Up1

app.py

@@ -5,7 +5,12 @@ import gradio as gr
 import pdfplumber
 import pandas as pd
 import time
-from cnocr import CnOcr
+# from cnocr import CnOcr
+
+from langchain.document_loaders import PyPDFLoader
+
+pages = loader.load_and_split()
+
 from sentence_transformers import SentenceTransformer, models, util
 word_embedding_model = models.Transformer('sentence-transformers/all-MiniLM-L6-v2', do_lower_case=True)
 pooling_model = models.Pooling(word_embedding_model.get_word_embedding_dimension(), pooling_mode='cls')
@@ -118,7 +123,8 @@ def up_file(files):
                     with open(file_name, mode='wb') as f:
                         f.write(img['stream'].get_data())
                     try:
-                        res = ocr.ocr(file_name)
+                        # res = ocr.ocr(file_name)
+                        res = PyPDFLoader(file_name)
                     except Exception as e:
                         res = []
                     if len(res) > 0: