Bump version: 0.39.0-beta.4 → 0.39.0-beta.5

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.39.0-beta.6"
+current_version = "0.39.0-beta.5"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/typos.yml

@@ -1,20 +0,0 @@
-name: Typo checker
-on:
-  push:
-    branches:
-      - main
-  pull_request:
-
-permissions:
-  contents: read
-
-jobs:
-  run:
-    name: Spell Check with Typos
-    runs-on: ubuntu-latest
-    steps:
-      - name: Check out code
-        uses: actions/checkout@v6
-
-      - name: Check spelling of the entire repository
-        uses: crate-ci/typos@6802cc60d4e7f78b9d5454f6cf3935c042d5e1e3 # v1.26.0

.pre-commit-config.yaml

@@ -10,10 +10,6 @@ repos:
     rev: v0.9.9
     hooks:
       - id: ruff
-  - repo: https://github.com/crate-ci/typos
-    rev: v1.26.0
-    hooks:
-      - id: typos
   # - repo: https://github.com/RobertCraigie/pyright-python
   #   rev: v1.1.395
   #   hooks:

.typos.toml

@@ -1,19 +0,0 @@
-[default]
-extend-ignore-re = ["(?Rm)^.*(#|//)\\s*spellchecker:disable-line$"]
-
-[default.extend-words]
-# Azure Kubernetes Service, mentioned in rust/lancedb/src/remote/oauth.rs.
-AKS = "AKS"
-# RabitQ is the name of a vector quantization algorithm, not a typo of "Rabbit".
-Rabit = "Rabit"
-# `VarBuilder::from_mmaped_safetensors` is the real (if oddly-spelled) name of
-# the candle-core API we call in rust/lancedb/src/embeddings/sentence_transformers.rs.
-mmaped = "mmaped"
-# `WriteableBuffer` is the real name of a type from Python's `_typeshed` stubs,
-# used in python/python/lancedb/_blob.py.
-Writeable = "Writeable"
-
-[files]
-extend-exclude = [
-    "*_THIRD_PARTY_LICENSES.*",
-]

Cargo.toml

@@ -13,20 +13,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=12.0.0-beta.17", default-features = false, "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=12.0.0-beta.17", default-features = false, "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=12.0.0-beta.17", default-features = false, "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=12.0.0-beta.17", "tag" = "v12.0.0-beta.17", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=12.0.0-beta.14", default-features = false, "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=12.0.0-beta.14", "tag" = "v12.0.0-beta.14", "git" = "https://github.com/lance-format/lance.git" }
 lancedb = { path = "rust/lancedb", default-features = false }
 ahash = "0.8"
 # Note that this one does not include pyarrow
@@ -60,7 +60,7 @@ log = "0.4"
 metrics = "0.24"
 metrics-util = "0.19"
 moka = { version = "0.12", features = ["future"] }
-object_store = "0.14.1"
+object_store = "0.13.2"
 pin-project = "1.0.7"
 rand = "0.9"
 snafu = "0.8"

docs/openapi.yml

@@ -155,7 +155,7 @@ paths:
                 vector:
                   type: FixedSizeList
                   description: |
-                    The targeted vector to search for. Required.
+                    The targetted vector to search for. Required.
                 vector_column:
                   type: string
                   description: |

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>0.39.0-beta.6</version>
+    <version>0.39.0-beta.5</version>
 </dependency>
 ```
 

docs/src/js/classes/MergeInsertBuilder.md

@@ -141,7 +141,7 @@ Currently this causes multiple copies of the row to be created
 but that behavior is subject to change.
 
 An optional condition may be specified.  If it is, then only
-matched rows that satisfy the condition will be updated.  Any
+matched rows that satisfy the condtion will be updated.  Any
 rows that do not satisfy the condition will be left as they
 are.  Failing to satisfy the condition does not cause a
 "matched row" to become a "not matched" row.

docs/src/js/classes/Table.md

@@ -1266,7 +1266,7 @@ value is 0")
 Note: if your condition is something like "some_id_column == 7" and
 you are updating many rows (with different ids) then you will get
 better performance with a single [`merge_insert`] call instead of
-repeatedly calling this method.
+repeatedly calilng this method.
 
 ##### Parameters
 

docs/src/js/interfaces/HnswPqOptions.md

@@ -118,7 +118,7 @@ Number of sub-vectors of PQ.
 This value controls how much the vector is compressed during the quantization step.
 The more sub vectors there are the less the vector is compressed.  The default is
 the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divided by 8.
+by 16 we use the dimension divded by 8.
 
 The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
 us to use efficient SIMD instructions.

docs/src/js/interfaces/IndexOptions.md

@@ -16,7 +16,7 @@ optional config: Index;
 
 Advanced index configuration
 
-This option allows you to specify a specific index to create and also
+This option allows you to specify a specfic index to create and also
 allows you to pass in configuration for training the index.
 
 See the static methods on Index for details on the various index types.

docs/src/js/interfaces/IvfPqOptions.md

@@ -112,7 +112,7 @@ Number of sub-vectors of PQ.
 This value controls how much the vector is compressed during the quantization step.
 The more sub vectors there are the less the vector is compressed.  The default is
 the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-by 16 we use the dimension divided by 8.
+by 16 we use the dimension divded by 8.
 
 The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
 us to use efficient SIMD instructions.

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.39.0-beta.6</version>
+      <version>0.39.0-beta.5</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.39.0-beta.6</version>
+    <version>0.39.0-beta.5</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>12.0.0-beta.17</lance-core.version>
+        <lance-core.version>12.0.0-beta.14</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 = "0.39.0-beta.6"
+version = "0.39.0-beta.5"
 publish = false
 license.workspace = true
 description.workspace = true

nodejs/__test__/table.test.ts

@@ -281,7 +281,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
         numIndices: 0,
         numRows: 3,
         // Full on-disk size of the two data files, footers and metadata included.
-        totalBytes: 550,
+        totalBytes: 684,
       });
 
       // Index files count toward totalBytes too (only deletion files and
@@ -289,7 +289,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       await table.createIndex("id", { config: Index.btree() });
       const statsWithIndex = await table.stats();
       expect(statsWithIndex.numIndices).toBe(1);
-      expect(statsWithIndex.totalBytes).toBeGreaterThan(550);
+      expect(statsWithIndex.totalBytes).toBeGreaterThan(684);
     });
 
     it("should overwrite data if asked", async () => {
@@ -3252,7 +3252,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       const db = await connect(tmpDir.name);
       const data = [
         { text: "fa", vector: [0.1, 0.2, 0.3] },
-        { text: "fo", vector: [0.4, 0.5, 0.6] }, // spellchecker:disable-line
+        { text: "fo", vector: [0.4, 0.5, 0.6] },
         { text: "fob", vector: [0.4, 0.5, 0.6] },
         { text: "focus", vector: [0.4, 0.5, 0.6] },
         { text: "foo", vector: [0.4, 0.5, 0.6] },
@@ -3277,7 +3277,7 @@ describe.each([arrow15, arrow16, arrow17, arrow18])(
       const resultSet = new Set(fuzzyResults.map((r) => r.text));
       expect(resultSet.has("foo")).toBe(true);
       expect(resultSet.has("fob")).toBe(true);
-      expect(resultSet.has("fo")).toBe(true); // spellchecker:disable-line
+      expect(resultSet.has("fo")).toBe(true);
       expect(resultSet.has("food")).toBe(true);
 
       const prefixResults = await table

nodejs/lancedb/arrow.ts

@@ -600,7 +600,7 @@ function makeVector(
   }
   if (values.length === 0) {
     throw Error(
-      "makeVector requires at least one value or the type must be specified",
+      "makeVector requires at least one value or the type must be specfied",
     );
   }
   const sampleValue = values.find((val) => val !== null && val !== undefined);
@@ -858,7 +858,7 @@ async function applyEmbeddings<T>(
  * customized by the `embeddingDataType` property of the embedding function.
  *
  * If a schema is provided in `makeTableOptions` then it should include the
- * embedding columns.  If no schema is provided then embedding columns will
+ * embedding columns.  If no schema is provded then embedding columns will
  * be placed at the end of the table, after all of the input columns.
  */
 export async function convertToTable(

nodejs/lancedb/indices.ts

@@ -26,7 +26,7 @@ export interface IvfPqOptions {
    * This value controls how much the vector is compressed during the quantization step.
    * The more sub vectors there are the less the vector is compressed.  The default is
    * the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-   * by 16 we use the dimension divided by 8.
+   * by 16 we use the dimension divded by 8.
    *
    * The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
    * us to use efficient SIMD instructions.
@@ -228,7 +228,7 @@ export interface HnswPqOptions {
    * This value controls how much the vector is compressed during the quantization step.
    * The more sub vectors there are the less the vector is compressed.  The default is
    * the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-   * by 16 we use the dimension divided by 8.
+   * by 16 we use the dimension divded by 8.
    *
    * The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
    * us to use efficient SIMD instructions.
@@ -825,7 +825,7 @@ export interface IndexOptions {
   /**
    * Advanced index configuration
    *
-   * This option allows you to specify a specific index to create and also
+   * This option allows you to specify a specfic index to create and also
    * allows you to pass in configuration for training the index.
    *
    * See the static methods on Index for details on the various index types.

nodejs/lancedb/merge.ts

@@ -27,7 +27,7 @@ export class MergeInsertBuilder {
    * but that behavior is subject to change.
    *
    * An optional condition may be specified.  If it is, then only
-   * matched rows that satisfy the condition will be updated.  Any
+   * matched rows that satisfy the condtion will be updated.  Any
    * rows that do not satisfy the condition will be left as they
    * are.  Failing to satisfy the condition does not cause a
    * "matched row" to become a "not matched" row.

nodejs/lancedb/sanitize.ts

@@ -3,7 +3,7 @@
 
 // The utilities in this file help sanitize data from the user's arrow
 // library into the types expected by vectordb's arrow library.  Node
-// generally allows for multiple versions of the same library (and sometimes
+// generally allows for mulitple versions of the same library (and sometimes
 // even multiple copies of the same version) to be installed at the same
 // time.  However, arrow-js uses instanceof which expected that the input
 // comes from the exact same library instance.  This is not always the case

nodejs/lancedb/table.ts

@@ -313,7 +313,7 @@ export abstract class Table {
    * Note: if your condition is something like "some_id_column == 7" and
    * you are updating many rows (with different ids) then you will get
    * better performance with a single [`merge_insert`] call instead of
-   * repeatedly calling this method.
+   * repeatedly calilng this method.
    * @param {Map<string, string> | Record<string, string>} updates - the
    * columns to update
    * @returns {Promise<UpdateResult>} A promise that resolves to an object

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.39.0-beta.6",
+	"version": "0.39.0-beta.5",
 	"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": "0.39.0-beta.6",
+	"version": "0.39.0-beta.5",
 	"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": "0.39.0-beta.6",
+	"version": "0.39.0-beta.5",
 	"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": "0.39.0-beta.6",
+	"version": "0.39.0-beta.5",
 	"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": "0.39.0-beta.6",
+	"version": "0.39.0-beta.5",
 	"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": "0.39.0-beta.6",
+  "version": "0.39.0-beta.5",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.39.0-beta.6",
+	"version": "0.39.0-beta.5",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.39.0-beta.6",
+  "version": "0.39.0-beta.5",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-python"
-version = "0.39.0-beta.6"
+version = "0.39.0-beta.5"
 publish = false
 edition.workspace = true
 description = "Python bindings for LanceDB"

python/python/lancedb/embeddings/gte.py

@@ -21,7 +21,7 @@ class GteEmbeddings(TextEmbeddingFunction):
     An embedding function that uses GTE-LARGE MLX format(for Apple silicon devices only)
     as well as the standard cpu/gpu version from: https://huggingface.co/thenlper/gte-large.
 
-    For Apple users, you will need the mlx package installed, which can be done with:
+    For Apple users, you will need the mlx package insalled, which can be done with:
         pip install mlx
 
     Parameters

python/python/lancedb/embeddings/instructor.py

@@ -60,7 +60,7 @@ class InstructorEmbeddingFunction(TextEmbeddingFunction):
 
     import lancedb
     from lancedb.pydantic import LanceModel, Vector
-    from lancedb.embeddings import get_registry, InstructorEmbeddingFunction
+    from lancedb.embeddings import get_registry, InstuctorEmbeddingFunction
 
     instructor = get_registry().get("instructor").create(
         source_instruction="represent the document for retrieval",

python/python/lancedb/index.py

@@ -751,7 +751,7 @@ class IvfPq:
         This value controls how much the vector is compressed during the
         quantization step.  The more sub vectors there are the less the vector is
         compressed.  The default is the dimension of the vector divided by 16.  If
-        the dimension is not evenly divisible by 16 we use the dimension divided by
+        the dimension is not evenly divisible by 16 we use the dimension divded by
         8.
 
         The above two cases are highly preferred.  Having 8 or 16 values per

python/python/lancedb/query.py

@@ -78,10 +78,6 @@ if TYPE_CHECKING:
 T = TypeVar("T", bound="LanceModel")
 AnalyzePlanDistributedMetrics = Literal["aggregate", "per_worker", "full"]
 
-# Number of rows a hybrid query returns when no limit was set on it. This
-# mirrors the default the Rust query builder applies to its sub-queries.
-DEFAULT_HYBRID_LIMIT = 10
-
 
 @runtime_checkable
 class _LanceScanner(Protocol):
@@ -863,7 +859,7 @@ class Query(pydantic.BaseModel):
         return query
 
     # This tells pydantic to allow custom types (needed for the `vector` query since
-    # pa.Array wouldn't be allowed otherwise)
+    # pa.Array wouln't be allowed otherwise)
     model_config = pydantic.ConfigDict(arbitrary_types_allowed=True)
 
 
@@ -3897,54 +3893,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
 
         return self
 
-    def _create_child_queries(
-        self,
-    ) -> Tuple["AsyncFTSQuery", "AsyncVectorQuery", int, int]:
-        """Build the sub-queries that make up this hybrid query.
-
-        Execution, `explain_plan` and `analyze_plan` all go through here so that
-        the plans that are reported are the plans that actually run.
-
-        Returns the two sub-queries along with the effective limit and offset of
-        the hybrid query itself.
-        """
-        fts_query = AsyncFTSQuery(self._inner.to_fts_query(), self._table)
-        vec_query = AsyncVectorQuery(self._inner.to_vector_query(), self._table)
-
-        fts_req = fts_query._inner.to_query_request()
-        vec_req = vec_query._inner.to_query_request()
-
-        # Only one of the two sub-queries carries the limit when it was never
-        # set explicitly: nearest_to()/nearest_to_text() build the sibling query
-        # from scratch, and that is where the default gets filled in. Which one
-        # that is depends on the order the hybrid query was built in, so look at
-        # both rather than at a single side.
-        limit = fts_req.limit if fts_req.limit is not None else vec_req.limit
-        if limit is None:
-            limit = DEFAULT_HYBRID_LIMIT
-        offset = fts_req.offset or vec_req.offset or 0
-
-        fts_query.with_row_id()
-        vec_query.with_row_id()
-
-        # offset() pushes the offset down into both sub-queries, which would make
-        # each of them skip its own first `offset` rows. The window has to be
-        # taken out of the combined, reranked results instead, so fetch the
-        # skipped prefix here too and slice it off afterwards.
-        fts_query.limit(limit + offset)
-        vec_query.limit(limit + offset)
-        fts_query.offset(0)
-        vec_query.offset(0)
-
-        return fts_query, vec_query, limit, offset
-
     async def to_batches(
         self,
         *,
         max_batch_length: Optional[int] = None,
         timeout: Optional[timedelta] = None,
     ) -> AsyncRecordBatchReader:
-        fts_query, vec_query, limit, offset = self._create_child_queries()
+        fts_query = AsyncFTSQuery(self._inner.to_fts_query(), self._table)
+        vec_query = AsyncVectorQuery(self._inner.to_vector_query(), self._table)
 
         req = fts_query._inner.to_query_request()
         blob_auto_row_id = False
@@ -3964,6 +3920,9 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         self._blob_auto_row_id = blob_auto_row_id
         self._blob_paths = blob_paths
 
+        fts_query.with_row_id()
+        vec_query.with_row_id()
+
         fts_results, vector_results = await asyncio.gather(
             fts_query.to_arrow(timeout=timeout),
             vec_query.to_arrow(timeout=timeout),
@@ -3975,9 +3934,8 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
             norm=self._norm,
             fts_query=fts_query.get_query(),
             reranker=self._reranker,
-            limit=limit,
+            limit=self._inner.get_limit(),
             with_row_ids=True,
-            offset=offset,
         )
         if (
             not self._user_requested_row_id()
@@ -4006,14 +3964,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         ...     print(plan)
         >>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
         RRFReranker(K=60)
-            ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance, _rowid@1 as _rowid]
+            ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance]
               LanceRead: uri=..., projection=[text], source=stream(_rowid)
                 GlobalLimitExec: skip=0, fetch=10
                   FilterExec: _distance@2 IS NOT NULL
                     SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
                       KNNVectorDistance: metric=l2
                         LanceRead: uri=..., projection=[vector], ...
-            ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score, _rowid@0 as _rowid]
+            ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score]
               LanceRead: uri=..., projection=[vector, text], source=stream(_rowid)
                 GlobalLimitExec: skip=0, fetch=10
                   MatchQuery: column=text, query=[hello]
@@ -4028,9 +3986,8 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         plan : str
         """  # noqa: E501
 
-        fts_query, vec_query, _, _ = self._create_child_queries()
-        vector_plan = await vec_query.explain_plan(verbose)
-        fts_plan = await fts_query.explain_plan(verbose)
+        vector_plan = await self._inner.to_vector_query().explain_plan(verbose)
+        fts_plan = await self._inner.to_fts_query().explain_plan(verbose)
         # Indent sub-plans under the reranker
         indented_vector = "\n".join("  " + line for line in vector_plan.splitlines())
         indented_fts = "\n".join("  " + line for line in fts_plan.splitlines())
@@ -4057,12 +4014,14 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         -------
         plan : str
         """
-        fts_query, vec_query, _, _ = self._create_child_queries()
-
         results = ["Vector Search Query:"]
-        results.append(await vec_query.analyze_plan(distributed_metrics))
+        results.append(
+            await self._inner.to_vector_query().analyze_plan(distributed_metrics)
+        )
         results.append("FTS Search Query:")
-        results.append(await fts_query.analyze_plan(distributed_metrics))
+        results.append(
+            await self._inner.to_fts_query().analyze_plan(distributed_metrics)
+        )
 
         return "\n".join(results)
 

python/python/lancedb/remote/table.py

@@ -720,7 +720,7 @@ class RemoteTable(Table):
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image

python/python/lancedb/rerankers/base.py

@@ -175,7 +175,7 @@ class Reranker(ABC):
             if the results haven't been executed yet or the results in arrow format.
         query : str or None,
             The input query. Some rerankers might not need the query to rerank.
-            In that case, it can be set to None explicitly. This is intended to
+            In that case, it can be set to None explicitly. This is inteded to
             be handled by the reranker implementations.
         deduplicate : bool, optional
             Whether to deduplicate the results based on the `_rowid` column,

python/python/lancedb/table.py

@@ -1619,7 +1619,7 @@ class Table(ABC):
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image
@@ -3841,7 +3841,7 @@ class LanceTable(Table):
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image
@@ -5638,7 +5638,7 @@ class AsyncTable:
         if fill_value is None:
             fill_value = 0.0
 
-        # _sanitize_data is an old code path, but we will use it until the
+        # _santitize_data is an old code path, but we will use it until the
         # new code path is ready.
         if mode == "overwrite":
             # For overwrite, apply the same preprocessing as create_table
@@ -5814,7 +5814,7 @@ class AsyncTable:
         Parameters
         ----------
         query: list/np.ndarray/str/PIL.Image.Image, default None
-            The targeted vector to search for.
+            The targetted vector to search for.
 
             - *default None*.
             Acceptable types are: list, np.ndarray, PIL.Image.Image

python/python/tests/test_blob.py

@@ -297,10 +297,7 @@ def test_blob_v2_projection_sources_use_typed_column_name():
 
 
 def _legacy_v1_table(name):
-    # Legacy v1 blob columns are only writable at file version <= 2.1.
-    db = lancedb.connect(
-        "memory:///", storage_options={"new_table_data_storage_version": "2.1"}
-    )
+    db = lancedb.connect("memory:///")
     schema = pa.schema(
         [
             pa.field("id", pa.int64()),

python/python/tests/test_embeddings.py

@@ -327,8 +327,8 @@ def test_embedding_function_with_pandas(tmp_path):
         ) -> List[np.array]:
             return [np.random.randn(self.ndims()).tolist() for _ in range(len(texts))]
 
-    registry = get_registry()
-    func = registry.get("mock-embedding").create()
+    registery = get_registry()
+    func = registery.get("mock-embedding").create()
 
     class TestSchema(LanceModel):
         text: str = func.SourceField()
@@ -394,9 +394,9 @@ def test_multiple_embeddings_for_pandas(tmp_path):
         ) -> List[np.array]:
             return [np.random.randn(self.ndims()).tolist() for _ in range(len(texts))]
 
-    registry = get_registry()
-    func1 = registry.get("mock-embedding").create()
-    func2 = registry.get("mock-embedding2").create()
+    registery = get_registry()
+    func1 = registery.get("mock-embedding").create()
+    func2 = registery.get("mock-embedding2").create()
 
     class TestSchema(LanceModel):
         text: str = func1.SourceField()

python/python/tests/test_fts.py

@@ -1011,13 +1011,8 @@ def test_fts_ngram(mem_db: DBConnection):
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
     results = (
-        table.search(
-            "nce",  # spellchecker:disable-line
-            query_type="fts",
-        )
-        .limit(10)
-        .to_list()
-    )
+        table.search("nce", query_type="fts").limit(10).to_list()
+    )  # spellchecker:disable-line
     assert len(results) == 2
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
@@ -1039,13 +1034,8 @@ def test_fts_ngram(mem_db: DBConnection):
     assert set(r["text"] for r in results) == {"lance database", "lance is cool"}
 
     results = (
-        table.search(
-            "nce",  # spellchecker:disable-line
-            query_type="fts",
-        )
-        .limit(10)
-        .to_list()
-    )
+        table.search("nce", query_type="fts").limit(10).to_list()
+    )  # spellchecker:disable-line
     assert len(results) == 0
 
     results = table.search("la", query_type="fts").limit(10).to_list()

python/python/tests/test_hybrid_query.py

@@ -203,93 +203,6 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
     assert texts.count("a") == 1
 
 
-@pytest.mark.asyncio
-async def test_async_hybrid_query_offset(table: AsyncTable):
-    # The offset window of a hybrid query must be a suffix of the same query
-    # run without an offset. Skipping the first rows of each sub-query instead
-    # of the first rows of the fused result silently changes which rows land in
-    # the window.
-    full = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("dog")
-        .limit(4)
-        .with_row_id()
-        .to_arrow()
-    )
-    assert len(full) == 4
-
-    second_page = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("dog")
-        .offset(2)
-        .limit(2)
-        .with_row_id()
-        .to_arrow()
-    )
-    assert second_page["_rowid"].to_pylist() == full["_rowid"].to_pylist()[2:]
-
-    first_page = await (
-        table.query()
-        .nearest_to([0.0, 0.4])
-        .nearest_to_text("dog")
-        .limit(2)
-        .with_row_id()
-        .to_arrow()
-    )
-    # Paging through the result must visit every row exactly once: no row
-    # repeated from the previous page and none dropped between the two.
-    paged = first_page["_rowid"].to_pylist() + second_page["_rowid"].to_pylist()
-    assert sorted(paged) == sorted(full["_rowid"].to_pylist())
-
-
-@pytest.mark.asyncio
-async def test_async_hybrid_query_fts_first_default_limit(table: AsyncTable):
-    # nearest_to() and nearest_to_text() build their new sibling sub-query from
-    # scratch, and that is the sub-query the default limit ends up on. So the
-    # side that carries the limit depends on the order the hybrid query was
-    # built in, and looking at only one side loses the limit for half the ways
-    # a hybrid query can be written. Without a limit the combined results are
-    # not truncated at all and the whole union of both candidate lists is
-    # returned.
-    await table.add([{"text": "dog", "vector": [50.0 + i, 50.0]} for i in range(10)])
-
-    result = await (
-        table.query().nearest_to_text("dog").nearest_to([0.1, 0.1]).to_arrow()
-    )
-    assert len(result) == 10
-
-    offset_result = await (
-        table.query().nearest_to_text("dog").nearest_to([0.1, 0.1]).offset(2).to_arrow()
-    )
-    assert len(offset_result) == 10
-
-
-@pytest.mark.asyncio
-async def test_async_hybrid_query_explain_plan_matches_execution(table: AsyncTable):
-    # Paging rewrites the sub-queries: each one fetches limit + offset rows with
-    # no offset of its own, and the window is sliced out after fusion. The plans
-    # have to be built from those rewritten sub-queries, otherwise explain_plan
-    # and analyze_plan describe a query that is never run.
-    query = (
-        table.query().nearest_to([0.0, 0.4]).nearest_to_text("dog").offset(2).limit(2)
-    )
-    await query.to_arrow()
-
-    plan = await query.explain_plan()
-    assert [
-        line.strip() for line in plan.splitlines() if "GlobalLimitExec" in line
-    ] == [
-        "GlobalLimitExec: skip=0, fetch=4",
-        "GlobalLimitExec: skip=0, fetch=4",
-    ]
-
-    analyzed = await query.analyze_plan()
-    assert analyzed.count("skip=0, fetch=4") == 2
-    assert "skip=2" not in analyzed
-
-
 def test_hybrid_query_offset(sync_table: Table):
     # The offset window of a hybrid query must be a suffix of the same query
     # run without an offset -- it must not be silently ignored.

python/python/tests/test_namespace.py

@@ -193,13 +193,7 @@ class TestNamespaceConnection:
             ),
         )
 
-        # Legacy v1 blob columns are only writable at file version <= 2.1.
-        table = db.create_table(
-            "blob_table",
-            data,
-            namespace_path=["test_ns"],
-            storage_options={"new_table_data_storage_version": "2.1"},
-        )
+        table = db.create_table("blob_table", data, namespace_path=["test_ns"])
         df = table.to_pandas(blob_mode="lazy").sort_values("id")
 
         blob = df["blob"].iloc[0]

python/python/tests/test_query.py

@@ -40,10 +40,6 @@ from utils import exception_output
 from importlib.util import find_spec
 
 
-# Legacy v1 blob columns are only writable at file version <= 2.1.
-LEGACY_BLOB_STORAGE_OPTIONS = {"new_table_data_storage_version": "2.1"}
-
-
 def _blob_query_data():
     return pa.table(
         {
@@ -123,17 +119,13 @@ def _assert_blob_bytes_projection(df):
 
 def _blob_query_table(db, name, blob_schema):
     if blob_schema == "v1":
-        return db.create_table(
-            name, _blob_query_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return db.create_table(name, _blob_query_data())
     return _create_blob_v2_query_table(db, name)
 
 
 async def _blob_query_table_async(db, name, blob_schema):
     if blob_schema == "v1":
-        return await db.create_table(
-            name, _blob_query_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return await db.create_table(name, _blob_query_data())
     return await _create_blob_v2_query_table_async(db, name)
 
 
@@ -283,9 +275,7 @@ async def test_query_to_pandas_kwargs(table, table_async):
 def test_plain_scan_query_to_pandas_blob_modes(tmp_db, blob_mode):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        f"test_query_to_pandas_blob_{blob_mode}",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        f"test_query_to_pandas_blob_{blob_mode}", _blob_query_data()
     )
 
     df = (
@@ -332,9 +322,7 @@ def test_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow(
 ):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        "test_query_to_pandas_blob_no_arrow_collect",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_query_to_pandas_blob_no_arrow_collect", _blob_query_data()
     )
     query = table.search().where("id = 1").select(["id", "blob"])
 
@@ -359,9 +347,7 @@ def test_plain_scan_query_to_pandas_blob_descriptions_flatten_uses_scanner(
 ):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        "test_query_to_pandas_blob_desc_flatten",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_query_to_pandas_blob_desc_flatten", _blob_query_data()
     )
     query = table.search().where("id = 1").select(["id", "blob"])
 
@@ -379,11 +365,7 @@ def test_plain_scan_query_to_pandas_blob_descriptions_flatten_uses_scanner(
 def test_plain_scan_query_to_pandas_scanner_state(tmp_db):
     pytest.importorskip("lance")
     data = _blob_query_data()
-    table = tmp_db.create_table(
-        "test_query_to_pandas_scanner_state",
-        data.slice(0, 2),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
-    )
+    table = tmp_db.create_table("test_query_to_pandas_scanner_state", data.slice(0, 2))
     table.add(data.slice(2, 2))
 
     fragments = table.to_lance().get_fragments()
@@ -418,9 +400,7 @@ def test_plain_scan_query_to_pandas_scanner_state(tmp_db):
 async def test_async_plain_scan_query_to_pandas_blob_projection(tmp_db_async):
     pytest.importorskip("lance")
     table = await tmp_db_async.create_table(
-        "test_async_query_to_pandas_blob_projection",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_async_query_to_pandas_blob_projection", _blob_query_data()
     )
 
     lazy_df = await (
@@ -472,9 +452,7 @@ async def test_async_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow
 ):
     pytest.importorskip("lance")
     table = await tmp_db_async.create_table(
-        "test_async_query_to_pandas_blob_no_arrow_collect",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_async_query_to_pandas_blob_no_arrow_collect", _blob_query_data()
     )
     query = table.query().where("id = 1").select(["id", "blob"])
 
@@ -496,11 +474,7 @@ async def test_async_plain_scan_query_to_pandas_blob_mode_does_not_collect_arrow
 
 def test_vector_query_to_pandas_blob_mode_requires_native_path(tmp_db):
     pytest.importorskip("lance")
-    table = tmp_db.create_table(
-        "test_vector_query_blob_mode",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
-    )
+    table = tmp_db.create_table("test_vector_query_blob_mode", _blob_query_data())
 
     with pytest.raises(RuntimeError, match="Lance native pandas conversion"):
         table.search([1.0, 0.0]).select(["blob", "vector"]).limit(1).to_pandas(
@@ -511,9 +485,7 @@ def test_vector_query_to_pandas_blob_mode_requires_native_path(tmp_db):
 def test_vector_query_to_pandas_blob_descriptions_requires_plain_scan(tmp_db):
     pytest.importorskip("lance")
     table = tmp_db.create_table(
-        "test_vector_query_blob_descriptions",
-        _blob_query_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
+        "test_vector_query_blob_descriptions", _blob_query_data()
     )
 
     with pytest.raises(RuntimeError, match="plain scan query"):

python/python/tests/test_rerankers.py

@@ -81,7 +81,7 @@ def get_test_table(tmp_path):
         "but his son was mortal",
         "there hasn't been a good battlefield game since 2142",
         "I wish they would make another one",
-        "campaigns are not as good as they used to be",
+        "campains are not as good as they used to be",
         "Multiplayer and open world games have destroyed the single player experience",
         "Maybe the future is console games",
         "I don't know",

python/python/tests/test_table.py

@@ -64,23 +64,15 @@ async def _blob_v2_table_async(db: AsyncConnection, name: str):
     return table
 
 
-# Legacy v1 blob columns are only writable at file version <= 2.1.
-LEGACY_BLOB_STORAGE_OPTIONS = {"new_table_data_storage_version": "2.1"}
-
-
 def _blob_table(db: DBConnection, name: str, blob_schema: str):
     if blob_schema == "v1":
-        return db.create_table(
-            name, data=_blob_test_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return db.create_table(name, data=_blob_test_data())
     return _blob_v2_table(db, name)
 
 
 async def _blob_table_async(db: AsyncConnection, name: str, blob_schema: str):
     if blob_schema == "v1":
-        return await db.create_table(
-            name, data=_blob_test_data(), storage_options=LEGACY_BLOB_STORAGE_OPTIONS
-        )
+        return await db.create_table(name, data=_blob_test_data())
     return await _blob_v2_table_async(db, name)
 
 
@@ -155,11 +147,7 @@ def test_table_to_pandas_invalid_blob_mode_non_blob_table(tmp_db: DBConnection):
 @pytest.mark.parametrize("blob_mode", ["lazy", "bytes", "descriptions"])
 def test_table_to_pandas_blob_modes(tmp_db: DBConnection, blob_mode):
     pytest.importorskip("lance")
-    table = tmp_db.create_table(
-        f"test_to_pandas_blob_{blob_mode}",
-        _blob_test_data(),
-        storage_options=LEGACY_BLOB_STORAGE_OPTIONS,
-    )
+    table = tmp_db.create_table(f"test_to_pandas_blob_{blob_mode}", _blob_test_data())
 
     df = table.to_pandas(blob_mode=blob_mode)
 
@@ -3354,7 +3342,7 @@ def test_empty_query(mem_db: DBConnection):
     # None is the same as default
     df = table.search().select(["id"]).limit(None).to_arrow()
     assert df.num_rows == 100
-    # invalid limist is the same as None, which is the same as default
+    # invalid limist is the same as None, wihch is the same as default
     df = table.search().select(["id"]).limit(-1).to_arrow()
     assert df.num_rows == 100
     # valid limit should work
@@ -3971,7 +3959,7 @@ def test_stats(mem_db: DBConnection):
     print(f"{stats=}")
     assert stats == {
         # Full on-disk size of the data file, footer and metadata included.
-        "total_bytes": 637,
+        "total_bytes": 633,
         "num_rows": 2,
         "num_indices": 0,
         "fragment_stats": {

python/src/query.rs

@@ -334,7 +334,7 @@ pub struct PyQueryRequest {
     pub column: Option<String>,
     pub query_vector: Option<PyQueryVectors>,
     pub minimum_nprobes: Option<usize>,
-    // None means user did not set it and default should be used (currently 20)
+    // None means user did not set it and default shoud be used (currenty 20)
     // Some(0) means user set it to None and there is no limit
     pub maximum_nprobes: Option<usize>,
     pub lower_bound: Option<f32>,

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.39.0-beta.6"
+version = "0.39.0-beta.5"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/arrow.rs

@@ -163,7 +163,7 @@ pub struct PolarsDataFrameRecordBatchReader {
 impl PolarsDataFrameRecordBatchReader {
     /// Creates a new `PolarsDataFrameRecordBatchReader` from a given Polars DataFrame.
     /// If the input dataframe does not have aligned chunks, this function undergoes
-    /// the costly operation of reallocating each series as a single contiguous chunk.
+    /// the costly operation of reallocating each series as a single contigous chunk.
     pub fn new(mut df: DataFrame) -> Result<Self> {
         df.align_chunks();
         let arrow_schema =

rust/lancedb/src/blob.rs

@@ -532,11 +532,10 @@ mod tests {
     fn storage_version_bumps_to_v2_2() {
         let mut params = WriteParams::default();
         ensure_blob_storage_version(&blob_schema(), &mut params);
-        let resolved = params
-            .data_storage_version
-            .unwrap_or(LanceFileVersion::Stable)
-            .resolve();
-        assert_eq!(resolved, ConcreteFileVersion::V2_2);
+        assert_eq!(
+            params.data_storage_version.unwrap().resolve(),
+            ConcreteFileVersion::V2_2
+        );
         assert!(!params.enable_stable_row_ids);
     }
 
@@ -548,11 +547,10 @@ mod tests {
         };
         ensure_blob_storage_version(&blob_schema(), &mut params);
         assert!(params.enable_stable_row_ids);
-        let resolved = params
-            .data_storage_version
-            .unwrap_or(LanceFileVersion::Stable)
-            .resolve();
-        assert_eq!(resolved, ConcreteFileVersion::V2_2);
+        assert_eq!(
+            params.data_storage_version.unwrap().resolve(),
+            ConcreteFileVersion::V2_2
+        );
     }
 
     #[test]

rust/lancedb/src/connection.rs

@@ -827,7 +827,7 @@ impl Connection {
 pub struct ConnectRequest {
     /// Database URI
     ///
-    /// ### Accepted URI formats
+    /// ### Accpeted URI formats
     ///
     /// - `/path/to/database` - local database on file system.
     /// - `s3://bucket/path/to/database` or `gs://bucket/path/to/database` - database on cloud object store

rust/lancedb/src/database/listing.rs

@@ -512,7 +512,7 @@ impl ListingDatabase {
                 // iter thru the query params and extract the commit store param
                 let mut engine = None;
                 let mut mirrored_store = None;
-                let mut filtered_queries = vec![];
+                let mut filtered_querys = vec![];
 
                 // WARNING: specifying engine is NOT a publicly supported feature in lancedb yet
                 // THE API WILL CHANGE
@@ -528,13 +528,13 @@ impl ListingDatabase {
                         mirrored_store = Some(value.to_string());
                     } else {
                         // to owned so we can modify the url
-                        filtered_queries.push((key.to_string(), value.to_string()));
+                        filtered_querys.push((key.to_string(), value.to_string()));
                     }
                 }
 
                 // Filter out the commit store query param -- it's a lancedb param
                 url.query_pairs_mut().clear();
-                url.query_pairs_mut().extend_pairs(filtered_queries);
+                url.query_pairs_mut().extend_pairs(filtered_querys);
                 // Take a copy of the query string so we can propagate it to lance.
                 // `query_pairs_mut()` leaves the URL with `Some("")` even when no
                 // pairs survive (or none existed in the first place), so an empty
@@ -896,11 +896,11 @@ impl Database for ListingDatabase {
     }
 
     async fn read_consistency(&self) -> Result<ReadConsistency> {
-        if let Some(interval) = self.read_consistency_interval {
-            if interval.is_zero() {
+        if let Some(read_consistency_inverval) = self.read_consistency_interval {
+            if read_consistency_inverval.is_zero() {
                 Ok(ReadConsistency::Strong)
             } else {
-                Ok(ReadConsistency::Eventual(interval))
+                Ok(ReadConsistency::Eventual(read_consistency_inverval))
             }
         } else {
             Ok(ReadConsistency::Manual)
@@ -3043,15 +3043,15 @@ mod tests {
     /// across platforms — see the `file://` test below).
     fn capture_query_like_connect(input_uri: &str) -> Option<String> {
         let mut url = url::Url::parse(input_uri).unwrap();
-        let mut filtered_queries = Vec::new();
+        let mut filtered_querys = Vec::new();
         for (key, value) in url.query_pairs() {
             if key == ENGINE || key == MIRRORED_STORE {
                 continue;
             }
-            filtered_queries.push((key.to_string(), value.to_string()));
+            filtered_querys.push((key.to_string(), value.to_string()));
         }
         url.query_pairs_mut().clear();
-        url.query_pairs_mut().extend_pairs(filtered_queries);
+        url.query_pairs_mut().extend_pairs(filtered_querys);
         url.query().filter(|q| !q.is_empty()).map(|s| s.to_string())
     }
 

rust/lancedb/src/database/namespace.rs

@@ -251,11 +251,11 @@ impl Database for LanceNamespaceDatabase {
     }
 
     async fn read_consistency(&self) -> Result<ReadConsistency> {
-        if let Some(interval) = self.read_consistency_interval {
-            if interval.is_zero() {
+        if let Some(read_consistency_inverval) = self.read_consistency_interval {
+            if read_consistency_inverval.is_zero() {
                 Ok(ReadConsistency::Strong)
             } else {
-                Ok(ReadConsistency::Eventual(interval))
+                Ok(ReadConsistency::Eventual(read_consistency_inverval))
             }
         } else {
             Ok(ReadConsistency::Manual)

rust/lancedb/src/index/vector.rs

@@ -125,7 +125,7 @@ macro_rules! impl_pq_params_setter {
         /// This value controls how much the vector is compressed during the quantization step.
         /// The more sub vectors there are the less the vector is compressed.  The default is
         /// the dimension of the vector divided by 16.  If the dimension is not evenly divisible
-        /// by 16 we use the dimension divided by 8.
+        /// by 16 we use the dimension divded by 8.
         ///
         /// The above two cases are highly preferred.  Having 8 or 16 values per subvector allows
         /// us to use efficient SIMD instructions.

rust/lancedb/src/materialized_view.rs

@@ -1917,16 +1917,7 @@ mod tests {
     /// declaration buried in a struct child binds as hard as one on top.
     #[tokio::test]
     async fn test_nested_projection_metadata_and_declarations() {
-        // The schema below carries the legacy v1 blob marker, which Lance only
-        // allows writing at file version <= 2.1.
-        let conn = connect("memory://")
-            .storage_options([(
-                crate::database::listing::OPT_NEW_TABLE_STORAGE_VERSION,
-                "2.1",
-            )])
-            .execute()
-            .await
-            .unwrap();
+        let conn = connect("memory://").execute().await.unwrap();
         let payload = crate::blob("payload", true).with_metadata(HashMap::from([
             ("lance-encoding:blob".to_string(), "true".to_string()),
             (

rust/lancedb/src/query.rs

@@ -1299,7 +1299,7 @@ impl VectorQuery {
     /// This can be useful when there is a narrow filter to allow these queries to
     /// spend more time searching and avoid potential false negatives.
     ///
-    /// Set to None to search all partitions, if needed, to satisfy the limit
+    /// Set to None to search all partitions, if needed, to satsify the limit
     pub fn maximum_nprobes(mut self, maximum_nprobes: Option<usize>) -> Result<Self> {
         if let Some(maximum_nprobes) = maximum_nprobes {
             if maximum_nprobes == 0 {

rust/lancedb/src/table.rs

@@ -240,7 +240,7 @@ enum BadVectorHandling {
     /// An error is returned
     #[default]
     Error,
-    /// The offending row is dropped
+    /// The offending row is droppped
     Drop,
     /// The invalid/missing items are replaced by fill_value
     Fill(f32),
@@ -1326,7 +1326,7 @@ impl Table {
     /// Note: if your condition is something like "some_id_column == 7" and
     /// you are updating many rows (with different ids) then you will get
     /// better performance with a single [`merge_insert`] call instead of
-    /// repeatedly calling this method.
+    /// repeatedly calilng this method.
     pub fn update(&self) -> UpdateBuilder {
         UpdateBuilder::new(self.inner.clone())
     }
@@ -5678,7 +5678,7 @@ mod tests {
             TableStatistics {
                 num_rows: 250,
                 num_indices: 0,
-                total_bytes: 8969,
+                total_bytes: 8925,
                 fragment_stats: FragmentStatistics {
                     num_fragments: 11,
                     num_small_fragments: 11,

rust/lancedb/src/table/dataset.rs

@@ -52,7 +52,7 @@ enum ConsistencyMode {
     /// refresh_window = min(3s, TTL/4)
     ///
     /// | t < TTL - refresh_window | t < TTL                           | t >= TTL            |
-    /// |  Return value            | Background refresh & return value |  synchronous refresh |
+    /// |  Return value            | Background refresh & return value |  syncronous refresh |
     Eventual(BackgroundCache<Arc<Dataset>, Error>),
 }
 

rust/lancedb/src/table/merge.rs

@@ -103,7 +103,7 @@ impl MergeInsertBuilder {
     /// but that behavior is subject to change.
     ///
     /// An optional condition may be specified.  If it is, then only
-    /// matched rows that satisfy the condition will be updated.  Any
+    /// matched rows that satisfy the condtion will be updated.  Any
     /// rows that do not satisfy the condition will be left as they
     /// are.  Failing to satisfy the condition does not cause a
     /// "matched row" to become a "not matched" row.

rust/lancedb/src/table/merge/lsm.rs

@@ -904,7 +904,7 @@ fn unsharded_shard_id() -> Uuid {
 
 /// Build a [`ShardWriterConfig`] from the persisted `writer_config_defaults`.
 ///
-/// Unknown or unparsable keys are ignored; absent keys keep the
+/// Unknown or unparseable keys are ignored; absent keys keep the
 /// [`ShardWriterConfig`] default. The shard id is set by `mem_wal_writer`.
 fn shard_writer_config_from_defaults(defaults: &HashMap<String, String>) -> ShardWriterConfig {
     let mut config = ShardWriterConfig::default().with_shard_spec_id(SHARDING_SPEC_ID);

rust/lancedb/tests/blob_integration.rs

@@ -19,7 +19,6 @@ use lancedb::{
     connect, connect_namespace,
     database::listing::{
         ListingDatabaseOptions, NewTableConfig, OPT_NEW_TABLE_ENABLE_STABLE_ROW_IDS,
-        OPT_NEW_TABLE_STORAGE_VERSION,
     },
     query::{ExecutableQuery, QueryBase},
     table::{AddDataMode, CompactionOptions, OptimizeAction, OptimizeStats, WriteOptions},
@@ -147,10 +146,7 @@ async fn non_blob_table_keeps_default_format_and_row_id_setting() -> Result<()>
     let schema = Arc::new(Schema::new(vec![Field::new("id", DataType::Int64, false)]));
     let table = db.create_empty_table("t", schema).execute().await?;
 
-    assert_eq!(
-        storage_format_version(&table).await,
-        LanceFileVersion::Stable.resolve()
-    );
+    assert!(!supports_blob_v2(storage_format_version(&table).await));
     assert!(!uses_stable_row_ids(&table).await);
     Ok(())
 }
@@ -813,11 +809,7 @@ async fn fetch_blobs_rejects_unknown_column() -> Result<()> {
 #[tokio::test]
 async fn fetch_blobs_rejects_legacy_v1_blob_column() -> Result<()> {
     let tmp = tempdir().unwrap();
-    // Legacy v1 blob columns are only writable at file version <= 2.1.
-    let db = connect(tmp.path().to_str().unwrap())
-        .storage_options([(OPT_NEW_TABLE_STORAGE_VERSION, "2.1")])
-        .execute()
-        .await?;
+    let db = connect(tmp.path().to_str().unwrap()).execute().await?;
     let legacy = Field::new("image", DataType::LargeBinary, true).with_metadata(
         std::collections::HashMap::from([("lance-encoding:blob".to_string(), "true".to_string())]),
     );