import gradio as gr
from transformers import pipeline, AutoModelForQuestionAnswering, AutoTokenizer
import json

# Load the dataset
with open('faq_dataset.json') as f:
    faq_data = json.load(f)

# Initialize the model and tokenizer
model_name = "distilbert-base-uncased-distilled-squad"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
nlp = pipeline("question-answering", model=model, tokenizer=tokenizer)

# Create a function to get answers
def get_answer(question):
    for item in faq_data:
        context = item['answer']
        result = nlp(question=question, context=context)
        if result['score'] > 0.5:
            return result['answer']
    return "Sorry, I don't know the answer to that question."

# Create the Gradio interface with updated components
iface = gr.Interface(
    fn=get_answer,
    inputs=gr.Textbox(label="Ask a Question"),
    outputs=gr.Textbox(label="Answer"),
    title="FAQ Chatbot",
    description="Ask a question and get an answer from the FAQ dataset."
)

# Launch the interface
iface.launch()