github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #670] Context at each token, to allow interrupting a response? #46811

New Issue
Closed
opened 2026-04-28 00:19:41 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 00:19:41 -05:00
Owner
Copy Link

Originally created by @tonyg on GitHub (Oct 2, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/670

Forgive me if I misunderstand, but would it be possible to get context at every streamed JSON partial-response, instead of just at the end, to allow the user to interrupt a response without the conversation losing a memory of how far it had gotten before being interrupted?

Originally created by @tonyg on GitHub (Oct 2, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/670 Forgive me if I misunderstand, but would it be possible to get context at every streamed JSON partial-response, instead of just at the end, to allow the user to interrupt a response without the conversation losing a memory of how far it had gotten before being interrupted?
GiteaMirror added the feature request label 2026-04-28 00:19:41 -05:00
GiteaMirror commented 2026-04-28 00:19:59 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Dec 24, 2023):

Hi there, we've designed the new Chat completion endpoint for this use case. With chat completions, no more worrying about passing in context. Instead, you can accumulate the response-so-far and send that in next.

I'll mark this issue as closed, that said let me know if it doesn't solve your use case and I'll make sure to re-open it :)

<!-- gh-comment-id:1868598605 --> @jmorganca commented on GitHub (Dec 24, 2023): Hi there, we've designed the new [Chat completion](https://github.com/jmorganca/ollama/blob/main/docs/api.md#generate-a-chat-completion) endpoint for this use case. With chat completions, no more worrying about passing in `context`. Instead, you can accumulate the response-so-far and send that in next. I'll mark this issue as closed, that said let me know if it doesn't solve your use case and I'll make sure to re-open it :)
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#46811
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?