Merge pull request #1050 from jannikstdl/rag-pdf-ocr

feat: added ocr functionality to the pdf loader

Merge pull request #1050 from jannikstdl/rag-pdf-ocr
feat: added ocr functionality to the pdf loader
8fb5f547 · Timothy Jaeryang Baek · GitHub · 2111398d · 089a63e0 · 8fb5f547
Unverified Commit 8fb5f547 authored Mar 06, 2024 by Timothy Jaeryang Baek Committed by GitHub Mar 06, 2024
Show 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
@@ -34,6 +34,7 @@ pandas
 openpyxl
 pyxlsb
 xlrd
+rapidocr-onnxruntime

 faster-whisper