Update scripts/process.py

scripts/process.py

@@ -91,19 +91,8 @@ def load_document(
             documents.append(Document(content=text, 
                                       meta={"name": file_name}, 
                                       id_hash_keys=id_hash_keys))
-            
-            '''check if text is empty and apply different pdf processor. \
-            This can happen whith certain pdf types.'''
-            for i in documents: 
-                if i.content == "":
-                    st.write("using pdfplumber")
-                    text = []
-                    with pdfplumber.open(file_path) as pdf:
-                        for page in pdf.pages:
-                            text.append(page.extract_text())
-                    i.content = ' '.join([page for page in text])
-    
-        return documents
+
+            return documents
 
  
 def preprocessing(document):