fix: ocr issue

sime2408 · Mar 7, 2024 · b88c64f · b88c64f
1 parent dc6e91a
commit b88c64f
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 1 deletion.
diff --git 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
@@ -35,6 +35,7 @@ openpyxl
 pyxlsb
 xlrd
 rapidocr-onnxruntime
+opencv-python-headless
 
 faster-whisper
-Original file line number
+Diff line change
@@ Expand Up / @@ -35,6 +35,7 @@ openpyxl @@
     pyxlsb
     xlrd
     rapidocr-onnxruntime
+    opencv-python-headless
     faster-whisper
@@ Expand Down @@