import gradio as gr
from util import summarizer, textproc
from util.examples import entries
import importlib

importlib.reload(summarizer)
importlib.reload(textproc)

model_collection = summarizer.init_models()
patent_summarizer = summarizer.PatentSummarizer(model_collection)
iface = gr.Interface(
    patent_summarizer.pipeline,
    theme="huggingface",
    examples=entries,
    examples_per_page=4,
    inputs=[
        gr.inputs.Textbox(label="Patent Information", 
                          placeholder="US10125002B2 or https://patents.google.com/patent/US10125002B2 ...", 
                          lines=1,
                          default="US10125002B2"),
        gr.inputs.CheckboxGroup(summarizer.summary_options, 
                                default=summarizer.summary_options,
                                label="Summaries to Generate"),
        gr.inputs.Dropdown(summarizer.model_names,
                           default=summarizer.model_names[3],
                           label="Abstract Model"),
        gr.inputs.Dropdown(summarizer.model_names,
                           default=summarizer.model_names[0],
                           label="Background Model"),
        gr.inputs.Dropdown(summarizer.model_names,
                           default=summarizer.model_names[2],
                           label="Claims Model"),
        gr.inputs.Checkbox(default=True, 
                           label="Collate Claims", 
                           optional=False),
        gr.inputs.Slider(minimum=250,
                         maximum=1000,
                         step=10,
                         default=250,
                         label="Input Document Word Limit"),
    ],
    outputs=[
        gr.outputs.Textbox(label="Abstract Summary"),
        gr.outputs.Textbox(label="Background Summary"),
        gr.outputs.Textbox(label="Sample Claims Summary")
    ],
    title="Patent Summarizer 📖",
    description="""
    v.1.0.0

    Reading through patent documents is oftentimes a long and tedious task.
    There are cases wherein one has to manually go through several pages in 
    order to determine if the patent is relevant to the prior art search.
    
    This application is meant to automate the initial phase of going through 
    patents so that the potential inventor or researcher may lessen the time 
    spent trying to filter documents.
    
    The Patent Summarizer:
    ✏️ Provides an interface for user input
    📂 Retrieves and parses the document from Patents Google based on the given patent information
    📑 Returns summaries for the abstract, background, and/or claims.
    
    Notes:
    - Increasing 'Input Document Word Limit' may improve results but will
    cause inference time to increase
    - Setting 'Collate Claims' to False will apply summarization across
    individual claims. Doing so will greatly increase inference time.

    Models explored:
    🤖 Big Bird: Transformers for Longer Sequences
    https://arxiv.org/abs/2007.14062 , https://huggingface.co/google/bigbird-pegasus-large-bigpatent
    🤖 T5
    https://arxiv.org/pdf/1910.10683.pdf , https://huggingface.co/cnicu/t5-small-booksum
    🤖 BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension 
    https://arxiv.org/abs/1910.13461, https://huggingface.co/sshleifer/distilbart-cnn-6-6
    🤖 PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
    https://arxiv.org/abs/1912.08777 , https://huggingface.co/google/pegasus-xsum
    """,
    
)

iface.launch(enable_queue=True)