fixed import error

main_utils.py

@@ -210,6 +210,118 @@ def enhance_query_with_keywords(query):
     return f"{query}"
 
 
+
+def merge_table_chunks(chunk_info):
+    merged = {}
+    
+    for chunk in chunk_info:
+        doc_type = chunk.get('type', 'text')
+        doc_id = chunk.get('document_id', 'unknown')
+        
+        if doc_type == 'table' or doc_type == 'table_row':
+            table_num = chunk.get('table_number', '')
+            key = f"{doc_id}_{table_num}"
+            
+            if key not in merged:
+                merged[key] = {
+                    'document_id': doc_id,
+                    'type': 'table',
+                    'table_number': table_num,
+                    'section_id': chunk.get('section_id', 'unknown'),
+                    'chunk_text': chunk.get('chunk_text', '')
+                }
+            else:
+                merged[key]['chunk_text'] += '\n' + chunk.get('chunk_text', '')
+        else:
+            unique_key = f"{doc_id}_{chunk.get('section_id', '')}_{chunk.get('chunk_id', 0)}"
+            merged[unique_key] = chunk
+    
+    return list(merged.values())
+
+def create_chunks_display_html(chunk_info):
+    if not chunk_info:
+        return "<div style='padding: 20px; text-align: center; color: black;'>Нет данных о чанках</div>"
+    
+    merged_chunks = merge_table_chunks(chunk_info)
+    
+    html = "<div style='max-height: 500px; overflow-y: auto; padding: 10px; color: black;'>"
+    html += f"<h4 style='color: black;'>Найдено релевантных чанков: {len(merged_chunks)}</h4>"
+    
+    for i, chunk in enumerate(merged_chunks):
+        bg_color = "#f8f9fa" if i % 2 == 0 else "#e9ecef"
+        section_display = get_section_display(chunk)
+        formatted_content = get_formatted_content(chunk)
+        
+        html += f"""
+        <div style='background-color: {bg_color}; padding: 10px; margin: 5px 0; border-radius: 5px; border-left: 4px solid #007bff; color: black;'>
+            <strong style='color: black;'>Документ:</strong> <span style='color: black;'>{chunk['document_id']}</span><br>
+            <strong style='color: black;'>Раздел:</strong> <span style='color: black;'>{section_display}</span><br>
+            <strong style='color: black;'>Содержание:</strong><br>
+            <div style='background-color: white; padding: 8px; margin-top: 5px; border-radius: 3px; font-family: monospace; font-size: 12px; color: black; max-height: 200px; overflow-y: auto;'>
+                {formatted_content}
+            </div>
+        </div>
+        """
+    
+    html += "</div>"
+    return html
+
+def get_section_display(chunk):
+    section_path = chunk.get('section_path', '')
+    section_id = chunk.get('section_id', 'unknown')
+    doc_type = chunk.get('type', 'text')
+    
+    if doc_type == 'table' and chunk.get('table_number'):
+        table_num = chunk.get('table_number')
+        if not str(table_num).startswith('№'):
+            table_num = f"№{table_num}"
+        return f"таблица {table_num}"
+    
+    if doc_type == 'image' and chunk.get('image_number'):
+        image_num = chunk.get('image_number')
+        if not str(image_num).startswith('№'):
+            image_num = f"№{image_num}"
+        return f"рисунок {image_num}"
+    
+    if section_path:
+        return section_path
+    elif section_id and section_id != 'unknown':
+        return section_id
+    
+    return section_id
+
+def get_formatted_content(chunk):
+    document_id = chunk.get('document_id', 'unknown')
+    section_path = chunk.get('section_path', '')
+    section_id = chunk.get('section_id', 'unknown')
+    section_text = chunk.get('section_text', '')
+    parent_section = chunk.get('parent_section', '')
+    parent_title = chunk.get('parent_title', '')
+    level = chunk.get('level', '')
+    chunk_text = chunk.get('chunk_text', '')
+    doc_type = chunk.get('type', 'text')
+    
+    # For text documents
+    if level in ['subsection', 'sub_subsection', 'sub_sub_subsection'] and parent_section:
+        current_section = section_path if section_path else section_id
+        parent_info = f"{parent_section} ({parent_title})" if parent_title else parent_section
+        return f"В разделе {parent_info} в документе {document_id}, пункт {current_section}: {chunk_text}"
+    else:
+        current_section = section_path if section_path else section_id
+        clean_text = chunk_text
+        if section_text and chunk_text.startswith(section_text):
+            section_title = section_text
+        elif chunk_text.startswith(f"{current_section} "):
+            clean_text = chunk_text[len(f"{current_section} "):].strip()
+            section_title = section_text if section_text else f"{current_section} {clean_text.split('.')[0] if '.' in clean_text else clean_text[:50]}"
+        else:
+            section_title = section_text if section_text else current_section
+            
+        return f"В разделе {current_section} в документе {document_id}, пункт {section_title}: {clean_text}"
+
+
+
+
 def answer_question(question, query_engine, reranker, current_model, chunks_df=None, rerank_top_k=20):
     normalized_question = normalize_text(question)
     normalized_question_2, query_changes, change_list = normalize_steel_designations(question)