feat: voyageai support (#1799)

Adding VoyageAI embedding and rerank support

python/python/tests/test_embeddings.py

@@ -196,6 +196,7 @@ def test_add_optional_vector(tmp_path):
         "ollama",
         "cohere",
         "instructor",
+        "voyageai",
     ],
 )
 def test_embedding_function_safe_model_dump(embedding_type):

python/python/tests/test_embeddings_slow.py

@@ -481,3 +481,22 @@ def test_ollama_embedding(tmp_path):
         json.dumps(dumped_model)
     except TypeError:
         pytest.fail("Failed to JSON serialize the dumped model")
+
+
+@pytest.mark.slow
+@pytest.mark.skipif(
+    os.environ.get("VOYAGE_API_KEY") is None, reason="VOYAGE_API_KEY not set"
+)
+def test_voyageai_embedding_function():
+    voyageai = get_registry().get("voyageai").create(name="voyage-3", max_retries=0)
+
+    class TextModel(LanceModel):
+        text: str = voyageai.SourceField()
+        vector: Vector(voyageai.ndims()) = voyageai.VectorField()
+
+    df = pd.DataFrame({"text": ["hello world", "goodbye world"]})
+    db = lancedb.connect("~/lancedb")
+    tbl = db.create_table("test", schema=TextModel, mode="overwrite")
+
+    tbl.add(df)
+    assert len(tbl.to_pandas()["vector"][0]) == voyageai.ndims()

python/python/tests/test_rerankers.py

@@ -16,6 +16,7 @@ from lancedb.rerankers import (
     OpenaiReranker,
     JinaReranker,
     AnswerdotaiRerankers,
+    VoyageAIReranker,
 )
 from lancedb.table import LanceTable
 
@@ -344,3 +345,14 @@ def test_jina_reranker(tmp_path, use_tantivy):
     table, schema = get_test_table(tmp_path, use_tantivy)
     reranker = JinaReranker()
     _run_test_reranker(reranker, table, "single player experience", None, schema)
+
+
+@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):
+    pytest.importorskip("voyageai")
+    reranker = VoyageAIReranker(model_name="rerank-2")
+    table, schema = get_test_table(tmp_path, use_tantivy)
+    _run_test_reranker(reranker, table, "single player experience", None, schema)