Update app.py

app.py

@@ -87,8 +87,16 @@ def embed_pdf(file, collection_name):
     # Save the uploaded file
     filename = file.name
     file_path = os.path.join('./', filename)
+
+    # Check if the file object has 'read' method
+    if hasattr(file, 'read'):
+        file_content = file.read()
+    else:
+        # Handle the case where 'read' method is not available
+        file_content = file.getvalue()  # Assuming it's a NamedString or similar object
+
     with open(file_path, 'wb') as f:
-        f.write(file.read())
+        f.write(file_content)
 
     # Checking filetype for document parsing
     mime_type = mimetypes.guess_type(file_path)[0]
@@ -121,13 +129,15 @@ def retrieve_info(query):
     # Rerank the top results
     reranked_results = co.rerank(query=query, documents=top_docs, top_n=3, model='rerank-english-v2.0')
 
-    # Format the reranked results
+    # Format the reranked results according to the Article schema
     formatted_results = []
     for idx, r in enumerate(reranked_results):
         formatted_result = {
             "Document Rank": idx + 1,
-            "Document Index": r.index,
-            "Document": r.document['text'],
+            "Title": r.document['title'],  
+            "Content": r.document['content'],  
+            "Author": r.document['author'],  
+            "Publish Date": r.document['publishDate'],  
             "Relevance Score": f"{r.relevance_score:.2f}"
         }
         formatted_results.append(formatted_result)