app.py

import gradio as gr
import pandas as pd
from util import summarizer, textproc

summary_options = ["Abstract", "Background", "Claims"]
model_names = ["google/bigbird-pegasus-large-bigpatent", 
               "huggingface/sshleifer/distilbart-cnn-12-6", 
               "huggingface/facebook/bart-large-cnn", 
               "huggingface/google/pegasus-xsum"]
      
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="US9820315B2 or https://patents.google.com/patent/US9820315B2 ...", 
                          lines=1,
                          default="US9820315B2"),
        # gr.inputs.Radio(["Link", "Patent Code"]), # Can be figured out automatically via parsing
        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=5,
                         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 based on the given patent information
    📑 Returns summaries for the abstract, background, and/or claims.
    
    Models explored:
    - https://huggingface.co/google/bigbird-pegasus-large-bigpatent
    - https://huggingface.co/cnicu/t5-small-booksum
    - https://huggingface.co/sshleifer/distilbart-cnn-6-6
    - https://huggingface.co/google/pegasus-xsum
    """
)

iface.launch()