Update app.py

app.py

@@ -3,9 +3,13 @@ import gradio as gr
 import json
 import os
 import time
+import subprocess
 from pathlib import Path
 from huggingface_hub import InferenceClient
 
+subprocess.run(["pip", "install", "pypdf", "-q"], capture_output=True)
+from pypdf import PdfReader
+
 SAVE_DIR = Path("/tmp/saved_docs")
 SAVE_DIR.mkdir(exist_ok=True)
 MODEL = "meta-llama/Llama-3.3-70B-Instruct"
@@ -20,13 +24,12 @@ def extract_pdf_text(path):
     if hasattr(path, "name"):
         path = path.name
     try:
-        import pdfplumber
-        with pdfplumber.open(path) as pdf:
-            pages = []
-            for i, page in enumerate(pdf.pages):
-                text = page.extract_text() or ""
-                if text.strip():
-                    pages.append(f"--- Page {i+1} ---\n{text.strip()}")
+        reader = PdfReader(path)
+        pages = []
+        for i, page in enumerate(reader.pages):
+            text = page.extract_text() or ""
+            if text.strip():
+                pages.append(f"--- Page {i+1} ---\n{text.strip()}")
         if not pages:
             return "[No extractable text — may be a scanned PDF]"
         full = "\n\n".join(pages)