1. pull image:
docker pull ghcr.io/opendevin/opendevin:latest2. make the installation script setup_opendevin.sh:
echo "Starting OpenDevin setup..."
export WORKSPACE_BASE=/home/yourUserName/dev/opendevin/workspace
echo "WORKSPACE_BASE set to $WORKSPACE_BASE"
echo "Checking .env file..."
cat .env
docker run \
-it \
--env-file .env \
-e SANDBOX_USER_ID=$(id -u) \
-e WORKSPACE_MOUNT_PATH=$WORKSPACE_BASE \
-v $WORKSPACE_BASE:/opt/workspace_base \
-v /var/run/docker.sock:/var/run/docker.sock \
-p 3000:3000 \
--add-host host.docker.internal:host-gateway \
ghcr.io/opendevin/opendevin:latest
echo "Docker container started."
3. make .env file: eg(Azure OpenAI):
LLM_BASE_URL="https://xxx.openai.azure.com/"
LLM_API_KEY=""
LLM_MODEL="azure/[yourDeployName]"
LLM_API_VERSION="2024-02-01"4. run installation script
5.access http://localhost:3000/index.html
reference:
KAGAYA's Blog 