Chat IA privé minimal : Ollama et Open WebUI

La stack la plus simple pour un chat IA privé : Ollama et Open WebUI en docker-compose, interface sur le port 3000.

Access Medium

• — Read files or data : No
• ✓ Modify or delete files
• ✓ Send data over the internet
• — Run commands on the machine : No

Services

• Ollama : fait tourner le modèle
• Open WebUI : interface de chat

Ports : 3000 (interface)

1. docker compose up -d 2. docker compose exec ollama ollama pull mistral 3. Ouvrir http://localhost:3000 et créer le compte administrateur.

docker-compose.yml

services:
  ollama:
    image: ollama/ollama
    volumes:
      - ollama:/root/.ollama

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    depends_on: [ollama]
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
    volumes:
      - open-webui:/app/backend/data
    ports:
      - "3000:8080"

volumes:
  ollama:
  open-webui:

Estimated cost

Input tokens per call : ≈ 268

Input cost only, excluding the model's answer. Providers' public standard prices (Mistral AI, DeepSeek, OpenAI, Anthropic) converted from USD to euros at the ECB rate of September 29, 2026. Estimate: 1 token ≈ 3.6 characters.

Identifier

contextetech--chatgpt-prive-ollama-open-webui

Type

Stacks

File

docker-compose.yml

Format

YML

Size

349 bytes

Encoding

UTF-8

Estimated tokens

≈ 97

Language

French

License

MIT

Commercial use

Allowed

Personal data

None

Version

1.0

Published on

October 1, 2026 at 6:55 PM

Updated on

October 1, 2026 at 6:55 PM

Storage

in database

Uses

0

Likes

0

docker-compose.yml

services:
  ollama:
    image: ollama/ollama
    volumes:
      - ollama:/root/.ollama

  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    depends_on: [ollama]
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
    volumes:
      - open-webui:/app/backend/data
    ports:
      - "3000:8080"

volumes:
  ollama:
  open-webui:

Launch

# enregistrez docker-compose.yml, puis :
docker compose up -d
docker compose ps