Bump version: 0.36.0-beta.1 → 0.36.0

The tests extra pinned 9.0.0rc1 because 9.0.0 had not been released yet.
It now resolves from PyPI instead of the preview index.

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.32.0-beta.3"
+current_version = "0.33.0-beta.0"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

Cargo.lock

@@ -3421,8 +3421,9 @@ checksum = "42703706b716c37f96a77aea830392ad231f44c9e9a67872fa5548707e11b11c"
 
 [[package]]
 name = "fsst"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d6f1155128aba964cf6925c22a667ed763b52c8c653693c4b46f8a79d509a8c1"
 dependencies = [
  "arrow-array",
  "rand 0.9.5",
@@ -4777,8 +4778,9 @@ checksum = "e037a2e1d8d5fdbd49b16a4ea09d5d6401c1f29eca5ff29d03d3824dba16256a"
 
 [[package]]
 name = "lance"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "23d04bed056e254bc6e31264b031c8492507ca57939586f016924081dcf221a9"
 dependencies = [
  "arc-swap",
  "arrow",
@@ -4852,8 +4854,9 @@ dependencies = [
 
 [[package]]
 name = "lance-arrow"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b6e7b87c8183988c40a6bd30a6d8ec588b84e53f702b82f19859dc71ba6c02bc"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4875,7 +4878,8 @@ dependencies = [
 [[package]]
 name = "lance-arrow-scalar"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "771f68b04b47f3addf781116f65061808de94b05e1e9411c23c18f32d14ebe79"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4889,17 +4893,20 @@ dependencies = [
 [[package]]
 name = "lance-arrow-stats"
 version = "58.0.0"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd47ec33c90bf29f688fd02118e37d3a5ad5c339caa3163f89e417dc0867001f"
 dependencies = [
  "arrow-array",
  "arrow-schema",
+ "half",
  "lance-arrow-scalar",
 ]
 
 [[package]]
 name = "lance-bitpacking"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4a4d84a3f36133c70bf89d306d813a29f8eb8555bba2b84995260867cfafdd5e"
 dependencies = [
  "arrayref",
  "crunchy",
@@ -4909,8 +4916,9 @@ dependencies = [
 
 [[package]]
 name = "lance-core"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "238c8a58308e7718d6bd96b53494eb7953fa299778bc4911cc571c3576e9446d"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -4933,7 +4941,6 @@ dependencies = [
  "object_store",
  "pin-project",
  "prost",
- "quick_cache",
  "rand 0.9.5",
  "roaring",
  "serde_json",
@@ -4949,8 +4956,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datafusion"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "12f0ac4e1cf2f9b1b2fb5ee11bcd04af617bdd6f6cca13726a41c4212220193e"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4980,8 +4988,9 @@ dependencies = [
 
 [[package]]
 name = "lance-datagen"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dd65e7ea88ab28e5d3e91b58a56c02bfd44c47474caae5f8aed1322df1611476"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4998,8 +5007,9 @@ dependencies = [
 
 [[package]]
 name = "lance-derive"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf46656b359786f0b73f13936193583972b7af6e53ccb542da87830be18e94b2"
 dependencies = [
  "proc-macro2",
  "quote",
@@ -5008,8 +5018,9 @@ dependencies = [
 
 [[package]]
 name = "lance-encoding"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4725f14fe6cc1b2a5644786b4afa828d0c243064e208fa17378f839243d049c0"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5044,8 +5055,9 @@ dependencies = [
 
 [[package]]
 name = "lance-file"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8c161b00eb5813f98f1d6d52e06f1b712f9eebb0a7f535a8dc1e1122ceca7307"
 dependencies = [
  "arrow-arith",
  "arrow-array",
@@ -5075,14 +5087,14 @@ dependencies = [
 
 [[package]]
 name = "lance-index"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bf7980b0a6287fd46b9308a31e2cf284065d5693bfb43336297f0400172670ad"
 dependencies = [
  "arc-swap",
  "arrow",
  "arrow-arith",
  "arrow-array",
- "arrow-ipc",
  "arrow-ord",
  "arrow-schema",
  "arrow-select",
@@ -5143,8 +5155,9 @@ dependencies = [
 
 [[package]]
 name = "lance-index-core"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a95f46ac3e4cdd710ca6929226cfb0dd343d5d2370ecb4b40e1c452043f7d27a"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5166,8 +5179,9 @@ dependencies = [
 
 [[package]]
 name = "lance-io"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6deecd351ed6849184cc83000eabb87c8a5bfc519996f92451284498af7b42c"
 dependencies = [
  "arrow",
  "arrow-arith",
@@ -5210,8 +5224,9 @@ dependencies = [
 
 [[package]]
 name = "lance-linalg"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0e5a9b99bd1f49bc2fe5afb81323141abc506c818f589de95dbab4f6143d9a88"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5227,8 +5242,9 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8624fd33a894b5f2eb411cb56588d29138137ce100dee8e335843828e249b860"
 dependencies = [
  "arrow",
  "async-trait",
@@ -5240,8 +5256,9 @@ dependencies = [
 
 [[package]]
 name = "lance-namespace-impls"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "39f0cb9651a65f8eb411d825f34967fff46ba575a76e6ae9becda6ee31c1a974"
 dependencies = [
  "arrow",
  "arrow-ipc",
@@ -5295,8 +5312,9 @@ dependencies = [
 
 [[package]]
 name = "lance-select"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bb5c718c141ea4f067203b11a54ccf57f8effbf963f345bc811f4837a660ad57"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5311,8 +5329,9 @@ dependencies = [
 
 [[package]]
 name = "lance-table"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ffc125611b4fe46f99f00b5262e71e17bd947a3bc3b81f3a4a604cc9ca290b3f"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -5351,8 +5370,9 @@ dependencies = [
 
 [[package]]
 name = "lance-testing"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2598f24fa7333b49fdfc9945dfe084dafef2fc9ac94b5017ab4fbe4cdcd59318"
 dependencies = [
  "arrow-array",
  "arrow-schema",
@@ -5365,8 +5385,9 @@ dependencies = [
 
 [[package]]
 name = "lance-tokenizer"
-version = "10.0.0-beta.5"
-source = "git+https://github.com/lance-format/lance.git?tag=v10.0.0-beta.5#ddb8e28ca238f29628b8e1795ddccbb7bf75e5c8"
+version = "9.0.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73060a844ceda2405759b8f0f16a1c586b5b285dbdf7a3784350d048f991cfd3"
 dependencies = [
  "icu_segmenter",
  "jieba-rs",
@@ -5379,7 +5400,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.32.0-beta.3"
+version = "0.33.0-beta.0"
 dependencies = [
  "ahash",
  "anyhow",
@@ -5467,7 +5488,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.32.0-beta.3"
+version = "0.33.0-beta.0"
 dependencies = [
  "arrow-array",
  "arrow-buffer",
@@ -5492,7 +5513,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.35.0-beta.3"
+version = "0.36.0-beta.0"
 dependencies = [
  "arrow",
  "async-trait",
@@ -7803,18 +7824,6 @@ dependencies = [
  "memchr",
 ]
 
-[[package]]
-name = "quick_cache"
-version = "0.6.24"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b9c6658afe513a3b484e3abfdaa0d03ef3c0bbf017542c178dd55f94eb3051f9"
-dependencies = [
- "ahash",
- "equivalent",
- "hashbrown 0.16.1",
- "parking_lot",
-]
-
 [[package]]
 name = "quinn"
 version = "0.11.9"

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=10.0.0-beta.5", default-features = false, "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=10.0.0-beta.5", "tag" = "v10.0.0-beta.5", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=9.0.0", default-features = false }
+lance-core = "=9.0.0"
+lance-datagen = "=9.0.0"
+lance-file = "=9.0.0"
+lance-io = { "version" = "=9.0.0", default-features = false }
+lance-index = "=9.0.0"
+lance-linalg = "=9.0.0"
+lance-namespace = "=9.0.0"
+lance-namespace-impls = { "version" = "=9.0.0", default-features = false }
+lance-table = "=9.0.0"
+lance-testing = "=9.0.0"
+lance-datafusion = "=9.0.0"
+lance-encoding = "=9.0.0"
+lance-arrow = "=9.0.0"
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "58.0.0", optional = false }

docs/openapi.yml

@@ -453,16 +453,6 @@ paths:
                     The metric type to use for the index. l2, Cosine, Dot are supported.
                 index_type:
                   type: string
-                custom_stop_words:
-                  type: [array, "null"]
-                  items:
-                    type: string
-                  description: |
-                    The custom stop-word list for an FTS index. A non-null
-                    array replaces the language's built-in stop-word list and is only
-                    applied when remove_stop_words is enabled. Null uses the built-in
-                    language list, while an empty array explicitly replaces it with no
-                    stop words.
       responses:
         "200":
           description: Index successfully created
@@ -520,4 +510,4 @@ paths:
         "401":
           $ref: "#/components/responses/unauthorized"
         "404":
-          $ref: "#/components/responses/not_found"
+          $ref: "#/components/responses/not_found"

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>0.32.0-beta.3</version>
+    <version>0.33.0-beta.0</version>
 </dependency>
 ```
 

docs/src/js/interfaces/FtsOptions.md

@@ -43,34 +43,6 @@ The following tokenizers are available:
 
 ***
 
-### blockSize?
-
-```ts
-optional blockSize: 128 | 256;
-```
-
-Number of documents per compressed posting block.
-
-The default is 128. Supported values are 128 and 256. A value of 256 uses
-the experimental FTS V3 format and may introduce breaking changes.
-
-***
-
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
-***
-
 ### language?
 
 ```ts

docs/src/js/interfaces/TokenizeOptions.md

@@ -30,21 +30,6 @@ The tokenizer to use. The default is "simple".
 
 ***
 
-### customStopWords?
-
-```ts
-optional customStopWords: string[];
-```
-
-Custom stop words that replace the built-in list for `language`.
-
-This option only affects tokenization when `removeStopWords` is true.
-
-`undefined` keeps the built-in language list. An empty array explicitly
-replaces it with no stop words.
-
-***
-
 ### language?
 
 ```ts

docs/src/python/python.md

@@ -94,33 +94,9 @@ of raw SQL strings with [where][lancedb.query.LanceQueryBuilder.where] and
 
 ## Full text search
 
-Pass `custom_stop_words` to [lancedb.index.FTS][]:
-
-```python
-from lancedb.index import FTS
-
-table.create_index(
-    "text",
-    config=FTS(remove_stop_words=True, custom_stop_words=["acme", "internal"]),
-)
-```
-
-The list replaces the built-in stop words and is used only when
-`remove_stop_words=True`:
-
-- `custom_stop_words=None` uses the built-in list for `language`.
-- `custom_stop_words=[]` removes no words.
-- Values are passed through without trimming, lowercasing, or other rewriting.
-
-The same option is available on `lancedb.tokenize(...)` and the deprecated
-[lancedb.table.Table.create_fts_index][] compatibility helper:
-
-```python
-import lancedb
-
-tokens = list(lancedb.tokenize("acme makes searchable data",
-                               custom_stop_words=["acme"]))
-```
+Use [lancedb.table.Table.create_fts_index][] for the synchronous API or
+[lancedb.table.AsyncTable.create_index][] with [lancedb.index.FTS][] for the
+asynchronous API.
 
 ::: lancedb.index.FTS
 

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.32.0-beta.3</version>
+      <version>0.33.0-beta.0</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.32.0-beta.3</version>
+    <version>0.33.0-beta.0</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>
@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>10.0.0-beta.5</lance-core.version>
+        <lance-core.version>9.0.0</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.32.0-beta.3"
+version = "0.33.0-beta.0"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/__test__/remote.test.ts

@@ -15,7 +15,6 @@ import {
   OAuthHeaderProvider,
   StaticHeaderProvider,
 } from "../lancedb/header";
-import { Index } from "../lancedb/indices";
 
 // Test-only header providers
 class CustomProvider extends HeaderProvider {
@@ -226,59 +225,6 @@ describe("remote connection", () => {
     );
   });
 
-  it("sends FTS options to remote tables", async () => {
-    let createIndexBody: Record<string, unknown> | undefined;
-
-    await withMockDatabase(
-      (req, res) => {
-        const path = req.url ?? "";
-        if (path.endsWith("/describe/")) {
-          res.writeHead(200, { "Content-Type": "application/json" }).end(
-            JSON.stringify({
-              name: "t",
-              version: 1,
-              schema: {
-                fields: [
-                  { name: "text", type: { type: "string" }, nullable: false },
-                ],
-              },
-            }),
-          );
-          return;
-        }
-
-        if (path.endsWith("/create_index/")) {
-          let raw = "";
-          req.on("data", (chunk) => {
-            raw += chunk;
-          });
-          req.on("end", () => {
-            createIndexBody = JSON.parse(raw);
-            res.writeHead(200).end();
-          });
-          return;
-        }
-
-        res.writeHead(404).end();
-      },
-      async (db) => {
-        const table = await db.openTable("t");
-        await table.createIndex("text", {
-          config: Index.fts({
-            blockSize: 256,
-            removeStopWords: true,
-            customStopWords: ["the"],
-          }),
-        });
-      },
-    );
-
-    expect(createIndexBody?.["column"]).toBe("text");
-    expect(createIndexBody?.["index_type"]).toBe("FTS");
-    expect(createIndexBody?.["block_size"]).toBe(256);
-    expect(createIndexBody?.["custom_stop_words"]).toEqual(["the"]);
-  });
-
   it("diffs and merges remote branches", async () => {
     const sampleDiff = {
       fromBranch: "exp",

nodejs/__test__/table.test.ts

@@ -2527,35 +2527,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       expect(results3.length).toBe(1);
     });
 
-    test("full text search with custom posting block size", async () => {
-      const db = await connect(tmpDir.name);
-      const data = [
-        { text: "hello world", vector: [0.1, 0.2, 0.3] },
-        { text: "goodbye world", vector: [0.4, 0.5, 0.6] },
-      ];
-      const table = await db.createTable("test", data);
-      await table.createIndex("text", {
-        config: Index.fts({ blockSize: 256 }),
-      });
-
-      const index = (await table.listIndices()).find(
-        (index) => index.indexType === "FTS",
-      );
-      expect(index?.indexVersion).toBe(3);
-      expect(
-        (index?.indexDetails as Record<string, unknown>)["block_size"],
-      ).toBe(256);
-
-      const results = await table.search("hello").toArray();
-      expect(results[0].text).toBe(data[0].text);
-    });
-
-    test("rejects invalid full text posting block size", () => {
-      expect(() => Index.fts({ blockSize: 129 as 128 | 256 })).toThrow(
-        "128 or 256",
-      );
-    });
-
     test("full text search without lowercase", async () => {
       const db = await connect(tmpDir.name);
       const data = [
@@ -2761,15 +2732,6 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
   },
 );
 
-test("tokenize supports custom stop words", async () => {
-  const tokens = await tokenize("the lance data", {
-    stem: false,
-    removeStopWords: true,
-    customStopWords: ["lance"],
-  });
-  expect(tokens.map((token) => token.text)).toEqual(["the", "data"]);
-});
-
 describe("when calling explainPlan", () => {
   let tmpDir: tmp.DirResult;
   let table: Table;

nodejs/examples/full_text_search.test.ts

@@ -29,14 +29,8 @@ test("full text search", async () => {
     const tbl = await db.createTable("myVectors", data, { mode: "overwrite" });
 
     await tbl.createIndex("doc", {
-      config: lancedb.Index.fts({
-        stem: false,
-        removeStopWords: true,
-        customStopWords: ["banana"],
-      }),
+      config: lancedb.Index.fts(),
     });
-    const tokens = await tbl.tokenize("apple banana", { column: "doc" });
-    expect(tokens.map((token) => token.text)).toEqual(["apple"]);
 
     // --8<-- [start:full_text_search]
     const result = await tbl

nodejs/lancedb/index.ts

@@ -194,16 +194,6 @@ export interface TokenizeOptions {
   /** Whether to remove stop words. */
   removeStopWords?: boolean;
 
-  /**
-   * Custom stop words that replace the built-in list for `language`.
-   *
-   * This option only affects tokenization when `removeStopWords` is true.
-   *
-   * `undefined` keeps the built-in language list. An empty array explicitly
-   * replaces it with no stop words.
-   */
-  customStopWords?: string[];
-
   /** Whether to fold ASCII characters. */
   asciiFolding?: boolean;
 
@@ -235,7 +225,6 @@ export async function tokenize(
     options?.lowercase,
     options?.stem,
     options?.removeStopWords,
-    options?.customStopWords,
     options?.asciiFolding,
     options?.ngramMinLength,
     options?.ngramMaxLength,

nodejs/lancedb/indices.ts

@@ -553,16 +553,6 @@ export interface FtsOptions {
    */
   removeStopWords?: boolean;
 
-  /**
-   * Custom stop words that replace the built-in list for `language`.
-   *
-   * This option only affects tokenization when `removeStopWords` is true.
-   *
-   * `undefined` keeps the built-in language list. An empty array explicitly
-   * replaces it with no stop words.
-   */
-  customStopWords?: string[];
-
   /**
    * whether to remove punctuation
    */
@@ -582,14 +572,6 @@ export interface FtsOptions {
    * whether to only index the prefix of the token for ngram tokenizer
    */
   prefixOnly?: boolean;
-
-  /**
-   * Number of documents per compressed posting block.
-   *
-   * The default is 128. Supported values are 128 and 256. A value of 256 uses
-   * the experimental FTS V3 format and may introduce breaking changes.
-   */
-  blockSize?: 128 | 256;
 }
 
 export class Index {
@@ -765,12 +747,10 @@ export class Index {
         options?.lowercase,
         options?.stem,
         options?.removeStopWords,
-        options?.customStopWords,
         options?.asciiFolding,
         options?.ngramMinLength,
         options?.ngramMaxLength,
         options?.prefixOnly,
-        options?.blockSize,
       ),
     );
   }

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.32.0-beta.3",
+	"version": "0.33.0-beta.0",
 	"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": "0.32.0-beta.3",
+	"version": "0.33.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-musl",
-	"version": "0.32.0-beta.3",
+	"version": "0.33.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["arm64"],
 	"main": "lancedb.linux-arm64-musl.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-gnu",
-	"version": "0.32.0-beta.3",
+	"version": "0.33.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-gnu.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-x64-musl",
-	"version": "0.32.0-beta.3",
+	"version": "0.33.0-beta.0",
 	"os": ["linux"],
 	"cpu": ["x64"],
 	"main": "lancedb.linux-x64-musl.node",

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

@@ -1,6 +1,6 @@
 {
   "name": "@lancedb/lancedb-win32-arm64-msvc",
-  "version": "0.32.0-beta.3",
+  "version": "0.33.0-beta.0",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.32.0-beta.3",
+	"version": "0.33.0-beta.0",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.32.0-beta.3",
+  "version": "0.33.0-beta.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.32.0-beta.3",
+      "version": "0.33.0-beta.0",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.32.0-beta.3",
+  "version": "0.33.0-beta.0",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

nodejs/src/index.rs

@@ -43,7 +43,6 @@ pub fn tokenize(
     lower_case: Option<bool>,
     stem: Option<bool>,
     remove_stop_words: Option<bool>,
-    custom_stop_words: Option<Vec<String>>,
     ascii_folding: Option<bool>,
     ngram_min_length: Option<u32>,
     ngram_max_length: Option<u32>,
@@ -73,7 +72,6 @@ pub fn tokenize(
     if let Some(remove_stop_words) = remove_stop_words {
         opts = opts.remove_stop_words(remove_stop_words);
     }
-    opts = opts.custom_stop_words(custom_stop_words);
     if let Some(ascii_folding) = ascii_folding {
         opts = opts.ascii_folding(ascii_folding);
     }
@@ -224,13 +222,11 @@ impl Index {
         lower_case: Option<bool>,
         stem: Option<bool>,
         remove_stop_words: Option<bool>,
-        custom_stop_words: Option<Vec<String>>,
         ascii_folding: Option<bool>,
         ngram_min_length: Option<u32>,
         ngram_max_length: Option<u32>,
         prefix_only: Option<bool>,
-        block_size: Option<u32>,
-    ) -> napi::Result<Self> {
+    ) -> Self {
         let mut opts = FtsIndexBuilder::default();
         if let Some(with_position) = with_position {
             opts = opts.with_position(with_position);
@@ -253,7 +249,6 @@ impl Index {
         if let Some(remove_stop_words) = remove_stop_words {
             opts = opts.remove_stop_words(remove_stop_words);
         }
-        opts = opts.custom_stop_words(custom_stop_words);
         if let Some(ascii_folding) = ascii_folding {
             opts = opts.ascii_folding(ascii_folding);
         }
@@ -266,15 +261,10 @@ impl Index {
         if let Some(prefix_only) = prefix_only {
             opts = opts.ngram_prefix_only(prefix_only);
         }
-        if let Some(block_size) = block_size {
-            opts = opts
-                .block_size(block_size as usize)
-                .map_err(|err| napi::Error::from_reason(err.to_string()))?;
-        }
 
-        Ok(Self {
+        Self {
             inner: Mutex::new(Some(LanceDbIndex::FTS(opts))),
-        })
+        }
     }
 
     #[napi(factory)]

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.35.0-beta.3"
+current_version = "0.36.0"
 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 = "0.35.0-beta.3"
+version = "0.36.0"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"

python/pyproject.toml

@@ -63,7 +63,7 @@ tests = [
     "polars>=0.19, <=1.3.0",
     "pyarrow<25",
     "pyarrow-stubs>=16.0",
-    "pylance==9.0.0rc1",
+    "pylance==9.0.0",
     "requests>=2.31.0",
     "datafusion>=54,<55",
     "opentelemetry-sdk>=1.30.0",

python/python/lancedb/__init__.py

@@ -258,7 +258,6 @@ def tokenize(
     lower_case: bool = True,
     stem: bool = True,
     remove_stop_words: bool = True,
-    custom_stop_words: Optional[List[str]] = None,
     ascii_folding: bool = True,
     ngram_min_length: int = 3,
     ngram_max_length: int = 3,
@@ -266,10 +265,9 @@ def tokenize(
 ) -> Iterable[FtsToken]:
     """Tokenize a full-text search query using an explicit tokenizer.
 
-    This does not require an FTS index. The tokenizer options match
-    :class:`lancedb.index.FTS`. ``custom_stop_words`` accepts a list of strings.
+    This does not require a table or FTS index. The tokenizer options match
+    :class:`lancedb.index.FTS`.
     """
-
     return _tokenize(
         query,
         base_tokenizer=base_tokenizer,
@@ -278,7 +276,6 @@ def tokenize(
         lower_case=lower_case,
         stem=stem,
         remove_stop_words=remove_stop_words,
-        custom_stop_words=custom_stop_words,
         ascii_folding=ascii_folding,
         ngram_min_length=ngram_min_length,
         ngram_max_length=ngram_max_length,

python/python/lancedb/_lancedb.pyi

@@ -59,7 +59,6 @@ def tokenize(
     lower_case: bool = True,
     stem: bool = True,
     remove_stop_words: bool = True,
-    custom_stop_words: Optional[List[str]] = None,
     ascii_folding: bool = True,
     ngram_min_length: int = 3,
     ngram_max_length: int = 3,

python/python/lancedb/index.py

@@ -2,7 +2,7 @@
 # SPDX-FileCopyrightText: Copyright The LanceDB Authors
 
 from dataclasses import dataclass
-from typing import List, Literal, Optional
+from typing import Literal, Optional
 
 from ._lancedb import (
     IndexConfig,
@@ -115,12 +115,6 @@ class FTS:
 
     For example, it works with `title`, `description`, `content`, etc.
 
-    Examples
-    --------
-    Create an index configuration that uses 256-document posting blocks:
-
-    >>> config = FTS(block_size=256)
-
     Attributes
     ----------
     with_position : bool, default False
@@ -151,18 +145,9 @@ class FTS:
     remove_stop_words : bool, default True
         Whether to remove stop words. Stop words are common words that are often
         removed from text before indexing. For example, in English "the" and "and".
-    custom_stop_words : list of str, optional
-        Custom words replace the built-in language stop words
-        and only take effect when ``remove_stop_words`` is True. ``None`` uses
-        the built-in language list, while an empty list explicitly uses no
-        stop words.
     ascii_folding : bool, default True
         Whether to fold ASCII characters. This converts accented characters to
         their ASCII equivalent. For example, "café" would be converted to "cafe".
-    block_size : int, default 128
-        The number of documents per compressed posting block. Supported values
-        are 128 and 256. A value of 256 uses the experimental FTS V3 format
-        and may introduce breaking changes.
 
     Notes
     -----
@@ -183,8 +168,6 @@ class FTS:
     ngram_min_length: int = 3
     ngram_max_length: int = 3
     prefix_only: bool = False
-    block_size: int = 128
-    custom_stop_words: Optional[List[str]] = None
 
 
 @dataclass

python/python/lancedb/remote/table.py

@@ -340,12 +340,10 @@ class RemoteTable(Table):
         lower_case: bool = True,
         stem: bool = True,
         remove_stop_words: bool = True,
-        custom_stop_words: Optional[List[str]] = None,
         ascii_folding: bool = True,
         ngram_min_length: int = 3,
         ngram_max_length: int = 3,
         prefix_only: bool = False,
-        block_size: int = 128,
         name: Optional[str] = None,
     ):
         """Create a full-text search index on a column.
@@ -362,12 +360,10 @@ class RemoteTable(Table):
             lower_case=lower_case,
             stem=stem,
             remove_stop_words=remove_stop_words,
-            custom_stop_words=custom_stop_words,
             ascii_folding=ascii_folding,
             ngram_min_length=ngram_min_length,
             ngram_max_length=ngram_max_length,
             prefix_only=prefix_only,
-            block_size=block_size,
         )
         LOOP.run(
             self._table.create_index(

python/python/lancedb/rerankers/answerdotai.py

@@ -23,7 +23,7 @@ class AnswerdotaiRerankers(Reranker):
     column : str, default "text"
         The name of the column to use as input to the cross encoder model.
     return_score : str, default "relevance"
-        options are "relevance" or "all".
+        options are "relevance" or "all". Only "relevance" is supported for now.
     **kwargs
         Additional keyword arguments to pass to the model. For example, 'device'.
         See AnswerDotAI/rerankers for more information.
@@ -77,13 +77,12 @@ class AnswerdotaiRerankers(Reranker):
         vector_results: pa.Table,
         fts_results: pa.Table,
     ):
-        if self.score == "all":
-            combined_results = self._merge_and_keep_scores(vector_results, fts_results)
-        else:
-            combined_results = self.merge_results(vector_results, fts_results)
+        combined_results = self.merge_results(vector_results, fts_results)
         combined_results = self._rerank(combined_results, query)
         if self.score == "relevance":
             combined_results = self._keep_relevance_score(combined_results)
+        elif self.score == "all":
+            combined_results = self._merge_and_keep_scores(vector_results, fts_results)
         combined_results = combined_results.sort_by(
             [("_relevance_score", "descending")]
         )

python/python/lancedb/rerankers/colbert.py

@@ -16,7 +16,7 @@ class ColbertReranker(AnswerdotaiRerankers):
     column : str, default "text"
         The name of the column to use as input to the cross encoder model.
     return_score : str, default "relevance"
-        options are "relevance" or "all".
+        options are "relevance" or "all". Only "relevance" is supported for now.
     **kwargs
         Additional keyword arguments to pass to the model, for example, 'device'.
         See AnswerDotAI/rerankers for more information.

python/python/lancedb/table.py

@@ -1102,12 +1102,10 @@ class Table(ABC):
         lower_case: bool = True,
         stem: bool = True,
         remove_stop_words: bool = True,
-        custom_stop_words: Optional[List[str]] = None,
         ascii_folding: bool = True,
         ngram_min_length: int = 3,
         ngram_max_length: int = 3,
         prefix_only: bool = False,
-        block_size: int = 128,
         wait_timeout: Optional[timedelta] = None,
         name: Optional[str] = None,
     ):
@@ -1170,9 +1168,6 @@ class Table(ABC):
         remove_stop_words : bool, default True
             Whether to remove stop words. Stop words are common words that are often
             removed from text before indexing. For example, in English "the" and "and".
-        custom_stop_words : list of str, optional
-            Custom words that replace the built-in language stop words. ``None``
-            uses the built-in list; an empty list explicitly uses no stop words.
         ascii_folding : bool, default True
             Whether to fold ASCII characters. This converts accented characters to
             their ASCII equivalent. For example, "café" would be converted to "cafe".
@@ -1182,10 +1177,6 @@ class Table(ABC):
             The maximum length of an n-gram.
         prefix_only: bool, default False
             Whether to only index the prefix of the token for ngram tokenizer.
-        block_size: int, default 128
-            The number of documents per compressed posting block. Must be 128
-            or 256. A value of 256 uses the experimental FTS V3 format and
-            may introduce breaking changes.
         wait_timeout: timedelta, optional
             The timeout to wait if indexing is asynchronous.
         name: str, optional
@@ -3031,12 +3022,10 @@ class LanceTable(Table):
         lower_case: bool = True,
         stem: bool = True,
         remove_stop_words: bool = True,
-        custom_stop_words: Optional[List[str]] = None,
         ascii_folding: bool = True,
         ngram_min_length: int = 3,
         ngram_max_length: int = 3,
         prefix_only: bool = False,
-        block_size: int = 128,
         name: Optional[str] = None,
     ):
         """Create a full-text search index on a column.
@@ -3078,7 +3067,6 @@ class LanceTable(Table):
                 "lower_case": lower_case,
                 "stem": stem,
                 "remove_stop_words": remove_stop_words,
-                "custom_stop_words": custom_stop_words,
                 "ascii_folding": ascii_folding,
                 "ngram_min_length": ngram_min_length,
                 "ngram_max_length": ngram_max_length,
@@ -3086,9 +3074,10 @@ class LanceTable(Table):
             }
         else:
             tokenizer_configs = self.infer_tokenizer_configs(tokenizer_name)
-            tokenizer_configs["custom_stop_words"] = custom_stop_words
 
-        config = FTS(block_size=block_size, **tokenizer_configs)
+        config = FTS(
+            **tokenizer_configs,
+        )
 
         try:
             LOOP.run(

python/python/tests/test_fts.py

@@ -219,48 +219,11 @@ def test_create_inverted_index(table, with_position):
         table.create_fts_index(
             "text",
             with_position=with_position,
-            custom_stop_words=["puppy"],
             name="custom_fts_index",
         )
     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)
-    assert fts_indices[0].index_details["custom_stop_words"] == ["puppy"]
-
-
-@pytest.mark.parametrize("block_size", [128, 256])
-def test_create_inverted_index_block_size(table, block_size):
-    table.create_index("text", config=FTS(block_size=block_size))
-
-    index = next(index for index in table.list_indices() if index.index_type == "FTS")
-    assert index.index_details["block_size"] == block_size
-    assert index.index_version == (2 if block_size == 128 else 3)
-
-    results = table.search("puppy").limit(5).to_list()
-    assert len(results) == 5
-
-
-def test_create_inverted_index_rejects_invalid_block_size(table):
-    with pytest.raises(ValueError, match="128 or 256"):
-        table.create_index("text", config=FTS(block_size=129))
-
-
-def test_custom_stop_words_list(table):
-    table.create_index(
-        "text",
-        config=FTS(stem=False, custom_stop_words=["lance"]),
-    )
-
-    assert table.list_indices()[0].index_details["custom_stop_words"] == ["lance"]
-    tokens = table.tokenize("the lance data", column="text")
-    assert [token.text for token in tokens] == ["the", "data"]
-    empty_tokens = ldb.tokenize("the lance data", stem=False, custom_stop_words=[])
-    assert [token.text for token in empty_tokens] == ["the", "lance", "data"]
-    with pytest.raises(TypeError, match=r"custom_stop_words.*int"):
-        ldb.tokenize(
-            "the lance data",
-            custom_stop_words=["lance", 42],
-        )
 
 
 def test_search_fts(table):

python/python/tests/test_remote_db.py

@@ -768,11 +768,7 @@ def test_table_create_indices():
         # Test create_fts_index with custom name (legacy method)
         with pytest.warns(DeprecationWarning, match="create_fts_index"):
             table.create_fts_index(
-                "text",
-                wait_timeout=timedelta(seconds=2),
-                block_size=256,
-                custom_stop_words=["cloud"],
-                name="custom_fts_idx",
+                "text", wait_timeout=timedelta(seconds=2), name="custom_fts_idx"
             )
 
         # Test create_index with custom name (legacy form: vector_column_name kwarg)
@@ -795,8 +791,6 @@ def test_table_create_indices():
         fts_req = received_requests[1]
         assert "name" in fts_req
         assert fts_req["name"] == "custom_fts_idx"
-        assert fts_req["block_size"] == 256
-        assert fts_req["custom_stop_words"] == ["cloud"]
 
         # Check vector index request has custom name
         vector_req = received_requests[2]
@@ -882,7 +876,7 @@ def test_remote_create_index_new_api():
             _warnings.simplefilter("error", DeprecationWarning)
             table.create_index("vector", config=IvfPq(distance_type="l2"))
             table.create_index("category", config=BTree())
-            table.create_index("text", config=FTS(block_size=256))
+            table.create_index("text", config=FTS())
             # IvfRq via new API
             table.create_index("vector", config=IvfRq(distance_type="l2"))
 
@@ -902,7 +896,6 @@ def test_remote_create_index_new_api():
             "vector",
             "vector",
         ]
-        assert received_requests[2]["block_size"] == 256
 
 
 def test_table_wait_for_index_timeout():

python/python/tests/test_rerankers.py

@@ -644,21 +644,6 @@ def test_cross_encoder_reranker_return_all(tmp_path):
     assert "_distance" in result.column_names
 
 
-def test_answerdotai_reranker_return_all(tmp_path):
-    pytest.importorskip("rerankers")
-    reranker = AnswerdotaiRerankers(return_score="all")
-    table, schema = get_test_table(tmp_path)
-    query = "single player experience"
-    result = (
-        table.search(query, query_type="hybrid", vector_column_name="vector")
-        .rerank(reranker=reranker)
-        .to_arrow()
-    )
-    assert "_relevance_score" in result.column_names
-    assert "_score" in result.column_names
-    assert "_distance" in result.column_names
-
-
 # ---------------------------------------------------------------------------
 # Regression tests for LinearCombinationReranker scoring bugs (issue #3154)
 # ---------------------------------------------------------------------------

python/src/index.rs

@@ -59,11 +59,7 @@ pub fn extract_index_params(source: &Option<Bound<'_, PyAny>>) -> PyResult<Lance
                     .ascii_folding(params.ascii_folding)
                     .ngram_min_length(params.ngram_min_length)
                     .ngram_max_length(params.ngram_max_length)
-                    .ngram_prefix_only(params.prefix_only)
-                    .custom_stop_words(params.custom_stop_words);
-                let inner_opts = inner_opts
-                    .block_size(params.block_size)
-                    .map_err(|err| PyValueError::new_err(err.to_string()))?;
+                    .ngram_prefix_only(params.prefix_only);
                 Ok(LanceDbIndex::FTS(inner_opts))
             }
             "IvfFlat" => {
@@ -207,12 +203,10 @@ struct FtsParams {
     lower_case: bool,
     stem: bool,
     remove_stop_words: bool,
-    custom_stop_words: Option<Vec<String>>,
     ascii_folding: bool,
     ngram_min_length: u32,
     ngram_max_length: u32,
     prefix_only: bool,
-    block_size: usize,
 }
 
 #[derive(FromPyObject)]

python/src/table.rs

@@ -520,7 +520,6 @@ impl From<LanceDbFtsToken> for FtsToken {
     lower_case = true,
     stem = true,
     remove_stop_words = true,
-    custom_stop_words = None,
     ascii_folding = true,
     ngram_min_length = 3,
     ngram_max_length = 3,
@@ -535,7 +534,6 @@ pub fn tokenize(
     lower_case: bool,
     stem: bool,
     remove_stop_words: bool,
-    custom_stop_words: Option<Vec<String>>,
     ascii_folding: bool,
     ngram_min_length: u32,
     ngram_max_length: u32,
@@ -557,8 +555,7 @@ pub fn tokenize(
         .ascii_folding(ascii_folding)
         .ngram_min_length(ngram_min_length)
         .ngram_max_length(ngram_max_length)
-        .ngram_prefix_only(prefix_only)
-        .custom_stop_words(custom_stop_words);
+        .ngram_prefix_only(prefix_only);
     let tokens = lancedb_tokenize(&query, &params).infer_error()?;
     Ok(tokens.into_iter().map(FtsToken::from).collect())
 }

python/uv.lock

@@ -1998,7 +1998,7 @@ requires-dist = [
     { name = "pyarrow-stubs", marker = "extra == 'tests'", specifier = ">=16.0" },
     { name = "pydantic", specifier = ">=1.10" },
     { name = "pylance", marker = "extra == 'pylance'", specifier = ">=5.0.0b5" },
-    { name = "pylance", marker = "extra == 'tests'", specifier = "==9.0.0rc1" },
+    { name = "pylance", marker = "extra == 'tests'", specifier = "==9.0.0" },
     { name = "pyright", marker = "extra == 'dev'", specifier = ">=1.1.350" },
     { name = "pytest", marker = "extra == 'tests'", specifier = ">=7.0" },
     { name = "pytest-asyncio", marker = "extra == 'tests'", specifier = ">=0.21" },
@@ -3854,8 +3854,8 @@ crypto = [
 
 [[package]]
 name = "pylance"
-version = "9.0.0rc1"
-source = { registry = "https://pypi.fury.io/lance-format" }
+version = "9.0.0"
+source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "lance-namespace" },
     { name = "numpy", version = "2.2.6", source = { registry = "https://pypi.org/simple" }, marker = "python_full_version < '3.11'" },
@@ -3863,12 +3863,12 @@ dependencies = [
     { name = "pyarrow" },
 ]
 wheels = [
-    { url = "https://pypi.fury.io/lance-format/-/ver_vEHBE/pylance-9.0.0rc1-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:f0b6b02a1808bb3072ee7fe4e36614cae6f86302513e73ec7f55b2234a963b24" },
-    { url = "https://pypi.fury.io/lance-format/-/ver_1Jipm4/pylance-9.0.0rc1-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:30f0ebf0d88034301819eb964f9236ce555aaa58e7ab89c5975a3e2250bbb405" },
-    { url = "https://pypi.fury.io/lance-format/-/ver_IvKxo/pylance-9.0.0rc1-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:44609ea2615ea6e684b85478d1694af2026458f61cf7895ecc75e238bfd17aa8" },
-    { url = "https://pypi.fury.io/lance-format/-/ver_2hidj1/pylance-9.0.0rc1-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:182167a8dba9eeabffbffd53bd5b8548613d4d459b7cd7b34a840dd00cbb806f" },
-    { url = "https://pypi.fury.io/lance-format/-/ver_1dFx3r/pylance-9.0.0rc1-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:8a63b11e814b7eab758bcaf0d6f97eb05ea86203d9fb0af718c462c24c7d6c9c" },
-    { url = "https://pypi.fury.io/lance-format/-/ver_2a8dSh/pylance-9.0.0rc1-cp310-abi3-win_amd64.whl", hash = "sha256:2ff8b953ae2b0550490c1a7efd210aa91bc223d200ffac28849056cfd7436d97" },
+    { url = "https://files.pythonhosted.org/packages/e9/be/45733acd64801991852aac8e658601fd8fc12f76ceb81e57fca690896b90/pylance-9.0.0-cp310-abi3-macosx_11_0_arm64.whl", hash = "sha256:8257213501d3298c5b6a344d60938e4bbe4de9f00cd3265371a56d1dc3dd15ca", size = 68377982, upload-time = "2026-07-24T16:53:45.247Z" },
+    { url = "https://files.pythonhosted.org/packages/d0/3e/1ef707cb215cc7268c63ad84a91344ad6313d3984b343eeb19a9b708698e/pylance-9.0.0-cp310-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:804eedfa1fda2e703cca8580c76f0b44a1b849b725a8908c06f8acfca811732f", size = 71844362, upload-time = "2026-07-24T16:56:07.6Z" },
+    { url = "https://files.pythonhosted.org/packages/c8/fb/a499e5c53ddb75c7de44100fd2bb1f7cc735966200d20292eed7af9ef552/pylance-9.0.0-cp310-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0a0b75595e3766c1d5f4c90abdc52337b4de60f1a52d123a4f8c4e5bcbbbfa8f", size = 75663088, upload-time = "2026-07-24T17:10:31.283Z" },
+    { url = "https://files.pythonhosted.org/packages/e9/80/0714e09f64a68dbdf62558955e737a7436df763b9834a6aba506861b5352/pylance-9.0.0-cp310-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:d2f69c5c390ae3710c35a429905fe15f769951777fafb1b72a359e035ec121f7", size = 71866858, upload-time = "2026-07-24T16:56:35.937Z" },
+    { url = "https://files.pythonhosted.org/packages/4b/3c/78d3a6d6ca0d843b7c3ac0c30d9cd2cf4635b0c2cabe6ec66583d5bfc1a1/pylance-9.0.0-cp310-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:836268a7832d62f3d5ccbe1c3fca239621971d90297bcfff14a70b3cb6842aa8", size = 75642656, upload-time = "2026-07-24T17:13:11.879Z" },
+    { url = "https://files.pythonhosted.org/packages/cf/c1/dc9c9a31e171530ec0add024d922488c046437d32a7087c29e254a7eacc7/pylance-9.0.0-cp310-abi3-win_amd64.whl", hash = "sha256:96441d27a5ed3805300388ccf8f31835cd280c98751f80b6a1a11dcd6808fc43", size = 81668288, upload-time = "2026-07-24T17:05:38.707Z" },
 ]
 
 [[package]]

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.32.0-beta.3"
+version = "0.33.0-beta.0"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/examples/full_text_search.rs

@@ -76,12 +76,7 @@ async fn create_table(db: &Connection) -> Result<Table> {
 
 async fn create_index(table: &Table) -> Result<()> {
     table
-        .create_index(
-            &["doc"],
-            Index::FTS(
-                FtsIndexBuilder::default().custom_stop_words(Some(vec!["example".to_owned()])),
-            ),
-        )
+        .create_index(&["doc"], Index::FTS(FtsIndexBuilder::default()))
         .execute()
         .await?;
     Ok(())

rust/lancedb/src/blob.rs

@@ -273,11 +273,7 @@ pub(crate) async fn take_blobs_aligned(
         if *is_null {
             builder.append_null();
         } else {
-            if let Some(data) = &payloads[payload_idx].data {
-                builder.append_value(data);
-            } else {
-                builder.append_null();
-            }
+            builder.append_value(payloads[payload_idx].data.as_ref());
             payload_idx += 1;
         }
     }
@@ -319,7 +315,7 @@ pub(crate) async fn take_blob_files_aligned(
             if *is_null {
                 None
             } else {
-                handles.next().flatten()
+                Some(handles.next().unwrap())
             }
         })
         .collect())

rust/lancedb/src/index.rs

@@ -54,26 +54,7 @@ pub enum Index {
     /// substrings of the raw bytes, unlike the tokenized [`Index::FTS`] index.
     Fm(FmIndexBuilder),
 
-    /// Full text search index using BM25.
-    ///
-    /// The posting block size defaults to 128. Supported values are 128 and 256;
-    /// a value of 256 uses the experimental FTS V3 format and may introduce
-    /// breaking changes.
-    ///
-    /// ```
-    /// use lancedb::index::{Index, scalar::FtsIndexBuilder};
-    ///
-    /// # async fn create_fts_index(
-    /// #     table: &lancedb::Table,
-    /// # ) -> Result<(), Box<dyn std::error::Error>> {
-    /// let params = FtsIndexBuilder::default().block_size(256)?;
-    /// table
-    ///     .create_index(&["text"], Index::FTS(params))
-    ///     .execute()
-    ///     .await?;
-    /// # Ok(())
-    /// # }
-    /// ```
+    /// Full text search index using bm25.
     FTS(FtsIndexBuilder),
 
     /// IVF index

rust/lancedb/src/remote/table.rs

@@ -4496,28 +4496,6 @@ mod tests {
                 serde_json::to_value(InvertedIndexParams::default()).unwrap(),
                 Index::FTS(Default::default()),
             ),
-            (
-                "FTS",
-                {
-                    let mut body = serde_json::to_value(InvertedIndexParams::default()).unwrap();
-                    body["block_size"] = 256.into();
-                    body
-                },
-                Index::FTS(InvertedIndexParams::default().block_size(256).unwrap()),
-            ),
-            (
-                "FTS",
-                {
-                    let mut body = serde_json::to_value(InvertedIndexParams::default()).unwrap();
-                    body["custom_stop_words"] = json!(["cat", " cat ", "CAT"]);
-                    body
-                },
-                Index::FTS(InvertedIndexParams::default().custom_stop_words(Some(vec![
-                    "cat".to_string(),
-                    " cat ".to_string(),
-                    "CAT".to_string(),
-                ]))),
-            ),
         ];
 
         for (index_type, expected_body, index) in cases {
@@ -5049,9 +5027,8 @@ mod tests {
             "max_token_length": 40,
             "lower_case": true,
             "stem": false,
-            "remove_stop_words": true,
+            "remove_stop_words": false,
             "ascii_folding": true,
-            "custom_stop_words": ["hello"],
         })
         .to_string();
         let table = Table::new_with_handler("my_table", move |request| {
@@ -5089,6 +5066,10 @@ mod tests {
         assert_eq!(
             tokens,
             vec![
+                FtsToken {
+                    text: "hello".to_string(),
+                    position: 0,
+                },
                 FtsToken {
                     text: "こんにちは".to_string(),
                     position: 1,

rust/lancedb/src/table.rs

@@ -21,7 +21,6 @@ use lance::dataset::WriteMode;
 use lance::dataset::builder::DatasetBuilder;
 use lance::dataset::{InsertBuilder, WriteParams};
 use lance::index::DatasetIndexExt;
-use lance::index::scalar::load_segment_params;
 use lance::io::{ObjectStoreParams, WrappingObjectStore};
 use lance_datafusion::utils::StreamingWriteSource;
 use lance_index::IndexCriteria;
@@ -3132,9 +3131,10 @@ impl BaseTable for NativeTable {
     async fn list_indices(&self) -> Result<Vec<IndexConfig>> {
         let dataset = self.dataset.get().await?;
         let total_rows = dataset.count_rows(None).await? as u64;
-        let descriptions = dataset.describe_indices(None).await?;
-        let mut indices: Vec<IndexConfig> = descriptions
-            .iter()
+        let indices = dataset
+            .describe_indices(None)
+            .await?
+            .into_iter()
             .filter_map(|idx_desc| {
                 let index_type: crate::index::IndexType = idx_desc
                     .index_type()
@@ -3192,31 +3192,6 @@ impl BaseTable for NativeTable {
                 })
             })
             .collect();
-
-        for index in indices
-            .iter_mut()
-            .filter(|index| index.index_type == crate::index::IndexType::FTS)
-        {
-            let Some(description) = descriptions
-                .iter()
-                .find(|description| description.name() == index.name)
-            else {
-                continue;
-            };
-            let segments = description.segments();
-            let Some(segment) = segments.first() else {
-                continue;
-            };
-            let params = load_segment_params(&dataset, segment).await?;
-            let details = serde_json::to_string(&params).map_err(|source| Error::Other {
-                message: format!(
-                    "Failed to serialize full text search configuration for index '{}'",
-                    index.name
-                ),
-                source: Some(Box::new(source)),
-            })?;
-            index.index_details = Some(details);
-        }
         Ok(indices)
     }
 

rust/lancedb/src/table/create_index.rs

@@ -382,9 +382,7 @@ mod tests {
     use crate::connect;
     use crate::connection::ConnectBuilder;
     use crate::index::Index;
-    use crate::index::scalar::{
-        BTreeIndexBuilder, BitmapIndexBuilder, FmIndexBuilder, FtsIndexBuilder,
-    };
+    use crate::index::scalar::{BTreeIndexBuilder, BitmapIndexBuilder, FmIndexBuilder};
     use crate::index::vector::{
         IvfHnswFlatIndexBuilder, IvfHnswPqIndexBuilder, IvfHnswSqIndexBuilder,
     };
@@ -1364,57 +1362,16 @@ mod tests {
             .unwrap();
 
         table
-            .create_index(
-                &["text"],
-                Index::FTS(
-                    FtsIndexBuilder::default()
-                        .stem(false)
-                        .custom_stop_words(Some(vec!["cat".to_string()]))
-                        .block_size(256)
-                        .unwrap(),
-                ),
-            )
+            .create_index(&["text"], Index::FTS(Default::default()))
             .execute()
             .await
             .unwrap();
-        drop(table);
-        let table = conn.open_table("test_bitmap").execute().await.unwrap();
         let index_configs = table.list_indices().await.unwrap();
         assert_eq!(index_configs.len(), 1);
         let index = index_configs.into_iter().next().unwrap();
         assert_eq!(index.index_type, crate::index::IndexType::FTS);
         assert_eq!(index.columns, vec!["text".to_string()]);
         assert_eq!(index.name, "text_idx");
-        assert_eq!(index.index_version, Some(3));
-        let index_params: FtsIndexBuilder =
-            serde_json::from_str(index.index_details.as_deref().unwrap()).unwrap();
-        assert_eq!(index_params.posting_block_size(), 256);
-        assert_eq!(
-            serde_json::to_value(&index_params).unwrap()["custom_stop_words"],
-            serde_json::json!(["cat"])
-        );
-        assert_eq!(
-            table
-                .tokenize("cat dog", "text_idx")
-                .await
-                .unwrap()
-                .into_iter()
-                .map(|token| token.text)
-                .collect::<Vec<_>>(),
-            vec!["dog"]
-        );
-
-        let batches = table
-            .query()
-            .full_text_search(FullTextSearchQuery::new("cat dog".to_string()))
-            .limit(120)
-            .execute()
-            .await
-            .unwrap()
-            .try_collect::<Vec<_>>()
-            .await
-            .unwrap();
-        assert_eq!(batches.iter().map(RecordBatch::num_rows).sum::<usize>(), 40);
 
         let num_rows = 120;
         let stats = table.index_stats("text_idx").await.unwrap().unwrap();