github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-21 05:01:48 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1318] How to Open Ollama Service to the Outside World with HTTPS Compatibility? #685

New Issue
Closed
opened 2026-04-12 10:21:58 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 10:21:58 -05:00
Owner
Copy Link

Originally created by @rehberim360 on GitHub (Nov 29, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1318

Hello,

Problem: The Ollama service I've installed on Google VM doesn't seem to accept incoming requests over HTTPS. I'm aiming to allow external requests to reach the server and enable HTTPS support for the Ollama service. I've taken the following steps:

Server Configuration: I configured a reverse proxy using Apache2. I've correctly installed SSL/TLS certificates and attempted to establish a direct connection to the Ollama service.

Firewall Settings: I've set up the necessary firewall rules on Google Cloud and ensured that the correct ports are open.

Documentation and Research: I've reviewed the documentation regarding HTTPS support for the Ollama service but haven't found a definitive solution. I've searched forums and other resources but couldn't find a clear resolution.

Preferred Solution: I've noticed that enabling HTTPS support for Ollama requires specific configurations, yet I haven't found a straightforward approach.

Additional Information: Could any insights be shared regarding the server's current status, Ollama service configurations, or any hints related to HTTPS?

I would appreciate your assistance. I need guidance or suggestions to move forward with this issue. Thank you.

Originally created by @rehberim360 on GitHub (Nov 29, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1318 Hello, Problem: The Ollama service I've installed on Google VM doesn't seem to accept incoming requests over HTTPS. I'm aiming to allow external requests to reach the server and enable HTTPS support for the Ollama service. I've taken the following steps: Server Configuration: I configured a reverse proxy using Apache2. I've correctly installed SSL/TLS certificates and attempted to establish a direct connection to the Ollama service. Firewall Settings: I've set up the necessary firewall rules on Google Cloud and ensured that the correct ports are open. Documentation and Research: I've reviewed the documentation regarding HTTPS support for the Ollama service but haven't found a definitive solution. I've searched forums and other resources but couldn't find a clear resolution. Preferred Solution: I've noticed that enabling HTTPS support for Ollama requires specific configurations, yet I haven't found a straightforward approach. Additional Information: Could any insights be shared regarding the server's current status, Ollama service configurations, or any hints related to HTTPS? I would appreciate your assistance. I need guidance or suggestions to move forward with this issue. Thank you.
GiteaMirror commented 2026-04-12 10:21:58 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Nov 30, 2023):

The easiest way to do this with a reverse proxy with a web server such as nginx. There are lots of tutorials online on how to do this, but I watched part of this one which seemed pretty straight forward: https://www.youtube.com/watch?v=DyXl4c2XN-o. Alternatively, since you're using Google Cloud, you can use their Cloud Load Balancing service to terminate TLS and potentially use it to load balance in front of multiple ollama instances.

Also, you should keep in mind that you want to restrict access to pushing/pulling models as this could lead to a DOS attack on your host. Since Ollama only services one request at a time, if you have a lot of clients which are trying to connect to it you could end up with not great performance unless you go the load balancer route.

<!-- gh-comment-id:1834624935 --> @pdevine commented on GitHub (Nov 30, 2023): The easiest way to do this with a reverse proxy with a web server such as nginx. There are lots of tutorials online on how to do this, but I watched part of this one which seemed pretty straight forward: https://www.youtube.com/watch?v=DyXl4c2XN-o. Alternatively, since you're using Google Cloud, you can use their Cloud Load Balancing service to terminate TLS and potentially use it to load balance in front of multiple ollama instances. Also, you should keep in mind that you want to restrict access to pushing/pulling models as this could lead to a DOS attack on your host. Since Ollama only services one request at a time, if you have a lot of clients which are trying to connect to it you could end up with not great performance unless you go the load balancer route.
GiteaMirror commented 2026-04-12 10:21:59 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Dec 4, 2023):

It looks like Patrick has answered the question and you are good to go. So I will go ahead and close the now. If you think there is anything we left out, reopen and we can address. Thanks for being part of this great community.

<!-- gh-comment-id:1839577675 --> @technovangelist commented on GitHub (Dec 4, 2023): It looks like Patrick has answered the question and you are good to go. So I will go ahead and close the now. If you think there is anything we left out, reopen and we can address. Thanks for being part of this great community.
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#685
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?