txtai
Joined 4 years ago
Karma
243
Submissions
198
Member since
Feb 25
Joined 4 years ago
It's an embeddings database of Wikipedia abstracts with page view data integrated to enable filtering pages based on popularity in addition to similarity.
This is a pretty straight forward problem and a good fit for a standard text classifier as well.
Here is an example of fine-tuning a model with txtai: https://colab.research.google.com/github/neuml/txtai/blob/ma...
For example: SELECT id, text, date FROM txtai WHERE similar('machine learning') AND date >= '2023-03-30'
GitHub: https://github.com/neuml/txtai
This article is a deep dive on how the index format works: https://neuml.hashnode.dev/anatomy-of-a-txtai-index