trying pdf tp txt converter

app.py

@@ -41,11 +41,20 @@ from utils.ui import reset_results, set_initial_state
 import pandas as pd
 import haystack
 
+from datetime import datetime
+
+from haystack.nodes import TextConverter, PDFToTextConverter, DocxToTextConverter, PreProcessor
+
+pdf_converter = PDFToTextConverter(remove_numeric_tables=True, valid_languages=["en","de"])
+docx_converter = DocxToTextConverter(remove_numeric_tables=False, valid_languages=["en","de"])
+txt_converter = TextConverter(remove_numeric_tables=True, valid_languages=["en","de"])
+
 
 # Whether the file upload should be enabled or not
 DISABLE_FILE_UPLOAD = bool(os.getenv("DISABLE_FILE_UPLOAD"))
 # Define a function to handle file uploads
 def upload_files():
+    print(f'Uploading files at {datetime.now()}')
     uploaded_files = upload_container.file_uploader(
             "upload", type=["pdf", "txt", "docx"], accept_multiple_files=True, label_visibility="collapsed"
         )
@@ -78,7 +87,7 @@ def process_file(data_file, preprocesor, document_store):
         print(e)
 
 def reset_documents():
-    print('Reseting documents list')
+    print('\nReseting documents list at ' + str(datetime.now()) + '\n')
     document_store.delete_documents()
 
 def upload_document():

requirements.txt

@@ -1,5 +1,5 @@
 safetensors==0.3.3.post1
-farm-haystack[inference,weaviate,opensearch]==1.20.0
+farm-haystack[inference,weaviate,opensearch,file-conversion,pdf]==1.20.0
 milvus-haystack
 streamlit==1.23.0
 markdown