Spaces:
Running
Running
File size: 1,757 Bytes
72f3c46 54f6bea 72f3c46 54f6bea 72f3c46 c81e42a 72f3c46 54f6bea 72f3c46 54f6bea 72f3c46 54f6bea 72f3c46 54f6bea 72f3c46 54f6bea 72f3c46 54f6bea |
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 |
import gradio as gr
import google.generativeai as genai
import base64
import io
from PIL import Image
import fitz # PyMuPDF
import os
# Configure Gemini API
genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
model = genai.GenerativeModel('gemini-1.5-flash')
# Prompt for Gemini
prompt = """
You are analyzing a medical document or an application form from patient.
Extract the following fields as JSON:
- Position applied for
- Office/Ministry
- Duty station
- First name(s)
- Surname
- Date of birth
- Gender
- Citizenship
- Postal Address
- Residential Address
- Email
- Phone number (mobile)
"""
def process_pdf(pdf_bytes: bytes):
doc = fitz.open(stream=pdf_bytes, filetype="pdf")
results = []
for page_num in range(len(doc)):
page = doc.load_page(page_num)
pix = page.get_pixmap(dpi=200)
# Convert to PIL image
image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
# Convert to JPEG bytes
buffered = io.BytesIO()
image.save(buffered, format="JPEG")
jpeg_bytes = buffered.getvalue()
# Send to Gemini
response = model.generate_content([
prompt,
{
"mime_type": "image/jpeg",
"data": jpeg_bytes
}
])
results.append(response.text.strip())
return "\n\n---\n\n".join(results)
# Gradio interface
demo = gr.Interface(
fn=process_pdf,
inputs=gr.File(type="binary", label="Upload PDF Form"),
outputs="textbox",
title="Healthelic Form Data Extractor (PDF Scanner) - Gemini 1.5 Flash",
description="Upload a scanned medical form in PDF format to extract key fields using Gemini 1.5 Flash."
)
if __name__ == "__main__":
demo.launch()
|