add workflow dispatch - v0.6.2

Reviewed-on: godber/embedding-buddy#7

.claude/settings.local.json

@@ -4,7 +4,9 @@
       "Bash(mkdir:*)",
       "Bash(uv run:*)",
       "Bash(uv add:*)",
-      "Bash(uv sync:*)"
+      "Bash(uv sync:*)",
+      "Bash(tree:*)",
+      "WebFetch(domain:www.dash-bootstrap-components.com)"
     ],
     "deny": [],
     "ask": [],

.gitea/workflows/release.yml

@@ -71,22 +71,15 @@ jobs:
           echo '```' >> release-notes.md
 
       - name: Create Release
-        uses: actions/create-release@v1
+        uses: akkuman/gitea-release-action@v1
         env:
-          GITHUB_TOKEN: ${{ secrets.GITEA_TOKEN }}
+          NODE_OPTIONS: '--experimental-fetch'
         with:
+          token: ${{ secrets.GITEA_TOKEN }}
           tag_name: ${{ github.ref_name || github.event.inputs.version }}
           release_name: Release ${{ github.ref_name || github.event.inputs.version }}
           body_path: release-notes.md
           draft: false
           prerelease: false
-
+          files: |-
-      - name: Upload Release Assets
+            dist/*
-        uses: actions/upload-release-asset@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITEA_TOKEN }}
-        with:
-          upload_url: ${{ steps.create_release.outputs.upload_url }}
-          asset_path: dist/
-          asset_name: embeddingbuddy-dist
-          asset_content_type: application/zip

.github/workflows/docker-release.yml

@@ -0,0 +1,54 @@
+name: Docker Release
+
+on:
+  push:
+    tags:
+      - 'v[0-9]+.[0-9]+.[0-9]+'
+  workflow_dispatch:
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=ref,event=tag
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

CLAUDE.md

@@ -22,11 +22,13 @@ uv sync
 **Run the application:**
 
 Development mode (with auto-reload):
+
 ```bash
 uv run run_dev.py
 ```
 
 Production mode (with Gunicorn WSGI server):
+
 ```bash
 # First install production dependencies
 uv sync --extra prod
@@ -36,11 +38,12 @@ uv run run_prod.py
 ```
 
 Legacy mode (basic Dash server):
+
 ```bash
 uv run main.py
 ```
 
-The app will be available at http://127.0.0.1:8050
+The app will be available at <http://127.0.0.1:8050>
 
 **Run tests:**
 

Dockerfile

@@ -2,6 +2,9 @@
 # Stage 1: Builder
 FROM python:3.11-slim as builder
 
+# Create non-root user early in builder stage
+RUN groupadd -r appuser && useradd -r -g appuser appuser
+
 # Install system dependencies for building Python packages
 RUN apt-get update && apt-get install -y \
     build-essential \
@@ -25,6 +28,15 @@ COPY wsgi.py .
 COPY run_prod.py .
 COPY assets/ assets/
 
+# Change ownership of source files before building (lighter I/O)
+RUN chown -R appuser:appuser /app
+
+# Create and set permissions for appuser home directory (needed for uv cache)
+RUN mkdir -p /home/appuser && chown -R appuser:appuser /home/appuser
+
+# Switch to non-root user before building
+USER appuser
+
 # Create virtual environment and install dependencies (including production extras)
 RUN uv venv .venv
 RUN uv sync --frozen --extra prod 
@@ -32,23 +44,28 @@ RUN uv sync --frozen --extra prod
 # Stage 2: Runtime
 FROM python:3.11-slim as runtime
 
+# Create non-root user in runtime stage
+RUN groupadd -r appuser && useradd -r -g appuser appuser
+
 # Install runtime dependencies for compiled packages
 RUN apt-get update && apt-get install -y \
     libgomp1 \
     && rm -rf /var/lib/apt/lists/*
 
-# Set working directory
+# Set working directory and change ownership (small directory)
 WORKDIR /app
+RUN chown appuser:appuser /app
 
-# Copy virtual environment from builder stage
+# Copy files from builder with correct ownership
-COPY --from=builder /app/.venv /app/.venv
+COPY --from=builder --chown=appuser:appuser /app/.venv /app/.venv
+COPY --from=builder --chown=appuser:appuser /app/src /app/src
+COPY --from=builder --chown=appuser:appuser /app/main.py /app/main.py
+COPY --from=builder --chown=appuser:appuser /app/assets /app/assets
+COPY --from=builder --chown=appuser:appuser /app/wsgi.py /app/wsgi.py
+COPY --from=builder --chown=appuser:appuser /app/run_prod.py /app/run_prod.py
 
-# Copy application files from builder stage
+# Switch to non-root user
-COPY --from=builder /app/src /app/src
+USER appuser
-COPY --from=builder /app/main.py /app/main.py
-COPY --from=builder /app/assets /app/assets
-COPY --from=builder /app/wsgi.py /app/wsgi.py
-COPY --from=builder /app/run_prod.py /app/run_prod.py
 
 # Make sure the virtual environment is in PATH
 ENV PATH="/app/.venv/bin:$PATH"

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Austin Godber - EmbeddingBuddy
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -152,22 +152,38 @@ The application follows a modular architecture for improved maintainability and
 
 ```text
 src/embeddingbuddy/
-├── config/          # Configuration management
+├── app.py                     # Main application entry point and factory
-│   └── settings.py  # Centralized app settings
+├── config/                    # Configuration management
-├── data/           # Data parsing and processing
+│   └── settings.py            # Centralized app settings
-│   ├── parser.py   # NDJSON parsing logic
+├── data/                      # Data parsing and processing
-│   └── processor.py # Data transformation utilities
+│   ├── parser.py              # NDJSON parsing logic
-├── models/         # Data schemas and algorithms
+│   ├── processor.py           # Data transformation utilities
-│   ├── schemas.py  # Pydantic data models
+│   └── sources/               # Data source integrations
-│   └── reducers.py # Dimensionality reduction algorithms
+│       └── opensearch.py      # OpenSearch data source
-├── visualization/ # Plot creation and styling
+├── models/                    # Data schemas and algorithms
-│   ├── plots.py   # Plot factory and creation logic
+│   ├── schemas.py             # Pydantic data models
-│   └── colors.py  # Color mapping utilities
+│   ├── reducers.py            # Dimensionality reduction algorithms
-├── ui/            # User interface components
+│   └── field_mapper.py        # Field mapping utilities
-│   ├── layout.py  # Main application layout
+├── visualization/             # Plot creation and styling
-│   ├── components/ # Reusable UI components
+│   ├── plots.py               # Plot factory and creation logic
-│   └── callbacks/ # Organized callback functions
+│   └── colors.py              # Color mapping utilities
-└── utils/         # Utility functions
+├── ui/                        # User interface components
+│   ├── layout.py              # Main application layout
+│   ├── components/            # Reusable UI components
+│   │   ├── sidebar.py         # Sidebar component
+│   │   ├── upload.py          # Upload components
+│   │   ├── textinput.py       # Text input components
+│   │   └── datasource.py      # Data source components
+│   └── callbacks/             # Organized callback functions
+│       ├── data_processing.py # Data upload/processing callbacks
+│       ├── visualization.py   # Plot update callbacks
+│       └── interactions.py    # User interaction callbacks
+└── utils/                     # Utility functions
+
+main.py            # Application runner (at project root)
+main.py            # Application runner (at project root)
+run_dev.py         # Development server runner
+run_prod.py        # Production server runner
 ```
 
 ### Testing

assets/custom.css

@@ -0,0 +1,17 @@
+/* CSS override for transparent hover boxes in Plotly plots */
+
+/* Make hover boxes transparent while preserving text readability */
+.hovertext {
+    fill-opacity: 0.8 !important;
+    stroke-opacity: 1 !important;
+}
+
+/* Alternative selector for different Plotly versions */
+g.hovertext > path {
+    opacity: 0.8 !important;
+}
+
+/* Ensure text remains fully visible */
+.hovertext text {
+    opacity: 1 !important;
+}

assets/embeddings.js

@@ -45,28 +45,12 @@ class TransformersEmbedder {
                 console.log('✅ Using globally loaded Transformers.js pipeline');
             }
             
-            // Show loading progress to user
+            this.extractor = await window.transformers.pipeline('feature-extraction', modelName);
-            if (window.updateModelLoadingProgress) {
+
-                window.updateModelLoadingProgress(0, `Loading ${modelName}...`);
-            }
-            
-            this.extractor = await window.transformers.pipeline('feature-extraction', modelName, {
-                progress_callback: (data) => {
-                    if (window.updateModelLoadingProgress && data.progress !== undefined) {
-                        const progress = Math.round(data.progress);
-                        window.updateModelLoadingProgress(progress, data.status || 'Loading...');
-                    }
-                }
-            });
-            
             this.modelCache.set(modelName, this.extractor);
             this.currentModel = modelName;
             this.isLoading = false;
-            
+
-            if (window.updateModelLoadingProgress) {
-                window.updateModelLoadingProgress(100, 'Model loaded successfully');
-            }
-            
             return { success: true, model: modelName };
         } catch (error) {
             this.isLoading = false;
@@ -116,17 +100,8 @@ class TransformersEmbedder {
                     }
                 });
                 
-                // Update progress
-                const progress = Math.min(100, ((i + batch.length) / texts.length) * 100);
-                if (window.updateEmbeddingProgress) {
-                    window.updateEmbeddingProgress(progress, `Processing ${i + batch.length}/${texts.length} texts`);
-                }
             }
-            
+
-            if (window.updateEmbeddingProgress) {
-                window.updateEmbeddingProgress(100, `Generated ${embeddings.length} embeddings successfully`);
-            }
-            
             return embeddings;
         } catch (error) {
             console.error('Embedding generation error:', error);
@@ -139,30 +114,6 @@ class TransformersEmbedder {
 window.transformersEmbedder = new TransformersEmbedder();
 console.log('📦 TransformersEmbedder instance created');
 
-// Global progress update functions
-window.updateModelLoadingProgress = function(progress, status) {
-    const progressBar = document.getElementById('model-loading-progress');
-    const statusText = document.getElementById('model-loading-status');
-    if (progressBar) {
-        progressBar.style.width = progress + '%';
-        progressBar.setAttribute('aria-valuenow', progress);
-    }
-    if (statusText) {
-        statusText.textContent = status;
-    }
-};
-
-window.updateEmbeddingProgress = function(progress, status) {
-    const progressBar = document.getElementById('embedding-progress');
-    const statusText = document.getElementById('embedding-status');
-    if (progressBar) {
-        progressBar.style.width = progress + '%';
-        progressBar.setAttribute('aria-valuenow', progress);
-    }
-    if (statusText) {
-        statusText.textContent = status;
-    }
-};
 
 // Dash clientside callback functions
 window.dash_clientside = window.dash_clientside || {};
@@ -170,31 +121,28 @@ console.log('🔧 Setting up window.dash_clientside.transformers');
 window.dash_clientside.transformers = {
     generateEmbeddings: async function(nClicks, textContent, modelName, tokenizationMethod, category, subcategory) {
         console.log('🚀 generateEmbeddings called with:', { nClicks, modelName, tokenizationMethod, textLength: textContent?.length });
-        
+
         if (!nClicks || !textContent || textContent.trim().length === 0) {
             console.log('⚠️ Early return - missing required parameters');
             return window.dash_clientside.no_update;
         }
-        
+
         try {
             // Initialize model if needed
             const initResult = await window.transformersEmbedder.initializeModel(modelName);
             if (!initResult.success) {
                 return [
-                    { error: initResult.error },
+                    { error: `Model loading error: ${initResult.error}` },
-                    `❌ Model loading error: ${initResult.error}`,
-                    "danger",
                     false
                 ];
             }
-            
+
             // Tokenize text based on method
             let textChunks;
             const trimmedText = textContent.trim();
-            
+
             switch (tokenizationMethod) {
                 case 'sentence':
-                    // Simple sentence splitting - can be enhanced with proper NLP
                     textChunks = trimmedText
                         .split(/[.!?]+/)
                         .map(s => s.trim())
@@ -215,28 +163,24 @@ window.dash_clientside.transformers = {
                 default:
                     textChunks = [trimmedText];
             }
-            
+
             if (textChunks.length === 0) {
                 return [
                     { error: 'No valid text chunks found after tokenization' },
-                    '❌ Error: No valid text chunks found after tokenization',
-                    "danger",
                     false
                 ];
             }
-            
+
             // Generate embeddings
             const embeddings = await window.transformersEmbedder.generateEmbeddings(textChunks);
-            
+
             if (!embeddings || embeddings.length !== textChunks.length) {
                 return [
-                    { error: 'Embedding generation failed - mismatch in text chunks and embeddings' },
+                    { error: 'Embedding generation failed' },
-                    '❌ Error: Embedding generation failed',
-                    "danger",
                     false
                 ];
             }
-            
+
             // Create documents structure
             const documents = textChunks.map((text, i) => ({
                 id: `text_input_${Date.now()}_${i}`,
@@ -246,33 +190,36 @@ window.dash_clientside.transformers = {
                 subcategory: subcategory || "Generated",
                 tags: []
             }));
-            
+
+            // Return the successful embeddings data
+            const embeddingsData = {
+                documents: documents,
+                embeddings: embeddings
+            };
+
+            console.log('✅ Embeddings generated successfully:', embeddingsData);
+
             return [
-                {
+                embeddingsData,
-                    documents: documents,
-                    embeddings: embeddings
-                },
-                `✅ Generated embeddings for ${documents.length} text chunks using ${modelName}`,
-                "success",
                 false
             ];
-            
+
         } catch (error) {
             console.error('Client-side embedding error:', error);
             return [
                 { error: error.message },
-                `❌ Error: ${error.message}`,
-                "danger", 
                 false
             ];
         }
     }
 };
 
+
 console.log('✅ Transformers.js client-side setup complete');
 console.log('Available:', {
     transformersEmbedder: !!window.transformersEmbedder,
     dashClientside: !!window.dash_clientside,
     transformersModule: !!window.dash_clientside?.transformers,
-    generateFunction: typeof window.dash_clientside?.transformers?.generateEmbeddings
+    generateFunction: typeof window.dash_clientside?.transformers?.generateEmbeddings,
+    processAsync: typeof window.processEmbeddingsAsync
 });

assets/transformers-loader.js

@@ -104,17 +104,28 @@ window.dash_clientside = window.dash_clientside || {};
 window.dash_clientside.transformers = {
     generateEmbeddings: async function(nClicks, textContent, modelName, tokenizationMethod, category, subcategory) {
         console.log('🚀 Client-side generateEmbeddings called');
-        
+
         if (!nClicks || !textContent || textContent.trim().length === 0) {
             console.log('⚠️ Missing required parameters');
             return window.dash_clientside.no_update;
         }
-        
+
         try {
+            // Ensure Transformers.js is loaded
+            if (!window.transformersLibraryLoaded) {
+                const loaded = await initializeTransformers();
+                if (!loaded) {
+                    return [
+                        { error: 'Failed to load Transformers.js' },
+                        false
+                    ];
+                }
+            }
+
             // Tokenize text
             let textChunks;
             const trimmedText = textContent.trim();
-            
+
             switch (tokenizationMethod) {
                 case 'sentence':
                     textChunks = trimmedText.split(/[.!?]+/).map(s => s.trim()).filter(s => s.length > 0);
@@ -128,45 +139,50 @@ window.dash_clientside.transformers = {
                 default:
                     textChunks = [trimmedText];
             }
-            
+
             if (textChunks.length === 0) {
-                throw new Error('No valid text chunks after tokenization');
+                return [
+                    { error: 'No valid text chunks after tokenization' },
+                    false
+                ];
             }
-            
+
             // Generate embeddings
             const embeddings = await window.simpleEmbedder.generateEmbeddings(textChunks, modelName);
-            
+
             // Create documents
             const documents = textChunks.map((text, i) => ({
                 id: `text_input_${Date.now()}_${i}`,
                 text: text,
                 embedding: embeddings[i],
                 category: category || "Text Input",
-                subcategory: subcategory || "Generated", 
+                subcategory: subcategory || "Generated",
                 tags: []
             }));
-            
+
+            // Return the successful embeddings data
+            const embeddingsData = {
+                documents: documents,
+                embeddings: embeddings
+            };
+
+            console.log('✅ Embeddings generated successfully:', embeddingsData);
+
             return [
-                {
+                embeddingsData,
-                    documents: documents,
-                    embeddings: embeddings
-                },
-                `✅ Generated embeddings for ${documents.length} text chunks using ${modelName}`,
-                "success",
                 false
             ];
-            
+
         } catch (error) {
             console.error('❌ Error generating embeddings:', error);
             return [
                 { error: error.message },
-                `❌ Error: ${error.message}`,
-                "danger",
                 false
             ];
         }
     }
 };
 
+
 console.log('✅ Simple Transformers.js setup complete');
 console.log('Available functions:', Object.keys(window.dash_clientside.transformers));

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "embeddingbuddy"
-version = "0.4.0"
+version = "0.6.2"
 description = "A Python Dash application for interactive exploration and visualization of embedding vectors through dimensionality reduction techniques."
 readme = "README.md"
 requires-python = ">=3.11"

run_dev.py

@@ -11,10 +11,16 @@ def main():
     # Force development settings
     os.environ["EMBEDDINGBUDDY_ENV"] = "development"
     os.environ["EMBEDDINGBUDDY_DEBUG"] = "true"
+
+    # Check for OpenSearch disable flag (optional for testing)
+    # Set EMBEDDINGBUDDY_OPENSEARCH_ENABLED=false to test without OpenSearch
+    opensearch_status = os.getenv("EMBEDDINGBUDDY_OPENSEARCH_ENABLED", "true")
+    opensearch_enabled = opensearch_status.lower() == "true"
     
     print("🚀 Starting EmbeddingBuddy in development mode...")
     print("📁 Auto-reload enabled - changes will trigger restart")
     print("🌐 Server will be available at http://127.0.0.1:8050")
+    print(f"🔍 OpenSearch: {'Enabled' if opensearch_enabled else 'Disabled'}")
     print("⏹️  Press Ctrl+C to stop")
     
     app = create_app()

run_prod.py

@@ -13,6 +13,9 @@ def main():
     # Force production settings
     os.environ["EMBEDDINGBUDDY_ENV"] = "production"
     os.environ["EMBEDDINGBUDDY_DEBUG"] = "false"
+    # Disable OpenSearch by default in production (can be overridden by setting env var)
+    if "EMBEDDINGBUDDY_OPENSEARCH_ENABLED" not in os.environ:
+        os.environ["EMBEDDINGBUDDY_OPENSEARCH_ENABLED"] = "false"
     
     print("🚀 Starting EmbeddingBuddy in production mode...")
     print(f"⚙️  Workers: {AppSettings.GUNICORN_WORKERS}")
@@ -25,7 +28,7 @@ def main():
         "--workers", str(AppSettings.GUNICORN_WORKERS),
         "--bind", AppSettings.GUNICORN_BIND,
         "--timeout", str(AppSettings.GUNICORN_TIMEOUT),
-        "--keepalive", str(AppSettings.GUNICORN_KEEPALIVE),
+        "--keep-alive", str(AppSettings.GUNICORN_KEEPALIVE),
         "--access-logfile", "-",
         "--error-logfile", "-",
         "--log-level", "info",

src/embeddingbuddy/app.py

@@ -15,7 +15,34 @@ def create_app():
     assets_path = os.path.join(project_root, "assets")
 
     app = dash.Dash(
-        __name__, external_stylesheets=[dbc.themes.BOOTSTRAP], assets_folder=assets_path
+        __name__,
+        title="EmbeddingBuddy",
+        external_stylesheets=[
+            dbc.themes.BOOTSTRAP,
+            "https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css",
+        ],
+        assets_folder=assets_path,
+        meta_tags=[
+            {
+                "name": "description",
+                "content": "Interactive embedding visualization tool for exploring high-dimensional vectors through dimensionality reduction techniques like PCA, t-SNE, and UMAP.",
+            },
+            {"name": "author", "content": "EmbeddingBuddy"},
+            {
+                "name": "keywords",
+                "content": "embeddings, visualization, dimensionality reduction, PCA, t-SNE, UMAP, machine learning, data science",
+            },
+            {"name": "viewport", "content": "width=device-width, initial-scale=1.0"},
+            {
+                "property": "og:title",
+                "content": "EmbeddingBuddy - Interactive Embedding Visualization",
+            },
+            {
+                "property": "og:description",
+                "content": "Explore and visualize embedding vectors through interactive 2D/3D plots with multiple dimensionality reduction techniques.",
+            },
+            {"property": "og:type", "content": "website"},
+        ],
     )
 
     # Allow callbacks to components that are dynamically created in tabs
@@ -45,22 +72,22 @@ def _register_client_side_callbacks(app):
             if (!nClicks || !textContent || !textContent.trim()) {
                 return window.dash_clientside.no_update;
             }
-            
+
             console.log('🔍 Checking for Transformers.js...');
             console.log('window.dash_clientside:', typeof window.dash_clientside);
             console.log('window.dash_clientside.transformers:', typeof window.dash_clientside?.transformers);
             console.log('generateEmbeddings function:', typeof window.dash_clientside?.transformers?.generateEmbeddings);
-            
+
-            if (typeof window.dash_clientside !== 'undefined' && 
+            if (typeof window.dash_clientside !== 'undefined' &&
                 typeof window.dash_clientside.transformers !== 'undefined' &&
                 typeof window.dash_clientside.transformers.generateEmbeddings === 'function') {
-                
+
                 console.log('✅ Calling Transformers.js generateEmbeddings...');
                 return window.dash_clientside.transformers.generateEmbeddings(
                     nClicks, textContent, modelName, tokenizationMethod, category, subcategory
                 );
             }
-            
+
             // More detailed error information
             let errorMsg = '❌ Transformers.js not available. ';
             if (typeof window.dash_clientside === 'undefined') {
@@ -70,21 +97,17 @@ def _register_client_side_callbacks(app):
             } else if (typeof window.dash_clientside.transformers.generateEmbeddings !== 'function') {
                 errorMsg += 'generateEmbeddings function not found.';
             }
-            
+
             console.error(errorMsg);
-            
+
             return [
                 { error: 'Transformers.js not loaded. Please refresh the page and try again.' },
-                errorMsg + ' Please refresh the page.',
-                'danger',
                 false
             ];
         }
         """,
         [
             Output("embeddings-generated-trigger", "data"),
-            Output("text-input-status-immediate", "children"),
-            Output("text-input-status-immediate", "color"),
             Output("generate-embeddings-btn", "disabled", allow_duplicate=True),
         ],
         [Input("generate-embeddings-btn", "n_clicks")],

src/embeddingbuddy/config/settings.py

@@ -72,10 +72,12 @@ class AppSettings:
     DEBUG = os.getenv("EMBEDDINGBUDDY_DEBUG", "True").lower() == "true"
     HOST = os.getenv("EMBEDDINGBUDDY_HOST", "127.0.0.1")
     PORT = int(os.getenv("EMBEDDINGBUDDY_PORT", "8050"))
-    
+
     # Environment Configuration
-    ENVIRONMENT = os.getenv("EMBEDDINGBUDDY_ENV", "development")  # development, production
+    ENVIRONMENT = os.getenv(
-    
+        "EMBEDDINGBUDDY_ENV", "development"
+    )  # development, production
+
     # WSGI Server Configuration (for production)
     GUNICORN_WORKERS = int(os.getenv("GUNICORN_WORKERS", "4"))
     GUNICORN_BIND = os.getenv("GUNICORN_BIND", f"{HOST}:{PORT}")
@@ -83,6 +85,9 @@ class AppSettings:
     GUNICORN_KEEPALIVE = int(os.getenv("GUNICORN_KEEPALIVE", "5"))
 
     # OpenSearch Configuration
+    OPENSEARCH_ENABLED = (
+        os.getenv("EMBEDDINGBUDDY_OPENSEARCH_ENABLED", "True").lower() == "true"
+    )
     OPENSEARCH_DEFAULT_SIZE = 100
     OPENSEARCH_SAMPLE_SIZE = 5
     OPENSEARCH_CONNECTION_TIMEOUT = 30

src/embeddingbuddy/ui/callbacks/data_processing.py

@@ -82,19 +82,23 @@ class DataProcessingCallbacks:
         )
         def render_tab_content(active_tab):
             from ...ui.components.datasource import DataSourceComponent
+            from ...config.settings import AppSettings
 
             datasource = DataSourceComponent()
 
-            if active_tab == "opensearch-tab":
+            if active_tab == "opensearch-tab" and AppSettings.OPENSEARCH_ENABLED:
                 return [datasource.create_opensearch_tab()]
             elif active_tab == "text-input-tab":
                 return [datasource.create_text_input_tab()]
             else:
                 return [datasource.create_file_upload_tab()]
 
-        # Register callbacks for both data and prompts sections
+        # Register callbacks for both data and prompts sections (only if OpenSearch is enabled)
-        self._register_opensearch_callbacks("data", self.opensearch_client_data)
+        if AppSettings.OPENSEARCH_ENABLED:
-        self._register_opensearch_callbacks("prompts", self.opensearch_client_prompts)
+            self._register_opensearch_callbacks("data", self.opensearch_client_data)
+            self._register_opensearch_callbacks(
+                "prompts", self.opensearch_client_prompts
+            )
 
         # Register collapsible section callbacks
         self._register_collapse_callbacks()
@@ -621,6 +625,12 @@ class DataProcessingCallbacks:
             if not embeddings_data:
                 return no_update, no_update, no_update, no_update, no_update
 
+            # Check if this is a request trigger (contains textContent) vs actual embeddings data
+            if isinstance(embeddings_data, dict) and "textContent" in embeddings_data:
+                # This is a processing request trigger, not the actual results
+                # The JavaScript will handle the async processing and update the UI directly
+                return no_update, no_update, no_update, no_update, no_update
+
             processed_data = self.processor.process_client_embeddings(embeddings_data)
 
             if processed_data.error:

src/embeddingbuddy/ui/callbacks/interactions.py

@@ -1,6 +1,5 @@
 import dash
-from dash import callback, Input, Output, State, html
+from dash import callback, Input, Output
-import dash_bootstrap_components as dbc
 
 
 class InteractionCallbacks:
@@ -9,74 +8,25 @@ class InteractionCallbacks:
 
     def _register_callbacks(self):
         @callback(
-            Output("point-details", "children"),
+            Output("about-modal", "is_open"),
-            Input("embedding-plot", "clickData"),
+            [Input("about-button", "n_clicks"), Input("about-modal-close", "n_clicks")],
-            [State("processed-data", "data"), State("processed-prompts", "data")],
+            prevent_initial_call=True,
         )
-        def display_click_data(clickData, data, prompts_data):
+        def toggle_about_modal(about_clicks, close_clicks):
-            if not clickData or not data:
+            if about_clicks or close_clicks:
-                return "Click on a point to see details"
+                return True if about_clicks else False
-
+            return False
-            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"
-            else:
-                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,
         )
         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 dash.no_update, dash.no_update
 
-            return None, None, "Click on a point to see details"
+            return None, None
-
-    @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"),
-                    ]
-                )
-            ]
-        )

src/embeddingbuddy/ui/components/about.py

@@ -0,0 +1,90 @@
+from dash import html, dcc
+import dash_bootstrap_components as dbc
+
+
+class AboutComponent:
+    def _get_about_content(self):
+        return """
+# 🔍 Interactive Embedding Vector Visualization
+
+EmbeddingBuddy is a web application for interactive exploration and
+visualization of embedding vectors through dimensionality reduction techniques
+(PCA, t-SNE, UMAP).
+
+You have two ways to get started:
+
+1. Generate embeddings directly in the browser if it supports WebGPU.
+2. Upload your NDJSON file containing embedding vectors and metadata.
+
+## Generating Embeddings in Browser
+
+1. Expand the "Generate Embeddings" section.
+2. Input your text data (one entry per line).
+    1. Optionally you can use the built in sample data by clicking "Load Sample Data" button.
+3. Click "Generate Embeddings" to create vectors using a pre-trained model.
+
+## NDJSON File Format
+
+```json
+{"id": "doc_001", "embedding": [0.1, -0.3, 0.7, ...], "text": "Sample text content", "category": "news", "subcategory": "politics", "tags": ["election", "politics"]}
+{"id": "doc_002", "embedding": [0.2, -0.1, 0.9, ...], "text": "Another example", "category": "review", "subcategory": "product", "tags": ["tech", "gadget"]}
+```
+
+
+## ✨ Features
+
+- Drag-and-drop NDJSON file upload
+- Multiple dimensionality reduction algorithms
+- 2D/3D interactive plots with Plotly
+- Color coding by categories, subcategories, or tags
+- In-browser embedding generation
+- OpenSearch integration for data loading
+
+## 🔧 Supported Algorithms
+
+- **PCA** (Principal Component Analysis)
+- **t-SNE** (t-Distributed Stochastic Neighbor Embedding)
+- **UMAP** (Uniform Manifold Approximation and Projection)
+
+---
+
+📂 [View on GitHub](https://github.com/godber/EmbeddingBuddy)
+
+*Built with: Python, Dash, Plotly, scikit-learn, OpenTSNE, UMAP*
+        """.strip()
+
+    def create_about_modal(self):
+        return dbc.Modal(
+            [
+                dbc.ModalHeader(
+                    dbc.ModalTitle("Welcome to EmbeddingBuddy"),
+                    close_button=True,
+                ),
+                dbc.ModalBody(
+                    [dcc.Markdown(self._get_about_content(), className="mb-0")]
+                ),
+                dbc.ModalFooter(
+                    [
+                        dbc.Button(
+                            "Close",
+                            id="about-modal-close",
+                            color="secondary",
+                            n_clicks=0,
+                        )
+                    ]
+                ),
+            ],
+            id="about-modal",
+            is_open=True,
+            size="lg",
+        )
+
+    def create_about_button(self):
+        return dbc.Button(
+            [html.I(className="fas fa-info-circle me-2"), "About"],
+            id="about-button",
+            color="outline-info",
+            size="sm",
+            n_clicks=0,
+            className="ms-2",
+        )

src/embeddingbuddy/ui/components/datasource.py

@@ -1,26 +1,27 @@
 from dash import dcc, html
 import dash_bootstrap_components as dbc
 from .upload import UploadComponent
-from .textinput import TextInputComponent
+from embeddingbuddy.config.settings import AppSettings
 
 
 class DataSourceComponent:
     def __init__(self):
         self.upload_component = UploadComponent()
-        self.text_input_component = TextInputComponent()
 
     def create_tabbed_interface(self):
         """Create tabbed interface for different data sources."""
+        tabs = [dbc.Tab(label="File Upload", tab_id="file-tab")]
+
+        # Only add OpenSearch tab if enabled
+        if AppSettings.OPENSEARCH_ENABLED:
+            tabs.append(dbc.Tab(label="OpenSearch", tab_id="opensearch-tab"))
+
         return dbc.Card(
             [
                 dbc.CardHeader(
                     [
                         dbc.Tabs(
-                            [
+                            tabs,
-                                dbc.Tab(label="File Upload", tab_id="file-tab"),
-                                dbc.Tab(label="OpenSearch", tab_id="opensearch-tab"),
-                                dbc.Tab(label="Text Input", tab_id="text-input-tab"),
-                            ],
                             id="data-source-tabs",
                             active_tab="file-tab",
                         )
@@ -211,10 +212,6 @@ class DataSourceComponent:
             ]
         )
 
-    def create_text_input_tab(self):
-        """Create text input tab content for browser-based embedding generation."""
-        return html.Div([self.text_input_component.create_text_input_interface()])
-
     def _create_opensearch_section(self, section_type):
         """Create a complete OpenSearch section for either 'data' or 'prompts'."""
         section_id = section_type  # 'data' or 'prompts'

src/embeddingbuddy/ui/components/sidebar.py

@@ -2,31 +2,27 @@ from dash import dcc, html
 import dash_bootstrap_components as dbc
 from .upload import UploadComponent
 from .datasource import DataSourceComponent
+from .textinput import TextInputComponent
+from embeddingbuddy.config.settings import AppSettings
 
 
 class SidebarComponent:
     def __init__(self):
         self.upload_component = UploadComponent()
         self.datasource_component = DataSourceComponent()
+        self.textinput_component = TextInputComponent()
 
     def create_layout(self):
         return dbc.Col(
             [
-                html.H5("Data Sources", className="mb-3"),
+                dbc.Accordion(
-                self.datasource_component.create_error_alert(),
+                    [
-                self.datasource_component.create_success_alert(),
+                        self._create_data_sources_item(),
-                self.datasource_component.create_tabbed_interface(),
+                        self._create_generate_embeddings_item(),
-                html.H5("Visualization Controls", className="mb-3 mt-4"),
+                        self._create_visualization_controls_item(),
-            ]
+                    ],
-            + self._create_method_dropdown()
+                    always_open=True,
-            + 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"},
@@ -86,3 +82,67 @@ class SidebarComponent:
                 style={"margin-bottom": "20px"},
             ),
         ]
+
+    def _create_generate_embeddings_item(self):
+        return dbc.AccordionItem(
+            [
+                self.textinput_component.create_text_input_interface(),
+            ],
+            title=html.Span(
+                [
+                    "Generate Embeddings ",
+                    html.I(
+                        className="fas fa-info-circle text-muted",
+                        style={"cursor": "pointer"},
+                        id="generate-embeddings-info-icon",
+                        title="Create new embeddings from text input using various in-browser models",
+                    ),
+                ]
+            ),
+            item_id="generate-embeddings-accordion",
+        )
+
+    def _create_data_sources_item(self):
+        tooltip_text = "Load existing embeddings: upload files"
+        if AppSettings.OPENSEARCH_ENABLED:
+            tooltip_text += " or read from OpenSearch"
+
+        return dbc.AccordionItem(
+            [
+                self.datasource_component.create_error_alert(),
+                self.datasource_component.create_success_alert(),
+                self.datasource_component.create_tabbed_interface(),
+            ],
+            title=html.Span(
+                [
+                    "Load Embeddings ",
+                    html.I(
+                        className="fas fa-info-circle text-muted",
+                        style={"cursor": "pointer"},
+                        id="load-embeddings-info-icon",
+                        title=tooltip_text,
+                    ),
+                ]
+            ),
+            item_id="data-sources-accordion",
+        )
+
+    def _create_visualization_controls_item(self):
+        return dbc.AccordionItem(
+            self._create_method_dropdown()
+            + self._create_color_dropdown()
+            + self._create_dimension_toggle()
+            + self._create_prompts_toggle(),
+            title=html.Span(
+                [
+                    "Visualization Controls ",
+                    html.I(
+                        className="fas fa-info-circle text-muted",
+                        style={"cursor": "pointer"},
+                        id="visualization-controls-info-icon",
+                        title="Configure plot settings: select dimensionality reduction method, colors, and display options",
+                    ),
+                ]
+            ),
+            item_id="visualization-controls-accordion",
+        )

src/embeddingbuddy/ui/components/textinput.py

@@ -16,23 +16,20 @@ class TextInputComponent:
         """Create the complete text input interface with model selection and processing options."""
         return html.Div(
             [
-                # Model selection section
-                self._create_model_selection(),
-                html.Hr(),
                 # Text input section
                 self._create_text_input_area(),
                 # Text action buttons
                 self._create_text_action_buttons(),
                 html.Hr(),
+                # Model selection section
+                self._create_model_selection(),
+                html.Hr(),
                 # Processing options
                 self._create_processing_options(),
                 html.Hr(),
                 # Generation controls
                 self._create_generation_controls(),
                 html.Hr(),
-                # Progress indicators
-                self._create_progress_indicators(),
-                html.Hr(),
                 # Status and results
                 self._create_status_section(),
                 # Hidden components for data flow
@@ -297,65 +294,10 @@ class TextInputComponent:
             ]
         )
 
-    def _create_progress_indicators(self):
-        """Create progress bars for model loading and embedding generation."""
-        return html.Div(
-            [
-                # Model loading progress
-                html.Div(
-                    [
-                        html.H6("Model Loading Progress", className="mb-2"),
-                        dbc.Progress(
-                            id="model-loading-progress",
-                            value=0,
-                            striped=True,
-                            animated=True,
-                            className="mb-2",
-                        ),
-                        html.Small(
-                            id="model-loading-status",
-                            children="No model loading in progress",
-                            className="text-muted",
-                        ),
-                    ],
-                    id="model-loading-section",
-                    style={"display": "none"},
-                ),
-                html.Br(),
-                # Embedding generation progress
-                html.Div(
-                    [
-                        html.H6("Embedding Generation Progress", className="mb-2"),
-                        dbc.Progress(
-                            id="embedding-progress",
-                            value=0,
-                            striped=True,
-                            animated=True,
-                            className="mb-2",
-                        ),
-                        html.Small(
-                            id="embedding-status",
-                            children="No embedding generation in progress",
-                            className="text-muted",
-                        ),
-                    ],
-                    id="embedding-progress-section",
-                    style={"display": "none"},
-                ),
-            ]
-        )
-
     def _create_status_section(self):
         """Create status alerts and results preview."""
         return html.Div(
             [
-                # Immediate status (from client-side)
-                dbc.Alert(
-                    id="text-input-status-immediate",
-                    children="Ready to generate embeddings",
-                    color="light",
-                    className="mb-3",
-                ),
                 # Server-side status
                 dbc.Alert(
                     id="text-input-status",

src/embeddingbuddy/ui/components/upload.py

@@ -5,39 +5,75 @@ import dash_bootstrap_components as dbc
 class UploadComponent:
     @staticmethod
     def create_data_upload():
-        return dcc.Upload(
+        return html.Div(
-            id="upload-data",
+            [
-            children=html.Div(["Drag and Drop or ", html.A("Select Files")]),
+                dcc.Upload(
-            style={
+                    id="upload-data",
-                "width": "100%",
+                    children=html.Div(
-                "height": "60px",
+                        [
-                "lineHeight": "60px",
+                            "Upload Data ",
-                "borderWidth": "1px",
+                            html.I(
-                "borderStyle": "dashed",
+                                className="fas fa-info-circle",
-                "borderRadius": "5px",
+                                style={"color": "#6c757d", "fontSize": "14px"},
-                "textAlign": "center",
+                                id="data-upload-info",
-                "margin-bottom": "20px",
+                            ),
-            },
+                        ]
-            multiple=False,
+                    ),
+                    style={
+                        "width": "100%",
+                        "height": "60px",
+                        "lineHeight": "60px",
+                        "borderWidth": "1px",
+                        "borderStyle": "dashed",
+                        "borderRadius": "5px",
+                        "textAlign": "center",
+                        "margin-bottom": "20px",
+                    },
+                    multiple=False,
+                ),
+                dbc.Tooltip(
+                    "Click here or drag and drop NDJSON files containing document embeddings",
+                    target="data-upload-info",
+                    placement="top",
+                ),
+            ]
         )
 
     @staticmethod
     def create_prompts_upload():
-        return dcc.Upload(
+        return html.Div(
-            id="upload-prompts",
+            [
-            children=html.Div(["Drag and Drop Prompts or ", html.A("Select Files")]),
+                dcc.Upload(
-            style={
+                    id="upload-prompts",
-                "width": "100%",
+                    children=html.Div(
-                "height": "60px",
+                        [
-                "lineHeight": "60px",
+                            "Upload Prompts ",
-                "borderWidth": "1px",
+                            html.I(
-                "borderStyle": "dashed",
+                                className="fas fa-info-circle",
-                "borderRadius": "5px",
+                                style={"color": "#6c757d", "fontSize": "14px"},
-                "textAlign": "center",
+                                id="prompts-upload-info",
-                "margin-bottom": "20px",
+                            ),
-                "borderColor": "#28a745",
+                        ]
-            },
+                    ),
-            multiple=False,
+                    style={
+                        "width": "100%",
+                        "height": "60px",
+                        "lineHeight": "60px",
+                        "borderWidth": "1px",
+                        "borderStyle": "dashed",
+                        "borderRadius": "5px",
+                        "textAlign": "center",
+                        "margin-bottom": "20px",
+                        "borderColor": "#28a745",
+                    },
+                    multiple=False,
+                ),
+                dbc.Tooltip(
+                    "Click here or drag and drop NDJSON files containing prompt embeddings",
+                    target="prompts-upload-info",
+                    placement="top",
+                ),
+            ]
         )
 
     @staticmethod

src/embeddingbuddy/ui/layout.py

@@ -1,16 +1,19 @@
 from dash import dcc, html
 import dash_bootstrap_components as dbc
 from .components.sidebar import SidebarComponent
+from .components.about import AboutComponent
 
 
 class AppLayout:
     def __init__(self):
         self.sidebar = SidebarComponent()
+        self.about = AboutComponent()
 
     def create_layout(self):
         return dbc.Container(
             [self._create_header(), self._create_main_content()]
-            + self._create_stores(),
+            + self._create_stores()
+            + [self.about.create_about_modal()],
             fluid=True,
         )
 
@@ -19,7 +22,19 @@ class AppLayout:
             [
                 dbc.Col(
                     [
-                        html.H1("EmbeddingBuddy", className="text-center mb-4"),
+                        html.Div(
+                            [
+                                html.H1(
+                                    "EmbeddingBuddy",
+                                    className="text-center mb-4 d-inline",
+                                ),
+                                html.Div(
+                                    [self.about.create_about_button()],
+                                    className="float-end",
+                                ),
+                            ],
+                            className="d-flex justify-content-between align-items-center",
+                        ),
                         # Load Transformers.js from CDN
                         html.Script(
                             """

src/embeddingbuddy/visualization/plots.py

@@ -38,9 +38,9 @@ class PlotFactory:
         if dimensions == "3d":
             fig = px.scatter_3d(
                 df,
-                x="dim_1",
+                x="x",
-                y="dim_2",
+                y="y",
-                z="dim_3",
+                z="z",
                 color=color_values,
                 hover_data=hover_fields,
                 title=f"3D Embedding Visualization - {method} (colored by {color_by})",
@@ -49,8 +49,8 @@ class PlotFactory:
         else:
             fig = px.scatter(
                 df,
-                x="dim_1",
+                x="x",
-                y="dim_2",
+                y="y",
                 color=color_values,
                 hover_data=hover_fields,
                 title=f"2D Embedding Visualization - {method} (colored by {color_by})",
@@ -77,17 +77,17 @@ class PlotFactory:
         if dimensions == "3d":
             doc_fig = px.scatter_3d(
                 doc_df,
-                x="dim_1",
+                x="x",
-                y="dim_2",
+                y="y",
-                z="dim_3",
+                z="z",
                 color=doc_color_values,
                 hover_data=hover_fields,
             )
         else:
             doc_fig = px.scatter(
                 doc_df,
-                x="dim_1",
+                x="x",
-                y="dim_2",
+                y="y",
                 color=doc_color_values,
                 hover_data=hover_fields,
             )
@@ -114,17 +114,17 @@ class PlotFactory:
             if dimensions == "3d":
                 prompt_fig = px.scatter_3d(
                     prompt_df,
-                    x="dim_1",
+                    x="x",
-                    y="dim_2",
+                    y="y",
-                    z="dim_3",
+                    z="z",
                     color=prompt_color_values,
                     hover_data=hover_fields,
                 )
             else:
                 prompt_fig = px.scatter(
                     prompt_df,
-                    x="dim_1",
+                    x="x",
-                    y="dim_2",
+                    y="y",
                     color=prompt_color_values,
                     hover_data=hover_fields,
                 )
@@ -168,11 +168,11 @@ class PlotFactory:
                 "category": doc.category,
                 "subcategory": doc.subcategory,
                 "tags_str": ", ".join(doc.tags) if doc.tags else "None",
-                "dim_1": coordinates[i, 0],
+                "x": coordinates[i, 0],
-                "dim_2": coordinates[i, 1],
+                "y": coordinates[i, 1],
             }
             if dimensions == "3d":
-                row["dim_3"] = coordinates[i, 2]
+                row["z"] = coordinates[i, 2]
             df_data.append(row)
 
         return pd.DataFrame(df_data)

uv.lock

@@ -412,7 +412,7 @@ wheels = [
 
 [[package]]
 name = "embeddingbuddy"
-version = "0.3.0"
+version = "0.5.1"
 source = { editable = "." }
 dependencies = [
     { name = "dash" },