Comment

Comment by Adityav369

We have two ingestion pathways: 1. regular OCR + text embeddings; 2. Colpali. We've observed that Colpali does a much better job with tables since it can encode positional stuff and layouts as well.
parent Adityav369 1 year ago

Discussion

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton