Skip to content

Instantly share code, notes, and snippets.

@suoko
Last active April 14, 2024 20:45
Show Gist options
  • Save suoko/46f5810de7fc9d3e46dac6ae61a97181 to your computer and use it in GitHub Desktop.
Save suoko/46f5810de7fc9d3e46dac6ae61a97181 to your computer and use it in GitHub Desktop.
Open devin
sudo apt update
sudo apt install curl build-essential docker-compose-v2
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.39.1/install.sh | bash
export NVM_DIR="$HOME/.nvm"
wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
chmod +x https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh
Miniconda3-latest-Linux-x86_64.sh
curl -fsSL https://ollama.com/install.sh | sh
ollama run mistral:7b-instruct-v0.2-q4_K_M
git clone https://github.com/OpenDevin/OpenDevin.git
cd OpenDevin
conda create -n od python=3.11
conda activate od
Edit config.toml and put this:
LLM_API_KEY="ollama"
LLM_MODEL="ollama/mistral:7b-instruct-v0.2-q4_K_M"
LLM_EMBEDDING_MODEL="local"
LLM_BASE_URL="http://localhost:11434"
WORKSPACE_DIR="./workspace"
mkdir workspace
Add to /etc/systemd/system/ollama.service this line:
Environment="OLLAMA_HOST=0.0.0.0"
curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.35.3/install.sh | bash
nvm install 18.17.1
nvm use 18.17.1
python -m pip install litellm uvicorn fastapi toml playwright json_repair chromadb json_repair llama_index llama_index.vector_stores.chroma llama_index.embeddings.huggingface termcolor pexpect docker poetry PyJWT
make build
make run
- OR -
In one conda activated terminal:
make start-backend
In another conda activated terminal:
make start-frontend
@suoko
Copy link
Author

suoko commented Apr 14, 2024

That guide is for Ubuntu, something might differ in wsl

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment