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 #1119] Hi @jjsarf you can use the OLLAMA_HOST environment variable in combination with ollama serve #47076

New Issue
Closed
opened 2026-04-28 02:58:59 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-28 02:58:59 -05:00
Owner
Copy Link

Originally created by @jjsarf on GitHub (Nov 14, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1119

That did not work fully.
super@mario:/var/www/html$ curl -X POST http://ai:8080/api/generate -d '{
"model": "llama2",
"prompt": "How are you?",
"stream": true,
"options": {
"top_k": 20,
"top_p": 0.9,
"typical_p": 0.7,
"temperature": 0.8,
"repeat_penalty": 1.2,
"presence_penalty": 1.5,
"frequency_penalty": 1.0
}
}'
curl: (7) Failed to connect to ai port 8080 after 230 ms: Connection refused

I also tried with the IPs
C:\usb\laragon-portable\se>curl -X POST http://10.0.0.252:8080/api/generate -d "{"model": "llama2", "prompt": "Why is the sky blue?", "stream": true, "options": { "top_k": 20, "top_p": 0.9, "typical_p": 0.7, "temperature": 0.8, "repeat_penalty": 1.2, "presence_penalty": 1.5, "frequency_penalty": 1.0 }}"
curl: (7) Failed to connect to 10.0.0.252 port 8080: Connection refused

===
Hi @jjsarf you can use the OLLAMA_HOST environment variable in combination with ollama serve

E.g. to expose Ollama externally on port 8080 you can use:

OLLAMA_HOST=0.0.0.0:8080 ollama serve

Feel free to post another issue! Will close this one for now

Originally posted by @jmorganca in https://github.com/jmorganca/ollama/issues/1117#issuecomment-1809465610

Originally created by @jjsarf on GitHub (Nov 14, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1119 That did not work fully. super@mario:/var/www/html$ curl -X POST http://ai:8080/api/generate -d '{ "model": "llama2", "prompt": "How are you?", "stream": true, "options": { "top_k": 20, "top_p": 0.9, "typical_p": 0.7, "temperature": 0.8, "repeat_penalty": 1.2, "presence_penalty": 1.5, "frequency_penalty": 1.0 } }' curl: (7) Failed to connect to ai port 8080 after 230 ms: Connection refused I also tried with the IPs C:\usb\laragon-portable\se>curl -X POST http://10.0.0.252:8080/api/generate -d "{"model": "llama2", "prompt": "Why is the sky blue?", "stream": true, "options": { "top_k": 20, "top_p": 0.9, "typical_p": 0.7, "temperature": 0.8, "repeat_penalty": 1.2, "presence_penalty": 1.5, "frequency_penalty": 1.0 }}" curl: (7) Failed to connect to 10.0.0.252 port 8080: Connection refused === Hi @jjsarf you can use the `OLLAMA_HOST` environment variable in combination with `ollama serve` E.g. to expose Ollama externally on port 8080 you can use: ``` OLLAMA_HOST=0.0.0.0:8080 ollama serve ``` Feel free to post another issue! Will close this one for now _Originally posted by @jmorganca in https://github.com/jmorganca/ollama/issues/1117#issuecomment-1809465610_
GiteaMirror commented 2026-04-28 02:59:02 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Nov 14, 2023):

Hi @jjsarf sorry it's still not working. Do you know if port 8080 is open on your machine? Does logging into that machine and running curl http://localhost:8080/api/generate ... work? Closing for now since I believe this is a network issue but do let me know if you're still encountering it!

<!-- gh-comment-id:1810798014 --> @jmorganca commented on GitHub (Nov 14, 2023): Hi @jjsarf sorry it's still not working. Do you know if port 8080 is open on your machine? Does logging into that machine and running `curl http://localhost:8080/api/generate ...` work? Closing for now since I believe this is a network issue but do let me know if you're still encountering it!
GiteaMirror commented 2026-04-28 02:59:04 -05:00
Author
Owner
Copy Link

@jjsarf commented on GitHub (Nov 14, 2023):

super@mario:~$ curl -X POST http://172.26.96.1:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","s
tream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_pe
nalty": 1.5,"frequency_penalty": 1.0 }}'curl -X POST http://10.0.0.252:8080/api/generate -d '{"model": "llama2","prompt"
"Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat
_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}'
curl: (7) Failed to connect to 172.26.96.1 port 8080 after 0 ms: Connection refused
curl: (7) Failed to connect to 10.0.0.252 port 8080 after 0 ms: Connection refused
super@mario:$ curl -X POST http://10.0.0.252:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}'curl -X POST http://10.0.0.252:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}'
curl: (7) Failed to connect to 10.0.0.252 port 8080 after 0 ms: Connection refused
curl: (7) Failed to connect to 10.0.0.252 port 8080 after 0 ms: Connection refused
super@mario:$ curl -X POST http://ai:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}'
{"timestamp":1700000009,"level":"INFO","function":"log_server_request","line":1233,"message":"request","remote_addr":"127.0.0.1","remote_port":50324,"status":200,"method":"HEAD","path":"/","params":{}}
{"model":"llama2","created_at":"2023-11-14T22:13:29.558889954Z","response":"\n","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.606870611Z","response":"The","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.669844293Z","response":" sky","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.71778644Z","response":" appears","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.781741821Z","response":" blue","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.829792648Z","response":" because","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.876772284Z","response":" of","done":false}
{"model":"llama2","created_at":"2023-11-14T22:13:29.939741767Z","response":" a","done":false}

So it works with "localhost" and "ai" which is the host name of my computer. It does not work with IPs as per above. One is the wsl2 IP the other outer computer PC. Is there a config file or something else I could try?

<!-- gh-comment-id:1811448512 --> @jjsarf commented on GitHub (Nov 14, 2023): super@mario:~$ curl -X POST http://172.26.96.1:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","s tream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_pe nalty": 1.5,"frequency_penalty": 1.0 }}'curl -X POST http://10.0.0.252:8080/api/generate -d '{"model": "llama2","prompt" : "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat _penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}' curl: (7) Failed to connect to 172.26.96.1 port 8080 after 0 ms: Connection refused curl: (7) Failed to connect to 10.0.0.252 port 8080 after 0 ms: Connection refused super@mario:~$ curl -X POST http://10.0.0.252:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}'curl -X POST http://10.0.0.252:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}' curl: (7) Failed to connect to 10.0.0.252 port 8080 after 0 ms: Connection refused curl: (7) Failed to connect to 10.0.0.252 port 8080 after 0 ms: Connection refused super@mario:~$ curl -X POST http://ai:8080/api/generate -d '{"model": "llama2","prompt": "Why is the sky blue?","stream": true,"options": {"top_k": 20,"top_p": 0.9,"typical_p": 0.7,"temperature": 0.8,"repeat_penalty": 1.2,"presence_penalty": 1.5,"frequency_penalty": 1.0 }}' {"timestamp":1700000009,"level":"INFO","function":"log_server_request","line":1233,"message":"request","remote_addr":"127.0.0.1","remote_port":50324,"status":200,"method":"HEAD","path":"/","params":{}} {"model":"llama2","created_at":"2023-11-14T22:13:29.558889954Z","response":"\n","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.606870611Z","response":"The","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.669844293Z","response":" sky","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.71778644Z","response":" appears","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.781741821Z","response":" blue","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.829792648Z","response":" because","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.876772284Z","response":" of","done":false} {"model":"llama2","created_at":"2023-11-14T22:13:29.939741767Z","response":" a","done":false} So it works with "localhost" and "ai" which is the host name of my computer. It does not work with IPs as per above. One is the wsl2 IP the other outer computer PC. Is there a config file or something else I could try?
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#47076
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?