[GH-ISSUE #3872] Possibility to make the response leaner #2400

Closed
opened 2026-04-12 12:42:46 -05:00 by GiteaMirror · 1 comment
Owner

Originally created by @KevinKrueger on GitHub (Apr 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/3872

I have noticed that the return of the API if it is slightly larger in the answer due to the question, this is extremely inflated by the context, for example. A configuration option for the return parameters would be very useful here.

Originally created by @KevinKrueger on GitHub (Apr 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/3872 I have noticed that the return of the API if it is slightly larger in the answer due to the question, this is extremely inflated by the context, for example. A configuration option for the return parameters would be very useful here.
GiteaMirror added the feature request label 2026-04-12 12:42:46 -05:00
Author
Owner

@pdevine commented on GitHub (Jul 18, 2024):

@KevinKrueger Sorry for the slow reply; I'm a little unsure what you're asking for in the issue. You can change the parameters in your request to the API to:

  1. limit the context size
  2. add stop parameters

You can also tell the LLM as part of the prompt to not give as long of a reply.

I'm going to go ahead and close the issue, but we can reopen it if I didn't answer your question.

<!-- gh-comment-id:2237242218 --> @pdevine commented on GitHub (Jul 18, 2024): @KevinKrueger Sorry for the slow reply; I'm a little unsure what you're asking for in the issue. You can change the parameters in your request to the API to: 1. limit the context size 2. add stop parameters You can also tell the LLM as part of the prompt to not give as long of a reply. I'm going to go ahead and close the issue, but we can reopen it if I didn't answer your question.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2400