From f691b4ddd2c4f7187d4ce6ed21f74ab69eae02b8 Mon Sep 17 00:00:00 2001
From: Stephen Hu <stephenhu@seismic.com>
Date: Mon, 24 Mar 2025 19:08:22 +0800
Subject: [PATCH] Feat: Improve "/convert" API's performance  (#6465)

### What problem does this PR solve?

for batch requests based on get_by_ids to fetch all files first replace
the O(n) IO logic.

### Type of change


- [x] Performance Improvement
---
 api/apps/file2document_app.py | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/api/apps/file2document_app.py b/api/apps/file2document_app.py
index 48a607c0b..d67e5ef0a 100644
--- a/api/apps/file2document_app.py
+++ b/api/apps/file2document_app.py
@@ -38,8 +38,12 @@ def convert():
     file2documents = []
 
     try:
+        files = FileService.get_by_ids(file_ids)
+        files_set = set([file.id for file in files])
         for file_id in file_ids:
-            e, file = FileService.get_by_id(file_id)
+            file = files_set[file_id]
+            if not file:
+                return get_data_error_result(message="File not found!")
             file_ids_list = [file_id]
             if file.type == FileType.FOLDER.value:
                 file_ids_list = FileService.get_all_innermost_file_ids(file_id, [])
@@ -86,6 +90,7 @@ def convert():
                         "file_id": id,
                         "document_id": doc.id,
                     })
+
                     file2documents.append(file2document.to_json())
         return get_json_result(data=file2documents)
     except Exception as e: