Update pages/llm.py

pages/llm.py

@@ -33,8 +33,9 @@ def get_pdf_text(folder_path):
             for page in pdf_reader.pages:
                 text += page.extract_text()
             #text += '\n'
-
-    return translator.translate(text, src='de',dest ='en').text
+    text=text.replace("\n", " ")
+    text=text.replace("- ", "")
+    return translator.translate(text, dest ='en').text
 
 #Chunks erstellen
 def get_text_chunks(text):
@@ -80,7 +81,7 @@ def get_llm_answer(user_question):
             #if os.path.exists("./Store"): #Nutzereingabe nur eingelesen, wenn vectorstore angelegt
     # Retriever sucht passende Textausschnitte in den PDFs (unformatiert)
     translator = Translator()
-    translator.translate(user_question, src='de',dest='en')
+    translator.translate(user_question, dest='en')
     retriever=get_vectorstore().as_retriever()
     retrieved_docs=retriever.invoke(
     user_question
@@ -97,7 +98,7 @@ def get_llm_answer(user_question):
     # Frage beantworten mit Q&A Pipeline
     answer = qa_pipeline(question=user_question, context=context, max_length=200)
     
-    return translator.translate(answer["answer"], src='en', dest='de')
+    return translator.translate(answer["answer"],dest='de')
    
 def main():
     st.set_page_config(