec53c78b13c503b592794d125f9a3cc3afe992edf9e7f43"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -2484,12 +2494,6 @@ dependencies = [
  "subtle",
 ]
 
-[[package]]
-name = "fixedbitset"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0ce7134b9999ecaf8bcd65542e436736ef32ddca1b3e06094cb6ec5755203b80"
-
 [[package]]
 name = "fixedbitset"
 version = "0.5.7"
@@ -2570,8 +2574,9 @@ dependencies = [
 
 [[package]]
 name = "fsst"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "499049427ae23480696a1b728a292fec9fa554742ee26c0f35acbdade47801be"
 dependencies = [
  "rand",
 ]
@@ -3532,8 +3537,9 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "748d2bd8e36f25a7fc130398e115678d01a1b821aceafe790965a0511d2443fe"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -3592,8 +3598,9 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e5ca5041940b2623daf6398c1e297aedd99a9fc38070222e69a69f600dd374c9"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3610,8 +3617,9 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc3cd36bd1de369dd957e98fbacf8963fd1b147595fd4d2ba5e9f5866f143db9"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -3647,8 +3655,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "72791574cb837c5d2e89f3688b71c5fc9cc584f8f79cc50005787f5cbe285506"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3673,8 +3682,9 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c4739cefb4757f5405c09c848d71e5a3ec05fbff26ac1a6e799774a1e878ba72"
 dependencies = [
  "arrayref",
  "arrow",
@@ -3712,8 +3722,9 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "005824228e561b4fda8f3bfd9d755a6cbd14b2d68da93c4f094af9ee6981977f"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -3747,8 +3758,9 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "49177175c77cc1201366aba59ca4aa457893d1a0aad0fa6cbf7095741be7aeba"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3800,8 +3812,9 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ea5e9a5bbbab0e5efc3038abb49c74add55fe7d72541a448e8c8dc45d7cbe406"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -3839,8 +3852,9 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2c6958010c1f35babc9c68c5a4a49c154a3ecc2d0a9a11a11a970c06e2f2bdb5"
 dependencies = [
  "arrow-array",
  "arrow-ord",
@@ -3863,8 +3877,9 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6c08830bb24cadbbd24069e76d17570bfa7518eca9f2aa3651afb72035b74331"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -3903,8 +3918,9 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "0.24.0"
+version = "0.24.1"
-source = "git+https://github.com/lancedb/lance.git?tag=v0.24.0-beta.1#33ae43b2944c12e0dbd139e8aa098cffa74edef5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ae923e5c09091bcf48aa166ac362b0dd189b55779ff553281094510728ea0c66"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4044,7 +4060,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.21.0-beta.0"
+version = "0.21.0-beta.1"
 dependencies = [
  "arrow",
  "env_logger",
@@ -4053,7 +4069,7 @@ dependencies = [
  "pin-project",
  "pyo3",
  "pyo3-async-runtimes",
- "pyo3-build-config 0.20.3",
+ "pyo3-build-config",
  "tokio",
 ]
 
@@ -4974,23 +4990,13 @@ version = "0.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "df202b0b0f5b8e389955afd5f27b007b00fb948162953f1db9c70d2c7e3157d7"
 
-[[package]]
-name = "petgraph"
-version = "0.6.5"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b4c5cc86750666a3ed20bdaf5ca2a0344f9c67674cae0515bec2da16fbaa47db"
-dependencies = [
- "fixedbitset 0.4.2",
- "indexmap 2.7.1",
-]
-
 [[package]]
 name = "petgraph"
 version = "0.7.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "3672b37090dbd86368a4145bc067582552b29c27377cad4e0a306c97f9bd7772"
 dependencies = [
- "fixedbitset 0.5.7",
+ "fixedbitset",
  "indexmap 2.7.1",
 ]
 
@@ -5508,7 +5514,7 @@ dependencies = [
  "log",
  "multimap",
  "once_cell",
- "petgraph 0.7.1",
+ "petgraph",
  "prettyplease",
  "prost",
  "prost-types",
@@ -5562,9 +5568,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f402062616ab18202ae8319da13fa4279883a2b8a9d9f83f20dbade813ce1884"
+checksum = "7778bffd85cf38175ac1f545509665d0b9b92a198ca7941f131f85f7a4f9a872"
 dependencies = [
  "cfg-if",
  "indoc",
@@ -5572,7 +5578,7 @@ dependencies = [
  "memoffset",
  "once_cell",
  "portable-atomic",
- "pyo3-build-config 0.22.6",
+ "pyo3-build-config",
  "pyo3-ffi",
  "pyo3-macros",
  "unindent",
@@ -5580,9 +5586,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-async-runtimes"
-version = "0.22.0"
+version = "0.23.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2529f0be73ffd2be0cc43c013a640796558aa12d7ca0aab5cc14f375b4733031"
+checksum = "977dc837525cfd22919ba6a831413854beb7c99a256c03bf8624ad707e45810e"
 dependencies = [
  "futures",
  "once_cell",
@@ -5594,9 +5600,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-async-runtimes-macros"
-version = "0.22.0"
+version = "0.23.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "22c26fd8e9fc19f53f0c1e00bf61471de6789f7eb263056f7f944a9cceb5823e"
+checksum = "b2df2884957d2476731f987673befac5d521dff10abb0a7cbe12015bc7702fe9"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5605,19 +5611,9 @@ dependencies = [
 
 [[package]]
 name = "pyo3-build-config"
-version = "0.20.3"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "deaa5745de3f5231ce10517a1f5dd97d53e5a2fd77aa6b5842292085831d48d7"
+checksum = "94f6cbe86ef3bf18998d9df6e0f3fc1050a8c5efa409bf712e661a4366e010fb"
-dependencies = [
- "once_cell",
- "target-lexicon",
-]
-
-[[package]]
-name = "pyo3-build-config"
-version = "0.22.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b14b5775b5ff446dd1056212d778012cbe8a0fbffd368029fd9e25b514479c38"
 dependencies = [
  "once_cell",
  "target-lexicon",
@@ -5625,19 +5621,19 @@ dependencies = [
 
 [[package]]
 name = "pyo3-ffi"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9ab5bcf04a2cdcbb50c7d6105de943f543f9ed92af55818fd17b660390fc8636"
+checksum = "e9f1b4c431c0bb1c8fb0a338709859eed0d030ff6daa34368d3b152a63dfdd8d"
 dependencies = [
  "libc",
- "pyo3-build-config 0.22.6",
+ "pyo3-build-config",
 ]
 
 [[package]]
 name = "pyo3-macros"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fd24d897903a9e6d80b968368a34e1525aeb719d568dba8b3d4bfa5dc67d453"
+checksum = "fbc2201328f63c4710f68abdf653c89d8dbc2858b88c5d88b0ff38a75288a9da"
 dependencies = [
  "proc-macro2",
  "pyo3-macros-backend",
@@ -5647,13 +5643,13 @@ dependencies = [
 
 [[package]]
 name = "pyo3-macros-backend"
-version = "0.22.6"
+version = "0.23.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "36c011a03ba1e50152b4b394b479826cad97e7a21eb52df179cd91ac411cbfbe"
+checksum = "fca6726ad0f3da9c9de093d6f116a93c1a38e417ed73bf138472cf4064f72028"
 dependencies = [
  "heck 0.5.0",
  "proc-macro2",
- "pyo3-build-config 0.22.6",
+ "pyo3-build-config",
  "quote",
  "syn 2.0.98",
 ]

Cargo.toml

@@ -21,32 +21,30 @@ categories = ["database-implementations"]
 rust-version = "1.78.0"
 
 [workspace.dependencies]
-lance = { "version" = "=0.24.0", "features" = [
+lance = { "version" = "=0.24.1", "features" = ["dynamodb"] }
-    "dynamodb",
+lance-io = { version = "=0.24.1" }
-], git = "https://github.com/lancedb/lance.git", tag = "v0.24.0-beta.1" }
+lance-index = { version = "=0.24.1" }
-lance-io = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
+lance-linalg = { version = "=0.24.1" }
-lance-index = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
+lance-table = { version = "=0.24.1" }
-lance-linalg = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
+lance-testing = { version = "=0.24.1" }
-lance-table = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
+lance-datafusion = { version = "=0.24.1" }
-lance-testing = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
+lance-encoding = { version = "=0.24.1" }
-lance-datafusion = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
-lance-encoding = { version = "=0.24.0", tag = "v0.24.0-beta.1", git = "https://github.com/lancedb/lance.git" }
 # Note that this one does not include pyarrow
-arrow = { version = "53.2", optional = false }
+arrow = { version = "54.1", optional = false }
-arrow-array = "53.2"
+arrow-array = "54.1"
-arrow-data = "53.2"
+arrow-data = "54.1"
-arrow-ipc = "53.2"
+arrow-ipc = "54.1"
-arrow-ord = "53.2"
+arrow-ord = "54.1"
-arrow-schema = "53.2"
+arrow-schema = "54.1"
-arrow-arith = "53.2"
+arrow-arith = "54.1"
-arrow-cast = "53.2"
+arrow-cast = "54.1"
 async-trait = "0"
-datafusion = { version = "44.0", default-features = false }
+datafusion = { version = "45.0", default-features = false }
-datafusion-catalog = "44.0"
+datafusion-catalog = "45.0"
-datafusion-common = { version = "44.0", default-features = false }
+datafusion-common = { version = "45.0", default-features = false }
-datafusion-execution = "44.0"
+datafusion-execution = "45.0"
-datafusion-expr = "44.0"
+datafusion-expr = "45.0"
-datafusion-physical-plan = "44.0"
+datafusion-physical-plan = "45.0"
 env_logger = "0.11"
 half = { "version" = "=2.4.1", default-features = false, features = [
     "num-traits",

ci/parse_requirements.py

@@ -0,0 +1,41 @@
+import argparse
+import toml
+
+
+def parse_dependencies(pyproject_path, extras=None):
+    with open(pyproject_path, "r") as file:
+        pyproject = toml.load(file)
+
+    dependencies = pyproject.get("project", {}).get("dependencies", [])
+    for dependency in dependencies:
+        print(dependency)
+
+    optional_dependencies = pyproject.get("project", {}).get(
+        "optional-dependencies", {}
+    )
+
+    if extras:
+        for extra in extras.split(","):
+            for dep in optional_dependencies.get(extra, []):
+                print(dep)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Generate requirements.txt from pyproject.toml"
+    )
+    parser.add_argument("path", type=str, help="Path to pyproject.toml")
+    parser.add_argument(
+        "--extras",
+        type=str,
+        help="Comma-separated list of extras to include",
+        default="",
+    )
+
+    args = parser.parse_args()
+
+    parse_dependencies(args.path, args.extras)
+
+
+if __name__ == "__main__":
+    main()

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.18.0-beta.0</version>
+        <version>0.18.0-final.0</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.18.0-beta.0</version>
+    <version>0.18.0-final.0</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.18.0-beta.0",
+  "version": "0.18.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
       "cpu": [
         "x64",
         "arm64"
@@ -52,14 +52,14 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.18.0-beta.0",
+        "@lancedb/vectordb-darwin-arm64": "0.18.0",
-        "@lancedb/vectordb-darwin-x64": "0.18.0-beta.0",
+        "@lancedb/vectordb-darwin-x64": "0.18.0",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.18.0-beta.0",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.18.0",
-        "@lancedb/vectordb-linux-arm64-musl": "0.18.0-beta.0",
+        "@lancedb/vectordb-linux-arm64-musl": "0.18.0",
-        "@lancedb/vectordb-linux-x64-gnu": "0.18.0-beta.0",
+        "@lancedb/vectordb-linux-x64-gnu": "0.18.0",
-        "@lancedb/vectordb-linux-x64-musl": "0.18.0-beta.0",
+        "@lancedb/vectordb-linux-x64-musl": "0.18.0",
-        "@lancedb/vectordb-win32-arm64-msvc": "0.18.0-beta.0",
+        "@lancedb/vectordb-win32-arm64-msvc": "0.18.0",
-        "@lancedb/vectordb-win32-x64-msvc": "0.18.0-beta.0"
+        "@lancedb/vectordb-win32-x64-msvc": "0.18.0"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -330,9 +330,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.18.0.tgz",
-      "integrity": "sha512-dLLgMPllYJOiRfPqkqkmoQu48RIa7K4dOF/qFP8Aex3zqeHE/0sFm3DYjtSFc6SR/6yT8u6Y9iFo2cQp5rCFJA==",
+      "integrity": "sha512-ormNCmny1j64aSZRrZeUQ1Zs8cOFKrW14NgTmW3AehDuru+Ep+8AriHA5Pmyi6raBOZfNzDSiZs/LTzzyVaa7g==",
       "cpu": [
         "arm64"
       ],
@@ -343,9 +343,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.18.0.tgz",
-      "integrity": "sha512-la0eauU0rzHO5eeVjBt8o/5UW4VzRYAuRA7nqUFLX5T6SWP5+UWjqusVVbWGz3ski+8uEX6VhlaFZP5uIJKGIg==",
+      "integrity": "sha512-S4skQ1RXXQJciq40s84Kyy7v3YC+nao8pX4xUyxDcKRx+90Qg9eH+tehs6XLN1IjrQT/9CWKaE5wxZmv6Oys4g==",
       "cpu": [
         "x64"
       ],
@@ -356,9 +356,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.18.0.tgz",
-      "integrity": "sha512-AkXI/lB3yu1Di2G1lhilf89V6qPTppb13aAt+/6gU5/PSfA94y9VXD67D4WyvRbuQghJjDvAavMlWMrJc2NuMw==",
+      "integrity": "sha512-1txr4tasVdxy321/4Fw8GJPjzrf84F02L9ffN8JebHmmR0S8uk2MKf2WsyLaSVRPd4YHIvvf3qmG0RGaUsb2sw==",
       "cpu": [
         "arm64"
       ],
@@ -369,9 +369,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-musl": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-musl/-/vectordb-linux-arm64-musl-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-musl/-/vectordb-linux-arm64-musl-0.18.0.tgz",
-      "integrity": "sha512-kTVcJ4LA8w/7egY4m0EXOt8c1DeFUquVtyvexO+VzIFeeHfBkkrMI0DkE0CpHmk+gctkG7EY39jzjgLnPvppnw==",
+      "integrity": "sha512-8xS1xaoJeFDx6WmDBcfueWvIbdNX/ptQXfoC7hYICwNHizjlyt4O3Nxz8uG9URMF1y9saUYUditIHLzLVZc76g==",
       "cpu": [
         "arm64"
       ],
@@ -382,9 +382,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.18.0.tgz",
-      "integrity": "sha512-KbtIy5DkaWTsKENm5Q27hjovrR7FRuoHhl0wDJtO/2CUZYlrskjEIfcfkfA2CrEQesBug4s5jgsvNM4Wcp6zoA==",
+      "integrity": "sha512-8XUc2UnEV3awv0DGJS5gRA7yTkicX6oPN7GudXXxycCKL33FJ2ah7hkeDia9Bhk9MmvTonvsEDvUSqnglcpqfA==",
       "cpu": [
         "x64"
       ],
@@ -395,9 +395,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-musl": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-musl/-/vectordb-linux-x64-musl-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-musl/-/vectordb-linux-x64-musl-0.18.0.tgz",
-      "integrity": "sha512-SF07gmoGVExcF5v+IE6kBbCbXJSDyTgC7QCt+MDS1NsgoQ9OH7IyH7r6HJu16tKflUOUKlUHnP0hQOPpv1fWpg==",
+      "integrity": "sha512-LV7TuWgLcL82Wdq+EH2Xs3+apqeLohwYLlVIauVAwKEHvdwyNxTOW9TaNLvHXcbylIh7agl2xXvASCNhYZAyzA==",
       "cpu": [
         "x64"
       ],
@@ -408,9 +408,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-arm64-msvc": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-arm64-msvc/-/vectordb-win32-arm64-msvc-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-arm64-msvc/-/vectordb-win32-arm64-msvc-0.18.0.tgz",
-      "integrity": "sha512-YYBuSBGDlxJgSI5gHjDmQo9sl05lAXfzil6QiKfgmUMsBtb2sT+GoUCgG6qzsfe99sWiTf+pMeWDsQgfrj9vNw==",
+      "integrity": "sha512-kxdCnKfvnuDKoKZRUBbreMBpimHb+k9/pFR48GN6JSrIuzUDx5G1VjHKBmaFhbveZCOBjjtYlg/8ohnWQHZfeA==",
       "cpu": [
         "arm64"
       ],
@@ -421,9 +421,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.18.0-beta.0.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.18.0.tgz",
-      "integrity": "sha512-t9TXeUnMU7YbP+/nUJpStm75aWwUydZj2AK+G2XwDtQrQo4Xg7/NETEbBeogmIOHuidNQYia8jEeQCUon5/+Dw==",
+      "integrity": "sha512-uAE80q50cAp4gHoGvclxJqZGqj3/9oN9kz8iXgNIxiPngqnN01kVyaj4ulm4Qk/nauWUhHJ3tjTh/+CpkhSc2Q==",
       "cpu": [
         "x64"
       ],

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.18.0-beta.0",
+  "version": "0.18.0",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -92,13 +92,13 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.18.0-beta.0",
+    "@lancedb/vectordb-darwin-x64": "0.18.0",
-    "@lancedb/vectordb-darwin-arm64": "0.18.0-beta.0",
+    "@lancedb/vectordb-darwin-arm64": "0.18.0",
-    "@lancedb/vectordb-linux-x64-gnu": "0.18.0-beta.0",
+    "@lancedb/vectordb-linux-x64-gnu": "0.18.0",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.18.0-beta.0",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.18.0",
-    "@lancedb/vectordb-linux-x64-musl": "0.18.0-beta.0",
+    "@lancedb/vectordb-linux-x64-musl": "0.18.0",
-    "@lancedb/vectordb-linux-arm64-musl": "0.18.0-beta.0",
+    "@lancedb/vectordb-linux-arm64-musl": "0.18.0",
-    "@lancedb/vectordb-win32-x64-msvc": "0.18.0-beta.0",
+    "@lancedb/vectordb-win32-x64-msvc": "0.18.0",
-    "@lancedb/vectordb-win32-arm64-msvc": "0.18.0-beta.0"
+    "@lancedb/vectordb-win32-arm64-msvc": "0.18.0"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.18.0-beta.0"
+version = "0.18.0"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/__test__/s3_integration.test.ts

@@ -175,6 +175,8 @@ maybeDescribe("storage_options", () => {
 
     tableNames = await db.tableNames();
     expect(tableNames).toEqual([]);
+
+    await db.dropAllTables();
   });
 
   it("can configure encryption at connection and table level", async () => {
@@ -210,6 +212,8 @@ maybeDescribe("storage_options", () => {
     await table.add([{ a: 2, b: 3 }]);
 
     await bucket.assertAllEncrypted("test/table2.lance", kmsKey.keyId);
+
+    await db.dropAllTables();
   });
 });
 
@@ -298,5 +302,32 @@ maybeDescribe("DynamoDB Lock", () => {
 
     const rowCount = await table.countRows();
     expect(rowCount).toBe(6);
+
+    await db.dropAllTables();
+  });
+
+  it("clears dynamodb state after dropping all tables", async () => {
+    const uri = `s3+ddb://${bucket.name}/test?ddbTableName=${commitTable.name}`;
+    const db = await connect(uri, {
+      storageOptions: CONFIG,
+      readConsistencyInterval: 0,
+    });
+
+    await db.createTable("foo", [{ a: 1, b: 2 }]);
+    await db.createTable("bar", [{ a: 1, b: 2 }]);
+
+    let tableNames = await db.tableNames();
+    expect(tableNames).toEqual(["bar", "foo"]);
+
+    await db.dropAllTables();
+    tableNames = await db.tableNames();
+    expect(tableNames).toEqual([]);
+
+    // We can create a new table with the same name as the one we dropped.
+    await db.createTable("foo", [{ a: 1, b: 2 }]);
+    tableNames = await db.tableNames();
+    expect(tableNames).toEqual(["foo"]);
+
+    await db.dropAllTables();
   });
 });

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

nodejs/npm/linux-x64-gnu/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

nodejs/npm/linux-x64-musl/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

nodejs/npm/win32-arm64-msvc/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.18.0-beta.0",
+  "version": "0.18.0",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.18.0-beta.0",
+	"version": "0.18.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.18.0-beta.0",
+  "version": "0.18.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.18.0-beta.0",
+      "version": "0.18.0",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.18.0-beta.0",
+  "version": "0.18.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

pyright_report.csv

@@ -0,0 +1,56 @@
+file,errors,warnings,total_issues
+python/python/lancedb/arrow.py,0,0,0
+python/python/lancedb/background_loop.py,0,0,0
+python/python/lancedb/embeddings/__init__.py,0,0,0
+python/python/lancedb/exceptions.py,0,0,0
+python/python/lancedb/index.py,0,0,0
+python/python/lancedb/integrations/__init__.py,0,0,0
+python/python/lancedb/remote/__init__.py,0,0,0
+python/python/lancedb/remote/errors.py,0,0,0
+python/python/lancedb/rerankers/__init__.py,0,0,0
+python/python/lancedb/rerankers/answerdotai.py,0,0,0
+python/python/lancedb/rerankers/cohere.py,0,0,0
+python/python/lancedb/rerankers/colbert.py,0,0,0
+python/python/lancedb/rerankers/cross_encoder.py,0,0,0
+python/python/lancedb/rerankers/openai.py,0,0,0
+python/python/lancedb/rerankers/util.py,0,0,0
+python/python/lancedb/rerankers/voyageai.py,0,0,0
+python/python/lancedb/schema.py,0,0,0
+python/python/lancedb/types.py,0,0,0
+python/python/lancedb/__init__.py,0,1,1
+python/python/lancedb/conftest.py,1,0,1
+python/python/lancedb/embeddings/bedrock.py,1,0,1
+python/python/lancedb/merge.py,1,0,1
+python/python/lancedb/rerankers/base.py,1,0,1
+python/python/lancedb/rerankers/jinaai.py,0,1,1
+python/python/lancedb/rerankers/linear_combination.py,1,0,1
+python/python/lancedb/embeddings/instructor.py,2,0,2
+python/python/lancedb/embeddings/openai.py,2,0,2
+python/python/lancedb/embeddings/watsonx.py,2,0,2
+python/python/lancedb/embeddings/registry.py,3,0,3
+python/python/lancedb/embeddings/sentence_transformers.py,3,0,3
+python/python/lancedb/integrations/pyarrow.py,3,0,3
+python/python/lancedb/rerankers/rrf.py,3,0,3
+python/python/lancedb/dependencies.py,4,0,4
+python/python/lancedb/embeddings/gemini_text.py,4,0,4
+python/python/lancedb/embeddings/gte.py,4,0,4
+python/python/lancedb/embeddings/gte_mlx_model.py,4,0,4
+python/python/lancedb/embeddings/ollama.py,4,0,4
+python/python/lancedb/embeddings/transformers.py,4,0,4
+python/python/lancedb/remote/db.py,5,0,5
+python/python/lancedb/context.py,6,0,6
+python/python/lancedb/embeddings/cohere.py,6,0,6
+python/python/lancedb/fts.py,6,0,6
+python/python/lancedb/db.py,9,0,9
+python/python/lancedb/embeddings/utils.py,9,0,9
+python/python/lancedb/common.py,11,0,11
+python/python/lancedb/util.py,13,0,13
+python/python/lancedb/embeddings/imagebind.py,14,0,14
+python/python/lancedb/embeddings/voyageai.py,15,0,15
+python/python/lancedb/embeddings/open_clip.py,16,0,16
+python/python/lancedb/pydantic.py,16,0,16
+python/python/lancedb/embeddings/base.py,17,0,17
+python/python/lancedb/embeddings/jinaai.py,18,1,19
+python/python/lancedb/remote/table.py,23,0,23
+python/python/lancedb/query.py,47,1,48
+python/python/lancedb/table.py,61,0,61

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.21.0-beta.1"
+current_version = "0.21.1"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/CONTRIBUTING.md

@@ -8,9 +8,9 @@ For general contribution guidelines, see [CONTRIBUTING.md](../CONTRIBUTING.md).
 The Python package is a wrapper around the Rust library, `lancedb`. We use
 [pyo3](https://pyo3.rs/) to create the bindings between Rust and Python.
 
-* `src/`: Rust bindings source code
+- `src/`: Rust bindings source code
-* `python/lancedb`: Python package source code
+- `python/lancedb`: Python package source code
-* `python/tests`: Unit tests
+- `python/tests`: Unit tests
 
 ## Development environment
 
@@ -61,6 +61,12 @@ make test
 make doctest
 ```
 
+Run type checking:
+
+```shell
+make typecheck
+```
+
 To run a single test, you can use the `pytest` command directly. Provide the path
 to the test file, and optionally the test name after `::`.
 

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.21.0-beta.1"
+version = "0.21.1"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true
@@ -14,21 +14,20 @@ name = "_lancedb"
 crate-type = ["cdylib"]
 
 [dependencies]
-arrow = { version = "53.2", features = ["pyarrow"] }
+arrow = { version = "54.1", features = ["pyarrow"] }
 lancedb = { path = "../rust/lancedb", default-features = false }
 env_logger.workspace = true
-pyo3 = { version = "0.22.2", features = [
+pyo3 = { version = "0.23", features = ["extension-module", "abi3-py39"] }
-    "extension-module",
+pyo3-async-runtimes = { version = "0.23", features = [
-    "abi3-py39",
+    "attributes",
-    "gil-refs"
+    "tokio-runtime",
 ] }
-pyo3-async-runtimes = { version = "0.22", features = ["attributes", "tokio-runtime"] }
 pin-project = "1.1.5"
 futures.workspace = true
 tokio = { version = "1.40", features = ["sync"] }
 
 [build-dependencies]
-pyo3-build-config = { version = "0.20.3", features = [
+pyo3-build-config = { version = "0.23", features = [
     "extension-module",
     "abi3-py39",
 ] }

python/Makefile

@@ -23,6 +23,10 @@ check:		## Check formatting and lints.
 fix:		## Fix python lints
 	ruff check python --fix
 
+.PHONY: typecheck
+typecheck:	## Run type checking with pyright.
+	pyright
+
 .PHONY: doctest
 doctest:	## Run documentation tests.
 	pytest --doctest-modules python/lancedb
@@ -30,3 +34,7 @@ doctest:	## Run documentation tests.
 .PHONY: test
 test:		## Run tests.
 	pytest python/tests -vv --durations=10 -m "not slow and not s3_test"
+
+.PHONY: clean
+clean:
+	rm -rf data

python/pyproject.toml

@@ -9,6 +9,7 @@ dependencies = [
     "pydantic>=1.10",
     "packaging",
     "overrides>=0.7",
+    "pylance>=0.23.2",
 ]
 description = "lancedb"
 authors = [{ name = "LanceDB Devs", email = "dev@lancedb.com" }]
@@ -54,7 +55,6 @@ tests = [
     "polars>=0.19, <=1.3.0",
     "tantivy",
     "pyarrow-stubs",
-    "pylance~=0.23.2",
 ]
 dev = [
     "ruff",
@@ -92,7 +92,7 @@ requires = ["maturin>=1.4"]
 build-backend = "maturin"
 
 [tool.ruff.lint]
-select = ["F", "E", "W", "G", "TCH", "PERF"]
+select = ["F", "E", "W", "G", "PERF"]
 
 [tool.pytest.ini_options]
 addopts = "--strict-markers --ignore-glob=lancedb/embeddings/*.py"
@@ -103,5 +103,28 @@ markers = [
 ]
 
 [tool.pyright]
-include = ["python/lancedb/table.py"]
+include = [
+    "python/lancedb/index.py",
+    "python/lancedb/rerankers/util.py",
+    "python/lancedb/rerankers/__init__.py",
+    "python/lancedb/rerankers/voyageai.py",
+    "python/lancedb/rerankers/jinaai.py",
+    "python/lancedb/rerankers/openai.py",
+    "python/lancedb/rerankers/cross_encoder.py",
+    "python/lancedb/rerankers/colbert.py",
+    "python/lancedb/rerankers/answerdotai.py",
+    "python/lancedb/rerankers/cohere.py",
+    "python/lancedb/arrow.py",
+    "python/lancedb/__init__.py",
+    "python/lancedb/types.py",
+    "python/lancedb/integrations/__init__.py",
+    "python/lancedb/exceptions.py",
+    "python/lancedb/background_loop.py",
+    "python/lancedb/schema.py",
+    "python/lancedb/remote/__init__.py",
+    "python/lancedb/remote/errors.py",
+    "python/lancedb/embeddings/__init__.py",
+    "python/lancedb/_lancedb.pyi",
+]
+exclude = ["python/tests/"]
 pythonVersion = "3.12"

python/python/lancedb/__init__.py

@@ -14,6 +14,7 @@ from ._lancedb import connect as lancedb_connect
 from .common import URI, sanitize_uri
 from .db import AsyncConnection, DBConnection, LanceDBConnection
 from .remote import ClientConfig
+from .remote.db import RemoteDBConnection
 from .schema import vector
 from .table import AsyncTable
 
@@ -86,8 +87,6 @@ def connect(
     conn : DBConnection
         A connection to a LanceDB database.
     """
-    from .remote.db import RemoteDBConnection
-
     if isinstance(uri, str) and uri.startswith("db://"):
         if api_key is None:
             api_key = os.environ.get("LANCEDB_API_KEY")

python/python/lancedb/_lancedb.pyi

@@ -3,6 +3,7 @@ from typing import Dict, List, Optional, Tuple, Any, Union, Literal
 import pyarrow as pa
 
 from .index import BTree, IvfFlat, IvfPq, Bitmap, LabelList, HnswPq, HnswSq, FTS
+from .remote import ClientConfig
 
 class Connection(object):
     uri: str
@@ -71,11 +72,15 @@ async def connect(
     region: Optional[str],
     host_override: Optional[str],
     read_consistency_interval: Optional[float],
+    client_config: Optional[Union[ClientConfig, Dict[str, Any]]],
+    storage_options: Optional[Dict[str, str]],
 ) -> Connection: ...
 
 class RecordBatchStream:
+    @property
     def schema(self) -> pa.Schema: ...
-    async def next(self) -> Optional[pa.RecordBatch]: ...
+    def __aiter__(self) -> "RecordBatchStream": ...
+    async def __anext__(self) -> pa.RecordBatch: ...
 
 class Query:
     def where(self, filter: str): ...

python/python/lancedb/remote/db.py

@@ -9,7 +9,8 @@ from typing import Any, Dict, Iterable, List, Optional, Union
 from urllib.parse import urlparse
 import warnings
 
-from lancedb import connect_async
+# Remove this import to fix circular dependency
+# from lancedb import connect_async
 from lancedb.remote import ClientConfig
 import pyarrow as pa
 from overrides import override
@@ -78,6 +79,9 @@ class RemoteDBConnection(DBConnection):
 
         self.client_config = client_config
 
+        # Import connect_async here to avoid circular import
+        from lancedb import connect_async
+
         self._conn = LOOP.run(
             connect_async(
                 db_url,

python/python/lancedb/table.py

@@ -76,12 +76,21 @@ if TYPE_CHECKING:
     from .index import IndexConfig
     import pandas
     import PIL
+    from .types import (
+        QueryType,
+        OnBadVectorsType,
+        AddMode,
+        CreateMode,
+        VectorIndexType,
+        ScalarIndexType,
+        BaseTokenizerType,
+        DistanceType,
+    )
+
 
 pd = safe_import_pandas()
 pl = safe_import_polars()
 
-QueryType = Literal["vector", "fts", "hybrid", "auto"]
-
 
 def _into_pyarrow_reader(data) -> pa.RecordBatchReader:
     from lancedb.dependencies import datasets
@@ -178,7 +187,7 @@ def _sanitize_data(
     data: "DATA",
     target_schema: Optional[pa.Schema] = None,
     metadata: Optional[dict] = None,  # embedding metadata
-    on_bad_vectors: Literal["error", "drop", "fill", "null"] = "error",
+    on_bad_vectors: OnBadVectorsType = "error",
     fill_value: float = 0.0,
     *,
     allow_subschema: bool = False,
@@ -324,7 +333,7 @@ def sanitize_create_table(
     data,
     schema: Union[pa.Schema, LanceModel],
     metadata=None,
-    on_bad_vectors: str = "error",
+    on_bad_vectors: OnBadVectorsType = "error",
     fill_value: float = 0.0,
 ):
     if inspect.isclass(schema) and issubclass(schema, LanceModel):
@@ -576,9 +585,7 @@ class Table(ABC):
         accelerator: Optional[str] = None,
         index_cache_size: Optional[int] = None,
         *,
-        index_type: Literal[
+        index_type: VectorIndexType = "IVF_PQ",
-            "IVF_FLAT", "IVF_PQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"
-        ] = "IVF_PQ",
         num_bits: int = 8,
         max_iterations: int = 50,
         sample_rate: int = 256,
@@ -643,7 +650,7 @@ class Table(ABC):
         column: str,
         *,
         replace: bool = True,
-        index_type: Literal["BTREE", "BITMAP", "LABEL_LIST"] = "BTREE",
+        index_type: ScalarIndexType = "BTREE",
     ):
         """Create a scalar index on a column.
 
@@ -708,7 +715,7 @@ class Table(ABC):
         tokenizer_name: Optional[str] = None,
         with_position: bool = True,
         # tokenizer configs:
-        base_tokenizer: Literal["simple", "raw", "whitespace"] = "simple",
+        base_tokenizer: BaseTokenizerType = "simple",
         language: str = "English",
         max_token_length: Optional[int] = 40,
         lower_case: bool = True,
@@ -777,8 +784,8 @@ class Table(ABC):
     def add(
         self,
         data: DATA,
-        mode: str = "append",
+        mode: AddMode = "append",
-        on_bad_vectors: str = "error",
+        on_bad_vectors: OnBadVectorsType = "error",
         fill_value: float = 0.0,
     ):
         """Add more data to the [Table](Table).
@@ -960,7 +967,7 @@ class Table(ABC):
         self,
         merge: LanceMergeInsertBuilder,
         new_data: DATA,
-        on_bad_vectors: str,
+        on_bad_vectors: OnBadVectorsType,
         fill_value: float,
     ): ...
 
@@ -1572,10 +1579,10 @@ class LanceTable(Table):
 
     def create_index(
         self,
-        metric="L2",
+        metric: DistanceType = "l2",
         num_partitions=None,
         num_sub_vectors=None,
-        vector_column_name=VECTOR_COLUMN_NAME,
+        vector_column_name: str = VECTOR_COLUMN_NAME,
         replace: bool = True,
         accelerator: Optional[str] = None,
         index_cache_size: Optional[int] = None,
@@ -1661,7 +1668,7 @@ class LanceTable(Table):
         column: str,
         *,
         replace: bool = True,
-        index_type: Literal["BTREE", "BITMAP", "LABEL_LIST"] = "BTREE",
+        index_type: ScalarIndexType = "BTREE",
     ):
         if index_type == "BTREE":
             config = BTree()
@@ -1686,7 +1693,7 @@ class LanceTable(Table):
         tokenizer_name: Optional[str] = None,
         with_position: bool = True,
         # tokenizer configs:
-        base_tokenizer: str = "simple",
+        base_tokenizer: BaseTokenizerType = "simple",
         language: str = "English",
         max_token_length: Optional[int] = 40,
         lower_case: bool = True,
@@ -1820,8 +1827,8 @@ class LanceTable(Table):
     def add(
         self,
         data: DATA,
-        mode: str = "append",
+        mode: AddMode = "append",
-        on_bad_vectors: str = "error",
+        on_bad_vectors: OnBadVectorsType = "error",
         fill_value: float = 0.0,
     ):
         """Add data to the table.
@@ -2059,7 +2066,7 @@ class LanceTable(Table):
             query_type,
             vector_column_name=vector_column_name,
             ordering_field_name=ordering_field_name,
-            fts_columns=fts_columns,
+            fts_columns=fts_columns or [],
         )
 
     @classmethod
@@ -2069,13 +2076,13 @@ class LanceTable(Table):
         name: str,
         data: Optional[DATA] = None,
         schema: Optional[pa.Schema] = None,
-        mode: Literal["create", "overwrite"] = "create",
+        mode: CreateMode = "create",
         exist_ok: bool = False,
-        on_bad_vectors: str = "error",
+        on_bad_vectors: OnBadVectorsType = "error",
         fill_value: float = 0.0,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         *,
-        storage_options: Optional[Dict[str, str]] = None,
+        storage_options: Optional[Dict[str, str | bool]] = None,
         data_storage_version: Optional[str] = None,
         enable_v2_manifest_paths: Optional[bool] = None,
     ):
@@ -2229,7 +2236,7 @@ class LanceTable(Table):
         self,
         merge: LanceMergeInsertBuilder,
         new_data: DATA,
-        on_bad_vectors: str,
+        on_bad_vectors: OnBadVectorsType,
         fill_value: float,
     ):
         LOOP.run(self._table._do_merge(merge, new_data, on_bad_vectors, fill_value))
@@ -2880,7 +2887,7 @@ class AsyncTable:
         data: DATA,
         *,
         mode: Optional[Literal["append", "overwrite"]] = "append",
-        on_bad_vectors: Optional[str] = None,
+        on_bad_vectors: Optional[OnBadVectorsType] = None,
         fill_value: Optional[float] = None,
     ):
         """Add more data to the [Table](Table).
@@ -2986,7 +2993,7 @@ class AsyncTable:
     @overload
     async def search(
         self,
-        query: Optional[Union[str]] = None,
+        query: Optional[str] = None,
         vector_column_name: Optional[str] = None,
         query_type: Literal["auto"] = ...,
         ordering_field_name: Optional[str] = None,
@@ -2996,7 +3003,7 @@ class AsyncTable:
     @overload
     async def search(
         self,
-        query: Optional[Union[str]] = None,
+        query: Optional[str] = None,
         vector_column_name: Optional[str] = None,
         query_type: Literal["hybrid"] = ...,
         ordering_field_name: Optional[str] = None,
@@ -3040,7 +3047,7 @@ class AsyncTable:
         query_type: QueryType = "auto",
         ordering_field_name: Optional[str] = None,
         fts_columns: Optional[Union[str, List[str]]] = None,
-    ) -> AsyncQuery:
+    ) -> Union[AsyncHybridQuery | AsyncFTSQuery | AsyncVectorQuery]:
         """Create a search query to find the nearest neighbors
         of the given query vector. We currently support [vector search][search]
         and [full-text search][experimental-full-text-search].
@@ -3279,7 +3286,7 @@ class AsyncTable:
         self,
         merge: LanceMergeInsertBuilder,
         new_data: DATA,
-        on_bad_vectors: str,
+        on_bad_vectors: OnBadVectorsType,
         fill_value: float,
     ):
         schema = await self.schema()

python/python/lancedb/types.py

@@ -0,0 +1,28 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright The LanceDB Authors
+
+from typing import Literal
+
+# Query type literals
+QueryType = Literal["vector", "fts", "hybrid", "auto"]
+
+# Distance type literals
+DistanceType = Literal["l2", "cosine", "dot"]
+DistanceTypeWithHamming = Literal["l2", "cosine", "dot", "hamming"]
+
+# Vector handling literals
+OnBadVectorsType = Literal["error", "drop", "fill", "null"]
+
+# Mode literals
+AddMode = Literal["append", "overwrite"]
+CreateMode = Literal["create", "overwrite"]
+
+# Index type literals
+VectorIndexType = Literal["IVF_FLAT", "IVF_PQ", "IVF_HNSW_SQ", "IVF_HNSW_PQ"]
+ScalarIndexType = Literal["BTREE", "BITMAP", "LABEL_LIST"]
+IndexType = Literal[
+    "IVF_PQ", "IVF_HNSW_PQ", "IVF_HNSW_SQ", "FTS", "BTREE", "BITMAP", "LABEL_LIST"
+]
+
+# Tokenizer literals
+BaseTokenizerType = Literal["simple", "raw", "whitespace"]

python/python/tests/test_embeddings.py

@@ -419,17 +419,17 @@ def test_embedding_function_safe_model_dump(embedding_type):
 
     dumped_model = model.safe_model_dump()
 
-    assert all(
+    assert all(not k.startswith("_") for k in dumped_model.keys()), (
-        not k.startswith("_") for k in dumped_model.keys()
+        f"{embedding_type}: Dumped model contains keys starting with underscore"
-    ), f"{embedding_type}: Dumped model contains keys starting with underscore"
+    )
 
-    assert (
+    assert "max_retries" in dumped_model, (
-        "max_retries" in dumped_model
+        f"{embedding_type}: Essential field 'max_retries' is missing from dumped model"
-    ), f"{embedding_type}: Essential field 'max_retries' is missing from dumped model"
+    )
 
-    assert isinstance(
+    assert isinstance(dumped_model, dict), (
-        dumped_model, dict
+        f"{embedding_type}: Dumped model is not a dictionary"
-    ), f"{embedding_type}: Dumped model is not a dictionary"
+    )
 
     for key in model.__dict__:
         if key.startswith("_"):

python/python/tests/test_hybrid_query.py

@@ -129,6 +129,6 @@ def test_normalize_scores():
             if invert:
                 expected = pc.subtract(1.0, expected)
 
-            assert pc.equal(
+            assert pc.equal(result, expected), (
-                result, expected
+                f"Expected {expected} but got {result} for invert={invert}"
-            ), f"Expected {expected} but got {result} for invert={invert}"
+            )

python/python/tests/test_query.py

@@ -784,8 +784,7 @@ async def test_query_search_auto(mem_db_async: AsyncConnection):
     with pytest.raises(
         Exception,
         match=(
-            "Cannot perform full text search unless an INVERTED index has "
+            "Cannot perform full text search unless an INVERTED index has been created"
-            "been created"
         ),
     ):
         query = await (await tbl2.search("0.1")).to_arrow()

python/python/tests/test_rerankers.py

@@ -131,9 +131,9 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
         "represents the relevance of the result to the query & should "
         "be descending."
     )
-    assert np.all(
+    assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-        np.diff(result.column("_relevance_score").to_numpy()) <= 0
+        ascending_relevance_err
-    ), ascending_relevance_err
+    )
 
     # Vector search setting
     result = (
@@ -143,9 +143,9 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
         .to_arrow()
     )
     assert len(result) == 30
-    assert np.all(
+    assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-        np.diff(result.column("_relevance_score").to_numpy()) <= 0
+        ascending_relevance_err
-    ), ascending_relevance_err
+    )
     result_explicit = (
         table.search(query_vector, vector_column_name="vector")
         .rerank(reranker=reranker, query_string=query)
@@ -168,9 +168,9 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
         .to_arrow()
     )
     assert len(result) > 0
-    assert np.all(
+    assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-        np.diff(result.column("_relevance_score").to_numpy()) <= 0
+        ascending_relevance_err
-    ), ascending_relevance_err
+    )
 
     # empty FTS results
     query = "abcxyz" * 100
@@ -185,9 +185,9 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
 
     # should return _relevance_score column
     assert "_relevance_score" in result.column_names
-    assert np.all(
+    assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-        np.diff(result.column("_relevance_score").to_numpy()) <= 0
+        ascending_relevance_err
-    ), ascending_relevance_err
+    )
 
     # Multi-vector search setting
     rs1 = table.search(query, vector_column_name="vector").limit(10).with_row_id(True)
@@ -262,9 +262,9 @@ def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
         "represents the relevance of the result to the query & should "
         "be descending."
     )
-    assert np.all(
+    assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-        np.diff(result.column("_relevance_score").to_numpy()) <= 0
+        ascending_relevance_err
-    ), ascending_relevance_err
+    )
 
     # Test with empty FTS results
     query = "abcxyz" * 100
@@ -278,9 +278,9 @@ def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
     )
     # should return _relevance_score column
     assert "_relevance_score" in result.column_names
-    assert np.all(
+    assert np.all(np.diff(result.column("_relevance_score").to_numpy()) <= 0), (
-        np.diff(result.column("_relevance_score").to_numpy()) <= 0
+        ascending_relevance_err
-    ), ascending_relevance_err
+    )
 
 
 @pytest.mark.parametrize("use_tantivy", [True, False])

python/python/tests/test_s3.py

@@ -252,3 +252,27 @@ def test_s3_dynamodb_sync(s3_bucket: str, commit_table: str, monkeypatch):
     db.drop_table("test_ddb_sync")
     assert db.table_names() == []
     db.drop_database()
+
+
+@pytest.mark.s3_test
+def test_s3_dynamodb_drop_all_tables(s3_bucket: str, commit_table: str, monkeypatch):
+    for key, value in CONFIG.items():
+        monkeypatch.setenv(key.upper(), value)
+
+    uri = f"s3+ddb://{s3_bucket}/test2?ddbTableName={commit_table}"
+    db = lancedb.connect(uri, read_consistency_interval=timedelta(0))
+    data = pa.table({"x": ["a", "b", "c"]})
+
+    db.create_table("foo", data)
+    db.create_table("bar", data)
+    assert db.table_names() == ["bar", "foo"]
+
+    # dropping all tables should clear multiple tables
+    db.drop_all_tables()
+    assert db.table_names() == []
+
+    # create a new table with the same name to ensure DDB is clean
+    db.create_table("foo", data)
+    assert db.table_names() == ["foo"]
+
+    db.drop_all_tables()

python/src/error.rs

@@ -43,7 +43,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                 } => Python::with_gil(|py| {
                     let message = err.to_string();
                     let http_err_cls = py
-                        .import_bound(intern!(py, "lancedb.remote.errors"))?
+                        .import(intern!(py, "lancedb.remote.errors"))?
                         .getattr(intern!(py, "HttpError"))?;
                     let err = http_err_cls.call1((
                         message,
@@ -63,7 +63,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                         err.setattr(intern!(py, "__cause__"), cause_err)?;
                     }
 
-                    Err(PyErr::from_value_bound(err))
+                    Err(PyErr::from_value(err))
                 }),
                 LanceError::Retry {
                     request_id,
@@ -85,7 +85,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
 
                     let message = err.to_string();
                     let retry_error_cls = py
-                        .import_bound(intern!(py, "lancedb.remote.errors"))?
+                        .import(intern!(py, "lancedb.remote.errors"))?
                         .getattr("RetryError")?;
                     let err = retry_error_cls.call1((
                         message,
@@ -100,7 +100,7 @@ impl<T> PythonErrorExt<T> for std::result::Result<T, LanceError> {
                     ))?;
 
                     err.setattr(intern!(py, "__cause__"), cause_err)?;
-                    Err(PyErr::from_value_bound(err))
+                    Err(PyErr::from_value(err))
                 }),
                 _ => self.runtime_error(),
             },
@@ -127,18 +127,16 @@ fn http_from_rust_error(
     status_code: Option<u16>,
 ) -> PyResult<PyErr> {
     let message = err.to_string();
-    let http_err_cls = py
+    let http_err_cls = py.import("lancedb.remote.errors")?.getattr("HttpError")?;
-        .import_bound("lancedb.remote.errors")?
-        .getattr("HttpError")?;
     let py_err = http_err_cls.call1((message, request_id, status_code))?;
 
     // Reset the traceback since it doesn't provide additional information.
-    let py_err = py_err.call_method1(intern!(py, "with_traceback"), (PyNone::get_bound(py),))?;
+    let py_err = py_err.call_method1(intern!(py, "with_traceback"), (PyNone::get(py),))?;
 
     if let Some(cause) = err.source() {
         let cause_err = http_from_rust_error(py, cause, request_id, status_code)?;
         py_err.setattr(intern!(py, "__cause__"), cause_err)?;
     }
 
-    Ok(PyErr::from_value_bound(py_err))
+    Ok(PyErr::from_value(py_err))
 }

python/src/index.rs

@@ -7,29 +7,32 @@ use lancedb::index::{
     vector::{IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder, IvfPqIndexBuilder},
     Index as LanceDbIndex,
 };
+use pyo3::types::PyStringMethods;
+use pyo3::IntoPyObject;
 use pyo3::{
     exceptions::{PyKeyError, PyValueError},
     intern, pyclass, pymethods,
     types::PyAnyMethods,
-    Bound, FromPyObject, IntoPy, PyAny, PyObject, PyResult, Python,
+    Bound, FromPyObject, PyAny, PyResult, Python,
 };
 
 use crate::util::parse_distance_type;
 
-pub fn class_name<'a>(ob: &'a Bound<'_, PyAny>) -> PyResult<&'a str> {
+pub fn class_name(ob: &'_ Bound<'_, PyAny>) -> PyResult<String> {
-    let full_name: &str = ob
+    let full_name = ob
         .getattr(intern!(ob.py(), "__class__"))?
-        .getattr(intern!(ob.py(), "__name__"))?
+        .getattr(intern!(ob.py(), "__name__"))?;
-        .extract()?;
+    let full_name = full_name.downcast()?.to_string_lossy();
+
     match full_name.rsplit_once('.') {
-        Some((_, name)) => Ok(name),
+        Some((_, name)) => Ok(name.to_string()),
-        None => Ok(full_name),
+        None => Ok(full_name.to_string()),
     }
 }
 
 pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<LanceDbIndex> {
     if let Some(source) = source {
-        match class_name(source)? {
+        match class_name(source)?.as_str() {
             "BTree" => Ok(LanceDbIndex::BTree(BTreeIndexBuilder::default())),
             "Bitmap" => Ok(LanceDbIndex::Bitmap(Default::default())),
             "LabelList" => Ok(LanceDbIndex::LabelList(Default::default())),
@@ -196,11 +199,11 @@ impl IndexConfig {
 
     // For backwards-compatibility with the old sync SDK, we also support getting
     // attributes via __getitem__.
-    pub fn __getitem__(&self, key: String, py: Python<'_>) -> PyResult<PyObject> {
+    pub fn __getitem__<'a>(&self, key: String, py: Python<'a>) -> PyResult<Bound<'a, PyAny>> {
         match key.as_str() {
-            "index_type" => Ok(self.index_type.clone().into_py(py)),
+            "index_type" => Ok(self.index_type.clone().into_pyobject(py)?.into_any()),
-            "columns" => Ok(self.columns.clone().into_py(py)),
+            "columns" => Ok(self.columns.clone().into_pyobject(py)?.into_any()),
-            "name" | "index_name" => Ok(self.name.clone().into_py(py)),
+            "name" | "index_name" => Ok(self.name.clone().into_pyobject(py)?.into_any()),
             _ => Err(PyKeyError::new_err(format!("Invalid key: {}", key))),
         }
     }

python/src/table.rs

@@ -13,7 +13,7 @@ use pyo3::{
     exceptions::{PyKeyError, PyRuntimeError, PyValueError},
     pyclass, pymethods,
     types::{IntoPyDict, PyAnyMethods, PyDict, PyDictMethods},
-    Bound, FromPyObject, PyAny, PyRef, PyResult, Python, ToPyObject,
+    Bound, FromPyObject, PyAny, PyRef, PyResult, Python,
 };
 use pyo3_async_runtimes::tokio::future_into_py;
 use std::collections::HashMap;
@@ -222,7 +222,7 @@ impl Table {
             let stats = inner.index_stats(&index_name).await.infer_error()?;
             if let Some(stats) = stats {
                 Python::with_gil(|py| {
-                    let dict = PyDict::new_bound(py);
+                    let dict = PyDict::new(py);
                     dict.set_item("num_indexed_rows", stats.num_indexed_rows)?;
                     dict.set_item("num_unindexed_rows", stats.num_unindexed_rows)?;
                     dict.set_item("index_type", stats.index_type.to_string())?;
@@ -235,7 +235,7 @@ impl Table {
                         dict.set_item("num_indices", num_indices)?;
                     }
 
-                    Ok(Some(dict.to_object(py)))
+                    Ok(Some(dict.unbind()))
                 })
             } else {
                 Ok(None)
@@ -266,7 +266,7 @@ impl Table {
                 versions
                     .iter()
                     .map(|v| {
-                        let dict = PyDict::new_bound(py);
+                        let dict = PyDict::new(py);
                         dict.set_item("version", v.version).unwrap();
                         dict.set_item(
                             "timestamp",
@@ -275,14 +275,13 @@ impl Table {
                         .unwrap();
 
                         let tup: Vec<(&String, &String)> = v.metadata.iter().collect();
-                        dict.set_item("metadata", tup.into_py_dict_bound(py))
+                        dict.set_item("metadata", tup.into_py_dict(py)?).unwrap();
-                            .unwrap();
+                        Ok(dict.unbind())
-                        dict.to_object(py)
                     })
-                    .collect::<Vec<_>>()
+                    .collect::<PyResult<Vec<_>>>()
             });
 
-            Ok(versions_as_dict)
+            versions_as_dict
         })
     }
 

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.18.0-beta.0"
+version = "0.18.0"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.18.0-beta.0"
+version = "0.18.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/arrow.rs

@@ -4,12 +4,14 @@
 use std::{pin::Pin, sync::Arc};
 
 pub use arrow_schema;
-use futures::{Stream, StreamExt};
+use datafusion_common::DataFusionError;
+use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
+use futures::{Stream, StreamExt, TryStreamExt};
 
 #[cfg(feature = "polars")]
 use {crate::polars_arrow_convertors, polars::frame::ArrowChunk, polars::prelude::DataFrame};
 
-use crate::error::Result;
+use crate::{error::Result, Error};
 
 /// An iterator of batches that also has a schema
 pub trait RecordBatchReader: Iterator<Item = Result<arrow_array::RecordBatch>> {
@@ -65,6 +67,20 @@ impl<I: lance::io::RecordBatchStream + 'static> From<I> for SendableRecordBatchS
     }
 }
 
+pub trait SendableRecordBatchStreamExt {
+    fn into_df_stream(self) -> datafusion_physical_plan::SendableRecordBatchStream;
+}
+
+impl SendableRecordBatchStreamExt for SendableRecordBatchStream {
+    fn into_df_stream(self) -> datafusion_physical_plan::SendableRecordBatchStream {
+        let schema = self.schema();
+        Box::pin(RecordBatchStreamAdapter::new(
+            schema,
+            self.map_err(|ldb_err| DataFusionError::External(ldb_err.into())),
+        ))
+    }
+}
+
 /// A simple RecordBatchStream formed from the two parts (stream + schema)
 #[pin_project::pin_project]
 pub struct SimpleRecordBatchStream<S: Stream<Item = Result<arrow_array::RecordBatch>>> {
@@ -101,7 +117,7 @@ impl<S: Stream<Item = Result<arrow_array::RecordBatch>>> RecordBatchStream
 /// used in methods like [`crate::connection::Connection::create_table`]
 /// or [`crate::table::Table::add`]
 pub trait IntoArrow {
-    /// Convert the data into an Arrow array
+    /// Convert the data into an iterator of Arrow batches
     fn into_arrow(self) -> Result<Box<dyn arrow_array::RecordBatchReader + Send>>;
 }
 
@@ -113,11 +129,38 @@ impl<T: arrow_array::RecordBatchReader + Send + 'static> IntoArrow for T {
     }
 }
 
+/// A trait for converting incoming data to Arrow asynchronously
+///
+/// Serves the same purpose as [`IntoArrow`], but for asynchronous data.
+///
+/// Note: Arrow has no async equivalent to RecordBatchReader and so
+pub trait IntoArrowStream {
+    /// Convert the data into a stream of Arrow batches
+    fn into_arrow(self) -> Result<SendableRecordBatchStream>;
+}
+
 impl<S: Stream<Item = Result<arrow_array::RecordBatch>>> SimpleRecordBatchStream<S> {
     pub fn new(stream: S, schema: Arc<arrow_schema::Schema>) -> Self {
         Self { schema, stream }
     }
 }
+
+impl IntoArrowStream for SendableRecordBatchStream {
+    fn into_arrow(self) -> Result<SendableRecordBatchStream> {
+        Ok(self)
+    }
+}
+
+impl IntoArrowStream for datafusion_physical_plan::SendableRecordBatchStream {
+    fn into_arrow(self) -> Result<SendableRecordBatchStream> {
+        let schema = self.schema();
+        let stream = self.map_err(|df_err| Error::Runtime {
+            message: df_err.to_string(),
+        });
+        Ok(Box::pin(SimpleRecordBatchStream::new(stream, schema)))
+    }
+}
+
 #[cfg(feature = "polars")]
 /// An iterator of record batches formed from a Polars DataFrame.
 pub struct PolarsDataFrameRecordBatchReader {

rust/lancedb/src/connection.rs

@@ -11,7 +11,7 @@ use arrow_schema::{Field, SchemaRef};
 use lance::dataset::ReadParams;
 use object_store::aws::AwsCredential;
 
-use crate::arrow::IntoArrow;
+use crate::arrow::{IntoArrow, IntoArrowStream, SendableRecordBatchStream};
 use crate::database::listing::{
     ListingDatabase, OPT_NEW_TABLE_STORAGE_VERSION, OPT_NEW_TABLE_V2_MANIFEST_PATHS,
 };
@@ -75,6 +75,14 @@ impl IntoArrow for NoData {
     }
 }
 
+// Stores the value given from the initial CreateTableBuilder::new call
+// and defers errors until `execute` is called
+enum CreateTableBuilderInitialData {
+    None,
+    Iterator(Result<Box<dyn RecordBatchReader + Send>>),
+    Stream(Result<SendableRecordBatchStream>),
+}
+
 /// A builder for configuring a [`Connection::create_table`] operation
 pub struct CreateTableBuilder<const HAS_DATA: bool> {
     parent: Arc<dyn Database>,
@@ -83,7 +91,7 @@ pub struct CreateTableBuilder<const HAS_DATA: bool> {
     request: CreateTableRequest,
     // This is a bit clumsy but we defer errors until `execute` is called
     // to maintain backwards compatibility
-    data: Option<Result<Box<dyn RecordBatchReader + Send>>>,
+    data: CreateTableBuilderInitialData,
 }
 
 // Builder methods that only apply when we have initial data
@@ -103,7 +111,26 @@ impl CreateTableBuilder<true> {
             ),
             embeddings: Vec::new(),
             embedding_registry,
-            data: Some(data.into_arrow()),
+            data: CreateTableBuilderInitialData::Iterator(data.into_arrow()),
+        }
+    }
+
+    fn new_streaming<T: IntoArrowStream>(
+        parent: Arc<dyn Database>,
+        name: String,
+        data: T,
+        embedding_registry: Arc<dyn EmbeddingRegistry>,
+    ) -> Self {
+        let dummy_schema = Arc::new(arrow_schema::Schema::new(Vec::<Field>::default()));
+        Self {
+            parent,
+            request: CreateTableRequest::new(
+                name,
+                CreateTableData::Empty(TableDefinition::new_from_schema(dummy_schema)),
+            ),
+            embeddings: Vec::new(),
+            embedding_registry,
+            data: CreateTableBuilderInitialData::Stream(data.into_arrow()),
         }
     }
 
@@ -125,18 +152,38 @@ impl CreateTableBuilder<true> {
     }
 
     fn into_request(self) -> Result<CreateTableRequest> {
-        let data = if self.embeddings.is_empty() {
+        if self.embeddings.is_empty() {
-            self.data.unwrap()?
+            match self.data {
-        } else {
+                CreateTableBuilderInitialData::Iterator(maybe_iter) => {
-            let data = self.data.unwrap()?;
+                    let data = maybe_iter?;
-            Box::new(WithEmbeddings::new(data, self.embeddings))
-        };
-        let req = self.request;
                     Ok(CreateTableRequest {
                         data: CreateTableData::Data(data),
-            ..req
+                        ..self.request
                     })
                 }
+                CreateTableBuilderInitialData::None => {
+                    unreachable!("No data provided for CreateTableBuilder<true>")
+                }
+                CreateTableBuilderInitialData::Stream(maybe_stream) => {
+                    let data = maybe_stream?;
+                    Ok(CreateTableRequest {
+                        data: CreateTableData::StreamingData(data),
+                        ..self.request
+                    })
+                }
+            }
+        } else {
+            let CreateTableBuilderInitialData::Iterator(maybe_iter) = self.data else {
+                return Err(Error::NotSupported { message: "Creating a table with embeddings is currently not support when the input is streaming".to_string() });
+            };
+            let data = maybe_iter?;
+            let data = Box::new(WithEmbeddings::new(data, self.embeddings));
+            Ok(CreateTableRequest {
+                data: CreateTableData::Data(data),
+                ..self.request
+            })
+        }
+    }
 }
 
 // Builder methods that only apply when we do not have initial data
@@ -151,7 +198,7 @@ impl CreateTableBuilder<false> {
         Self {
             parent,
             request: CreateTableRequest::new(name, CreateTableData::Empty(table_definition)),
-            data: None,
+            data: CreateTableBuilderInitialData::None,
             embeddings: Vec::default(),
             embedding_registry,
         }
@@ -432,7 +479,7 @@ impl Connection {
         TableNamesBuilder::new(self.internal.clone())
     }
 
-    /// Create a new table from data
+    /// Create a new table from an iterator of data
     ///
     /// # Parameters
     ///
@@ -451,6 +498,25 @@ impl Connection {
         )
     }
 
+    /// Create a new table from a stream of data
+    ///
+    /// # Parameters
+    ///
+    /// * `name` - The name of the table
+    /// * `initial_data` - The initial data to write to the table
+    pub fn create_table_streaming<T: IntoArrowStream>(
+        &self,
+        name: impl Into<String>,
+        initial_data: T,
+    ) -> CreateTableBuilder<true> {
+        CreateTableBuilder::<true>::new_streaming(
+            self.internal.clone(),
+            name.into(),
+            initial_data,
+            self.embedding_registry.clone(),
+        )
+    }
+
     /// Create an empty table with a given schema
     ///
     /// # Parameters
@@ -788,12 +854,16 @@ mod test_utils {
 mod tests {
     use std::fs::create_dir_all;
 
+    use arrow::compute::concat_batches;
     use arrow_array::RecordBatchReader;
     use arrow_schema::{DataType, Field, Schema};
-    use futures::TryStreamExt;
+    use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
+    use futures::{stream, TryStreamExt};
+    use lance::error::{ArrowResult, DataFusionResult};
     use lance_testing::datagen::{BatchGenerator, IncrementingInt32};
     use tempfile::tempdir;
 
+    use crate::arrow::SimpleRecordBatchStream;
     use crate::database::listing::{ListingDatabaseOptions, NewTableConfig};
     use crate::query::QueryBase;
     use crate::query::{ExecutableQuery, QueryExecutionOptions};
@@ -976,6 +1046,63 @@ mod tests {
         assert_eq!(batches.len(), 1);
     }
 
+    #[tokio::test]
+    async fn test_create_table_streaming() {
+        let tmp_dir = tempdir().unwrap();
+
+        let uri = tmp_dir.path().to_str().unwrap();
+        let db = connect(uri).execute().await.unwrap();
+
+        let batches = make_data().collect::<ArrowResult<Vec<_>>>().unwrap();
+
+        let schema = batches.first().unwrap().schema();
+        let one_batch = concat_batches(&schema, batches.iter()).unwrap();
+
+        let ldb_stream = stream::iter(batches.clone().into_iter().map(Result::Ok));
+        let ldb_stream: SendableRecordBatchStream =
+            Box::pin(SimpleRecordBatchStream::new(ldb_stream, schema.clone()));
+
+        let tbl1 = db
+            .create_table_streaming("one", ldb_stream)
+            .execute()
+            .await
+            .unwrap();
+
+        let df_stream = stream::iter(batches.into_iter().map(DataFusionResult::Ok));
+        let df_stream: datafusion_physical_plan::SendableRecordBatchStream =
+            Box::pin(RecordBatchStreamAdapter::new(schema.clone(), df_stream));
+
+        let tbl2 = db
+            .create_table_streaming("two", df_stream)
+            .execute()
+            .await
+            .unwrap();
+
+        let tbl1_data = tbl1
+            .query()
+            .execute()
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap();
+
+        let tbl1_data = concat_batches(&schema, tbl1_data.iter()).unwrap();
+        assert_eq!(tbl1_data, one_batch);
+
+        let tbl2_data = tbl2
+            .query()
+            .execute()
+            .await
+            .unwrap()
+            .try_collect::<Vec<_>>()
+            .await
+            .unwrap();
+
+        let tbl2_data = concat_batches(&schema, tbl2_data.iter()).unwrap();
+        assert_eq!(tbl2_data, one_batch);
+    }
+
     #[tokio::test]
     async fn drop_table() {
         let tmp_dir = tempdir().unwrap();

rust/lancedb/src/database.rs

@@ -18,8 +18,13 @@ use std::collections::HashMap;
 use std::sync::Arc;
 
 use arrow_array::RecordBatchReader;
+use async_trait::async_trait;
+use datafusion_physical_plan::stream::RecordBatchStreamAdapter;
+use futures::stream;
 use lance::dataset::ReadParams;
+use lance_datafusion::utils::StreamingWriteSource;
 
+use crate::arrow::{SendableRecordBatchStream, SendableRecordBatchStreamExt};
 use crate::error::Result;
 use crate::table::{BaseTable, TableDefinition, WriteOptions};
 
@@ -81,12 +86,41 @@ impl Default for CreateTableMode {
 
 /// The data to start a table or a schema to create an empty table
 pub enum CreateTableData {
-    /// Creates a table using data, no schema required as it will be obtained from the data
+    /// Creates a table using an iterator of data, the schema will be obtained from the data
     Data(Box<dyn RecordBatchReader + Send>),
+    /// Creates a table using a stream of data, the schema will be obtained from the data
+    StreamingData(SendableRecordBatchStream),
     /// Creates an empty table, the definition / schema must be provided separately
     Empty(TableDefinition),
 }
 
+impl CreateTableData {
+    pub fn schema(&self) -> Arc<arrow_schema::Schema> {
+        match self {
+            Self::Data(reader) => reader.schema(),
+            Self::StreamingData(stream) => stream.schema(),
+            Self::Empty(definition) => definition.schema.clone(),
+        }
+    }
+}
+
+#[async_trait]
+impl StreamingWriteSource for CreateTableData {
+    fn arrow_schema(&self) -> Arc<arrow_schema::Schema> {
+        self.schema()
+    }
+    fn into_stream(self) -> datafusion_physical_plan::SendableRecordBatchStream {
+        match self {
+            Self::Data(reader) => reader.into_stream(),
+            Self::StreamingData(stream) => stream.into_df_stream(),
+            Self::Empty(table_definition) => {
+                let schema = table_definition.schema.clone();
+                Box::pin(RecordBatchStreamAdapter::new(schema, stream::empty()))
+            }
+        }
+    }
+}
+
 /// A request to create a table
 pub struct CreateTableRequest {
     /// The name of the new table

rust/lancedb/src/database/listing.rs

@@ -7,9 +7,9 @@ use std::fs::create_dir_all;
 use std::path::Path;
 use std::{collections::HashMap, sync::Arc};
 
-use arrow_array::RecordBatchIterator;
 use lance::dataset::{ReadParams, WriteMode};
 use lance::io::{ObjectStore, ObjectStoreParams, ObjectStoreRegistry, WrappingObjectStore};
+use lance_datafusion::utils::StreamingWriteSource;
 use lance_encoding::version::LanceFileVersion;
 use lance_table::io::commit::commit_handler_from_url;
 use object_store::local::LocalFileSystem;
@@ -22,8 +22,8 @@ use crate::table::NativeTable;
 use crate::utils::validate_table_name;
 
 use super::{
-    BaseTable, CreateTableData, CreateTableMode, CreateTableRequest, Database, DatabaseOptions,
+    BaseTable, CreateTableMode, CreateTableRequest, Database, DatabaseOptions, OpenTableRequest,
-    OpenTableRequest, TableNamesRequest,
+    TableNamesRequest,
 };
 
 /// File extension to indicate a lance table
@@ -322,6 +322,37 @@ impl ListingDatabase {
 
         Ok(uri)
     }
+
+    async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
+        let object_store_params = ObjectStoreParams {
+            storage_options: Some(self.storage_options.clone()),
+            ..Default::default()
+        };
+        let mut uri = self.uri.clone();
+        if let Some(query_string) = &self.query_string {
+            uri.push_str(&format!("?{}", query_string));
+        }
+        let commit_handler = commit_handler_from_url(&uri, &Some(object_store_params)).await?;
+        for name in names {
+            let dir_name = format!("{}.{}", name, LANCE_EXTENSION);
+            let full_path = self.base_path.child(dir_name.clone());
+
+            commit_handler.delete(&full_path).await?;
+
+            self.object_store
+                .remove_dir_all(full_path.clone())
+                .await
+                .map_err(|err| match err {
+                    // this error is not lance::Error::DatasetNotFound, as the method
+                    // `remove_dir_all` may be used to remove something not be a dataset
+                    lance::Error::NotFound { .. } => Error::TableNotFound {
+                        name: name.to_owned(),
+                    },
+                    _ => Error::from(err),
+                })?;
+        }
+        Ok(())
+    }
 }
 
 #[async_trait::async_trait]
@@ -401,19 +432,12 @@ impl Database for ListingDatabase {
             write_params.mode = WriteMode::Overwrite;
         }
 
-        let data = match request.data {
+        let data_schema = request.data.arrow_schema();
-            CreateTableData::Data(data) => data,
-            CreateTableData::Empty(table_definition) => {
-                let schema = table_definition.schema.clone();
-                Box::new(RecordBatchIterator::new(vec![], schema))
-            }
-        };
-        let data_schema = data.schema();
 
         match NativeTable::create(
             &table_uri,
             &request.name,
-            data,
+            request.data,
             self.store_wrapper.clone(),
             Some(write_params),
             self.read_consistency_interval,
@@ -500,40 +524,12 @@ impl Database for ListingDatabase {
     }
 
     async fn drop_table(&self, name: &str) -> Result<()> {
-        let dir_name = format!("{}.{}", name, LANCE_EXTENSION);
+        self.drop_tables(vec![name.to_string()]).await
-        let full_path = self.base_path.child(dir_name.clone());
-        self.object_store
-            .remove_dir_all(full_path.clone())
-            .await
-            .map_err(|err| match err {
-                // this error is not lance::Error::DatasetNotFound,
-                // as the method `remove_dir_all` may be used to remove something not be a dataset
-                lance::Error::NotFound { .. } => Error::TableNotFound {
-                    name: name.to_owned(),
-                },
-                _ => Error::from(err),
-            })?;
-
-        let object_store_params = ObjectStoreParams {
-            storage_options: Some(self.storage_options.clone()),
-            ..Default::default()
-        };
-        let mut uri = self.uri.clone();
-        if let Some(query_string) = &self.query_string {
-            uri.push_str(&format!("?{}", query_string));
-        }
-        let commit_handler = commit_handler_from_url(&uri, &Some(object_store_params))
-            .await
-            .unwrap();
-        commit_handler.delete(&full_path).await.unwrap();
-        Ok(())
     }
 
     async fn drop_all_tables(&self) -> Result<()> {
-        self.object_store
+        let tables = self.table_names(TableNamesRequest::default()).await?;
-            .remove_dir_all(self.base_path.clone())
+        self.drop_tables(tables).await
-            .await?;
-        Ok(())
     }
 
     fn as_any(&self) -> &dyn std::any::Any {

rust/lancedb/src/remote/db.rs

@@ -164,6 +164,11 @@ impl<S: HttpSend> Database for RemoteDatabase<S> {
     async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>> {
         let data = match request.data {
             CreateTableData::Data(data) => data,
+            CreateTableData::StreamingData(_) => {
+                return Err(Error::NotSupported {
+                    message: "Creating a remote table from a streaming source".to_string(),
+                })
+            }
             CreateTableData::Empty(table_definition) => {
                 let schema = table_definition.schema.clone();
                 Box::new(RecordBatchIterator::new(vec![], schema))

rust/lancedb/src/table.rs

@@ -28,13 +28,13 @@ pub use lance::dataset::NewColumnTransform;
 pub use lance::dataset::ReadParams;
 pub use lance::dataset::Version;
 use lance::dataset::{
-    Dataset, InsertBuilder, UpdateBuilder as LanceUpdateBuilder, WhenMatched, WriteMode,
+    InsertBuilder, UpdateBuilder as LanceUpdateBuilder, WhenMatched, WriteMode, WriteParams,
-    WriteParams,
 };
 use lance::dataset::{MergeInsertBuilder as LanceMergeInsertBuilder, WhenNotMatchedBySource};
 use lance::index::vector::utils::infer_vector_dim;
 use lance::io::WrappingObjectStore;
 use lance_datafusion::exec::execute_plan;
+use lance_datafusion::utils::StreamingWriteSource;
 use lance_index::vector::hnsw::builder::HnswBuildParams;
 use lance_index::vector::ivf::IvfBuildParams;
 use lance_index::vector::pq::PQBuildParams;
@@ -1264,7 +1264,7 @@ impl NativeTable {
     pub async fn create(
         uri: &str,
         name: &str,
-        batches: impl RecordBatchReader + Send + 'static,
+        batches: impl StreamingWriteSource,
         write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
         params: Option<WriteParams>,
         read_consistency_interval: Option<std::time::Duration>,
@@ -1279,7 +1279,9 @@ impl NativeTable {
             None => params,
         };
 
-        let dataset = Dataset::write(batches, uri, Some(params))
+        let insert_builder = InsertBuilder::new(uri).with_params(&params);
+        let dataset = insert_builder
+            .execute_stream(batches)
             .await
             .map_err(|e| match e {
                 lance::Error::DatasetAlreadyExists { .. } => Error::TableAlreadyExists {
@@ -1287,6 +1289,7 @@ impl NativeTable {
                 },
                 source => Error::Lance { source },
             })?;
+
         Ok(Self {
             name: name.to_string(),
             uri: uri.to_string(),
@@ -2391,8 +2394,9 @@ mod tests {
     use arrow_data::ArrayDataBuilder;
     use arrow_schema::{DataType, Field, Schema, TimeUnit};
     use futures::TryStreamExt;
-    use lance::dataset::{Dataset, WriteMode};
+    use lance::dataset::WriteMode;
     use lance::io::{ObjectStoreParams, WrappingObjectStore};
+    use lance::Dataset;
     use rand::Rng;
     use tempfile::tempdir;
 
@@ -2442,6 +2446,7 @@ mod tests {
         let uri = tmp_dir.path().to_str().unwrap();
 
         let batches = make_test_batches();
+        let batches = Box::new(batches) as Box<dyn RecordBatchReader + Send>;
         let table = NativeTable::create(uri, "test", batches, None, None, None)
             .await
             .unwrap();

rust/lancedb/src/table/datafusion.rs

@@ -151,7 +151,7 @@ impl TableProvider for BaseTableAdapter {
 
     async fn scan(
         &self,
-        _state: &dyn Session,
+        state: &dyn Session,
         projection: Option<&Vec<usize>>,
         filters: &[Expr],
         limit: Option<usize>,
@@ -177,9 +177,15 @@ impl TableProvider for BaseTableAdapter {
             // Need to override the default of 10
             query.limit = None;
         }
+
+        let options = QueryExecutionOptions {
+            max_batch_length: state.config().batch_size() as u32,
+            ..Default::default()
+        };
+
         let plan = self
             .table
-            .create_plan(&AnyQuery::Query(query), QueryExecutionOptions::default())
+            .create_plan(&AnyQuery::Query(query), options)
             .map_err(|err| DataFusionError::External(err.into()))
             .await?;
         Ok(Arc::new(MetadataEraserExec::new(plan)))
@@ -208,11 +214,14 @@ pub mod tests {
         RecordBatchReader, StringArray, UInt32Array,
     };
     use arrow_schema::{DataType, Field, Schema};
-    use datafusion::{datasource::provider_as_source, prelude::SessionContext};
+    use datafusion::{
+        datasource::provider_as_source,
+        prelude::{SessionConfig, SessionContext},
+    };
     use datafusion_catalog::TableProvider;
     use datafusion_execution::SendableRecordBatchStream;
     use datafusion_expr::{col, lit, LogicalPlan, LogicalPlanBuilder};
-    use futures::TryStreamExt;
+    use futures::{StreamExt, TryStreamExt};
     use tempfile::tempdir;
 
     use crate::{
@@ -332,7 +341,14 @@ pub mod tests {
         }
 
         async fn plan_to_stream(plan: LogicalPlan) -> SendableRecordBatchStream {
-            SessionContext::new()
+            Self::plan_to_stream_with_config(plan, SessionConfig::default()).await
+        }
+
+        async fn plan_to_stream_with_config(
+            plan: LogicalPlan,
+            config: SessionConfig,
+        ) -> SendableRecordBatchStream {
+            SessionContext::new_with_config(config)
                 .execute_logical_plan(plan)
                 .await
                 .unwrap()
@@ -382,6 +398,30 @@ pub mod tests {
         }
     }
 
+    #[tokio::test]
+    async fn test_batch_size() {
+        let fixture = TestFixture::new().await;
+
+        let plan = LogicalPlanBuilder::scan("foo", provider_as_source(fixture.adapter2), None)
+            .unwrap()
+            .build()
+            .unwrap();
+
+        let config = SessionConfig::default().with_batch_size(100);
+
+        let stream = TestFixture::plan_to_stream_with_config(plan.clone(), config).await;
+
+        let batch_count = stream.count().await;
+        assert_eq!(batch_count, 10);
+
+        let config = SessionConfig::default().with_batch_size(250);
+
+        let stream = TestFixture::plan_to_stream_with_config(plan, config).await;
+
+        let batch_count = stream.count().await;
+        assert_eq!(batch_count, 4);
+    }
+
     #[tokio::test]
     async fn test_metadata_erased() {
         let fixture = TestFixture::new().await;