Update app.py

app.py

@@ -11,16 +11,20 @@ import os
 import nltk
 nltk.download('punkt')
 
-# Install Poppler in the runtime environment
-os.system("apt-get update && apt-get install -y poppler-utils")
+# Install Poppler and Tesseract in the runtime environment
+os.system("apt-get update && apt-get install -y poppler-utils tesseract-ocr")
 
 secret = os.getenv('Groq_api')
 
 working_dir = os.path.dirname(os.path.abspath(__file__))
 
 def load_documents(file_path):
-    # Specify poppler_path to ensure compatibility in Spaces
-    loader = UnstructuredPDFLoader(file_path, poppler_path="/usr/bin")
+    # Specify poppler_path and tesseract_path to ensure compatibility
+    loader = UnstructuredPDFLoader(
+        file_path, 
+        poppler_path="/usr/bin", 
+        tesseract_path="/usr/bin/tesseract"
+    )
     documents = loader.load()
     return documents