push

app.py

@@ -1,16 +1,11 @@
-import fitz  # PyMuPDF
-import pytesseract
 import gradio as gr
-from PIL import Image
+from langchain.document_loaders import PyPDFLoader
 
 def pdf_to_text(pdf_file):
-    doc = fitz.open(pdf_file)
-    text = ""
-    for page in doc:
-        pix = page.get_pixmap()
-        img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
-        text += pytesseract.image_to_string(img)
-    doc.close()
+    loader = PyPDFLoader(pdf_file.name)
+    documents = loader.load()
+    text = "\n".join([doc.page_content for doc in documents])
+    print(text)  # Log the loaded text
     return text
 
 def pdf_to_text_interface(pdf_file):
@@ -19,4 +14,3 @@ def pdf_to_text_interface(pdf_file):
 
 iface = gr.Interface(fn=pdf_to_text_interface, inputs="file", outputs="text", title="PDF to Text Converter <3")
 iface.launch()
-