github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12456] Support binding multiple IPs #54789

New Issue
Open
opened 2026-04-29 07:18:36 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-04-29 07:18:36 -05:00
Owner
Copy Link

Originally created by @ryanisn on GitHub (Sep 30, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12456

I have web running in local docker that calls to ollama, and I also need to call ollama directly from host.
To secure the ollama API access, I want to bind ip to both localhost and host.docker.internal (172.17.0.1).

I do not want to bind to 0.0.0.0, that would be a security concern, this ollama server is for local use only.

Originally created by @ryanisn on GitHub (Sep 30, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12456 I have web running in local docker that calls to ollama, and I also need to call ollama directly from host. To secure the ollama API access, I want to bind ip to both localhost and host.docker.internal (172.17.0.1). I do not want to bind to 0.0.0.0, that would be a security concern, this ollama server is for local use only.
GiteaMirror added the feature request label 2026-04-29 07:18:36 -05:00
GiteaMirror commented 2026-04-29 07:18:38 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 30, 2025):

Put ollama in a container and adjust the port settings:

services:
  ollama:
    image: ollama/ollama:latest
    ports:
      - 127.0.0.1:11434:11434
      - 172.17.0.1:11434:11434
<!-- gh-comment-id:3352820111 --> @rick-github commented on GitHub (Sep 30, 2025): Put ollama in a container and adjust the port settings: ```yaml services: ollama: image: ollama/ollama:latest ports: - 127.0.0.1:11434:11434 - 172.17.0.1:11434:11434 ```
GiteaMirror commented 2026-04-29 07:18:40 -05:00
Author
Owner
Copy Link

@ryanisn commented on GitHub (Sep 30, 2025):

Put ollama in a container and adjust the port settings:

services:
ollama:
image: ollama/ollama:latest
ports:
- 127.0.0.1:11434:11434
- 172.17.0.1:11434:11434

I'd prefer to run ollama locally, docker service is not always up

<!-- gh-comment-id:3352833836 --> @ryanisn commented on GitHub (Sep 30, 2025): > Put ollama in a container and adjust the port settings: > > services: > ollama: > image: ollama/ollama:latest > ports: > - 127.0.0.1:11434:11434 > - 172.17.0.1:11434:11434 I'd prefer to run ollama locally, docker service is not always up
GiteaMirror commented 2026-04-29 07:18:42 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 30, 2025):

Add a firewall rule to drop packets to 11434 that come from the LAN/WAN.

<!-- gh-comment-id:3352888007 --> @rick-github commented on GitHub (Sep 30, 2025): Add a firewall rule to drop packets to 11434 that come from the LAN/WAN.
GiteaMirror commented 2026-04-29 07:18:42 -05:00
Author
Owner
Copy Link

@vanboom commented on GitHub (Oct 1, 2025):

Firewall rule would work but nobody does this for NGINX or Apache configurations. Is it not feasible to add support similar to NGINX "Listen" for multiple IP address?

<!-- gh-comment-id:3358310973 --> @vanboom commented on GitHub (Oct 1, 2025): Firewall rule would work but nobody does this for NGINX or Apache configurations. Is it not feasible to add support similar to NGINX "Listen" for multiple IP address?
GiteaMirror commented 2026-04-29 07:18:43 -05:00
Author
Owner
Copy Link

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

Run nginx as a reverse proxy, listening on multiple addresses and forwarding requests to an ollama server listening on 127.0.0.1:11435.

<!-- gh-comment-id:3358317958 --> @rick-github commented on GitHub (Oct 1, 2025): Run nginx as a reverse proxy, listening on multiple addresses and forwarding requests to an ollama server listening on 127.0.0.1:11435.
GiteaMirror commented 2026-04-29 07:18:44 -05:00
Author
Owner
Copy Link

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

To be clear, this is a valid feature request. I'm suggesting ways to achieve the required outcome now without waiting for a PR.

<!-- gh-comment-id:3358325199 --> @rick-github commented on GitHub (Oct 1, 2025): To be clear, this is a valid feature request. I'm suggesting ways to achieve the required outcome now without waiting for a PR.
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#54789
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?