github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #1411] Issue connecting to 11434 for local model query following sample #62788

New Issue
Closed
opened 2026-05-03 10:19:08 -05:00 by GiteaMirror · 6 comments
GiteaMirror commented 2026-05-03 10:19:08 -05:00
Owner
Copy Link

Originally created by @OpenSpacesAndPlaces on GitHub (Dec 7, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1411

I'm following this example as a basis for getting started:
https://www.youtube.com/watch?v=tvs350imHLY
https://gist.github.com/mneedham/eec9246a5ce95dc792f2e73b16dfe78e

Everything is working good except for actually running the query:
response = query_engine.query("What is my question?")

Which throws an error connecting to the Ollama service that was started:
requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/generate/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fa201bb77f0>: Failed to establish a new connection: [Errno 111] Connection refused'))

Also tried this instead of query_engine.query - but same error:

url = "http://localhost:11434/api/generate"
data = {
    "model": "llama2",
    "prompt": "What is my question?"
}
response = requests.post(url, json=data)

Running:
WSL - Ubuntu 22.04.3 LTS
Python 3.10

Any help appreciated!!!!

Originally created by @OpenSpacesAndPlaces on GitHub (Dec 7, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1411 I'm following this example as a basis for getting started: https://www.youtube.com/watch?v=tvs350imHLY https://gist.github.com/mneedham/eec9246a5ce95dc792f2e73b16dfe78e Everything is working good except for actually running the query: `response = query_engine.query("What is my question?")` Which throws an error connecting to the Ollama service that was started: `requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/generate/ (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7fa201bb77f0>: Failed to establish a new connection: [Errno 111] Connection refused'))` Also tried this instead of query_engine.query - but same error: ``` url = "http://localhost:11434/api/generate" data = { "model": "llama2", "prompt": "What is my question?" } response = requests.post(url, json=data) ``` Running: WSL - Ubuntu 22.04.3 LTS Python 3.10 Any help appreciated!!!!
GiteaMirror commented 2026-05-03 10:19:10 -05:00
Author
Owner
Copy Link

@OpenSpacesAndPlaces commented on GitHub (Dec 7, 2023):

@mneedham in-case you have any ideas from when you made this demo.
Thanks for any thoughts!

<!-- gh-comment-id:1845463793 --> @OpenSpacesAndPlaces commented on GitHub (Dec 7, 2023): @mneedham in-case you have any ideas from when you made this demo. Thanks for any thoughts!
GiteaMirror commented 2026-05-03 10:19:11 -05:00
Author
Owner
Copy Link

@OpenSpacesAndPlaces commented on GitHub (Dec 7, 2023):

I think I'm past this error.

I needed to specifically install ollama:
curl https://ollama.ai/install.sh | sh

Then open a separate prompt to run:
ollama serve

Appears to make the connection and fail with:
ValueError: Ollama call failed with status code 404. Details: model 'zephyr' not found, try pulling it first

Which should be fixed with:
ollama pull zephyr

Best I can see the original example missed some startup steps that were likely done already for another demo.

<!-- gh-comment-id:1845815091 --> @OpenSpacesAndPlaces commented on GitHub (Dec 7, 2023): I think I'm past this error. I needed to specifically install ollama: `curl https://ollama.ai/install.sh | sh` Then open a separate prompt to run: `ollama serve` Appears to make the connection and fail with: `ValueError: Ollama call failed with status code 404. Details: model 'zephyr' not found, try pulling it first` Which should be fixed with: `ollama pull zephyr` Best I can see the original example missed some startup steps that were likely done already for another demo.
GiteaMirror commented 2026-05-03 10:19:11 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Dec 7, 2023):

Thanks for providing the resolution @OpenSpacesAndPlaces, normally when ollama is installed via the install.sh script it starts a service running in the background, but if that isn't available it is necessary to run ollama serve.

Resolving this for now since there is no more to do here. Feel free to let us know if you hit any other issues.

<!-- gh-comment-id:1845930737 --> @BruceMacD commented on GitHub (Dec 7, 2023): Thanks for providing the resolution @OpenSpacesAndPlaces, normally when ollama is installed via the install.sh script it starts a service running in the background, but if that isn't available it is necessary to run `ollama serve`. Resolving this for now since there is no more to do here. Feel free to let us know if you hit any other issues.
GiteaMirror commented 2026-05-03 10:19:12 -05:00
Author
Owner
Copy Link

@ayttop commented on GitHub (Sep 8, 2024):

curl http://localhost:11434/api/chat -d "{"model": "llama3.1:8b", "stream": false, "messages": [{"role": "user", "content": "Why is the sky green?"}]}"

<!-- gh-comment-id:2336834701 --> @ayttop commented on GitHub (Sep 8, 2024): curl http://localhost:11434/api/chat -d "{\"model\": \"llama3.1:8b\", \"stream\": false, \"messages\": [{\"role\": \"user\", \"content\": \"Why is the sky green?\"}]}"
GiteaMirror commented 2026-05-03 10:19:13 -05:00
Author
Owner
Copy Link

@Mugane commented on GitHub (Feb 23, 2025):

http://localhost:11434/api/chat -d "{"model": "llama3.1:8b", "stream": false, "messages": [{"role": "user", "content": "Why is the sky green?"}]}"

How to do this using the url only? Is it possible (GET not POST)?

<!-- gh-comment-id:2677151736 --> @Mugane commented on GitHub (Feb 23, 2025): > http://localhost:11434/api/chat -d "{"model": "llama3.1:8b", "stream": false, "messages": [{"role": "user", "content": "Why is the sky green?"}]}" How to do this using the url only? Is it possible (GET not POST)?
GiteaMirror commented 2026-05-03 10:19:14 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (Feb 24, 2025):

@Mugane No that isn't possible.

<!-- gh-comment-id:2679185369 --> @BruceMacD commented on GitHub (Feb 24, 2025): @Mugane No that isn't possible.
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#62788
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?