Vector Store JSON Splitting

Questions
1

Describe the problem/error/question

I’ve just started diving deeper into vector databases and wanted to try uploading a JSON file into my Qdrant collection using n8n. However, the file gets split up in such a granular way that I can’t really understand the logic behind it. It would make sense to preserve the structure of the JSON so that relationships between the data can be captured, rather than treating each piece of information as standalone. But even with this small JSON file, 84 points are being created in Qdrant.

{
   "quiz": {
       "sport": {
           "q1": {
               "question": "Which one is correct team name in NBA?",
               "options": [
                   "New York Bulls",
                   "Los Angeles Kings",
                   "Golden State Warriros",
                   "Huston Rocket"
               ],
               "answer": "Huston Rocket"
           }
       },
       "maths": {
           "q1": {
               "question": "5 + 7 = ?",
               "options": [
                   "10",
                   "11",
                   "12",
                   "13"
               ],
               "answer": "12"
           },
           "q2": {
               "question": "12 - 8 = ?",
               "options": [
                   "1",
                   "2",
                   "3",
                   "4"
               ],
               "answer": "4"
           }
       }
   }
}

I look forward to your responses :slight_smile:

Please share your workflow

Information on your n8n setup

  • n8n version: 1.90.2
  • Database (default: SQLite): Default
  • n8n EXECUTIONS_PROCESS setting (default: own, main): default
  • Running n8n via (Docker, npm, n8n cloud, desktop app): Docker
  • Operating system: MacOS
1 Like
2

Hello Luxa!

Actually, I’m facing the same problem. I have a JSON file with almost 8 MB of size to upload, and it keeps running indefinitely. No record is being inserted on database…