app.py

import streamlit as st
from transformers import AutoModelForQuestionAnswering, AutoTokenizer
import torch

@st.cache_resource
def load_model():
    model_path = "YasirAbdali/roberta_qoura"  # Replace with your actual model path
    model = AutoModelForQuestionAnswering.from_pretrained(model_path)
    tokenizer = AutoTokenizer.from_pretrained(model_path)
    return model, tokenizer

def answer_question(question, model, tokenizer):
    inputs = tokenizer(question, return_tensors="pt", max_length=512, truncation=True, padding="max_length")
    
    with torch.no_grad():
        outputs = model(**inputs)
    
    start_logits = outputs.start_logits
    end_logits = outputs.end_logits
    
    start_index = torch.argmax(start_logits)
    end_index = torch.argmax(end_logits)
    
    answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(inputs["input_ids"][0][start_index:end_index+1]))
    
    return answer

st.title("Quora Question Answering")

model, tokenizer = load_model()

st.write("Enter a question, and the model will provide an answer based on its knowledge.")

question = st.text_area("Question")

if st.button("Get Answer"):
    if question:
        answer = answer_question(question, model, tokenizer)
        st.write("Answer:", answer)
    else:
        st.write("Please provide a question.")

# Optional: Add some example questions
st.sidebar.header("Example Questions")
example_questions = [
    "What is the capital of France?",
    "Who wrote 'Romeo and Juliet'?",
    "What is the boiling point of water?",
    "What year did World War II end?",
]
for example in example_questions:
    if st.sidebar.button(example):
        st.text_input("Question", value=example)