Halkali merkez neighborhood fatih st ozgur apt no 46 , Kucukcekmece , Istanbul , 34303 , TR
Deploy Ollama, Open WebUI, SearXNG and Redis on an Ubuntu GPU server to give local models controlled web search, with TLS, security, model tests and troubleshooting.
Deploy Ollama, Open WebUI, SearXNG and Redis on an Ubuntu GPU server to give local models controlled web search, with TLS, security, model tests and troubleshooting. Every command is presented as an operational step; replace example hostnames, passwords and secrets before execution.
Turkey (Turkish)
Germany (German)
Worldwide (English)
nvidia-smi
lspci -nn | grep -Ei "3d|display|vga"
docker run --rm --gpus all nvidia/cuda:12.6.0-base-ubuntu24.04 nvidia-smisudo mkdir -p /opt/eka-ai/searxng
cd /opt/eka-ai
openssl rand -hex 32use_default_settings: true
server:
secret_key: "GUCLU_RASTGELE_ANAHTAR"
limiter: true
image_proxy: true
search:
safe_search: 1
formats:
- html
- jsonservices:
ollama:
image: ollama/ollama:latest
restart: unless-stopped
volumes:
- ollama_veri:/root/.ollama
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
redis:
image: redis:7-alpine
restart: unless-stopped
command: redis-server --appendonly yes
volumes:
- redis_veri:/data
searxng:
image: searxng/searxng:latest
restart: unless-stopped
volumes:
- ./searxng/settings.yml:/etc/searxng/settings.yml:ro
depends_on:
- redis
open-webui:
image: ghcr.io/open-webui/open-webui:main
restart: unless-stopped
ports:
- 127.0.0.1:3000:8080
environment:
OLLAMA_BASE_URL: http://ollama:11434
ENABLE_WEB_SEARCH: "true"
WEB_SEARCH_ENGINE: searxng
SEARXNG_QUERY_URL: http://searxng:8080/search?q=<query>
volumes:
- openwebui_veri:/app/backend/data
depends_on:
- ollama
- searxng
volumes:
ollama_veri:
redis_veri:
openwebui_veri:sudo docker compose up -d
sudo docker compose exec ollama ollama pull qwen3:8b
sudo docker compose exec ollama ollama list
sudo docker compose pscurl -fsS http://127.0.0.1:3000/health
sudo docker compose exec searxng wget -qO- "http://127.0.0.1:8080/search?q=ubuntu&format=json" | head
sudo docker compose exec ollama ollama run qwen3:8b "Yalnızca TEST_OK yaz"watch -n 1 nvidia-smi
sudo docker compose logs -f --tail 100 open-webui searxng ollamasudo apt update
sudo apt install -y nginx certbot python3-certbot-nginx
sudo tee /etc/nginx/sites-available/ai.example.com > /dev/null <<'NGINX'
server {
listen 80;
listen [::]:80;
server_name ai.example.com;
client_max_body_size 10G;
proxy_read_timeout 3600;
proxy_send_timeout 3600;
location / {
proxy_pass http://127.0.0.1:3000;
proxy_http_version 1.1;
proxy_set_header Host $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_set_header Upgrade $http_upgrade;
proxy_set_header Connection "upgrade";
}
}
NGINX
sudo ln -s /etc/nginx/sites-available/ai.example.com /etc/nginx/sites-enabled/ai.example.com
sudo nginx -t
sudo systemctl reload nginxsudo certbot --nginx -d ai.example.com --redirect --agree-tos --no-eff-email -m [email protected]
sudo certbot renew --dry-run
curl -I https://ai.example.com
openssl s_client -connect ai.example.com:443 -servername ai.example.com </dev/null 2>/dev/null | openssl x509 -noout -subject -issuer -dates| Belirti / Symptom | Kök neden ve çözüm / Root cause and fix |
|---|---|
| Service or container does not start | Inspect compose configuration, dependency health, file permissions and the first fatal log line instead of repeatedly restarting. |
| Domain opens but HTTPS fails | Check A/AAAA records, ports 80/443, proxy mode, certificate challenge and conflicting reverse proxies. |
| Application cannot reach its database or queue | Use the internal service hostname, verify credentials and health checks, and keep database ports off the public interface. |
| Works initially but fails under load | Measure memory peaks, disk latency, connection pools and worker concurrency; increase capacity only after identifying the bottleneck. |
Yes after secrets are replaced, public access is restricted and a complete restore test has succeeded.
Minimums only prove the software can start. Size CPU, memory, IOPS and storage from representative workload measurements.
Yes. Use Full (strict) TLS and configure origin certificates, WebSockets and client IP forwarding where required.
Do not automatically apply major releases. Review migrations, back up data and retain the previous tested image.
Back up databases, uploaded files, persistent volumes, configuration, encryption keys and the deployed version together.
An NVMe VPS fits normal web workloads. Inference, accelerated OCR and video transcoding may require a compatible GPU.
Deploy Ollama, Open WebUI, SearXNG and Redis on an Ubuntu GPU server to give local models controlled web search, with TLS, security, model tests and troubleshooting.