Sign in Publish
contextetech/

Minimal private AI chat: Ollama and Open WebUI

v1
Contexte Tech

254 publication(s) · 347 uses

Configuration English License: MIT updated 3 days ago
# Minimal private AI chat: Ollama and Open WebUI
code: 1dabn54 | type: stack | language: en | licence: MIT | version: v1
description: The simplest stack for a private AI chat: Ollama and Open WebUI with docker-compose, interface on port 3000.
page: https://contextetech.com/en/stacks/minimal-private-ai-chat-1dabn54
mcp: connect https://contextetech.com/mcp then call load_resource with code "1dabn54" (or ask "load 1dabn54")
json: https://contextetech.com/api/resources/contextetech--minimal-private-ai-chat
python: pip install contexte && contexte get 1dabn54
citation (required by the licence): contextetech. (2026). Minimal private AI chat: Ollama and Open WebUI (Version 1) [Stack]. Contexte Tech. https://contextetech.com/en/stacks/minimal-private-ai-chat-1dabn54

The simplest stack for a private AI chat: Ollama and Open WebUI with docker-compose, interface on 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: runs the model
  • Open WebUI: chat interface

Ports : 3000 (interface)

1. docker compose up -d 2. docker compose exec ollama ollama pull llama3.1 3. Open http://localhost:3000 and create the admin account.

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:

Community

No comments yet. Share your feedback, it will help the next person.