From c53fcf3981cc7ded5005de8fe04730b1ccd662c0 Mon Sep 17 00:00:00 2001
From: Mark <348207283@qq.com>
Date: Mon, 27 Apr 2026 17:10:00 +0800
Subject: [PATCH] [fix] old code file_path

---
 api/app/tasks.py | 32 +-------------------------------
 1 file changed, 1 insertion(+), 31 deletions(-)

diff --git a/api/app/tasks.py b/api/app/tasks.py
index 578a0e8d..3ad1a0dd 100644
--- a/api/app/tasks.py
+++ b/api/app/tasks.py
@@ -280,39 +280,9 @@ def parse_document(file_key: str, document_id: uuid.UUID, file_name: str = ""):
         # Prepare vision_model for parsing
         vision_model = _build_vision_model(file_name, db_knowledge)
 
-        # 先将文件读入内存，避免解析过程中依赖 NFS 文件持续可访问
-        # python-docx 等库在 binary=None 时会用路径直接打开文件，
-        # 在 NFS/共享存储上可能因缓存失效导致 "Package not found"
-        max_wait_seconds = 30
-        wait_interval = 2
-        waited = 0
-        file_binary = None
-        while waited <= max_wait_seconds:
-            # os.listdir 强制 NFS 客户端刷新目录缓存
-            parent_dir = os.path.dirname(file_path)
-            try:
-                os.listdir(parent_dir)
-            except OSError:
-                pass
-            try:
-                with open(file_path, "rb") as f:
-                    file_binary = f.read()
-                if not file_binary:
-                    # NFS 上文件存在但内容为空（可能还在同步中）
-                    raise IOError(f"File is empty (0 bytes), NFS may still be syncing: {file_path}")
-                break
-            except (FileNotFoundError, IOError) as e:
-                if waited >= max_wait_seconds:
-                    raise type(e)(
-                        f"File not accessible at '{file_path}' after waiting {max_wait_seconds}s: {e}"
-                    )
-                logger.warning(f"File not ready on this node, retrying in {wait_interval}s: {file_path} ({e})")
-                time.sleep(wait_interval)
-                waited += wait_interval
-
         from app.core.rag.app.naive import chunk
         logger.info(f"[ParseDoc] file_binary size={len(file_binary)} bytes, type={type(file_binary).__name__}, bool={bool(file_binary)}")
-        res = chunk(filename=file_path,
+        res = chunk(filename=file_name,
                     binary=file_binary,
                     from_page=0,
                     to_page=DEFAULT_PARSE_TO_PAGE,