From 6b1221d2f64eb20a17134eafe59440148c985064 Mon Sep 17 00:00:00 2001
From: Tuan Le <30828528+tuankg1028@users.noreply.github.com>
Date: Thu, 26 Jun 2025 10:54:43 +0700
Subject: [PATCH] Fix parser_config access for layout_recognize in
 presentation.py (#8492)

### What problem does this PR solve?
This PR addresses an issue in the presentation parser where the
`layout_recognize` configuration was incorrectly retrieved from
`kwargs.get("layout_recognize", "DeepDOC")`. Instead, it should be
sourced from the `parser_config` parameter, specifically
`parser_config.get("layout_recognize", "DeepDOC")`.

This mismatch could cause the parser to default to the "DeepDOC" layout
recognizer, ignoring any alternative recognition method specified in the
parser configuration. As a result, PDF document parsing might use an
incorrect recognition engine.

The fix ensures the presentation parser consistently uses the
`layout_recognize` setting from `parser_config`, aligning with the
configuration access patterns used elsewhere in the codebase.

### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---
 rag/app/presentation.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/rag/app/presentation.py b/rag/app/presentation.py
index fd32c261b..45f72adf5 100644
--- a/rag/app/presentation.py
+++ b/rag/app/presentation.py
@@ -98,12 +98,14 @@ class PlainPdf(PlainParser):
 
 
 def chunk(filename, binary=None, from_page=0, to_page=100000,
-          lang="Chinese", callback=None, **kwargs):
+          lang="Chinese", callback=None, parser_config=None, **kwargs):
     """
     The supported file formats are pdf, pptx.
     Every page will be treated as a chunk. And the thumbnail of every page will be stored.
     PPT file will be parsed by using this method automatically, setting-up for every PPT file is not necessary.
     """
+    if parser_config is None:
+        parser_config = {}
     eng = lang.lower() == "english"
     doc = {
         "docnm_kwd": filename,
@@ -126,7 +128,7 @@ def chunk(filename, binary=None, from_page=0, to_page=100000,
             res.append(d)
         return res
     elif re.search(r"\.pdf$", filename, re.IGNORECASE):
-        layout_recognizer = kwargs.get("layout_recognize", "DeepDOC")
+        layout_recognizer = parser_config.get("layout_recognize", "DeepDOC")
         if layout_recognizer == "DeepDOC":
             pdf_parser = Pdf()
             sections = pdf_parser(filename, binary, from_page=from_page, to_page=to_page, callback=callback)