LOCAL model can't read Long Notes

[fabiensc0ville]

Describe how to reproduce
Both Chat and Long Note QA work great with LOCAL OLLAMA. However when I try local model on a long note, it ignores it, and comes back to the default prompt about Obsidian and AI

Expected behavior
Answer questions about the active note

Screenshots

CHAT MODE	LONG NOTE QA

Additional context
I believe the difference is the note length because it is the obvious one (it has 1 000 000 char and 1.2MB file size!), but I am not sure about it

[kiradzS]

Consumer-grade graphics cards cannot support the complete context token of the local model

[logancyang]

@fabiensc0ville have you checked the doc and set the context window explicitly in Ollama? https://github.com/logancyang/obsidian-copilot/blob/master/local_copilot.md#ollama

Also you didn't mention which model you were using, how long is its context window?