Update app.py

app.py

@@ -30,6 +30,22 @@ STANDARD_COLORS = {
     'WORK OF ART': '#DDA0DD'  # Plum
 }
 
+# Entity definitions for glossary
+ENTITY_DEFINITIONS = {
+    'DATE': 'Absolute or relative dates or periods',
+    'EVENT': 'Named hurricanes, battles, wars, sports events, etc.',
+    'FAC': 'Facilities - Buildings, airports, highways, bridges, etc.',
+    'GPE': 'Geopolitical entities - Countries, cities, states',
+    'LANG': 'Any named language',
+    'LOC': 'Non-GPE locations - Mountain ranges, bodies of water',
+    'MISC': 'Miscellaneous entities - Things that don\'t fit elsewhere',
+    'NORP': 'Nationalities or religious or political groups',
+    'ORG': 'Organizations - Companies, agencies, institutions, etc.',
+    'PER': 'People, including fictional characters',
+    'PRODUCT': 'Objects, vehicles, foods, etc. (Not services)',
+    'Work of Art': 'Titles of books, songs, movies, paintings, etc.'
+}
+
 # Additional colours for custom entities
 CUSTOM_COLOR_PALETTE = [
     '#FF9F43', '#10AC84', '#EE5A24', '#0FBC89', '#5F27CD',
@@ -730,9 +746,34 @@ def process_text(text, standard_entities, custom_entities_str, confidence_thresh
     
     return summary, legend_html + highlighted_html, results_html
 
+# Create colored checkbox labels
+def create_colored_checkbox_labels():
+    """Create checkbox labels with color indicators"""
+    labels = []
+    for entity in STANDARD_ENTITIES:
+        colour_key = "WORK OF ART" if entity == "Work of Art" else entity.upper()
+        colour = STANDARD_COLORS.get(colour_key, '#CCCCCC')
+        # Create label with color dot
+        labels.append(f"● {entity}")
+    return labels
+
 # Create Gradio interface
 def create_interface():
-    with gr.Blocks(title="Hybrid NER + GLiNER Tool", theme=gr.themes.Soft()) as demo:
+    # Custom CSS for colored checkboxes
+    custom_css = """
+    /* Color the checkbox labels based on entity type */
+    """
+    for i, entity in enumerate(STANDARD_ENTITIES):
+        colour_key = "WORK OF ART" if entity == "Work of Art" else entity.upper()
+        colour = STANDARD_COLORS.get(colour_key, '#CCCCCC')
+        custom_css += f"""
+        label[for="checkbox-{i}"] span:first-child {{
+            color: {colour} !important;
+            font-weight: bold;
+        }}
+        """
+    
+    with gr.Blocks(title="Hybrid NER + GLiNER Tool", theme=gr.themes.Soft(), css=custom_css) as demo:
         gr.Markdown("""
         # 🎯 Hybrid NER + Custom GLiNER Entity Recognition Tool
         
@@ -744,7 +785,7 @@ def create_interface():
         1. **📝 Enter your text** in the text area below
         2. **🎯 Select a model** from the dropdown for common entities
         3. **☑️ Select common entities** you want to find (PER, ORG, LOC, etc.)
-        4. **✨ Add custom entities** (comma-separated) like "relationships, occupations, skills"
+        4. **✨ Add custom entities** (comma-separated) like "relationships, occupations, skills" - powered by GLiNER
         5. **⚙️ Adjust confidence threshold** 
         6. **🔍 Click "Analyse Text"** to see results with organized output
         """)
@@ -771,6 +812,14 @@ def create_interface():
             with gr.Column():
                 gr.Markdown("### 🎯 Common Entity Types")
                 
+                # Add the inline help text
+                gr.HTML("""
+                <div style="background-color: #e3f2fd; padding: 10px; border-radius: 5px; margin-bottom: 10px; font-size: 13px;">
+                    <strong>Quick Guide:</strong> PER = People | ORG = Organizations | LOC = Locations | 
+                    GPE = Countries/Cities | FAC = Facilities | DATE = Dates | EVENT = Named Events
+                </div>
+                """)
+                
                 # Model selector
                 model_dropdown = gr.Dropdown(
                     choices=ner_manager.model_names,
@@ -779,11 +828,39 @@ def create_interface():
                     info="Choose which model to use for common NER"
                 )
                 
-                # Common entities with select all functionality
+                # Add collapsible glossary with colors
+                glossary_html = """
+                <details style="margin: 10px 0; padding: 10px; background-color: #f8f9fa; border-radius: 8px; border: 1px solid #ddd;">
+                    <summary style="cursor: pointer; font-weight: bold; padding: 5px; color: #1976d2;">
+                        ℹ️ Detailed Entity Type Definitions (Click to expand)
+                    </summary>
+                    <div style="margin-top: 10px; padding: 10px;">
+                        <dl style="margin: 0; font-size: 14px;">
+                """
+                
+                for entity, definition in ENTITY_DEFINITIONS.items():
+                    colour_key = "WORK OF ART" if entity == "Work of Art" else entity.upper()
+                    colour = STANDARD_COLORS.get(colour_key, '#CCCCCC')
+                    glossary_html += f"""
+                            <div style="margin-bottom: 8px;">
+                                <dt style="font-weight: bold; display: inline; color: {colour};">{entity}:</dt>
+                                <dd style="display: inline; margin-left: 5px;">{definition}</dd>
+                            </div>
+                    """
+                
+                glossary_html += """
+                        </dl>
+                    </div>
+                </details>
+                """
+                gr.HTML(glossary_html)
+                
+                # Common entities checkboxes with colored labels
                 standard_entities = gr.CheckboxGroup(
-                    choices=STANDARD_ENTITIES,
-                    value=['PER', 'ORG', 'LOC', 'MISC'],  # Default selection
-                    label="Select Common Entities"
+                    choices=create_colored_checkbox_labels(),
+                    value=[f"● {entity}" for entity in ['PER', 'ORG', 'LOC', 'MISC']],  # Default selection
+                    label="Select Common Entities",
+                    elem_id="standard-entities-checkbox"
                 )
                 
                 # Select/Deselect All button
@@ -797,7 +874,7 @@ def create_interface():
                         return [], "☑️ Select All"
                     else:
                         # If none selected, select all
-                        return STANDARD_ENTITIES, "🔘 Deselect All"
+                        return create_colored_checkbox_labels(), "🔘 Deselect All"
                 
                 select_all_btn.click(
                     fn=toggle_all_entities,
@@ -806,7 +883,7 @@ def create_interface():
                 )
             
             with gr.Column():
-                gr.Markdown("### ✨ Custom Entity Types")
+                gr.Markdown("### ✨ Custom Entity Types (Powered by GLiNER)")
                 custom_entities = gr.Textbox(
                     label="Custom Entities (comma-separated)",
                     placeholder="e.g. relationships, occupations, skills, emotions",
@@ -818,6 +895,8 @@ def create_interface():
                 - emotions, actions, objects  
                 - medical conditions, treatments
                 - financial terms, business roles
+                
+                *GLiNER model will extract these custom entity types from your text*
                 """)
         
         analyse_btn = gr.Button("🔍 Analyse Text", variant="primary", size="lg")
@@ -835,9 +914,15 @@ def create_interface():
                 gr.Markdown("### 📋 Detailed Results")
                 results_output = gr.HTML(label="Entity Results")
         
+        # Function to process with colored labels
+        def process_with_colored_labels(text, colored_labels, custom_entities, confidence_threshold, selected_model, progress=gr.Progress()):
+            # Remove the color dots from labels
+            standard_entities = [label.replace("● ", "") for label in colored_labels]
+            return process_text(text, standard_entities, custom_entities, confidence_threshold, selected_model, progress)
+        
         # Connect the button to the processing function
         analyse_btn.click(
-            fn=process_text,
+            fn=process_with_colored_labels,
             inputs=[
                 text_input,
                 standard_entities,
@@ -853,21 +938,21 @@ def create_interface():
             examples=[
                 [
                     "John Smith works at Google in New York. He graduated from Stanford University in 2015 and specialises in artificial intelligence research. His wife Sarah is a doctor at Mount Sinai Hospital.",
-                    ["PER", "ORG", "LOC", "DATE"],
+                    [f"● {entity}" for entity in ["PER", "ORG", "LOC", "DATE"]],
                     "relationships, occupations, educational background",
                     0.3,
                     "entities_spacy_en_core_web_trf"
                 ],
                 [
                     "The meeting between CEO Jane Doe and the board of directors at Microsoft headquarters in Seattle discussed the Q4 financial results and the new AI strategy for 2024.",
-                    ["PER", "ORG", "LOC", "DATE"],
+                    [f"● {entity}" for entity in ["PER", "ORG", "LOC", "DATE"]],
                     "corporate roles, business events, financial terms",
                     0.4,
                     "entities_flair_ner-ontonotes-large"
                 ],
                 [
                     "Dr. Emily Watson published a research paper on machine learning algorithms at MIT. She collaborates with her colleague Prof. David Chen on natural language processing projects.",
-                    ["PER", "ORG", "Work of Art"],
+                    [f"● {entity}" for entity in ["PER", "ORG", "Work of Art"]],
                     "academic titles, research topics, collaborations",
                     0.3,
                     "entities_gliner_knowledgator/modern-gliner-bi-large-v1.0"
@@ -881,6 +966,37 @@ def create_interface():
                 model_dropdown
             ]
         )
+        
+        # Add model information links
+        gr.HTML("""
+        <hr style="margin-top: 40px; margin-bottom: 20px;">
+        <div style="background-color: #f8f9fa; padding: 20px; border-radius: 8px; margin-top: 20px;">
+            <h4 style="margin-top: 0;">📚 Model Information & Documentation</h4>
+            <p style="font-size: 14px; margin-bottom: 15px;">Learn more about the models used in this tool:</p>
+            <ul style="font-size: 14px; line-height: 1.8;">
+                <li><strong>entities_flair_ner-large:</strong> 
+                    <a href="https://huggingface.co/flair/ner-english-large" target="_blank" style="color: #1976d2;">
+                        Flair NER English Large Model ↗
+                    </a>
+                </li>
+                <li><strong>entities_spacy_en_core_web_trf:</strong> 
+                    <a href="https://spacy.io/models/en#en_core_web_trf" target="_blank" style="color: #1976d2;">
+                        spaCy English Transformer Model ↗
+                    </a>
+                </li>
+                <li><strong>entities_flair_ner-ontonotes-large:</strong> 
+                    <a href="https://huggingface.co/flair/ner-english-ontonotes-large" target="_blank" style="color: #1976d2;">
+                        Flair OntoNotes Large Model ↗
+                    </a>
+                </li>
+                <li><strong>entities_gliner_knowledgator/modern-gliner-bi-large-v1.0:</strong> 
+                    <a href="https://github.com/urchade/GLiNER/blob/main/README_Extended.md" target="_blank" style="color: #1976d2;">
+                        GLiNER Extended Documentation ↗
+                    </a>
+                </li>
+            </ul>
+        </div>
+        """)
 
     return demo