ocr_land_records/
├── main.py
├── ocr_words.py
├── words_to_lines.py
├── lines_to_rows.py
├── multipage_merge.py
├── build_final_json.py
├── bengali_normalize.py
├── utils.py
└── requirements.txt






For Chatgpt project
python3 -m venv venv
source venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txt

To run api for ssh session
uvicorn api_filter:app --reload --port 8000

To run continuously
nohup uvicorn app:app --host 0.0.0.0 --port 8900 > app.log 2>&1 &

To kill
sudo lsof -i :8900
sudo kill -9 858138


188.166.254.225,root, inQube@96740AI




Within this folder there are two projectsOne from ChatGPT and another one from Copilot. I am using Copilot right now. But ChatGPT part is also applicable but Copilot is best for now.


Call POST /process_docs with JSON body
{
  "document_urls": ["https://.../doc1.pdf", "..."],
  "data": [
    { "daag_no": "371", "khatian_no": "479", "farmer_name_en": "Ramsharon Mondal" },
    { "daag_no": "371", "khatian_no": "1077", "farmer_name_en": "Sushanta Mondal" }
  ]
}



curl -X POST "http://localhost:8000/process_docs" \
 -H "Content-Type: application/json" \
 -d '{
  "document_urls":["http://localhost:9000/371(Plot No)_Suahanta Mondal.pdf"],
  "data":[
    {"daag_no":"371","khatian_no":"479","farmer_name_en":"Ramsharon Mondal"},
    {"daag_no":"371","khatian_no":"1077","farmer_name_en":"Sushanta Mondal"}
  ]
}'



Aadhar Check payload 

{
  "aadhar_files": ["http://your.server/test_aadhar1.jpg"],
  "people": [{"name":"Suman Chatterjee","age":46}],
  "name_threshold": 0.78,
  "age_tolerance": 1,
  "debug": true
}