AI Sauna/Vector database of Senates Justice Department

Vector database of Senate Justice Department edit

Description edit

We wanted to try how vector databases help in search of HTR'd data. We used the data created by National Archives of Finland and stored it into vector database (Qdrant) that was set up by the National Library of Finland.

We also tried to create QA bots, but we ran out of time.

The team edit

  • Atte Föhr
  • Mikko Lipsanen
  • Juho Inkinen
  • Ilkka Jokipii

Created by: $4

Team members: $6

Results edit

Our method edit

Resources we used edit

National Library of Finland installation of Qdrant vector database

OpenAI embedding models on National Library of Finland's Azure

Conclusion edit

  • Embedding and storing the embeddings in vector database is quite simple
  • Qdrant visualisation tool is a nice way explore the data

What next edit

Do you wish to continue exploring this? What was not covered? What did you get curious about?

Links, images, documentation edit

Upload at least one image to Wikimedia Commons for the image of the page banner.