fix: ocr issue

b88c64f8 · Timothy J. Baek · dc6e91a2 · b88c64f8 · b88c64f8
Commit b88c64f8 authored Mar 06, 2024 by Timothy J. Baek
Hide whitespace changes
Inline Side-by-side

Showing with 2 additions and 1 deletion

backend/apps/rag/main.py backend/apps/rag/main.py +1 -1

backend/requirements.txt backend/requirements.txt +1 -0

No files found.
--- 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":

--- a/backend/requirements.txt
+++ b/backend/requirements.txt
@@ -35,6 +35,7 @@ openpyxl
 pyxlsb
 xlrd
 rapidocr-onnxruntime
+opencv-python-headless
 faster-whisper