dc-ml-emea-ar/app_emea_ar.py

from flask import Flask, request, jsonify, render_template  
from flasgger import Swagger, swag_from
from main import EMEA_AR_Parsing
from utils.logger import logger
from utils.biz_utils import clean_folder
from tqdm import tqdm
import pandas as pd
import os

  
template = {
    "info": {
        "title": "EMEA AR Data Extraction API",
        "description": 'EMEA AR Data Extraction API',
        "version": "1.0"
    }
}
app = Flask(__name__)
# By Swagger, we can see the API documentation in the browser, the example URL is http://127.0.0.1:8080/apidocs/
swagger = Swagger(app, template=template)

  
@app.route('/automation/api/model/emea_ar', methods=['POST'])
@swag_from('yml/emea_ar.yml')
def emea_ar_data_extract():
    """
    Extract EMEA AR cost data from EMEA LUX PDF document
    input sample:
    {
        "doc_id": "501380553"
    }
    output: EMEA AR cost data as a list of dictionaries
    :return:
    :rtype:
    """
    logger.info('EMEA AR data extraction begin')
    doc_id = request.json.get('doc_id')
  
    if not doc_id:  
        return jsonify({"error": "doc_id is required"}), 400
    
    pdf_folder = r"./data/emea_ar/pdf/"
    output_pdf_text_folder = r"./data/emea_ar/output/pdf_text/"
    output_extract_data_folder = r"./data/emea_ar/output/extract_data/docs/"
    output_mapping_data_folder = r"./data/emea_ar/output/mapping_data/docs/"
    drilldown_folder = r"./data/emea_ar/output/drilldown/"
    db_mapping_document_folder = r"./data/emea_ar/output/db_mapping/document/"
    db_mapping_provider_folder = r"./data/emea_ar/output/db_mapping/provider/"
    extract_way = "text"
    
    os.makedirs(pdf_folder, exist_ok=True)
    os.makedirs(output_pdf_text_folder, exist_ok=True)
    os.makedirs(output_extract_data_folder, exist_ok=True)
    os.makedirs(output_mapping_data_folder, exist_ok=True)
    os.makedirs(drilldown_folder, exist_ok=True)
    os.makedirs(db_mapping_document_folder, exist_ok=True)
    os.makedirs(db_mapping_provider_folder, exist_ok=True)
    
    clean_folder(pdf_folder)
    clean_folder(output_pdf_text_folder)
    clean_folder(output_extract_data_folder)
    clean_folder(output_mapping_data_folder)
    clean_folder(drilldown_folder)
    clean_folder(db_mapping_document_folder)
    clean_folder(db_mapping_provider_folder)
    
    re_run_extract_data = False
    re_run_mapping_data = False
    
    try:
        emea_ar_parsing = EMEA_AR_Parsing(doc_id=doc_id,
                                          doc_source="emea_ar",
                                          pdf_folder=pdf_folder,
                                          output_pdf_text_folder=output_pdf_text_folder,
                                          output_extract_data_folder=output_extract_data_folder,
                                          output_mapping_data_folder=output_mapping_data_folder,
                                          extract_way=extract_way,
                                          drilldown_folder=drilldown_folder,
                                          compare_with_provider=False)
        doc_data_from_gpt, annotation_list = emea_ar_parsing.extract_data(re_run=re_run_extract_data)
        doc_mapping_data = emea_ar_parsing.mapping_data(
            data_from_gpt=doc_data_from_gpt, re_run=re_run_mapping_data
        )
        results = {"extract_data": doc_mapping_data,
                   "annotation_data": annotation_list}
        return jsonify(results)
    except Exception as e:
        logger.error(f"Error: {e}")
        results = {"extract_data": [],
                   "annotation_data": [],
                   "error": str(e)}
        return jsonify(results)


if __name__ == '__main__':
    # Add use_reloader = False to avoid init twice
    app.run(host='0.0.0.0', port="8080", debug=False, use_reloader=False)