Automatisations locales : n8n et Ollama

Stack docker-compose pour automatiser avec une IA locale : n8n (workflows) et Ollama (modèle), sans envoyer de données à une API externe.

Access Medium

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

Services

• n8n : éditeur de workflows
• Ollama : modèle local, joignable à l'adresse http://ollama:11434

Ports : 5678 (n8n)

1. docker compose up -d 2. docker compose exec ollama ollama pull mistral 3. Ouvrir http://localhost:5678 ; dans les nœuds Ollama de n8n, utiliser l'adresse http://ollama:11434.

docker-compose.yml

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

  n8n:
    image: n8nio/n8n
    depends_on: [ollama]
    environment:
      - GENERIC_TIMEZONE=Europe/Paris
    volumes:
      - n8n:/home/node/.n8n
    ports:
      - "5678:5678"

volumes:
  ollama:
  n8n:

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--n8n-ollama-automatisations-locales

Type

Stacks

File

docker-compose.yml

Format

YML

Size

295 bytes

Encoding

UTF-8

Estimated tokens

≈ 82

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

  n8n:
    image: n8nio/n8n
    depends_on: [ollama]
    environment:
      - GENERIC_TIMEZONE=Europe/Paris
    volumes:
      - n8n:/home/node/.n8n
    ports:
      - "5678:5678"

volumes:
  ollama:
  n8n:

Launch

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