github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 13:47:08 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1546] Is running behind a proxy fully supported? #844

New Issue
Closed
opened 2026-04-12 10:30:32 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 10:30:32 -05:00
Owner
Copy Link

Originally created by @pardeike on GitHub (Dec 15, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1546

Hi,

when I run with a configured proxy, I get the error lookup registry.ollama.ai: no such host:

> HTTPS_PROXY=http://REDACTED.XXX:10000 ollama run llama2
pulling manifest 
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp: lookup registry.ollama.ai: no such host

I then added a manual dns entry to /etc/hosts and ran the command again, but this time after trying to fetch the manifest, I get

> HTTPS_PROXY=http://REDACTED.XXX:10000 ollama run llama2
pulling manifest 
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp 34.120.132.20:443: connect: network is unreachable

Going to those urls in Safari works just fine so it seems that the proxy support isn't fully working.

Originally created by @pardeike on GitHub (Dec 15, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1546 Hi, when I run with a configured proxy, I get the error `lookup registry.ollama.ai: no such host`: ``` > HTTPS_PROXY=http://REDACTED.XXX:10000 ollama run llama2 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp: lookup registry.ollama.ai: no such host ``` I then added a manual dns entry to /etc/hosts and ran the command again, but this time after trying to fetch the manifest, I get ``` > HTTPS_PROXY=http://REDACTED.XXX:10000 ollama run llama2 pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp 34.120.132.20:443: connect: network is unreachable ``` Going to those urls in Safari works just fine so it seems that the proxy support isn't fully working.
GiteaMirror commented 2026-04-12 10:30:33 -05:00
Author
Owner
Copy Link

@mxyng commented on GitHub (Dec 15, 2023):

HTTPS_PROXY must be applied to ollama serve since that's the process actually reaching out to get the models. setting it with ollama run has no effect. Please see the FAQ for more details.

<!-- gh-comment-id:1858228015 --> @mxyng commented on GitHub (Dec 15, 2023): `HTTPS_PROXY` must be applied to `ollama serve` since that's the process actually reaching out to get the models. setting it with `ollama run` has no effect. Please see the [FAQ](https://github.com/jmorganca/ollama/blob/main/docs/faq.md#how-do-i-use-ollama-behind-a-proxy) for more details.
GiteaMirror commented 2026-04-12 10:30:33 -05:00
Author
Owner
Copy Link

@pardeike commented on GitHub (Dec 15, 2023):

My bad, I did not realise that the Ollama app had put itself in my menu bar. After quitting it, then running the proxied ollama serve from command line I could run ollama run llama2 as intended.

<!-- gh-comment-id:1858239940 --> @pardeike commented on GitHub (Dec 15, 2023): My bad, I did not realise that the Ollama app had put itself in my menu bar. After quitting it, then running the proxied ollama serve from command line I could run `ollama run llama2` as intended.
GiteaMirror commented 2026-04-12 10:30:33 -05:00
Author
Owner
Copy Link

@GuiZhaoyang commented on GitHub (Dec 28, 2023):

@mxyng hi, I run the ollama run llama2 in terminal,but still meet the error:

pulling manifest
Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp 34.120.132.20:443: connect: network is unreachable

The ollama server logs:
2023/12/28 11:38:48 images.go:1066: request failed: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp 34.120.132.20:443: connect: network is unreachable
[GIN] 2023/12/28 - 11:38:48 | 200 | 267.776118ms | 127.0.0.1 | POST "/api/pull"

<!-- gh-comment-id:1870796632 --> @GuiZhaoyang commented on GitHub (Dec 28, 2023): @mxyng hi, I run the ollama run llama2 in terminal,but still meet the error: pulling manifest Error: pull model manifest: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp 34.120.132.20:443: connect: network is unreachable The ollama server logs: 2023/12/28 11:38:48 images.go:1066: request failed: Get "https://registry.ollama.ai/v2/library/llama2/manifests/latest": dial tcp 34.120.132.20:443: connect: network is unreachable [GIN] 2023/12/28 - 11:38:48 | 200 | 267.776118ms | 127.0.0.1 | POST "/api/pull"
GiteaMirror commented 2026-04-12 10:30:34 -05:00
Author
Owner
Copy Link

@pardeike commented on GitHub (Dec 28, 2023):

Did you run ollama serve with proxy settings @GuiZhaoyang ?

<!-- gh-comment-id:1871113276 --> @pardeike commented on GitHub (Dec 28, 2023): Did you run `ollama serve` with proxy settings @GuiZhaoyang ?
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#844
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?