pdf fix

app.py

@@ -15,7 +15,7 @@ from langchain.chains.question_answering import load_qa_chain
 from PIL import Image
 from datetime import datetime
 from tempfile import NamedTemporaryFile
-from pdf2image import convert_from_path
+import pypdfium2 as pdfium
     
 st.subheader("Upload CV in PDF or image format")
 uploaded_file = st.file_uploader("Upload PDF or Images", type=["pdf","png","jpg","jpeg"])
@@ -36,9 +36,15 @@ if uploaded_file:
         with NamedTemporaryFile(delete=False, dir='.', suffix='.pdf') as f:
             f.write(uploaded_file.getbuffer())
             PDFFileName = f.name
-        images = convert_from_path(PDFFileName)
-        for i in range(len(images)):
-            st.image(images[i],width=700)
+            pdf = pdfium.PdfDocument("my_pdf_file.pdf")
+            n_pages = len(pdf)
+            for page_number in range(n_pages):
+                page = pdf.get_page(page_number)
+                pil_image = page.render_topil(scale=1,rotation=0,crop=(0, 0, 0, 0),colour=(255, 255, 255, 255),annotations=True,greyscale=False,optimise_mode=pdfium.OptimiseMode.NONE,)
+                st.image(pil_image,width=700)
+#        images = convert_from_path(PDFFileName)
+#        for i in range(len(images)):
+#            st.image(images[i],width=700)
 #        with open(PDFFileName,"rb") as f:
 #            base64_pdf = base64.b64encode(f.read()).decode('utf-8')
 #            pdf_display = f'<iframe src="data:application/pdf;base64,{base64_pdf}" width="800" height="800" type="application/pdf"></iframe>'

packages.txt

@@ -2,4 +2,3 @@ poppler-utils
 tesseract-ocr
 chromium
 chromium-driver
-pdf2image