←back to thread

Run structured extraction on documents/images locally with Ollama and Pydantic

(github.com)
166 points EarlyOom | 1 comments | 20 Feb 25 01:54 UTC | HN request time: 0.214s | source
Show context
Inviz ◴[20 Feb 25 09:49 UTC] No.43112884[source]▶
What are the most promising ways to extract information from picture like this, if the domain has strict time constraints? What's the second best way that is still fast?
replies(1): >>43115335 #
1. fzysingularity ◴[20 Feb 25 14:50 UTC] No.43115335[source]▶
You can always distill VLMs into much smaller / faster models that’s specific to your domain or use-case.

What’s the use-case and what kind of latency do you require?