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 #11458] keep_alive Parameter Ignored When Using OpenAI SDK with Ollama API #54079

New Issue
Closed
opened 2026-04-29 05:11:30 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-29 05:11:30 -05:00
Owner
Copy Link

Originally created by @alexander-fischer on GitHub (Jul 17, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11458

What is the issue?

When using the OpenAI SDK to call the Ollama /chat/completions endpoint and passing keep_alive as an extra argument in the request body, Ollama appears to ignore the provided value. Instead, it defaults to the standard 5 minutes, even if a different value (e.g., "24h") is explicitly set.

My code:

client = openai.OpenAI(base_url="http://localhost:11434/v1", api_key=LLM_API_KEY)

def stream_llm(instruction: str, model_id: str):
    return client.chat.completions.create(
        model=model_id,
        messages=[{"role": "user", "content": instruction}],
        temperature=0.1,
        extra_body={"keep_alive": "24h"},
        stream=True,
    )

Curl command to reproduce:

curl -X POST http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "Whats the weather in London?"
      }
    ],
    "model": "gemma3:1b-it-qat",
    "temperature": 0.1,
    "keep_alive": "24h"
  }'

Expected behavior

The keep_alive parameter should be respected, and the session/model should be kept alive for the specified duration (e.g., 24 hours), not the default 5 minutes.

Actual behavior

Ollama defaults to the 5-minute keep_alive, ignoring the value provided in the request body.

Environment:
Ollama version: 0.9.6
OpenAI SDK version: 1.96.1
Operating System: MacOS

Relevant log output

OS

macOS

GPU

No response

CPU

No response

Ollama version

0.9.6

Originally created by @alexander-fischer on GitHub (Jul 17, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11458 ### What is the issue? When using the OpenAI SDK to call the Ollama /chat/completions endpoint and passing keep_alive as an extra argument in the request body, Ollama appears to ignore the provided value. Instead, it defaults to the standard 5 minutes, even if a different value (e.g., "24h") is explicitly set. My code: ```python client = openai.OpenAI(base_url="http://localhost:11434/v1", api_key=LLM_API_KEY) def stream_llm(instruction: str, model_id: str): return client.chat.completions.create( model=model_id, messages=[{"role": "user", "content": instruction}], temperature=0.1, extra_body={"keep_alive": "24h"}, stream=True, ) ``` Curl command to reproduce: ```bash curl -X POST http://localhost:11434/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Whats the weather in London?" } ], "model": "gemma3:1b-it-qat", "temperature": 0.1, "keep_alive": "24h" }' ``` **Expected behavior** The keep_alive parameter should be respected, and the session/model should be kept alive for the specified duration (e.g., 24 hours), not the default 5 minutes. **Actual behavior** Ollama defaults to the 5-minute keep_alive, ignoring the value provided in the request body. Environment: Ollama version: 0.9.6 OpenAI SDK version: 1.96.1 Operating System: MacOS ### Relevant log output ```shell ``` ### OS macOS ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.9.6
GiteaMirror added the bug label 2026-04-29 05:11:30 -05:00
GiteaMirror commented 2026-04-29 05:11:33 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jul 17, 2025):

#2963

<!-- gh-comment-id:3083765201 --> @rick-github commented on GitHub (Jul 17, 2025): #2963
GiteaMirror commented 2026-04-29 05:11:34 -05:00
Author
Owner
Copy Link

@onakatomi commented on GitHub (Nov 12, 2025):

Did you figure this out?

<!-- gh-comment-id:3524336521 --> @onakatomi commented on GitHub (Nov 12, 2025): Did you figure this out?
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 bug
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#54079
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?