add unit tests for Doc2VecEmbedding and Doc2VecVectorStore

pkgs/standards/swarmauri_doc2vec_vectorstore/swarmauri_doc2vec_vectorstore/Doc2VecEmbedding.py

@@ -1,10 +1,11 @@
-from typing import List, Any, Optional, Literal
+from typing import List, Any, Literal
 from gensim.models.doc2vec import Doc2Vec, TaggedDocument
 from swarmauri_standard.vectors.Vector import Vector
 from swarmauri_base.embeddings.EmbeddingBase import EmbeddingBase
 from swarmauri_core.ComponentBase import ComponentBase
 
-@ComponentBase.register_type(EmbeddingBase, 'Doc2VecEmbedding')
+
+@ComponentBase.register_type(EmbeddingBase, "Doc2VecEmbedding")
 class Doc2VecEmbedding(EmbeddingBase):
     _model: Doc2Vec
     type: Literal["Doc2VecEmbedding"] = "Doc2VecEmbedding"

pkgs/standards/swarmauri_doc2vec_vectorstore/tests/unit/Doc2VecEmbedding_unit_test.py

@@ -0,0 +1,29 @@
+import pytest
+from swarmauri_doc2vec_vectorstore.Doc2VecEmbedding import Doc2VecEmbedding
+
+
+@pytest.mark.unit
+def test_ubc_resource():
+    assert Doc2VecEmbedding().resource == "Embedding"
+
+
+@pytest.mark.unit
+def test_ubc_type():
+    assert Doc2VecEmbedding().type == "Doc2VecEmbedding"
+
+
+@pytest.mark.unit
+def test_serialization():
+    embedder = Doc2VecEmbedding()
+    assert (
+        embedder.id
+        == Doc2VecEmbedding.model_validate_json(embedder.model_dump_json()).id
+    )
+
+
+@pytest.mark.unit
+def test_fit_transform():
+    embedder = Doc2VecEmbedding()
+    documents = ["test", "cat", "banana"]
+    embedder.fit_transform(documents)
+    assert ["banana", "cat", "test"] == embedder.extract_features()

pkgs/standards/swarmauri_doc2vec_vectorstore/tests/unit/Doc2VecVectorStore_unit_test.py

@@ -0,0 +1,72 @@
+import pytest
+from swarmauri_standard.documents.Document import Document
+from swarmauri_doc2vec_vectorstore.Doc2VecVectorStore import Doc2VecVectorStore
+
+
+@pytest.mark.unit
+def test_ubc_resource():
+    vs = Doc2VecVectorStore()
+    assert vs.resource == "VectorStore"
+    assert vs.embedder.resource == "Embedding"
+
+
+@pytest.mark.unit
+def test_ubc_type():
+    vs = Doc2VecVectorStore()
+    assert vs.type == "Doc2VecVectorStore"
+
+
+@pytest.mark.unit
+def test_serialization():
+    vs = Doc2VecVectorStore()
+    assert vs.id == Doc2VecVectorStore.model_validate_json(vs.model_dump_json()).id
+
+
+@pytest.mark.unit
+def test_top_k():
+    vs = Doc2VecVectorStore()
+    documents = [
+        Document(content="test"),
+        Document(content="test1"),
+        Document(content="test2"),
+        Document(content="test3"),
+    ]
+
+    vs.add_documents(documents)
+    assert len(vs.retrieve(query="test", top_k=2)) == 2
+
+
+@pytest.mark.unit
+def test_adding_more_doc():
+    vs = Doc2VecVectorStore()
+    documents_batch_1 = [
+        Document(content="test"),
+        Document(content="test1"),
+        Document(content="test2"),
+        Document(content="test3"),
+    ]
+    documents_batch_2 = [
+        Document(content="This is a test. Test number 4"),
+        Document(content="This is a test. Test number 5"),
+        Document(content="This is a test. Test number 6"),
+        Document(content="This is a test. Test number 7"),
+    ]
+    doc_count = len(documents_batch_1) + len(documents_batch_2)
+
+    vs.add_documents(documents_batch_1)
+    vs.add_documents(documents_batch_2)
+    assert len(vs.retrieve(query="test", top_k=doc_count)) == doc_count
+
+
+@pytest.mark.unit
+def test_oov():
+    """Test for Out Of Vocabulary (OOV) words"""
+    vs = Doc2VecVectorStore()
+    documents = [
+        Document(content="test"),
+        Document(content="test1"),
+        Document(content="test2"),
+        Document(content="test3"),
+    ]
+    vs.add_documents(documents)
+    assert len(vs.retrieve(query="what is test 4", top_k=2)) == 2