MCP Run Python

🚀 PydanticAI Bank Support Agent Example

This README provides an example of building a bank support agent using PydanticAI, including dependency injection, dynamic system prompts, and the definition of tool functions.

🚀 Quick Start

To get started with PydanticAI, refer to the following resources:

• Example Documentation
• General Documentation for more information on building applications.
• API Reference to understand the PydanticAI interfaces.

💻 Usage Examples

Basic Usage

1. Define Dependencies

from dataclasses import dataclass

from pydantic import BaseModel, Field
from pydantic_ai import Agent, RunContext

from bank_database import DatabaseConn


# Dependencies required for the support agent, including customer ID and database connection.
@dataclass
class SupportDependencies:
    customer_id: int
    db: DatabaseConn

2. Define the Output Model

# The output model defines the structure of the results returned by the support agent.
class SupportOutput(BaseModel):
    support_advice: str = Field(description='Advice to be provided to the customer')
    block_card: bool = Field(description="Whether to block the customer's card")
    risk: int = Field(description='Risk level of the query', ge=0, le=10)

3. Define the Support Agent

# The support agent acts as the front-line support for the bank, handling customer queries.
support_agent = Agent(
    'openai:gpt-4o',
    deps_type=SupportDependencies,
    output_type=SupportOutput,
    system_prompt=(
        'You are a bank support agent. Provide support based on customer needs and assess the risk level of the query.'
    ),
)

4. Define the Dynamic System Prompt

# The dynamic system prompt can customize the response based on the customer name in the dependencies.
@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}"

5. Define the Tool Function

# The tool function allows the agent to call external functions, such as querying the customer's balance.
@support_agent.tool
async def customer_balance(
        ctx: RunContext[SupportDependencies], include_pending: bool
) -> float:
    """Return the customer's current account balance."""
    balance = await ctx.deps.db.customer_balance(
        id=ctx.deps.customer_id,
        include_pending=include_pending,
    )
    return balance

6. Use the Agent to Handle Queries

async def main():
    deps = SupportDependencies(customer_id=123, db=DatabaseConn())
    result = await support_agent.run('What is my balance?', deps=deps)
    print(result.output)
    # Example output:
    # support_advice='Hello, Mr. John, your current account balance is $123.45.' block_card=False risk=1

    result = await support_agent.run('I just lost my card!', deps=deps)
    print(result.output)
    # Example output:
    # support_advice="I'm very sorry to hear that, Mr. John. To prevent unauthorized transactions, we have temporarily blocked your card." block_card=True risk=8

📚 Documentation

For more usage examples of PydanticAI, please refer to the Example Documentation.

Summary

By using PydanticAI, you can easily build a support agent with dependency injection, dynamic system prompts, and tool functions to meet various business needs. Hope these examples are helpful to you!