fix: remove .lance-reserved marker after writing table in namespace mode

lance v6.0.0-beta.2 introduced a `.lance-reserved` marker file in
declare_table to prevent directory scans from seeing incomplete tables.
lancedb calls declare_table to get the canonical URI, then writes data
separately via NativeTable::create_from_namespace, but never cleaned up
the marker. This caused list_directory_tables() to skip tables with the
marker, making newly created tables invisible in table_names().

After writing the table, delete the marker using the dataset's configured
object store so it works for both local and cloud storage.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.28.0-beta.2"
+current_version = "0.28.0-beta.9"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/ISSUE_TEMPLATE/documentation.yml

@@ -18,6 +18,6 @@ body:
       label: Link
       description: >
         Provide a link to the existing documentation, if applicable.
-      placeholder: ex. https://lancedb.com/docs/tables/...
+      placeholder: ex. https://docs.lancedb.com/tables/...
     validations:
       required: false

.github/workflows/dev.yml

@@ -8,6 +8,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   labeler:
     permissions:

.github/workflows/java-publish.yml

@@ -19,6 +19,9 @@ on:
     paths:
       - .github/workflows/java-publish.yml
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     name: Build and Publish

.github/workflows/java.yml

@@ -24,6 +24,9 @@ on:
       - java/**
       - .github/workflows/java.yml
 
+permissions:
+  contents: read
+
 jobs:
   build-java:
     runs-on: ubuntu-24.04

.github/workflows/license-header-check.yml

@@ -10,6 +10,10 @@ on:
       - nodejs/**
       - java/**
       - .github/workflows/license-header-check.yml
+
+permissions:
+  contents: read
+
 jobs:
   check-licenses:
     runs-on: ubuntu-latest

.github/workflows/nodejs.yml

@@ -15,6 +15,9 @@ on:
       - .github/workflows/nodejs.yml
       - docker-compose.yml
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true

.github/workflows/pypi-publish.yml

@@ -14,6 +14,9 @@ on:
 env:
   PIP_EXTRA_INDEX_URL: "https://pypi.fury.io/lance-format/ https://pypi.fury.io/lancedb/"
 
+permissions:
+  contents: read
+
 jobs:
   linux:
     name: Python ${{ matrix.config.platform }} manylinux${{ matrix.config.manylinux }}

.github/workflows/python.yml

@@ -17,6 +17,9 @@ on:
       - .github/workflows/build_windows_wheel/**
       - .github/workflows/run_tests/**
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
@@ -108,7 +111,6 @@ jobs:
       - name: Install
         run: |
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests,dev,embeddings]
-          pip install tantivy
           pip install mlx
       - name: Doctest
         run: pytest --doctest-modules python/lancedb
@@ -227,6 +229,5 @@ jobs:
           pip install "pydantic<2"
           pip install pyarrow==16
           pip install --extra-index-url https://pypi.fury.io/lance-format/ --extra-index-url https://pypi.fury.io/lancedb/ -e .[tests]
-          pip install tantivy
       - name: Run tests
         run: pytest -m "not slow and not s3_test" -x -v --durations=30 python/tests

.github/workflows/rust.yml

@@ -12,6 +12,9 @@ on:
       - rust/**
       - .github/workflows/rust.yml
 
+permissions:
+  contents: read
+
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true

.github/workflows/update_package_lock_run.yml

@@ -3,6 +3,9 @@ name: Update package-lock.json
 on:
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     runs-on: ubuntu-latest

.github/workflows/update_package_lock_run_nodejs.yml

@@ -3,6 +3,9 @@ name: Update NodeJs package-lock.json
 on:
   workflow_dispatch:
 
+permissions:
+  contents: read
+
 jobs:
   publish:
     runs-on: ubuntu-latest

Cargo.lock

@@ -137,15 +137,6 @@ dependencies = [
  "object",
 ]
 
-[[package]]
-name = "arc-swap"
-version = "1.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a07d1f37ff60921c83bdfc7407723bdefe89b44b98a9b772f225c8f9d67141a6"
-dependencies = [
- "rustversion",
-]
-
 [[package]]
 name = "argminmax"
 version = "0.6.3"
@@ -302,7 +293,7 @@ dependencies = [
  "arrow-schema",
  "arrow-select",
  "flatbuffers",
- "lz4_flex 0.12.1",
+ "lz4_flex",
  "zstd",
 ]
 
@@ -1278,31 +1269,6 @@ dependencies = [
  "generic-array",
 ]
 
-[[package]]
-name = "bon"
-version = "3.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f47dbe92550676ee653353c310dfb9cf6ba17ee70396e1f7cf0a2020ad49b2fe"
-dependencies = [
- "bon-macros",
- "rustversion",
-]
-
-[[package]]
-name = "bon-macros"
-version = "3.9.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "519bd3116aeeb42d5372c29d982d16d0170d3d4a5ed85fc7dd91642ffff3c67c"
-dependencies = [
- "darling 0.20.11",
- "ident_case",
- "prettyplease",
- "proc-macro2",
- "quote",
- "rustversion",
- "syn 2.0.117",
-]
-
 [[package]]
 name = "brotli"
 version = "3.5.0"
@@ -1472,12 +1438,6 @@ dependencies = [
  "shlex",
 ]
 
-[[package]]
-name = "census"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "4f4c707c6a209cbe82d10abd08e1ea8995e9ea937d2550646e02798948992be0"
-
 [[package]]
 name = "cfg-if"
 version = "1.0.4"
@@ -1795,7 +1755,7 @@ dependencies = [
  "crossterm_winapi",
  "document-features",
  "parking_lot",
- "rustix 1.1.4",
+ "rustix",
  "winapi",
 ]
 
@@ -2714,12 +2674,6 @@ dependencies = [
  "litrs",
 ]
 
-[[package]]
-name = "downcast-rs"
-version = "2.0.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "117240f60069e65410b3ae1bb213295bd828f707b5bec6596a1afc8793ce0cbc"
-
 [[package]]
 name = "dtor"
 version = "0.1.1"
@@ -2955,12 +2909,6 @@ version = "0.2.3"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f8eb564c5c7423d25c886fb561d1e4ee69f72354d16918afa32c08811f6b6a55"
 
-[[package]]
-name = "fastdivide"
-version = "0.4.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9afc2bd4d5a73106dd53d10d73d3401c2f32730ba2c0b93ddb888a8983680471"
-
 [[package]]
 name = "fastrand"
 version = "2.3.0"
@@ -3054,16 +3002,6 @@ dependencies = [
  "percent-encoding",
 ]
 
-[[package]]
-name = "fs4"
-version = "0.8.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f7e180ac76c23b45e767bd7ae9579bc0bb458618c4bc71835926e098e61d15f8"
-dependencies = [
- "rustix 0.38.44",
- "windows-sys 0.52.0",
-]
-
 [[package]]
 name = "fs_extra"
 version = "1.3.0"
@@ -3072,8 +3010,8 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-array",
  "rand 0.9.2",
@@ -3560,12 +3498,6 @@ dependencies = [
  "windows-sys 0.61.2",
 ]
 
-[[package]]
-name = "htmlescape"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e9025058dae765dee5070ec375f591e2ba14638c63feff74f13805a72e523163"
-
 [[package]]
 name = "http"
 version = "0.2.12"
@@ -4134,8 +4066,8 @@ dependencies = [
 
 [[package]]
 name = "lance"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4178,12 +4110,14 @@ dependencies = [
  "lance-linalg",
  "lance-namespace",
  "lance-table",
+ "lance-tokenizer",
  "log",
  "moka",
  "object_store",
  "permutation",
  "pin-project",
  "prost",
+ "prost-build",
  "prost-types",
  "rand 0.9.2",
  "roaring",
@@ -4191,7 +4125,6 @@ dependencies = [
  "serde",
  "serde_json",
  "snafu 0.9.0",
- "tantivy",
  "tokio",
  "tokio-stream",
  "tokio-util",
@@ -4202,8 +4135,8 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4224,8 +4157,8 @@ dependencies = [
 
 [[package]]
 name = "lance-bitpacking"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrayref",
  "paste",
@@ -4234,8 +4167,8 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4272,8 +4205,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4304,8 +4237,8 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4323,8 +4256,8 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4361,8 +4294,8 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -4394,8 +4327,8 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4432,6 +4365,7 @@ dependencies = [
  "lance-io",
  "lance-linalg",
  "lance-table",
+ "lance-tokenizer",
  "libm",
  "log",
  "ndarray",
@@ -4449,7 +4383,6 @@ dependencies = [
  "serde_json",
  "smallvec",
  "snafu 0.9.0",
- "tantivy",
  "tempfile",
  "tokio",
  "tracing",
@@ -4459,8 +4392,8 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -4504,8 +4437,8 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4521,8 +4454,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "async-trait",
@@ -4535,8 +4468,8 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -4581,8 +4514,8 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4621,8 +4554,8 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "5.1.0-beta.2"
-source = "git+https://github.com/lance-format/lance.git?tag=v5.1.0-beta.2#df61d95cac9ab579e4bc4ff41d1bd749b24af7f0"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -4631,9 +4564,19 @@ dependencies = [
  "rand 0.9.2",
 ]
 
+[[package]]
+name = "lance-tokenizer"
+version = "6.0.0-beta.2"
+source = "git+https://github.com/lance-format/lance.git?tag=v6.0.0-beta.2#d244dad1f461e5cb2fbfc8a428b767c4e0196b2d"
+dependencies = [
+ "rust-stemmers",
+ "serde",
+ "unicode-normalization",
+]
+
 [[package]]
 name = "lancedb"
-version = "0.28.0-beta.2"
+version = "0.28.0-beta.9"
 dependencies = [
  "ahash",
  "anyhow",
@@ -4715,7 +4658,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.28.0-beta.2"
+version = "0.28.0-beta.9"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4737,7 +4680,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.31.0-beta.2"
+version = "0.31.0-beta.9"
 dependencies = [
  "arrow",
  "async-trait",
@@ -4775,12 +4718,6 @@ version = "0.1.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "09edd9e8b54e49e587e4f6295a7d29c3ea94d469cb40ab8ca70b288248a81db2"
 
-[[package]]
-name = "levenshtein_automata"
-version = "0.2.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c2cdeb66e45e9f36bfad5bbdb4d2384e70936afbee843c6f6543f0c551ebb25"
-
 [[package]]
 name = "lexical-core"
 version = "1.0.6"
@@ -4869,12 +4806,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "linux-raw-sys"
-version = "0.4.15"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d26c52dbd32dccf2d10cac7725f8eae5296885fb5703b261f7d0a0739ec807ab"
-
 [[package]]
 name = "linux-raw-sys"
 version = "0.12.1"
@@ -4955,12 +4886,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "lz4_flex"
-version = "0.11.6"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "373f5eceeeab7925e0c1098212f2fbc4d416adec9d35051a6ab251e824c1854a"
-
 [[package]]
 name = "lz4_flex"
 version = "0.12.1"
@@ -5035,15 +4960,6 @@ dependencies = [
  "digest",
 ]
 
-[[package]]
-name = "measure_time"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "51c55d61e72fc3ab704396c5fa16f4c184db37978ae4e94ca8959693a235fc0e"
-dependencies = [
- "log",
-]
-
 [[package]]
 name = "memchr"
 version = "2.8.0"
@@ -5197,12 +5113,6 @@ dependencies = [
  "target-features",
 ]
 
-[[package]]
-name = "murmurhash32"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2195bf6aa996a481483b29d62a7663eed3fe39600c460e323f8ff41e90bdd89b"
-
 [[package]]
 name = "napi"
 version = "3.8.3"
@@ -5491,12 +5401,6 @@ version = "1.70.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "384b8ab6d37215f3c5301a95a4accb5d64aa607f1fcb26a11b5303878451b4fe"
 
-[[package]]
-name = "oneshot"
-version = "0.1.13"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "269bca4c2591a28585d6bf10d9ed0332b7d76900a1b02bec41bdc3a2cdcda107"
-
 [[package]]
 name = "onig"
 version = "6.5.1"
@@ -5586,15 +5490,6 @@ version = "0.5.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1a80800c0488c3a21695ea981a54918fbb37abf04f4d0720c453632255e2ff0e"
 
-[[package]]
-name = "ownedbytes"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2fbd56f7631767e61784dc43f8580f403f4475bd4aaa4da003e6295e1bab4a7e"
-dependencies = [
- "stable_deref_trait",
-]
-
 [[package]]
 name = "p256"
 version = "0.11.1"
@@ -7049,19 +6944,6 @@ dependencies = [
  "semver",
 ]
 
-[[package]]
-name = "rustix"
-version = "0.38.44"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "fdb5bc1ae2baa591800df16c9ca78619bf65c0488b41b96ccec5d11220d8c154"
-dependencies = [
- "bitflags",
- "errno",
- "libc",
- "linux-raw-sys 0.4.15",
- "windows-sys 0.59.0",
-]
-
 [[package]]
 name = "rustix"
 version = "1.1.4"
@@ -7071,7 +6953,7 @@ dependencies = [
  "bitflags",
  "errno",
  "libc",
- "linux-raw-sys 0.12.1",
+ "linux-raw-sys",
  "windows-sys 0.59.0",
 ]
 
@@ -7536,15 +7418,6 @@ version = "1.0.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "b2aa850e253778c88a04c3d7323b043aeda9d3e30d5971937c1855769763678e"
 
-[[package]]
-name = "sketches-ddsketch"
-version = "0.3.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0c6f73aeb92d671e0cc4dca167e59b2deb6387c375391bc99ee743f326994a2b"
-dependencies = [
- "serde",
-]
-
 [[package]]
 name = "slab"
 version = "0.4.12"
@@ -7917,152 +7790,6 @@ version = "0.2.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "7b2093cf4c8eb1e67749a6762251bc9cd836b6fc171623bd0a9d324d37af2417"
 
-[[package]]
-name = "tantivy"
-version = "0.24.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "64a966cb0e76e311f09cf18507c9af192f15d34886ee43d7ba7c7e3803660c43"
-dependencies = [
- "aho-corasick",
- "arc-swap",
- "base64 0.22.1",
- "bitpacking",
- "bon",
- "byteorder",
- "census",
- "crc32fast",
- "crossbeam-channel",
- "downcast-rs",
- "fastdivide",
- "fnv",
- "fs4",
- "htmlescape",
- "hyperloglogplus",
- "itertools 0.14.0",
- "levenshtein_automata",
- "log",
- "lru",
- "lz4_flex 0.11.6",
- "measure_time",
- "memmap2 0.9.10",
- "once_cell",
- "oneshot",
- "rayon",
- "regex",
- "rust-stemmers",
- "rustc-hash",
- "serde",
- "serde_json",
- "sketches-ddsketch",
- "smallvec",
- "tantivy-bitpacker",
- "tantivy-columnar",
- "tantivy-common",
- "tantivy-fst",
- "tantivy-query-grammar",
- "tantivy-stacker",
- "tantivy-tokenizer-api",
- "tempfile",
- "thiserror 2.0.18",
- "time",
- "uuid",
- "winapi",
-]
-
-[[package]]
-name = "tantivy-bitpacker"
-version = "0.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1adc286a39e089ae9938935cd488d7d34f14502544a36607effd2239ff0e2494"
-dependencies = [
- "bitpacking",
-]
-
-[[package]]
-name = "tantivy-columnar"
-version = "0.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "6300428e0c104c4f7db6f95b466a6f5c1b9aece094ec57cdd365337908dc7344"
-dependencies = [
- "downcast-rs",
- "fastdivide",
- "itertools 0.14.0",
- "serde",
- "tantivy-bitpacker",
- "tantivy-common",
- "tantivy-sstable",
- "tantivy-stacker",
-]
-
-[[package]]
-name = "tantivy-common"
-version = "0.9.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e91b6ea6090ce03dc72c27d0619e77185d26cc3b20775966c346c6d4f7e99d7f"
-dependencies = [
- "async-trait",
- "byteorder",
- "ownedbytes",
- "serde",
- "time",
-]
-
-[[package]]
-name = "tantivy-fst"
-version = "0.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d60769b80ad7953d8a7b2c70cdfe722bbcdcac6bccc8ac934c40c034d866fc18"
-dependencies = [
- "byteorder",
- "regex-syntax",
- "utf8-ranges",
-]
-
-[[package]]
-name = "tantivy-query-grammar"
-version = "0.24.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e810cdeeebca57fc3f7bfec5f85fdbea9031b2ac9b990eb5ff49b371d52bbe6a"
-dependencies = [
- "nom 7.1.3",
- "serde",
- "serde_json",
-]
-
-[[package]]
-name = "tantivy-sstable"
-version = "0.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "709f22c08a4c90e1b36711c1c6cad5ae21b20b093e535b69b18783dd2cb99416"
-dependencies = [
- "futures-util",
- "itertools 0.14.0",
- "tantivy-bitpacker",
- "tantivy-common",
- "tantivy-fst",
- "zstd",
-]
-
-[[package]]
-name = "tantivy-stacker"
-version = "0.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2bcdebb267671311d1e8891fd9d1301803fdb8ad21ba22e0a30d0cab49ba59c1"
-dependencies = [
- "murmurhash32",
- "rand_distr 0.4.3",
- "tantivy-common",
-]
-
-[[package]]
-name = "tantivy-tokenizer-api"
-version = "0.5.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "dfa942fcee81e213e09715bbce8734ae2180070b97b33839a795ba1de201547d"
-dependencies = [
- "serde",
-]
-
 [[package]]
 name = "tap"
 version = "1.0.1"
@@ -8090,7 +7817,7 @@ dependencies = [
  "fastrand",
  "getrandom 0.4.2",
  "once_cell",
- "rustix 1.1.4",
+ "rustix",
  "windows-sys 0.59.0",
 ]
 
@@ -8542,6 +8269,15 @@ version = "1.0.24"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
 
+[[package]]
+name = "unicode-normalization"
+version = "0.1.25"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5fd4f6878c9cb28d874b009da9e8d183b5abc80117c40bbd187a1fde336be6e8"
+dependencies = [
+ "tinyvec",
+]
+
 [[package]]
 name = "unicode-normalization-alignments"
 version = "0.1.12"

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=5.1.0-beta.2", default-features = false, "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=5.1.0-beta.2", default-features = false, "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=5.1.0-beta.2", default-features = false, "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=5.1.0-beta.2", "tag" = "v5.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=6.0.0-beta.2", default-features = false, "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=6.0.0-beta.2", default-features = false, "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=6.0.0-beta.2", default-features = false, "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=6.0.0-beta.2", "tag" = "v6.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }

README.md

@@ -15,7 +15,7 @@
 
 # **The Multimodal AI Lakehouse**
 
-[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://lancedb.com/docs) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
+[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https://docs.lancedb.com) ✦ [**Tutorials and Recipes**](https://github.com/lancedb/vectordb-recipes/tree/main) ✦  [**Contributors**](#contributors) 
 
 **The ultimate multimodal data platform for AI/ML applications.** 
 
@@ -57,7 +57,7 @@ LanceDB is a central location where developers can build, train and analyze thei
 
 ## **How to Install**:
 
-Follow the [Quickstart](https://lancedb.com/docs/quickstart/) doc to set up LanceDB locally. 
+Follow the [Quickstart](https://docs.lancedb.com/quickstart) doc to set up LanceDB locally. 
 
 **API & SDK:** We also support Python, Typescript and Rust SDKs
 

dockerfiles/Dockerfile

@@ -24,4 +24,4 @@ RUN python --version && \
   rustc --version && \
   protoc --version
 
-RUN pip install --no-cache-dir tantivy lancedb
+RUN pip install --no-cache-dir lancedb

docs/README.md

@@ -1,6 +1,6 @@
 # LanceDB Documentation
 
-LanceDB docs are available at [lancedb.com/docs](https://lancedb.com/docs).
+LanceDB docs are available at [docs.lancedb.com](https://docs.lancedb.com).
 
 The SDK docs are built and deployed automatically by [Github Actions](../.github/workflows/docs.yml)
 whenever a commit is pushed to the `main` branch. So it is possible for the docs to show

docs/src/java/java.md

@@ -14,7 +14,7 @@ Add the following dependency to your `pom.xml`:
 <dependency>
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-core</artifactId>
-    <version>0.28.0-beta.2</version>
+    <version>0.28.0-beta.9</version>
 </dependency>
 ```
 

docs/src/js/README.md

@@ -34,7 +34,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
+The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
 
 ## Development
 

docs/src/js/interfaces/ConnectionOptions.md

@@ -89,4 +89,4 @@ optional storageOptions: Record<string, string>;
 
 (For LanceDB OSS only): configuration for object storage.
 
-The available options are described at https://lancedb.com/docs/storage/
+The available options are described at https://docs.lancedb.com/storage/

docs/src/js/interfaces/CreateTableOptions.md

@@ -97,4 +97,4 @@ Configuration for object storage.
 Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
-The available options are described at https://lancedb.com/docs/storage/
+The available options are described at https://docs.lancedb.com/storage/

docs/src/js/interfaces/OpenTableOptions.md

@@ -42,4 +42,4 @@ Configuration for object storage.
 Options already set on the connection will be inherited by the table,
 but can be overridden here.
 
-The available options are described at https://lancedb.com/docs/storage/
+The available options are described at https://docs.lancedb.com/storage/

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.28.0-beta.2</version>
+      <version>0.28.0-beta.9</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.28.0-beta.2</version>
+    <version>0.28.0-beta.9</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>5.1.0-beta.2</lance-core.version>
+        <lance-core.version>6.0.0-beta.2</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.28.0-beta.2"
+version = "0.28.0-beta.9"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/README.md

@@ -30,7 +30,7 @@ const results = await table.vectorSearch([0.1, 0.3]).limit(20).toArray();
 console.log(results);
 ```
 
-The [quickstart](https://lancedb.com/docs/quickstart/basic-usage/) contains more complete examples.
+The [quickstart](https://docs.lancedb.com/quickstart/) contains more complete examples.
 
 ## Development
 

nodejs/__test__/rerankers.test.ts

@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
+import { spawn } from "node:child_process";
+import * as path from "node:path";
 import { RecordBatch } from "apache-arrow";
 import * as tmp from "tmp";
 import { Connection, Index, Table, connect, makeArrowTable } from "../lancedb";
@@ -76,4 +78,91 @@ describe("rerankers", function () {
 
     expect(result).toHaveLength(2);
   });
+
+  it("does not keep process alive after rerank query", async function () {
+    const script = `
+import * as lancedb from "./dist/index.js";
+import * as os from "node:os";
+import * as path from "node:path";
+import * as fs from "node:fs/promises";
+
+const dir = await fs.mkdtemp(path.join(os.tmpdir(), "lancedb-rerank-exit-"));
+const db = await lancedb.connect(dir);
+const table = await db.createTable("test", [{ text: "hello", vector: [1, 2, 3] }], {
+  mode: "overwrite",
+});
+await table.createIndex("text", { config: lancedb.Index.fts() });
+await table.waitForIndex(["text_idx"], 30);
+
+const reranker = await lancedb.rerankers.RRFReranker.create();
+await table
+  .query()
+  .nearestTo([1, 2, 3])
+  .fullTextSearch("hello")
+  .rerank(reranker)
+  .toArray();
+
+table.close();
+db.close();
+`;
+
+    await new Promise<void>((resolve, reject) => {
+      const child = spawn(
+        process.execPath,
+        ["--input-type=module", "-e", script],
+        {
+          cwd: path.resolve(__dirname, ".."),
+          stdio: ["ignore", "pipe", "pipe"],
+        },
+      );
+
+      let stdout = "";
+      let stderr = "";
+
+      child.stdout.on("data", (chunk) => {
+        stdout += chunk.toString();
+      });
+
+      child.stderr.on("data", (chunk) => {
+        stderr += chunk.toString();
+      });
+
+      const timeout = setTimeout(() => {
+        child.kill();
+        reject(
+          new Error(
+            `child process did not exit in time\nstdout:\n${stdout}\nstderr:\n${stderr}`,
+          ),
+        );
+      }, 20_000);
+
+      child.on("error", (err) => {
+        clearTimeout(timeout);
+        reject(err);
+      });
+
+      child.on("exit", (code, signal) => {
+        clearTimeout(timeout);
+        if (signal !== null) {
+          reject(
+            new Error(
+              `child process exited with signal ${signal}\nstdout:\n${stdout}\nstderr:\n${stderr}`,
+            ),
+          );
+          return;
+        }
+
+        if (code !== 0) {
+          reject(
+            new Error(
+              `child process exited with code ${code}\nstdout:\n${stdout}\nstderr:\n${stderr}`,
+            ),
+          );
+          return;
+        }
+
+        resolve();
+      });
+    });
+  });
 });

nodejs/lancedb/connection.ts

@@ -42,7 +42,7 @@ export interface CreateTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://lancedb.com/docs/storage/
+   * The available options are described at https://docs.lancedb.com/storage/
    */
   storageOptions?: Record<string, string>;
 
@@ -78,7 +78,7 @@ export interface OpenTableOptions {
    * Options already set on the connection will be inherited by the table,
    * but can be overridden here.
    *
-   * The available options are described at https://lancedb.com/docs/storage/
+   * The available options are described at https://docs.lancedb.com/storage/
    */
   storageOptions?: Record<string, string>;
   /**

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.28.0-beta.2",
+	"version": "0.28.0-beta.9",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.28.0-beta.2",
+	"version": "0.28.0-beta.9",
 	"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": "0.28.0-beta.2",
+	"version": "0.28.0-beta.9",
 	"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": "0.28.0-beta.2",
+	"version": "0.28.0-beta.9",
 	"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": "0.28.0-beta.2",
+	"version": "0.28.0-beta.9",
 	"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": "0.28.0-beta.2",
+  "version": "0.28.0-beta.9",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.28.0-beta.2",
+	"version": "0.28.0-beta.9",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.28.0-beta.2",
+  "version": "0.28.0-beta.9",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.28.0-beta.2",
+      "version": "0.28.0-beta.9",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.28.0-beta.2",
+  "version": "0.28.0-beta.9",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/lib.rs

@@ -35,7 +35,7 @@ pub struct ConnectionOptions {
     pub read_consistency_interval: Option<f64>,
     /// (For LanceDB OSS only): configuration for object storage.
     ///
-    /// The available options are described at https://lancedb.com/docs/storage/
+    /// The available options are described at https://docs.lancedb.com/storage/
     pub storage_options: Option<HashMap<String, String>>,
     /// (For LanceDB OSS only): the session to use for this connection. Holds
     /// shared caches and other session-specific state.

nodejs/src/rerankers.rs

@@ -18,6 +18,7 @@ type RerankHybridFn = ThreadsafeFunction<
     RerankHybridCallbackArgs,
     Status,
     false,
+    true,
 >;
 
 /// Reranker implementation that "wraps" a NodeJS Reranker implementation.
@@ -32,7 +33,10 @@ impl Reranker {
     pub fn new(
         rerank_hybrid: Function<RerankHybridCallbackArgs, Promise<Buffer>>,
     ) -> napi::Result<Self> {
-        let rerank_hybrid = rerank_hybrid.build_threadsafe_function().build()?;
+        let rerank_hybrid = rerank_hybrid
+            .build_threadsafe_function()
+            .weak::<true>()
+            .build()?;
         Ok(Self { rerank_hybrid })
     }
 }

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.31.0-beta.3"
+current_version = "0.31.0-beta.9"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.31.0-beta.3"
+version = "0.31.0-beta.9"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/PYTHON_THIRD_PARTY_LICENSES.md

@@ -183,7 +183,6 @@
 | stack-data                     | 0.6.3           | MIT License                                                                                      | http://github.com/alexmojaki/stack_data                                                           |
 | sympy                          | 1.14.0          | BSD License                                                                                      | https://sympy.org                                                                                 |
 | tabulate                       | 0.9.0           | MIT License                                                                                      | https://github.com/astanin/python-tabulate                                                        |
-| tantivy                        | 0.25.1          | UNKNOWN                                                                                          | UNKNOWN                                                                                           |
 | threadpoolctl                  | 3.6.0           | BSD License                                                                                      | https://github.com/joblib/threadpoolctl                                                           |
 | timm                           | 1.0.24          | Apache Software License                                                                          | https://github.com/huggingface/pytorch-image-models                                               |
 | tinycss2                       | 1.4.0           | BSD License                                                                                      | https://www.courtbouillon.org/tinycss2                                                            |

python/pyproject.toml

@@ -57,7 +57,6 @@ tests = [
     "duckdb>=0.9.0",
     "pytz>=2023.3",
     "polars>=0.19, <=1.3.0",
-    "tantivy>=0.20.0",
     "pyarrow-stubs>=16.0",
     "pylance>=5.0.0b5",
     "requests>=2.31.0",

python/python/lancedb/__init__.py

@@ -110,7 +110,7 @@ def connect(
         default configuration is used.
     storage_options: dict, optional
         Additional options for the storage backend. See available options at
-        <https://lancedb.com/docs/storage/>
+        <https://docs.lancedb.com/storage/>
     session: Session, optional
         (For LanceDB OSS only)
         A session to use for this connection. Sessions allow you to configure
@@ -215,6 +215,85 @@ def connect(
     )
 
 
+WORKER_PROPERTY_PREFIX = "_lancedb_worker_"
+
+
+def _apply_worker_overrides(props: dict[str, str]) -> dict[str, str]:
+    """Apply worker property overrides.
+
+    Any key starting with ``_lancedb_worker_`` is extracted, the prefix
+    is stripped, and the resulting key-value pair is put back into the
+    map (overriding the existing value if present).  The original
+    prefixed key is removed.
+    """
+    worker_keys = [k for k in props if k.startswith(WORKER_PROPERTY_PREFIX)]
+    if not worker_keys:
+        return props
+    result = dict(props)
+    for key in worker_keys:
+        value = result.pop(key)
+        real_key = key[len(WORKER_PROPERTY_PREFIX) :]
+        result[real_key] = value
+    return result
+
+
+def deserialize_conn(
+    data: str,
+    *,
+    for_worker: bool = False,
+) -> DBConnection:
+    """Reconstruct a DBConnection from a serialized string.
+
+    The string must have been produced by
+    :meth:`DBConnection.serialize`.
+
+    Parameters
+    ----------
+    data : str
+        String produced by ``serialize()``.
+    for_worker : bool, default False
+        When ``True``, any namespace client property whose key starts
+        with ``_lancedb_worker_`` has that prefix stripped and the
+        value overrides the corresponding property.  For example,
+        ``_lancedb_worker_uri`` replaces ``uri``.
+
+    Returns
+    -------
+    DBConnection
+        A new connection matching the serialized state.
+    """
+    import json
+
+    parsed = json.loads(data)
+    connection_type = parsed.get("connection_type")
+
+    rci_secs = parsed.get("read_consistency_interval_seconds")
+    rci = timedelta(seconds=rci_secs) if rci_secs is not None else None
+    storage_options = parsed.get("storage_options")
+
+    if connection_type == "namespace":
+        props = dict(parsed.get("namespace_client_properties") or {})
+        if for_worker:
+            props = _apply_worker_overrides(props)
+        return connect_namespace(
+            namespace_client_impl=parsed["namespace_client_impl"],
+            namespace_client_properties=props,
+            read_consistency_interval=rci,
+            storage_options=storage_options,
+            namespace_client_pushdown_operations=parsed.get(
+                "namespace_client_pushdown_operations"
+            ),
+        )
+    elif connection_type == "local":
+        return LanceDBConnection(
+            parsed["uri"],
+            read_consistency_interval=rci,
+            storage_options=storage_options,
+        )
+    else:
+        raise ValueError(f"Unknown connection_type: {connection_type}")
+
+
 async def connect_async(
     uri: URI,
     *,
@@ -257,7 +336,7 @@ async def connect_async(
         default configuration is used.
     storage_options: dict, optional
         Additional options for the storage backend. See available options at
-        <https://lancedb.com/docs/storage/>
+        <https://docs.lancedb.com/storage/>
     session: Session, optional
         (For LanceDB OSS only)
         A session to use for this connection. Sessions allow you to configure

python/python/lancedb/common.py

@@ -96,7 +96,7 @@ def data_to_reader(
             f"Unknown data type {type(data)}. "
             "Supported types: list of dicts, pandas DataFrame, polars DataFrame, "
             "pyarrow Table/RecordBatch, or Pydantic models. "
-            "See https://lancedb.com/docs/tables/ for examples."
+            "See https://docs.lancedb.com/tables/ for examples."
         )
 
 

python/python/lancedb/db.py

@@ -282,7 +282,7 @@ class DBConnection(EnforceOverrides):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.com/docs/storage/>
+            <https://docs.lancedb.com/storage/>
 
             To enable stable row IDs (row IDs remain stable after compaction,
             update, delete, and merges), set `new_table_enable_stable_row_ids`
@@ -433,7 +433,7 @@ class DBConnection(EnforceOverrides):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.com/docs/storage/>
+            <https://docs.lancedb.com/storage/>
 
         Returns
         -------
@@ -529,6 +529,19 @@ class DBConnection(EnforceOverrides):
             "namespace_client is not supported for this connection type"
         )
 
+    def serialize(self) -> str:
+        """Serialize this connection for reconstruction.
+
+        The returned string can be passed to :func:`lancedb.deserialize_conn`
+        to recreate an equivalent connection, e.g. in a remote worker.
+
+        Returns
+        -------
+        str
+            Serialized representation of this connection.
+        """
+        raise NotImplementedError("serialize is not supported for this connection type")
+
 
 class LanceDBConnection(DBConnection):
     """
@@ -581,6 +594,7 @@ class LanceDBConnection(DBConnection):
     ):
         if _inner is not None:
             self._conn = _inner
+            self._cached_namespace_client = None
             return
 
         if not isinstance(uri, Path):
@@ -628,6 +642,7 @@ class LanceDBConnection(DBConnection):
         # beyond _conn.
         self.storage_options = storage_options
         self._conn = AsyncConnection(LOOP.run(do_connect()))
+        self._cached_namespace_client: Optional[LanceNamespace] = None
 
     @property
     def read_consistency_interval(self) -> Optional[timedelta]:
@@ -652,6 +667,22 @@ class LanceDBConnection(DBConnection):
         val += ")"
         return val
 
+    @override
+    def serialize(self) -> str:
+        import json
+
+        rci = self.read_consistency_interval
+        return json.dumps(
+            {
+                "connection_type": "local",
+                "uri": self.uri,
+                "storage_options": self.storage_options,
+                "read_consistency_interval_seconds": (
+                    rci.total_seconds() if rci else None
+                ),
+            }
+        )
+
     async def _async_get_table_names(self, start_after: Optional[str], limit: int):
         conn = AsyncConnection(await lancedb_connect(self.uri))
         return await conn.table_names(start_after=start_after, limit=limit)
@@ -687,10 +718,10 @@ class LanceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
-        return LOOP.run(
-            self._conn.list_namespaces(
-                namespace_path=namespace_path, page_token=page_token, limit=limit
-            )
+        return self._namespace_conn().list_namespaces(
+            namespace_path=namespace_path,
+            page_token=page_token,
+            limit=limit,
         )
 
     @override
@@ -700,27 +731,10 @@ class LanceDBConnection(DBConnection):
         mode: Optional[str] = None,
         properties: Optional[Dict[str, str]] = None,
     ) -> CreateNamespaceResponse:
-        """Create a new namespace.
-
-        Parameters
-        ----------
-        namespace_path: List[str]
-            The namespace identifier to create.
-        mode: str, optional
-            Creation mode - "create" (fail if exists), "exist_ok" (skip if exists),
-            or "overwrite" (replace if exists). Case insensitive.
-        properties: Dict[str, str], optional
-            Properties to set on the namespace.
-
-        Returns
-        -------
-        CreateNamespaceResponse
-            Response containing the properties of the created namespace.
-        """
-        return LOOP.run(
-            self._conn.create_namespace(
-                namespace_path=namespace_path, mode=mode, properties=properties
-            )
+        return self._namespace_conn().create_namespace(
+            namespace_path=namespace_path,
+            mode=mode,
+            properties=properties,
         )
 
     @override
@@ -730,46 +744,19 @@ class LanceDBConnection(DBConnection):
         mode: Optional[str] = None,
         behavior: Optional[str] = None,
     ) -> DropNamespaceResponse:
-        """Drop a namespace.
-
-        Parameters
-        ----------
-        namespace_path: List[str]
-            The namespace identifier to drop.
-        mode: str, optional
-            Whether to skip if not exists ("SKIP") or fail ("FAIL"). Case insensitive.
-        behavior: str, optional
-            Whether to restrict drop if not empty ("RESTRICT") or cascade ("CASCADE").
-            Case insensitive.
-
-        Returns
-        -------
-        DropNamespaceResponse
-            Response containing properties and transaction_id if applicable.
-        """
-        return LOOP.run(
-            self._conn.drop_namespace(
-                namespace_path=namespace_path, mode=mode, behavior=behavior
-            )
+        return self._namespace_conn().drop_namespace(
+            namespace_path=namespace_path,
+            mode=mode,
+            behavior=behavior,
         )
 
     @override
     def describe_namespace(
         self, namespace_path: List[str]
     ) -> DescribeNamespaceResponse:
-        """Describe a namespace.
-
-        Parameters
-        ----------
-        namespace_path: List[str]
-            The namespace identifier to describe.
-
-        Returns
-        -------
-        DescribeNamespaceResponse
-            Response containing the namespace properties.
-        """
-        return LOOP.run(self._conn.describe_namespace(namespace_path=namespace_path))
+        return self._namespace_conn().describe_namespace(
+            namespace_path=namespace_path,
+        )
 
     @override
     def list_tables(
@@ -798,6 +785,12 @@ class LanceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
+        if namespace_path:
+            return self._namespace_conn().list_tables(
+                namespace_path=namespace_path,
+                page_token=page_token,
+                limit=limit,
+            )
         return LOOP.run(
             self._conn.list_tables(
                 namespace_path=namespace_path, page_token=page_token, limit=limit
@@ -886,6 +879,22 @@ class LanceDBConnection(DBConnection):
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
 
+        if namespace_path:
+            return self._namespace_conn().create_table(
+                name,
+                data=data,
+                schema=schema,
+                mode=mode,
+                exist_ok=exist_ok,
+                on_bad_vectors=on_bad_vectors,
+                fill_value=fill_value,
+                embedding_functions=embedding_functions,
+                namespace_path=namespace_path,
+                storage_options=storage_options,
+                data_storage_version=data_storage_version,
+                enable_v2_manifest_paths=enable_v2_manifest_paths,
+            )
+
         tbl = LanceTable.create(
             self,
             name,
@@ -901,6 +910,19 @@ class LanceDBConnection(DBConnection):
         )
         return tbl
 
+    def _namespace_conn(self) -> DBConnection:
+        """Return a LanceNamespaceDBConnection backed by this connection's
+        directory namespace.  Used to delegate child-namespace operations."""
+        from lancedb.namespace import LanceNamespaceDBConnection
+
+        return LanceNamespaceDBConnection(
+            self.namespace_client(),
+            read_consistency_interval=self.read_consistency_interval,
+            storage_options=self.storage_options,
+            namespace_client_impl=None,
+            namespace_client_properties=None,
+        )
+
     @override
     def open_table(
         self,
@@ -917,7 +939,8 @@ class LanceDBConnection(DBConnection):
         name: str
             The name of the table.
         namespace_path: List[str], optional
-            The namespace to open the table from.
+            The namespace to open the table from.  When non-empty, the
+            table is resolved through the directory namespace client.
 
         Returns
         -------
@@ -936,6 +959,14 @@ class LanceDBConnection(DBConnection):
                 stacklevel=2,
             )
 
+        if namespace_path:
+            return self._namespace_conn().open_table(
+                name,
+                namespace_path=namespace_path,
+                storage_options=storage_options,
+                index_cache_size=index_cache_size,
+            )
+
         return LanceTable.open(
             self,
             name,
@@ -1020,6 +1051,9 @@ class LanceDBConnection(DBConnection):
         """
         if namespace_path is None:
             namespace_path = []
+        if namespace_path:
+            self._namespace_conn().drop_table(name, namespace_path=namespace_path)
+            return
         LOOP.run(
             self._conn.drop_table(
                 name, namespace_path=namespace_path, ignore_missing=ignore_missing
@@ -1071,14 +1105,17 @@ class LanceDBConnection(DBConnection):
         """Get the equivalent namespace client for this connection.
 
         Returns a DirectoryNamespace pointing to the same root with the
-        same storage options.
+        same storage options.  The result is cached for the lifetime of
+        this connection.
 
         Returns
         -------
         LanceNamespace
             The namespace client for this connection.
         """
-        return LOOP.run(self._conn.namespace_client())
+        if self._cached_namespace_client is None:
+            self._cached_namespace_client = LOOP.run(self._conn.namespace_client())
+        return self._cached_namespace_client
 
     @deprecation.deprecated(
         deprecated_in="0.15.1",
@@ -1353,6 +1390,7 @@ class AsyncConnection(object):
         namespace_path: Optional[List[str]] = None,
         embedding_functions: Optional[List[EmbeddingFunctionConfig]] = None,
         location: Optional[str] = None,
+        namespace_client: Optional[Any] = None,
     ) -> AsyncTable:
         """Create an [AsyncTable][lancedb.table.AsyncTable] in the database.
 
@@ -1397,7 +1435,7 @@ class AsyncConnection(object):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.com/docs/storage/>
+            <https://docs.lancedb.com/storage/>
 
             To enable stable row IDs (row IDs remain stable after compaction,
             update, delete, and merges), set `new_table_enable_stable_row_ids`
@@ -1550,6 +1588,7 @@ class AsyncConnection(object):
                 namespace_path=namespace_path,
                 storage_options=storage_options,
                 location=location,
+                namespace_client=namespace_client,
             )
         else:
             data = data_to_reader(data, schema)
@@ -1560,6 +1599,7 @@ class AsyncConnection(object):
                 namespace_path=namespace_path,
                 storage_options=storage_options,
                 location=location,
+                namespace_client=namespace_client,
             )
 
         return AsyncTable(new_table)
@@ -1588,7 +1628,7 @@ class AsyncConnection(object):
             Additional options for the storage backend. Options already set on the
             connection will be inherited by the table, but can be overridden here.
             See available options at
-            <https://lancedb.com/docs/storage/>
+            <https://docs.lancedb.com/storage/>
         index_cache_size: int, default 256
             **Deprecated**: Use session-level cache configuration instead.
             Create a Session with custom cache sizes and pass it to lancedb.connect().

python/python/lancedb/fts.py

@@ -1,201 +0,0 @@
-# SPDX-License-Identifier: Apache-2.0
-# SPDX-FileCopyrightText: Copyright The LanceDB Authors
-
-"""Full text search index using tantivy-py"""
-
-import os
-from typing import List, Tuple, Optional
-
-import pyarrow as pa
-
-try:
-    import tantivy
-except ImportError:
-    raise ImportError(
-        "Please install tantivy-py `pip install tantivy` to use the full text search feature."  # noqa: E501
-    )
-
-from .table import LanceTable
-
-
-def create_index(
-    index_path: str,
-    text_fields: List[str],
-    ordering_fields: Optional[List[str]] = None,
-    tokenizer_name: str = "default",
-) -> tantivy.Index:
-    """
-    Create a new Index (not populated)
-
-    Parameters
-    ----------
-    index_path : str
-        Path to the index directory
-    text_fields : List[str]
-        List of text fields to index
-    ordering_fields: List[str]
-        List of unsigned type fields to order by at search time
-    tokenizer_name : str, default "default"
-        The tokenizer to use
-
-    Returns
-    -------
-    index : tantivy.Index
-        The index object (not yet populated)
-    """
-    if ordering_fields is None:
-        ordering_fields = []
-    # Declaring our schema.
-    schema_builder = tantivy.SchemaBuilder()
-    # special field that we'll populate with row_id
-    schema_builder.add_integer_field("doc_id", stored=True)
-    # data fields
-    for name in text_fields:
-        schema_builder.add_text_field(name, stored=True, tokenizer_name=tokenizer_name)
-    if ordering_fields:
-        for name in ordering_fields:
-            schema_builder.add_unsigned_field(name, fast=True)
-    schema = schema_builder.build()
-    os.makedirs(index_path, exist_ok=True)
-    index = tantivy.Index(schema, path=index_path)
-    return index
-
-
-def populate_index(
-    index: tantivy.Index,
-    table: LanceTable,
-    fields: List[str],
-    writer_heap_size: Optional[int] = None,
-    ordering_fields: Optional[List[str]] = None,
-) -> int:
-    """
-    Populate an index with data from a LanceTable
-
-    Parameters
-    ----------
-    index : tantivy.Index
-        The index object
-    table : LanceTable
-        The table to index
-    fields : List[str]
-        List of fields to index
-    writer_heap_size : int
-        The writer heap size in bytes, defaults to 1GB
-
-    Returns
-    -------
-    int
-        The number of rows indexed
-    """
-    if ordering_fields is None:
-        ordering_fields = []
-    writer_heap_size = writer_heap_size or 1024 * 1024 * 1024
-    # first check the fields exist and are string or large string type
-    nested = []
-
-    for name in fields:
-        try:
-            f = table.schema.field(name)  # raises KeyError if not found
-        except KeyError:
-            f = resolve_path(table.schema, name)
-            nested.append(name)
-
-        if not pa.types.is_string(f.type) and not pa.types.is_large_string(f.type):
-            raise TypeError(f"Field {name} is not a string type")
-
-    # create a tantivy writer
-    writer = index.writer(heap_size=writer_heap_size)
-    # write data into index
-    dataset = table.to_lance()
-    row_id = 0
-
-    max_nested_level = 0
-    if len(nested) > 0:
-        max_nested_level = max([len(name.split(".")) for name in nested])
-
-    for b in dataset.to_batches(columns=fields + ordering_fields):
-        if max_nested_level > 0:
-            b = pa.Table.from_batches([b])
-            for _ in range(max_nested_level - 1):
-                b = b.flatten()
-        for i in range(b.num_rows):
-            doc = tantivy.Document()
-            for name in fields:
-                value = b[name][i].as_py()
-                if value is not None:
-                    doc.add_text(name, value)
-            for name in ordering_fields:
-                value = b[name][i].as_py()
-                if value is not None:
-                    doc.add_unsigned(name, value)
-            if not doc.is_empty:
-                doc.add_integer("doc_id", row_id)
-                writer.add_document(doc)
-            row_id += 1
-    # commit changes
-    writer.commit()
-    return row_id
-
-
-def resolve_path(schema, field_name: str) -> pa.Field:
-    """
-    Resolve a nested field path to a list of field names
-
-    Parameters
-    ----------
-    field_name : str
-        The field name to resolve
-
-    Returns
-    -------
-    List[str]
-        The resolved path
-    """
-    path = field_name.split(".")
-    field = schema.field(path.pop(0))
-    for segment in path:
-        if pa.types.is_struct(field.type):
-            field = field.type.field(segment)
-        else:
-            raise KeyError(f"field {field_name} not found in schema {schema}")
-    return field
-
-
-def search_index(
-    index: tantivy.Index, query: str, limit: int = 10, ordering_field=None
-) -> Tuple[Tuple[int], Tuple[float]]:
-    """
-    Search an index for a query
-
-    Parameters
-    ----------
-    index : tantivy.Index
-        The index object
-    query : str
-        The query string
-    limit : int
-        The maximum number of results to return
-
-    Returns
-    -------
-    ids_and_score: list[tuple[int], tuple[float]]
-        A tuple of two tuples, the first containing the document ids
-        and the second containing the scores
-    """
-    searcher = index.searcher()
-    query = index.parse_query(query)
-    # get top results
-    if ordering_field:
-        results = searcher.search(query, limit, order_by_field=ordering_field)
-    else:
-        results = searcher.search(query, limit)
-    if results.count == 0:
-        return tuple(), tuple()
-    return tuple(
-        zip(
-            *[
-                (searcher.doc(doc_address)["doc_id"][0], score)
-                for score, doc_address in results.hits
-            ]
-        )
-    )

python/python/lancedb/namespace.py

@@ -10,7 +10,6 @@ through a namespace abstraction.
 
 from __future__ import annotations
 
-import asyncio
 import sys
 from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Union
 
@@ -25,7 +24,24 @@ if TYPE_CHECKING:
 from datetime import timedelta
 import pyarrow as pa
 
-from lancedb.db import DBConnection, LanceDBConnection
+from lance_namespace_urllib3_client.models.json_arrow_data_type import JsonArrowDataType
+from lance_namespace_urllib3_client.models.json_arrow_field import JsonArrowField
+from lance_namespace_urllib3_client.models.json_arrow_schema import JsonArrowSchema
+from lance_namespace_urllib3_client.models.query_table_request import QueryTableRequest
+from lance_namespace_urllib3_client.models.query_table_request_columns import (
+    QueryTableRequestColumns,
+)
+from lance_namespace_urllib3_client.models.query_table_request_full_text_query import (
+    QueryTableRequestFullTextQuery,
+)
+from lance_namespace_urllib3_client.models.query_table_request_vector import (
+    QueryTableRequestVector,
+)
+from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
+from lance_namespace.errors import TableNotFoundError
+from lancedb._lancedb import connect_namespace_client as _connect_namespace_client
+from lancedb.background_loop import LOOP
+from lancedb.db import AsyncConnection, DBConnection
 from lancedb.namespace_utils import (
     _normalize_create_namespace_mode,
     _normalize_drop_namespace_mode,
@@ -40,14 +56,11 @@ from lance_namespace import (
     ListNamespacesResponse,
     ListTablesResponse,
     ListTablesRequest,
-    DescribeTableRequest,
     DescribeNamespaceRequest,
     DropTableRequest,
     ListNamespacesRequest,
     CreateNamespaceRequest,
     DropNamespaceRequest,
-    DeclareTableRequest,
-    CreateTableRequest,
 )
 from lancedb.table import AsyncTable, LanceTable, Table
 from lancedb.util import validate_table_name
@@ -56,21 +69,6 @@ from lancedb.pydantic import LanceModel
 from lancedb.embeddings import EmbeddingFunctionConfig
 from ._lancedb import Session
 
-from lance_namespace_urllib3_client.models.json_arrow_schema import JsonArrowSchema
-from lance_namespace_urllib3_client.models.json_arrow_field import JsonArrowField
-from lance_namespace_urllib3_client.models.json_arrow_data_type import JsonArrowDataType
-from lance_namespace_urllib3_client.models.query_table_request import QueryTableRequest
-from lance_namespace_urllib3_client.models.query_table_request_vector import (
-    QueryTableRequestVector,
-)
-from lance_namespace_urllib3_client.models.query_table_request_columns import (
-    QueryTableRequestColumns,
-)
-from lance_namespace_urllib3_client.models.query_table_request_full_text_query import (
-    QueryTableRequestFullTextQuery,
-)
-from lance_namespace_urllib3_client.models.string_fts_query import StringFtsQuery
-
 
 def _query_to_namespace_request(
     table_id: List[str],
@@ -381,6 +379,8 @@ class LanceNamespaceDBConnection(DBConnection):
         storage_options: Optional[Dict[str, str]] = None,
         session: Optional[Session] = None,
         namespace_client_pushdown_operations: Optional[List[str]] = None,
+        namespace_client_impl: Optional[str] = None,
+        namespace_client_properties: Optional[Dict[str, str]] = None,
     ):
         """
         Initialize a namespace-based LanceDB connection.
@@ -406,12 +406,60 @@ class LanceNamespaceDBConnection(DBConnection):
               namespace.create_table() instead of using declare_table + local write.
 
             Default is None (no pushdown, all operations run locally).
+        namespace_client_impl : Optional[str]
+            The namespace implementation name used to create this connection.
+            Stored for serialization purposes.
+        namespace_client_properties : Optional[Dict[str, str]]
+            The namespace properties used to create this connection.
+            Stored for serialization purposes.
         """
         self._namespace_client = namespace_client
         self.read_consistency_interval = read_consistency_interval
         self.storage_options = storage_options or {}
         self.session = session
-        self._pushdown_operations = set(namespace_client_pushdown_operations or [])
+        self._namespace_client_pushdown_operations = set(
+            namespace_client_pushdown_operations or []
+        )
+        self._namespace_client_impl = namespace_client_impl
+        self._namespace_client_properties = namespace_client_properties
+        self._inner = AsyncConnection(
+            _connect_namespace_client(
+                namespace_client,
+                read_consistency_interval=(
+                    read_consistency_interval.total_seconds()
+                    if read_consistency_interval is not None
+                    else None
+                ),
+                storage_options=self.storage_options or None,
+                session=session,
+                namespace_client_pushdown_operations=(
+                    list(self._namespace_client_pushdown_operations)
+                ),
+                namespace_client_impl=namespace_client_impl,
+                namespace_client_properties=namespace_client_properties,
+            )
+        )
+
+    @override
+    def serialize(self) -> str:
+        import json
+
+        return json.dumps(
+            {
+                "connection_type": "namespace",
+                "namespace_client_impl": self._namespace_client_impl,
+                "namespace_client_properties": self._namespace_client_properties,
+                "namespace_client_pushdown_operations": sorted(
+                    self._namespace_client_pushdown_operations
+                ),
+                "storage_options": self.storage_options or None,
+                "read_consistency_interval_seconds": (
+                    self.read_consistency_interval.total_seconds()
+                    if self.read_consistency_interval
+                    else None
+                ),
+            }
+        )
 
     @override
     def table_names(
@@ -464,13 +512,10 @@ class LanceNamespaceDBConnection(DBConnection):
         if mode.lower() not in ["create", "overwrite"]:
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
-
-        table_id = namespace_path + [name]
-
-        if "CreateTable" in self._pushdown_operations:
-            return self._create_table_server_side(
-                name=name,
-                data=data,
+        async_table = LOOP.run(
+            self._inner.create_table(
+                name,
+                data,
                 schema=schema,
                 mode=mode,
                 exist_ok=exist_ok,
@@ -480,127 +525,15 @@ class LanceNamespaceDBConnection(DBConnection):
                 namespace_path=namespace_path,
                 storage_options=storage_options,
             )
-
-        # Local create path: declare_table + local write
-        # Step 1: Get the table location and storage options from namespace
-        # In overwrite mode, if table exists, use describe_table to get
-        # existing location. Otherwise, call create_empty_table to reserve
-        # a new location
-        location = None
-        namespace_storage_options = None
-        if mode.lower() == "overwrite":
-            # Try to describe the table first to see if it exists
-            try:
-                describe_request = DescribeTableRequest(id=table_id)
-                describe_response = self._namespace_client.describe_table(
-                    describe_request
-                )
-                location = describe_response.location
-                namespace_storage_options = describe_response.storage_options
-            except Exception:
-                # Table doesn't exist, will create a new one below
-                pass
-
-        if location is None:
-            # Table doesn't exist or mode is "create", reserve a new location
-            declare_request = DeclareTableRequest(
-                id=table_id,
-                location=None,
-                properties=self.storage_options if self.storage_options else None,
-            )
-            declare_response = self._namespace_client.declare_table(declare_request)
-
-            if not declare_response.location:
-                raise ValueError(
-                    "Table location is missing from declare_table response"
-                )
-
-            location = declare_response.location
-            namespace_storage_options = declare_response.storage_options
-
-        # Merge storage options: self.storage_options < user options < namespace options
-        merged_storage_options = dict(self.storage_options)
-        if storage_options:
-            merged_storage_options.update(storage_options)
-        if namespace_storage_options:
-            merged_storage_options.update(namespace_storage_options)
-
-        # Step 2: Create table using LanceTable.create with the location
-        # We need a temporary connection for the LanceTable.create method
-        temp_conn = LanceDBConnection(
-            location,  # Use the actual location as the connection URI
-            read_consistency_interval=self.read_consistency_interval,
-            storage_options=merged_storage_options,
-            session=self.session,
         )
 
-        # Note: storage_options_provider is auto-created in Rust from namespace_client
-        tbl = LanceTable.create(
-            temp_conn,
+        return LanceTable(
+            self,
             name,
-            data,
-            schema,
-            mode=mode,
-            exist_ok=exist_ok,
-            on_bad_vectors=on_bad_vectors,
-            fill_value=fill_value,
-            embedding_functions=embedding_functions,
             namespace_path=namespace_path,
-            storage_options=merged_storage_options,
-            location=location,
             namespace_client=self._namespace_client,
-            pushdown_operations=self._pushdown_operations,
-        )
-
-        return tbl
-
-    def _create_table_server_side(
-        self,
-        name: str,
-        data: Optional[DATA],
-        schema: Optional[Union[pa.Schema, LanceModel]],
-        mode: str,
-        exist_ok: bool,
-        on_bad_vectors: str,
-        fill_value: float,
-        embedding_functions: Optional[List[EmbeddingFunctionConfig]],
-        namespace_path: Optional[List[str]],
-        storage_options: Optional[Dict[str, str]],
-    ) -> Table:
-        """Create a table using server-side namespace.create_table()."""
-        if namespace_path is None:
-            namespace_path = []
-        table_id = namespace_path + [name]
-
-        arrow_ipc_bytes = _data_to_arrow_ipc(
-            data=data,
-            schema=schema,
-            embedding_functions=embedding_functions,
-            on_bad_vectors=on_bad_vectors,
-            fill_value=fill_value,
-        )
-
-        request = CreateTableRequest(
-            id=table_id,
-            mode=_normalize_create_table_mode(mode),
-            properties=self.storage_options if self.storage_options else None,
-        )
-
-        try:
-            self._namespace_client.create_table(request, arrow_ipc_bytes)
-        except Exception as e:
-            if exist_ok and "already exists" in str(e).lower():
-                return self.open_table(
-                    name,
-                    namespace_path=namespace_path,
-                    storage_options=storage_options,
-                )
-            raise
-
-        return self.open_table(
-            name,
-            namespace_path=namespace_path,
-            storage_options=storage_options,
+            pushdown_operations=self._namespace_client_pushdown_operations,
+            _async=async_table,
         )
 
     @override
@@ -614,30 +547,28 @@ class LanceNamespaceDBConnection(DBConnection):
     ) -> Table:
         if namespace_path is None:
             namespace_path = []
-        table_id = namespace_path + [name]
-        request = DescribeTableRequest(id=table_id)
-        response = self._namespace_client.describe_table(request)
+        try:
+            async_table = LOOP.run(
+                self._inner.open_table(
+                    name,
+                    namespace_path=namespace_path,
+                    storage_options=storage_options,
+                    index_cache_size=index_cache_size,
+                )
+            )
+        except RuntimeError as e:
+            if "Table not found" in str(e):
+                table_id = namespace_path + [name]
+                raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
+            raise
 
-        # Merge storage options: self.storage_options < user options < namespace options
-        merged_storage_options = dict(self.storage_options)
-        if storage_options:
-            merged_storage_options.update(storage_options)
-        if response.storage_options:
-            merged_storage_options.update(response.storage_options)
-
-        # Pass managed_versioning to avoid redundant describe_table call in Rust.
-        # Convert None to False since we already have the answer from describe_table.
-        managed_versioning = response.managed_versioning is True
-
-        # Note: storage_options_provider is auto-created in Rust from namespace_client
-        return self._lance_table_from_uri(
+        return LanceTable(
+            self,
             name,
-            response.location,
             namespace_path=namespace_path,
-            storage_options=merged_storage_options,
-            index_cache_size=index_cache_size,
             namespace_client=self._namespace_client,
-            managed_versioning=managed_versioning,
+            pushdown_operations=self._namespace_client_pushdown_operations,
+            _async=async_table,
         )
 
     @override
@@ -861,33 +792,34 @@ class LanceNamespaceDBConnection(DBConnection):
         namespace_client: Optional[Any] = None,
         managed_versioning: Optional[bool] = None,
     ) -> LanceTable:
-        # Open a table directly from a URI using the location parameter
-        # Note: storage_options should already be merged by the caller
-        # Note: storage_options_provider is auto-created in Rust from namespace_client
+        # Open a table directly from the namespace-resolved physical location.
+        #
+        # Open the table through the Rust namespace-backed connection.  The Rust
+        # layer keeps the logical namespace path and namespace client intact.
         if namespace_path is None:
             namespace_path = []
-        temp_conn = LanceDBConnection(
-            table_uri,  # Use the table location as the connection URI
-            read_consistency_interval=self.read_consistency_interval,
-            storage_options=storage_options if storage_options is not None else {},
-            session=self.session,
+
+        async_table = LOOP.run(
+            self._inner.open_table(
+                name,
+                namespace_path=namespace_path,
+                storage_options=storage_options,
+                index_cache_size=index_cache_size,
+                location=None,
+                namespace_client=namespace_client,
+                managed_versioning=managed_versioning,
+            )
         )
 
-        # Open the table using the temporary connection with the location parameter
-        # Pass namespace_client to enable managed versioning support and auto-create
-        # storage options provider
-        # Pass managed_versioning to avoid redundant describe_table call
-        # Pass pushdown_operations if configured on this connection
-        return LanceTable.open(
-            temp_conn,
+        return LanceTable(
+            self,
             name,
             namespace_path=namespace_path,
-            storage_options=storage_options,
-            index_cache_size=index_cache_size,
             location=table_uri,
             namespace_client=namespace_client,
             managed_versioning=managed_versioning,
-            pushdown_operations=self._pushdown_operations,
+            pushdown_operations=self._namespace_client_pushdown_operations,
+            _async=async_table,
         )
 
     @override
@@ -951,7 +883,26 @@ class AsyncLanceNamespaceDBConnection:
         self.read_consistency_interval = read_consistency_interval
         self.storage_options = storage_options or {}
         self.session = session
-        self._pushdown_operations = set(namespace_client_pushdown_operations or [])
+        self._namespace_client_pushdown_operations = set(
+            namespace_client_pushdown_operations or []
+        )
+        self._inner = AsyncConnection(
+            _connect_namespace_client(
+                namespace_client,
+                read_consistency_interval=(
+                    read_consistency_interval.total_seconds()
+                    if read_consistency_interval is not None
+                    else None
+                ),
+                storage_options=self.storage_options or None,
+                session=session,
+                namespace_client_pushdown_operations=(
+                    list(self._namespace_client_pushdown_operations)
+                ),
+                namespace_client_impl=None,
+                namespace_client_properties=None,
+            )
+        )
 
     async def table_names(
         self,
@@ -1003,145 +954,16 @@ class AsyncLanceNamespaceDBConnection:
         if mode.lower() not in ["create", "overwrite"]:
             raise ValueError("mode must be either 'create' or 'overwrite'")
         validate_table_name(name)
-
-        table_id = namespace_path + [name]
-
-        if "CreateTable" in self._pushdown_operations:
-            return await self._create_table_server_side(
-                name=name,
-                data=data,
-                schema=schema,
-                mode=mode,
-                exist_ok=exist_ok,
-                on_bad_vectors=on_bad_vectors,
-                fill_value=fill_value,
-                embedding_functions=embedding_functions,
-                namespace_path=namespace_path,
-                storage_options=storage_options,
-            )
-
-        # Local create path: declare_table + local write
-        # Step 1: Get the table location and storage options from namespace
-        location = None
-        namespace_storage_options = None
-        if mode.lower() == "overwrite":
-            # Try to describe the table first to see if it exists
-            try:
-                describe_request = DescribeTableRequest(id=table_id)
-                describe_response = self._namespace_client.describe_table(
-                    describe_request
-                )
-                location = describe_response.location
-                namespace_storage_options = describe_response.storage_options
-            except Exception:
-                # Table doesn't exist, will create a new one below
-                pass
-
-        if location is None:
-            # Table doesn't exist or mode is "create", reserve a new location
-            declare_request = DeclareTableRequest(
-                id=table_id,
-                location=None,
-                properties=self.storage_options if self.storage_options else None,
-            )
-            declare_response = self._namespace_client.declare_table(declare_request)
-
-            if not declare_response.location:
-                raise ValueError(
-                    "Table location is missing from declare_table response"
-                )
-
-            location = declare_response.location
-            namespace_storage_options = declare_response.storage_options
-
-        # Merge storage options: self.storage_options < user options < namespace options
-        merged_storage_options = dict(self.storage_options)
-        if storage_options:
-            merged_storage_options.update(storage_options)
-        if namespace_storage_options:
-            merged_storage_options.update(namespace_storage_options)
-
-        # Step 2: Create table using LanceTable.create with the location
-        # Run the sync operation in a thread
-        def _create_table():
-            temp_conn = LanceDBConnection(
-                location,
-                read_consistency_interval=self.read_consistency_interval,
-                storage_options=merged_storage_options,
-                session=self.session,
-            )
-
-            # storage_options_provider is auto-created in Rust from namespace_client
-            return LanceTable.create(
-                temp_conn,
-                name,
-                data,
-                schema,
-                mode=mode,
-                exist_ok=exist_ok,
-                on_bad_vectors=on_bad_vectors,
-                fill_value=fill_value,
-                embedding_functions=embedding_functions,
-                namespace_path=namespace_path,
-                storage_options=merged_storage_options,
-                location=location,
-                namespace_client=self._namespace_client,
-                pushdown_operations=self._pushdown_operations,
-            )
-
-        lance_table = await asyncio.to_thread(_create_table)
-        # Get the underlying async table from LanceTable
-        return lance_table._table
-
-    async def _create_table_server_side(
-        self,
-        name: str,
-        data: Optional[DATA],
-        schema: Optional[Union[pa.Schema, LanceModel]],
-        mode: str,
-        exist_ok: bool,
-        on_bad_vectors: str,
-        fill_value: float,
-        embedding_functions: Optional[List[EmbeddingFunctionConfig]],
-        namespace_path: Optional[List[str]],
-        storage_options: Optional[Dict[str, str]],
-    ) -> AsyncTable:
-        """Create a table using server-side namespace.create_table()."""
-        if namespace_path is None:
-            namespace_path = []
-        table_id = namespace_path + [name]
-
-        def _prepare_and_create():
-            arrow_ipc_bytes = _data_to_arrow_ipc(
-                data=data,
-                schema=schema,
-                embedding_functions=embedding_functions,
-                on_bad_vectors=on_bad_vectors,
-                fill_value=fill_value,
-            )
-
-            request = CreateTableRequest(
-                id=table_id,
-                mode=_normalize_create_table_mode(mode),
-                properties=self.storage_options if self.storage_options else None,
-            )
-
-            self._namespace_client.create_table(request, arrow_ipc_bytes)
-
-        try:
-            await asyncio.to_thread(_prepare_and_create)
-        except Exception as e:
-            if exist_ok and "already exists" in str(e).lower():
-                return await self.open_table(
-                    name,
-                    namespace_path=namespace_path,
-                    storage_options=storage_options,
-                )
-            raise
-
-        return await self.open_table(
+        return await self._inner.create_table(
             name,
+            data,
+            schema=schema,
+            mode=mode,
+            exist_ok=exist_ok,
+            on_bad_vectors=on_bad_vectors,
+            fill_value=fill_value,
             namespace_path=namespace_path,
+            embedding_functions=embedding_functions,
             storage_options=storage_options,
         )
 
@@ -1156,45 +978,18 @@ class AsyncLanceNamespaceDBConnection:
         """Open an existing table from the namespace."""
         if namespace_path is None:
             namespace_path = []
-        table_id = namespace_path + [name]
-        request = DescribeTableRequest(id=table_id)
-        response = self._namespace_client.describe_table(request)
-
-        # Merge storage options: self.storage_options < user options < namespace options
-        merged_storage_options = dict(self.storage_options)
-        if storage_options:
-            merged_storage_options.update(storage_options)
-        if response.storage_options:
-            merged_storage_options.update(response.storage_options)
-
-        # Capture managed_versioning from describe response.
-        # Convert None to False since we already have the answer from describe_table.
-        managed_versioning = response.managed_versioning is True
-
-        # Open table in a thread
-        # Note: storage_options_provider is auto-created in Rust from namespace_client
-        def _open_table():
-            temp_conn = LanceDBConnection(
-                response.location,
-                read_consistency_interval=self.read_consistency_interval,
-                storage_options=merged_storage_options,
-                session=self.session,
-            )
-
-            return LanceTable.open(
-                temp_conn,
+        try:
+            return await self._inner.open_table(
                 name,
                 namespace_path=namespace_path,
-                storage_options=merged_storage_options,
+                storage_options=storage_options,
                 index_cache_size=index_cache_size,
-                location=response.location,
-                namespace_client=self._namespace_client,
-                managed_versioning=managed_versioning,
-                pushdown_operations=self._pushdown_operations,
             )
-
-        lance_table = await asyncio.to_thread(_open_table)
-        return lance_table._table
+        except RuntimeError as e:
+            if "Table not found" in str(e):
+                table_id = namespace_path + [name]
+                raise TableNotFoundError(f"Table not found: {'$'.join(table_id)}")
+            raise
 
     async def drop_table(self, name: str, namespace_path: Optional[List[str]] = None):
         """Drop a table from the namespace."""
@@ -1472,6 +1267,8 @@ def connect_namespace(
         storage_options=storage_options,
         session=session,
         namespace_client_pushdown_operations=namespace_client_pushdown_operations,
+        namespace_client_impl=namespace_client_impl,
+        namespace_client_properties=namespace_client_properties,
     )
 
 

python/python/lancedb/query.py

@@ -25,7 +25,6 @@ import deprecation
 import numpy as np
 import pyarrow as pa
 import pyarrow.compute as pc
-import pyarrow.fs as pa_fs
 import pydantic
 
 from lancedb.pydantic import PYDANTIC_VERSION
@@ -1526,9 +1525,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
         return self._table._output_schema(self.to_query_object())
 
     def to_arrow(self, *, timeout: Optional[timedelta] = None) -> pa.Table:
-        path, fs, exist = self._table._get_fts_index_path()
-        if exist:
-            return self.tantivy_to_arrow()
+        self._table._ensure_no_legacy_fts_index()
 
         query = self._query
         if self._phrase_query:
@@ -1552,90 +1549,6 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
     ):
         raise NotImplementedError("to_batches on an FTS query")
 
-    def tantivy_to_arrow(self) -> pa.Table:
-        try:
-            import tantivy
-        except ImportError:
-            raise ImportError(
-                "Please install tantivy-py `pip install tantivy` to use the full text search feature."  # noqa: E501
-            )
-
-        from .fts import search_index
-
-        # get the index path
-        path, fs, exist = self._table._get_fts_index_path()
-
-        # check if the index exist
-        if not exist:
-            raise FileNotFoundError(
-                "Fts index does not exist. "
-                "Please first call table.create_fts_index(['<field_names>']) to "
-                "create the fts index."
-            )
-
-        # Check that we are on local filesystem
-        if not isinstance(fs, pa_fs.LocalFileSystem):
-            raise NotImplementedError(
-                "Tantivy-based full text search "
-                "is only supported on the local filesystem"
-            )
-        # open the index
-        index = tantivy.Index.open(path)
-        # get the scores and doc ids
-        query = self._query
-        if self._phrase_query:
-            query = query.replace('"', "'")
-            query = f'"{query}"'
-        limit = self._limit if self._limit is not None else 10
-        row_ids, scores = search_index(
-            index, query, limit, ordering_field=self.ordering_field_name
-        )
-        if len(row_ids) == 0:
-            empty_schema = pa.schema([pa.field("_score", pa.float32())])
-            return pa.Table.from_batches([], schema=empty_schema)
-        scores = pa.array(scores)
-        output_tbl = self._table.to_lance().take(row_ids, columns=self._columns)
-        output_tbl = output_tbl.append_column("_score", scores)
-        # this needs to match vector search results which are uint64
-        row_ids = pa.array(row_ids, type=pa.uint64())
-
-        if self._where is not None:
-            tmp_name = "__lancedb__duckdb__indexer__"
-            output_tbl = output_tbl.append_column(
-                tmp_name, pa.array(range(len(output_tbl)))
-            )
-            try:
-                # TODO would be great to have Substrait generate pyarrow compute
-                # expressions or conversely have pyarrow support SQL expressions
-                # using Substrait
-                import duckdb
-
-                indexer = duckdb.sql(
-                    f"SELECT {tmp_name} FROM output_tbl WHERE {self._where}"
-                ).to_arrow_table()[tmp_name]
-                output_tbl = output_tbl.take(indexer).drop([tmp_name])
-                row_ids = row_ids.take(indexer)
-
-            except ImportError:
-                import tempfile
-
-                import lance
-
-                # TODO Use "memory://" instead once that's supported
-                with tempfile.TemporaryDirectory() as tmp:
-                    ds = lance.write_dataset(output_tbl, tmp)
-                    output_tbl = ds.to_table(filter=self._where)
-                    indexer = output_tbl[tmp_name]
-                    row_ids = row_ids.take(indexer)
-                    output_tbl = output_tbl.drop([tmp_name])
-
-        if self._with_row_id:
-            output_tbl = output_tbl.append_column("_rowid", row_ids)
-
-        if self._reranker is not None:
-            output_tbl = self._reranker.rerank_fts(self._query, output_tbl)
-        return output_tbl
-
     def rerank(self, reranker: Reranker) -> LanceFtsQueryBuilder:
         """Rerank the results using the specified reranker.
 

python/python/lancedb/table.py

@@ -191,7 +191,7 @@ def _into_pyarrow_reader(
             f"Unknown data type {type(data)}. "
             "Supported types: list of dicts, pandas DataFrame, polars DataFrame, "
             "pyarrow Table/RecordBatch, or Pydantic models. "
-            "See https://lancedb.com/docs/tables/ for examples."
+            "See https://docs.lancedb.com/tables/ for examples."
         )
 
 
@@ -943,29 +943,26 @@ class Table(ABC):
         Parameters
         ----------
         field_names: str or list of str
-            The name(s) of the field to index.
-            If ``use_tantivy`` is False (default), only a single field name
-            (str) is supported. To index multiple fields, create a separate
-            FTS index for each field.
+            The name of the field to index. Native FTS indexes can only be
+            created on a single field at a time. To search over multiple text
+            fields, create a separate FTS index for each field.
         replace: bool, default False
             If True, replace the existing index if it exists. Note that this is
             not yet an atomic operation; the index will be temporarily
             unavailable while the new index is being created.
         writer_heap_size: int, default 1GB
-            Only available with use_tantivy=True
+            Deprecated legacy Tantivy parameter. Any value other than the
+            default raises an error.
         ordering_field_names:
-            A list of unsigned type fields to index to optionally order
-            results on at search time.
-            only available with use_tantivy=True
+            Deprecated legacy Tantivy parameter. Setting this raises an error.
         tokenizer_name: str, default "default"
-            The tokenizer to use for the index. Can be "raw", "default" or the 2 letter
-            language code followed by "_stem". So for english it would be "en_stem".
-            For available languages see: https://docs.rs/tantivy/latest/tantivy/tokenizer/enum.Language.html
+            A compatibility alias for native tokenizer configs. Can be "raw",
+            "default" or the 2 letter language code followed by "_stem". So
+            for english it would be "en_stem".
         use_tantivy: bool, default False
-            If True, use the legacy full-text search implementation based on tantivy.
-            If False, use the new full-text search implementation based on lance-index.
+            Deprecated legacy Tantivy parameter. Setting this to True raises an
+            error.
         with_position: bool, default False
-            Only available with use_tantivy=False
             If False, do not store the positions of the terms in the text.
             This can reduce the size of the index and improve indexing speed.
             But it will raise an exception for phrase queries.
@@ -1746,6 +1743,16 @@ class Table(ABC):
         index_exists = fs.get_file_info(path).type != pa_fs.FileType.NotFound
         return (path, fs, index_exists)
 
+    def _ensure_no_legacy_fts_index(self):
+        path, _, exists = self._get_fts_index_path()
+        if exists:
+            raise ValueError(
+                "Legacy Tantivy FTS index detected at "
+                f"{path}. Tantivy-based FTS has been removed. "
+                "Delete the legacy index and recreate it with "
+                "table.create_fts_index(...)."
+            )
+
     @abstractmethod
     def uses_v2_manifest_paths(self) -> bool:
         """
@@ -2405,84 +2412,63 @@ class LanceTable(Table):
         prefix_only: bool = False,
         name: Optional[str] = None,
     ):
-        if not use_tantivy:
-            if not isinstance(field_names, str):
-                raise ValueError(
-                    "Native FTS indexes can only be created on a single field "
-                    "at a time. To search over multiple text fields, create a "
-                    "separate FTS index for each field."
-                )
+        self._ensure_no_legacy_fts_index()
 
-            if tokenizer_name is None:
-                tokenizer_configs = {
-                    "base_tokenizer": base_tokenizer,
-                    "language": language,
-                    "with_position": with_position,
-                    "max_token_length": max_token_length,
-                    "lower_case": lower_case,
-                    "stem": stem,
-                    "remove_stop_words": remove_stop_words,
-                    "ascii_folding": ascii_folding,
-                    "ngram_min_length": ngram_min_length,
-                    "ngram_max_length": ngram_max_length,
-                    "prefix_only": prefix_only,
-                }
-            else:
-                tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
-
-            config = FTS(
-                **tokenizer_configs,
+        if use_tantivy:
+            raise ValueError(
+                "Tantivy-based FTS has been removed. "
+                "Remove use_tantivy and recreate the index with native FTS."
             )
-
-            # delete the existing legacy index if it exists
-            if replace:
-                path, fs, exist = self._get_fts_index_path()
-                if exist:
-                    fs.delete_dir(path)
-
-            LOOP.run(
-                self._table.create_index(
-                    field_names,
-                    replace=replace,
-                    config=config,
-                    name=name,
-                )
+        if ordering_field_names is not None:
+            raise ValueError(
+                "ordering_field_names was only supported by the removed "
+                "Tantivy-based FTS implementation."
             )
-            return
-
-        from .fts import create_index, populate_index
-
-        if isinstance(field_names, str):
-            field_names = [field_names]
-
-        if isinstance(ordering_field_names, str):
-            ordering_field_names = [ordering_field_names]
-
-        path, fs, exist = self._get_fts_index_path()
-        if exist:
-            if not replace:
-                raise ValueError("Index already exists. Use replace=True to overwrite.")
-            fs.delete_dir(path)
-
-        if not isinstance(fs, pa_fs.LocalFileSystem):
-            raise NotImplementedError(
-                "Full-text search is only supported on the local filesystem"
+        if writer_heap_size != 1024 * 1024 * 1024:
+            raise ValueError(
+                "writer_heap_size was only supported by the removed "
+                "Tantivy-based FTS implementation."
+            )
+        if not isinstance(field_names, str):
+            raise ValueError(
+                "Native FTS indexes can only be created on a single field "
+                "at a time. To search over multiple text fields, create a "
+                "separate FTS index for each field."
+            )
+        if "." in field_names:
+            raise ValueError(
+                "Native FTS indexes can only be created on top-level fields. "
+                f"Received nested field path: {field_names!r}."
             )
 
         if tokenizer_name is None:
-            tokenizer_name = "default"
-        index = create_index(
-            path,
-            field_names,
-            ordering_fields=ordering_field_names,
-            tokenizer_name=tokenizer_name,
+            tokenizer_configs = {
+                "base_tokenizer": base_tokenizer,
+                "language": language,
+                "with_position": with_position,
+                "max_token_length": max_token_length,
+                "lower_case": lower_case,
+                "stem": stem,
+                "remove_stop_words": remove_stop_words,
+                "ascii_folding": ascii_folding,
+                "ngram_min_length": ngram_min_length,
+                "ngram_max_length": ngram_max_length,
+                "prefix_only": prefix_only,
+            }
+        else:
+            tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
+
+        config = FTS(
+            **tokenizer_configs,
         )
-        populate_index(
-            index,
-            self,
-            field_names,
-            ordering_fields=ordering_field_names,
-            writer_heap_size=writer_heap_size,
+
+        LOOP.run(
+            self._table.create_index(
+                field_names,
+                replace=replace,
+                config=config,
+                name=name,
+            )
         )
 
     @staticmethod
@@ -2929,6 +2915,7 @@ class LanceTable(Table):
                 namespace_path=namespace_path,
                 storage_options=storage_options,
                 location=location,
+                namespace_client=namespace_client,
             )
         )
         return self

python/python/tests/docs/test_search.py

@@ -180,7 +180,7 @@ def test_fts_fuzzy_query():
         ),
         mode="overwrite",
     )
-    table.create_fts_index("text", use_tantivy=False, replace=True)
+    table.create_fts_index("text", replace=True)
 
     results = table.search(MatchQuery("foo", "text", fuzziness=1)).to_pandas()
     assert len(results) == 4
@@ -230,7 +230,7 @@ def test_fts_boost_query():
         ),
         mode="overwrite",
     )
-    table.create_fts_index("desc", use_tantivy=False, replace=True)
+    table.create_fts_index("desc", replace=True)
 
     results = table.search(
         BoostQuery(
@@ -265,7 +265,7 @@ def test_fts_boolean_query(tmp_path):
         ],
         mode="overwrite",
     )
-    table.create_fts_index("text", use_tantivy=False, replace=True)
+    table.create_fts_index("text", replace=True)
 
     # SHOULD
     results = table.search(
@@ -319,9 +319,7 @@ def test_fts_native():
         ],
     )
 
-    # passing `use_tantivy=False` to use lance FTS index
-    # `use_tantivy=True` by default
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")
     table.search("puppy").limit(10).select(["text"]).to_list()
     # [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
     # ...
@@ -332,7 +330,6 @@ def test_fts_native():
     # --8<-- [start:fts_config_folding]
     table.create_fts_index(
         "text",
-        use_tantivy=False,
         language="French",
         stem=True,
         ascii_folding=True,
@@ -346,7 +343,7 @@ def test_fts_native():
     table.search("puppy").limit(10).where("text='foo'", prefilter=False).to_list()
     # --8<-- [end:fts_postfiltering]
     # --8<-- [start:fts_with_position]
-    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
+    table.create_fts_index("text", with_position=True, replace=True)
     # --8<-- [end:fts_with_position]
     # --8<-- [start:fts_incremental_index]
     table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])

python/python/tests/test_db.py

@@ -15,8 +15,7 @@ import pytest
 from lancedb.pydantic import LanceModel, Vector
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_basic(tmp_path, use_tantivy):
+def test_basic(tmp_path):
     db = lancedb.connect(tmp_path)
 
     assert db.uri == str(tmp_path)
@@ -49,7 +48,7 @@ def test_basic(tmp_path, use_tantivy):
     assert len(rs) == 1
     assert rs["item"].iloc[0] == "foo"
 
-    table.create_fts_index("item", use_tantivy=use_tantivy)
+    table.create_fts_index("item")
     rs = table.search("bar", query_type="fts").to_pandas()
     assert len(rs) == 1
     assert rs["item"].iloc[0] == "bar"
@@ -897,42 +896,22 @@ def test_bypass_vector_index_sync(tmp_db: lancedb.DBConnection):
 
 
 def test_local_namespace_operations(tmp_path):
-    """Test that local mode namespace operations behave as expected."""
-    # Create a local database connection
+    """Test that local mode namespace operations work via directory namespace."""
     db = lancedb.connect(tmp_path)
 
-    # Test list_namespaces returns empty list for root namespace
-    namespaces = db.list_namespaces().namespaces
-    assert namespaces == []
+    # Root namespace starts empty
+    assert db.list_namespaces().namespaces == []
 
-    # Test list_namespaces with non-empty namespace raises NotImplementedError
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace operations are not supported for listing database",
-    ):
-        db.list_namespaces(namespace_path=["test"])
+    # Create and list child namespace
+    db.create_namespace(["child"])
+    assert "child" in db.list_namespaces().namespaces
 
+    # List namespaces under child
+    assert db.list_namespaces(namespace_path=["child"]).namespaces == []
 
-def test_local_create_namespace_not_supported(tmp_path):
-    """Test that create_namespace is not supported in local mode."""
-    db = lancedb.connect(tmp_path)
-
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace operations are not supported for listing database",
-    ):
-        db.create_namespace(["test_namespace"])
-
-
-def test_local_drop_namespace_not_supported(tmp_path):
-    """Test that drop_namespace is not supported in local mode."""
-    db = lancedb.connect(tmp_path)
-
-    with pytest.raises(
-        NotImplementedError,
-        match="Namespace operations are not supported for listing database",
-    ):
-        db.drop_namespace(["test_namespace"])
+    # Drop namespace
+    db.drop_namespace(["child"])
+    assert db.list_namespaces().namespaces == []
 
 
 def test_clone_table_latest_version(tmp_path):

python/python/tests/test_fts.py

@@ -36,9 +36,6 @@ import pytest
 import pytest_asyncio
 from utils import exception_output
 
-pytest.importorskip("lancedb.fts")
-tantivy = pytest.importorskip("tantivy")
-
 
 @pytest.fixture
 def table(tmp_path) -> ldb.table.LanceTable:
@@ -144,58 +141,53 @@ async def async_table(tmp_path) -> ldb.table.AsyncTable:
     return table
 
 
-def test_create_index(tmp_path):
-    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    assert isinstance(index, tantivy.Index)
-    assert os.path.exists(str(tmp_path / "index"))
+@pytest.mark.parametrize(
+    ("kwargs", "match"),
+    [
+        (
+            {"use_tantivy": True},
+            "Tantivy-based FTS has been removed",
+        ),
+        (
+            {"ordering_field_names": ["count"]},
+            "ordering_field_names was only supported",
+        ),
+        (
+            {"writer_heap_size": 128},
+            "writer_heap_size was only supported",
+        ),
+    ],
+)
+def test_reject_removed_tantivy_parameters(table, kwargs, match):
+    with pytest.raises(ValueError, match=match):
+        table.create_fts_index("text", **kwargs)
 
 
-def test_create_index_with_stemming(tmp_path, table):
-    index = ldb.fts.create_index(
-        str(tmp_path / "index"), ["text"], tokenizer_name="en_stem"
-    )
-    assert isinstance(index, tantivy.Index)
-    assert os.path.exists(str(tmp_path / "index"))
+def test_reject_legacy_tantivy_index(table):
+    path, _, _ = table._get_fts_index_path()
+    os.makedirs(path, exist_ok=True)
 
-    # Check stemming by running tokenizer on non empty table
-    table.create_fts_index("text", tokenizer_name="en_stem", use_tantivy=True)
+    with pytest.raises(ValueError, match="Legacy Tantivy FTS index detected"):
+        table.search("puppy").limit(5).to_list()
+
+    with pytest.raises(ValueError, match="Legacy Tantivy FTS index detected"):
+        table.create_fts_index("text")
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
 @pytest.mark.parametrize("with_position", [True, False])
-def test_create_inverted_index(table, use_tantivy, with_position):
-    if use_tantivy and not with_position:
-        pytest.skip("we don't support building a tantivy index without position")
+def test_create_inverted_index(table, with_position):
     table.create_fts_index(
         "text",
-        use_tantivy=use_tantivy,
         with_position=with_position,
         name="custom_fts_index",
     )
-    if not use_tantivy:
-        indices = table.list_indices()
-        fts_indices = [i for i in indices if i.index_type == "FTS"]
-        assert any(i.name == "custom_fts_index" for i in fts_indices)
+    indices = table.list_indices()
+    fts_indices = [i for i in indices if i.index_type == "FTS"]
+    assert any(i.name == "custom_fts_index" for i in fts_indices)
 
 
-def test_populate_index(tmp_path, table):
-    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    assert ldb.fts.populate_index(index, table, ["text"]) == len(table)
-
-
-def test_search_index(tmp_path, table):
-    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    ldb.fts.populate_index(index, table, ["text"])
-    index.reload()
-    results = ldb.fts.search_index(index, query="puppy", limit=5)
-    assert len(results) == 2
-    assert len(results[0]) == 5  # row_ids
-    assert len(results[1]) == 5  # _score
-
-
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_search_fts(table, use_tantivy):
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+def test_search_fts(table):
+    table.create_fts_index("text")
     results = table.search("puppy").select(["id", "text"]).limit(5).to_list()
     assert len(results) == 5
     assert len(results[0]) == 3  # id, text, _score
@@ -204,53 +196,52 @@ def test_search_fts(table, use_tantivy):
     results = table.search("puppy").select(["id", "text"]).to_list()
     assert len(results) == 10
 
-    if not use_tantivy:
-        # Test with a query
-        results = (
-            table.search(MatchQuery("puppy", "text"))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
+    # Test with a query
+    results = (
+        table.search(MatchQuery("puppy", "text"))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
 
-        # Test boost query
-        results = (
-            table.search(
-                BoostQuery(
-                    MatchQuery("puppy", "text"),
-                    MatchQuery("runs", "text"),
-                )
+    # Test boost query
+    results = (
+        table.search(
+            BoostQuery(
+                MatchQuery("puppy", "text"),
+                MatchQuery("runs", "text"),
             )
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
         )
-        assert len(results) == 5
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
 
-        # Test multi match query
-        table.create_fts_index("text2", use_tantivy=use_tantivy)
-        results = (
-            table.search(MultiMatchQuery("puppy", ["text", "text2"]))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-        assert len(results[0]) == 3  # id, text, _score
+    # Test multi match query
+    table.create_fts_index("text2")
+    results = (
+        table.search(MultiMatchQuery("puppy", ["text", "text2"]))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
 
-        # Test boolean query
-        results = (
-            table.search(MatchQuery("puppy", "text") & MatchQuery("runs", "text"))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-        assert len(results[0]) == 3  # id, text, _score
-        for r in results:
-            assert "puppy" in r["text"]
-            assert "runs" in r["text"]
+    # Test boolean query
+    results = (
+        table.search(MatchQuery("puppy", "text") & MatchQuery("runs", "text"))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
+    for r in results:
+        assert "puppy" in r["text"]
+        assert "runs" in r["text"]
 
 
 @pytest.mark.asyncio
@@ -318,13 +309,13 @@ async def test_fts_select_async(async_table):
 
 
 def test_search_fts_phrase_query(table):
-    table.create_fts_index("text", use_tantivy=False, with_position=False)
+    table.create_fts_index("text", with_position=False)
     try:
         phrase_results = table.search('"puppy runs"').limit(100).to_list()
         assert False
     except Exception:
         pass
-    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
+    table.create_fts_index("text", with_position=True, replace=True)
     results = table.search("puppy").limit(100).to_list()
 
     # Test with quotation marks
@@ -375,8 +366,8 @@ async def test_search_fts_phrase_query_async(async_table):
 
 
 def test_search_fts_specify_column(table):
-    table.create_fts_index("text", use_tantivy=False)
-    table.create_fts_index("text2", use_tantivy=False)
+    table.create_fts_index("text")
+    table.create_fts_index("text2")
 
     results = table.search("puppy", fts_columns="text").limit(5).to_list()
     assert len(results) == 5
@@ -470,42 +461,8 @@ async def test_search_fts_specify_column_async(async_table):
         pass
 
 
-def test_search_ordering_field_index_table(tmp_path, table):
-    table.create_fts_index("text", ordering_field_names=["count"], use_tantivy=True)
-    rows = (
-        table.search("puppy", ordering_field_name="count")
-        .limit(20)
-        .select(["text", "count"])
-        .to_list()
-    )
-    for r in rows:
-        assert "puppy" in r["text"]
-    assert sorted(rows, key=lambda x: x["count"], reverse=True) == rows
-
-
-def test_search_ordering_field_index(tmp_path, table):
-    index = ldb.fts.create_index(
-        str(tmp_path / "index"), ["text"], ordering_fields=["count"]
-    )
-
-    ldb.fts.populate_index(index, table, ["text"], ordering_fields=["count"])
-    index.reload()
-    results = ldb.fts.search_index(
-        index, query="puppy", limit=5, ordering_field="count"
-    )
-    assert len(results) == 2
-    assert len(results[0]) == 5  # row_ids
-    assert len(results[1]) == 5  # _distance
-    rows = table.to_lance().take(results[0]).to_pylist()
-
-    for r in rows:
-        assert "puppy" in r["text"]
-    assert sorted(rows, key=lambda x: x["count"], reverse=True) == rows
-
-
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_create_index_from_table(tmp_path, table, use_tantivy):
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+def test_create_index_from_table(tmp_path, table):
+    table.create_fts_index("text")
     df = table.search("puppy").limit(5).select(["text"]).to_pandas()
     assert len(df) <= 5
     assert "text" in df.columns
@@ -525,36 +482,24 @@ def test_create_index_from_table(tmp_path, table, use_tantivy):
     )
 
     with pytest.raises(Exception, match="already exists"):
-        table.create_fts_index("text", use_tantivy=use_tantivy)
+        table.create_fts_index("text")
 
-    table.create_fts_index("text", replace=True, use_tantivy=use_tantivy)
+    table.create_fts_index("text", replace=True)
     assert len(table.search("gorilla").limit(1).to_pandas()) == 1
 
 
 def test_create_index_multiple_columns(tmp_path, table):
-    table.create_fts_index(["text", "text2"], use_tantivy=True)
-    df = table.search("puppy").limit(5).to_pandas()
-    assert len(df) == 5
-    assert "text" in df.columns
-    assert "text2" in df.columns
-
-
-def test_empty_rs(tmp_path, table, mocker):
-    table.create_fts_index(["text", "text2"], use_tantivy=True)
-    mocker.patch("lancedb.fts.search_index", return_value=([], []))
-    df = table.search("puppy").limit(5).to_pandas()
-    assert len(df) == 0
+    with pytest.raises(ValueError, match="Native FTS indexes can only be created"):
+        table.create_fts_index(["text", "text2"])
 
 
 def test_nested_schema(tmp_path, table):
-    table.create_fts_index("nested.text", use_tantivy=True)
-    rs = table.search("puppy").limit(5).to_list()
-    assert len(rs) == 5
+    with pytest.raises(ValueError, match="top-level fields"):
+        table.create_fts_index("nested.text")
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_search_index_with_filter(table, use_tantivy):
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+def test_search_index_with_filter(table):
+    table.create_fts_index("text")
     orig_import = __import__
 
     def import_mock(name, *args):
@@ -584,8 +529,7 @@ def test_search_index_with_filter(table, use_tantivy):
         assert r["_rowid"] is not None
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_null_input(table, use_tantivy):
+def test_null_input(table):
     table.add(
         [
             {
@@ -598,14 +542,13 @@ def test_null_input(table, use_tantivy):
             }
         ]
     )
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+    table.create_fts_index("text")
 
 
 def test_syntax(table):
     # https://github.com/lancedb/lancedb/issues/769
-    table.create_fts_index("text", use_tantivy=True)
-    with pytest.raises(ValueError, match="Syntax Error"):
-        table.search("they could have been dogs OR").limit(10).to_list()
+    table.create_fts_index("text")
+    table.search("they could have been dogs OR").limit(10).to_list()
 
     # these should work
 
@@ -616,6 +559,7 @@ def test_syntax(table):
     ).to_list()
 
     # phrase queries
+    table.create_fts_index("text", with_position=True, replace=True)
     table.search("they could have been dogs OR cats").phrase_query().limit(10).to_list()
     table.search('"they could have been dogs OR cats"').limit(10).to_list()
     table.search('''"the cats OR dogs were not really 'pets' at all"''').limit(
@@ -639,7 +583,7 @@ def test_language(mem_db: DBConnection):
     table = mem_db.create_table("test", data=data)
 
     with pytest.raises(ValueError) as e:
-        table.create_fts_index("text", use_tantivy=False, language="klingon")
+        table.create_fts_index("text", language="klingon")
 
     assert exception_output(e) == (
         "ValueError: LanceDB does not support the requested language: 'klingon'\n"
@@ -650,7 +594,6 @@ def test_language(mem_db: DBConnection):
 
     table.create_fts_index(
         "text",
-        use_tantivy=False,
         language="French",
         stem=True,
         ascii_folding=True,
@@ -690,7 +633,7 @@ def test_fts_on_list(mem_db: DBConnection):
         }
     )
     table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", use_tantivy=False, with_position=True)
+    table.create_fts_index("text", with_position=True)
 
     res = table.search("lance").limit(5).to_list()
     assert len(res) == 3
@@ -702,7 +645,7 @@ def test_fts_on_list(mem_db: DBConnection):
 def test_fts_ngram(mem_db: DBConnection):
     data = pa.table({"text": ["hello world", "lance database", "lance is cool"]})
     table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", use_tantivy=False, base_tokenizer="ngram")
+    table.create_fts_index("text", base_tokenizer="ngram")
 
     results = table.search("lan", query_type="fts").limit(10).to_list()
     assert len(results) == 2
@@ -721,7 +664,6 @@ def test_fts_ngram(mem_db: DBConnection):
     # test setting min_ngram_length and prefix_only
     table.create_fts_index(
         "text",
-        use_tantivy=False,
         base_tokenizer="ngram",
         replace=True,
         ngram_min_length=2,
@@ -886,7 +828,7 @@ def test_fts_query_to_json():
 
 
 def test_fts_fast_search(table):
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")
 
     # Insert some unindexed data
     table.add(

python/python/tests/test_hybrid_query.py

@@ -28,7 +28,7 @@ def sync_table(tmpdir_factory) -> Table:
         }
     )
     table = db.create_table("test", data)
-    table.create_fts_index("text", with_position=False, use_tantivy=False)
+    table.create_fts_index("text", with_position=False)
     return table
 
 
@@ -192,7 +192,7 @@ def table_with_id(tmpdir_factory) -> Table:
         }
     )
     table = db.create_table("test_with_id", data)
-    table.create_fts_index("text", with_position=False, use_tantivy=False)
+    table.create_fts_index("text", with_position=False)
     return table
 
 

python/python/tests/test_namespace.py

@@ -681,7 +681,7 @@ class TestPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["QueryTable"],
         )
-        assert "QueryTable" in db._pushdown_operations
+        assert "QueryTable" in db._namespace_client_pushdown_operations
 
     def test_create_table_pushdown_stored(self):
         """Test that CreateTable pushdown is stored on sync connection."""
@@ -690,7 +690,7 @@ class TestPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["CreateTable"],
         )
-        assert "CreateTable" in db._pushdown_operations
+        assert "CreateTable" in db._namespace_client_pushdown_operations
 
     def test_both_pushdowns_stored(self):
         """Test that both pushdown operations can be set together."""
@@ -699,13 +699,13 @@ class TestPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["QueryTable", "CreateTable"],
         )
-        assert "QueryTable" in db._pushdown_operations
-        assert "CreateTable" in db._pushdown_operations
+        assert "QueryTable" in db._namespace_client_pushdown_operations
+        assert "CreateTable" in db._namespace_client_pushdown_operations
 
     def test_pushdown_defaults_to_empty(self):
         """Test that pushdown operations default to empty."""
         db = lancedb.connect_namespace("dir", {"root": self.temp_dir})
-        assert len(db._pushdown_operations) == 0
+        assert len(db._namespace_client_pushdown_operations) == 0
 
 
 @pytest.mark.asyncio
@@ -727,7 +727,7 @@ class TestAsyncPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["QueryTable"],
         )
-        assert "QueryTable" in db._pushdown_operations
+        assert "QueryTable" in db._namespace_client_pushdown_operations
 
     async def test_async_create_table_pushdown_stored(self):
         """Test that CreateTable pushdown is stored on async connection."""
@@ -736,9 +736,9 @@ class TestAsyncPushdownOperations:
             {"root": self.temp_dir},
             namespace_client_pushdown_operations=["CreateTable"],
         )
-        assert "CreateTable" in db._pushdown_operations
+        assert "CreateTable" in db._namespace_client_pushdown_operations
 
     async def test_async_pushdown_defaults_to_empty(self):
         """Test that pushdown operations default to empty on async connection."""
         db = lancedb.connect_namespace_async("dir", {"root": self.temp_dir})
-        assert len(db._pushdown_operations) == 0
+        assert len(db._namespace_client_pushdown_operations) == 0

python/python/tests/test_namespace_integration.py

@@ -18,6 +18,9 @@ Tests verify:
 """
 
 import copy
+import shutil
+import sys
+import tempfile
 import time
 import uuid
 from typing import Dict, Optional
@@ -387,6 +390,66 @@ def test_namespace_open_table_with_provider(s3_bucket: str, use_custom: bool):
     assert get_describe_call_count(inner_ns_client) == describe_count_after_open
 
 
+@pytest.mark.skipif(
+    sys.platform == "win32",
+    reason="TODO: fix schema-only namespace metrics test on Windows",
+)
+@pytest.mark.parametrize("use_custom", [False, True], ids=["DirectoryNS", "CustomNS"])
+def test_namespace_create_schema_only_with_provider(use_custom: bool):
+    """
+    Test creating a schema-only table through namespace with storage options provider.
+
+    Verifies:
+    - declare_table is called once to reserve the location
+    - describe_table is not needed during create in create mode
+    - the table can be reopened successfully afterward
+    - opening the table triggers exactly one describe_table call
+    """
+    temp_dir = tempfile.mkdtemp()
+    try:
+        ns_client, inner_ns_client = create_tracking_namespace(
+            bucket_name=temp_dir,
+            storage_options={},
+            credential_expires_in_seconds=3600,
+            use_custom=use_custom,
+        )
+
+        db = LanceNamespaceDBConnection(ns_client)
+
+        namespace_name = f"test_ns_{uuid.uuid4().hex[:8]}"
+        db.create_namespace([namespace_name])
+
+        table_name = f"test_table_{uuid.uuid4().hex}"
+        namespace_path = [namespace_name]
+        schema = pa.schema(
+            [
+                pa.field("id", pa.int64()),
+                pa.field("vector", pa.list_(pa.float32(), 2)),
+                pa.field("text", pa.string()),
+            ]
+        )
+
+        assert get_declare_call_count(inner_ns_client) == 0
+        assert get_describe_call_count(inner_ns_client) == 0
+
+        table = db.create_table(
+            table_name, schema=schema, namespace_path=namespace_path
+        )
+
+        assert table.name == table_name
+        assert table.namespace == namespace_path
+        assert get_declare_call_count(inner_ns_client) == 1
+        assert get_describe_call_count(inner_ns_client) == 0
+
+        reopened_table = db.open_table(table_name, namespace_path=namespace_path)
+
+        assert reopened_table.schema == schema
+        assert get_declare_call_count(inner_ns_client) == 1
+        assert get_describe_call_count(inner_ns_client) == 1
+    finally:
+        shutil.rmtree(temp_dir, ignore_errors=True)
+
+
 @pytest.mark.s3_test
 @pytest.mark.parametrize("use_custom", [False, True], ids=["DirectoryNS", "CustomNS"])
 def test_namespace_credential_refresh_on_read(s3_bucket: str, use_custom: bool):

python/python/tests/test_query.py

@@ -1385,7 +1385,7 @@ def test_query_timeout(tmp_path):
         }
     )
     table = db.create_table("test", data)
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")
 
     with pytest.raises(Exception, match="Query timeout"):
         table.search().where("text = 'a'").to_list(timeout=timedelta(0))

python/python/tests/test_rerankers.py

@@ -26,11 +26,8 @@ from lancedb.rerankers import (
 )
 from lancedb.table import LanceTable
 
-# Tests rely on FTS index
-pytest.importorskip("lancedb.fts")
 
-
-def get_test_table(tmp_path, use_tantivy):
+def get_test_table(tmp_path):
     db = lancedb.connect(tmp_path)
     # Create a LanceDB table schema with a vector and a text column
     emb = EmbeddingFunctionRegistry.get_instance().get("test").create()
@@ -98,7 +95,7 @@ def get_test_table(tmp_path, use_tantivy):
     )
 
     # Create a fts index
-    table.create_fts_index("text", use_tantivy=use_tantivy, replace=True)
+    table.create_fts_index("text", replace=True)
 
     return table, MyTable
 
@@ -208,8 +205,8 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
     assert len(result) == 20 and result == result_arrow
 
 
-def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
-    table, schema = get_test_table(tmp_path, use_tantivy)
+def _run_test_hybrid_reranker(reranker, tmp_path):
+    table, schema = get_test_table(tmp_path)
     # The default reranker
     result1 = (
         table.search(
@@ -285,8 +282,7 @@ def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
     )
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_linear_combination(tmp_path, use_tantivy):
+def test_linear_combination(tmp_path):
     reranker = LinearCombinationReranker()
 
     vector_results = pa.Table.from_pydict(
@@ -313,22 +309,20 @@ def test_linear_combination(tmp_path, use_tantivy):
     assert "_score" not in combined_results.column_names
     assert "_relevance_score" in combined_results.column_names
 
-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
+    _run_test_hybrid_reranker(reranker, tmp_path)
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_rrf_reranker(tmp_path, use_tantivy):
+def test_rrf_reranker(tmp_path):
     reranker = RRFReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
+    _run_test_hybrid_reranker(reranker, tmp_path)
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_mrr_reranker(tmp_path, use_tantivy):
+def test_mrr_reranker(tmp_path):
     reranker = MRRReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
+    _run_test_hybrid_reranker(reranker, tmp_path)
 
     # Test multi-vector part
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     query = "single player experience"
     rs1 = table.search(query, vector_column_name="vector").limit(10).with_row_id(True)
     rs2 = (
@@ -363,7 +357,7 @@ def test_rrf_reranker_distance():
     table = db.create_table("test", data)
 
     table.create_index(num_partitions=1, num_sub_vectors=2)
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")
 
     reranker = RRFReranker(return_score="all")
 
@@ -422,35 +416,31 @@ def test_rrf_reranker_distance():
 @pytest.mark.skipif(
     os.environ.get("COHERE_API_KEY") is None, reason="COHERE_API_KEY not set"
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_cohere_reranker(tmp_path, use_tantivy):
+def test_cohere_reranker(tmp_path):
     pytest.importorskip("cohere")
     reranker = CohereReranker()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_cross_encoder_reranker(tmp_path, use_tantivy):
+def test_cross_encoder_reranker(tmp_path):
     pytest.importorskip("sentence_transformers")
     reranker = CrossEncoderReranker()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_colbert_reranker(tmp_path, use_tantivy):
+def test_colbert_reranker(tmp_path):
     pytest.importorskip("rerankers")
     reranker = ColbertReranker()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_answerdotai_reranker(tmp_path, use_tantivy):
+def test_answerdotai_reranker(tmp_path):
     pytest.importorskip("rerankers")
     reranker = AnswerdotaiRerankers()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
 
@@ -459,10 +449,9 @@ def test_answerdotai_reranker(tmp_path, use_tantivy):
     or os.environ.get("OPENAI_BASE_URL") is not None,
     reason="OPENAI_API_KEY not set",
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_openai_reranker(tmp_path, use_tantivy):
+def test_openai_reranker(tmp_path):
     pytest.importorskip("openai")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     reranker = OpenaiReranker()
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
@@ -470,10 +459,9 @@ def test_openai_reranker(tmp_path, use_tantivy):
 @pytest.mark.skipif(
     os.environ.get("JINA_API_KEY") is None, reason="JINA_API_KEY not set"
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_jina_reranker(tmp_path, use_tantivy):
+def test_jina_reranker(tmp_path):
     pytest.importorskip("jina")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     reranker = JinaReranker()
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
@@ -481,11 +469,10 @@ def test_jina_reranker(tmp_path, use_tantivy):
 @pytest.mark.skipif(
     os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_voyageai_reranker(tmp_path, use_tantivy):
+def test_voyageai_reranker(tmp_path):
     pytest.importorskip("voyageai")
     reranker = VoyageAIReranker(model_name="rerank-2.5")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     _run_test_reranker(reranker, table, "single player experience", None, schema)
 
 
@@ -504,7 +491,7 @@ def test_empty_result_reranker():
 
     # Create empty table with schema
     empty_table = db.create_table("empty_table", schema=schema, mode="overwrite")
-    empty_table.create_fts_index("text", use_tantivy=False, replace=True)
+    empty_table.create_fts_index("text", replace=True)
     for reranker in [
         CrossEncoderReranker(),
         # ColbertReranker(),
@@ -603,11 +590,10 @@ def test_empty_hybrid_result_reranker():
     assert "_rowid" in result.column_names
 
 
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_cross_encoder_reranker_return_all(tmp_path, use_tantivy):
+def test_cross_encoder_reranker_return_all(tmp_path):
     pytest.importorskip("sentence_transformers")
     reranker = CrossEncoderReranker(return_score="all")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
     query = "single player experience"
     result = (
         table.search(query, query_type="hybrid", vector_column_name="vector")

python/python/tests/test_s3.py

@@ -242,8 +242,8 @@ def test_s3_dynamodb_sync(s3_bucket: str, commit_table: str, monkeypatch):
 
     # FTS indices should error since they are not supported yet.
     with pytest.raises(
-        NotImplementedError,
-        match="Full-text search is only supported on the local filesystem",
+        ValueError,
+        match="Tantivy-based FTS has been removed",
     ):
         table.create_fts_index("x", use_tantivy=True)
 

python/python/tests/test_table.py

@@ -3,6 +3,7 @@
 
 
 import os
+import sys
 from datetime import date, datetime, timedelta
 from time import sleep
 from typing import List
@@ -1947,7 +1948,6 @@ def setup_hybrid_search_table(db: DBConnection, embedding_func):
 
 def test_hybrid_search(tmp_db: DBConnection):
     # This test uses an FTS index
-    pytest.importorskip("lancedb.fts")
     pytest.importorskip("lance")
 
     table, MyTable, emb = setup_hybrid_search_table(tmp_db, "test")
@@ -2018,7 +2018,6 @@ def test_hybrid_search(tmp_db: DBConnection):
 
 def test_hybrid_search_metric_type(tmp_db: DBConnection):
     # This test uses an FTS index
-    pytest.importorskip("lancedb.fts")
     pytest.importorskip("lance")
 
     # Need to use nonnorm as the embedding function so l2 and dot results
@@ -2040,6 +2039,13 @@ def test_hybrid_search_metric_type(tmp_db: DBConnection):
 @pytest.mark.parametrize(
     "consistency_interval", [None, timedelta(seconds=0), timedelta(seconds=0.1)]
 )
+@pytest.mark.skipif(
+    sys.platform == "win32",
+    reason=(
+        "TODO: directory namespace is not supported on Windows yet; "
+        "re-enable after that is fixed."
+    ),
+)
 def test_consistency(tmp_path, consistency_interval):
     db = lancedb.connect(tmp_path)
     table = db.create_table("my_table", data=[{"id": 0}])
@@ -2060,7 +2066,6 @@ def test_consistency(tmp_path, consistency_interval):
     elif consistency_interval == timedelta(seconds=0):
         assert table2.version == table.version
     else:
-        # (consistency_interval == timedelta(seconds=0.1)
         assert table2.version == table.version - 1
         sleep(0.1)
         assert table2.version == table.version

python/src/connection.rs

@@ -1,11 +1,17 @@
 // SPDX-License-Identifier: Apache-2.0
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
-use std::{collections::HashMap, sync::Arc, time::Duration};
+use std::{
+    collections::{HashMap, HashSet},
+    sync::Arc,
+    time::Duration,
+};
 
 use arrow::{datatypes::Schema, ffi_stream::ArrowArrayStreamReader, pyarrow::FromPyArrow};
 use lancedb::{
     connection::Connection as LanceConnection,
+    connection::NamespaceClientPushdownOperation,
+    database::namespace::LanceNamespaceDatabase,
     database::{CreateTableMode, Database, ReadConsistency},
 };
 use pyo3::{
@@ -39,6 +45,29 @@ impl Connection {
     }
 }
 
+fn parse_namespace_client_pushdown_operations(
+    operations: Option<Vec<String>>,
+) -> PyResult<HashSet<NamespaceClientPushdownOperation>> {
+    let mut parsed = HashSet::new();
+    for operation in operations.unwrap_or_default() {
+        match operation.as_str() {
+            "QueryTable" => {
+                parsed.insert(NamespaceClientPushdownOperation::QueryTable);
+            }
+            "CreateTable" => {
+                parsed.insert(NamespaceClientPushdownOperation::CreateTable);
+            }
+            _ => {
+                return Err(PyValueError::new_err(format!(
+                    "Invalid pushdown operation: {}",
+                    operation
+                )));
+            }
+        }
+    }
+    Ok(parsed)
+}
+
 impl Connection {
     fn parse_create_mode_str(mode: &str) -> PyResult<CreateTableMode> {
         match mode {
@@ -538,6 +567,52 @@ pub fn connect(
     })
 }
 
+#[pyfunction]
+#[pyo3(signature = (
+    namespace_client,
+    read_consistency_interval=None,
+    storage_options=None,
+    session=None,
+    namespace_client_pushdown_operations=None,
+    namespace_client_impl=None,
+    namespace_client_properties=None,
+))]
+#[allow(clippy::too_many_arguments)]
+pub fn connect_namespace_client(
+    py: Python<'_>,
+    namespace_client: Py<PyAny>,
+    read_consistency_interval: Option<f64>,
+    storage_options: Option<HashMap<String, String>>,
+    session: Option<crate::session::Session>,
+    namespace_client_pushdown_operations: Option<Vec<String>>,
+    namespace_client_impl: Option<String>,
+    namespace_client_properties: Option<HashMap<String, String>>,
+) -> PyResult<Connection> {
+    let namespace_client = extract_namespace_arc(py, namespace_client)?;
+    let read_consistency_interval = read_consistency_interval.map(Duration::from_secs_f64);
+    let namespace_client_pushdown_operations =
+        parse_namespace_client_pushdown_operations(namespace_client_pushdown_operations)?;
+    let ns_impl = namespace_client_impl.unwrap_or_else(|| "python".to_string());
+    let ns_properties = namespace_client_properties.unwrap_or_default();
+    let storage_options = storage_options.unwrap_or_default();
+    let session = session.map(|s| s.inner.clone());
+
+    let database = LanceNamespaceDatabase::from_namespace_client(
+        namespace_client,
+        ns_impl,
+        ns_properties,
+        storage_options,
+        read_consistency_interval,
+        session,
+        namespace_client_pushdown_operations,
+    );
+
+    Ok(Connection::new(LanceConnection::new(
+        Arc::new(database),
+        Arc::new(lancedb::embeddings::MemoryRegistry::new()),
+    )))
+}
+
 #[derive(FromPyObject)]
 pub struct PyClientConfig {
     user_agent: String,

python/src/lib.rs

@@ -2,7 +2,7 @@
 // SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 use arrow::RecordBatchStream;
-use connection::{Connection, connect};
+use connection::{Connection, connect, connect_namespace_client};
 use env_logger::Env;
 use expr::{PyExpr, expr_col, expr_func, expr_lit};
 use index::IndexConfig;
@@ -58,6 +58,7 @@ pub fn _lancedb(_py: Python, m: &Bound<'_, PyModule>) -> PyResult<()> {
     m.add_class::<PyPermutationReader>()?;
     m.add_class::<PyExpr>()?;
     m.add_function(wrap_pyfunction!(connect, m)?)?;
+    m.add_function(wrap_pyfunction!(connect_namespace_client, m)?)?;
     m.add_function(wrap_pyfunction!(permutation::async_permutation_builder, m)?)?;
     m.add_function(wrap_pyfunction!(util::validate_table_name, m)?)?;
     m.add_function(wrap_pyfunction!(query::fts_query_to_json, m)?)?;

python/uv.lock

@@ -1996,7 +1996,6 @@ tests = [
     { name = "pytest-mock" },
     { name = "pytz" },
     { name = "requests" },
-    { name = "tantivy" },
 ]
 
 [package.metadata]
@@ -2050,7 +2049,6 @@ requires-dist = [
     { name = "sentence-transformers", marker = "extra == 'embeddings'", specifier = ">=2.2.0" },
     { name = "sentencepiece", marker = "extra == 'embeddings'", specifier = ">=0.1.99" },
     { name = "sentencepiece", marker = "extra == 'siglip'" },
-    { name = "tantivy", marker = "extra == 'tests'", specifier = ">=0.20.0" },
     { name = "torch", marker = "extra == 'clip'" },
     { name = "torch", marker = "extra == 'embeddings'", specifier = ">=2.0.0" },
     { name = "torch", marker = "extra == 'siglip'" },
@@ -4779,44 +4777,6 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/40/44/4a5f08c96eb108af5cb50b41f76142f0afa346dfa99d5296fe7202a11854/tabulate-0.9.0-py3-none-any.whl", hash = "sha256:024ca478df22e9340661486f85298cff5f6dcdba14f3813e8830015b9ed1948f", size = 35252, upload-time = "2022-10-06T17:21:44.262Z" },
 ]
 
-[[package]]
-name = "tantivy"
-version = "0.25.1"
-source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/1b/f9/0cd3955d155d3e3ef74b864769514dd191e5dacba9f0beb7af2d914942ce/tantivy-0.25.1.tar.gz", hash = "sha256:68a3314699a7d18fcf338b52bae8ce46a97dde1128a3e47e33fa4db7f71f265e", size = 75120, upload-time = "2025-12-02T11:57:12.997Z" }
-wheels = [
-    { url = "https://files.pythonhosted.org/packages/80/f7/2276bed3bed983ce2970dc70e3571f372587fe4f5f2bac1d6d617df08fa3/tantivy-0.25.1-cp310-cp310-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:7aa587a3dc9470584cacf5e3640fee93d12ec5f10109669c1f47c4e90820b958", size = 7638510, upload-time = "2025-12-02T11:56:08.754Z" },
-    { url = "https://files.pythonhosted.org/packages/20/8c/078dc50570e243414356b05633f52fe544b85179281ffa9f1fe05d76bbd8/tantivy-0.25.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:56d77fe667595693d9fa5f0b4545776d84da9526bab0273b3fc6c7536dc0d8a2", size = 3932659, upload-time = "2025-12-02T11:56:10.621Z" },
-    { url = "https://files.pythonhosted.org/packages/bd/dc/281c48436a1e3178b58fe463af314434fe0f3a4ec0c7588a362900e0c69e/tantivy-0.25.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5ba8c347cd48595fcaeabb28a909ebce92cf9c5e5c84ab5ba1136a280a307b5c", size = 4197430, upload-time = "2025-12-02T11:56:12.65Z" },
-    { url = "https://files.pythonhosted.org/packages/7b/6c/61e6e0b0a350007d10a9b66a35703361d3345e14e7a7cc83494776b2a054/tantivy-0.25.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:aa7c4932e8fde1f09f2d46226060e827e197c2749abdc6129d73a752773adc38", size = 4184055, upload-time = "2025-12-02T11:56:14.647Z" },
-    { url = "https://files.pythonhosted.org/packages/5f/fd/0eb059b12f0b6f91623a54a46448a83b7f716d08f3bca68c095d697b85da/tantivy-0.25.1-cp310-cp310-win_amd64.whl", hash = "sha256:afcfc5dbb0bcd5d24531f4471737ae0896f33528426ab0b1dad3e427c19120f6", size = 3424134, upload-time = "2025-12-02T11:56:16.242Z" },
-    { url = "https://files.pythonhosted.org/packages/4e/7a/8a277f377e8a151fc0e71d4ffc1114aefb6e5e1c7dd609fed0955cf34ed8/tantivy-0.25.1-cp311-cp311-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:d363d7b4207d3a5aa7f0d212420df35bed18bdb6bae26a2a8bd57428388b7c29", size = 7637033, upload-time = "2025-12-02T11:56:18.104Z" },
-    { url = "https://files.pythonhosted.org/packages/71/31/8b4acdedfc9f9a2d04b1340d07eef5213d6f151d1e18da0cb423e5f090d2/tantivy-0.25.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:8f4389cf1d889a1df7c5a3195806b4b56c37cee10d8a26faaa0dea35a867b5ff", size = 3932180, upload-time = "2025-12-02T11:56:19.833Z" },
-    { url = "https://files.pythonhosted.org/packages/2f/dc/3e8499c21b4b9795e8f2fc54c68ce5b92905aaeadadaa56ecfa9180b11b1/tantivy-0.25.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99864c09fc54652c3c2486cdf13f86cdc8200f4b481569cb291e095ca5d496e5", size = 4197620, upload-time = "2025-12-02T11:56:21.496Z" },
-    { url = "https://files.pythonhosted.org/packages/f8/8e/f2ce62fffc811eb62bead92c7b23c2e218f817cbd54c4f3b802e03ba1438/tantivy-0.25.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:05abf37ddbc5063c575548be0d62931629c086bff7a5a1b67cf5a8f5ebf4cd8c", size = 4183794, upload-time = "2025-12-02T11:56:23.215Z" },
-    { url = "https://files.pythonhosted.org/packages/de/64/24e2891b0ba3fd9853e10c296095a33b89bf3efd65e29da1ee5dae736040/tantivy-0.25.1-cp311-cp311-win_amd64.whl", hash = "sha256:f307ee8ad21597b0be23af83008fd66cfd5f958cdfa24ec0aaa08a38e86bbef4", size = 3424235, upload-time = "2025-12-02T11:56:25.172Z" },
-    { url = "https://files.pythonhosted.org/packages/41/e7/6849c713ed0996c7628324c60512c4882006f0a62145e56c624a93407f90/tantivy-0.25.1-cp312-cp312-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:90fd919e5f611809f746560ecf36eb9be824dec62e21ae17a27243759edb9aa1", size = 7621494, upload-time = "2025-12-02T11:56:27.069Z" },
-    { url = "https://files.pythonhosted.org/packages/c5/22/c3d8294600dc6e7fa350daef9ff337d3c06e132b81df727de9f7a50c692a/tantivy-0.25.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:4613c7cf6c23f3a97989819690a0f956d799354957de7a204abcc60083cebe02", size = 3925219, upload-time = "2025-12-02T11:56:29.403Z" },
-    { url = "https://files.pythonhosted.org/packages/41/fc/cbb1df71dd44c9110eff4eaaeda9d44f2d06182fe0452193be20ddfba93f/tantivy-0.25.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c477bd20b4df804d57dfc5033431bef27cde605695ae141b03abbf6ebc069129", size = 4198699, upload-time = "2025-12-02T11:56:31.359Z" },
-    { url = "https://files.pythonhosted.org/packages/47/4d/71abb78b774073c3ce12a4faa4351a9d910a71ffa3659526affba163873d/tantivy-0.25.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f9b1a1ba1113c523c7ff7b10f282d6c4074006f7ef8d71e1d973d51bf7291ddb", size = 4183585, upload-time = "2025-12-02T11:56:33.317Z" },
-    { url = "https://files.pythonhosted.org/packages/be/16/3f00cd7ec458b92a0e977960af9ddfbeb762127d9acc68da9094a1fda556/tantivy-0.25.1-cp312-cp312-win_amd64.whl", hash = "sha256:9de0bafd3bd7ac9f8f82d53e17562e9db11a5af308fe5185c4bd86feaddbe4a6", size = 3424622, upload-time = "2025-12-02T11:56:34.788Z" },
-    { url = "https://files.pythonhosted.org/packages/3d/25/73cfbcf1a8ea49be6c42817431cac46b70a119fe64da903fcc2d92b5b511/tantivy-0.25.1-cp313-cp313-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:f51ff7196c6f31719202080ed8372d5e3d51e92c749c032fb8234f012e99744c", size = 7622530, upload-time = "2025-12-02T11:56:36.839Z" },
-    { url = "https://files.pythonhosted.org/packages/12/c8/c0d7591cdf4f7e7a9fc4da786d1ca8cd1aacffaa2be16ea6d401a8e4a566/tantivy-0.25.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:550e63321bfcacc003859f2fa29c1e8e56450807b3c9a501c1add27cfb9236d9", size = 3925637, upload-time = "2025-12-02T11:56:38.425Z" },
-    { url = "https://files.pythonhosted.org/packages/3a/09/bedfc223bffec7641b417dd7ab071134b2ef8f8550e9b1fb6014657ef52e/tantivy-0.25.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fde31cc8d6e122faf7902aeea32bc008a429a6e8904e34d3468126a3ec01b016", size = 4197322, upload-time = "2025-12-02T11:56:40.411Z" },
-    { url = "https://files.pythonhosted.org/packages/f5/f1/1fa5183500c8042200c9f2b840d34f5bbcfb434a1ee750e7132262d2a5c9/tantivy-0.25.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b11bd5a518b0be645320b47af8493f6a40c4f3234313e37adcf4534a564d27dd", size = 4183143, upload-time = "2025-12-02T11:56:42.048Z" },
-    { url = "https://files.pythonhosted.org/packages/d5/74/a4c4f4eb95888ccb784da3b017aa0625ab1ac411bf5d022a9a797d9a2334/tantivy-0.25.1-cp313-cp313-win_amd64.whl", hash = "sha256:cc7fe88853e06b3251ee4fa42b7a2038727f850c8765bcc8167cfc73585dd24e", size = 3423491, upload-time = "2025-12-02T11:56:43.858Z" },
-    { url = "https://files.pythonhosted.org/packages/8b/2f/581519492226f97d23bd0adc95dad991ebeaa73ea6abc8bff389a3096d9a/tantivy-0.25.1-cp313-cp313t-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:dae99e75b7eaa9bf5bd16ab106b416370f08c135aed0e117d62a3201cd1ffe36", size = 7610316, upload-time = "2025-12-02T11:56:45.927Z" },
-    { url = "https://files.pythonhosted.org/packages/91/40/5d7bc315ab9e6a22c5572656e8ada1c836cfa96dccf533377504fbc3c9d9/tantivy-0.25.1-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:506e9533c5ef4d3df43bad64ffecc0aa97c76e361ea610815dc3a20a9d6b30b3", size = 3919882, upload-time = "2025-12-02T11:56:48.469Z" },
-    { url = "https://files.pythonhosted.org/packages/02/b9/e0ef2f57a6a72444cb66c2ffbc310ab33ffaace275f1c4b0319d84ea3f18/tantivy-0.25.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5dbd4f8f264dacbcc9dee542832da2173fd53deaaea03f082d95214f8b5ed6bc", size = 4196031, upload-time = "2025-12-02T11:56:50.151Z" },
-    { url = "https://files.pythonhosted.org/packages/1e/02/bf3f8cacfd08642e14a73f7956a3fb95d58119132c98c121b9065a1f8615/tantivy-0.25.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:824c643ccb640dd9e35e00c5d5054ddf3323f56fe4219d57d428a9eeea13d22c", size = 4183437, upload-time = "2025-12-02T11:56:51.818Z" },
-    { url = "https://files.pythonhosted.org/packages/9c/83/afa90e570198e2d1139dd567bec3c9cf44d8c54f63a649f16d711ede02f5/tantivy-0.25.1-cp313-cp313t-win_amd64.whl", hash = "sha256:09c987b840afcebac817836ac08407eff17272d8aa60ce6e291f89c81830221d", size = 3419409, upload-time = "2025-12-02T11:56:53.451Z" },
-    { url = "https://files.pythonhosted.org/packages/ff/44/9f1d67aa5030f7eebc966c863d1316a510a971dd8bb45651df4acdfae9ed/tantivy-0.25.1-cp314-cp314-macosx_10_12_x86_64.macosx_11_0_arm64.macosx_10_12_universal2.whl", hash = "sha256:7f5d29ae85dd0f23df8d15b3e7b341d4f9eb5a446bbb9640df48ac1f6d9e0c6c", size = 7623723, upload-time = "2025-12-02T11:56:55.066Z" },
-    { url = "https://files.pythonhosted.org/packages/db/30/6e085bd3ed9d12da3c91c185854abd70f9dfd35fb36a75ea98428d42c30b/tantivy-0.25.1-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:f2d2938fb69a74fc1bb36edfaf7f0d1596fa1264db0f377bda2195c58bcb6245", size = 3926243, upload-time = "2025-12-02T11:56:57.058Z" },
-    { url = "https://files.pythonhosted.org/packages/32/f5/a00d65433430f51718e5cc6938df571765d7c4e03aedec5aef4ab567aa9b/tantivy-0.25.1-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4f5ff124c4802558e627091e780b362ca944169736caba5a372eef39a79d0ae0", size = 4207186, upload-time = "2025-12-02T11:56:58.803Z" },
-    { url = "https://files.pythonhosted.org/packages/19/63/61bdb12fc95f2a7f77bd419a5149bfa9f28caa76cb569bf2b6b06e1d033e/tantivy-0.25.1-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:43b80ef62a340416139c93d19264e5f808da48e04f9305f1092b8ed22be0a5be", size = 4187312, upload-time = "2025-12-02T11:57:00.595Z" },
-    { url = "https://files.pythonhosted.org/packages/b7/de/e39c0b01d59019bf5c38face8b81defbc4a68cebf5e0c53bcb2cd715a449/tantivy-0.25.1-cp314-cp314-win_amd64.whl", hash = "sha256:286b654f40c70c1e6b64b9bc7031ed0bf5c440f5bffeaeeee21a0ee6cc39f0e2", size = 3436535, upload-time = "2025-12-02T11:57:02.267Z" },
-]
-
 [[package]]
 name = "threadpoolctl"
 version = "3.6.0"

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.28.0-beta.2"
+version = "0.28.0-beta.9"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/connection.rs

@@ -171,7 +171,7 @@ impl OpenTableBuilder {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         let store_params = self
             .request
@@ -188,7 +188,7 @@ impl OpenTableBuilder {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -582,6 +582,14 @@ pub struct ConnectRequest {
     /// Database specific options
     pub options: HashMap<String, String>,
 
+    /// Extra properties for the equivalent namespace client.
+    ///
+    /// For a local [`ListingDatabase`], these are merged into the backing
+    /// `DirectoryNamespace` properties. This is useful for namespace-specific
+    /// settings such as `table_version_tracking_enabled` that are distinct from
+    /// storage options.
+    pub namespace_client_properties: HashMap<String, String>,
+
     /// The interval at which to check for updates from other processes.
     ///
     /// If None, then consistency is not checked. For performance
@@ -621,6 +629,7 @@ impl ConnectBuilder {
                 client_config: Default::default(),
                 read_consistency_interval: None,
                 options: HashMap::new(),
+                namespace_client_properties: HashMap::new(),
                 session: None,
             },
             embedding_registry: None,
@@ -738,7 +747,7 @@ impl ConnectBuilder {
 
     /// Set an option for the storage layer.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         self.request.options.insert(key.into(), value.into());
         self
@@ -746,7 +755,7 @@ impl ConnectBuilder {
 
     /// Set multiple options for the storage layer.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -757,6 +766,31 @@ impl ConnectBuilder {
         self
     }
 
+    /// Set an additional property for the equivalent namespace client.
+    pub fn namespace_client_property(
+        mut self,
+        key: impl Into<String>,
+        value: impl Into<String>,
+    ) -> Self {
+        self.request
+            .namespace_client_properties
+            .insert(key.into(), value.into());
+        self
+    }
+
+    /// Set multiple additional properties for the equivalent namespace client.
+    pub fn namespace_client_properties(
+        mut self,
+        pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
+    ) -> Self {
+        for (key, value) in pairs {
+            self.request
+                .namespace_client_properties
+                .insert(key.into(), value.into());
+        }
+        self
+    }
+
     /// The interval at which to check for updates from other processes. This
     /// only affects LanceDB OSS.
     ///
@@ -881,7 +915,7 @@ use std::collections::HashSet;
 /// These operations will be executed on the namespace server instead of locally
 /// when enabled via [`ConnectNamespaceBuilder::pushdown_operations`].
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
-pub enum PushdownOperation {
+pub enum NamespaceClientPushdownOperation {
     /// Execute queries on the namespace server via `query_table()` instead of locally.
     QueryTable,
     /// Execute table creation on the namespace server via `create_table()`
@@ -893,10 +927,11 @@ pub struct ConnectNamespaceBuilder {
     ns_impl: String,
     properties: HashMap<String, String>,
     storage_options: HashMap<String, String>,
+    namespace_client_properties: HashMap<String, String>,
     read_consistency_interval: Option<std::time::Duration>,
     embedding_registry: Option<Arc<dyn EmbeddingRegistry>>,
     session: Option<Arc<lance::session::Session>>,
-    pushdown_operations: HashSet<PushdownOperation>,
+    pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
 }
 
 impl ConnectNamespaceBuilder {
@@ -905,6 +940,7 @@ impl ConnectNamespaceBuilder {
             ns_impl: ns_impl.to_string(),
             properties,
             storage_options: HashMap::new(),
+            namespace_client_properties: HashMap::new(),
             read_consistency_interval: None,
             embedding_registry: None,
             session: None,
@@ -914,7 +950,7 @@ impl ConnectNamespaceBuilder {
 
     /// Set an option for the storage layer.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         self.storage_options.insert(key.into(), value.into());
         self
@@ -922,7 +958,7 @@ impl ConnectNamespaceBuilder {
 
     /// Set multiple options for the storage layer.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -933,6 +969,29 @@ impl ConnectNamespaceBuilder {
         self
     }
 
+    /// Set an additional namespace client property.
+    pub fn namespace_client_property(
+        mut self,
+        key: impl Into<String>,
+        value: impl Into<String>,
+    ) -> Self {
+        self.namespace_client_properties
+            .insert(key.into(), value.into());
+        self
+    }
+
+    /// Set multiple additional namespace client properties.
+    pub fn namespace_client_properties(
+        mut self,
+        pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
+    ) -> Self {
+        for (key, value) in pairs {
+            self.namespace_client_properties
+                .insert(key.into(), value.into());
+        }
+        self
+    }
+
     /// The interval at which to check for updates from other processes.
     ///
     /// If left unset, consistency is not checked. For maximum read
@@ -970,11 +1029,11 @@ impl ConnectNamespaceBuilder {
     /// and leveraging server-side compute resources.
     ///
     /// Available operations:
-    /// - [`PushdownOperation::QueryTable`]: Execute queries via `namespace.query_table()`
-    /// - [`PushdownOperation::CreateTable`]: Execute table creation via `namespace.create_table()`
+    /// - [`NamespaceClientPushdownOperation::QueryTable`]: Execute queries via `namespace.query_table()`
+    /// - [`NamespaceClientPushdownOperation::CreateTable`]: Execute table creation via `namespace.create_table()`
     ///
     /// By default, no operations are pushed down (all executed locally).
-    pub fn pushdown_operation(mut self, operation: PushdownOperation) -> Self {
+    pub fn pushdown_operation(mut self, operation: NamespaceClientPushdownOperation) -> Self {
         self.pushdown_operations.insert(operation);
         self
     }
@@ -984,7 +1043,7 @@ impl ConnectNamespaceBuilder {
     /// See [`Self::pushdown_operation`] for details.
     pub fn pushdown_operations(
         mut self,
-        operations: impl IntoIterator<Item = PushdownOperation>,
+        operations: impl IntoIterator<Item = NamespaceClientPushdownOperation>,
     ) -> Self {
         self.pushdown_operations.extend(operations);
         self
@@ -994,10 +1053,13 @@ impl ConnectNamespaceBuilder {
     pub async fn execute(self) -> Result<Connection> {
         use crate::database::namespace::LanceNamespaceDatabase;
 
+        let mut properties = self.properties;
+        properties.extend(self.namespace_client_properties);
+
         let internal = Arc::new(
             LanceNamespaceDatabase::connect(
                 &self.ns_impl,
-                self.properties,
+                properties,
                 self.storage_options,
                 self.read_consistency_interval,
                 self.session,
@@ -1117,6 +1179,31 @@ mod tests {
         assert_eq!(db.uri(), relative_uri.to_str().unwrap().to_string());
     }
 
+    #[tokio::test]
+    async fn test_connect_with_namespace_client_properties() {
+        let tmp_dir = tempdir().unwrap();
+        let uri = tmp_dir.path().to_str().unwrap();
+
+        let db = connect(uri)
+            .namespace_client_property("table_version_tracking_enabled", "true")
+            .namespace_client_property("manifest_enabled", "true")
+            .execute()
+            .await
+            .unwrap();
+
+        let (ns_impl, properties) = db.namespace_client_config().await.unwrap();
+        assert_eq!(ns_impl, "dir");
+        assert_eq!(properties.get("root"), Some(&uri.to_string()));
+        assert_eq!(
+            properties.get("table_version_tracking_enabled"),
+            Some(&"true".to_string())
+        );
+        assert_eq!(
+            properties.get("manifest_enabled"),
+            Some(&"true".to_string())
+        );
+    }
+
     #[tokio::test]
     async fn test_table_names() {
         let tc = new_test_connection().await.unwrap();

rust/lancedb/src/connection/create_table.rs

@@ -55,7 +55,7 @@ impl CreateTableBuilder {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         let store_params = self
             .request
@@ -73,7 +73,7 @@ impl CreateTableBuilder {
     /// Options already set on the connection will be inherited by the table,
     /// but can be overridden here.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,

rust/lancedb/src/database/listing.rs

@@ -20,6 +20,7 @@ use snafu::ResultExt;
 
 use crate::connection::ConnectRequest;
 use crate::database::ReadConsistency;
+use crate::database::namespace::LanceNamespaceDatabase;
 use crate::error::{CreateDirSnafu, Error, Result};
 use crate::io::object_store::MirroringObjectStoreWrapper;
 use crate::table::NativeTable;
@@ -73,7 +74,7 @@ pub struct ListingDatabaseOptions {
     /// These are used to create/list tables and they are inherited by all tables
     /// opened by this database.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub storage_options: HashMap<String, String>,
 }
 
@@ -185,7 +186,7 @@ impl ListingDatabaseOptionsBuilder {
 
     /// Set an option for the storage layer.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_option(mut self, key: impl Into<String>, value: impl Into<String>) -> Self {
         self.options
             .storage_options
@@ -195,7 +196,7 @@ impl ListingDatabaseOptionsBuilder {
 
     /// Set multiple options for the storage layer.
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     pub fn storage_options(
         mut self,
         pairs: impl IntoIterator<Item = (impl Into<String>, impl Into<String>)>,
@@ -255,6 +256,9 @@ pub struct ListingDatabase {
 
     // Session for object stores and caching
     session: Arc<lance::session::Session>,
+
+    // Namespace-backed database for child namespace operations
+    namespace_database: Arc<LanceNamespaceDatabase>,
 }
 
 impl std::fmt::Display for ListingDatabase {
@@ -281,6 +285,44 @@ const MIRRORED_STORE: &str = "mirroredStore";
 
 /// A connection to LanceDB
 impl ListingDatabase {
+    fn build_namespace_client_properties(
+        uri: &str,
+        storage_options: &HashMap<String, String>,
+        namespace_client_properties: HashMap<String, String>,
+    ) -> HashMap<String, String> {
+        let mut properties = namespace_client_properties;
+        properties.insert("root".to_string(), uri.to_string());
+        for (key, value) in storage_options {
+            properties.insert(format!("storage.{}", key), value.clone());
+        }
+        properties
+    }
+
+    async fn connect_namespace_database(
+        uri: &str,
+        storage_options: HashMap<String, String>,
+        namespace_client_properties: HashMap<String, String>,
+        read_consistency_interval: Option<std::time::Duration>,
+        session: Arc<lance::session::Session>,
+    ) -> Result<Arc<LanceNamespaceDatabase>> {
+        let ns_properties = Self::build_namespace_client_properties(
+            uri,
+            &storage_options,
+            namespace_client_properties,
+        );
+        Ok(Arc::new(
+            LanceNamespaceDatabase::connect(
+                "dir",
+                ns_properties,
+                storage_options,
+                read_consistency_interval,
+                Some(session),
+                HashSet::new(),
+            )
+            .await?,
+        ))
+    }
+
     /// Connect to a listing database
     ///
     /// The URI should be a path to a directory where the tables are stored.
@@ -300,6 +342,7 @@ impl ListingDatabase {
                     uri,
                     request.read_consistency_interval,
                     options.new_table_config,
+                    request.namespace_client_properties.clone(),
                     request.session.clone(),
                 )
                 .await
@@ -387,6 +430,15 @@ impl ListingDatabase {
                     None => None,
                 };
 
+                let namespace_database = Self::connect_namespace_database(
+                    &table_base_uri,
+                    options.storage_options.clone(),
+                    request.namespace_client_properties.clone(),
+                    request.read_consistency_interval,
+                    session.clone(),
+                )
+                .await?;
+
                 Ok(Self {
                     uri: table_base_uri,
                     query_string,
@@ -398,6 +450,7 @@ impl ListingDatabase {
                     storage_options_provider: None,
                     new_table_config: options.new_table_config,
                     session,
+                    namespace_database,
                 })
             }
             Err(_) => {
@@ -405,6 +458,7 @@ impl ListingDatabase {
                     uri,
                     request.read_consistency_interval,
                     options.new_table_config,
+                    request.namespace_client_properties.clone(),
                     request.session.clone(),
                 )
                 .await
@@ -416,6 +470,7 @@ impl ListingDatabase {
         path: &str,
         read_consistency_interval: Option<std::time::Duration>,
         new_table_config: NewTableConfig,
+        namespace_client_properties: HashMap<String, String>,
         session: Option<Arc<lance::session::Session>>,
     ) -> Result<Self> {
         let session = session.unwrap_or_else(|| Arc::new(lance::session::Session::default()));
@@ -429,6 +484,15 @@ impl ListingDatabase {
             Self::try_create_dir(path).context(CreateDirSnafu { path })?;
         }
 
+        let namespace_database = Self::connect_namespace_database(
+            path,
+            HashMap::new(),
+            namespace_client_properties,
+            read_consistency_interval,
+            session.clone(),
+        )
+        .await?;
+
         Ok(Self {
             uri: path.to_string(),
             query_string: None,
@@ -440,6 +504,7 @@ impl ListingDatabase {
             storage_options_provider: None,
             new_table_config,
             session,
+            namespace_database,
         })
     }
 
@@ -497,6 +562,10 @@ impl ListingDatabase {
         Ok(uri)
     }
 
+    fn namespace_database(&self) -> Arc<LanceNamespaceDatabase> {
+        self.namespace_database.clone()
+    }
+
     async fn drop_tables(&self, names: Vec<String>) -> Result<()> {
         let object_store_params = ObjectStoreParams {
             storage_options_accessor: if self.storage_options.is_empty() {
@@ -696,16 +765,7 @@ impl Database for ListingDatabase {
         &self,
         request: ListNamespacesRequest,
     ) -> Result<ListNamespacesResponse> {
-        if request.id.as_ref().map(|v| !v.is_empty()).unwrap_or(false) {
-            return Err(Error::NotSupported {
-                message: "Namespace operations are not supported for listing database".into(),
-            });
-        }
-
-        Ok(ListNamespacesResponse {
-            namespaces: Vec::new(),
-            page_token: None,
-        })
+        self.namespace_database().list_namespaces(request).await
     }
 
     fn uri(&self) -> &str {
@@ -726,36 +786,26 @@ impl Database for ListingDatabase {
 
     async fn create_namespace(
         &self,
-        _request: CreateNamespaceRequest,
+        request: CreateNamespaceRequest,
     ) -> Result<CreateNamespaceResponse> {
-        Err(Error::NotSupported {
-            message: "Namespace operations are not supported for listing database".into(),
-        })
+        self.namespace_database().create_namespace(request).await
     }
 
-    async fn drop_namespace(
-        &self,
-        _request: DropNamespaceRequest,
-    ) -> Result<DropNamespaceResponse> {
-        Err(Error::NotSupported {
-            message: "Namespace operations are not supported for listing database".into(),
-        })
+    async fn drop_namespace(&self, request: DropNamespaceRequest) -> Result<DropNamespaceResponse> {
+        self.namespace_database().drop_namespace(request).await
     }
 
     async fn describe_namespace(
         &self,
-        _request: DescribeNamespaceRequest,
+        request: DescribeNamespaceRequest,
     ) -> Result<DescribeNamespaceResponse> {
-        Err(Error::NotSupported {
-            message: "Namespace operations are not supported for listing database".into(),
-        })
+        self.namespace_database().describe_namespace(request).await
     }
 
+    #[allow(deprecated)]
     async fn table_names(&self, request: TableNamesRequest) -> Result<Vec<String>> {
         if !request.namespace_path.is_empty() {
-            return Err(Error::NotSupported {
-                message: "Namespace parameter is not supported for listing database. Only root namespace is supported.".into(),
-            });
+            return self.namespace_database().table_names(request).await;
         }
         let mut f = self
             .object_store
@@ -788,9 +838,7 @@ impl Database for ListingDatabase {
 
     async fn list_tables(&self, request: ListTablesRequest) -> Result<ListTablesResponse> {
         if request.id.as_ref().map(|v| !v.is_empty()).unwrap_or(false) {
-            return Err(Error::NotSupported {
-                message: "Namespace parameter is not supported for listing database. Only root namespace is supported.".into(),
-            });
+            return self.namespace_database().list_tables(request).await;
         }
         let mut f = self
             .object_store
@@ -838,11 +886,8 @@ impl Database for ListingDatabase {
     }
 
     async fn create_table(&self, request: CreateTableRequest) -> Result<Arc<dyn BaseTable>> {
-        // When namespace is not empty, location must be provided
-        if !request.namespace_path.is_empty() && request.location.is_none() {
-            return Err(Error::InvalidInput {
-                message: "Location must be provided when namespace is not empty".into(),
-            });
+        if !request.namespace_path.is_empty() {
+            return self.namespace_database().create_table(request).await;
         }
         // Use provided location if available, otherwise derive from table name
         let table_uri = request
@@ -959,11 +1004,8 @@ impl Database for ListingDatabase {
     }
 
     async fn open_table(&self, mut request: OpenTableRequest) -> Result<Arc<dyn BaseTable>> {
-        // When namespace is not empty, location must be provided
-        if !request.namespace_path.is_empty() && request.location.is_none() {
-            return Err(Error::InvalidInput {
-                message: "Location must be provided when namespace is not empty".into(),
-            });
+        if !request.namespace_path.is_empty() {
+            return self.namespace_database().open_table(request).await;
         }
         // Use provided location if available, otherwise derive from table name
         let table_uri = request
@@ -1059,9 +1101,10 @@ impl Database for ListingDatabase {
 
     async fn drop_table(&self, name: &str, namespace_path: &[String]) -> Result<()> {
         if !namespace_path.is_empty() {
-            return Err(Error::NotSupported {
-                message: "Namespace parameter is not supported for listing database.".into(),
-            });
+            return self
+                .namespace_database()
+                .drop_table(name, namespace_path)
+                .await;
         }
         self.drop_tables(vec![name.to_string()]).await
     }
@@ -1070,9 +1113,10 @@ impl Database for ListingDatabase {
     async fn drop_all_tables(&self, namespace_path: &[String]) -> Result<()> {
         // Check if namespace parameter is provided
         if !namespace_path.is_empty() {
-            return Err(Error::NotSupported {
-                message: "Namespace parameter is not supported for listing database.".into(),
-            });
+            return self
+                .namespace_database()
+                .drop_all_tables(namespace_path)
+                .await;
         }
         let tables = self.table_names(TableNamesRequest::default()).await?;
         self.drop_tables(tables).await
@@ -1083,30 +1127,11 @@ impl Database for ListingDatabase {
     }
 
     async fn namespace_client(&self) -> Result<Arc<dyn lance_namespace::LanceNamespace>> {
-        // Create a DirectoryNamespace pointing to the same root with the same storage options
-        let mut builder = lance_namespace_impls::DirectoryNamespaceBuilder::new(&self.uri);
-
-        // Add storage options
-        if !self.storage_options.is_empty() {
-            builder = builder.storage_options(self.storage_options.clone());
-        }
-
-        // Use the same session
-        builder = builder.session(self.session.clone());
-
-        let namespace = builder.build().await.map_err(|e| Error::Runtime {
-            message: format!("Failed to create namespace client: {}", e),
-        })?;
-        Ok(Arc::new(namespace) as Arc<dyn lance_namespace::LanceNamespace>)
+        self.namespace_database.namespace_client().await
     }
 
     async fn namespace_client_config(&self) -> Result<(String, HashMap<String, String>)> {
-        let mut properties = HashMap::new();
-        properties.insert("root".to_string(), self.uri.clone());
-        for (key, value) in &self.storage_options {
-            properties.insert(format!("storage.{}", key), value.clone());
-        }
-        Ok(("dir".to_string(), properties))
+        self.namespace_database.namespace_client_config().await
     }
 }
 
@@ -1132,6 +1157,7 @@ mod tests {
             #[cfg(feature = "remote")]
             client_config: Default::default(),
             options: Default::default(),
+            namespace_client_properties: Default::default(),
             read_consistency_interval: None,
             session: None,
         };
@@ -1265,6 +1291,7 @@ mod tests {
             #[cfg(feature = "remote")]
             client_config: Default::default(),
             options: options.clone(),
+            namespace_client_properties: Default::default(),
             read_consistency_interval: None,
             session: None,
         };
@@ -1799,6 +1826,7 @@ mod tests {
             #[cfg(feature = "remote")]
             client_config: Default::default(),
             options,
+            namespace_client_properties: Default::default(),
             read_consistency_interval: None,
             session: None,
         };
@@ -1904,6 +1932,7 @@ mod tests {
             #[cfg(feature = "remote")]
             client_config: Default::default(),
             options,
+            namespace_client_properties: Default::default(),
             read_consistency_interval: None,
             session: None,
         };
@@ -1975,6 +2004,7 @@ mod tests {
             #[cfg(feature = "remote")]
             client_config: Default::default(),
             options,
+            namespace_client_properties: Default::default(),
             read_consistency_interval: None,
             session: None,
         };
@@ -2108,4 +2138,209 @@ mod tests {
         assert!(tables.contains(&"table1".to_string()));
         assert!(tables.contains(&"table2".to_string()));
     }
+
+    #[tokio::test]
+    async fn test_listing_database_namespace_operations() {
+        let (_tempdir, db) = setup_database().await;
+
+        db.create_namespace(CreateNamespaceRequest {
+            id: Some(vec!["parent".to_string()]),
+            ..Default::default()
+        })
+        .await
+        .unwrap();
+
+        db.create_namespace(CreateNamespaceRequest {
+            id: Some(vec!["parent".to_string(), "child".to_string()]),
+            ..Default::default()
+        })
+        .await
+        .unwrap();
+
+        let root_namespaces = db
+            .list_namespaces(ListNamespacesRequest {
+                id: Some(vec![]),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+        assert!(root_namespaces.namespaces.contains(&"parent".to_string()));
+
+        let child_namespaces = db
+            .list_namespaces(ListNamespacesRequest {
+                id: Some(vec!["parent".to_string()]),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+        assert!(child_namespaces.namespaces.contains(&"child".to_string()));
+
+        db.describe_namespace(DescribeNamespaceRequest {
+            id: Some(vec!["parent".to_string(), "child".to_string()]),
+            ..Default::default()
+        })
+        .await
+        .unwrap();
+    }
+
+    #[tokio::test]
+    #[cfg(not(windows))] // TODO: support Windows once directory namespace-backed listing DB tests are supported.
+    async fn test_listing_database_with_namespace_client_properties() {
+        let tempdir = tempdir().unwrap();
+        let uri = tempdir.path().to_str().unwrap();
+
+        let mut namespace_client_properties = HashMap::new();
+        namespace_client_properties.insert(
+            "table_version_tracking_enabled".to_string(),
+            "true".to_string(),
+        );
+        namespace_client_properties.insert("manifest_enabled".to_string(), "true".to_string());
+
+        let request = ConnectRequest {
+            uri: uri.to_string(),
+            #[cfg(feature = "remote")]
+            client_config: Default::default(),
+            options: Default::default(),
+            namespace_client_properties,
+            read_consistency_interval: None,
+            session: None,
+        };
+
+        let db = ListingDatabase::connect_with_options(&request)
+            .await
+            .unwrap();
+        let namespace_path = vec!["test_ns".to_string()];
+
+        db.create_namespace(CreateNamespaceRequest {
+            id: Some(namespace_path.clone()),
+            ..Default::default()
+        })
+        .await
+        .unwrap();
+
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("id", DataType::Int32, false),
+            Field::new("name", DataType::Utf8, false),
+        ]));
+
+        db.create_table(CreateTableRequest {
+            name: "managed_table".to_string(),
+            namespace_path: namespace_path.clone(),
+            data: Box::new(RecordBatch::new_empty(schema)) as Box<dyn Scannable>,
+            mode: CreateTableMode::Create,
+            write_options: Default::default(),
+            location: None,
+            namespace_client: None,
+        })
+        .await
+        .unwrap();
+
+        let namespace_client = db.namespace_client().await.unwrap();
+        let describe = namespace_client
+            .describe_table(lance_namespace::models::DescribeTableRequest {
+                id: Some(vec!["test_ns".to_string(), "managed_table".to_string()]),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+
+        assert_eq!(describe.managed_versioning, Some(true));
+    }
+
+    #[tokio::test]
+    async fn test_listing_database_nested_namespace_table_ops() {
+        let (_tempdir, db) = setup_database().await;
+        let namespace_path = vec!["parent".to_string(), "child".to_string()];
+
+        db.create_namespace(CreateNamespaceRequest {
+            id: Some(vec!["parent".to_string()]),
+            ..Default::default()
+        })
+        .await
+        .unwrap();
+        db.create_namespace(CreateNamespaceRequest {
+            id: Some(namespace_path.clone()),
+            ..Default::default()
+        })
+        .await
+        .unwrap();
+
+        let schema = Arc::new(Schema::new(vec![
+            Field::new("id", DataType::Int32, false),
+            Field::new("name", DataType::Utf8, false),
+        ]));
+
+        db.create_table(CreateTableRequest {
+            name: "nested_table".to_string(),
+            namespace_path: namespace_path.clone(),
+            data: Box::new(RecordBatch::new_empty(schema)) as Box<dyn Scannable>,
+            mode: CreateTableMode::Create,
+            write_options: Default::default(),
+            location: None,
+            namespace_client: None,
+        })
+        .await
+        .unwrap();
+
+        let namespace_client = db.namespace_client().await.unwrap();
+        let describe = namespace_client
+            .describe_table(lance_namespace::models::DescribeTableRequest {
+                id: Some(vec![
+                    "parent".to_string(),
+                    "child".to_string(),
+                    "nested_table".to_string(),
+                ]),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+        assert!(describe.location.is_some());
+
+        let table = db
+            .open_table(OpenTableRequest {
+                name: "nested_table".to_string(),
+                namespace_path: namespace_path.clone(),
+                index_cache_size: None,
+                lance_read_params: None,
+                location: None,
+                namespace_client: None,
+                managed_versioning: None,
+            })
+            .await
+            .unwrap();
+        assert_eq!(table.name(), "nested_table");
+
+        #[allow(deprecated)]
+        let table_names = db
+            .table_names(TableNamesRequest {
+                namespace_path: namespace_path.clone(),
+                start_after: None,
+                limit: None,
+            })
+            .await
+            .unwrap();
+        assert_eq!(table_names, vec!["nested_table".to_string()]);
+
+        let list_tables = db
+            .list_tables(ListTablesRequest {
+                id: Some(namespace_path.clone()),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+        assert_eq!(list_tables.tables, vec!["nested_table".to_string()]);
+
+        db.drop_table("nested_table", &namespace_path)
+            .await
+            .unwrap();
+
+        let post_drop = db
+            .list_tables(ListTablesRequest {
+                id: Some(namespace_path),
+                ..Default::default()
+            })
+            .await
+            .unwrap();
+        assert!(post_drop.tables.is_empty());
+    }
 }

rust/lancedb/src/database/namespace.rs

@@ -8,7 +8,9 @@ use std::sync::Arc;
 
 use async_trait::async_trait;
 use lance::io::commit::namespace_manifest::LanceNamespaceExternalManifestStore;
-use lance_io::object_store::{ObjectStoreParams, StorageOptionsAccessor};
+use lance_io::object_store::{
+    ObjectStore as LanceObjectStore, ObjectStoreParams, ObjectStoreRegistry, StorageOptionsAccessor,
+};
 use lance_namespace::{
     LanceNamespace,
     models::{
@@ -22,10 +24,11 @@ use lance_namespace_impls::ConnectBuilder;
 use lance_table::io::commit::CommitHandler;
 use lance_table::io::commit::external_manifest::ExternalManifestCommitHandler;
 
-use crate::connection::PushdownOperation;
+use crate::connection::NamespaceClientPushdownOperation;
 use crate::database::ReadConsistency;
 use crate::error::{Error, Result};
 use crate::table::NativeTable;
+use lance::dataset::WriteMode;
 
 use super::{
     BaseTable, CloneTableRequest, CreateTableMode, CreateTableRequest as DbCreateTableRequest,
@@ -44,7 +47,7 @@ pub struct LanceNamespaceDatabase {
     // database URI
     uri: String,
     // Operations to push down to the namespace server
-    pushdown_operations: HashSet<PushdownOperation>,
+    pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
     // Namespace implementation type (e.g., "dir", "rest")
     ns_impl: String,
     // Namespace properties used to construct the namespace client
@@ -52,13 +55,34 @@ pub struct LanceNamespaceDatabase {
 }
 
 impl LanceNamespaceDatabase {
+    pub fn from_namespace_client(
+        namespace_client: Arc<dyn LanceNamespace>,
+        namespace_client_impl: String,
+        namespace_client_properties: HashMap<String, String>,
+        storage_options: HashMap<String, String>,
+        read_consistency_interval: Option<std::time::Duration>,
+        session: Option<Arc<lance::session::Session>>,
+        namespace_client_pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
+    ) -> Self {
+        Self {
+            namespace: namespace_client,
+            storage_options,
+            read_consistency_interval,
+            session,
+            uri: format!("namespace://{}", namespace_client_impl),
+            pushdown_operations: namespace_client_pushdown_operations,
+            ns_impl: namespace_client_impl,
+            ns_properties: namespace_client_properties,
+        }
+    }
+
     pub async fn connect(
         ns_impl: &str,
         ns_properties: HashMap<String, String>,
         storage_options: HashMap<String, String>,
         read_consistency_interval: Option<std::time::Duration>,
         session: Option<Arc<lance::session::Session>>,
-        pushdown_operations: HashSet<PushdownOperation>,
+        pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
     ) -> Result<Self> {
         let mut builder = ConnectBuilder::new(ns_impl);
         for (key, value) in ns_properties.clone() {
@@ -163,37 +187,23 @@ impl Database for LanceNamespaceDatabase {
     async fn create_table(&self, request: DbCreateTableRequest) -> Result<Arc<dyn BaseTable>> {
         let mut table_id = request.namespace_path.clone();
         table_id.push(request.name.clone());
-        let describe_request = DescribeTableRequest {
-            id: Some(table_id.clone()),
-            ..Default::default()
-        };
-
-        let describe_result = self.namespace.describe_table(describe_request).await;
+        let mut existing_table = None;
 
         match request.mode {
-            CreateTableMode::Create => {
-                if describe_result.is_ok() {
-                    return Err(Error::TableAlreadyExists {
-                        name: request.name.clone(),
-                    });
-                }
-            }
+            CreateTableMode::Create => {}
             CreateTableMode::Overwrite => {
-                if describe_result.is_ok() {
-                    // Drop the existing table - must succeed
-                    let drop_request = DropTableRequest {
-                        id: Some(table_id.clone()),
-                        ..Default::default()
-                    };
-                    self.namespace
-                        .drop_table(drop_request)
-                        .await
-                        .map_err(|e| Error::Runtime {
-                            message: format!("Failed to drop existing table for overwrite: {}", e),
-                        })?;
-                }
+                let describe_request = DescribeTableRequest {
+                    id: Some(table_id.clone()),
+                    ..Default::default()
+                };
+                existing_table = self.namespace.describe_table(describe_request).await.ok();
             }
             CreateTableMode::ExistOk(_) => {
+                let describe_request = DescribeTableRequest {
+                    id: Some(table_id.clone()),
+                    ..Default::default()
+                };
+                let describe_result = self.namespace.describe_table(describe_request).await;
                 if describe_result.is_ok() {
                     let native_table = NativeTable::open_from_namespace(
                         self.namespace.clone(),
@@ -221,21 +231,82 @@ impl Database for LanceNamespaceDatabase {
         };
 
         let (location, initial_storage_options, managed_versioning) = {
-            let response = self.namespace.declare_table(declare_request).await?;
-            let loc = response.location.ok_or_else(|| Error::Runtime {
-                message: "Table location is missing from declare_table response".to_string(),
-            })?;
-            // Use storage options from response, fall back to self.storage_options
-            let opts = response
-                .storage_options
-                .or_else(|| Some(self.storage_options.clone()))
-                .filter(|o| !o.is_empty());
-            (loc, opts, response.managed_versioning)
+            if let Some(response) = existing_table {
+                let loc = response.location.ok_or_else(|| Error::Runtime {
+                    message: "Table location is missing from describe_table response".to_string(),
+                })?;
+                let opts = response
+                    .storage_options
+                    .or_else(|| Some(self.storage_options.clone()))
+                    .filter(|o| !o.is_empty());
+                (loc, opts, response.managed_versioning)
+            } else {
+                match self.namespace.declare_table(declare_request).await {
+                    Ok(response) => {
+                        let loc = response.location.ok_or_else(|| Error::Runtime {
+                            message: "Table location is missing from declare_table response"
+                                .to_string(),
+                        })?;
+                        let opts = response
+                            .storage_options
+                            .or_else(|| Some(self.storage_options.clone()))
+                            .filter(|o: &HashMap<String, String>| !o.is_empty());
+                        (loc, opts, response.managed_versioning)
+                    }
+                    Err(e)
+                        if matches!(request.mode, CreateTableMode::Create) && {
+                            let err_str = e.to_string();
+                            err_str.contains("already exists")
+                                || err_str.contains("TableAlreadyExists")
+                                || err_str.contains("table already exists")
+                        } =>
+                    {
+                        let response = self
+                            .namespace
+                            .describe_table(DescribeTableRequest {
+                                id: Some(table_id.clone()),
+                                ..Default::default()
+                            })
+                            .await
+                            .map_err(|describe_err| Error::Runtime {
+                                message: format!(
+                                    "Failed to describe existing declared table after declare conflict: {}",
+                                    describe_err
+                                ),
+                            })?;
+
+                        if response.version.is_some() && response.schema.is_some() {
+                            return Err(Error::TableAlreadyExists {
+                                name: request.name.clone(),
+                            });
+                        }
+
+                        let loc = response.location.ok_or_else(|| Error::Runtime {
+                            message: "Table location is missing from describe_table response"
+                                .to_string(),
+                        })?;
+                        let opts = response
+                            .storage_options
+                            .or_else(|| Some(self.storage_options.clone()))
+                            .filter(|o: &HashMap<String, String>| !o.is_empty());
+                        (loc, opts, response.managed_versioning)
+                    }
+                    Err(e) => {
+                        return Err(Error::Runtime {
+                            message: format!("Failed to declare table: {}", e),
+                        });
+                    }
+                }
+            }
         };
 
         // Build write params with storage options and commit handler
         let mut params = request.write_options.lance_write_params.unwrap_or_default();
 
+        if matches!(request.mode, CreateTableMode::Overwrite) {
+            params.mode = WriteMode::Overwrite;
+        }
+
         // Set up storage options if provided
         if let Some(storage_opts) = initial_storage_options {
             let store_params = params
@@ -272,6 +343,20 @@ impl Database for LanceNamespaceDatabase {
         )
         .await?;
 
+        // lance >= v6.0.0-beta.2: declare_table creates a `.lance-reserved` marker file to
+        // prevent directory scanning from seeing an incomplete table. After writing data we
+        // must remove it so the table appears in directory listings.
+        if let Ok(dataset) = native_table.dataset.get().await {
+            let registry = Arc::new(ObjectStoreRegistry::default());
+            if let Ok(table_path) = LanceObjectStore::extract_path_from_uri(registry, dataset.uri())
+            {
+                let _ = dataset
+                    .object_store
+                    .delete(&table_path.child(".lance-reserved"))
+                    .await;
+            }
+        }
+
         Ok(Arc::new(native_table))
     }
 
@@ -450,6 +535,47 @@ mod tests {
         ));
     }
 
+    #[tokio::test]
+    async fn test_namespace_connection_with_namespace_client_properties() {
+        let tmp_dir = tempdir().unwrap();
+        let root_path = tmp_dir.path().to_str().unwrap().to_string();
+
+        let mut properties = HashMap::new();
+        properties.insert("root".to_string(), root_path);
+
+        let conn = connect_namespace("dir", properties)
+            .namespace_client_property("table_version_tracking_enabled", "true")
+            .namespace_client_property("manifest_enabled", "true")
+            .execute()
+            .await
+            .expect("Failed to connect to namespace");
+
+        conn.create_namespace(CreateNamespaceRequest {
+            id: Some(vec!["test_ns".into()]),
+            ..Default::default()
+        })
+        .await
+        .expect("Failed to create namespace");
+
+        let test_data = create_test_data();
+        conn.create_table("test_table", test_data)
+            .namespace(vec!["test_ns".into()])
+            .execute()
+            .await
+            .expect("Failed to create table");
+
+        let namespace_client = conn.namespace_client().await.unwrap();
+        let describe = namespace_client
+            .describe_table(DescribeTableRequest {
+                id: Some(vec!["test_ns".into(), "test_table".into()]),
+                ..Default::default()
+            })
+            .await
+            .expect("Failed to describe table");
+
+        assert_eq!(describe.managed_versioning, Some(true));
+    }
+
     #[tokio::test]
     async fn test_namespace_create_table_basic() {
         // Setup: Create a temporary directory for the namespace
@@ -651,6 +777,58 @@ mod tests {
         assert_eq!(id_col.value(2), 30);
     }
 
+    #[tokio::test]
+    async fn test_namespace_create_table_after_declare_conflict() {
+        let tmp_dir = tempdir().unwrap();
+        let root_path = tmp_dir.path().to_str().unwrap().to_string();
+
+        let mut properties = HashMap::new();
+        properties.insert("root".to_string(), root_path);
+
+        let conn = connect_namespace("dir", properties)
+            .execute()
+            .await
+            .expect("Failed to connect to namespace");
+
+        conn.create_namespace(CreateNamespaceRequest {
+            id: Some(vec!["test_ns".into()]),
+            ..Default::default()
+        })
+        .await
+        .expect("Failed to create namespace");
+
+        let namespace_client = conn.namespace_client().await.unwrap();
+        namespace_client
+            .declare_table(DeclareTableRequest {
+                id: Some(vec!["test_ns".into(), "declared_test".into()]),
+                ..Default::default()
+            })
+            .await
+            .expect("Failed to declare table");
+
+        let test_data = create_test_data();
+        let table = conn
+            .create_table("declared_test", test_data)
+            .namespace(vec!["test_ns".into()])
+            .execute()
+            .await
+            .expect("Failed to create table after declare conflict");
+
+        let results = table
+            .query()
+            .execute()
+            .await
+            .expect("Failed to query table")
+            .try_collect::<Vec<_>>()
+            .await
+            .expect("Failed to collect results");
+
+        assert_eq!(results.len(), 1);
+        assert_eq!(results[0].num_rows(), 5);
+        assert_eq!(table.namespace(), &["test_ns"]);
+        assert_eq!(table.id(), "test_ns$declared_test");
+    }
+
     #[tokio::test]
     async fn test_namespace_create_table_exist_ok_mode() {
         // Setup: Create a temporary directory for the namespace

rust/lancedb/src/lib.rs

@@ -69,7 +69,7 @@
 //! It treats [`FixedSizeList<Float16/Float32>`](https://docs.rs/arrow/latest/arrow/array/struct.FixedSizeListArray.html)
 //! columns as vector columns.
 //!
-//! For more details, please refer to the [LanceDB documentation](https://lancedb.com/docs).
+//! For more details, please refer to the [LanceDB documentation](https://docs.lancedb.com).
 //!
 //! #### Create a table
 //!

rust/lancedb/src/remote/client.rs

@@ -16,7 +16,7 @@ use crate::remote::retry::{ResolvedRetryConfig, RetryCounter};
 const REQUEST_ID_HEADER: HeaderName = HeaderName::from_static("x-request-id");
 
 /// Configuration for TLS/mTLS settings.
-#[derive(Clone, Debug, Default)]
+#[derive(Clone, Debug)]
 pub struct TlsConfig {
     /// Path to the client certificate file (PEM format)
     pub cert_file: Option<String>,
@@ -24,10 +24,22 @@ pub struct TlsConfig {
     pub key_file: Option<String>,
     /// Path to the CA certificate file for server verification (PEM format)
     pub ssl_ca_cert: Option<String>,
-    /// Whether to verify the hostname in the server's certificate
+    /// Whether to verify the hostname in the server's certificate.
+    /// Defaults to `true`.
     pub assert_hostname: bool,
 }
 
+impl Default for TlsConfig {
+    fn default() -> Self {
+        Self {
+            cert_file: None,
+            key_file: None,
+            ssl_ca_cert: None,
+            assert_hostname: true,
+        }
+    }
+}
+
 /// Trait for providing custom headers for each request
 #[async_trait::async_trait]
 pub trait HeaderProvider: Send + Sync + std::fmt::Debug {
@@ -926,7 +938,7 @@ mod tests {
         assert!(config.cert_file.is_none());
         assert!(config.key_file.is_none());
         assert!(config.ssl_ca_cert.is_none());
-        assert!(!config.assert_hostname);
+        assert!(config.assert_hostname);
     }
 
     #[test]

rust/lancedb/src/remote/db.rs

@@ -97,7 +97,7 @@ pub struct RemoteDatabaseOptions {
     pub host_override: Option<String>,
     /// Storage options configure the storage layer (e.g. S3, GCS, Azure, etc.)
     ///
-    /// See available options at <https://lancedb.com/docs/storage/>
+    /// See available options at <https://docs.lancedb.com/storage/>
     ///
     /// These options are only used for LanceDB Enterprise and only a subset of options
     /// are supported.

rust/lancedb/src/table.rs

@@ -47,7 +47,7 @@ use std::format;
 use std::path::Path;
 use std::sync::Arc;
 
-use crate::connection::PushdownOperation;
+use crate::connection::NamespaceClientPushdownOperation;
 
 use crate::data::scannable::{PeekedScannable, Scannable, estimate_write_partitions};
 use crate::database::Database;
@@ -1272,7 +1272,7 @@ pub struct NativeTable {
     pub(crate) namespace_client: Option<Arc<dyn LanceNamespace>>,
     // Operations to push down to the namespace server.
     // pub(crate) so query.rs can access the field for server-side query execution.
-    pub(crate) pushdown_operations: HashSet<PushdownOperation>,
+    pub(crate) pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
 }
 
 impl std::fmt::Debug for NativeTable {
@@ -1359,7 +1359,7 @@ impl NativeTable {
         params: Option<ReadParams>,
         read_consistency_interval: Option<std::time::Duration>,
         namespace_client: Option<Arc<dyn LanceNamespace>>,
-        pushdown_operations: HashSet<PushdownOperation>,
+        pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
         managed_versioning: Option<bool>,
     ) -> Result<Self> {
         let params = params.unwrap_or_default();
@@ -1470,7 +1470,7 @@ impl NativeTable {
         write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
         params: Option<ReadParams>,
         read_consistency_interval: Option<std::time::Duration>,
-        pushdown_operations: HashSet<PushdownOperation>,
+        pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
         session: Option<Arc<lance::session::Session>>,
     ) -> Result<Self> {
         let mut params = params.unwrap_or_default();
@@ -1518,7 +1518,7 @@ impl NativeTable {
         let id = Self::build_id(&namespace, name);
 
         let stored_namespace_client =
-            if pushdown_operations.contains(&PushdownOperation::QueryTable) {
+            if pushdown_operations.contains(&NamespaceClientPushdownOperation::QueryTable) {
                 Some(namespace_client)
             } else {
                 None
@@ -1588,7 +1588,7 @@ impl NativeTable {
         params: Option<WriteParams>,
         read_consistency_interval: Option<std::time::Duration>,
         namespace_client: Option<Arc<dyn LanceNamespace>>,
-        pushdown_operations: HashSet<PushdownOperation>,
+        pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
     ) -> Result<Self> {
         // Default params uses format v1.
         let params = params.unwrap_or(WriteParams {
@@ -1635,7 +1635,7 @@ impl NativeTable {
         params: Option<WriteParams>,
         read_consistency_interval: Option<std::time::Duration>,
         namespace_client: Option<Arc<dyn LanceNamespace>>,
-        pushdown_operations: HashSet<PushdownOperation>,
+        pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
     ) -> Result<Self> {
         let data: Box<dyn Scannable> = Box::new(RecordBatch::new_empty(schema));
         Self::create(
@@ -1685,7 +1685,7 @@ impl NativeTable {
         write_store_wrapper: Option<Arc<dyn WrappingObjectStore>>,
         params: Option<WriteParams>,
         read_consistency_interval: Option<std::time::Duration>,
-        pushdown_operations: HashSet<PushdownOperation>,
+        pushdown_operations: HashSet<NamespaceClientPushdownOperation>,
         session: Option<Arc<lance::session::Session>>,
     ) -> Result<Self> {
         // Build table_id from namespace + name for the storage options provider
@@ -1738,7 +1738,7 @@ impl NativeTable {
         let id = Self::build_id(&namespace, name);
 
         let stored_namespace_client =
-            if pushdown_operations.contains(&PushdownOperation::QueryTable) {
+            if pushdown_operations.contains(&NamespaceClientPushdownOperation::QueryTable) {
                 Some(namespace_client)
             } else {
                 None

rust/lancedb/src/table/dataset.rs

@@ -285,7 +285,10 @@ mod tests {
 
     use super::*;
 
-    use crate::{connect, io::object_store::io_tracking::IoStatsHolder, table::WriteOptions};
+    use crate::{
+        connect, io::object_store::io_tracking::IoStatsHolder, table::WriteOptions,
+        utils::background_cache::clock,
+    };
 
     async fn create_test_dataset(uri: &str) -> Dataset {
         let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int32, false)]));
@@ -463,6 +466,10 @@ mod tests {
         let uri = dir.path().to_str().unwrap();
         let ds = create_test_dataset(uri).await;
 
+        // Other tests use a thread-local mock clock. Simulate leaked state from a
+        // previous test to ensure this wrapper starts from real time.
+        clock::advance_by(Duration::from_secs(60));
+
         let wrapper = DatasetConsistencyWrapper::new_latest(ds, Some(Duration::from_millis(200)));
 
         // Populate the cache

rust/lancedb/src/table/query.rs

@@ -4,7 +4,7 @@
 use std::sync::Arc;
 
 use super::NativeTable;
-use crate::connection::PushdownOperation;
+use crate::connection::NamespaceClientPushdownOperation;
 use crate::error::{Error, Result};
 use crate::expr::expr_to_sql_string;
 use crate::query::{
@@ -44,7 +44,7 @@ pub async fn execute_query(
     // If QueryTable pushdown is enabled and namespace client is configured, use server-side query execution
     if table
         .pushdown_operations
-        .contains(&PushdownOperation::QueryTable)
+        .contains(&NamespaceClientPushdownOperation::QueryTable)
         && let Some(ref namespace_client) = table.namespace_client
     {
         return execute_namespace_query(table, namespace_client.clone(), query, options).await;

rust/lancedb/src/utils/background_cache.rs

@@ -107,6 +107,14 @@ where
             refresh_window < ttl,
             "refresh_window ({refresh_window:?}) must be less than ttl ({ttl:?})"
         );
+        #[cfg(test)]
+        {
+            // Tests may advance the thread-local mock clock and leave it behind for
+            // the next test that happens to run on the same worker thread. Each new
+            // cache should start from a clean clock state instead of inheriting
+            // unrelated mock time from a previous test.
+            clock::clear_mock();
+        }
         Self {
             inner: Arc::new(Mutex::new(CacheInner {
                 state: State::Empty,