add ci workflows (#1)

Reviewed-on: godber/embedding-buddy#1

src/embeddingbuddy/ui/callbacks/data_processing.py

@@ -1,61 +1,62 @@
-import numpy as np
 from dash import callback, Input, Output, State
 from ...data.processor import DataProcessor
 
 
 class DataProcessingCallbacks:
-    
     def __init__(self):
         self.processor = DataProcessor()
         self._register_callbacks()
-    
+
     def _register_callbacks(self):
-        
         @callback(
-            Output('processed-data', 'data'),
-            Input('upload-data', 'contents'),
-            State('upload-data', 'filename')
+            Output("processed-data", "data"),
+            Input("upload-data", "contents"),
+            State("upload-data", "filename"),
         )
         def process_uploaded_file(contents, filename):
             if contents is None:
                 return None
-            
+
             processed_data = self.processor.process_upload(contents, filename)
-            
+
             if processed_data.error:
-                return {'error': processed_data.error}
-            
+                return {"error": processed_data.error}
+
             return {
-                'documents': [self._document_to_dict(doc) for doc in processed_data.documents],
-                'embeddings': processed_data.embeddings.tolist()
+                "documents": [
+                    self._document_to_dict(doc) for doc in processed_data.documents
+                ],
+                "embeddings": processed_data.embeddings.tolist(),
             }
-        
+
         @callback(
-            Output('processed-prompts', 'data'),
-            Input('upload-prompts', 'contents'),
-            State('upload-prompts', 'filename')
+            Output("processed-prompts", "data"),
+            Input("upload-prompts", "contents"),
+            State("upload-prompts", "filename"),
         )
         def process_uploaded_prompts(contents, filename):
             if contents is None:
                 return None
-            
+
             processed_data = self.processor.process_upload(contents, filename)
-            
+
             if processed_data.error:
-                return {'error': processed_data.error}
-            
+                return {"error": processed_data.error}
+
             return {
-                'prompts': [self._document_to_dict(doc) for doc in processed_data.documents],
-                'embeddings': processed_data.embeddings.tolist()
+                "prompts": [
+                    self._document_to_dict(doc) for doc in processed_data.documents
+                ],
+                "embeddings": processed_data.embeddings.tolist(),
             }
-    
+
     @staticmethod
     def _document_to_dict(doc):
         return {
-            'id': doc.id,
-            'text': doc.text,
-            'embedding': doc.embedding,
-            'category': doc.category,
-            'subcategory': doc.subcategory,
-            'tags': doc.tags
-        }
+            "id": doc.id,
+            "text": doc.text,
+            "embedding": doc.embedding,
+            "category": doc.category,
+            "subcategory": doc.subcategory,
+            "tags": doc.tags,
+        }

src/embeddingbuddy/ui/callbacks/interactions.py

@@ -4,63 +4,79 @@ import dash_bootstrap_components as dbc
 
 
 class InteractionCallbacks:
-    
     def __init__(self):
         self._register_callbacks()
-    
+
     def _register_callbacks(self):
-        
         @callback(
-            Output('point-details', 'children'),
-            Input('embedding-plot', 'clickData'),
-            [State('processed-data', 'data'),
-             State('processed-prompts', 'data')]
+            Output("point-details", "children"),
+            Input("embedding-plot", "clickData"),
+            [State("processed-data", "data"), State("processed-prompts", "data")],
         )
         def display_click_data(clickData, data, prompts_data):
             if not clickData or not data:
                 return "Click on a point to see details"
-            
-            point_data = clickData['points'][0]
-            trace_name = point_data.get('fullData', {}).get('name', 'Documents')
-            
-            if 'pointIndex' in point_data:
-                point_index = point_data['pointIndex']
-            elif 'pointNumber' in point_data:
-                point_index = point_data['pointNumber']
+
+            point_data = clickData["points"][0]
+            trace_name = point_data.get("fullData", {}).get("name", "Documents")
+
+            if "pointIndex" in point_data:
+                point_index = point_data["pointIndex"]
+            elif "pointNumber" in point_data:
+                point_index = point_data["pointNumber"]
             else:
                 return "Could not identify clicked point"
-            
-            if trace_name.startswith('Prompts') and prompts_data and 'prompts' in prompts_data:
-                item = prompts_data['prompts'][point_index]
-                item_type = 'Prompt'
+
+            if (
+                trace_name.startswith("Prompts")
+                and prompts_data
+                and "prompts" in prompts_data
+            ):
+                item = prompts_data["prompts"][point_index]
+                item_type = "Prompt"
             else:
-                item = data['documents'][point_index]
-                item_type = 'Document'
-            
+                item = data["documents"][point_index]
+                item_type = "Document"
+
             return self._create_detail_card(item, item_type)
-        
+
         @callback(
-            [Output('processed-data', 'data', allow_duplicate=True),
-             Output('processed-prompts', 'data', allow_duplicate=True),
-             Output('point-details', 'children', allow_duplicate=True)],
-            Input('reset-button', 'n_clicks'),
-            prevent_initial_call=True
+            [
+                Output("processed-data", "data", allow_duplicate=True),
+                Output("processed-prompts", "data", allow_duplicate=True),
+                Output("point-details", "children", allow_duplicate=True),
+            ],
+            Input("reset-button", "n_clicks"),
+            prevent_initial_call=True,
         )
         def reset_data(n_clicks):
             if n_clicks is None or n_clicks == 0:
                 return dash.no_update, dash.no_update, dash.no_update
-            
+
             return None, None, "Click on a point to see details"
-    
+
     @staticmethod
     def _create_detail_card(item, item_type):
-        return dbc.Card([
-            dbc.CardBody([
-                html.H5(f"{item_type}: {item['id']}", className="card-title"),
-                html.P(f"Text: {item['text']}", className="card-text"),
-                html.P(f"Category: {item.get('category', 'Unknown')}", className="card-text"),
-                html.P(f"Subcategory: {item.get('subcategory', 'Unknown')}", className="card-text"),
-                html.P(f"Tags: {', '.join(item.get('tags', [])) if item.get('tags') else 'None'}", className="card-text"),
-                html.P(f"Type: {item_type}", className="card-text text-muted")
-            ])
-        ])
+        return dbc.Card(
+            [
+                dbc.CardBody(
+                    [
+                        html.H5(f"{item_type}: {item['id']}", className="card-title"),
+                        html.P(f"Text: {item['text']}", className="card-text"),
+                        html.P(
+                            f"Category: {item.get('category', 'Unknown')}",
+                            className="card-text",
+                        ),
+                        html.P(
+                            f"Subcategory: {item.get('subcategory', 'Unknown')}",
+                            className="card-text",
+                        ),
+                        html.P(
+                            f"Tags: {', '.join(item.get('tags', [])) if item.get('tags') else 'None'}",
+                            className="card-text",
+                        ),
+                        html.P(f"Type: {item_type}", className="card-text text-muted"),
+                    ]
+                )
+            ]
+        )

src/embeddingbuddy/ui/callbacks/visualization.py

@@ -7,81 +7,102 @@ from ...visualization.plots import PlotFactory
 
 
 class VisualizationCallbacks:
-    
     def __init__(self):
         self.plot_factory = PlotFactory()
         self._register_callbacks()
-    
+
     def _register_callbacks(self):
-        
         @callback(
-            Output('embedding-plot', 'figure'),
-            [Input('processed-data', 'data'),
-             Input('processed-prompts', 'data'),
-             Input('method-dropdown', 'value'),
-             Input('color-dropdown', 'value'),
-             Input('dimension-toggle', 'value'),
-             Input('show-prompts-toggle', 'value')]
+            Output("embedding-plot", "figure"),
+            [
+                Input("processed-data", "data"),
+                Input("processed-prompts", "data"),
+                Input("method-dropdown", "value"),
+                Input("color-dropdown", "value"),
+                Input("dimension-toggle", "value"),
+                Input("show-prompts-toggle", "value"),
+            ],
         )
         def update_plot(data, prompts_data, method, color_by, dimensions, show_prompts):
-            if not data or 'error' in data:
+            if not data or "error" in data:
                 return go.Figure().add_annotation(
                     text="Upload a valid NDJSON file to see visualization",
-                    xref="paper", yref="paper",
-                    x=0.5, y=0.5, xanchor='center', yanchor='middle',
-                    showarrow=False, font=dict(size=16)
+                    xref="paper",
+                    yref="paper",
+                    x=0.5,
+                    y=0.5,
+                    xanchor="center",
+                    yanchor="middle",
+                    showarrow=False,
+                    font=dict(size=16),
                 )
-            
+
             try:
-                doc_embeddings = np.array(data['embeddings'])
+                doc_embeddings = np.array(data["embeddings"])
                 all_embeddings = doc_embeddings
-                has_prompts = prompts_data and 'error' not in prompts_data and prompts_data.get('prompts')
-                
+                has_prompts = (
+                    prompts_data
+                    and "error" not in prompts_data
+                    and prompts_data.get("prompts")
+                )
+
                 if has_prompts:
-                    prompt_embeddings = np.array(prompts_data['embeddings'])
+                    prompt_embeddings = np.array(prompts_data["embeddings"])
                     all_embeddings = np.vstack([doc_embeddings, prompt_embeddings])
-                
-                n_components = 3 if dimensions == '3d' else 2
-                
-                reducer = ReducerFactory.create_reducer(method, n_components=n_components)
+
+                n_components = 3 if dimensions == "3d" else 2
+
+                reducer = ReducerFactory.create_reducer(
+                    method, n_components=n_components
+                )
                 reduced_data = reducer.fit_transform(all_embeddings)
-                
-                doc_reduced = reduced_data.reduced_embeddings[:len(doc_embeddings)]
+
+                doc_reduced = reduced_data.reduced_embeddings[: len(doc_embeddings)]
                 prompt_reduced = None
                 if has_prompts:
-                    prompt_reduced = reduced_data.reduced_embeddings[len(doc_embeddings):]
-                
-                documents = [self._dict_to_document(doc) for doc in data['documents']]
+                    prompt_reduced = reduced_data.reduced_embeddings[
+                        len(doc_embeddings) :
+                    ]
+
+                documents = [self._dict_to_document(doc) for doc in data["documents"]]
                 prompts = None
                 if has_prompts:
-                    prompts = [self._dict_to_document(prompt) for prompt in prompts_data['prompts']]
-                
+                    prompts = [
+                        self._dict_to_document(prompt)
+                        for prompt in prompts_data["prompts"]
+                    ]
+
                 plot_data = PlotData(
                     documents=documents,
                     coordinates=doc_reduced,
                     prompts=prompts,
-                    prompt_coordinates=prompt_reduced
+                    prompt_coordinates=prompt_reduced,
                 )
-                
+
                 return self.plot_factory.create_plot(
                     plot_data, dimensions, color_by, reduced_data.method, show_prompts
                 )
-                
+
             except Exception as e:
                 return go.Figure().add_annotation(
                     text=f"Error creating visualization: {str(e)}",
-                    xref="paper", yref="paper",
-                    x=0.5, y=0.5, xanchor='center', yanchor='middle',
-                    showarrow=False, font=dict(size=16)
+                    xref="paper",
+                    yref="paper",
+                    x=0.5,
+                    y=0.5,
+                    xanchor="center",
+                    yanchor="middle",
+                    showarrow=False,
+                    font=dict(size=16),
                 )
-    
+
     @staticmethod
     def _dict_to_document(doc_dict):
         return Document(
-            id=doc_dict['id'],
-            text=doc_dict['text'],
-            embedding=doc_dict['embedding'],
-            category=doc_dict.get('category'),
-            subcategory=doc_dict.get('subcategory'),
-            tags=doc_dict.get('tags', [])
-        )
+            id=doc_dict["id"],
+            text=doc_dict["text"],
+            embedding=doc_dict["embedding"],
+            category=doc_dict.get("category"),
+            subcategory=doc_dict.get("subcategory"),
+            tags=doc_dict.get("tags", []),
+        )

src/embeddingbuddy/ui/components/sidebar.py

@@ -4,79 +4,81 @@ from .upload import UploadComponent
 
 
 class SidebarComponent:
-    
     def __init__(self):
         self.upload_component = UploadComponent()
-    
+
     def create_layout(self):
-        return dbc.Col([
-            html.H5("Upload Data", className="mb-3"),
-            self.upload_component.create_data_upload(),
-            self.upload_component.create_prompts_upload(),
-            self.upload_component.create_reset_button(),
-            
-            html.H5("Visualization Controls", className="mb-3"),
-            self._create_method_dropdown(),
-            self._create_color_dropdown(),
-            self._create_dimension_toggle(),
-            self._create_prompts_toggle(),
-            
-            html.H5("Point Details", className="mb-3"),
-            html.Div(id='point-details', children="Click on a point to see details")
-            
-        ], width=3, style={'padding-right': '20px'})
-    
+        return dbc.Col(
+            [
+                html.H5("Upload Data", className="mb-3"),
+                self.upload_component.create_data_upload(),
+                self.upload_component.create_prompts_upload(),
+                self.upload_component.create_reset_button(),
+                html.H5("Visualization Controls", className="mb-3"),
+                self._create_method_dropdown(),
+                self._create_color_dropdown(),
+                self._create_dimension_toggle(),
+                self._create_prompts_toggle(),
+                html.H5("Point Details", className="mb-3"),
+                html.Div(
+                    id="point-details", children="Click on a point to see details"
+                ),
+            ],
+            width=3,
+            style={"padding-right": "20px"},
+        )
+
     def _create_method_dropdown(self):
         return [
             dbc.Label("Method:"),
             dcc.Dropdown(
-                id='method-dropdown',
+                id="method-dropdown",
                 options=[
-                    {'label': 'PCA', 'value': 'pca'},
-                    {'label': 't-SNE', 'value': 'tsne'},
-                    {'label': 'UMAP', 'value': 'umap'}
+                    {"label": "PCA", "value": "pca"},
+                    {"label": "t-SNE", "value": "tsne"},
+                    {"label": "UMAP", "value": "umap"},
                 ],
-                value='pca',
-                style={'margin-bottom': '15px'}
-            )
+                value="pca",
+                style={"margin-bottom": "15px"},
+            ),
         ]
-    
+
     def _create_color_dropdown(self):
         return [
             dbc.Label("Color by:"),
             dcc.Dropdown(
-                id='color-dropdown',
+                id="color-dropdown",
                 options=[
-                    {'label': 'Category', 'value': 'category'},
-                    {'label': 'Subcategory', 'value': 'subcategory'},
-                    {'label': 'Tags', 'value': 'tags'}
+                    {"label": "Category", "value": "category"},
+                    {"label": "Subcategory", "value": "subcategory"},
+                    {"label": "Tags", "value": "tags"},
                 ],
-                value='category',
-                style={'margin-bottom': '15px'}
-            )
+                value="category",
+                style={"margin-bottom": "15px"},
+            ),
         ]
-    
+
     def _create_dimension_toggle(self):
         return [
             dbc.Label("Dimensions:"),
             dcc.RadioItems(
-                id='dimension-toggle',
+                id="dimension-toggle",
                 options=[
-                    {'label': '2D', 'value': '2d'},
-                    {'label': '3D', 'value': '3d'}
+                    {"label": "2D", "value": "2d"},
+                    {"label": "3D", "value": "3d"},
                 ],
-                value='3d',
-                style={'margin-bottom': '20px'}
-            )
+                value="3d",
+                style={"margin-bottom": "20px"},
+            ),
         ]
-    
+
     def _create_prompts_toggle(self):
         return [
             dbc.Label("Show Prompts:"),
             dcc.Checklist(
-                id='show-prompts-toggle',
-                options=[{'label': 'Show prompts on plot', 'value': 'show'}],
-                value=['show'],
-                style={'margin-bottom': '20px'}
-            )
-        ]
+                id="show-prompts-toggle",
+                options=[{"label": "Show prompts on plot", "value": "show"}],
+                value=["show"],
+                style={"margin-bottom": "20px"},
+            ),
+        ]

src/embeddingbuddy/ui/components/upload.py

@@ -3,58 +3,51 @@ import dash_bootstrap_components as dbc
 
 
 class UploadComponent:
-    
     @staticmethod
     def create_data_upload():
         return dcc.Upload(
-            id='upload-data',
-            children=html.Div([
-                'Drag and Drop or ',
-                html.A('Select Files')
-            ]),
+            id="upload-data",
+            children=html.Div(["Drag and Drop or ", html.A("Select Files")]),
             style={
-                'width': '100%',
-                'height': '60px',
-                'lineHeight': '60px',
-                'borderWidth': '1px',
-                'borderStyle': 'dashed',
-                'borderRadius': '5px',
-                'textAlign': 'center',
-                'margin-bottom': '20px'
+                "width": "100%",
+                "height": "60px",
+                "lineHeight": "60px",
+                "borderWidth": "1px",
+                "borderStyle": "dashed",
+                "borderRadius": "5px",
+                "textAlign": "center",
+                "margin-bottom": "20px",
             },
-            multiple=False
+            multiple=False,
         )
-    
+
     @staticmethod
     def create_prompts_upload():
         return dcc.Upload(
-            id='upload-prompts',
-            children=html.Div([
-                'Drag and Drop Prompts or ',
-                html.A('Select Files')
-            ]),
+            id="upload-prompts",
+            children=html.Div(["Drag and Drop Prompts or ", html.A("Select Files")]),
             style={
-                'width': '100%',
-                'height': '60px',
-                'lineHeight': '60px',
-                'borderWidth': '1px',
-                'borderStyle': 'dashed',
-                'borderRadius': '5px',
-                'textAlign': 'center',
-                'margin-bottom': '20px',
-                'borderColor': '#28a745'
+                "width": "100%",
+                "height": "60px",
+                "lineHeight": "60px",
+                "borderWidth": "1px",
+                "borderStyle": "dashed",
+                "borderRadius": "5px",
+                "textAlign": "center",
+                "margin-bottom": "20px",
+                "borderColor": "#28a745",
             },
-            multiple=False
+            multiple=False,
         )
-    
+
     @staticmethod
     def create_reset_button():
         return dbc.Button(
             "Reset All Data",
-            id='reset-button',
-            color='danger',
+            id="reset-button",
+            color="danger",
             outline=True,
-            size='sm',
-            className='mb-3',
-            style={'width': '100%'}
-        )
+            size="sm",
+            className="mb-3",
+            style={"width": "100%"},
+        )

src/embeddingbuddy/ui/layout.py

@@ -4,41 +4,43 @@ from .components.sidebar import SidebarComponent
 
 
 class AppLayout:
-    
     def __init__(self):
         self.sidebar = SidebarComponent()
-    
+
     def create_layout(self):
-        return dbc.Container([
-            self._create_header(),
-            self._create_main_content(),
-            self._create_stores()
-        ], fluid=True)
-    
+        return dbc.Container(
+            [self._create_header(), self._create_main_content(), self._create_stores()],
+            fluid=True,
+        )
+
     def _create_header(self):
-        return dbc.Row([
-            dbc.Col([
-                html.H1("EmbeddingBuddy", className="text-center mb-4"),
-            ], width=12)
-        ])
-    
+        return dbc.Row(
+            [
+                dbc.Col(
+                    [
+                        html.H1("EmbeddingBuddy", className="text-center mb-4"),
+                    ],
+                    width=12,
+                )
+            ]
+        )
+
     def _create_main_content(self):
-        return dbc.Row([
-            self.sidebar.create_layout(),
-            self._create_visualization_area()
-        ])
-    
+        return dbc.Row(
+            [self.sidebar.create_layout(), self._create_visualization_area()]
+        )
+
     def _create_visualization_area(self):
-        return dbc.Col([
-            dcc.Graph(
-                id='embedding-plot',
-                style={'height': '85vh', 'width': '100%'},
-                config={'responsive': True, 'displayModeBar': True}
-            )
-        ], width=9)
-    
+        return dbc.Col(
+            [
+                dcc.Graph(
+                    id="embedding-plot",
+                    style={"height": "85vh", "width": "100%"},
+                    config={"responsive": True, "displayModeBar": True},
+                )
+            ],
+            width=9,
+        )
+
     def _create_stores(self):
-        return [
-            dcc.Store(id='processed-data'),
-            dcc.Store(id='processed-prompts')
-        ]
+        return [dcc.Store(id="processed-data"), dcc.Store(id="processed-prompts")]