github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #9440] Allow change of the context window from Python #6155

New Issue
Closed
opened 2026-04-12 17:30:18 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 17:30:18 -05:00
Owner
Copy Link

Originally created by @mmb78 on GitHub (Mar 1, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9440

It would be great if one could change the context window length parameter "num_ctx" also from Python when using OpenAI library.
So that this can be regulated per request and not globally for the ollama server.

Originally created by @mmb78 on GitHub (Mar 1, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9440 It would be great if one could change the context window length parameter "num_ctx" also from Python when using OpenAI library. So that this can be regulated per request and not globally for the ollama server.
GiteaMirror added the feature request label 2026-04-12 17:30:18 -05:00
GiteaMirror commented 2026-04-12 17:30:19 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 1, 2025):

Changing the size of the context in the API will cause a model reload. The best approach is to set the context length to the maximum required and just let the clients use whatever part of the buffer they need. For openAI calls, you can either set num_ctx on a per-model basis in the Modelfile, or set OLLAMA_CONTEXT_LENGTH on a server-wide basis.

<!-- gh-comment-id:2692244422 --> @rick-github commented on GitHub (Mar 1, 2025): Changing the size of the context in the API will cause a model reload. The best approach is to set the context length to the maximum required and just let the clients use whatever part of the buffer they need. For openAI calls, you can either set `num_ctx` on a per-model basis in the [Modelfile](https://github.com/ollama/ollama/blob/main/docs/openai.md#setting-the-context-size), or set [`OLLAMA_CONTEXT_LENGTH`](https://github.com/ollama/ollama/blob/bebb6823c03df34404753e42a41e7be8049d3146/envconfig/config.go#L258C1-L259C1) on a server-wide basis.
GiteaMirror commented 2026-04-12 17:30:20 -05:00
Author
Owner
Copy Link

@mmb78 commented on GitHub (Mar 1, 2025):

Well .. this seems to be possible:

curl http://localhost:11434/api/generate -d '{
"model": "llama3.2",
"prompt": "Why is the sky blue?",
"options": {
"num_ctx": 4096
}
}'

It would be nice, if I could do that from Python.

<!-- gh-comment-id:2692268241 --> @mmb78 commented on GitHub (Mar 1, 2025): Well .. this seems to be possible: curl http://localhost:11434/api/generate -d '{ "model": "llama3.2", "prompt": "Why is the sky blue?", "options": { "num_ctx": 4096 } }' It would be nice, if I could do that from Python.
GiteaMirror commented 2026-04-12 17:30:20 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Mar 1, 2025):

You can do it from python, for the ollama API. You can't do it for the openAI API.

<!-- gh-comment-id:2692278540 --> @rick-github commented on GitHub (Mar 1, 2025): You can do it from python, for the ollama API. You can't do it for the openAI API.
GiteaMirror commented 2026-04-12 17:30:21 -05:00
Author
Owner
Copy Link

@lemassykoi commented on GitHub (Mar 4, 2025):

You can do it from python, for the ollama API. You can't do it for the openAI API.

this is possible with ChatOllama from langchain_ollama too

<!-- gh-comment-id:2697323368 --> @lemassykoi commented on GitHub (Mar 4, 2025): > You can do it from python, for the ollama API. You can't do it for the openAI API. this is possible with ChatOllama from langchain_ollama too
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#6155
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?