Daita Init
Initialize a new Daita project with a minimal structure and example components. This command creates everything you need to start building AI agents.
#Syntax
bash
daita init [PROJECT_NAME] [OPTIONS]#Arguments
| Argument | Type | Required | Description |
|---|---|---|---|
PROJECT_NAME | string | No | Name of the project directory to create. If not provided, prompts for name or uses current directory |
#Options
| Option | Description |
|---|---|
--force | Overwrite existing project directory if it exists |
--verbose | Show detailed output during initialization |
#Examples
#Basic Usage
bash
# Create a new project in a new directory
daita init my-agent
# Create project in current directory (will prompt for name)
daita init
# Force overwrite existing directory
daita init existing-project --force
# Show detailed output during creation
daita init my-agent --verbose#Generated Project Structure
When you run daita init, a minimal project structure is created:
python
my-project/
├── .daita/ # Daita metadata (auto-generated)
├── agents/ # Your AI agents
│ ├── __init__.py
│ └── my_agent.py # Example agent
├── workflows/ # Your workflows
│ ├── __init__.py
│ └── my_workflow.py # Example workflow
├── data/ # Data files
│ └── .gitkeep
├── tests/ # Test files
│ ├── __init__.py
│ └── test_basic.py # Example tests
├── daita-project.yaml # Project configuration
├── requirements.txt # Python dependencies
├── .gitignore # Git ignore patterns
└── README.md # Project documentation#Configuration Files
#daita-project.yaml
The initial configuration file is minimal:
yaml
name: my-project
version: 1.0.0
description: A Daita AI agent project
created_at: '2025-01-15T10:00:00'
agents: [] # Populated as you create agents
workflows: [] # Populated as you create workflows
environments:
development: {}
staging: {}
production: {}#requirements.txt
Minimal dependencies for getting started:
txt
# Daita Agents Framework
daita-agents>=0.1.0
# LLM provider (choose one)
openai>=1.0.0
# Development
pytest>=7.0.0
pytest-asyncio>=0.21.0#Example Agent Template
Generated in agents/my_agent.py:
python
"""
My Agent
A simple starter agent. Replace this with your own logic.
"""
from daita import Agent
def create_agent():
"""Create the agent instance using direct Agent pattern."""
# Option 1: Simple instantiation (uses defaults)
agent = Agent(name="My Agent")
# Option 2: Direct LLM configuration (uncomment and modify as needed)
# import os
# agent = Agent(
# name="My Agent",
# llm_provider="openai",
# model="gpt-4",
# api_key=os.getenv("OPENAI_API_KEY")
# )
# Optional: Add plugins
# from daita.plugins import postgresql
# agent.add_plugin(postgresql(host="localhost", database="mydb"))
return agent
if __name__ == "__main__":
import asyncio
async def main():
agent = create_agent()
result = await agent.process("test_task", "Hello, world!")
print(result)
asyncio.run(main())#Example Workflow Template
Generated in workflows/my_workflow.py:
python
"""
My Workflow
A simple starter workflow. Replace this with your own logic.
"""
from daita import Agent, Workflow
def create_workflow():
"""Create the workflow instance using direct Workflow pattern."""
workflow = Workflow("My Workflow")
# Add your agents here
# agent = Agent(name="Agent")
# workflow.add_agent("agent", agent)
return workflow
async def run_workflow(data=None):
"""Run the workflow with direct pattern."""
workflow = create_workflow()
try:
await workflow.start()
# Your workflow logic here
result = f"Workflow processed: {data}"
return {
'status': 'success',
'result': result
}
finally:
await workflow.stop()
if __name__ == "__main__":
import asyncio
async def main():
result = await run_workflow("Hello, workflow!")
print(result)
asyncio.run(main())#Post-Initialization Steps
After running daita init, follow these steps:
#1. Navigate to Project
bash
cd my-project#2. Install Dependencies
bash
# Install dependencies
pip install -r requirements.txt
# Or use a virtual environment (recommended)
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt#3. Set LLM API Key
bash
# Set your LLM provider key
export OPENAI_API_KEY="your-openai-key"
# Or use .env file
echo "OPENAI_API_KEY=your-key" > .env#4. Test the Example Agent
bash
# Test directly
python agents/my_agent.py
# Or use the test command
daita test#Common Issues and Solutions
#Permission Denied
bash
❌ Permission denied: Cannot create directory 'my-project'Solution: Ensure you have write permissions in the current directory:
bash
# Check permissions
ls -la
# Create with sudo if needed (not recommended)
sudo daita init my-project
sudo chown -R $USER:$USER my-project#Directory Already Exists
bash
❌ Error: Directory 'my-project' already existsSolutions:
bash
# Use --force to overwrite
daita init my-project --force
# Or choose a different name
daita init my-project-v2
# Or remove existing directory
rm -rf my-project
daita init my-project#Missing Dependencies
bash
❌ Missing CLI dependenciesSolution: Install CLI dependencies:
bash
pip install daita-agents[cli]#Next Steps
After initializing your project:
- Create Components - Add more agents and workflows
- Test Your Project - Test and debug your agents
- Configure Settings - Customize project configuration
- Deploy - Deploy to production
#Best Practices
#Project Naming
- Use descriptive, kebab-case names:
data-processor,sentiment-analyzer - Avoid spaces and special characters
- Keep names concise but meaningful
#Version Control
bash
# Initialize git repository
cd my-project
git init
git add .
git commit -m "Initial Daita project setup"The generated .gitignore includes:
.daita/cache directory- Python bytecode (
.pyc,__pycache__) .envfiles and API keys- Virtual environments