Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Better external apps support for the Ollama AI enginer [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#16226•Fetched 2026-05-20 03:39:27
View on GitHub
Comments
1
Participants
2
Timeline
2
Reactions
0
Author
SIBA-DKSIBA-DK
Participants
rick-githubrick-githubSIBA-DKSIBA-DK
Timeline (top)
commented ×1labeled ×1

Code Example

# --------------------------------------------------------------------------------------------------------------------------
#
# Ollama setup added to Apple MacOSX users .zprofile 
#
# --------------------------------------------------------------------------------------------------------------------------
#
launchctl setenv OLLAMA_FLASH_ATTENTION "1";
launchctl setenv OLLAMA_HOST "0.0.0.0:11434";
launchctl setenv OLLAMA_LOAD_TIMEOUT "20";
launchctl setenv OLLAMA_NEW_ENGINE "1";
launchctl setenv OLLAMA_NOHISTORY "1";
launchctl setenv OLLAMA_ORIGINS "chrome-extension://*,moz-extension://*,safari-web-extension://*,*" ;
#
OLLAMA_FLASH_ATTENTION="1"
OLLAMA_HOST="0.0.0.0:11434"
OLLAMA_LOAD_TIMEOUT="20"
OLLAMA_NEW_ENGINE="1"
OLLAMA_NOHISTORY="1"
OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*,*"
#
export OLLAMA_FLASH_ATTENTION
export OLLAMA_HOST
export OLLAMA_LOAD_TIMEOUT
export OLLAMA_NEW_ENGINE
export OLLAMA_NOHISTORY
export OLLAMA_ORIGINS
#
# launchctl setenv OLLAMA_ORIGINS "*";
# Allow all Chrome, Firefox, and Safari extensions
# pkill ollama;
# nohup 'OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*,*" ollama serve' >/dev/null 2>&1 ;
# --------------------------------------------------------------------------------------------------------------------------

---

# --------------------------------------------------------------------------------------------------------------------------
#
#    Ollama AI server global setup added to file /etc/profile
#
# --------------------------------------------------------------------------------------------------------------------------
# export OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*"
# export OLLAMA_HOST="0.0.0.0:11434"
# export OLLAMA_SCHED_SPREAD="true"
#
export OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*,*"
export OLLAMA_HOST="0.0.0.0:11434"
export OLLAMA_SCHED_SPREAD="true"
export OLLAMA_MAX_LOADED_MODELS=3
export OLLAMA_FLASH_ATTENTION=1
export OLLAMA_KEEP_ALIVE=5m
export OLLAMA_DEBUG=3
export OLLAMA_CONTEXT_LENGTH=131072
export OLLAMA_LOAD_TIMEOUT=20
export OLLAMA_NUM_PARALLEL=6
# --------------------------------------------------------------------------------------------------------------------------
#
# --------------------------------------------------------------------------------------------------------------------------
#
#    Claude code local AI -- server global setup 
#
#    Note claude code is part of OLLAMA server 
# --------------------------------------------------------------------------------------------------------------------------
export ANTHROPIC_BASE_URL="http://localhost:11434"
export ANTHROPIC_AUTH_TOKEN="ollama"
export ANTHROPIC_API_KEY=""
#
#    to run    claude --model gpt-oss:20b
#
# --------------------------------------------------------------------------------------------------------------------------

---
RAW_BUFFERClick to expand / collapse

What is the issue?

I use , the following computers with Ollama

A) WIN11 - CUDA 2x RTX2080TI + 64Core AMD Threadripper +128GB ram B) Apple MacMini Pro M2 16GB ram C) Nvidia GDX Spark with GB10 128GB Ram + Nvidia Ubuntu Linux

With the above user case machines type B) & C) I experience problem in getting external application to talk to Ollama GUI APP when runs in its normal form , where Ollama automatically starts at boot.

Please could you update the Ollama GUI APP , so that you have expert users setting page which allows any users to set all of the available setting in Ollama , so that users can have much more control of how Ollama works so that they do not have to do all these work arrounds to fix annoying issues.

Computer B) & C) run different versions of unix like operating systems

These issues seem to be manly a unix user related issues , but they are very annoying I have to make work arround to fix basic issues.

I use the following programs with Ollama as the AI engine : Thunderbird_EMAIl - with the ThunderAI extenstion plug in https://addons.thunderbird.net/en-US/thunderbird/addon/thunderai-sparks/ https://github.com/micz/ThunderAI-Sparks Microsoft Excel - with the OLLAMA plugin for excel https://github.com/deepanshu88/ollama-excel Microsoft Edge Webrowser with the Ollama-ai extension https://chromewebstore.google.com/detail/ollama-ui/cmgdpmlhgjhoadnonobjeekmfcehffco

On my Apple MacMini , I have to stop the Ollama standard GUI application and then go into a unix shell and type : ollama serve

I also have to modify my Apple MacOSX user shell profile file : .zprofile with the following

# --------------------------------------------------------------------------------------------------------------------------
#
# Ollama setup added to Apple MacOSX users .zprofile 
#
# --------------------------------------------------------------------------------------------------------------------------
#
launchctl setenv OLLAMA_FLASH_ATTENTION "1";
launchctl setenv OLLAMA_HOST "0.0.0.0:11434";
launchctl setenv OLLAMA_LOAD_TIMEOUT "20";
launchctl setenv OLLAMA_NEW_ENGINE "1";
launchctl setenv OLLAMA_NOHISTORY "1";
launchctl setenv OLLAMA_ORIGINS "chrome-extension://*,moz-extension://*,safari-web-extension://*,*" ;
#
OLLAMA_FLASH_ATTENTION="1"
OLLAMA_HOST="0.0.0.0:11434"
OLLAMA_LOAD_TIMEOUT="20"
OLLAMA_NEW_ENGINE="1"
OLLAMA_NOHISTORY="1"
OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*,*"
#
export OLLAMA_FLASH_ATTENTION
export OLLAMA_HOST
export OLLAMA_LOAD_TIMEOUT
export OLLAMA_NEW_ENGINE
export OLLAMA_NOHISTORY
export OLLAMA_ORIGINS
#
# launchctl setenv OLLAMA_ORIGINS "*";
# Allow all Chrome, Firefox, and Safari extensions
# pkill ollama;
# nohup 'OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*,*" ollama serve' >/dev/null 2>&1 ;
# --------------------------------------------------------------------------------------------------------------------------

On my Nvidia GDX Spark I have had to modify the system main profile settings held /etc/profile

# --------------------------------------------------------------------------------------------------------------------------
#
#    Ollama AI server global setup added to file /etc/profile
#
# --------------------------------------------------------------------------------------------------------------------------
# export OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*"
# export OLLAMA_HOST="0.0.0.0:11434"
# export OLLAMA_SCHED_SPREAD="true"
#
export OLLAMA_ORIGINS="chrome-extension://*,moz-extension://*,safari-web-extension://*,*"
export OLLAMA_HOST="0.0.0.0:11434"
export OLLAMA_SCHED_SPREAD="true"
export OLLAMA_MAX_LOADED_MODELS=3
export OLLAMA_FLASH_ATTENTION=1
export OLLAMA_KEEP_ALIVE=5m
export OLLAMA_DEBUG=3
export OLLAMA_CONTEXT_LENGTH=131072
export OLLAMA_LOAD_TIMEOUT=20
export OLLAMA_NUM_PARALLEL=6
# --------------------------------------------------------------------------------------------------------------------------
#
# --------------------------------------------------------------------------------------------------------------------------
#
#    Claude code local AI -- server global setup 
#
#    Note claude code is part of OLLAMA server 
# --------------------------------------------------------------------------------------------------------------------------
export ANTHROPIC_BASE_URL="http://localhost:11434"
export ANTHROPIC_AUTH_TOKEN="ollama"
export ANTHROPIC_API_KEY=""
#
#    to run    claude --model gpt-oss:20b
#
# --------------------------------------------------------------------------------------------------------------------------

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#embedding generation#cache error#pipeline error#runtime error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

ollama - 💡(How to fix) Fix Better external apps support for the Ollama AI enginer [1 comments, 2 participants]