Bump version: 0.22.0-beta.10 → 0.22.0-beta.11

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

- **New Features**
- Added support for distance range filtering in hybrid vector queries,
allowing users to specify lower and upper bounds for search results.

- **Tests**
- Introduced new tests to validate distance range filtering and
reranking in both synchronous and asynchronous hybrid query scenarios.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Signed-off-by: BubbleCal <bubble-cal@outlook.com>

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.19.0-beta.9"
+current_version = "0.19.0-beta.10"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/docs.yml

@@ -18,17 +18,24 @@ concurrency:
   group: "pages"
   cancel-in-progress: true
 
+env:
+  # This reduces the disk space needed for the build
+  RUSTFLAGS: "-C debuginfo=0"
+  # according to: https://matklad.github.io/2021/09/04/fast-rust-builds.html
+  # CI builds are faster with incremental disabled.
+  CARGO_INCREMENTAL: "0"
+
 jobs:
   # Single deploy job since we're just deploying
   build:
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}
-    runs-on: buildjet-8vcpu-ubuntu-2204
+    runs-on: ubuntu-24.04
     steps:
       - name: Checkout
         uses: actions/checkout@v4
-      - name: Install dependecies needed for ubuntu
+      - name: Install dependencies needed for ubuntu
         run: |
           sudo apt install -y protobuf-compiler libssl-dev
           rustup update && rustup default
@@ -38,6 +45,7 @@ jobs:
           python-version: "3.10"
           cache: "pip"
           cache-dependency-path: "docs/requirements.txt"
+      - uses: Swatinem/rust-cache@v2
       - name: Build Python
         working-directory: python
         run: |
@@ -49,7 +57,6 @@ jobs:
           node-version: 20
           cache: 'npm'
           cache-dependency-path: node/package-lock.json
-      - uses: Swatinem/rust-cache@v2
       - name: Install node dependencies
         working-directory: node
         run: |

Cargo.lock

@@ -4136,7 +4136,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb"
-version = "0.19.0-beta.9"
+version = "0.19.0-beta.10"
 dependencies = [
  "arrow",
  "arrow-array",
@@ -4223,7 +4223,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-node"
-version = "0.19.0-beta.9"
+version = "0.19.0-beta.10"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4248,7 +4248,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-nodejs"
-version = "0.19.0-beta.9"
+version = "0.19.0-beta.10"
 dependencies = [
  "arrow-array",
  "arrow-ipc",
@@ -4266,7 +4266,7 @@ dependencies = [
 
 [[package]]
 name = "lancedb-python"
-version = "0.22.0-beta.9"
+version = "0.22.0-beta.10"
 dependencies = [
  "arrow",
  "env_logger",

java/core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
         <groupId>com.lancedb</groupId>
         <artifactId>lancedb-parent</artifactId>
-        <version>0.19.0-beta.9</version>
+        <version>0.19.0-beta.10</version>
         <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.19.0-beta.9</version>
+    <version>0.19.0-beta.10</version>
     <packaging>pom</packaging>
 
     <name>LanceDB Parent</name>

node/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "vectordb",
-  "version": "0.19.0-beta.9",
+  "version": "0.19.0-beta.10",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "vectordb",
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
       "cpu": [
         "x64",
         "arm64"
@@ -52,11 +52,11 @@
         "uuid": "^9.0.0"
       },
       "optionalDependencies": {
-        "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.9",
+        "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.10",
-        "@lancedb/vectordb-darwin-x64": "0.19.0-beta.9",
+        "@lancedb/vectordb-darwin-x64": "0.19.0-beta.10",
-        "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.9",
+        "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.10",
-        "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.9",
+        "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.10",
-        "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.9"
+        "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.10"
       },
       "peerDependencies": {
         "@apache-arrow/ts": "^14.0.2",
@@ -327,9 +327,9 @@
       }
     },
     "node_modules/@lancedb/vectordb-darwin-arm64": {
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.0-beta.9.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-arm64/-/vectordb-darwin-arm64-0.19.0-beta.10.tgz",
-      "integrity": "sha512-Sc4FFWT7ck7U2BKXnFl5EdPsb2ay8yOX3AqpIYbhenhpAkzLBS8NPUztuhybFoPeLSWKVUtwp9NGAxNyL9lgrQ==",
+      "integrity": "sha512-4PvsrE+hJ+AqFY33yHIEVET2ayv0pzpiWqCnMQ5OdpakQZvfykmp9ykc5KI80VuWAlniJDYuW+fju3z8/wiUHQ==",
       "cpu": [
         "arm64"
       ],
@@ -340,9 +340,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-darwin-x64": {
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.0-beta.9.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-darwin-x64/-/vectordb-darwin-x64-0.19.0-beta.10.tgz",
-      "integrity": "sha512-KiYzFFX7Hvq/OvsA7VZt0xfGRW4eoDcLwgWdXxgsNzB6X6d3eupUqkrTKe3KlHrnm170s5fwSFrJHIU/NPoA/A==",
+      "integrity": "sha512-YHXHkD4mmIry+KMoTX7Qts5Ea9fG0DklywIiF8TS7h/9XbXLG74lf+GUy2Eh/s1wKLd4LtRh2SbHpOtZoOH4lA==",
       "cpu": [
         "x64"
       ],
@@ -353,9 +353,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-arm64-gnu": {
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.0-beta.9.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-arm64-gnu/-/vectordb-linux-arm64-gnu-0.19.0-beta.10.tgz",
-      "integrity": "sha512-TCK/PEqvoVa/oxYHWsjpB+BaQ/KDfwOI76grbezAEDGYS76USAnNb8KB8bDnnadOu9/i4Zsha0Bk0fsHfDSSpg==",
+      "integrity": "sha512-c019rw30N25WIXnkhAwJ4QkpUcUJqbkGay3RiR3vTmGQ5YOZWw5V5g/v2y7APcv+ZlZfJ4YgDjFH8wqtiECNJQ==",
       "cpu": [
         "arm64"
       ],
@@ -366,9 +366,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-linux-x64-gnu": {
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.0-beta.9.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-linux-x64-gnu/-/vectordb-linux-x64-gnu-0.19.0-beta.10.tgz",
-      "integrity": "sha512-Ti7Z2Am5ziYZmQBpLfVwGWe+zl11xed084Gv6WFcYfyLz6FJ/0+CEMVx1wIsoZ1gq6tvH0vgZLYxsMF5C5xVnw==",
+      "integrity": "sha512-xnbC6rqpuJDv2q6xNBKrrocNOTcM4z6+8Zi7wP+Sb+WXvLzkR7hm7ZS0gyeExRknEEd91imhL/ZuAxEq1892YA==",
       "cpu": [
         "x64"
       ],
@@ -379,9 +379,9 @@
       ]
     },
     "node_modules/@lancedb/vectordb-win32-x64-msvc": {
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
-      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.0-beta.9.tgz",
+      "resolved": "https://registry.npmjs.org/@lancedb/vectordb-win32-x64-msvc/-/vectordb-win32-x64-msvc-0.19.0-beta.10.tgz",
-      "integrity": "sha512-MUSECQGbpRi3qbG6CsLJAInT0ZIMpr/RBhEx5CUlwZiEIWaUc/CQMoNJh7W+1s5Cd3UMBgkMpgmfj21Qd9fsHw==",
+      "integrity": "sha512-bUDKvY4tmMEeBpzPfRu2lVo+07nRGzUoUm60WzfvRpa/Y6rwjcCCRuuTOvfTcrnbGYN/kw5yoUu8ZDsZ7mT77Q==",
       "cpu": [
         "x64"
       ],

node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "vectordb",
-  "version": "0.19.0-beta.9",
+  "version": "0.19.0-beta.10",
   "description": " Serverless, low-latency vector database for AI applications",
   "private": false,
   "main": "dist/index.js",
@@ -89,10 +89,10 @@
     }
   },
   "optionalDependencies": {
-    "@lancedb/vectordb-darwin-x64": "0.19.0-beta.9",
+    "@lancedb/vectordb-darwin-x64": "0.19.0-beta.10",
-    "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.9",
+    "@lancedb/vectordb-darwin-arm64": "0.19.0-beta.10",
-    "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.9",
+    "@lancedb/vectordb-linux-x64-gnu": "0.19.0-beta.10",
-    "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.9",
+    "@lancedb/vectordb-linux-arm64-gnu": "0.19.0-beta.10",
-    "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.9"
+    "@lancedb/vectordb-win32-x64-msvc": "0.19.0-beta.10"
   }
 }

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.19.0-beta.9"
+version = "0.19.0-beta.10"
 license.workspace = true
 description.workspace = true
 repository.workspace = true

nodejs/npm/darwin-arm64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-arm64",
-	"version": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"os": ["darwin"],
 	"cpu": ["arm64"],
 	"main": "lancedb.darwin-arm64.node",

nodejs/npm/darwin-x64/package.json

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-darwin-x64",
-	"version": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"os": ["darwin"],
 	"cpu": ["x64"],
 	"main": "lancedb.darwin-x64.node",

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-linux-arm64-gnu",
-	"version": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"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": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"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": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"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": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"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": "0.19.0-beta.9",
+  "version": "0.19.0-beta.10",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.19.0-beta.9",
+	"version": "0.19.0-beta.10",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.19.0-beta.9",
+  "version": "0.19.0-beta.10",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.19.0-beta.9",
+      "version": "0.19.0-beta.10",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.19.0-beta.9",
+  "version": "0.19.0-beta.10",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.22.0-beta.10"
+current_version = "0.22.0-beta.11"
 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 = "0.22.0-beta.10"
+version = "0.22.0-beta.11"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/python/lancedb/query.py

@@ -28,6 +28,8 @@ import pyarrow.compute as pc
 import pyarrow.fs as pa_fs
 import pydantic
 
+from lancedb.pydantic import PYDANTIC_VERSION
+
 from . import __version__
 from .arrow import AsyncRecordBatchReader
 from .dependencies import pandas as pd
@@ -498,10 +500,14 @@ class Query(pydantic.BaseModel):
             )
         return query
 
-    class Config:
+    # This tells pydantic to allow custom types (needed for the `vector` query since
-        # This tells pydantic to allow custom types (needed for the `vector` query since
+    # pa.Array wouln't be allowed otherwise)
-        # pa.Array wouln't be allowed otherwise)
+    if PYDANTIC_VERSION.major < 2:  # Pydantic 1.x compat
-        arbitrary_types_allowed = True
+
+        class Config:
+            arbitrary_types_allowed = True
+    else:
+        model_config = {"arbitrary_types_allowed": True}
 
 
 class LanceQueryBuilder(ABC):
@@ -1586,6 +1592,8 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
         self._refine_factor = None
         self._distance_type = None
         self._phrase_query = None
+        self._lower_bound = None
+        self._upper_bound = None
 
     def _validate_query(self, query, vector=None, text=None):
         if query is not None and (vector is not None or text is not None):
@@ -1665,6 +1673,10 @@ class LanceHybridQueryBuilder(LanceQueryBuilder):
             self._vector_query.ef(self._ef)
         if self._bypass_vector_index:
             self._vector_query.bypass_vector_index()
+        if self._lower_bound or self._upper_bound:
+            self._vector_query.distance_range(
+                lower_bound=self._lower_bound, upper_bound=self._upper_bound
+            )
 
         if self._reranker is None:
             self._reranker = RRFReranker()

python/python/tests/test_hybrid_query.py

@@ -4,13 +4,32 @@
 import lancedb
 
 from lancedb.query import LanceHybridQueryBuilder
+from lancedb.rerankers.rrf import RRFReranker
 import pyarrow as pa
 import pyarrow.compute as pc
 import pytest
 import pytest_asyncio
 
 from lancedb.index import FTS
-from lancedb.table import AsyncTable
+from lancedb.table import AsyncTable, Table
+
+
+@pytest.fixture
+def sync_table(tmpdir_factory) -> Table:
+    tmp_path = str(tmpdir_factory.mktemp("data"))
+    db = lancedb.connect(tmp_path)
+    data = pa.table(
+        {
+            "text": pa.array(["a", "b", "cat", "dog"]),
+            "vector": pa.array(
+                [[0.1, 0.1], [2, 2], [-0.1, -0.1], [0.5, -0.5]],
+                type=pa.list_(pa.float32(), list_size=2),
+            ),
+        }
+    )
+    table = db.create_table("test", data)
+    table.create_fts_index("text", with_position=False, use_tantivy=False)
+    return table
 
 
 @pytest_asyncio.fixture
@@ -102,6 +121,42 @@ async def test_async_hybrid_query_default_limit(table: AsyncTable):
     assert texts.count("a") == 1
 
 
+def test_hybrid_query_distance_range(sync_table: Table):
+    reranker = RRFReranker(return_score="all")
+    result = (
+        sync_table.search(query_type="hybrid")
+        .vector([0.0, 0.4])
+        .text("cat and dog")
+        .distance_range(lower_bound=0.2, upper_bound=0.5)
+        .rerank(reranker)
+        .limit(2)
+        .to_arrow()
+    )
+    assert len(result) == 2
+    print(result)
+    for dist in result["_distance"]:
+        if dist.is_valid:
+            assert 0.2 <= dist.as_py() <= 0.5
+
+
+@pytest.mark.asyncio
+async def test_hybrid_query_distance_range_async(table: AsyncTable):
+    reranker = RRFReranker(return_score="all")
+    result = await (
+        table.query()
+        .nearest_to([0.0, 0.4])
+        .nearest_to_text("cat and dog")
+        .distance_range(lower_bound=0.2, upper_bound=0.5)
+        .rerank(reranker)
+        .limit(2)
+        .to_arrow()
+    )
+    assert len(result) == 2
+    for dist in result["_distance"]:
+        if dist.is_valid:
+            assert 0.2 <= dist.as_py() <= 0.5
+
+
 @pytest.mark.asyncio
 async def test_explain_plan(table: AsyncTable):
     plan = await (

python/src/query.rs

@@ -652,6 +652,11 @@ impl HybridQuery {
         self.inner_vec.bypass_vector_index();
     }
 
+    #[pyo3(signature = (lower_bound=None, upper_bound=None))]
+    pub fn distance_range(&mut self, lower_bound: Option<f32>, upper_bound: Option<f32>) {
+        self.inner_vec.distance_range(lower_bound, upper_bound);
+    }
+
     pub fn to_vector_query(&mut self) -> PyResult<VectorQuery> {
         Ok(VectorQuery {
             inner: self.inner_vec.inner.clone(),

rust/ffi/node/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb-node"
-version = "0.19.0-beta.9"
+version = "0.19.0-beta.10"
 description = "Serverless, low-latency vector database for AI applications"
 license.workspace = true
 edition.workspace = true

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.19.0-beta.9"
+version = "0.19.0-beta.10"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true

rust/lancedb/src/remote/table.rs

@@ -224,7 +224,8 @@ impl<S: HttpSend> RemoteTable<S> {
         }
 
         // Server requires k.
-        let limit = params.limit.unwrap_or(usize::MAX);
+        // use isize::MAX as usize to avoid overflow: https://github.com/lancedb/lancedb/issues/2211
+        let limit = params.limit.unwrap_or(isize::MAX as usize);
         body["k"] = serde_json::Value::Number(serde_json::Number::from(limit));
 
         if let Some(filter) = &params.filter {
@@ -1616,7 +1617,7 @@ mod tests {
             let body = request.body().unwrap().as_bytes().unwrap();
             let body: serde_json::Value = serde_json::from_slice(body).unwrap();
             let expected_body = serde_json::json!({
-                "k": usize::MAX,
+                "k": isize::MAX as usize,
                 "prefilter": true,
                 "vector": [], // Empty vector means no vector query.
                 "version": null,