Update unified_document_processor.py

unified_document_processor.py

@@ -373,51 +373,57 @@ class UnifiedDocumentProcessor:
             return f"Error processing your question: {str(e)}"
 
     def get_detailed_context(self, question: str, selected_files: List[str], n_results: int = 5) -> Dict:
-        """Get detailed context including path and metadata information"""
-        try:
-            filter_dict = {
-                'source_file': {'$in': selected_files}
-            }
-
-            results = self.collection.query(
-                query_texts=[question],
-                n_results=n_results,
-                where=filter_dict,
-                include=["documents", "metadatas", "distances"]
-            )
-
-            if not results['documents'][0]:
-                return {
-                    'success': False,
-                    'error': "No relevant content found"
-                }
+    """Get detailed context with enhanced scoring"""
+    try:
+        filter_dict = {
+            'source_file': {'$in': selected_files}
+        }
 
-            detailed_results = []
-            for doc, meta, distance in zip(results['documents'][0], results['metadatas'][0], results['distances'][0]):
-                result_info = {
-                    'content': doc,
-                    'metadata': meta,
-                    'relevance_score': 1 - distance,  # Convert distance to similarity score
-                    'source_info': {
-                        'file': meta['source_file'],
-                        'type': meta['content_type'],
-                        'path': meta.get('xml_path', 'N/A'),  # Only for XML files
-                        'context': json.loads(meta['context']) if meta.get('context') else {}
-                    }
-                }
-                detailed_results.append(result_info)
+        results = self.collection.query(
+            query_texts=[question],
+            n_results=n_results,
+            where=filter_dict,
+            include=["documents", "metadatas", "distances"]
+        )
 
+        if not results['documents'][0]:
             return {
-                'success': True,
-                'results': detailed_results,
-                'query': question
+                'success': False,
+                'error': "No relevant content found"
             }
 
-        except Exception as e:
-            return {
-                'success': False,
-                'error': str(e)
+        detailed_results = []
+        for doc, meta, distance in zip(results['documents'][0], results['metadatas'][0], results['distances'][0]):
+            # Calculate detailed score
+            detailed_score = self.calculate_detailed_score(distance, meta, doc, question)
+            
+            result_info = {
+                'content': doc,
+                'metadata': meta,
+                'score_details': detailed_score,
+                'source_info': {
+                    'file': meta['source_file'],
+                    'type': meta['content_type'],
+                    'path': meta.get('xml_path', 'N/A'),
+                    'context': json.loads(meta['context']) if meta.get('context') else {}
+                }
             }
+            detailed_results.append(result_info)
+
+        # Sort results by total score
+        detailed_results.sort(key=lambda x: x['score_details']['total_score'], reverse=True)
+
+        return {
+            'success': True,
+            'results': detailed_results,
+            'query': question
+        }
+
+    except Exception as e:
+        return {
+            'success': False,
+            'error': str(e)
+        }
 
     def get_hierarchical_context(self, question: str, selected_files: List[str], n_results: int = 5) -> Dict:
         """Get hierarchical context for XML files including parent-child relationships"""