Spaces:
Running
Running
| import streamlit as st | |
| import wikipedia | |
| from haystack.document_stores import InMemoryDocumentStore | |
| from haystack.utils import clean_wiki_text, convert_files_to_docs | |
| from haystack.nodes import TfidfRetriever, FARMReader | |
| from haystack.pipelines import ExtractiveQAPipeline | |
| from main import print_qa, QuestionGenerator | |
| def main(): | |
| # Set the Streamlit app title | |
| st.title("Question Generation using Haystack and Streamlit") | |
| # Select the input type | |
| inputs = ["Input Paragraph", "Wikipedia Examples"] | |
| input_type = st.selectbox("Select an input type:", inputs) | |
| # Initialize wiki_text as an empty string | |
| wiki_text = "" | |
| # Handle different input types | |
| if input_type == "Input Paragraph": | |
| # Allow user to input text paragraph | |
| wiki_text = st.text_area("Input paragraph:", height=200) | |
| elif input_type == "Wikipedia Examples": | |
| # Define topics for selection | |
| topics = ["Deep Learning", "Machine Learning"] | |
| selected_topic = st.selectbox("Select a topic:", topics) | |
| # Retrieve Wikipedia content based on the selected topic | |
| if selected_topic: | |
| wiki = wikipedia.page(selected_topic) | |
| wiki_text = wiki.content | |
| # Display the retrieved Wikipedia content (optional) | |
| st.text_area("Retrieved Wikipedia content:", wiki_text, height=200) | |
| # Preprocess the input text | |
| wiki_text = clean_wiki_text(wiki_text) | |
| # Allow user to specify the number of questions to generate | |
| num_questions = st.slider("Number of questions to generate:", min_value=1, max_value=20, value=5) | |
| # Allow user to specify the model to use | |
| model_options = ["deepset/roberta-base-squad2", "deepset/roberta-base-squad2-distilled", "bert-large-uncased-whole-word-masking-squad2", "deepset/flan-t5-xl-squad2"] | |
| model_name = st.selectbox("Select model:", model_options) | |
| # Button to generate questions | |
| if st.button("Generate Questions"): | |
| document_store = InMemoryDocumentStore() | |
| # Convert the preprocessed text into a document | |
| document = {"content": wiki_text} | |
| document_store.write_documents([document]) | |
| # Initialize a TfidfRetriever | |
| retriever = TfidfRetriever(document_store=document_store) | |
| # Initialize a FARMReader with the selected model | |
| reader = FARMReader(model_name_or_path=model_name, use_gpu=False) | |
| # Initialize the question generation pipeline | |
| pipe = ExtractiveQAPipeline(reader, retriever) | |
| # Initialize the QuestionGenerator | |
| qg = QuestionGenerator() | |
| # Generate multiple-choice questions | |
| qa_list = qg.generate( | |
| wiki_text, | |
| num_questions=num_questions, | |
| answer_style='multiple_choice' | |
| ) | |
| # Display the generated questions and answers | |
| st.header("Generated Questions and Answers:") | |
| for idx, qa in enumerate(qa_list): | |
| # Display the question | |
| st.write(f"Question {idx + 1}: {qa['question']}") | |
| # Display the answer options | |
| if 'answer' in qa: | |
| for i, option in enumerate(qa['answer']): | |
| correct_marker = "(correct)" if option["correct"] else "" | |
| st.write(f"Option {i + 1}: {option['answer']} {correct_marker}") | |
| # Add a separator after each question-answer pair | |
| st.write("-" * 40) | |
| # Run the Streamlit app | |
| if __name__ == "__main__": | |
| main() | |