I have searched the existing issues and discussions.
I am using the latest version of Open WebUI.
Installation Method
Git Clone
Open WebUI Version
v0.5.20
Ollama Version (if applicable)
0.6.2
Operating System
Ubuntu 24.04 / Docker
Browser (if applicable)
No response
Confirmation
I have read and followed all instructions in README.md.
I am using the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.
I have listed steps to reproduce the bug in detail.
Expected Behavior
The model should be downloaded over the UI like calling docker exec -it ollama ollama pull gemma3:latest, which works perfectly.
Actual Behavior
I use an Nginx reverse proxy to secure my open-webui, as well as the Olama API and comfy UI. Everything works normally, but I can't download models directly over the open-webui. Surprisingly, I can't see any error in the open-webui docker log, only in the ollama logs.
It also surprised me that this ollama API call will be performed over my public IP instead of the localhost.
When I enter the Model I want, for example gemma3:latest it makes an ollama api call with /api/pull/0
Originally created by @Mozartuss on GitHub (Apr 1, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12272
### Check Existing Issues
- [x] I have searched the existing issues and discussions.
- [x] I am using the latest version of Open WebUI.
### Installation Method
Git Clone
### Open WebUI Version
v0.5.20
### Ollama Version (if applicable)
0.6.2
### Operating System
Ubuntu 24.04 / Docker
### Browser (if applicable)
_No response_
### Confirmation
- [x] I have read and followed all instructions in `README.md`.
- [x] I am using the latest version of **both** Open WebUI and Ollama.
- [x] I have included the browser console logs.
- [x] I have included the Docker container logs.
- [x] I have listed steps to reproduce the bug in detail.
### Expected Behavior
The model should be downloaded over the UI like calling `docker exec -it ollama ollama pull gemma3:latest`, which works perfectly.
### Actual Behavior
I use an Nginx reverse proxy to secure my open-webui, as well as the Olama API and comfy UI. Everything works normally, but I can't download models directly over the open-webui. Surprisingly, I can't see any error in the open-webui docker log, only in the ollama logs.
It also surprised me that this ollama API call will be performed over my public IP instead of the localhost.
When I enter the Model I want, for example `gemma3:latest` it makes an ollama api call with `/api/pull/0`
The Following is my nginx config:
```
server {
listen 80;
server_name ai.ai.tha.de;
return 302 https://$host$request_uri;
}
server {
listen [::]:443 ssl;
listen 443 ssl;
http2 on;
client_max_body_size 0;
server_name MY_DOMAIN;
ssl_certificate /etc/letsencrypt/live/MY_DOMAIN/fullchain.pem;
ssl_certificate_key /etc/letsencrypt/live/MY_DOMAIN/privkey.pem;
ssl_protocols TLSv1 TLSv1.1 TLSv1.2;
ssl_prefer_server_ciphers on;
ssl_dhparam /etc/ssl/certs/dhparam.pem;
ssl_ciphers 'ECDHE-RSA-AES128-GCM-SHA256:ECDHE-ECDSA-AES128-GCM-SHA256:ECDHE-RSA-AES256-GCM-SHA384:ECDHE-ECDSA-AES256-GCM-SHA384:DHE-RSA-AES128-GCM-SHA256:DHE-DSS-AES128-GCM-SHA256:kEDH+AESGCM:ECDHE-RSA-AES128-SHA256:ECDHE-ECDSA-AES128-SHA256:ECDHE-RSA-AES128-SHA:ECDHE-ECDSA-AES128-SHA:ECDHE-RSA-AES256-SHA384:ECDHE-ECDSA-AES256-SHA384:ECDHE-RSA-AES256-SHA:ECDHE-ECDSA-AES256-SHA:DHE-RSA-AES128-SHA256:DHE-RSA-AES128-SHA:DHE-DSS-AES128-SHA256:DHE-RSA-AES256-SHA256:DHE-DSS-AES256-SHA:DHE-RSA-AES256-SHA:AES128-GCM-SHA256:AES256-GCM-SHA384:AES128-SHA256:AES256-SHA256:AES128-SHA:AES256-SHA:AES:CAMELLIA:DES-CBC3-SHA:!aNULL:!eNULL:!EXPORT:!DES:!RC4:!MD5:!PSK:!aECDH:!EDH-DSS-DES-CBC3-SHA:!EDH-RSA-DES-CBC3-SHA:!KRB5-DES-CBC3-SHA';
ssl_session_timeout 1d;
ssl_session_cache shared:SSL:50m;
ssl_stapling on;
ssl_stapling_verify on;
add_header Strict-Transport-Security max-age=15768000;
location / {
proxy_pass http://open-webui:8080;
proxy_http_version 1.1;
proxy_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
proxy_set_header Host $http_host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_buffering off;
proxy_read_timeout 600;
proxy_send_timeout 600;
}
location /openwebui/api {
proxy_buffering off;
proxy_set_header Origin '';
proxy_set_header Referer '';
proxy_pass http://open-webui:8080/api;
proxy_read_timeout 600;
proxy_send_timeout 600;
}
location /ollama/api {
proxy_pass http://ollama:11434/api;
proxy_set_header Host $http_host;
proxy_set_header X-Real-IP $remote_addr;
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
proxy_set_header X-Forwarded-Proto $scheme;
proxy_buffering off;
# Increase timeouts to prevent premature gateway errors
proxy_connect_timeout 300s;
proxy_send_timeout 300s;
proxy_read_timeout 300s;
send_timeout 300s;
# Disable request buffering for real-time streaming responses
proxy_request_buffering off;
# Prevent dropped connections
proxy_http_version 1.1;
proxy_set_header Connection "Keep-Alive";
proxy_set_header Proxy-Connection "Keep-Alive";
# Avoid caching issues
proxy_set_header Cache-Control "no-cache";
# Enable retries if the server is slow
proxy_next_upstream error timeout invalid_header http_500 http_502 http_503 http_504;
}
location /openwebui/api/v1 {
proxy_pass http://open-webui:8080/api/v1;
}
```
And my docker-compose.yml:
```
services:
ollama:
image: ollama/ollama:${OLLAMA_DOCKER_TAG-latest}
container_name: ollama
pull_policy: always
tty: true
restart: unless-stopped
volumes:
- ollama:/root/.ollama
- /etc/timezone:/etc/timezone:ro
- /etc/localtime:/etc/localtime:ro
ports:
- 11434
environment:
- OLLAMA_DEBUG=0
- OLLAMA_FLASH_ATTENTION=1
- OLLAMA_LOAD_TIMEOUT=30m
- OLLAMA_NEW_ENGINE=1
- OLLAMA_NUM_PARALLEL=4
- OLLAMA_KEEP_ALIVE=30m
- OLLAMA_MAX_LOADED_MODELS=7
- OLLAMA_CONTEXT_LENGTH=4096
logging:
driver: json-file
options:
max-size: "5m"
max-file: "2"
deploy:
resources:
reservations:
devices:
- driver: nvidia
device_ids: ["0", "1", "2", "3", "4", "5", "6", "7"]
capabilities:
- gpu
networks:
- internet
open-webui:
image: ghcr.io/open-webui/open-webui:${WEBUI_DOCKER_TAG-main}
container_name: open-webui
volumes:
- /var/ollama/open-webui:/app/backend/data
- /etc/timezone:/etc/timezone:ro
- /etc/localtime:/etc/localtime:ro
depends_on:
- ollama
ports:
- 8080
environment:
- OLLAMA_BASE_URL=http://ollama:11434
- FORWARDED_ALLOW_IPS=*
- 'WEBUI_SECRET_KEY='
- ENABLE_AUTOCOMPLETE_GENERATION=False
restart: unless-stopped
extra_hosts:
- host.docker.internal:host-gateway
logging:
driver: json-file
options:
max-size: "5m"
max-file: "2"
networks:
- internet
nginx:
image: nginx:alpine
container_name: reverse-proxy
ports:
- "80:80"
- "443:443"
restart: unless-stopped
depends_on:
- open-webui
volumes:
- ./open-webui.conf:/etc/nginx/conf.d/open-webui.conf
- ./certbot/letsencrypt:/etc/letsencrypt:ro
- /etc/ssl/certs/dhparam.pem:/etc/ssl/certs/dhparam.pem:ro
- /etc/timezone:/etc/timezone:ro
- /etc/localtime:/etc/localtime:ro
logging:
driver: json-file
options:
max-size: "5m"
max-file: "2"
networks:
- internet
```
### Steps to Reproduce
1. Use the docker compose with the nginx config
2. try to download a Model with the openwebui
### Logs & Screenshots
### Ollama logs
```
....
[GIN] 2025/04/01 - 09:11:37 | 200 | 787.609778ms | 172.18.0.4 | POST "/api/chat"
[GIN] 2025/04/01 - 09:11:54 | 200 | 13.983479806s | 172.18.0.4 | POST "/api/chat"
[GIN] 2025/04/01 - 09:11:54 | 200 | 669.648151ms | 172.18.0.4 | POST "/api/chat"
[GIN] 2025/04/01 - 09:11:55 | 200 | 900.411233ms | 172.18.0.4 | POST "/api/chat"
[GIN] 2025/04/01 - 09:19:59 | 404 | 12.482µs | <public_ip> | POST "/api/pull/0"
[GIN] 2025/04/01 - 09:22:06 | 200 | 177.282µs | <public_ip> | GET "/api/version"
```
### Additional Information
_No response_
GiteaMirror
added the bug label 2026-04-19 22:25:44 -05:00
Blocking a user prevents them from interacting with repositories, such as opening or commenting on pull requests or issues. Learn more about blocking a user.
Originally created by @Mozartuss on GitHub (Apr 1, 2025).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/12272
Check Existing Issues
Installation Method
Git Clone
Open WebUI Version
v0.5.20
Ollama Version (if applicable)
0.6.2
Operating System
Ubuntu 24.04 / Docker
Browser (if applicable)
No response
Confirmation
README.md.Expected Behavior
The model should be downloaded over the UI like calling
docker exec -it ollama ollama pull gemma3:latest, which works perfectly.Actual Behavior
I use an Nginx reverse proxy to secure my open-webui, as well as the Olama API and comfy UI. Everything works normally, but I can't download models directly over the open-webui. Surprisingly, I can't see any error in the open-webui docker log, only in the ollama logs.
It also surprised me that this ollama API call will be performed over my public IP instead of the localhost.
When I enter the Model I want, for example
gemma3:latestit makes an ollama api call with/api/pull/0The Following is my nginx config:
And my docker-compose.yml:
Steps to Reproduce
Logs & Screenshots
Ollama logs
Additional Information
No response