File size: 1,257 Bytes
2aa380f d8432f9 2aa380f d8432f9 2aa380f d8432f9 2aa380f d8432f9 2aa380f d8432f9 2aa380f d8432f9 2aa380f |
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 |
# app.py
import gradio as gr
import pdfplumber
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# Load the model
model_name = "ibm-granite/granite-docling-258m-demo"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
# Function to extract text from PDF
def extract_text_from_pdf(pdf_file):
text = ""
with pdfplumber.open(pdf_file.name) as pdf:
for page in pdf.pages:
page_text = page.extract_text()
if page_text:
text += page_text + "\n"
return text
# Function to generate JSON from text
def pdf_to_json(pdf_file):
text = extract_text_from_pdf(pdf_file)
inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=2048)
outputs = model.generate(**inputs, max_new_tokens=1024)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
return result
# Gradio interface
interface = gr.Interface(
fn=pdf_to_json,
inputs=gr.File(file_types=[".pdf"]),
outputs=gr.Textbox(label="Generated JSON"),
title="PDF to JSON using Granite DocLing",
description="Upload a PDF and get a JSON output using the ibm-granite/granite-docling-258m-demo model."
)
interface.launch()
|