File size: 3,958 Bytes
5822e62 e5c5bb1 5822e62 ae94f55 2f10589 5822e62 523db29 5822e62 a9ec8e1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 |
import os
os.system('git clone https://github.com/facebookresearch/detectron2.git@v0.6')
os.system('pip install -e detectron2')
os.system("git clone https://github.com/microsoft/unilm.git")
os.system("sed -i 's/from collections import Iterable/from collections.abc import Iterable/' unilm/dit/object_detection/ditod/table_evaluation/data_structure.py")
os.system("curl -LJ -o publaynet_dit-b_cascade.pth 'https://layoutlm.blob.core.windows.net/dit/dit-fts/publaynet_dit-b_cascade.pth?sv=2022-11-02&ss=b&srt=o&sp=r&se=2033-06-08T16:48:15Z&st=2023-06-08T08:48:15Z&spr=https&sig=a9VXrihTzbWyVfaIDlIT1Z0FoR1073VB0RLQUMuudD4%3D'")
import sys
sys.path.append("unilm")
sys.path.append("detectron2")
import uuid # Import the UUID library
import torch
import gradio as gr
from pdfextract_fun import *
from pdfsummary_fun import *
from imagesummary_fun import *
# Assuming all your defined functions are above and imported correctly into this script
@spaces.GPU
def process_pdf(pdf_file,state):
#base_name = os.path.splitext(os.path.basename(pdf_file.name))[0]
unique_id = str(uuid.uuid4()) # Generate a unique identifier
output_folder = os.path.join("processed_files", unique_id) # Use UUID for the output folder name, within a parent directory
if not os.path.exists(output_folder):
os.makedirs(output_folder)
# Convert the uploaded PDF file to JPG images
convert_pdf_to_jpg(pdf_file.name, output_folder)
# Process the images to analyze and extract instances, then rename files sequentially and perform OCR
process_jpeg_images(output_folder)
#process_jpeg_images(output_folder)
rename_files_sequentially(output_folder)
ocr_folder(output_folder)
image_files = [os.path.join(output_folder, f) for f in os.listdir(output_folder)
if f.endswith('.jpg') and ('figure' in f or 'table' in f)]
#images = [Image.open(f) for f in image_files]
images = [(Image.open(f), os.path.basename(f).split('.')[0]) for f in image_files]
# For demonstration, let's just return the path to the output folder
# In a real app, you'd want to return images, texts, or links to download the results
return images, output_folder
def call_pdf_summary(state):
ocr_results_folder = os.path.join(state, "ocr_results")
summary = pdf_summary(ocr_results_folder) # Assuming pdf_summary accepts an output folder argument
return summary
def handle_summary_button_click(selected_images):
# Check if any image is selected
summary = get_image_summary(selected_images)
return summary
with gr.Blocks(theme=gr.themes.Monochrome()) as app:
gr.Markdown("# ChatPaper!")
state = gr.State() # Initialize state
with gr.Row():
file_input = gr.File(type="filepath", label="Upload a PDF")
with gr.Row():
gallery_output = gr.Gallery(label="Extracted Figures and Tables", show_label=True,columns=[3], rows=[1], object_fit="contain", height="auto")
with gr.Column():
summary_output = gr.Textbox(label="PDF Summary")
summary_button = gr.Button("Generate Summary")
with gr.Row():
# Initialize Dropdown without choices; they will be set dynamically
image_input = gr.Image(label="Select an Figure or Table for analysis",type='filepath',show_label=True, height="auto")
with gr.Column():
image_summary_output = gr.Textbox(label="Figure or Table analysis")
image_summary_button = gr.Button("Generate Figure or Table analysis")
file_input.change(process_pdf, inputs=[file_input, state], outputs=[gallery_output, state])
summary_button.click(call_pdf_summary, inputs=[state], outputs=[summary_output])
image_summary_button.click(handle_summary_button_click, inputs=image_input, outputs=image_summary_output)
# Note: Authentication details removed for security reasons
app.launch(share=True) # Launch the app with sharing enabled |