Home›Team Workspace

Deploy Open WebUI with DeepSeek for Team Chat and Private RAG

Open WebUI is the leading open-source ChatGPT alternative. Follow this guide to deploy Open WebUI using Docker and configure DeepSeek API for team collaboration and document search.

Maintained by DeepSeekDSH (independent site)Updated: 2026-09-13

On this page

Open WebUI parameters

OpenAI-compatible Endpoint: https://api.deepseek.com/v1 or https://api.deepseek.com
API key: Generated in your DeepSeek Platform console.
Default web interface: http://localhost:3000 or http://your-server-ip:3000

STEP 1

One-line Docker & Docker Compose setup

Launch Open WebUI using the official container image:

# Option A: Single command Docker run
docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://api.deepseek.com/v1 \
  -e OPENAI_API_KEY=sk-your_deepseek_api_key \
  -v open-webui:/app/backend/data \
  --name open-webui \
  --restart always \
  ghcr.io/open-webui/open-webui:main

Or use docker-compose.yml for persistent multi-container workflows:

version: '3.8'
services:
  open-webui:
    image: ghcr.io/open-webui/open-webui:main
    container_name: open-webui
    ports:
      - "3000:8080"
    environment:
      - OPENAI_API_BASE_URL=https://api.deepseek.com/v1
      - OPENAI_API_KEY=sk-your_deepseek_api_key
    volumes:
      - open-webui-data:/app/backend/data
    restart: always

volumes:
  open-webui-data:

STEP 2

Web interface initialization and model activation

Open http://localhost:3000 in your browser and create your administrator account.
Navigate to Admin Panel → Settings → Connections in the bottom-left menu.
Under OpenAI API, verify the Base URL is https://api.deepseek.com/v1 and paste your API key.
Click the refresh icon to verify that deepseek-chat and deepseek-reasoner are populated and enabled.

STEP 3

Build document RAG knowledge bases

Open WebUI natively supports uploading PDF, Markdown, TXT, and DOCX files for private retrieval:

Click Workspace → Knowledge in the sidebar and create a new knowledge collection.
Upload your project manuals or internal wikis; the engine chunks and indexes the content automatically.
In any chat conversation, type #collection-name or attach the knowledge base to query your documents directly with DeepSeek.

STEP 4

Enable web search integration

In Admin Settings → Web Search, enable built-in DuckDuckGo (zero configuration required) or connect SearXNG / Tavily. When toggled on in conversations, DeepSeek queries live internet sources to answer recent questions.

Troubleshooting

Empty model catalog

Ensure OPENAI_API_BASE_URL includes the /v1 suffix and that the server has outbound internet access to api.deepseek.com.

R1 reasoning chain rendering issues

Recent releases of Open WebUI support foldable reasoning_content blocks out of the box. Ensure you are running the latest open-webui:main Docker tag.