Quick Start Guide

🚀 Your First Agent in 5 Minutes

Welcome to DeepCore! This guide will help you create your first AI agent in just a few minutes. Let's get started!

Prerequisites

Before you begin, make sure you have:

• Python 3.11+

• pip or poetry

• Basic understanding of Python

• An API key for your preferred AI model (e.g., OpenAI, Claude)

Installation

# Using pip
pip install deepcore
​
# Or using poetry
poetry add deepcore

1. Create Your First Agent

from deepcore import Agent
​
# Initialize a simple agent
agent = Agent(
    name="my_first_agent",
    description="A helpful assistant",
    model="gpt-4"  # or any other supported model
)
​
# Start a conversation
response = agent.chat("Hello! Can you help me with some data analysis?")
print(response)

2. Add Tools to Your Agent

from deepcore.tools import Calculator, WebSearch
​
# Create an agent with tools
agent = Agent(
    name="powered_agent",
    description="An agent that can calculate and search",
    model="gpt-4",
    tools=[Calculator(), WebSearch()]
)
​
# Ask the agent to use tools
response = agent.chat("What is the square root of 144 plus the current temperature in New York?")
print(response)

3. Create a Custom Tool

from deepcore.tools import BaseTool
​
class WeatherTool(BaseTool):
    def __init__(self):
        super().__init__(
            name="weather",
            description="Get weather information"
        )
    
    async def _run(self, location: str) -> str:
        # Implement weather checking logic
        return f"Weather information for {location}"
​
# Use your custom tool
agent = Agent(
    name="weather_agent",
    tools=[WeatherTool()]
)

4. Multi-Agent Collaboration

from deepcore import Agent, Team
​
# Create specialized agents
researcher = Agent(name="researcher", tools=["web_search"])
analyst = Agent(name="analyst", tools=["calculator"])
writer = Agent(name="writer", tools=["text_processor"])
​
# Create a team
team = Team(
    name="research_team",
    agents=[researcher, analyst, writer]
)
​
# Let the team work together
result = team.collaborate("Research the impact of AI on healthcare and prepare a report")

5. Deploy Your Agent

from deepcore.deploy import APIServer
​
# Create an API server
server = APIServer(agents=[agent])
​
# Start the server
server.run(host="localhost", port=8000)

Now your agent is accessible via REST API:

curl -X POST http://localhost:8000/chat \
    -H "Content-Type: application/json" \
    -d '{"message": "Hello, agent!"}'

Next Steps

Explore More Features

• Add memory to your agents

• Implement custom workflows

• Create agent teams

• Add authentication

• Monitor performance

Advanced Topics

• Custom model integration

• Advanced tool development

• Multi-agent orchestration

• Performance optimization

• Security implementation

Best Practices

1. Always handle errors gracefully

2. Monitor agent performance

3. Implement rate limiting

4. Secure sensitive information

5. Test thoroughly

Common Use Cases

Customer Service

service_agent = Agent(
    name="customer_service",
    description="Helpful customer service agent",
    tools=["faq", "ticket_system", "email"]
)

Data Analysis

analysis_agent = Agent(
    name="data_analyst",
    description="Data analysis specialist",
    tools=["pandas", "matplotlib", "database"]
)

Content Creation

content_agent = Agent(
    name="content_creator",
    description="Creative content writer",
    tools=["text_generator", "image_creator"]
)

Troubleshooting

Common Issues

1. Model API Issues

# Implement fallback
agent = Agent(
    name="reliable_agent",
    model="gpt-4",
    fallback_model="gpt-3.5-turbo"
)

1. Rate Limiting

# Implement rate limiting
agent = Agent(
    name="controlled_agent",
    rate_limit=10,  # requests per minute
    rate_limit_period=60
)

1. Memory Issues

# Manage memory
agent = Agent(
    name="memory_efficient",
    max_memory_tokens=1000,
    memory_type="sliding_window"
)