Update app.py

app.py

@@ -1,5 +1,5 @@
-from pdfminer.high_level import extract_pages
-from pdfminer.layout import LTTextContainer
+# from pdfminer.high_level import extract_pages
+# from pdfminer.layout import LTTextContainer
 from tqdm import tqdm
 import re
 import gradio as gr
@@ -9,6 +9,7 @@ import spaces
 import subprocess
 from huggingface_hub import hf_hub_download
 from llama_cpp import Llama
+from docling.document_converter import DocumentConverter
 
 from huggingface_hub import login
 
@@ -88,10 +89,13 @@ def craft_cv(llm, cv_text, job_description, maxtokens, temperature, top_probabil
 
 @spaces.GPU(duration=150)
 def pdf_to_text(cv_file, job_description, maxtokens=2048, temperature=0, top_probability=0.95):
-    page2content = process_document(cv_file)
-    cv_text = ""
-    for page_id in page2content:
-        cv_text += page2content[page_id] + ' '
+    # page2content = process_document(cv_file)
+    # cv_text = ""
+    # for page_id in page2content:
+    #     cv_text += page2content[page_id] + ' '
+    converter = DocumentConverter()
+    result = converter.convert(cv_file)
+    cv_text = result.document.export_to_markdown()
     llm = Llama(
         model_path="models/" + model_id,
         flash_attn=True,