add ci workflows (#1)

Reviewed-on: #1

tests/test_data_processing.py

@@ -6,62 +6,64 @@ from src.embeddingbuddy.models.schemas import Document
 
 
 class TestNDJSONParser:
-    
     def test_parse_text_basic(self):
-        text_content = '{"id": "test1", "text": "Hello world", "embedding": [0.1, 0.2, 0.3]}'
+        text_content = (
+            '{"id": "test1", "text": "Hello world", "embedding": [0.1, 0.2, 0.3]}'
+        )
         documents = NDJSONParser.parse_text(text_content)
-        
+
         assert len(documents) == 1
         assert documents[0].id == "test1"
         assert documents[0].text == "Hello world"
         assert documents[0].embedding == [0.1, 0.2, 0.3]
-    
+
     def test_parse_text_with_metadata(self):
         text_content = '{"id": "test1", "text": "Hello", "embedding": [0.1, 0.2], "category": "greeting", "tags": ["test"]}'
         documents = NDJSONParser.parse_text(text_content)
-        
+
         assert documents[0].category == "greeting"
         assert documents[0].tags == ["test"]
-    
+
     def test_parse_text_missing_id(self):
         text_content = '{"text": "Hello", "embedding": [0.1, 0.2]}'
         documents = NDJSONParser.parse_text(text_content)
-        
+
         assert len(documents) == 1
         assert documents[0].id is not None  # Should be auto-generated
 
 
 class TestDataProcessor:
-    
     def test_extract_embeddings(self):
         documents = [
             Document(id="1", text="test1", embedding=[0.1, 0.2]),
-            Document(id="2", text="test2", embedding=[0.3, 0.4])
+            Document(id="2", text="test2", embedding=[0.3, 0.4]),
         ]
-        
+
         processor = DataProcessor()
         embeddings = processor._extract_embeddings(documents)
-        
+
         assert embeddings.shape == (2, 2)
         assert np.allclose(embeddings[0], [0.1, 0.2])
         assert np.allclose(embeddings[1], [0.3, 0.4])
-    
+
     def test_combine_data(self):
         from src.embeddingbuddy.models.schemas import ProcessedData
-        
+
         doc_data = ProcessedData(
             documents=[Document(id="1", text="doc", embedding=[0.1, 0.2])],
-            embeddings=np.array([[0.1, 0.2]])
+            embeddings=np.array([[0.1, 0.2]]),
         )
-        
+
         prompt_data = ProcessedData(
             documents=[Document(id="p1", text="prompt", embedding=[0.3, 0.4])],
-            embeddings=np.array([[0.3, 0.4]])
+            embeddings=np.array([[0.3, 0.4]]),
         )
-        
+
         processor = DataProcessor()
-        all_embeddings, documents, prompts = processor.combine_data(doc_data, prompt_data)
-        
+        all_embeddings, documents, prompts = processor.combine_data(
+            doc_data, prompt_data
+        )
+
         assert all_embeddings.shape == (2, 2)
         assert len(documents) == 1
         assert len(prompts) == 1
@@ -70,4 +72,4 @@ class TestDataProcessor:
 
 
 if __name__ == "__main__":
-    pytest.main([__file__])
+    pytest.main([__file__])

tests/test_reducers.py

@@ -1,89 +1,90 @@
 import pytest
 import numpy as np
-from src.embeddingbuddy.models.reducers import ReducerFactory, PCAReducer, TSNEReducer, UMAPReducer
+from src.embeddingbuddy.models.reducers import (
+    ReducerFactory,
+    PCAReducer,
+    TSNEReducer,
+    UMAPReducer,
+)
 
 
 class TestReducerFactory:
-    
     def test_create_pca_reducer(self):
-        reducer = ReducerFactory.create_reducer('pca', n_components=2)
+        reducer = ReducerFactory.create_reducer("pca", n_components=2)
         assert isinstance(reducer, PCAReducer)
         assert reducer.n_components == 2
-    
+
     def test_create_tsne_reducer(self):
-        reducer = ReducerFactory.create_reducer('tsne', n_components=3)
+        reducer = ReducerFactory.create_reducer("tsne", n_components=3)
         assert isinstance(reducer, TSNEReducer)
         assert reducer.n_components == 3
-    
+
     def test_create_umap_reducer(self):
-        reducer = ReducerFactory.create_reducer('umap', n_components=2)
+        reducer = ReducerFactory.create_reducer("umap", n_components=2)
         assert isinstance(reducer, UMAPReducer)
         assert reducer.n_components == 2
-    
+
     def test_invalid_method(self):
         with pytest.raises(ValueError, match="Unknown reduction method"):
-            ReducerFactory.create_reducer('invalid_method')
-    
+            ReducerFactory.create_reducer("invalid_method")
+
     def test_available_methods(self):
         methods = ReducerFactory.get_available_methods()
-        assert 'pca' in methods
-        assert 'tsne' in methods
-        assert 'umap' in methods
+        assert "pca" in methods
+        assert "tsne" in methods
+        assert "umap" in methods
 
 
 class TestPCAReducer:
-    
     def test_fit_transform(self):
         embeddings = np.random.rand(100, 512)
         reducer = PCAReducer(n_components=2)
-        
+
         result = reducer.fit_transform(embeddings)
-        
+
         assert result.reduced_embeddings.shape == (100, 2)
         assert result.variance_explained is not None
         assert result.method == "PCA"
         assert result.n_components == 2
-    
+
     def test_method_name(self):
         reducer = PCAReducer()
         assert reducer.get_method_name() == "PCA"
 
 
 class TestTSNEReducer:
-    
     def test_fit_transform_small_dataset(self):
         embeddings = np.random.rand(30, 10)  # Small dataset for faster testing
         reducer = TSNEReducer(n_components=2)
-        
+
         result = reducer.fit_transform(embeddings)
-        
+
         assert result.reduced_embeddings.shape == (30, 2)
         assert result.variance_explained is None  # t-SNE doesn't provide this
         assert result.method == "t-SNE"
         assert result.n_components == 2
-    
+
     def test_method_name(self):
         reducer = TSNEReducer()
         assert reducer.get_method_name() == "t-SNE"
 
 
 class TestUMAPReducer:
-    
     def test_fit_transform(self):
         embeddings = np.random.rand(50, 10)
         reducer = UMAPReducer(n_components=2)
-        
+
         result = reducer.fit_transform(embeddings)
-        
+
         assert result.reduced_embeddings.shape == (50, 2)
         assert result.variance_explained is None  # UMAP doesn't provide this
         assert result.method == "UMAP"
         assert result.n_components == 2
-    
+
     def test_method_name(self):
         reducer = UMAPReducer()
         assert reducer.get_method_name() == "UMAP"
 
 
 if __name__ == "__main__":
-    pytest.main([__file__])
+    pytest.main([__file__])