chore: update lance dependency to v4.0.0-beta.2

Cargo.toml

@@ -15,20 +15,20 @@ categories = ["database-implementations"]
 rust-version = "1.91.0"
 
 [workspace.dependencies]
-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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.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" = "=3.0.0-rc.2", "tag" = "v3.0.0-rc.2", "git" = "https://github.com/lance-format/lance.git" }
+lance = { "version" = "=4.0.0-beta.2", default-features = false, "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-core = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datagen = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-file = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-io = { "version" = "=4.0.0-beta.2", default-features = false, "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-index = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-linalg = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-namespace-impls = { "version" = "=4.0.0-beta.2", default-features = false, "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-table = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-testing = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-datafusion = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-encoding = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
+lance-arrow = { "version" = "=4.0.0-beta.2", "tag" = "v4.0.0-beta.2", "git" = "https://github.com/lance-format/lance.git" }
 ahash = "0.8"
 # Note that this one does not include pyarrow
 arrow = { version = "57.2", optional = false }

java/pom.xml

@@ -28,7 +28,7 @@
     <properties>
         <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
         <arrow.version>15.0.0</arrow.version>
-        <lance-core.version>3.1.0-beta.2</lance-core.version>
+        <lance-core.version>4.0.0-beta.2</lance-core.version>
         <spotless.skip>false</spotless.skip>
         <spotless.version>2.30.0</spotless.version>
         <spotless.java.googlejavaformat.version>1.7</spotless.java.googlejavaformat.version>

python/.bumpversion.toml

@@ -1,5 +1,5 @@
 [tool.bumpversion]
-current_version = "0.30.0-beta.3"
+current_version = "0.30.0-beta.2"
 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.3"
+version = "0.30.0-beta.2"
 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,<3.0.0",
+    "pylance>=1.0.0b14",
     "requests",
     "datafusion<52",
 ]

python/python/lancedb/query.py

@@ -1462,7 +1462,6 @@ 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
@@ -1484,19 +1483,6 @@ 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,
@@ -1508,7 +1494,6 @@ 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

@@ -882,105 +882,3 @@ 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