refactor(python): remove legacy tantivy FTS support (#3282)

This follows the Rust-side Tantivy removal by deleting the remaining Python Tantivy runtime, tests, and packaging references. It also turns the legacy Python-only Tantivy parameters into explicit errors and stops reading legacy `_indices/fts` directories so Python FTS is fully native-only.
2026-06-03 20:30:42 +00:00 · 2026-04-20 09:28:45 +08:00
parent ba6c44abc9
commit c54888a83a
16 changed files with 212 additions and 636 deletions
--- a/python/python/tests/docs/test_search.py
+++ b/python/python/tests/docs/test_search.py
@@ -180,7 +180,7 @@ def test_fts_fuzzy_query():
        ),
        mode="overwrite",
    )
-    table.create_fts_index("text", use_tantivy=False, replace=True)
+    table.create_fts_index("text", replace=True)

    results = table.search(MatchQuery("foo", "text", fuzziness=1)).to_pandas()
    assert len(results) == 4
@@ -230,7 +230,7 @@ def test_fts_boost_query():
        ),
        mode="overwrite",
    )
-    table.create_fts_index("desc", use_tantivy=False, replace=True)
+    table.create_fts_index("desc", replace=True)

    results = table.search(
        BoostQuery(
@@ -265,7 +265,7 @@ def test_fts_boolean_query(tmp_path):
        ],
        mode="overwrite",
    )
-    table.create_fts_index("text", use_tantivy=False, replace=True)
+    table.create_fts_index("text", replace=True)

    # SHOULD
    results = table.search(
@@ -319,9 +319,7 @@ def test_fts_native():
        ],
    )

-    # passing `use_tantivy=False` to use lance FTS index
-    # `use_tantivy=True` by default
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")
    table.search("puppy").limit(10).select(["text"]).to_list()
    # [{'text': 'Frodo was a happy puppy', '_score': 0.6931471824645996}]
    # ...
@@ -332,7 +330,6 @@ def test_fts_native():
    # --8<-- [start:fts_config_folding]
    table.create_fts_index(
        "text",
-        use_tantivy=False,
        language="French",
        stem=True,
        ascii_folding=True,
@@ -346,7 +343,7 @@ def test_fts_native():
    table.search("puppy").limit(10).where("text='foo'", prefilter=False).to_list()
    # --8<-- [end:fts_postfiltering]
    # --8<-- [start:fts_with_position]
-    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
+    table.create_fts_index("text", with_position=True, replace=True)
    # --8<-- [end:fts_with_position]
    # --8<-- [start:fts_incremental_index]
    table.add([{"vector": [3.1, 4.1], "text": "Frodo was a happy puppy"}])
--- a/python/python/tests/test_db.py
+++ b/python/python/tests/test_db.py
@@ -15,8 +15,7 @@ import pytest
 from lancedb.pydantic import LanceModel, Vector


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_basic(tmp_path, use_tantivy):
+def test_basic(tmp_path):
    db = lancedb.connect(tmp_path)

    assert db.uri == str(tmp_path)
@@ -49,7 +48,7 @@ def test_basic(tmp_path, use_tantivy):
    assert len(rs) == 1
    assert rs["item"].iloc[0] == "foo"

-    table.create_fts_index("item", use_tantivy=use_tantivy)
+    table.create_fts_index("item")
    rs = table.search("bar", query_type="fts").to_pandas()
    assert len(rs) == 1
    assert rs["item"].iloc[0] == "bar"
--- a/python/python/tests/test_fts.py
+++ b/python/python/tests/test_fts.py
@@ -36,9 +36,6 @@ import pytest
 import pytest_asyncio
 from utils import exception_output

-pytest.importorskip("lancedb.fts")
-tantivy = pytest.importorskip("tantivy")
-

@pytest.fixture
 def table(tmp_path) -> ldb.table.LanceTable:
@@ -144,58 +141,53 @@ async def async_table(tmp_path) -> ldb.table.AsyncTable:
    return table


-def test_create_index(tmp_path):
-    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    assert isinstance(index, tantivy.Index)
-    assert os.path.exists(str(tmp_path / "index"))
+@pytest.mark.parametrize(
+    ("kwargs", "match"),
+    [
+        (
+            {"use_tantivy": True},
+            "Tantivy-based FTS has been removed",
+        ),
+        (
+            {"ordering_field_names": ["count"]},
+            "ordering_field_names was only supported",
+        ),
+        (
+            {"writer_heap_size": 128},
+            "writer_heap_size was only supported",
+        ),
+    ],
+)
+def test_reject_removed_tantivy_parameters(table, kwargs, match):
+    with pytest.raises(ValueError, match=match):
+        table.create_fts_index("text", **kwargs)


-def test_create_index_with_stemming(tmp_path, table):
-    index = ldb.fts.create_index(
-        str(tmp_path / "index"), ["text"], tokenizer_name="en_stem"
-    )
-    assert isinstance(index, tantivy.Index)
-    assert os.path.exists(str(tmp_path / "index"))
+def test_reject_legacy_tantivy_index(table):
+    path, _, _ = table._get_fts_index_path()
+    os.makedirs(path, exist_ok=True)

-    # Check stemming by running tokenizer on non empty table
-    table.create_fts_index("text", tokenizer_name="en_stem", use_tantivy=True)
+    with pytest.raises(ValueError, match="Legacy Tantivy FTS index detected"):
+        table.search("puppy").limit(5).to_list()
+
+    with pytest.raises(ValueError, match="Legacy Tantivy FTS index detected"):
+        table.create_fts_index("text")


-@pytest.mark.parametrize("use_tantivy", [True, False])
@pytest.mark.parametrize("with_position", [True, False])
-def test_create_inverted_index(table, use_tantivy, with_position):
-    if use_tantivy and not with_position:
-        pytest.skip("we don't support building a tantivy index without position")
+def test_create_inverted_index(table, with_position):
    table.create_fts_index(
        "text",
-        use_tantivy=use_tantivy,
        with_position=with_position,
        name="custom_fts_index",
    )
-    if not use_tantivy:
-        indices = table.list_indices()
-        fts_indices = [i for i in indices if i.index_type == "FTS"]
-        assert any(i.name == "custom_fts_index" for i in fts_indices)
+    indices = table.list_indices()
+    fts_indices = [i for i in indices if i.index_type == "FTS"]
+    assert any(i.name == "custom_fts_index" for i in fts_indices)


-def test_populate_index(tmp_path, table):
-    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    assert ldb.fts.populate_index(index, table, ["text"]) == len(table)
-
-
-def test_search_index(tmp_path, table):
-    index = ldb.fts.create_index(str(tmp_path / "index"), ["text"])
-    ldb.fts.populate_index(index, table, ["text"])
-    index.reload()
-    results = ldb.fts.search_index(index, query="puppy", limit=5)
-    assert len(results) == 2
-    assert len(results[0]) == 5  # row_ids
-    assert len(results[1]) == 5  # _score
-
-
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_search_fts(table, use_tantivy):
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+def test_search_fts(table):
+    table.create_fts_index("text")
    results = table.search("puppy").select(["id", "text"]).limit(5).to_list()
    assert len(results) == 5
    assert len(results[0]) == 3  # id, text, _score
@@ -204,53 +196,52 @@ def test_search_fts(table, use_tantivy):
    results = table.search("puppy").select(["id", "text"]).to_list()
    assert len(results) == 10

-    if not use_tantivy:
-        # Test with a query
-        results = (
-            table.search(MatchQuery("puppy", "text"))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
+    # Test with a query
+    results = (
+        table.search(MatchQuery("puppy", "text"))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5

-        # Test boost query
-        results = (
-            table.search(
-                BoostQuery(
-                    MatchQuery("puppy", "text"),
-                    MatchQuery("runs", "text"),
-                )
+    # Test boost query
+    results = (
+        table.search(
+            BoostQuery(
+                MatchQuery("puppy", "text"),
+                MatchQuery("runs", "text"),
            )
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
        )
-        assert len(results) == 5
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5

-        # Test multi match query
-        table.create_fts_index("text2", use_tantivy=use_tantivy)
-        results = (
-            table.search(MultiMatchQuery("puppy", ["text", "text2"]))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-        assert len(results[0]) == 3  # id, text, _score
+    # Test multi match query
+    table.create_fts_index("text2")
+    results = (
+        table.search(MultiMatchQuery("puppy", ["text", "text2"]))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score

-        # Test boolean query
-        results = (
-            table.search(MatchQuery("puppy", "text") & MatchQuery("runs", "text"))
-            .select(["id", "text"])
-            .limit(5)
-            .to_list()
-        )
-        assert len(results) == 5
-        assert len(results[0]) == 3  # id, text, _score
-        for r in results:
-            assert "puppy" in r["text"]
-            assert "runs" in r["text"]
+    # Test boolean query
+    results = (
+        table.search(MatchQuery("puppy", "text") & MatchQuery("runs", "text"))
+        .select(["id", "text"])
+        .limit(5)
+        .to_list()
+    )
+    assert len(results) == 5
+    assert len(results[0]) == 3  # id, text, _score
+    for r in results:
+        assert "puppy" in r["text"]
+        assert "runs" in r["text"]


@pytest.mark.asyncio
@@ -318,13 +309,13 @@ async def test_fts_select_async(async_table):


 def test_search_fts_phrase_query(table):
-    table.create_fts_index("text", use_tantivy=False, with_position=False)
+    table.create_fts_index("text", with_position=False)
    try:
        phrase_results = table.search('"puppy runs"').limit(100).to_list()
        assert False
    except Exception:
        pass
-    table.create_fts_index("text", use_tantivy=False, with_position=True, replace=True)
+    table.create_fts_index("text", with_position=True, replace=True)
    results = table.search("puppy").limit(100).to_list()

    # Test with quotation marks
@@ -375,8 +366,8 @@ async def test_search_fts_phrase_query_async(async_table):


 def test_search_fts_specify_column(table):
-    table.create_fts_index("text", use_tantivy=False)
-    table.create_fts_index("text2", use_tantivy=False)
+    table.create_fts_index("text")
+    table.create_fts_index("text2")

    results = table.search("puppy", fts_columns="text").limit(5).to_list()
    assert len(results) == 5
@@ -470,42 +461,8 @@ async def test_search_fts_specify_column_async(async_table):
        pass


-def test_search_ordering_field_index_table(tmp_path, table):
-    table.create_fts_index("text", ordering_field_names=["count"], use_tantivy=True)
-    rows = (
-        table.search("puppy", ordering_field_name="count")
-        .limit(20)
-        .select(["text", "count"])
-        .to_list()
-    )
-    for r in rows:
-        assert "puppy" in r["text"]
-    assert sorted(rows, key=lambda x: x["count"], reverse=True) == rows
-
-
-def test_search_ordering_field_index(tmp_path, table):
-    index = ldb.fts.create_index(
-        str(tmp_path / "index"), ["text"], ordering_fields=["count"]
-    )
-
-    ldb.fts.populate_index(index, table, ["text"], ordering_fields=["count"])
-    index.reload()
-    results = ldb.fts.search_index(
-        index, query="puppy", limit=5, ordering_field="count"
-    )
-    assert len(results) == 2
-    assert len(results[0]) == 5  # row_ids
-    assert len(results[1]) == 5  # _distance
-    rows = table.to_lance().take(results[0]).to_pylist()
-
-    for r in rows:
-        assert "puppy" in r["text"]
-    assert sorted(rows, key=lambda x: x["count"], reverse=True) == rows
-
-
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_create_index_from_table(tmp_path, table, use_tantivy):
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+def test_create_index_from_table(tmp_path, table):
+    table.create_fts_index("text")
    df = table.search("puppy").limit(5).select(["text"]).to_pandas()
    assert len(df) <= 5
    assert "text" in df.columns
@@ -525,36 +482,24 @@ def test_create_index_from_table(tmp_path, table, use_tantivy):
    )

    with pytest.raises(Exception, match="already exists"):
-        table.create_fts_index("text", use_tantivy=use_tantivy)
+        table.create_fts_index("text")

-    table.create_fts_index("text", replace=True, use_tantivy=use_tantivy)
+    table.create_fts_index("text", replace=True)
    assert len(table.search("gorilla").limit(1).to_pandas()) == 1


 def test_create_index_multiple_columns(tmp_path, table):
-    table.create_fts_index(["text", "text2"], use_tantivy=True)
-    df = table.search("puppy").limit(5).to_pandas()
-    assert len(df) == 5
-    assert "text" in df.columns
-    assert "text2" in df.columns
-
-
-def test_empty_rs(tmp_path, table, mocker):
-    table.create_fts_index(["text", "text2"], use_tantivy=True)
-    mocker.patch("lancedb.fts.search_index", return_value=([], []))
-    df = table.search("puppy").limit(5).to_pandas()
-    assert len(df) == 0
+    with pytest.raises(ValueError, match="Native FTS indexes can only be created"):
+        table.create_fts_index(["text", "text2"])


 def test_nested_schema(tmp_path, table):
-    table.create_fts_index("nested.text", use_tantivy=True)
-    rs = table.search("puppy").limit(5).to_list()
-    assert len(rs) == 5
+    with pytest.raises(ValueError, match="top-level fields"):
+        table.create_fts_index("nested.text")


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_search_index_with_filter(table, use_tantivy):
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+def test_search_index_with_filter(table):
+    table.create_fts_index("text")
    orig_import = __import__

    def import_mock(name, *args):
@@ -584,8 +529,7 @@ def test_search_index_with_filter(table, use_tantivy):
        assert r["_rowid"] is not None


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_null_input(table, use_tantivy):
+def test_null_input(table):
    table.add(
        [
            {
@@ -598,14 +542,13 @@ def test_null_input(table, use_tantivy):
            }
        ]
    )
-    table.create_fts_index("text", use_tantivy=use_tantivy)
+    table.create_fts_index("text")


 def test_syntax(table):
    # https://github.com/lancedb/lancedb/issues/769
-    table.create_fts_index("text", use_tantivy=True)
-    with pytest.raises(ValueError, match="Syntax Error"):
-        table.search("they could have been dogs OR").limit(10).to_list()
+    table.create_fts_index("text")
+    table.search("they could have been dogs OR").limit(10).to_list()

    # these should work

@@ -616,6 +559,7 @@ def test_syntax(table):
    ).to_list()

    # phrase queries
+    table.create_fts_index("text", with_position=True, replace=True)
    table.search("they could have been dogs OR cats").phrase_query().limit(10).to_list()
    table.search('"they could have been dogs OR cats"').limit(10).to_list()
    table.search('''"the cats OR dogs were not really 'pets' at all"''').limit(
@@ -639,7 +583,7 @@ def test_language(mem_db: DBConnection):
    table = mem_db.create_table("test", data=data)

    with pytest.raises(ValueError) as e:
-        table.create_fts_index("text", use_tantivy=False, language="klingon")
+        table.create_fts_index("text", language="klingon")

    assert exception_output(e) == (
        "ValueError: LanceDB does not support the requested language: 'klingon'\n"
@@ -650,7 +594,6 @@ def test_language(mem_db: DBConnection):

    table.create_fts_index(
        "text",
-        use_tantivy=False,
        language="French",
        stem=True,
        ascii_folding=True,
@@ -690,7 +633,7 @@ def test_fts_on_list(mem_db: DBConnection):
        }
    )
    table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", use_tantivy=False, with_position=True)
+    table.create_fts_index("text", with_position=True)

    res = table.search("lance").limit(5).to_list()
    assert len(res) == 3
@@ -702,7 +645,7 @@ def test_fts_on_list(mem_db: DBConnection):
 def test_fts_ngram(mem_db: DBConnection):
    data = pa.table({"text": ["hello world", "lance database", "lance is cool"]})
    table = mem_db.create_table("test", data=data)
-    table.create_fts_index("text", use_tantivy=False, base_tokenizer="ngram")
+    table.create_fts_index("text", base_tokenizer="ngram")

    results = table.search("lan", query_type="fts").limit(10).to_list()
    assert len(results) == 2
@@ -721,7 +664,6 @@ def test_fts_ngram(mem_db: DBConnection):
    # test setting min_ngram_length and prefix_only
    table.create_fts_index(
        "text",
-        use_tantivy=False,
        base_tokenizer="ngram",
        replace=True,
        ngram_min_length=2,
@@ -886,7 +828,7 @@ def test_fts_query_to_json():


 def test_fts_fast_search(table):
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")

    # Insert some unindexed data
    table.add(
--- a/python/python/tests/test_hybrid_query.py
+++ b/python/python/tests/test_hybrid_query.py
@@ -28,7 +28,7 @@ def sync_table(tmpdir_factory) -> Table:
        }
    )
    table = db.create_table("test", data)
-    table.create_fts_index("text", with_position=False, use_tantivy=False)
+    table.create_fts_index("text", with_position=False)
    return table


@@ -192,7 +192,7 @@ def table_with_id(tmpdir_factory) -> Table:
        }
    )
    table = db.create_table("test_with_id", data)
-    table.create_fts_index("text", with_position=False, use_tantivy=False)
+    table.create_fts_index("text", with_position=False)
    return table


--- a/python/python/tests/test_query.py
+++ b/python/python/tests/test_query.py
@@ -1385,7 +1385,7 @@ def test_query_timeout(tmp_path):
        }
    )
    table = db.create_table("test", data)
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")

    with pytest.raises(Exception, match="Query timeout"):
        table.search().where("text = 'a'").to_list(timeout=timedelta(0))
--- a/python/python/tests/test_rerankers.py
+++ b/python/python/tests/test_rerankers.py
@@ -26,11 +26,8 @@ from lancedb.rerankers import (
 )
 from lancedb.table import LanceTable

-# Tests rely on FTS index
-pytest.importorskip("lancedb.fts")

-
-def get_test_table(tmp_path, use_tantivy):
+def get_test_table(tmp_path):
    db = lancedb.connect(tmp_path)
    # Create a LanceDB table schema with a vector and a text column
    emb = EmbeddingFunctionRegistry.get_instance().get("test").create()
@@ -98,7 +95,7 @@ def get_test_table(tmp_path, use_tantivy):
    )

    # Create a fts index
-    table.create_fts_index("text", use_tantivy=use_tantivy, replace=True)
+    table.create_fts_index("text", replace=True)

    return table, MyTable

@@ -208,8 +205,8 @@ def _run_test_reranker(reranker, table, query, query_vector, schema):
    assert len(result) == 20 and result == result_arrow


-def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
-    table, schema = get_test_table(tmp_path, use_tantivy)
+def _run_test_hybrid_reranker(reranker, tmp_path):
+    table, schema = get_test_table(tmp_path)
    # The default reranker
    result1 = (
        table.search(
@@ -285,8 +282,7 @@ def _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy):
    )


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_linear_combination(tmp_path, use_tantivy):
+def test_linear_combination(tmp_path):
    reranker = LinearCombinationReranker()

    vector_results = pa.Table.from_pydict(
@@ -313,22 +309,20 @@ def test_linear_combination(tmp_path, use_tantivy):
    assert "_score" not in combined_results.column_names
    assert "_relevance_score" in combined_results.column_names

-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
+    _run_test_hybrid_reranker(reranker, tmp_path)


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_rrf_reranker(tmp_path, use_tantivy):
+def test_rrf_reranker(tmp_path):
    reranker = RRFReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
+    _run_test_hybrid_reranker(reranker, tmp_path)


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_mrr_reranker(tmp_path, use_tantivy):
+def test_mrr_reranker(tmp_path):
    reranker = MRRReranker()
-    _run_test_hybrid_reranker(reranker, tmp_path, use_tantivy)
+    _run_test_hybrid_reranker(reranker, tmp_path)

    # Test multi-vector part
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    query = "single player experience"
    rs1 = table.search(query, vector_column_name="vector").limit(10).with_row_id(True)
    rs2 = (
@@ -363,7 +357,7 @@ def test_rrf_reranker_distance():
    table = db.create_table("test", data)

    table.create_index(num_partitions=1, num_sub_vectors=2)
-    table.create_fts_index("text", use_tantivy=False)
+    table.create_fts_index("text")

    reranker = RRFReranker(return_score="all")

@@ -422,35 +416,31 @@ def test_rrf_reranker_distance():
@pytest.mark.skipif(
    os.environ.get("COHERE_API_KEY") is None, reason="COHERE_API_KEY not set"
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_cohere_reranker(tmp_path, use_tantivy):
+def test_cohere_reranker(tmp_path):
    pytest.importorskip("cohere")
    reranker = CohereReranker()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    _run_test_reranker(reranker, table, "single player experience", None, schema)


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_cross_encoder_reranker(tmp_path, use_tantivy):
+def test_cross_encoder_reranker(tmp_path):
    pytest.importorskip("sentence_transformers")
    reranker = CrossEncoderReranker()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    _run_test_reranker(reranker, table, "single player experience", None, schema)


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_colbert_reranker(tmp_path, use_tantivy):
+def test_colbert_reranker(tmp_path):
    pytest.importorskip("rerankers")
    reranker = ColbertReranker()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    _run_test_reranker(reranker, table, "single player experience", None, schema)


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_answerdotai_reranker(tmp_path, use_tantivy):
+def test_answerdotai_reranker(tmp_path):
    pytest.importorskip("rerankers")
    reranker = AnswerdotaiRerankers()
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    _run_test_reranker(reranker, table, "single player experience", None, schema)


@@ -459,10 +449,9 @@ def test_answerdotai_reranker(tmp_path, use_tantivy):
    or os.environ.get("OPENAI_BASE_URL") is not None,
    reason="OPENAI_API_KEY not set",
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_openai_reranker(tmp_path, use_tantivy):
+def test_openai_reranker(tmp_path):
    pytest.importorskip("openai")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    reranker = OpenaiReranker()
    _run_test_reranker(reranker, table, "single player experience", None, schema)

@@ -470,10 +459,9 @@ def test_openai_reranker(tmp_path, use_tantivy):
@pytest.mark.skipif(
    os.environ.get("JINA_API_KEY") is None, reason="JINA_API_KEY not set"
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_jina_reranker(tmp_path, use_tantivy):
+def test_jina_reranker(tmp_path):
    pytest.importorskip("jina")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    reranker = JinaReranker()
    _run_test_reranker(reranker, table, "single player experience", None, schema)

@@ -481,11 +469,10 @@ def test_jina_reranker(tmp_path, use_tantivy):
@pytest.mark.skipif(
    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
 )
-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_voyageai_reranker(tmp_path, use_tantivy):
+def test_voyageai_reranker(tmp_path):
    pytest.importorskip("voyageai")
    reranker = VoyageAIReranker(model_name="rerank-2.5")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    _run_test_reranker(reranker, table, "single player experience", None, schema)


@@ -504,7 +491,7 @@ def test_empty_result_reranker():

    # Create empty table with schema
    empty_table = db.create_table("empty_table", schema=schema, mode="overwrite")
-    empty_table.create_fts_index("text", use_tantivy=False, replace=True)
+    empty_table.create_fts_index("text", replace=True)
    for reranker in [
        CrossEncoderReranker(),
        # ColbertReranker(),
@@ -603,11 +590,10 @@ def test_empty_hybrid_result_reranker():
    assert "_rowid" in result.column_names


-@pytest.mark.parametrize("use_tantivy", [True, False])
-def test_cross_encoder_reranker_return_all(tmp_path, use_tantivy):
+def test_cross_encoder_reranker_return_all(tmp_path):
    pytest.importorskip("sentence_transformers")
    reranker = CrossEncoderReranker(return_score="all")
-    table, schema = get_test_table(tmp_path, use_tantivy)
+    table, schema = get_test_table(tmp_path)
    query = "single player experience"
    result = (
        table.search(query, query_type="hybrid", vector_column_name="vector")
--- a/python/python/tests/test_s3.py
+++ b/python/python/tests/test_s3.py
@@ -242,8 +242,8 @@ def test_s3_dynamodb_sync(s3_bucket: str, commit_table: str, monkeypatch):

    # FTS indices should error since they are not supported yet.
    with pytest.raises(
-        NotImplementedError,
-        match="Full-text search is only supported on the local filesystem",
+        ValueError,
+        match="Tantivy-based FTS has been removed",
    ):
        table.create_fts_index("x", use_tantivy=True)

--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -1948,7 +1948,6 @@ def setup_hybrid_search_table(db: DBConnection, embedding_func):

 def test_hybrid_search(tmp_db: DBConnection):
    # This test uses an FTS index
-    pytest.importorskip("lancedb.fts")
    pytest.importorskip("lance")

    table, MyTable, emb = setup_hybrid_search_table(tmp_db, "test")
@@ -2019,7 +2018,6 @@ def test_hybrid_search(tmp_db: DBConnection):

 def test_hybrid_search_metric_type(tmp_db: DBConnection):
    # This test uses an FTS index
-    pytest.importorskip("lancedb.fts")
    pytest.importorskip("lance")

    # Need to use nonnorm as the embedding function so l2 and dot results