🖼️Framework Guide

Basic Usage

Hello World Example

pythonCopyfrom praxis_ai import Agent

agent = Agent(  
    'gemini-1.5-flash',
    system_prompt='Be concise, reply with one sentence.',  
)

result = agent.run_sync('Where does "hello world" come from?')  
print(result.data)

Advanced Features

Tools & Dependency Injection

pythonCopyfrom dataclasses import dataclass
from praxis import BaseModel, Field
from praxis_ai import Agent, RunContext

@dataclass
class SupportDependencies:  
    customer_id: int
    db: DatabaseConn  

class SupportResult(BaseModel):  
    support_advice: str = Field(description='Advice returned to the customer')
    block_card: bool = Field(description="Whether to block the customer's card")
    risk: int = Field(description='Risk level of query', ge=0, le=10)

support_agent = Agent(  
    'openai:gpt-4',  
    deps_type=SupportDependencies,
    result_type=SupportResult,  
    system_prompt=(  
        'You are a support agent in our bank, give the '
        'customer support and judge the risk level of their query.'
    ),
)

System Prompts

pythonCopy@support_agent.system_prompt  
async def add_customer_name(ctx: RunContext[SupportDependencies]) -> str:
    customer_name = await ctx.deps.db.customer_name(id=ctx.deps.customer_id)
    return f"The customer's name is {customer_name!r}"

Tools

pythonCopy@support_agent.tool  
async def customer_balance(
    ctx: RunContext[SupportDependencies], 
    include_pending: bool
) -> float:
    """Returns the customer's current account balance."""  
    return await ctx.deps.db.customer_balance(
        id=ctx.deps.customer_id,
        include_pending=include_pending,
    )

Monitoring and Debugging

Logfire Integration

pythonCopyimport logfire

logfire.configure()  
logfire.instrument_asyncpg()

Best Practices

Code Organization

• Keep agent definitions in separate modules

• Use dependency injection for external services

• Implement proper error handling

• Document tools and dependencies

Performance Optimization

• Use async/await for I/O operations

• Implement proper caching strategies

• Monitor and optimize token usage

• Leverage streaming for large responses

Testing

• Use dependency injection for mocking

• Implement unit tests for tools

• Create integration tests for full workflows

• Use Logfire for debugging and monitoring