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 #465] deployment on ubuntu server with nginx causes 504 timeout #216

New Issue
Closed
opened 2026-04-12 09:44:17 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 09:44:17 -05:00
Owner
Copy Link

Originally created by @helxsz on GitHub (Sep 3, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/465

I am running a ollama server which runs a llama2 on the cloud server with ubuntu.

curl -X POST http://localhost:11434/api/generate -d '{
>   "model": "llama2",
>   "prompt":"Why is the sky blue?"
> }'

the result is starting to stream in 3 seconds

{"model":"llama2","created_at":"2023-09-01T22:35:43.271181437Z","response":" The","done":false}
....
....
However, for the public visit there is a nginx server connecting to this ollama server, but everytime visiting the service in cloud IP address always causes 504 timeout.

the configuration of nginx server timeout doesn't work.

server {
        listen 9003;
        server_name xx.xx.xx.xx;

        location / {
                proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
                proxy_set_header   Host      $http_host;
                proxy_set_header X-Forwarded-Proto $scheme;

                proxy_read_timeout 150000;
                proxy_connect_timeout 150000;
                proxy_send_timeout 150000;
     }
}

usually timeout 150000 should be enough to solve the timeout issue since ollama inference is only within 3 seconds.

any ideas on the deployment

Originally created by @helxsz on GitHub (Sep 3, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/465 I am running a ollama server which runs a llama2 on the cloud server with ubuntu. ``` curl -X POST http://localhost:11434/api/generate -d '{ > "model": "llama2", > "prompt":"Why is the sky blue?" > }' ``` the result is starting to stream in 3 seconds {"model":"llama2","created_at":"2023-09-01T22:35:43.271181437Z","response":" The","done":false} .... .... However, for the public visit there is a nginx server connecting to this ollama server, but everytime visiting the service in cloud IP address always causes 504 timeout. the configuration of nginx server timeout doesn't work. ``` server { listen 9003; server_name xx.xx.xx.xx; location / { proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header Host $http_host; proxy_set_header X-Forwarded-Proto $scheme; proxy_read_timeout 150000; proxy_connect_timeout 150000; proxy_send_timeout 150000; } } ``` usually timeout 150000 should be enough to solve the timeout issue since ollama inference is only within 3 seconds. any ideas on the deployment
GiteaMirror commented 2026-04-12 09:44:18 -05:00
Author
Owner
Copy Link

@helxsz commented on GitHub (Sep 4, 2023):

investigate more on 'event-stream',

 header:{
  'Content-Type': 'text/event-stream'
}

therefore

proxy_http_version 1.1; version 1.1 supports long connection

       proxy_set_header Connection 'keep-alive';
       proxy_set_header Cache-Control 'no-cache';
       proxy_set_header Content-Type 'text/event-stream';

proxy_buffering off; disable the buffering to make sure the real time connection

<!-- gh-comment-id:1705662099 --> @helxsz commented on GitHub (Sep 4, 2023): investigate more on 'event-stream', ``` header:{ 'Content-Type': 'text/event-stream' } ``` therefore `proxy_http_version 1.1;` version 1.1 supports long connection ``` proxy_set_header Connection 'keep-alive'; proxy_set_header Cache-Control 'no-cache'; proxy_set_header Content-Type 'text/event-stream'; ``` ` proxy_buffering off; ` disable the buffering to make sure the real time connection
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#216
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?