added the table and image sources

utils.py

@@ -99,36 +99,86 @@ def generate_sources_html(nodes, chunks_df=None):
     html = "<div style='background-color: #2d3748; color: white; padding: 20px; border-radius: 10px; max-height: 400px; overflow-y: auto;'>"
     html += "<h3 style='color: #63b3ed; margin-top: 0;'>Источники:</h3>"
     
+    # Group nodes by document to avoid duplicates
+    sources_by_doc = {}
+    
     for i, node in enumerate(nodes):
         metadata = node.metadata if hasattr(node, 'metadata') else {}
         doc_type = metadata.get('type', 'text')
         doc_id = metadata.get('document_id', 'unknown')
-        section_id = metadata.get('section_id', '') 
+        section_id = metadata.get('section_id', '')
+        section_text = metadata.get('section_text', '')
+        section_path = metadata.get('section_path', '')
+        
+        # Create a unique key for grouping
+        if doc_type == 'table':
+            table_num = metadata.get('table_number', 'unknown')
+            key = f"{doc_id}_table_{table_num}"
+        elif doc_type == 'image':
+            image_num = metadata.get('image_number', 'unknown')
+            key = f"{doc_id}_image_{image_num}"
+        else:
+            # For text documents, group by section path or section id
+            section_key = section_path if section_path else section_id
+            key = f"{doc_id}_text_{section_key}"
+        
+        if key not in sources_by_doc:
+            sources_by_doc[key] = {
+                'doc_id': doc_id,
+                'doc_type': doc_type,
+                'metadata': metadata,
+                'sections': set()
+            }
+        
+        # Add section information
+        if section_path:
+            sources_by_doc[key]['sections'].add(f"пункт {section_path}")
+        elif section_id and section_id != 'unknown':
+            sources_by_doc[key]['sections'].add(f"пункт {section_id}")
+    
+    # Generate HTML for each unique source
+    for source_info in sources_by_doc.values():
+        metadata = source_info['metadata']
+        doc_type = source_info['doc_type']
+        doc_id = source_info['doc_id']
         
         html += f"<div style='margin-bottom: 15px; padding: 15px; border: 1px solid #4a5568; border-radius: 8px; background-color: #1a202c;'>"
         
         if doc_type == 'text':
             html += f"<h4 style='margin: 0 0 10px 0; color: #63b3ed;'>📄 {doc_id}</h4>"
-            html += f"<h4 style='margin: 0 0 10px 0; color: #63b3ed;'>📌 {section_id}</h4>"
+            # Show all sections for this document
+            if source_info['sections']:
+                sections_text = ", ".join(sorted(source_info['sections']))
+                html += f"<p style='margin: 5px 0; color: #a0aec0; font-size: 14px;'>{sections_text}</p>"
 
-        elif doc_type == 'table':
+        elif doc_type == 'table' or doc_type == 'table_row':
             table_num = metadata.get('table_number', 'unknown')
+            table_title = metadata.get('table_title', '')
             if table_num and table_num != 'unknown':
-                if not table_num.startswith('№'):
+                if not str(table_num).startswith('№'):
                     table_num = f"№{table_num}"
                 html += f"<h4 style='margin: 0 0 10px 0; color: #68d391;'>📊 Таблица {table_num} - {doc_id}</h4>"
+                if table_title and table_title != 'unknown':
+                    html += f"<p style='margin: 5px 0; color: #a0aec0; font-size: 14px;'>{table_title}</p>"
             else:
                 html += f"<h4 style='margin: 0 0 10px 0; color: #68d391;'>📊 Таблица - {doc_id}</h4>"
+                
         elif doc_type == 'image':
             image_num = metadata.get('image_number', 'unknown')
+            image_title = metadata.get('image_title', '')
             section = metadata.get('section', '')
             if image_num and image_num != 'unknown':
                 if not str(image_num).startswith('№'):
                     image_num = f"№{image_num}"
-                html += f"<h4 style='margin: 0 0 10px 0; color: #fbb6ce;'>🖼️ Изображение {image_num} - {doc_id} ({section})</h4>"
+                html += f"<h4 style='margin: 0 0 10px 0; color: #fbb6ce;'>🖼️ Изображение {image_num} - {doc_id}</h4>"
+                if image_title and image_title != 'unknown':
+                    html += f"<p style='margin: 5px 0; color: #a0aec0; font-size: 14px;'>{image_title}</p>"
+                if section and section != 'unknown':
+                    html += f"<p style='margin: 5px 0; color: #a0aec0; font-size: 12px;'>Раздел: {section}</p>"
             else:
-                html += f"<h4 style='margin: 0 0 10px 0; color: #fbb6ce;'>🖼️ Изображение - {doc_id} ({section})</h4>"
+                html += f"<h4 style='margin: 0 0 10px 0; color: #fbb6ce;'>🖼️ Изображение - {doc_id}</h4>"
         
+        # Add file link if available
         if chunks_df is not None and 'file_link' in chunks_df.columns and doc_type == 'text':
             doc_rows = chunks_df[chunks_df['document_id'] == doc_id]
             if not doc_rows.empty: