From 039dec682008d44bfd2bddf4610214f4c002115e Mon Sep 17 00:00:00 2001
From: ayan4m1 <andrew@bulletlogic.com>
Date: Sun, 20 Apr 2025 17:36:40 +0200
Subject: [PATCH] fix: pass header to Tika if PDF_EXTRACT_IMAGES is true

---
 backend/open_webui/retrieval/loaders/main.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/backend/open_webui/retrieval/loaders/main.py b/backend/open_webui/retrieval/loaders/main.py
index 24944bd8a..0403c5c51 100644
--- a/backend/open_webui/retrieval/loaders/main.py
+++ b/backend/open_webui/retrieval/loaders/main.py
@@ -99,6 +99,9 @@ class TikaLoader:
         else:
             headers = {}
 
+        if self.kwargs.get("PDF_EXTRACT_IMAGES") == True:
+            headers['X-Tika-PDFextractInlineImages'] = 'true'
+
         endpoint = self.url
         if not endpoint.endswith("/"):
             endpoint += "/"