Documentation Index
Fetch the complete documentation index at: https://mintlify.com/AsyncFuncAI/deepwiki-open/llms.txt
Use this file to discover all available pages before exploring further.
Docker is the easiest way to deploy DeepWiki Open in a reproducible environment. The project ships a multi-stage Dockerfile that builds the Python backend and Next.js frontend into a single image, and a docker-compose.yml that wires up environment variables, port mappings, and persistent volume mounts for you.
Repository data, embeddings, and generated wiki cache are stored in ~/.adalflow on your host machine. This directory is mounted into the container so your data survives container restarts and upgrades.
Deployment options
Docker Compose
Docker Run
Build Locally
Docker Compose is the recommended method for most deployments. It reads your .env file automatically and configures logging, health checks, and memory limits.1. Clone the repository and create a .env file:git clone https://github.com/AsyncFuncAI/deepwiki-open.git
cd deepwiki-open
GOOGLE_API_KEY=your_google_api_key
OPENAI_API_KEY=your_openai_api_key
# Optional providers
OPENROUTER_API_KEY=your_openrouter_api_key
AZURE_OPENAI_API_KEY=your_azure_openai_api_key
AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint
AZURE_OPENAI_VERSION=your_azure_openai_version
OLLAMA_HOST=your_ollama_host
# Optional: embedder type (openai | google | ollama)
DEEPWIKI_EMBEDDER_TYPE=google
# Optional: logging
LOG_LEVEL=INFO
LOG_FILE_PATH=api/logs/application.log
Full docker-compose.yml reference:services:
deepwiki:
build:
context: .
dockerfile: Dockerfile
ports:
- "${PORT:-8001}:${PORT:-8001}" # API port
- "3000:3000" # Next.js port
env_file:
- .env
environment:
- PORT=${PORT:-8001}
- NODE_ENV=production
- SERVER_BASE_URL=http://localhost:${PORT:-8001}
- LOG_LEVEL=${LOG_LEVEL:-INFO}
- LOG_FILE_PATH=${LOG_FILE_PATH:-api/logs/application.log}
volumes:
- ~/.adalflow:/root/.adalflow # Persist repository and embedding data
- ./api/logs:/app/api/logs # Persist log files across container restarts
mem_limit: 6g
mem_reservation: 2g
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:${PORT:-8001}/health"]
interval: 60s
timeout: 10s
retries: 3
start_period: 30s
Use a standalone docker run command when you want to launch the pre-built image from GitHub Container Registry without cloning the repository.Pull the image:docker pull ghcr.io/asyncfuncai/deepwiki-open:latest
docker run -p 8001:8001 -p 3000:3000 \
-e GOOGLE_API_KEY=your_google_api_key \
-e OPENAI_API_KEY=your_openai_api_key \
-e OPENROUTER_API_KEY=your_openrouter_api_key \
-e OLLAMA_HOST=your_ollama_host \
-e AZURE_OPENAI_API_KEY=your_azure_openai_api_key \
-e AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint \
-e AZURE_OPENAI_VERSION=your_azure_openai_version \
-v ~/.adalflow:/root/.adalflow \
ghcr.io/asyncfuncai/deepwiki-open:latest
.env file instead:docker run -p 8001:8001 -p 3000:3000 \
-v $(pwd)/.env:/app/.env \
-v ~/.adalflow:/root/.adalflow \
ghcr.io/asyncfuncai/deepwiki-open:latest
docker run -p 8001:8001 -p 3000:3000 \
-e GOOGLE_API_KEY=your_google_api_key \
-e DEEPWIKI_EMBEDDER_TYPE=google \
-v ~/.adalflow:/root/.adalflow \
ghcr.io/asyncfuncai/deepwiki-open:latest
Build the Docker image from source if you have made local modifications or need to include custom SSL certificates.Basic local build:git clone https://github.com/AsyncFuncAI/deepwiki-open.git
cd deepwiki-open
docker build -t deepwiki-open .
docker run -p 8001:8001 -p 3000:3000 \
-e GOOGLE_API_KEY=your_google_api_key \
-e OPENAI_API_KEY=your_openai_api_key \
-e OPENROUTER_API_KEY=your_openrouter_api_key \
-e AZURE_OPENAI_API_KEY=your_azure_openai_api_key \
-e AZURE_OPENAI_ENDPOINT=your_azure_openai_endpoint \
-e AZURE_OPENAI_VERSION=your_azure_openai_version \
-e OLLAMA_HOST=your_ollama_host \
deepwiki-open
# Place .crt or .pem files in a directory (default: certs/)
mkdir certs
cp /path/to/your/cert.crt certs/
# Build using the default directory
docker build .
# Or specify a custom directory with the build argument
docker build --build-arg CUSTOM_CERT_DIR=my-custom-certs .
CUSTOM_CERT_DIR build argument tells the Dockerfile where to find certificate files to install into the system trust store via update-ca-certificates. Volume mounts explained
The two volume mounts used in both docker-compose.yml and the docker run examples serve distinct purposes:
| Host path | Container path | Contents |
|---|
~/.adalflow | /root/.adalflow | Cloned repos (repos/), vector indexes (databases/), and wiki cache (wikicache/) |
./api/logs | /app/api/logs | Application log files |
~/.adalflow mount, every container restart triggers a full re-clone and re-index of every repository you have processed. The logs mount is optional but useful for auditing and debugging production deployments.
Health check
The docker-compose.yml configures an HTTP health check against the backend API:
curl -f http://localhost:8001/health