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 #885] Add Parameter Environment="OLLAMA_HOST=127.0.0.1:11434" to the ollama.service file #427

New Issue
Closed
opened 2026-04-12 10:05:05 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 10:05:05 -05:00
Owner
Copy Link

Originally created by @byteconcepts on GitHub (Oct 23, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/885

For those who prefer to use ollama primarily via it's API it would be nice if the ollama.service file would already contain the line...
Environment="OLLAMA_HOST=127.0.0.1:11434"

Additionally it would be nice if the info that for the service the interface IP and Port may be changed in this file, would be added to the Readme.

For access over all interfaces on port 4711 change to:
Environment="OLLAMA_HOST=0.0.0.0:4711"

But if you like to use the console command then, you then need to use it like this:
OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS]:4711" ollama show llama2-uncensored --modelfile

As shortcuts, you then may add for example two aliases to your ~/.bash_aliases:

alias ollama-run='OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS or localhost]:4711" ollama run'
alias ollama-list='OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS or localhost]:4711" ollama list'
alias ollama-show='OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS or localhost]:4711" ollama show'

After you have added the aliases, you need to logoff and logon again or do...
source ~/.bash_aliases

Additionally, if you like to run for example chatbot-ollama on the same machine like ollama, but like to make chatbot-ollama available for the whole network, you may then start that one with this command:
OLLAMA_HOST="http://127.0.0.1:4711" npm run dev -- -H [REAL-INTERFACE-IP-ADDRESS-OF-CHATBOT-OLLAMA]

If you do that on a machine accessible by the public, be sure to block the chatbot-ollama service/website for the public or use eg. apache or nginx as a proxy to protect it with username/password protection.

Originally created by @byteconcepts on GitHub (Oct 23, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/885 For those who prefer to use ollama primarily via it's API it would be nice if the ollama.service file would already contain the line... `Environment="OLLAMA_HOST=127.0.0.1:11434"` Additionally it would be nice if the info that for the service the interface IP and Port may be changed in this file, would be added to the Readme. For access over all interfaces on port 4711 change to: `Environment="OLLAMA_HOST=0.0.0.0:4711"` But if you like to use the console command then, you then need to use it like this: `OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS]:4711" ollama show llama2-uncensored --modelfile` As shortcuts, you then may add for example two aliases to your ~/.bash_aliases: ``` alias ollama-run='OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS or localhost]:4711" ollama run' alias ollama-list='OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS or localhost]:4711" ollama list' alias ollama-show='OLLAMA_HOST="[REAL-INTERFACE-IP-ADDRESS or localhost]:4711" ollama show' ``` After you have added the aliases, you need to logoff and logon again or do... `source ~/.bash_aliases` Additionally, if you like to run for example chatbot-ollama on the same machine like ollama, but like to make chatbot-ollama available for the whole network, you may then start that one with this command: `OLLAMA_HOST="http://127.0.0.1:4711" npm run dev -- -H [REAL-INTERFACE-IP-ADDRESS-OF-CHATBOT-OLLAMA]` If you do that on a machine accessible by the public, be sure to block the chatbot-ollama service/website for the public or use eg. apache or nginx as a proxy to protect it with username/password protection.
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
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#427
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?