suna安装指北

Requirements

You'll need the following components:

A Supabase project for database and authentication
Redis database for caching and session management
Daytona sandbox for secure agent execution
Python 3.11 for the API backend
API keys for LLM providers (OpenAI or Anthropic)
(Optional but recommended) Tavily API key for enhanced search capabilities

Prerequisites

  1. Supabase:

    • Create a new Supabase project
    • Save your project's API URL, anon key, and service role key for later use
    • Install the Supabase CLI
  2. Redis: Set up a Redis instance using one of these options:

    • Upstash Redis (recommended for cloud deployments)
    • Local installation:
      • Mac: brew install redis
      • Linux: Follow distribution-specific instructions
      • Windows: Use WSL2 or Docker
    • Save your Redis connection details for later use
  3. Daytona:

    • Create an account on Daytona
    • Generate an API key from your account settings
    • Go to Images
    • Click "Add Image"
    • Enter adamcohenhillel/kortix-suna:0.0.20 as the image name
    • Set exec /usr/bin/supervisord -n -c /etc/supervisor/conf.d/supervisord.conf as the Entrypoint
  4. LLM API Keys:

    • Obtain an API key from OpenAI or Anthropic
    • While other providers should work via LiteLLM, OpenAI and Anthropic are recommended
  5. Search API Key (可选,但推荐):

    • For enhanced search capabilities, obtain an Tavily API key
  6. RapidAPI API Key (可选,但推荐):

    • To enable API services like LinkedIn, and others, you'll need a RapidAPI key
    • Each service requires individual activation in your RapidAPI account:
      1. Locate the service's base_url in its corresponding file (e.g., "https://linkedin-data-scraper.p.rapidapi.com" in backend/agent/tools/data_providers/LinkedinProvider.py)
      2. Visit that specific API on the RapidAPI marketplace
      3. Subscribe to the service (many offer free tiers with limited requests)
      4. Once subscribed, the service will be available to your agent through the API Services tool

Installation Steps

  1. Clone the repository:
git clone https://github.com/kortix-ai/suna.git
cd suna
  1. Configure backend environment:
cd backend
cp .env.example .env  # Create from example if available, or use the following template

Edit the .env file and fill in your credentials:

NEXT_PUBLIC_URL="http://localhost:3000"

# Supabase credentials from step 1
SUPABASE_URL=your_supabase_url
SUPABASE_ANON_KEY=your_supabase_anon_key
SUPABASE_SERVICE_ROLE_KEY=your_supabase_service_role_key

# Redis credentials from step 2
REDIS_HOST=your_redis_host
REDIS_PORT=6379
REDIS_PASSWORD=your_redis_password
REDIS_SSL=True  # Set to False for local Redis without SSL

# Daytona credentials from step 3
DAYTONA_API_KEY=your_daytona_api_key
DAYTONA_SERVER_URL="https://app.daytona.io/api"
DAYTONA_TARGET="us"

# Anthropic or OpenAI: 
# Anthropic
ANTHROPIC_API_KEY=
MODEL_TO_USE="anthropic/claude-3-7-sonnet-latest"

# OR OpenAI API:
OPENAI_API_KEY=your_openai_api_key
MODEL_TO_USE="gpt-4o"

# Optional but recommended
TAVILY_API_KEY=your_tavily_api_key  # Optional
RAPID_API_KEY=
  1. Set up Supabase database:
# Login to Supabase CLI
supabase login

# Link to your project (find your project reference in the Supabase dashboard)
supabase link --project-ref your_project_reference_id

# Push database migrations
supabase db push
  1. Configure frontend environment:
cd ../frontend
cp .env.example .env.local  # Create from example if available, or use the following template

Edit the .env.local file:

NEXT_PUBLIC_SUPABASE_URL=your_supabase_url
NEXT_PUBLIC_SUPABASE_ANON_KEY=your_supabase_anon_key
NEXT_PUBLIC_BACKEND_URL="http://localhost:8000/api"
NEXT_PUBLIC_URL="http://localhost:3000"
  1. Install dependencies:
# Install frontend dependencies
cd frontend
npm install

# Install backend dependencies
cd ../backend
pip install -r requirements.txt
  1. Start the application:

    In one terminal, start the frontend:

cd frontend
npm run dev

In another terminal, start the backend:

cd backend
python api.py
  1. Access Suna:
    • Open your browser and navigate to http://localhost:3000
    • Sign up for an account using the Supabase authentication
    • Start using your self-hosted Suna instance!

你可能感兴趣的:(deepseek,java)