(github.com)

129 points arkohut | 1 comments | 17 Nov 24 12:59 UTC | HN request time: 0.204s | source

Show context

moltar ◴[17 Nov 24 17:26 UTC] No.42165442[source]▶

How’s the performance with Python? What’s the overhead?

1. arkohut ◴[18 Nov 24 05:27 UTC] No.42169941[source]▶

In fact, this project is indeed very computing-consuming, but it’s not Python’s fault. The main reason lies in the use of several machine learning models:

  1. OCR model
  2. Embedding model
  3. VLM model (optional)

I’ve tried many optimization approaches to ensure it doesn’t affect daily usage, though this comes at the cost of reduced search performance.

↑

Memos – An open source Rewinds / Recall