github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 08:02:14 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8354] Dynamic context size in OpenAI API compatibility. #5356

New Issue
Closed
opened 2026-04-12 16:33:42 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 16:33:42 -05:00
Owner
Copy Link

Originally created by @x0wllaar on GitHub (Jan 9, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8354

I noticed that the issue (#5356 ) regarding dynamically setting the context size (num_ctx) in OpenAI API was closed with a note saying it wasn't possible due to limitations of the API. However, I'd like to reopen this discussion as there seems to be a using the extra_body parameter available in the OpenAI API clients. This parameter allows to pass arbitrary data/parameters to the endpoint, and will be useful here.

It should be possible to pass additional parameters through the API call with the extra_body option, as shown below:

client.chat.completions.create(
    model="phi4",
    messages=messages,
    extra_body={"num_ctx": 16384},
)

See https://github.com/openai/openai-python/blob/main/src/openai/resources/chat/completions.py#L102 for normal and https://github.com/openai/openai-python/blob/main/src/openai/resources/beta/chat/completions.py#L101 for structured completion functions.

I would also like to note that other implementations of OpenAI API already use this approach, for example, here's vLLM: https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#extra-parameters

I'm willing to work on a pull request if you think this approach is feasible. There already is a similar PR #5357, I'm ready to help getting it to a mergeable state.

Thank you so much for all your work on Ollama!

Originally created by @x0wllaar on GitHub (Jan 9, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8354 I noticed that the issue (#5356 ) regarding dynamically setting the context size (num_ctx) in OpenAI API was closed with a note saying it wasn't possible due to limitations of the API. However, I'd like to reopen this discussion as there seems to be a using the extra_body parameter available in the OpenAI API clients. This parameter allows to pass arbitrary data/parameters to the endpoint, and will be useful here. It should be possible to pass additional parameters through the API call with the extra_body option, as shown below: ``` client.chat.completions.create( model="phi4", messages=messages, extra_body={"num_ctx": 16384}, ) ``` See https://github.com/openai/openai-python/blob/main/src/openai/resources/chat/completions.py#L102 for normal and https://github.com/openai/openai-python/blob/main/src/openai/resources/beta/chat/completions.py#L101 for structured completion functions. I would also like to note that other implementations of OpenAI API already use this approach, for example, here's vLLM: https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#extra-parameters I'm willing to work on a pull request if you think this approach is feasible. There already is a similar PR #5357, I'm ready to help getting it to a mergeable state. Thank you so much for all your work on Ollama!
GiteaMirror added the feature request label 2026-04-12 16:33:42 -05:00
GiteaMirror commented 2026-04-12 16:33:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 9, 2025):

https://github.com/ollama/ollama/pull/6504

<!-- gh-comment-id:2578965503 --> @rick-github commented on GitHub (Jan 9, 2025): https://github.com/ollama/ollama/pull/6504
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#5356
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?