---
title: Teach the vision model your world before it looks
summary: Give the vision and reasoning models a few sentences of your own vocabulary before indexing, and everything indexed afterwards is better for it.
lede: A few sentences of your vocabulary, given to the models before they look
outcome: organise
tools: set_vision_context, set_reasoning_context, index_folder, job_wait, get_clip_metadata
order: 12
---

> Set this as GroundSlate's vision context before it indexes anything else: everything it is about to look at is a Pakistani street food channel; deep fried chicken at a Kohat bazaar stall, the cook is Ruzi Khan, the huge flat pan is a kadai, the yellow coating is spiced chickpea flour. Give the reasoning model the same vocabulary, so summaries and event names use it too. Then index /Volumes/Cards/2026-08, and when the first clips finish, show me their summaries so I can see whether the vocabulary took.

- It shows up in search, shot descriptions, summaries and event names.
- If your library reads as generic, a missing context is usually why, not the model.