From b88c64f80eea89cbd698ce20e2df6b22ecab8b33 Mon Sep 17 00:00:00 2001
From: "Timothy J. Baek" <timothyjrbeck@gmail.com>
Date: Wed, 6 Mar 2024 17:54:42 -0800
Subject: [PATCH] fix: ocr issue

---
 backend/apps/rag/main.py | 2 +-
 backend/requirements.txt | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/backend/apps/rag/main.py b/backend/apps/rag/main.py
index 99aa69594..45ad69707 100644
--- a/backend/apps/rag/main.py
+++ b/backend/apps/rag/main.py
@@ -425,7 +425,7 @@ def get_loader(filename: str, file_content_type: str, file_path: str):
     ]
 
     if file_ext == "pdf":
-        loader = PyPDFLoader(file_path)
+        loader = PyPDFLoader(file_path, extract_images=True)
     elif file_ext == "csv":
         loader = CSVLoader(file_path)
     elif file_ext == "rst":
diff --git a/backend/requirements.txt b/backend/requirements.txt
index 190d12980..fd38df0b0 100644
--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -35,6 +35,7 @@ openpyxl
 pyxlsb
 xlrd
 rapidocr-onnxruntime
+opencv-python-headless
 
 faster-whisper