github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 08:59:13 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6719] (111) Connection refused #66268

New Issue
Closed
opened 2026-05-04 01:42:50 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-04 01:42:50 -05:00
Owner
Copy Link

Originally created by @SheltonLiu-N on GitHub (Sep 10, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6719

What is the issue?

I met a wired problem. When I use ollama in a server, I can run ollama run llama3.1:70b successfully in cmd, but failed in my python projects

process = subprocess.Popen("ollama serve", shell=True)
time.sleep(10)
ollama.pull("llama3.1:70b")

which returns:

<blockquote id="error">
<p><b>Connection to 127.0.0.1 failed.</b></p>
</blockquote>

<p id="sysmsg">The system returned: <i>(111) Connection refused</i></p>

also, I tested in cmd with:

curl http://127.0.0.1:11434/api/pull

and it returns:

div id="content">
<p>The following error was encountered while trying to retrieve the URL: <a href="http://127.0.0.1:11434/api/pull">http://127.0.0.1:11434/api/pull</a></p>

<blockquote id="error">
<p><b>Connection to 127.0.0.1 failed.</b></p>
</blockquote>

<p id="sysmsg">The system returned: <i>(111) Connection refused</i></p>

I verified that the ollama is listening to 127.0.0.1:11434

How to solve this problem?

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

v0.3.10

Originally created by @SheltonLiu-N on GitHub (Sep 10, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6719 ### What is the issue? I met a wired problem. When I use ollama in a server, I can run `ollama run llama3.1:70b` successfully in cmd, but failed in my python projects ``` process = subprocess.Popen("ollama serve", shell=True) time.sleep(10) ollama.pull("llama3.1:70b") ``` which returns: ``` <blockquote id="error"> <p><b>Connection to 127.0.0.1 failed.</b></p> </blockquote> <p id="sysmsg">The system returned: <i>(111) Connection refused</i></p> ``` also, I tested in cmd with: `curl http://127.0.0.1:11434/api/pull` and it returns: ```< div id="content"> <p>The following error was encountered while trying to retrieve the URL: <a href="http://127.0.0.1:11434/api/pull">http://127.0.0.1:11434/api/pull</a></p> <blockquote id="error"> <p><b>Connection to 127.0.0.1 failed.</b></p> </blockquote> <p id="sysmsg">The system returned: <i>(111) Connection refused</i></p> ``` I verified that the ollama is listening to `127.0.0.1:11434` How to solve this problem? ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version v0.3.10
GiteaMirror added the bug label 2026-05-04 01:42:52 -05:00
GiteaMirror commented 2026-05-04 01:43:45 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 10, 2024):

What does the following return

curl --noproxy "*" localhost:11434
<!-- gh-comment-id:2340019404 --> @rick-github commented on GitHub (Sep 10, 2024): What does the following return ``` curl --noproxy "*" localhost:11434 ```
GiteaMirror commented 2026-05-04 01:43:50 -05:00
Author
Owner
Copy Link

@SheltonLiu-N commented on GitHub (Sep 10, 2024):

@rick-github Hi Rick, the return displays my GPU infos and shows that ollama is running:

time=2024-09-10T09:43:12.531-05:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cuda_v11 cuda_v12 rocm_v60102 cpu]"
time=2024-09-10T09:43:12.531-05:00 level=INFO source=gpu.go:200 msg="looking for compatible GPUs"
time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-050b457a-023b-cbf0-15b9-12910510da5c library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB"
time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-3581e78c-3f53-31e4-d1c5-e1602530cdae library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB"
time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-5e81643e-819f-c754-25e9-9416bf3e5126 library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB"
time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-7aa67590-ccf0-f7e2-cf7f-e6aa9cfdeaf2 library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB"
[GIN] 2024/09/10 - 09:43:14 | 200 |      58.361µs |       127.0.0.1 | GET      "/"
Ollama is running
<!-- gh-comment-id:2341074981 --> @SheltonLiu-N commented on GitHub (Sep 10, 2024): @rick-github Hi Rick, the return displays my GPU infos and shows that ollama is running: ``` time=2024-09-10T09:43:12.531-05:00 level=INFO source=payload.go:44 msg="Dynamic LLM libraries [cpu_avx cpu_avx2 cuda_v11 cuda_v12 rocm_v60102 cpu]" time=2024-09-10T09:43:12.531-05:00 level=INFO source=gpu.go:200 msg="looking for compatible GPUs" time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-050b457a-023b-cbf0-15b9-12910510da5c library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB" time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-3581e78c-3f53-31e4-d1c5-e1602530cdae library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB" time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-5e81643e-819f-c754-25e9-9416bf3e5126 library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB" time=2024-09-10T09:43:14.012-05:00 level=INFO source=types.go:107 msg="inference compute" id=GPU-7aa67590-ccf0-f7e2-cf7f-e6aa9cfdeaf2 library=cuda variant=v12 compute=8.0 driver=12.4 name="NVIDIA A100-SXM4-80GB" total="79.1 GiB" available="78.7 GiB" [GIN] 2024/09/10 - 09:43:14 | 200 | 58.361µs | 127.0.0.1 | GET "/" Ollama is running ```
GiteaMirror commented 2026-05-04 01:43:56 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Sep 10, 2024):

You have a client-side proxy configured, so connections from the ollama client and your python project are being sent to the proxy rather than going to localhost:11434. The most likely reason is you have HTTP_PROXY (or http_proxy) set in your environment. You can try adding no_proxy=localhost,127.0.0.0,127.0.0.1,127.0.1.1 to your environment, or unsetting HTTP_PROXY (http_proxy).

<!-- gh-comment-id:2341127549 --> @rick-github commented on GitHub (Sep 10, 2024): You have a client-side proxy configured, so connections from the `ollama` client and your python project are being sent to the proxy rather than going to `localhost:11434`. The most likely reason is you have `HTTP_PROXY` (or `http_proxy`) set in your environment. You can try adding `no_proxy=localhost,127.0.0.0,127.0.0.1,127.0.1.1` to your environment, or unsetting `HTTP_PROXY` (`http_proxy`).
GiteaMirror commented 2026-05-04 01:44:03 -05:00
Author
Owner
Copy Link

@SheltonLiu-N commented on GitHub (Sep 10, 2024):

It works! Thank you so much, Rick! @rick-github

<!-- gh-comment-id:2341239829 --> @SheltonLiu-N commented on GitHub (Sep 10, 2024): It works! Thank you so much, Rick! @rick-github
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 bug
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#66268
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?