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 #1579] Error while running ollama locally. #868

New Issue
Closed
opened 2026-04-12 10:31:50 -05:00 by GiteaMirror · 15 comments
GiteaMirror commented 2026-04-12 10:31:50 -05:00
Owner
Copy Link

Originally created by @nehalmathew1996 on GitHub (Dec 18, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1579

Originally assigned to: @dhiltgen on GitHub.

ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/generate/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000002298AE1EF50>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))

Originally created by @nehalmathew1996 on GitHub (Dec 18, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1579 Originally assigned to: @dhiltgen on GitHub. ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/generate/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000002298AE1EF50>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))
GiteaMirror commented 2026-04-12 10:31:52 -05:00
Author
Owner
Copy Link

@duhow commented on GitHub (Dec 18, 2023):

Maybe this can help?

86b0dd4b16/docs/faq.md (how-can-i-expose-ollama-on-my-network)

<!-- gh-comment-id:1860088662 --> @duhow commented on GitHub (Dec 18, 2023): Maybe this can help? https://github.com/jmorganca/ollama/blob/86b0dd4b165497e08ec331e3c2c2aa229beb09db/docs/faq.md#how-can-i-expose-ollama-on-my-network
GiteaMirror commented 2026-04-12 10:31:52 -05:00
Author
Owner
Copy Link

@technovangelist commented on GitHub (Dec 19, 2023):

@nehalmathew1996 can you tell us more about what you are trying to do?

<!-- gh-comment-id:1863320586 --> @technovangelist commented on GitHub (Dec 19, 2023): @nehalmathew1996 can you tell us more about what you are trying to do?
GiteaMirror commented 2026-04-12 10:31:52 -05:00
Author
Owner
Copy Link

@Hidayathamir commented on GitHub (Dec 20, 2023):

Get Started

  1. Run the Ollama Docker container:
sudo docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

For more detailed information, refer to the Ollama Quickstart Docker. Please note we are using CPU only, the AI will response slow, if you have GPU, you can follow the instruction to run the docker and using your GPU to improve performance.

  1. Pull the llama2 model:
curl --location 'http://localhost:11434/api/pull' \
--header 'Content-Type: application/json' \
--data '{
    "name": "llama2:7b"
}'
  1. Chat with llama2
curl --location 'http://localhost:11434/api/chat' \
--header 'Content-Type: application/json' \
--data '{
    "model": "llama2:7b",
    "messages": [
        {
            "role": "user",
            "content": "why sky blue"
        }
    ]
}'

I create a PR about this.

https://github.com/jmorganca/ollama/pull/1622

<!-- gh-comment-id:1863882802 --> @Hidayathamir commented on GitHub (Dec 20, 2023): ## Get Started 1. Run the Ollama Docker container: ```shell sudo docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama ``` For more detailed information, refer to the [Ollama Quickstart Docker](https://hub.docker.com/r/ollama/ollama). Please note we are using CPU only, the AI will response slow, if you have GPU, you can follow the instruction to run the docker and using your GPU to improve performance. 2. Pull the llama2 model: ```shell curl --location 'http://localhost:11434/api/pull' \ --header 'Content-Type: application/json' \ --data '{ "name": "llama2:7b" }' ``` 3. Chat with llama2 ````shell curl --location 'http://localhost:11434/api/chat' \ --header 'Content-Type: application/json' \ --data '{ "model": "llama2:7b", "messages": [ { "role": "user", "content": "why sky blue" } ] }' ```` I create a PR about this. https://github.com/jmorganca/ollama/pull/1622
GiteaMirror commented 2026-04-12 10:31:53 -05:00
Author
Owner
Copy Link

@shreyasd2301 commented on GitHub (Jan 20, 2024):

ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/generate/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000002298AE1EF50>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))

what was the issue?

i'm facing similar problem

<!-- gh-comment-id:1902268567 --> @shreyasd2301 commented on GitHub (Jan 20, 2024): > ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/generate/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000002298AE1EF50>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it')) what was the issue? i'm facing similar problem
GiteaMirror commented 2026-04-12 10:31:53 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jan 27, 2024):

@nehalmathew1996 are you still having problems? Can you upgrade to 0.1.22 and see if that resolves you problem?

<!-- gh-comment-id:1912894920 --> @dhiltgen commented on GitHub (Jan 27, 2024): @nehalmathew1996 are you still having problems? Can you upgrade to 0.1.22 and see if that resolves you problem?
GiteaMirror commented 2026-04-12 10:31:53 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Feb 1, 2024):

If you're still having problems with 0.1.22 or newer, please re-open.

<!-- gh-comment-id:1922462229 --> @dhiltgen commented on GitHub (Feb 1, 2024): If you're still having problems with 0.1.22 or newer, please re-open.
GiteaMirror commented 2026-04-12 10:31:54 -05:00
Author
Owner
Copy Link

@eons2long commented on GitHub (Mar 17, 2024):

I have a same problem, used with docker, sometime is happened with this:
[ollama] Connection Error, HTTPConnectionPool(host='172.17.0.1', port=11434): Read timed out. (read timeout=60)

my ollama version is 0.1.28

<!-- gh-comment-id:2002479908 --> @eons2long commented on GitHub (Mar 17, 2024): I have a same problem, used with docker, sometime is happened with this: [ollama] Connection Error, HTTPConnectionPool(host='172.17.0.1', port=11434): Read timed out. (read timeout=60) my ollama version is 0.1.28
GiteaMirror commented 2026-04-12 10:31:54 -05:00
Author
Owner
Copy Link

@imen-ben-atig commented on GitHub (Mar 25, 2024):

same problem here

<!-- gh-comment-id:2017138519 --> @imen-ben-atig commented on GitHub (Mar 25, 2024): same problem here
GiteaMirror commented 2026-04-12 10:31:54 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Mar 25, 2024):

@yixian3500 @imen-ben-atig Ollama is a client-server architecture, and this error is the client failing to connect to the server. The underlying problem is likely a crash or hang in the server, and most likely your problems are unrelated to whatever was going wrong in Dec 18th when this issue was opened. Please go ahead and file new issues for your individual connection problem and please include the server.log so we can investigate.

See https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md for guidance on how to find your server log.

<!-- gh-comment-id:2017888780 --> @dhiltgen commented on GitHub (Mar 25, 2024): @yixian3500 @imen-ben-atig Ollama is a client-server architecture, and this error is the client failing to connect to the server. The underlying problem is likely a crash or hang in the server, and most likely your problems are unrelated to whatever was going wrong in Dec 18th when this issue was opened. Please go ahead and file new issues for your individual connection problem and please include the server.log so we can investigate. See https://github.com/ollama/ollama/blob/main/docs/troubleshooting.md for guidance on how to find your server log.
GiteaMirror commented 2026-04-12 10:31:55 -05:00
Author
Owner
Copy Link

@mlatti commented on GitHub (Apr 5, 2024):

Install ollama on your system.
This may not cover all of the occurences, but if you're like me just getting started with llm's and your 101 tutorial doesn't mention this, you need to download and install ollama

<!-- gh-comment-id:2040531821 --> @mlatti commented on GitHub (Apr 5, 2024): Install ollama on your system. This may not cover all of the occurences, but if you're like me just getting started with llm's and your 101 tutorial doesn't mention this, you need to download and install ollama
GiteaMirror commented 2026-04-12 10:31:55 -05:00
Author
Owner
Copy Link

@thepyper commented on GitHub (Apr 5, 2024):

Ok, I think I've solved that in my setup, let's see if that's useful to anybody else...

My setup is:

  1. Windows 10, where I installed ollama (with OllamaSetup.exe)
  2. WSL + Ubuntu, where I installed OpenDevin

Actually the issue is made of the following issues:

  1. You need to check that ollama is actually running, so try in windows 10 (ms-dos prompt or powershell)
    curl 127.0.0.1:11434
    You should get a "ollama is running" message
  2. You need to understand that WSL is like a virtual machine, then "127.0.0.1" inside WSL does NOT mean connecting to windows 10, but connecting into the virtual environment in WSL.
  3. You need to figure out the actual IP of the windows 10 machine seen from WSL.
    I did it with a "traceroute www.google.com" command, it gave me the following:
traceroute to www.google.com (142.250.180.132), 30 hops max, 60 byte packets
 1  DESKTOP-K5HF2NK.mshome.net (172.19.80.1)  0.315 ms  0.230 ms  0.207 ms
... more stuff...

So my windows 10 is seen from WSL + Ubuntu as 172.19.80.1.
So, my config.toml file in OpenDevin looks like:

LLM_MODEL="ollama/llama2"
LLM_API_KEY="na"
LLM_BASE_URL="http://172.19.80.1:11434"
LLM_EMBEDDING_MODEL="llama2"
WORKSPACE_DIR="./workspace"
  1. Still things does not work, because by default ollama is only accepting local network connections.
    So, you need to add an environment variable:
    OLLAMA_HOST="0.0.0.0"
    in your windows 10.
    You can test quickly that in PowerShell, just quit ollama then open PowerShell and give:
$env:OLLAMA_HOST="0.0.0.0"
ollama serve
  1. Now opening "localhost:3001" in browser (in windows 10) should give you a working OpenDevin.
    At least mine is doing something with ollama, I can see in the console but I'm still waiting my response to "hello" :)

... yep I got a silly reply, it's working !!!

Hope this helps....

<!-- gh-comment-id:2040632540 --> @thepyper commented on GitHub (Apr 5, 2024): Ok, I think I've solved that in my setup, let's see if that's useful to anybody else... My setup is: 1) Windows 10, where I installed ollama (with OllamaSetup.exe) 2) WSL + Ubuntu, where I installed OpenDevin Actually the issue is made of the following issues: 1) You need to check that ollama is actually running, so try in windows 10 (ms-dos prompt or powershell) curl 127.0.0.1:11434 You should get a "ollama is running" message 2) You need to understand that WSL is like a virtual machine, then "127.0.0.1" inside WSL does NOT mean connecting to windows 10, but connecting into the virtual environment in WSL. 3) You need to figure out the actual IP of the windows 10 machine seen from WSL. I did it with a "traceroute www.google.com" command, it gave me the following: ``` traceroute to www.google.com (142.250.180.132), 30 hops max, 60 byte packets 1 DESKTOP-K5HF2NK.mshome.net (172.19.80.1) 0.315 ms 0.230 ms 0.207 ms ... more stuff... ``` So my windows 10 is seen from WSL + Ubuntu as 172.19.80.1. So, my config.toml file in OpenDevin looks like: ``` LLM_MODEL="ollama/llama2" LLM_API_KEY="na" LLM_BASE_URL="http://172.19.80.1:11434" LLM_EMBEDDING_MODEL="llama2" WORKSPACE_DIR="./workspace" ``` 4) Still things does not work, because by default ollama is only accepting local network connections. So, you need to add an environment variable: OLLAMA_HOST="0.0.0.0" in your windows 10. You can test quickly that in PowerShell, just quit ollama then open PowerShell and give: ``` $env:OLLAMA_HOST="0.0.0.0" ollama serve ``` 5) Now opening "localhost:3001" in browser (in windows 10) should give you a working OpenDevin. At least mine is doing something with ollama, I can see in the console but I'm still waiting my response to "hello" :) ... yep I got a silly reply, it's working !!! Hope this helps....
GiteaMirror commented 2026-04-12 10:31:55 -05:00
Author
Owner
Copy Link

@mzeeshanarshad commented on GitHub (Feb 27, 2025):

Anyone still having this error should try increasing the time out.

<!-- gh-comment-id:2686774155 --> @mzeeshanarshad commented on GitHub (Feb 27, 2025): Anyone still having this error should try increasing the time out.
GiteaMirror commented 2026-04-12 10:31:56 -05:00
Author
Owner
Copy Link

@wybaby commented on GitHub (Mar 3, 2025):

  1. set the URL be "http://host.docker.internal:11434" or your IP, instead of 127.0.0.1 or localhost.
  2. add an enviroment variable OLLAMA_HOST="0.0.0.0" (for Windows).
<!-- gh-comment-id:2693667615 --> @wybaby commented on GitHub (Mar 3, 2025): 1. set the URL be "http://host.docker.internal:11434" or your IP, instead of 127.0.0.1 or localhost. 2. add an enviroment variable OLLAMA_HOST="0.0.0.0" (for Windows).
GiteaMirror commented 2026-04-12 10:31:56 -05:00
Author
Owner
Copy Link

@aleksadvaisly commented on GitHub (Mar 5, 2025):

Don't do that.

Instead OLLAMA_HOST="0.0.0.0"
Set OLLAMA_HOST="127.0.0.1"

I found 0.0.0.0 not working when using python ollama library

<!-- gh-comment-id:2702254581 --> @aleksadvaisly commented on GitHub (Mar 5, 2025): Don't do that. Instead OLLAMA_HOST="0.0.0.0" Set OLLAMA_HOST="127.0.0.1" I found 0.0.0.0 not working when using python ollama library
GiteaMirror commented 2026-04-12 10:31:56 -05:00
Author
Owner
Copy Link

@cadubarbosabr commented on GitHub (Jun 18, 2025):

Had the same issue.

Instead of using
base_url: str = "http://localhost:11434"):
Try
base_url: str = "http://127.0.0.1:11434"):

<!-- gh-comment-id:2985672300 --> @cadubarbosabr commented on GitHub (Jun 18, 2025): Had the same issue. Instead of using base_url: str = "http://**localhost**:11434"): Try base_url: str = "http://**127.0.0.1**:11434"):
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#868
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?