feat: added ocr functionality to the pdf loader

sime2408 · Mar 5, 2024 · 089a63e · 089a63e
1 parent eb51ad1
commit 089a63e
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
@@ -419,7 +419,7 @@ 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
@@ -33,6 +33,7 @@ pandas
 openpyxl
 pyxlsb
 xlrd
+rapidocr-onnxruntime
 
 faster-whisper
-Original file line number
+Diff line change
@@ Expand Up / @@ -33,6 +33,7 @@ pandas @@
     openpyxl
     pyxlsb
     xlrd
+    rapidocr-onnxruntime
     faster-whisper
@@ Expand Down @@