Bump version: 0.30.0-beta.2 → 0.30.0-beta.3

Fix clippy:

```
error: fields `overwrite` and `rescannable` are never read
Error:    --> /home/runner/work/xxxx/xxxx/src/lancedb/rust/lancedb/src/table/add_data.rs:158:9
    |
156 | pub struct PreprocessingOutput {
    |            ------------------- fields in this struct
157 |     pub plan: Arc<dyn datafusion_physical_plan::ExecutionPlan>,
158 |     pub overwrite: bool,
    |         ^^^^^^^^^
159 |     pub rescannable: bool,
    |         ^^^^^^^^^^^
    |
    = note: `-D dead-code` implied by `-D warnings`
    = help: to override `-D warnings` add `#[allow(dead_code)]`
```

.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.27.0-beta.1"
+current_version = "0.27.0-beta.2"
 parse = """(?x)
     (?P<major>0|[1-9]\\d*)\\.
     (?P<minor>0|[1-9]\\d*)\\.

.github/workflows/rust.yml

@@ -100,7 +100,9 @@ jobs:
           lfs: true
       - uses: Swatinem/rust-cache@v2
       - name: Install dependencies
-        run: sudo apt install -y protobuf-compiler libssl-dev
+        run: |
+          sudo apt update
+          sudo apt install -y protobuf-compiler libssl-dev
       - uses: rui314/setup-mold@v1
       - name: Make Swap
         run: |

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-lance = { "version" = "=3.1.0-beta.2", default-features = false, "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-core = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datagen = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-file = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-io = { "version" = "=3.1.0-beta.2", default-features = false, "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-index = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-linalg = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-namespace-impls = { "version" = "=3.1.0-beta.2", default-features = false, "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=3.0.0-rc.2", default-features = false, "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-table = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-testing = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-datafusion = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-encoding = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
-lance-arrow = { "version" = "=3.1.0-beta.2", "tag" = "v3.1.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }
@@ -40,13 +40,15 @@ arrow-schema = "57.2"
 arrow-select = "57.2"
 arrow-cast = "57.2"
 async-trait = "0"
-datafusion = { version = "51.0", default-features = false }
+datafusion = { version = "52.1", default-features = false }
-datafusion-catalog = "51.0"
+datafusion-catalog = "52.1"
-datafusion-common = { version = "51.0", default-features = false }
+datafusion-common = { version = "52.1", default-features = false }
-datafusion-execution = "51.0"
+datafusion-execution = "52.1"
-datafusion-expr = "51.0"
+datafusion-expr = "52.1"
-datafusion-physical-plan = "51.0"
+datafusion-functions = "52.1"
-datafusion-physical-expr = "51.0"
+datafusion-physical-plan = "52.1"
+datafusion-physical-expr = "52.1"
+datafusion-sql = "52.1"
 env_logger = "0.11"
 half = { "version" = "2.7.1", default-features = false, features = [
     "num-traits",

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>0.27.0-beta.1</version>
+    <version>0.27.0-beta.2</version>
 </dependency>
 ```
 

java/lancedb-core/pom.xml

@@ -8,7 +8,7 @@
     <parent>
       <groupId>com.lancedb</groupId>
       <artifactId>lancedb-parent</artifactId>
-      <version>0.27.0-beta.1</version>
+      <version>0.27.0-beta.2</version>
       <relativePath>../pom.xml</relativePath>
     </parent>
 

java/pom.xml

@@ -6,7 +6,7 @@
 
     <groupId>com.lancedb</groupId>
     <artifactId>lancedb-parent</artifactId>
-    <version>0.27.0-beta.1</version>
+    <version>0.27.0-beta.2</version>
     <packaging>pom</packaging>
     <name>${project.artifactId}</name>
     <description>LanceDB Java SDK Parent POM</description>

nodejs/Cargo.toml

@@ -1,7 +1,7 @@
 [package]
 name = "lancedb-nodejs"
 edition.workspace = true
-version = "0.27.0-beta.1"
+version = "0.27.0-beta.2"
 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": "0.27.0-beta.1",
+	"version": "0.27.0-beta.2",
 	"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": "0.27.0-beta.1",
+	"version": "0.27.0-beta.2",
 	"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": "0.27.0-beta.1",
+	"version": "0.27.0-beta.2",
 	"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": "0.27.0-beta.1",
+	"version": "0.27.0-beta.2",
 	"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": "0.27.0-beta.1",
+	"version": "0.27.0-beta.2",
 	"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": "0.27.0-beta.1",
+  "version": "0.27.0-beta.2",
   "os": [
     "win32"
   ],

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

@@ -1,6 +1,6 @@
 {
 	"name": "@lancedb/lancedb-win32-x64-msvc",
-	"version": "0.27.0-beta.1",
+	"version": "0.27.0-beta.2",
 	"os": ["win32"],
 	"cpu": ["x64"],
 	"main": "lancedb.win32-x64-msvc.node",

nodejs/package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@lancedb/lancedb",
-  "version": "0.27.0-beta.1",
+  "version": "0.27.0-beta.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@lancedb/lancedb",
-      "version": "0.27.0-beta.1",
+      "version": "0.27.0-beta.2",
       "cpu": [
         "x64",
         "arm64"

nodejs/package.json

@@ -11,7 +11,7 @@
     "ann"
   ],
   "private": false,
-  "version": "0.27.0-beta.1",
+  "version": "0.27.0-beta.2",
   "main": "dist/index.js",
   "exports": {
     ".": "./dist/index.js",

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.30.0-beta.2"
+current_version = "0.30.0-beta.3"
 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 = "0.30.0-beta.2"
+version = "0.30.0-beta.3"
 edition.workspace = true
 description = "Python bindings for LanceDB"
 license.workspace = true

python/pyproject.toml

@@ -59,7 +59,7 @@ tests = [
     "polars>=0.19, <=1.3.0",
     "tantivy",
     "pyarrow-stubs",
-    "pylance>=1.0.0b14",
+    "pylance>=1.0.0b14,<3.0.0",
     "requests",
     "datafusion<52",
 ]

python/python/lancedb/query.py

@@ -1462,6 +1462,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
         self._phrase_query = False
         self.ordering_field_name = ordering_field_name
         self._reranker = None
+        self._fast_search = None
         if isinstance(fts_columns, str):
             fts_columns = [fts_columns]
         self._fts_columns = fts_columns
@@ -1483,6 +1484,19 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
         self._phrase_query = phrase_query
         return self
 
+    def fast_search(self) -> LanceFtsQueryBuilder:
+        """
+        Skip a flat search of unindexed data. This will improve
+        search performance but search results will not include unindexed data.
+
+        Returns
+        -------
+        LanceFtsQueryBuilder
+            The LanceFtsQueryBuilder object.
+        """
+        self._fast_search = True
+        return self
+
     def to_query_object(self) -> Query:
         return Query(
             columns=self._columns,
@@ -1494,6 +1508,7 @@ class LanceFtsQueryBuilder(LanceQueryBuilder):
                 query=self._query, columns=self._fts_columns
             ),
             offset=self._offset,
+            fast_search=self._fast_search,
         )
 
     def output_schema(self) -> pa.Schema:

python/python/tests/test_fts.py

@@ -882,3 +882,105 @@ def test_fts_query_to_json():
         '"must_not":[]}}'
     )
     assert json_str == expected
+
+
+def test_fts_fast_search(table):
+    table.create_fts_index("text", use_tantivy=False)
+
+    # Insert some unindexed data
+    table.add(
+        [
+            {
+                "text": "xyz",
+                "vector": [0 for _ in range(128)],
+                "id": 101,
+                "text2": "xyz",
+                "nested": {"text": "xyz"},
+                "count": 10,
+            }
+        ]
+    )
+
+    # Without fast_search, the query object should not have fast_search set
+    builder = table.search("xyz", query_type="fts").limit(10)
+    query = builder.to_query_object()
+    assert query.fast_search is None
+
+    # With fast_search, the query object should have fast_search=True
+    builder = table.search("xyz", query_type="fts").fast_search().limit(10)
+    query = builder.to_query_object()
+    assert query.fast_search is True
+
+    # fast_search should be chainable with other methods
+    builder = (
+        table.search("xyz", query_type="fts").fast_search().select(["text"]).limit(5)
+    )
+    query = builder.to_query_object()
+    assert query.fast_search is True
+    assert query.limit == 5
+    assert query.columns == ["text"]
+
+    # Verify it executes without error and skips unindexed data
+    results = table.search("xyz", query_type="fts").fast_search().limit(5).to_list()
+    assert len(results) == 0
+
+    # Update index and verify it returns results
+    table.optimize()
+    results = table.search("xyz", query_type="fts").fast_search().limit(5).to_list()
+    assert len(results) > 0
+
+
+@pytest.mark.asyncio
+async def test_fts_fast_search_async(async_table):
+    await async_table.create_index("text", config=FTS())
+
+    # Insert some unindexed data
+    await async_table.add(
+        [
+            {
+                "text": "xyz",
+                "vector": [0 for _ in range(128)],
+                "id": 101,
+                "text2": "xyz",
+                "nested": {"text": "xyz"},
+                "count": 10,
+            }
+        ]
+    )
+
+    # Without fast_search, should return results
+    results = await async_table.query().nearest_to_text("xyz").limit(5).to_list()
+    assert len(results) > 0
+
+    # With fast_search, should return no results data unindexed
+    fast_results = (
+        await async_table.query()
+        .nearest_to_text("xyz")
+        .fast_search()
+        .limit(5)
+        .to_list()
+    )
+    assert len(fast_results) == 0
+
+    # Update index and verify it returns results
+    await async_table.optimize()
+
+    fast_results = (
+        await async_table.query()
+        .nearest_to_text("xyz")
+        .fast_search()
+        .limit(5)
+        .to_list()
+    )
+    assert len(fast_results) > 0
+
+    # fast_search should be chainable with other methods
+    results = (
+        await async_table.query()
+        .nearest_to_text("xyz")
+        .fast_search()
+        .select(["text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) > 0

rust/lancedb/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "lancedb"
-version = "0.27.0-beta.1"
+version = "0.27.0-beta.2"
 edition.workspace = true
 description = "LanceDB: A serverless, low-latency vector database for AI applications"
 license.workspace = true
@@ -25,9 +25,9 @@ datafusion-catalog.workspace = true
 datafusion-common.workspace = true
 datafusion-execution.workspace = true
 datafusion-expr.workspace = true
-datafusion-functions = "51.0"
+datafusion-functions.workspace = true
 datafusion-physical-expr.workspace = true
-datafusion-sql = "51.0"
+datafusion-sql.workspace = true
 datafusion-physical-plan.workspace = true
 datafusion.workspace = true
 object_store = { workspace = true }

rust/lancedb/src/table/add_data.rs

@@ -155,7 +155,9 @@ impl AddDataBuilder {
 
 pub struct PreprocessingOutput {
     pub plan: Arc<dyn datafusion_physical_plan::ExecutionPlan>,
+    #[cfg_attr(not(feature = "remote"), allow(dead_code))]
     pub overwrite: bool,
+    #[cfg_attr(not(feature = "remote"), allow(dead_code))]
     pub rescannable: bool,
     pub write_options: WriteOptions,
     pub mode: AddDataMode,