update

news_crawler/crawler_service.py

@@ -388,6 +388,21 @@ def crawl_rss_feed(feed_url, feed_name, feed_category='general', max_articles=10
                         print(f"   ⚠ Summarization failed: {summary_result['error']}")
                         failed_summaries += 1
                 
+                # Extract keywords for personalization
+                keywords_result = None
+                if Config.OLLAMA_ENABLED and summary_result and summary_result['success']:
+                    print(f"   🔑 Extracting keywords...")
+                    keywords_result = ollama_client.extract_keywords(
+                        original_title,
+                        summary_result['summary'],
+                        max_keywords=5
+                    )
+                    
+                    if keywords_result['success']:
+                        print(f"   ✓ Keywords: {', '.join(keywords_result['keywords'])} ({keywords_result['duration']:.1f}s)")
+                    else:
+                        print(f"   ⚠ Keyword extraction failed: {keywords_result['error']}")
+                
                 # Prepare document
                 article_doc = {
                     'title': original_title,
@@ -396,6 +411,7 @@ def crawl_rss_feed(feed_url, feed_name, feed_category='general', max_articles=10
                     'link': article_url,
                     'content': article_data.get('content', ''),  # Full article content
                     'summary': summary_result['summary'] if summary_result and summary_result['success'] else None,
+                    'keywords': keywords_result['keywords'] if keywords_result and keywords_result['success'] else [],
                     'word_count': article_data.get('word_count', 0),
                     'summary_word_count': summary_result['summary_word_count'] if summary_result and summary_result['success'] else None,
                     'source': feed_name,