import gradio as gr
from fastai.text.all import *
from blurr.text.data.all import *
from blurr.text.modeling.all import *
from transformers import T5Tokenizer, T5ForConditionalGeneration
from transformers import BartForConditionalGeneration

# Load the pre-trained model and tokenizer
pretrained_model_name = "facebook/bart-large-cnn"
hf_tokenizer = T5Tokenizer.from_pretrained(pretrained_model_name)
learn = load_learner('article_highlights.pkl')

def summarize(article):
  # Preprocess the input text
  processed_text = learn.dblock.pipeline(article)

  # Generate the summary
  summary = learn.predict(processed_text)[0]['highlights']

  return summary

# Create the Gradio interface
iface = gr.Interface(
    fn=summarize,
    inputs="text",
    outputs="text",
    title="Article Summarizer (Part 3)",
    description="Enter an article and get a summary.",
    examples=[["This is an example article..."]]
)

# Launch the Gradio interface
iface.launch()