fix colors linting

.claude/settings.local.json

@@ -6,7 +6,6 @@
       "Bash(uv add:*)"
     ],
     "deny": [],
-    "ask": [],
-    "defaultMode": "acceptEdits"
+    "ask": []
   }
 }

.gitea/workflows/release.yml

@@ -26,10 +26,12 @@ jobs:
         run: uv python install 3.11
 
       - name: Install dependencies
-        run: uv sync --extra test
+        run: uv sync
 
       - name: Run full test suite
-        run: uv run pytest tests/ -v --cov=src/embeddingbuddy --cov-report=term-missing
+        run: |
+          uv add pytest-cov
+          uv run pytest tests/ -v --cov=src/embeddingbuddy --cov-report=term-missing
 
   build-and-release:
     runs-on: ubuntu-latest

.gitea/workflows/security.yml

@@ -25,7 +25,12 @@ jobs:
         run: uv python install 3.11
 
       - name: Install dependencies
-        run: uv sync --extra security
+        run: uv sync
+
+      - name: Add security tools
+        run: |
+          uv add bandit[toml]
+          uv add safety
 
       - name: Run bandit security linter
         run: uv run bandit -r src/ -f json -o bandit-report.json
@@ -36,7 +41,7 @@ jobs:
         continue-on-error: true
 
       - name: Upload security reports
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: security-reports
           path: |
@@ -59,12 +64,13 @@ jobs:
 
       - name: Check for dependency vulnerabilities
         run: |
-          uv sync --extra security
+          uv sync
+          uv add pip-audit
           uv run pip-audit --format=json --output=pip-audit-report.json
         continue-on-error: true
 
       - name: Upload dependency audit report
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: dependency-audit
           path: pip-audit-report.json

.gitea/workflows/test.yml

@@ -2,20 +2,16 @@ name: Test Suite
 
 on:
   push:
-    branches: 
-      - "main"
-      - "develop"
+    branches: ["*"]
   pull_request:
-    branches: 
-      - "main"
-  workflow_dispatch:
+    branches: ["main", "master"]
 
 jobs:
   test:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.11"]
+        python-version: ["3.11", "3.12"]
 
     steps:
       - name: Checkout code
@@ -30,13 +26,15 @@ jobs:
         run: uv python install ${{ matrix.python-version }}
 
       - name: Install dependencies
-        run: uv sync --extra test
+        run: uv sync
 
       - name: Run tests with pytest
         run: uv run pytest tests/ -v --tb=short
 
       - name: Run tests with coverage
-        run: uv run pytest tests/ --cov=src/embeddingbuddy --cov-report=term-missing --cov-report=xml
+        run: |
+          uv add pytest-cov
+          uv run pytest tests/ --cov=src/embeddingbuddy --cov-report=term-missing --cov-report=xml
 
       - name: Upload coverage reports
         uses: codecov/codecov-action@v4
@@ -60,7 +58,12 @@ jobs:
         run: uv python install 3.11
 
       - name: Install dependencies
-        run: uv sync --extra lint
+        run: uv sync
+
+      - name: Add linting tools
+        run: |
+          uv add ruff
+          uv add mypy
 
       - name: Run ruff linter
         run: uv run ruff check src/ tests/
@@ -68,9 +71,8 @@ jobs:
       - name: Run ruff formatter check
         run: uv run ruff format --check src/ tests/
 
-      # TODO fix this it throws errors
-      # - name: Run mypy type checker
-      #   run: uv run mypy src/embeddingbuddy/ --ignore-missing-imports
+      - name: Run mypy type checker
+        run: uv run mypy src/embeddingbuddy/ --ignore-missing-imports
 
   build:
     runs-on: ubuntu-latest
@@ -98,7 +100,7 @@ jobs:
           uv run python -c "from src.embeddingbuddy.app import create_app; app = create_app(); print('✅ Package builds and imports successfully')"
 
       - name: Upload build artifacts
-        uses: actions/upload-artifact@v3
+        uses: actions/upload-artifact@v4
         with:
           name: dist-files
           path: dist/

CLAUDE.md

@@ -30,28 +30,9 @@ The app will be available at http://127.0.0.1:8050
 **Run tests:**
 
 ```bash
-uv sync --extra test
 uv run pytest tests/ -v
 ```
 
-**Development tools:**
-
-```bash
-# Install all dev dependencies
-uv sync --extra dev
-
-# Linting and formatting
-uv run ruff check src/ tests/
-uv run ruff format src/ tests/
-
-# Type checking
-uv run mypy src/embeddingbuddy/
-
-# Security scanning
-uv run bandit -r src/
-uv run safety check
-```
-
 **Test with sample data:**
 Use the included `sample_data.ndjson` and `sample_prompts.ndjson` files for testing the application functionality.
 
@@ -61,7 +42,7 @@ Use the included `sample_data.ndjson` and `sample_prompts.ndjson` files for test
 
 The application follows a modular architecture with clear separation of concerns:
 
-```text
+```
 src/embeddingbuddy/
 ├── app.py              # Main application entry point and factory
 ├── main.py             # Application runner
@@ -91,32 +72,27 @@ src/embeddingbuddy/
 ### Key Components
 
 **Data Layer:**
-
 - `data/parser.py` - NDJSON parsing with error handling
 - `data/processor.py` - Data transformation and combination logic
 - `models/schemas.py` - Dataclasses for type safety and validation
 
 **Algorithm Layer:**
-
 - `models/reducers.py` - Modular dimensionality reduction with factory pattern
 - Supports PCA, t-SNE (openTSNE), and UMAP algorithms
 - Abstract base class for easy extension
 
 **Visualization Layer:**
-
 - `visualization/plots.py` - Plot factory with single and dual plot support
 - `visualization/colors.py` - Color mapping and grayscale conversion utilities
 - Plotly-based 2D/3D scatter plots with interactive features
 
 **UI Layer:**
-
 - `ui/layout.py` - Main application layout composition
 - `ui/components/` - Reusable, testable UI components
 - `ui/callbacks/` - Organized callbacks grouped by functionality
 - Bootstrap-styled sidebar with controls and large visualization area
 
 **Configuration:**
-
 - `config/settings.py` - Centralized settings with environment variable support
 - Plot styling, marker configurations, and app-wide constants
 
@@ -136,19 +112,16 @@ Optional fields: `id`, `category`, `subcategory`, `tags`
 The refactored callback system is organized by functionality:
 
 **Data Processing (`ui/callbacks/data_processing.py`):**
-
 - File upload handling
 - NDJSON parsing and validation
 - Data storage in dcc.Store components
 
 **Visualization (`ui/callbacks/visualization.py`):**
-
 - Dimensionality reduction pipeline
 - Plot generation and updates
 - Method/parameter change handling
 
 **Interactions (`ui/callbacks/interactions.py`):**
-
 - Point click handling and detail display
 - Reset functionality
 - User interaction management
@@ -158,18 +131,15 @@ The refactored callback system is organized by functionality:
 The modular design enables comprehensive testing:
 
 **Unit Tests:**
-
 - `tests/test_data_processing.py` - Parser and processor logic
 - `tests/test_reducers.py` - Dimensionality reduction algorithms
 - `tests/test_visualization.py` - Plot creation and color mapping
 
 **Integration Tests:**
-
 - End-to-end data pipeline testing
 - Component integration verification
 
 **Key Testing Benefits:**
-
 - Fast test execution (milliseconds vs seconds)
 - Isolated component testing
 - Easy mocking and fixture creation
@@ -197,7 +167,6 @@ Uses modern Python stack with uv for dependency management:
 5. **Tests** - Write tests for all new functionality
 
 **Code Organization Principles:**
-
 - Single responsibility principle
 - Clear module boundaries  
 - Testable, isolated components
@@ -205,8 +174,7 @@ Uses modern Python stack with uv for dependency management:
 - Error handling at appropriate layers
 
 **Testing Requirements:**
-
 - Unit tests for all core logic
 - Integration tests for data flow
 - Component tests for UI elements
-- Maintain high test coverage
+- Maintain high test coverage

README.md

@@ -90,7 +90,7 @@ uv run python main.py
 
 The application follows a modular architecture for improved maintainability and testability:
 
-```text
+```
 src/embeddingbuddy/
 ├── config/          # Configuration management
 │   └── settings.py  # Centralized app settings
@@ -115,8 +115,8 @@ src/embeddingbuddy/
 Run the test suite to verify functionality:
 
 ```bash
-# Install test dependencies
-uv sync --extra test
+# Install pytest
+uv add pytest
 
 # Run all tests
 uv run pytest tests/ -v
@@ -128,31 +128,6 @@ uv run pytest tests/test_data_processing.py -v
 uv run pytest tests/ --cov=src/embeddingbuddy
 ```
 
-### Development Tools
-
-Install development dependencies for linting, type checking, and security:
-
-```bash
-# Install all dev dependencies
-uv sync --extra dev
-
-# Or install specific groups
-uv sync --extra test        # Testing tools
-uv sync --extra lint        # Linting and formatting
-uv sync --extra security    # Security scanning tools
-
-# Run linting
-uv run ruff check src/ tests/
-uv run ruff format src/ tests/
-
-# Run type checking
-uv run mypy src/embeddingbuddy/
-
-# Run security scans
-uv run bandit -r src/
-uv run safety check
-```
-
 ### Adding New Features
 
 The modular architecture makes it easy to extend functionality:

app.py

@@ -0,0 +1,515 @@
+import json
+import uuid
+from io import StringIO
+import base64
+
+import dash
+from dash import dcc, html, Input, Output, State, callback
+import dash_bootstrap_components as dbc
+import plotly.express as px
+import plotly.graph_objects as go
+import pandas as pd
+import numpy as np
+from sklearn.decomposition import PCA
+import umap
+from openTSNE import TSNE
+
+
+app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
+
+def parse_ndjson(contents):
+    """Parse NDJSON content and return list of documents."""
+    content_type, content_string = contents.split(',')
+    decoded = base64.b64decode(content_string)
+    text_content = decoded.decode('utf-8')
+    
+    documents = []
+    for line in text_content.strip().split('\n'):
+        if line.strip():
+            doc = json.loads(line)
+            if 'id' not in doc:
+                doc['id'] = str(uuid.uuid4())
+            documents.append(doc)
+    return documents
+
+def apply_dimensionality_reduction(embeddings, method='pca', n_components=3):
+    """Apply dimensionality reduction to embeddings."""
+    if method == 'pca':
+        reducer = PCA(n_components=n_components)
+        reduced = reducer.fit_transform(embeddings)
+        variance_explained = reducer.explained_variance_ratio_
+        return reduced, variance_explained
+    elif method == 'tsne':
+        reducer = TSNE(n_components=n_components, random_state=42)
+        reduced = reducer.fit(embeddings)
+        return reduced, None
+    elif method == 'umap':
+        reducer = umap.UMAP(n_components=n_components, random_state=42)
+        reduced = reducer.fit_transform(embeddings)
+        return reduced, None
+    else:
+        raise ValueError(f"Unknown method: {method}")
+
+def create_color_mapping(documents, color_by):
+    """Create color mapping for documents based on specified field."""
+    if color_by == 'category':
+        values = [doc.get('category', 'Unknown') for doc in documents]
+    elif color_by == 'subcategory':
+        values = [doc.get('subcategory', 'Unknown') for doc in documents]
+    elif color_by == 'tags':
+        values = [', '.join(doc.get('tags', [])) if doc.get('tags') else 'No tags' for doc in documents]
+    else:
+        values = ['All'] * len(documents)
+    
+    return values
+
+def create_plot(df, dimensions='3d', color_by='category', method='PCA'):
+    """Create plotly scatter plot."""
+    color_values = create_color_mapping(df.to_dict('records'), color_by)
+    
+    # Truncate text for hover display
+    df_display = df.copy()
+    df_display['text_preview'] = df_display['text'].apply(lambda x: x[:100] + "..." if len(x) > 100 else x)
+    
+    # Include all metadata fields in hover
+    hover_fields = ['id', 'text_preview', 'category', 'subcategory']
+    # Add tags as a string for hover
+    df_display['tags_str'] = df_display['tags'].apply(lambda x: ', '.join(x) if x else 'None')
+    hover_fields.append('tags_str')
+    
+    if dimensions == '3d':
+        fig = px.scatter_3d(
+            df_display, x='dim_1', y='dim_2', z='dim_3',
+            color=color_values,
+            hover_data=hover_fields,
+            title=f'3D Embedding Visualization - {method} (colored by {color_by})'
+        )
+        fig.update_traces(marker=dict(size=5))
+    else:
+        fig = px.scatter(
+            df_display, x='dim_1', y='dim_2',
+            color=color_values,
+            hover_data=hover_fields,
+            title=f'2D Embedding Visualization - {method} (colored by {color_by})'
+        )
+        fig.update_traces(marker=dict(size=8))
+    
+    fig.update_layout(
+        height=None,  # Let CSS height control this
+        autosize=True,
+        margin=dict(l=0, r=0, t=50, b=0)
+    )
+    return fig
+
+def create_dual_plot(doc_df, prompt_df, dimensions='3d', color_by='category', method='PCA', show_prompts=None):
+    """Create plotly scatter plot with separate traces for documents and prompts."""
+    
+    # Create the base figure
+    fig = go.Figure()
+    
+    # Helper function to convert colors to grayscale
+    def to_grayscale_hex(color_str):
+        """Convert a color to grayscale while maintaining some distinction."""
+        import plotly.colors as pc
+        # Try to get RGB values from the color
+        try:
+            if color_str.startswith('#'):
+                # Hex color
+                rgb = tuple(int(color_str[i:i+2], 16) for i in (1, 3, 5))
+            else:
+                # Named color or other format - convert through plotly
+                rgb = pc.hex_to_rgb(pc.convert_colors_to_same_type([color_str], colortype='hex')[0][0])
+            
+            # Convert to grayscale using luminance formula, but keep some color
+            gray_value = int(0.299 * rgb[0] + 0.587 * rgb[1] + 0.114 * rgb[2])
+            # Make it a bit more gray but not completely
+            gray_rgb = (gray_value * 0.7 + rgb[0] * 0.3, 
+                       gray_value * 0.7 + rgb[1] * 0.3, 
+                       gray_value * 0.7 + rgb[2] * 0.3)
+            return f'rgb({int(gray_rgb[0])},{int(gray_rgb[1])},{int(gray_rgb[2])})'
+        except:
+            return 'rgb(128,128,128)'  # fallback gray
+    
+    # Create document plot using plotly express for consistent colors
+    doc_color_values = create_color_mapping(doc_df.to_dict('records'), color_by)
+    doc_df_display = doc_df.copy()
+    doc_df_display['text_preview'] = doc_df_display['text'].apply(lambda x: x[:100] + "..." if len(x) > 100 else x)
+    doc_df_display['tags_str'] = doc_df_display['tags'].apply(lambda x: ', '.join(x) if x else 'None')
+    
+    hover_fields = ['id', 'text_preview', 'category', 'subcategory', 'tags_str']
+    
+    # Create documents plot to get the color mapping
+    if dimensions == '3d':
+        doc_fig = px.scatter_3d(
+            doc_df_display, x='dim_1', y='dim_2', z='dim_3',
+            color=doc_color_values,
+            hover_data=hover_fields
+        )
+    else:
+        doc_fig = px.scatter(
+            doc_df_display, x='dim_1', y='dim_2',
+            color=doc_color_values,
+            hover_data=hover_fields
+        )
+    
+    # Add document traces to main figure
+    for trace in doc_fig.data:
+        trace.name = f'Documents - {trace.name}'
+        if dimensions == '3d':
+            trace.marker.size = 5
+            trace.marker.symbol = 'circle'
+        else:
+            trace.marker.size = 8
+            trace.marker.symbol = 'circle'
+        trace.marker.opacity = 1.0
+        fig.add_trace(trace)
+    
+    # Add prompt traces if they exist
+    if prompt_df is not None and show_prompts and 'show' in show_prompts:
+        prompt_color_values = create_color_mapping(prompt_df.to_dict('records'), color_by)
+        prompt_df_display = prompt_df.copy()
+        prompt_df_display['text_preview'] = prompt_df_display['text'].apply(lambda x: x[:100] + "..." if len(x) > 100 else x)
+        prompt_df_display['tags_str'] = prompt_df_display['tags'].apply(lambda x: ', '.join(x) if x else 'None')
+        
+        # Create prompts plot to get consistent color grouping
+        if dimensions == '3d':
+            prompt_fig = px.scatter_3d(
+                prompt_df_display, x='dim_1', y='dim_2', z='dim_3',
+                color=prompt_color_values,
+                hover_data=hover_fields
+            )
+        else:
+            prompt_fig = px.scatter(
+                prompt_df_display, x='dim_1', y='dim_2',
+                color=prompt_color_values,
+                hover_data=hover_fields
+            )
+        
+        # Add prompt traces with grayed colors
+        for trace in prompt_fig.data:
+            # Convert the color to grayscale
+            original_color = trace.marker.color
+            if hasattr(trace.marker, 'color') and isinstance(trace.marker.color, str):
+                trace.marker.color = to_grayscale_hex(trace.marker.color)
+            
+            trace.name = f'Prompts - {trace.name}'
+            if dimensions == '3d':
+                trace.marker.size = 6
+                trace.marker.symbol = 'diamond'
+            else:
+                trace.marker.size = 10
+                trace.marker.symbol = 'diamond'
+            trace.marker.opacity = 0.8
+            fig.add_trace(trace)
+    
+    title = f'{dimensions.upper()} Embedding Visualization - {method} (colored by {color_by})'
+    fig.update_layout(
+        title=title,
+        height=None,
+        autosize=True,
+        margin=dict(l=0, r=0, t=50, b=0)
+    )
+    
+    return fig
+
+# Layout
+app.layout = dbc.Container([
+    dbc.Row([
+        dbc.Col([
+            html.H1("EmbeddingBuddy", className="text-center mb-4"),
+        ], width=12)
+    ]),
+    
+    dbc.Row([
+        # Left sidebar with controls
+        dbc.Col([
+            html.H5("Upload Data", className="mb-3"),
+            dcc.Upload(
+                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'
+                },
+                multiple=False
+            ),
+            
+            dcc.Upload(
+                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'
+                },
+                multiple=False
+            ),
+            
+            dbc.Button(
+                "Reset All Data",
+                id='reset-button',
+                color='danger',
+                outline=True,
+                size='sm',
+                className='mb-3',
+                style={'width': '100%'}
+            ),
+            
+            html.H5("Visualization Controls", className="mb-3"),
+            
+            dbc.Label("Method:"),
+            dcc.Dropdown(
+                id='method-dropdown',
+                options=[
+                    {'label': 'PCA', 'value': 'pca'},
+                    {'label': 't-SNE', 'value': 'tsne'},
+                    {'label': 'UMAP', 'value': 'umap'}
+                ],
+                value='pca',
+                style={'margin-bottom': '15px'}
+            ),
+            
+            dbc.Label("Color by:"),
+            dcc.Dropdown(
+                id='color-dropdown',
+                options=[
+                    {'label': 'Category', 'value': 'category'},
+                    {'label': 'Subcategory', 'value': 'subcategory'},
+                    {'label': 'Tags', 'value': 'tags'}
+                ],
+                value='category',
+                style={'margin-bottom': '15px'}
+            ),
+            
+            dbc.Label("Dimensions:"),
+            dcc.RadioItems(
+                id='dimension-toggle',
+                options=[
+                    {'label': '2D', 'value': '2d'},
+                    {'label': '3D', 'value': '3d'}
+                ],
+                value='3d',
+                style={'margin-bottom': '20px'}
+            ),
+            
+            dbc.Label("Show Prompts:"),
+            dcc.Checklist(
+                id='show-prompts-toggle',
+                options=[{'label': 'Show prompts on plot', 'value': 'show'}],
+                value=['show'],
+                style={'margin-bottom': '20px'}
+            ),
+            
+            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'}),
+        
+        # Main visualization area
+        dbc.Col([
+            dcc.Graph(
+                id='embedding-plot',
+                style={'height': '85vh', 'width': '100%'},
+                config={'responsive': True, 'displayModeBar': True}
+            )
+        ], width=9)
+    ]),
+    
+    dcc.Store(id='processed-data'),
+    dcc.Store(id='processed-prompts')
+], fluid=True)
+
+@callback(
+    Output('processed-data', 'data'),
+    Input('upload-data', 'contents'),
+    State('upload-data', 'filename')
+)
+def process_uploaded_file(contents, filename):
+    if contents is None:
+        return None
+    
+    try:
+        documents = parse_ndjson(contents)
+        embeddings = np.array([doc['embedding'] for doc in documents])
+        
+        # Store original embeddings and documents
+        return {
+            'documents': documents,
+            'embeddings': embeddings.tolist()
+        }
+    except Exception as e:
+        return {'error': str(e)}
+
+@callback(
+    Output('processed-prompts', 'data'),
+    Input('upload-prompts', 'contents'),
+    State('upload-prompts', 'filename')
+)
+def process_uploaded_prompts(contents, filename):
+    if contents is None:
+        return None
+    
+    try:
+        prompts = parse_ndjson(contents)
+        embeddings = np.array([prompt['embedding'] for prompt in prompts])
+        
+        # Store original embeddings and prompts
+        return {
+            'prompts': prompts,
+            'embeddings': embeddings.tolist()
+        }
+    except Exception as e:
+        return {'error': str(e)}
+
+@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')]
+)
+def update_plot(data, prompts_data, method, color_by, dimensions, show_prompts):
+    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)
+        )
+    
+    # Prepare embeddings for dimensionality reduction
+    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')
+    
+    if has_prompts:
+        prompt_embeddings = np.array(prompts_data['embeddings'])
+        all_embeddings = np.vstack([doc_embeddings, prompt_embeddings])
+    
+    n_components = 3 if dimensions == '3d' else 2
+    
+    # Apply dimensionality reduction to combined data
+    reduced, variance_explained = apply_dimensionality_reduction(
+        all_embeddings, method=method, n_components=n_components
+    )
+    
+    # Split reduced embeddings back
+    doc_reduced = reduced[:len(doc_embeddings)]
+    prompt_reduced = reduced[len(doc_embeddings):] if has_prompts else None
+    
+    # Create dataframes
+    doc_df_data = []
+    for i, doc in enumerate(data['documents']):
+        row = {
+            'id': doc['id'],
+            'text': doc['text'],
+            'category': doc.get('category', 'Unknown'),
+            'subcategory': doc.get('subcategory', 'Unknown'),
+            'tags': doc.get('tags', []),
+            'dim_1': doc_reduced[i, 0],
+            'dim_2': doc_reduced[i, 1],
+            'type': 'document'
+        }
+        if dimensions == '3d':
+            row['dim_3'] = doc_reduced[i, 2]
+        doc_df_data.append(row)
+    
+    doc_df = pd.DataFrame(doc_df_data)
+    
+    prompt_df = None
+    if has_prompts and prompt_reduced is not None:
+        prompt_df_data = []
+        for i, prompt in enumerate(prompts_data['prompts']):
+            row = {
+                'id': prompt['id'],
+                'text': prompt['text'],
+                'category': prompt.get('category', 'Unknown'),
+                'subcategory': prompt.get('subcategory', 'Unknown'),
+                'tags': prompt.get('tags', []),
+                'dim_1': prompt_reduced[i, 0],
+                'dim_2': prompt_reduced[i, 1],
+                'type': 'prompt'
+            }
+            if dimensions == '3d':
+                row['dim_3'] = prompt_reduced[i, 2]
+            prompt_df_data.append(row)
+        
+        prompt_df = pd.DataFrame(prompt_df_data)
+    
+    return create_dual_plot(doc_df, prompt_df, dimensions, color_by, method.upper(), show_prompts)
+
+@callback(
+    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"
+    
+    # Get point info from click
+    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"
+    
+    # Determine which dataset this point belongs to
+    if trace_name == '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'
+    
+    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")
+        ])
+    ])
+
+@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
+)
+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"
+
+if __name__ == '__main__':
+    app.run(debug=True)

example/bad/bad_binary_content.ndjson

@@ -1,2 +0,0 @@
-<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>{"id": "doc_001", "embedding": [0.1, -0.3, 0.7, 0.2], "text": "Binary junk at start"}
-{"id": "doc_002", "embedding": [0.5, 0.1, -0.2, 0.8], "text": "Normal line"}<7D><><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>

example/bad/bad_empty_lines.ndjson

@@ -1,6 +0,0 @@
-{"id": "doc_001", "embedding": [0.1, -0.3, 0.7, 0.2], "text": "First line"}
-
-{"id": "doc_002", "embedding": [0.5, 0.1, -0.2, 0.8], "text": "After empty line"}
-
-
-{"id": "doc_003", "embedding": [0.3, 0.4, 0.1, -0.1], "text": "After multiple empty lines"}

example/bad/bad_inconsistent_dimensions.ndjson

@@ -1,4 +0,0 @@
-{"id": "doc_001", "embedding": [0.1, -0.3, 0.7, 0.2], "text": "4D embedding"}
-{"id": "doc_002", "embedding": [0.5, 0.1, -0.2], "text": "3D embedding"}
-{"id": "doc_003", "embedding": [0.3, 0.4, 0.1, -0.1, 0.8], "text": "5D embedding"}
-{"id": "doc_004", "embedding": [0.2, 0.1], "text": "2D embedding"}

example/bad/bad_invalid_embeddings.ndjson

@@ -1,8 +0,0 @@
-{"id": "doc_001", "embedding": "not_an_array", "text": "Embedding as string"}
-{"id": "doc_002", "embedding": [0.1, "text", 0.7, 0.2], "text": "Mixed types in embedding"}
-{"id": "doc_003", "embedding": [], "text": "Empty embedding array"}
-{"id": "doc_004", "embedding": [0.1], "text": "Single dimension embedding"}
-{"id": "doc_005", "embedding": null, "text": "Null embedding"}
-{"id": "doc_006", "embedding": [0.1, 0.2, null, 0.4], "text": "Null value in embedding"}
-{"id": "doc_007", "embedding": [0.1, 0.2, "NaN", 0.4], "text": "String NaN in embedding"}
-{"id": "doc_008", "embedding": [0.1, 0.2, Infinity, 0.4], "text": "Infinity in embedding"}

example/bad/bad_malformed_json.ndjson

@@ -1,5 +0,0 @@
-{"id": "doc_001", "embedding": [0.1, -0.3, 0.7, "text": "Valid line"}
-{"id": "doc_002", "embedding": [0.5, 0.1, -0.2, 0.8], "text": "Missing closing brace"
-{"id": "doc_003" "embedding": [0.3, 0.4, 0.1, -0.1], "text": "Missing colon after id"}
-{id: "doc_004", "embedding": [0.2, 0.1, 0.3, 0.4], "text": "Unquoted key"}
-{"id": "doc_005", "embedding": [0.1, 0.2, 0.3, 0.4], "text": "Valid line again"}

example/bad/bad_missing_embedding.ndjson

@@ -1,3 +0,0 @@
-{"id": "doc_001", "text": "Sample text without embedding field", "category": "test"}
-{"id": "doc_002", "text": "Another text without embedding", "category": "test"}
-{"id": "doc_003", "text": "Third text missing embedding", "category": "test"}

example/bad/bad_missing_text.ndjson

@@ -1,3 +0,0 @@
-{"id": "doc_001", "embedding": [0.1, -0.3, 0.7, 0.2], "category": "test"}
-{"id": "doc_002", "embedding": [0.5, 0.1, -0.2, 0.8], "category": "test"}
-{"id": "doc_003", "embedding": [0.3, 0.4, 0.1, -0.1], "category": "test"}

example/bad/bad_not_ndjson.json

@@ -1,4 +0,0 @@
-[
-  {"id": "doc_001", "embedding": [0.1, -0.3, 0.7, 0.2], "text": "Regular JSON array"},
-  {"id": "doc_002", "embedding": [0.5, 0.1, -0.2, 0.8], "text": "Instead of NDJSON"}
-]

pyproject.toml

@@ -14,28 +14,7 @@ dependencies = [
     "umap-learn>=0.5.8",
     "numba>=0.56.4",
     "openTSNE>=1.0.0",
-    "mypy>=1.17.1",
-]
-
-[project.optional-dependencies]
-test = [
     "pytest>=8.4.1",
-    "pytest-cov>=4.1.0",
-]
-lint = [
-    "ruff>=0.1.0",
-    "mypy>=1.5.0",
-]
-security = [
-    "bandit[toml]>=1.7.5",
-    "safety>=2.3.0",
-    "pip-audit>=2.6.0",
-]
-dev = [
-    "embeddingbuddy[test,lint,security]",
-]
-all = [
-    "embeddingbuddy[test,lint,security]",
 ]
 
 [build-system]

src/embeddingbuddy/__init__.py

@@ -1,3 +1,3 @@
 """EmbeddingBuddy - Interactive exploration and visualization of embedding vectors."""
 
-__version__ = "0.1.0"
+__version__ = "0.1.0"

src/embeddingbuddy/app.py

@@ -8,29 +8,32 @@ from .ui.callbacks.interactions import InteractionCallbacks
 
 
 def create_app():
-    app = dash.Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
-
+    app = dash.Dash(
+        __name__, 
+        external_stylesheets=[dbc.themes.BOOTSTRAP]
+    )
+    
     layout_manager = AppLayout()
     app.layout = layout_manager.create_layout()
-
+    
     DataProcessingCallbacks()
     VisualizationCallbacks()
     InteractionCallbacks()
-
+    
     return app
 
 
 def run_app(app=None, debug=None, host=None, port=None):
     if app is None:
         app = create_app()
-
+    
     app.run(
         debug=debug if debug is not None else AppSettings.DEBUG,
         host=host if host is not None else AppSettings.HOST,
-        port=port if port is not None else AppSettings.PORT,
+        port=port if port is not None else AppSettings.PORT
     )
 
 
-if __name__ == "__main__":
+if __name__ == '__main__':
     app = create_app()
-    run_app(app)
+    run_app(app)

src/embeddingbuddy/config/settings.py

@@ -3,100 +3,105 @@ import os
 
 
 class AppSettings:
+    
     # UI Configuration
     UPLOAD_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'
     }
-
-    PROMPTS_UPLOAD_STYLE = {**UPLOAD_STYLE, "borderColor": "#28a745"}
-
-    PLOT_CONFIG = {"responsive": True, "displayModeBar": True}
-
-    PLOT_STYLE = {"height": "85vh", "width": "100%"}
-
+    
+    PROMPTS_UPLOAD_STYLE = {
+        **UPLOAD_STYLE,
+        'borderColor': '#28a745'
+    }
+    
+    PLOT_CONFIG = {
+        'responsive': True,
+        'displayModeBar': True
+    }
+    
+    PLOT_STYLE = {
+        'height': '85vh',
+        'width': '100%'
+    }
+    
     PLOT_LAYOUT_CONFIG = {
-        "height": None,
-        "autosize": True,
-        "margin": dict(l=0, r=0, t=50, b=0),
+        'height': None,
+        'autosize': True,
+        'margin': dict(l=0, r=0, t=50, b=0)
     }
-
+    
     # Dimensionality Reduction Settings
     DEFAULT_N_COMPONENTS_3D = 3
     DEFAULT_N_COMPONENTS_2D = 2
     DEFAULT_RANDOM_STATE = 42
-
+    
     # Available Methods
     REDUCTION_METHODS = [
-        {"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'}
     ]
-
+    
     COLOR_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'}
     ]
-
-    DIMENSION_OPTIONS = [{"label": "2D", "value": "2d"}, {"label": "3D", "value": "3d"}]
-
+    
+    DIMENSION_OPTIONS = [
+        {'label': '2D', 'value': '2d'},
+        {'label': '3D', 'value': '3d'}
+    ]
+    
     # Default Values
-    DEFAULT_METHOD = "pca"
-    DEFAULT_COLOR_BY = "category"
-    DEFAULT_DIMENSIONS = "3d"
-    DEFAULT_SHOW_PROMPTS = ["show"]
-
+    DEFAULT_METHOD = 'pca'
+    DEFAULT_COLOR_BY = 'category'
+    DEFAULT_DIMENSIONS = '3d'
+    DEFAULT_SHOW_PROMPTS = ['show']
+    
     # Plot Marker Settings
     DOCUMENT_MARKER_SIZE_2D = 8
     DOCUMENT_MARKER_SIZE_3D = 5
     PROMPT_MARKER_SIZE_2D = 10
     PROMPT_MARKER_SIZE_3D = 6
-
-    DOCUMENT_MARKER_SYMBOL = "circle"
-    PROMPT_MARKER_SYMBOL = "diamond"
-
+    
+    DOCUMENT_MARKER_SYMBOL = 'circle'
+    PROMPT_MARKER_SYMBOL = 'diamond'
+    
     DOCUMENT_OPACITY = 1.0
     PROMPT_OPACITY = 0.8
-
+    
     # Text Processing
     TEXT_PREVIEW_LENGTH = 100
-
+    
     # App Configuration
-    DEBUG = os.getenv("EMBEDDINGBUDDY_DEBUG", "True").lower() == "true"
-    HOST = os.getenv("EMBEDDINGBUDDY_HOST", "127.0.0.1")
-    PORT = int(os.getenv("EMBEDDINGBUDDY_PORT", "8050"))
-
+    DEBUG = os.getenv('EMBEDDINGBUDDY_DEBUG', 'True').lower() == 'true'
+    HOST = os.getenv('EMBEDDINGBUDDY_HOST', '127.0.0.1')
+    PORT = int(os.getenv('EMBEDDINGBUDDY_PORT', '8050'))
+    
     # Bootstrap Theme
-    EXTERNAL_STYLESHEETS = [
-        "https://cdn.jsdelivr.net/npm/bootstrap@5.1.3/dist/css/bootstrap.min.css"
-    ]
-
+    EXTERNAL_STYLESHEETS = ['https://cdn.jsdelivr.net/npm/bootstrap@5.1.3/dist/css/bootstrap.min.css']
+    
     @classmethod
-    def get_plot_marker_config(
-        cls, dimensions: str, is_prompt: bool = False
-    ) -> Dict[str, Any]:
+    def get_plot_marker_config(cls, dimensions: str, is_prompt: bool = False) -> Dict[str, Any]:
         if is_prompt:
-            size = (
-                cls.PROMPT_MARKER_SIZE_3D
-                if dimensions == "3d"
-                else cls.PROMPT_MARKER_SIZE_2D
-            )
+            size = cls.PROMPT_MARKER_SIZE_3D if dimensions == '3d' else cls.PROMPT_MARKER_SIZE_2D
             symbol = cls.PROMPT_MARKER_SYMBOL
             opacity = cls.PROMPT_OPACITY
         else:
-            size = (
-                cls.DOCUMENT_MARKER_SIZE_3D
-                if dimensions == "3d"
-                else cls.DOCUMENT_MARKER_SIZE_2D
-            )
+            size = cls.DOCUMENT_MARKER_SIZE_3D if dimensions == '3d' else cls.DOCUMENT_MARKER_SIZE_2D
             symbol = cls.DOCUMENT_MARKER_SYMBOL
             opacity = cls.DOCUMENT_OPACITY
-
-        return {"size": size, "symbol": symbol, "opacity": opacity}
+        
+        return {
+            'size': size,
+            'symbol': symbol,
+            'opacity': opacity
+        }

src/embeddingbuddy/data/parser.py

@@ -6,67 +6,34 @@ from ..models.schemas import Document
 
 
 class NDJSONParser:
+    
     @staticmethod
     def parse_upload_contents(contents: str) -> List[Document]:
-        content_type, content_string = contents.split(",")
+        content_type, content_string = contents.split(',')
         decoded = base64.b64decode(content_string)
-        text_content = decoded.decode("utf-8")
+        text_content = decoded.decode('utf-8')
         return NDJSONParser.parse_text(text_content)
-
+    
     @staticmethod
     def parse_text(text_content: str) -> List[Document]:
         documents = []
-        for line_num, line in enumerate(text_content.strip().split("\n"), 1):
+        for line in text_content.strip().split('\n'):
             if line.strip():
-                try:
-                    doc_dict = json.loads(line)
-                    doc = NDJSONParser._dict_to_document(doc_dict)
-                    documents.append(doc)
-                except json.JSONDecodeError as e:
-                    raise json.JSONDecodeError(
-                        f"Invalid JSON on line {line_num}: {e.msg}", e.doc, e.pos
-                    )
-                except KeyError as e:
-                    raise KeyError(f"Missing required field {e} on line {line_num}")
-                except (TypeError, ValueError) as e:
-                    raise ValueError(
-                        f"Invalid data format on line {line_num}: {str(e)}"
-                    )
+                doc_dict = json.loads(line)
+                doc = NDJSONParser._dict_to_document(doc_dict)
+                documents.append(doc)
         return documents
-
+    
     @staticmethod
     def _dict_to_document(doc_dict: dict) -> Document:
-        if "id" not in doc_dict:
-            doc_dict["id"] = str(uuid.uuid4())
-
-        # Validate required fields
-        if "text" not in doc_dict:
-            raise KeyError("'text'")
-        if "embedding" not in doc_dict:
-            raise KeyError("'embedding'")
-
-        # Validate embedding format
-        embedding = doc_dict["embedding"]
-        if not isinstance(embedding, list):
-            raise ValueError(
-                f"Embedding must be a list, got {type(embedding).__name__}"
-            )
-
-        if not embedding:
-            raise ValueError("Embedding cannot be empty")
-
-        # Check that all embedding values are numbers
-        for i, val in enumerate(embedding):
-            if not isinstance(val, (int, float)) or val != val:  # NaN check
-                raise ValueError(
-                    f"Embedding contains invalid value at index {i}: {val}"
-                )
-
+        if 'id' not in doc_dict:
+            doc_dict['id'] = str(uuid.uuid4())
+        
         return Document(
-            id=doc_dict["id"],
-            text=doc_dict["text"],
-            embedding=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/data/processor.py

@@ -5,19 +5,18 @@ from .parser import NDJSONParser
 
 
 class DataProcessor:
+    
     def __init__(self):
         self.parser = NDJSONParser()
-
-    def process_upload(
-        self, contents: str, filename: Optional[str] = None
-    ) -> ProcessedData:
+    
+    def process_upload(self, contents: str, filename: Optional[str] = None) -> ProcessedData:
         try:
             documents = self.parser.parse_upload_contents(contents)
             embeddings = self._extract_embeddings(documents)
             return ProcessedData(documents=documents, embeddings=embeddings)
         except Exception as e:
             return ProcessedData(documents=[], embeddings=np.array([]), error=str(e))
-
+    
     def process_text(self, text_content: str) -> ProcessedData:
         try:
             documents = self.parser.parse_text(text_content)
@@ -25,35 +24,31 @@ class DataProcessor:
             return ProcessedData(documents=documents, embeddings=embeddings)
         except Exception as e:
             return ProcessedData(documents=[], embeddings=np.array([]), error=str(e))
-
+    
     def _extract_embeddings(self, documents: List[Document]) -> np.ndarray:
         if not documents:
             return np.array([])
         return np.array([doc.embedding for doc in documents])
-
-    def combine_data(
-        self, doc_data: ProcessedData, prompt_data: Optional[ProcessedData] = None
-    ) -> Tuple[np.ndarray, List[Document], Optional[List[Document]]]:
+    
+    def combine_data(self, doc_data: ProcessedData, prompt_data: Optional[ProcessedData] = None) -> Tuple[np.ndarray, List[Document], Optional[List[Document]]]:
         if not doc_data or doc_data.error:
             raise ValueError("Invalid document data")
-
+        
         all_embeddings = doc_data.embeddings
         documents = doc_data.documents
         prompts = None
-
+        
         if prompt_data and not prompt_data.error and prompt_data.documents:
             all_embeddings = np.vstack([doc_data.embeddings, prompt_data.embeddings])
             prompts = prompt_data.documents
-
+        
         return all_embeddings, documents, prompts
-
-    def split_reduced_data(
-        self, reduced_embeddings: np.ndarray, n_documents: int, n_prompts: int = 0
-    ) -> Tuple[np.ndarray, Optional[np.ndarray]]:
+    
+    def split_reduced_data(self, reduced_embeddings: np.ndarray, n_documents: int, n_prompts: int = 0) -> Tuple[np.ndarray, Optional[np.ndarray]]:
         doc_reduced = reduced_embeddings[:n_documents]
         prompt_reduced = None
-
+        
         if n_prompts > 0:
-            prompt_reduced = reduced_embeddings[n_documents : n_documents + n_prompts]
-
-        return doc_reduced, prompt_reduced
+            prompt_reduced = reduced_embeddings[n_documents:n_documents + n_prompts]
+        
+        return doc_reduced, prompt_reduced

src/embeddingbuddy/models/reducers.py

@@ -7,89 +7,88 @@ from .schemas import ReducedData
 
 
 class DimensionalityReducer(ABC):
+    
     def __init__(self, n_components: int = 3, random_state: int = 42):
         self.n_components = n_components
         self.random_state = random_state
         self._reducer = None
-
+    
     @abstractmethod
     def fit_transform(self, embeddings: np.ndarray) -> ReducedData:
         pass
-
+    
     @abstractmethod
     def get_method_name(self) -> str:
         pass
 
 
 class PCAReducer(DimensionalityReducer):
+    
     def fit_transform(self, embeddings: np.ndarray) -> ReducedData:
         self._reducer = PCA(n_components=self.n_components)
         reduced = self._reducer.fit_transform(embeddings)
         variance_explained = self._reducer.explained_variance_ratio_
-
+        
         return ReducedData(
             reduced_embeddings=reduced,
             variance_explained=variance_explained,
             method=self.get_method_name(),
-            n_components=self.n_components,
+            n_components=self.n_components
         )
-
+    
     def get_method_name(self) -> str:
         return "PCA"
 
 
 class TSNEReducer(DimensionalityReducer):
+    
     def fit_transform(self, embeddings: np.ndarray) -> ReducedData:
-        self._reducer = TSNE(
-            n_components=self.n_components, random_state=self.random_state
-        )
+        self._reducer = TSNE(n_components=self.n_components, random_state=self.random_state)
         reduced = self._reducer.fit(embeddings)
-
+        
         return ReducedData(
             reduced_embeddings=reduced,
             variance_explained=None,
             method=self.get_method_name(),
-            n_components=self.n_components,
+            n_components=self.n_components
         )
-
+    
     def get_method_name(self) -> str:
         return "t-SNE"
 
 
 class UMAPReducer(DimensionalityReducer):
+    
     def fit_transform(self, embeddings: np.ndarray) -> ReducedData:
-        self._reducer = umap.UMAP(
-            n_components=self.n_components, random_state=self.random_state
-        )
+        self._reducer = umap.UMAP(n_components=self.n_components, random_state=self.random_state)
         reduced = self._reducer.fit_transform(embeddings)
-
+        
         return ReducedData(
             reduced_embeddings=reduced,
             variance_explained=None,
             method=self.get_method_name(),
-            n_components=self.n_components,
+            n_components=self.n_components
         )
-
+    
     def get_method_name(self) -> str:
         return "UMAP"
 
 
 class ReducerFactory:
+    
     @staticmethod
-    def create_reducer(
-        method: str, n_components: int = 3, random_state: int = 42
-    ) -> DimensionalityReducer:
+    def create_reducer(method: str, n_components: int = 3, random_state: int = 42) -> DimensionalityReducer:
         method_lower = method.lower()
-
-        if method_lower == "pca":
+        
+        if method_lower == 'pca':
             return PCAReducer(n_components=n_components, random_state=random_state)
-        elif method_lower == "tsne":
+        elif method_lower == 'tsne':
             return TSNEReducer(n_components=n_components, random_state=random_state)
-        elif method_lower == "umap":
+        elif method_lower == 'umap':
             return UMAPReducer(n_components=n_components, random_state=random_state)
         else:
             raise ValueError(f"Unknown reduction method: {method}")
-
+    
     @staticmethod
     def get_available_methods() -> list:
-        return ["pca", "tsne", "umap"]
+        return ['pca', 'tsne', 'umap']

src/embeddingbuddy/models/schemas.py

@@ -50,11 +50,9 @@ class PlotData:
     coordinates: np.ndarray
     prompts: Optional[List[Document]] = None
     prompt_coordinates: Optional[np.ndarray] = None
-
+    
     def __post_init__(self):
         if not isinstance(self.coordinates, np.ndarray):
             self.coordinates = np.array(self.coordinates)
-        if self.prompt_coordinates is not None and not isinstance(
-            self.prompt_coordinates, np.ndarray
-        ):
-            self.prompt_coordinates = np.array(self.prompt_coordinates)
+        if self.prompt_coordinates is not None and not isinstance(self.prompt_coordinates, np.ndarray):
+            self.prompt_coordinates = np.array(self.prompt_coordinates)

src/embeddingbuddy/ui/callbacks/data_processing.py

@@ -3,118 +3,58 @@ 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", allow_duplicate=True),
-                Output("upload-error-alert", "children", allow_duplicate=True),
-                Output("upload-error-alert", "is_open", allow_duplicate=True),
-            ],
-            Input("upload-data", "contents"),
-            State("upload-data", "filename"),
-            prevent_initial_call=True,
+            Output('processed-data', 'data'),
+            Input('upload-data', 'contents'),
+            State('upload-data', 'filename')
         )
         def process_uploaded_file(contents, filename):
             if contents is None:
-                return None, "", False
-
+                return None
+            
             processed_data = self.processor.process_upload(contents, filename)
-
+            
             if processed_data.error:
-                error_message = self._format_error_message(
-                    processed_data.error, filename
-                )
-                return (
-                    {"error": processed_data.error},
-                    error_message,
-                    True,  # Show error alert
-                )
-
-            return (
-                {
-                    "documents": [
-                        self._document_to_dict(doc) for doc in processed_data.documents
-                    ],
-                    "embeddings": processed_data.embeddings.tolist(),
-                },
-                "",
-                False,  # Hide error alert
-            )
-
+                return {'error': processed_data.error}
+            
+            return {
+                'documents': [self._document_to_dict(doc) for doc in processed_data.documents],
+                'embeddings': processed_data.embeddings.tolist()
+            }
+        
         @callback(
-            Output("processed-prompts", "data", allow_duplicate=True),
-            Input("upload-prompts", "contents"),
-            State("upload-prompts", "filename"),
-            prevent_initial_call=True,
+            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,
-        }
-
-    @staticmethod
-    def _format_error_message(error: str, filename: str | None = None) -> str:
-        """Format error message with helpful guidance for users."""
-        file_part = f" in file '{filename}'" if filename else ""
-
-        # Check for common error patterns and provide helpful messages
-        if "embedding" in error.lower() and (
-            "key" in error.lower() or "required field" in error.lower()
-        ):
-            return (
-                f"❌ Missing 'embedding' field{file_part}. "
-                "Each line must contain an 'embedding' field with a list of numbers."
-            )
-        elif "text" in error.lower() and (
-            "key" in error.lower() or "required field" in error.lower()
-        ):
-            return (
-                f"❌ Missing 'text' field{file_part}. "
-                "Each line must contain a 'text' field with the document content."
-            )
-        elif "json" in error.lower() and "decode" in error.lower():
-            return (
-                f"❌ Invalid JSON format{file_part}. "
-                "Please check that each line is valid JSON with proper syntax (quotes, braces, etc.)."
-            )
-        elif "unicode" in error.lower() or "decode" in error.lower():
-            return (
-                f"❌ File encoding issue{file_part}. "
-                "Please ensure the file is saved in UTF-8 format and contains no binary data."
-            )
-        elif "array" in error.lower() or "list" in error.lower():
-            return (
-                f"❌ Invalid embedding format{file_part}. "
-                "Embeddings must be arrays/lists of numbers, not strings or other types."
-            )
-        else:
-            return (
-                f"❌ Error processing file{file_part}: {error}. "
-                "Please check that your file is valid NDJSON with required 'text' and 'embedding' fields."
-            )
+            'id': doc.id,
+            'text': doc.text,
+            'embedding': doc.embedding,
+            'category': doc.category,
+            'subcategory': doc.subcategory,
+            'tags': doc.tags
+        }

src/embeddingbuddy/ui/callbacks/interactions.py

@@ -4,79 +4,63 @@ 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

@@ -7,102 +7,81 @@ 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

@@ -4,84 +4,79 @@ 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_error_alert(),
-                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

@@ -3,62 +3,58 @@ 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%"},
-        )
-
-    @staticmethod
-    def create_error_alert():
-        """Create error alert component for data upload issues."""
-        return dbc.Alert(
-            id="upload-error-alert",
-            dismissable=True,
-            is_open=False,
-            color="danger",
-            className="mb-3",
-        )
+            size='sm',
+            className='mb-3',
+            style={'width': '100%'}
+        )

src/embeddingbuddy/ui/layout.py

@@ -4,44 +4,41 @@ 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')
+        ]

src/embeddingbuddy/visualization/colors.py

@@ -4,33 +4,30 @@ from ..models.schemas import Document
 
 
 class ColorMapper:
+    
     @staticmethod
     def create_color_mapping(documents: List[Document], color_by: str) -> List[str]:
-        if color_by == "category":
+        if color_by == 'category':
             return [doc.category for doc in documents]
-        elif color_by == "subcategory":
+        elif color_by == 'subcategory':
             return [doc.subcategory for doc in documents]
-        elif color_by == "tags":
-            return [", ".join(doc.tags) if doc.tags else "No tags" for doc in documents]
+        elif color_by == 'tags':
+            return [', '.join(doc.tags) if doc.tags else 'No tags' for doc in documents]
         else:
-            return ["All"] * len(documents)
-
+            return ['All'] * len(documents)
+    
     @staticmethod
     def to_grayscale_hex(color_str: str) -> str:
         try:
-            if color_str.startswith("#"):
-                rgb = tuple(int(color_str[i : i + 2], 16) for i in (1, 3, 5))
+            if color_str.startswith('#'):
+                rgb = tuple(int(color_str[i:i+2], 16) for i in (1, 3, 5))
             else:
-                rgb = pc.hex_to_rgb(
-                    pc.convert_colors_to_same_type([color_str], colortype="hex")[0][0]
-                )
-
+                rgb = pc.hex_to_rgb(pc.convert_colors_to_same_type([color_str], colortype='hex')[0][0])
+            
             gray_value = int(0.299 * rgb[0] + 0.587 * rgb[1] + 0.114 * rgb[2])
-            gray_rgb = (
-                gray_value * 0.7 + rgb[0] * 0.3,
-                gray_value * 0.7 + rgb[1] * 0.3,
-                gray_value * 0.7 + rgb[2] * 0.3,
-            )
-            return f"rgb({int(gray_rgb[0])},{int(gray_rgb[1])},{int(gray_rgb[2])})"
-        except:  # noqa: E722
-            return "rgb(128,128,128)"
+            gray_rgb = (gray_value * 0.7 + rgb[0] * 0.3, 
+                       gray_value * 0.7 + rgb[1] * 0.3, 
+                       gray_value * 0.7 + rgb[2] * 0.3)
+            return f'rgb({int(gray_rgb[0])},{int(gray_rgb[1])},{int(gray_rgb[2])})'
+        except: # noqa: E722
+            return 'rgb(128,128,128)'

src/embeddingbuddy/visualization/plots.py

@@ -7,172 +7,139 @@ from .colors import ColorMapper
 
 
 class PlotFactory:
+    
     def __init__(self):
         self.color_mapper = ColorMapper()
-
-    def create_plot(
-        self,
-        plot_data: PlotData,
-        dimensions: str = "3d",
-        color_by: str = "category",
-        method: str = "PCA",
-        show_prompts: Optional[List[str]] = None,
-    ) -> go.Figure:
-        if plot_data.prompts and show_prompts and "show" in show_prompts:
+    
+    def create_plot(self, plot_data: PlotData, dimensions: str = '3d', 
+                   color_by: str = 'category', method: str = 'PCA',
+                   show_prompts: Optional[List[str]] = None) -> go.Figure:
+        
+        if plot_data.prompts and show_prompts and 'show' in show_prompts:
             return self._create_dual_plot(plot_data, dimensions, color_by, method)
         else:
             return self._create_single_plot(plot_data, dimensions, color_by, method)
-
-    def _create_single_plot(
-        self, plot_data: PlotData, dimensions: str, color_by: str, method: str
-    ) -> go.Figure:
-        df = self._prepare_dataframe(
-            plot_data.documents, plot_data.coordinates, dimensions
-        )
-        color_values = self.color_mapper.create_color_mapping(
-            plot_data.documents, color_by
-        )
-
-        hover_fields = ["id", "text_preview", "category", "subcategory", "tags_str"]
-
-        if dimensions == "3d":
+    
+    def _create_single_plot(self, plot_data: PlotData, dimensions: str, 
+                           color_by: str, method: str) -> go.Figure:
+        df = self._prepare_dataframe(plot_data.documents, plot_data.coordinates, dimensions)
+        color_values = self.color_mapper.create_color_mapping(plot_data.documents, color_by)
+        
+        hover_fields = ['id', 'text_preview', 'category', 'subcategory', 'tags_str']
+        
+        if dimensions == '3d':
             fig = px.scatter_3d(
-                df,
-                x="dim_1",
-                y="dim_2",
-                z="dim_3",
+                df, x='dim_1', y='dim_2', z='dim_3',
                 color=color_values,
                 hover_data=hover_fields,
-                title=f"3D Embedding Visualization - {method} (colored by {color_by})",
+                title=f'3D Embedding Visualization - {method} (colored by {color_by})'
             )
             fig.update_traces(marker=dict(size=5))
         else:
             fig = px.scatter(
-                df,
-                x="dim_1",
-                y="dim_2",
+                df, x='dim_1', y='dim_2',
                 color=color_values,
                 hover_data=hover_fields,
-                title=f"2D Embedding Visualization - {method} (colored by {color_by})",
+                title=f'2D Embedding Visualization - {method} (colored by {color_by})'
             )
             fig.update_traces(marker=dict(size=8))
-
-        fig.update_layout(height=None, autosize=True, margin=dict(l=0, r=0, t=50, b=0))
+        
+        fig.update_layout(
+            height=None,
+            autosize=True,
+            margin=dict(l=0, r=0, t=50, b=0)
+        )
         return fig
-
-    def _create_dual_plot(
-        self, plot_data: PlotData, dimensions: str, color_by: str, method: str
-    ) -> go.Figure:
+    
+    def _create_dual_plot(self, plot_data: PlotData, dimensions: str, 
+                         color_by: str, method: str) -> go.Figure:
         fig = go.Figure()
-
-        doc_df = self._prepare_dataframe(
-            plot_data.documents, plot_data.coordinates, dimensions
-        )
-        doc_color_values = self.color_mapper.create_color_mapping(
-            plot_data.documents, color_by
-        )
-
-        hover_fields = ["id", "text_preview", "category", "subcategory", "tags_str"]
-
-        if dimensions == "3d":
+        
+        doc_df = self._prepare_dataframe(plot_data.documents, plot_data.coordinates, dimensions)
+        doc_color_values = self.color_mapper.create_color_mapping(plot_data.documents, color_by)
+        
+        hover_fields = ['id', 'text_preview', 'category', 'subcategory', 'tags_str']
+        
+        if dimensions == '3d':
             doc_fig = px.scatter_3d(
-                doc_df,
-                x="dim_1",
-                y="dim_2",
-                z="dim_3",
+                doc_df, x='dim_1', y='dim_2', z='dim_3',
                 color=doc_color_values,
-                hover_data=hover_fields,
+                hover_data=hover_fields
             )
         else:
             doc_fig = px.scatter(
-                doc_df,
-                x="dim_1",
-                y="dim_2",
+                doc_df, x='dim_1', y='dim_2',
                 color=doc_color_values,
-                hover_data=hover_fields,
+                hover_data=hover_fields
             )
-
+        
         for trace in doc_fig.data:
-            trace.name = f"Documents - {trace.name}"
-            if dimensions == "3d":
+            trace.name = f'Documents - {trace.name}'
+            if dimensions == '3d':
                 trace.marker.size = 5
-                trace.marker.symbol = "circle"
+                trace.marker.symbol = 'circle'
             else:
                 trace.marker.size = 8
-                trace.marker.symbol = "circle"
+                trace.marker.symbol = 'circle'
             trace.marker.opacity = 1.0
             fig.add_trace(trace)
-
+        
         if plot_data.prompts and plot_data.prompt_coordinates is not None:
-            prompt_df = self._prepare_dataframe(
-                plot_data.prompts, plot_data.prompt_coordinates, dimensions
-            )
-            prompt_color_values = self.color_mapper.create_color_mapping(
-                plot_data.prompts, color_by
-            )
-
-            if dimensions == "3d":
+            prompt_df = self._prepare_dataframe(plot_data.prompts, plot_data.prompt_coordinates, dimensions)
+            prompt_color_values = self.color_mapper.create_color_mapping(plot_data.prompts, color_by)
+            
+            if dimensions == '3d':
                 prompt_fig = px.scatter_3d(
-                    prompt_df,
-                    x="dim_1",
-                    y="dim_2",
-                    z="dim_3",
+                    prompt_df, x='dim_1', y='dim_2', z='dim_3',
                     color=prompt_color_values,
-                    hover_data=hover_fields,
+                    hover_data=hover_fields
                 )
             else:
                 prompt_fig = px.scatter(
-                    prompt_df,
-                    x="dim_1",
-                    y="dim_2",
+                    prompt_df, x='dim_1', y='dim_2',
                     color=prompt_color_values,
-                    hover_data=hover_fields,
+                    hover_data=hover_fields
                 )
-
+            
             for trace in prompt_fig.data:
-                if hasattr(trace.marker, "color") and isinstance(
-                    trace.marker.color, str
-                ):
-                    trace.marker.color = self.color_mapper.to_grayscale_hex(
-                        trace.marker.color
-                    )
-
-                trace.name = f"Prompts - {trace.name}"
-                if dimensions == "3d":
+                if hasattr(trace.marker, 'color') and isinstance(trace.marker.color, str):
+                    trace.marker.color = self.color_mapper.to_grayscale_hex(trace.marker.color)
+                
+                trace.name = f'Prompts - {trace.name}'
+                if dimensions == '3d':
                     trace.marker.size = 6
-                    trace.marker.symbol = "diamond"
+                    trace.marker.symbol = 'diamond'
                 else:
                     trace.marker.size = 10
-                    trace.marker.symbol = "diamond"
+                    trace.marker.symbol = 'diamond'
                 trace.marker.opacity = 0.8
                 fig.add_trace(trace)
-
-        title = f"{dimensions.upper()} Embedding Visualization - {method} (colored by {color_by})"
+        
+        title = f'{dimensions.upper()} Embedding Visualization - {method} (colored by {color_by})'
         fig.update_layout(
-            title=title, height=None, autosize=True, margin=dict(l=0, r=0, t=50, b=0)
+            title=title,
+            height=None,
+            autosize=True,
+            margin=dict(l=0, r=0, t=50, b=0)
         )
-
+        
         return fig
-
-    def _prepare_dataframe(
-        self, documents: List[Document], coordinates, dimensions: str
-    ) -> pd.DataFrame:
+    
+    def _prepare_dataframe(self, documents: List[Document], coordinates, dimensions: str) -> pd.DataFrame:
         df_data = []
         for i, doc in enumerate(documents):
             row = {
-                "id": doc.id,
-                "text": doc.text,
-                "text_preview": doc.text[:100] + "..."
-                if len(doc.text) > 100
-                else doc.text,
-                "category": doc.category,
-                "subcategory": doc.subcategory,
-                "tags_str": ", ".join(doc.tags) if doc.tags else "None",
-                "dim_1": coordinates[i, 0],
-                "dim_2": coordinates[i, 1],
+                'id': doc.id,
+                'text': doc.text,
+                'text_preview': doc.text[:100] + "..." if len(doc.text) > 100 else doc.text,
+                'category': doc.category,
+                'subcategory': doc.subcategory,
+                'tags_str': ', '.join(doc.tags) if doc.tags else 'None',
+                'dim_1': coordinates[i, 0],
+                'dim_2': coordinates[i, 1],
             }
-            if dimensions == "3d":
-                row["dim_3"] = coordinates[i, 2]
+            if dimensions == '3d':
+                row['dim_3'] = coordinates[i, 2]
             df_data.append(row)
-
-        return pd.DataFrame(df_data)
+        
+        return pd.DataFrame(df_data)

tests/test_bad_data.py

@@ -1,197 +0,0 @@
-"""Tests for handling bad/invalid data files."""
-
-import pytest
-import json
-import base64
-from src.embeddingbuddy.data.parser import NDJSONParser
-from src.embeddingbuddy.data.processor import DataProcessor
-
-
-class TestBadDataHandling:
-    """Test suite for various types of invalid input data."""
-
-    def setup_method(self):
-        """Set up test fixtures."""
-        self.parser = NDJSONParser()
-        self.processor = DataProcessor()
-
-    def _create_upload_contents(self, text_content: str) -> str:
-        """Helper to create upload contents format."""
-        encoded = base64.b64encode(text_content.encode("utf-8")).decode("utf-8")
-        return f"data:application/json;base64,{encoded}"
-
-    def test_missing_embedding_field(self):
-        """Test files missing required embedding field."""
-        bad_content = '{"id": "doc_001", "text": "Sample text", "category": "test"}'
-
-        with pytest.raises(KeyError, match="embedding"):
-            self.parser.parse_text(bad_content)
-
-        # Test processor error handling
-        upload_contents = self._create_upload_contents(bad_content)
-        result = self.processor.process_upload(upload_contents)
-        assert result.error is not None
-        assert "embedding" in result.error
-
-    def test_missing_text_field(self):
-        """Test files missing required text field."""
-        bad_content = (
-            '{"id": "doc_001", "embedding": [0.1, 0.2, 0.3], "category": "test"}'
-        )
-
-        with pytest.raises(KeyError, match="text"):
-            self.parser.parse_text(bad_content)
-
-        # Test processor error handling
-        upload_contents = self._create_upload_contents(bad_content)
-        result = self.processor.process_upload(upload_contents)
-        assert result.error is not None
-        assert "text" in result.error
-
-    def test_malformed_json_lines(self):
-        """Test files with malformed JSON syntax."""
-        # Missing closing brace
-        bad_content = '{"id": "doc_001", "embedding": [0.1, 0.2], "text": "test"'
-
-        with pytest.raises(json.JSONDecodeError):
-            self.parser.parse_text(bad_content)
-
-        # Test processor error handling
-        upload_contents = self._create_upload_contents(bad_content)
-        result = self.processor.process_upload(upload_contents)
-        assert result.error is not None
-
-    def test_invalid_embedding_types(self):
-        """Test files with invalid embedding data types."""
-        test_cases = [
-            # String instead of array
-            '{"id": "doc_001", "embedding": "not_an_array", "text": "test"}',
-            # Mixed types in array
-            '{"id": "doc_002", "embedding": [0.1, "text", 0.3], "text": "test"}',
-            # Empty array
-            '{"id": "doc_003", "embedding": [], "text": "test"}',
-            # Null embedding
-            '{"id": "doc_004", "embedding": null, "text": "test"}',
-        ]
-
-        for bad_content in test_cases:
-            upload_contents = self._create_upload_contents(bad_content)
-            result = self.processor.process_upload(upload_contents)
-            assert result.error is not None, f"Should fail for: {bad_content}"
-
-    def test_inconsistent_embedding_dimensions(self):
-        """Test files with embeddings of different dimensions."""
-        bad_content = """{"id": "doc_001", "embedding": [0.1, 0.2, 0.3, 0.4], "text": "4D embedding"}
-{"id": "doc_002", "embedding": [0.1, 0.2, 0.3], "text": "3D embedding"}"""
-
-        upload_contents = self._create_upload_contents(bad_content)
-        result = self.processor.process_upload(upload_contents)
-
-        # This might succeed parsing but fail in processing
-        # The error depends on where dimension validation occurs
-        if result.error is None:
-            # If parsing succeeds, check that embeddings have inconsistent shapes
-            assert len(result.documents) == 2
-            assert len(result.documents[0].embedding) != len(
-                result.documents[1].embedding
-            )
-
-    def test_empty_lines_in_ndjson(self):
-        """Test files with empty lines mixed in."""
-        content_with_empty_lines = """{"id": "doc_001", "embedding": [0.1, 0.2], "text": "First line"}
-
-{"id": "doc_002", "embedding": [0.3, 0.4], "text": "After empty line"}"""
-
-        # This should work - empty lines should be skipped
-        documents = self.parser.parse_text(content_with_empty_lines)
-        assert len(documents) == 2
-        assert documents[0].id == "doc_001"
-        assert documents[1].id == "doc_002"
-
-    def test_not_ndjson_format(self):
-        """Test regular JSON array instead of NDJSON."""
-        json_array = """[
-  {"id": "doc_001", "embedding": [0.1, 0.2], "text": "First"},
-  {"id": "doc_002", "embedding": [0.3, 0.4], "text": "Second"}
-]"""
-
-        with pytest.raises(json.JSONDecodeError):
-            self.parser.parse_text(json_array)
-
-    def test_binary_content_in_file(self):
-        """Test files with binary content mixed in."""
-        # Simulate binary content that can't be decoded
-        binary_content = (
-            b'\x00\x01\x02{"id": "doc_001", "embedding": [0.1], "text": "test"}'
-        )
-
-        # This should result in an error when processing
-        encoded = base64.b64encode(binary_content).decode("utf-8")
-        upload_contents = f"data:application/json;base64,{encoded}"
-        result = self.processor.process_upload(upload_contents)
-
-        # Should either fail with UnicodeDecodeError or JSON parsing error
-        assert result.error is not None
-
-    def test_extremely_large_embeddings(self):
-        """Test embeddings with very large dimensions."""
-        large_embedding = [0.1] * 10000  # 10k dimensions
-        content = json.dumps(
-            {
-                "id": "doc_001",
-                "embedding": large_embedding,
-                "text": "Large embedding test",
-            }
-        )
-
-        # This should work but might be slow
-        upload_contents = self._create_upload_contents(content)
-        result = self.processor.process_upload(upload_contents)
-
-        if result.error is None:
-            assert len(result.documents) == 1
-            assert len(result.documents[0].embedding) == 10000
-
-    def test_special_characters_in_text(self):
-        """Test handling of special characters and unicode."""
-        special_content = json.dumps(
-            {
-                "id": "doc_001",
-                "embedding": [0.1, 0.2],
-                "text": 'Special chars: 🚀 ñoñó 中文 \n\t"',
-            },
-            ensure_ascii=False,
-        )
-
-        upload_contents = self._create_upload_contents(special_content)
-        result = self.processor.process_upload(upload_contents)
-
-        assert result.error is None
-        assert len(result.documents) == 1
-        assert "🚀" in result.documents[0].text
-
-    def test_processor_error_structure(self):
-        """Test that processor returns proper error structure."""
-        bad_content = '{"invalid": "json"'  # Missing closing brace
-        upload_contents = self._create_upload_contents(bad_content)
-
-        result = self.processor.process_upload(upload_contents)
-
-        # Check error structure
-        assert result.error is not None
-        assert isinstance(result.error, str)
-        assert len(result.documents) == 0
-        assert result.embeddings.size == 0
-
-    def test_multiple_errors_in_file(self):
-        """Test file with multiple different types of errors."""
-        multi_error_content = """{"id": "doc_001", "text": "Missing embedding"}
-{"id": "doc_002", "embedding": "wrong_type", "text": "Wrong embedding type"}
-{"id": "doc_003", "embedding": [0.1, 0.2], "text": "Valid line"}
-{"id": "doc_004", "embedding": [0.3, 0.4]"""  # Missing text and closing brace
-
-        upload_contents = self._create_upload_contents(multi_error_content)
-        result = self.processor.process_upload(upload_contents)
-
-        # Should fail on first error encountered
-        assert result.error is not None

tests/test_data_processing.py

@@ -6,64 +6,62 @@ 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
@@ -72,4 +70,4 @@ class TestDataProcessor:
 
 
 if __name__ == "__main__":
-    pytest.main([__file__])
+    pytest.main([__file__])

tests/test_reducers.py

@@ -1,90 +1,89 @@
 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__])