app.py

from transformers import LayoutLMForTokenClassification, LayoutLMTokenizer
import gradio as gr
import cv2
import easyocr
from simple_salesforce import Salesforce
import re

# Salesforce credentials
Salesforce_User_Name = 'sathkruthatech@hms.com'  # Your Salesforce username
Salesforce_Password = 'Sathkrutha@06'
SALESFORCE_INSTANCE_URL = 'https://sathkruthatechsolutions63-dev-ed.develop.lightning.force.com'
SALESFORCE_ACCESS_TOKEN = 'UnByPih7PWmoWLzRuRyFrXzw'

# Initialize EasyOCR reader for text extraction
reader = easyocr.Reader(['en'])

# Load pre-trained LayoutLM model and tokenizer
model = LayoutLMForTokenClassification.from_pretrained("microsoft/layoutlm-large-uncased")
tokenizer = LayoutLMTokenizer.from_pretrained("microsoft/layoutlm-large-uncased")

# Salesforce Connection Setup
sf = Salesforce(username=Salesforce_User_Name, password=Salesforce_Password, security_token=SALESFORCE_ACCESS_TOKEN)

# Function to extract text using EasyOCR and process with LayoutLM
def extract_patient_info(image):
    # Convert the uploaded image to RGB (required by LayoutLM)
    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

    # Use EasyOCR to extract text from the image
    result = reader.readtext(image_rgb)
    
    # Debug: Print OCR result
    print("OCR Result:", result)
    
    # Extracted text from OCR
    extracted_text = " ".join([detection[1] for detection in result])
    
    # Debug: Print the extracted text
    print("Extracted Text:", extracted_text)

    # Extract relevant details (Name, Age, Gender, Phone number) from the extracted text
    details = extract_details_from_text(extracted_text)
    
    # Debug: Print parsed details
    print("Parsed Details:", details)
    
    # Create a record in Salesforce using the extracted details
    create_salesforce_record(details)

    # Return the extracted text for display
    return extracted_text

# Function to extract details from the extracted text using regex
def extract_details_from_text(extracted_text):
    # Regex patterns to match Name, Age, Gender, and Phone number
    details = {}

    # Extract Name
    name_match = re.search(r"Name[:\s]*([A-Za-z\s]+)", extracted_text)
    if name_match:
        details['Name'] = name_match.group(1)
    else:
        print("Error: Name not found!")

    # Extract Age
    age_match = re.search(r"Age[:\s]*([\d]+)", extracted_text)
    if age_match:
        details['Age'] = age_match.group(1)
    else:
        print("Error: Age not found!")

    # Extract Gender
    gender_match = re.search(r"Gender[:\s]*(Male|Female)", extracted_text, re.IGNORECASE)
    if gender_match:
        details['Gender'] = gender_match.group(1)
    else:
        print("Error: Gender not found!")

    # Extract Phone number
    phone_match = re.search(r"Phone number[:\s]*([\d]+)", extracted_text)
    if phone_match:
        details['Phone Number'] = phone_match.group(1)
    else:
        print("Error: Phone number not found!")

    return details

# Function to create a record in Salesforce using the extracted details
def create_salesforce_record(details):
    # Prepare the data to be inserted into Salesforce
    data = {
        'Name__c': details['Name'],
        'Age__c': int(details['Age']),
        'Gender__c': details['Gender'],
        'Phone_Number__c': details['Phone Number']
    }
    
    # Debug: Print the data before inserting into Salesforce
    print("Data to be inserted into Salesforce:", data)
    
    try:
        # Create a new record in Salesforce
        sf.Patient_Registration__c.create(data)
        print("Salesforce record created successfully!")
    except Exception as e:
        # Handle any exceptions during Salesforce record creation
        print(f"Error creating Salesforce record: {e}")

# Gradio interface setup
with gr.Blocks() as demo:
    gr.Markdown("### OCR Using LayoutLM Pretrained Model with EasyOCR and Salesforce Integration")

    # Image upload component
    image_input = gr.Image(type="numpy", label="Upload Image")

    # Output textboxes to display the extracted information
    output_text = gr.Textbox(label="Extracted Text")

    # Button to trigger image processing and text extraction
    process_button = gr.Button("Process Image")

    # When the button is clicked, process the image and show results in textboxes
    process_button.click(fn=extract_patient_info, inputs=image_input, outputs=output_text)

# Launch the Gradio app
if __name__ == "__main__":
    demo.launch()