Unlocking The Future Of Smart Applications: In-Depth Look At Phidata Framework And Usage Tips

❝

“The future is here, the blue ocean of smart applications is unfolding before us!” 🌊

❞

In this rapidly changing era, our lives are being transformed by various smart applications, emerging like bamboo shoots after a rain! But what are the supporting forces behind this smart revolution? Of course, it is the Phidata framework!✨ It is undoubtedly a brilliant gem that attracts the attention of countless developers. Phidata not only provides flexible and convenient tools to help developers design multimodal agents with intelligent behaviors but also embodies the best spirit of open source, encouraging more participation and contribution! Through this framework, developers can turn their imagination into reality, allowing smart applications to truly integrate into our lives!

1. Phidata: The Ultimate Building Framework For Intelligent Agents 🧠

Phidata is a super cool open-source framework tailored for developers, aimed at simplifying the process of building multimodal intelligent agents. 💪 With it, developers can create agents with memory, reasoning, and tool integration capabilities, making smart applications easily accessible! Whether it’s text, images, audio, or video, Phidata can easily handle various data formats, providing users with a rich interactive experience!🌈

2. Features Of Phidata: Key Abilities That Surpass Competitors 💡

3. Why Choose Phidata: Reasons Developers Prefer It 🌟

Many developers are fond of Phidata because it is easy to install, the code implementation is elegant, especially excelling in multi-agent collaboration!📈 Even better, the project provides rich monitoring and debugging tools, helping developers achieve more with less effort when building smart applications. The design philosophy of Phidata aims to simplify the creation and management of complex multimodal agents, providing reliable support for developers, allowing them to quickly implement efficient smart applications even in complex environments!💪

Through Phidata, developers can unleash their creativity and potential, stepping into a new era of smarter applications!😄

Mastering Phidata’s Usage Tips 🔧

Next, let’s dive deeper into the usage tips of Phidata together, gradually helping you master this open-source project through code examples!🚀

How To Install 📦

First, ensure that phidata and its dependencies are installed in your development environment! Open your terminal and enter the following command:

pip install -U phidata

Next, install the libraries required for specific agents using the following command:

pip install openai duckduckgo-search yfinance lancedb tantivy pypdf sqlalchemy fastapi[standard]

Creating A Web Search Agent 🌐

Let’s create a simple web search agent! You need to create a file named web_search.py in the project directory and input the following code:

from phi.agent import Agent  # Import Agent class to create agents
from phi.model.openai import OpenAIChat  # Import OpenAIChat model
from phi.tools.duckduckgo import DuckDuckGo  # Import DuckDuckGo search tool

# Create an agent named web_agent
web_agent = Agent(
    model=OpenAIChat(id="gpt-4o"),  # Use OpenAI's GPT-4 model
    tools=[DuckDuckGo()],  # Use DuckDuckGo search tool
    instructions=["Always include sources"],  # Set agent instructions to always include sources
    show_tool_calls=True,  # Set to show tool call status
    markdown=True,  # Enable markdown format for better presentation
)

# Print response, here it will ask for information about OpenAI Sora
web_agent.print_response("Tell me about OpenAI Sora?", stream=True)

To start the agent, remember to execute the following command and replace it with your OpenAI API key:

export OPENAI_API_KEY=sk-xxxx  # Replace with your OpenAI API key
python web_search.py

Creating A Financial Agent 💹

Next, let’s create an agent for financial analysis. Create a file named finance_agent.py and input this code:

from phi.agent import Agent  # Import Agent class
from phi.model.openai import OpenAIChat  # Import OpenAIChat model
from phi.tools.yfinance import YFinanceTools  # Import YFinanceTools to get financial data

# Create an agent named finance_agent
finance_agent = Agent(
    name="Finance Agent",  # Set agent name
    model=OpenAIChat(id="gpt-4o"),  # Continue using OpenAI's GPT-4 model
    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True, company_news=True)],  # Use YFinanceTools for various financial data retrieval
    instructions=["Use tables to display data"],  # Set agent instructions
    show_tool_calls=True,  # Show tool call status
    markdown=True,  # Enable markdown for beautifying output
)

# Print a summary of analyst recommendations for NVDA
finance_agent.print_response("Summarize analyst recommendations for NVDA", stream=True)

Simply enter the command:

python finance_agent.py

Creating An Image Processing Agent 🖼️

Next, let’s create an agent that can process images. Create a file named image_agent.py with the following code:

from phi.agent import Agent  # Import Agent class
from phi.model.openai import OpenAIChat  # Import OpenAIChat model
from phi.tools.duckduckgo import DuckDuckGo  # Also use DuckDuckGo search tool

# Create an agent named agent
agent = Agent(
    model=OpenAIChat(id="gpt-4o"),  # Use OpenAI's GPT-4 model
    tools=[DuckDuckGo()],  # Use DuckDuckGo search tool
    markdown=True,  # Enable markdown
)

# Print image information and related news
agent.print_response(
    "Tell me about this image and give me the latest news about it.", 
    images=["https://upload.wikimedia.org/wikipedia/commons/b/bf/Krakow_-_Kosciol_Mariacki.jpg"],  # Specify the image URL
    stream=True,
)

Enter the command to run it:

python image_agent.py

Creating A Multi-Agent Collaboration 🤝

Finally, let’s implement an example where an agent team collaborates together. Create a file named agent_team.py and add this code:

from phi.agent import Agent  # Import Agent class
from phi.model.openai import OpenAIChat  # Import OpenAIChat model
from phi.tools.duckduckgo import DuckDuckGo  # Import DuckDuckGo tool
from phi.tools.yfinance import YFinanceTools  # Import YFinanceTools

# Create Web Agent
web_agent = Agent(
    name="Web Agent",  # Set Web agent name
    role="Search the web for information",  # Set agent role
    model=OpenAIChat(id="gpt-4o"),  # Use GPT-4 model
    tools=[DuckDuckGo()],  # Add DuckDuckGo tool
    instructions=["Always include sources"],  # Set instructions
    show_tool_calls=True,  # Show tool calls
    markdown=True,  # Enable markdown display
)

# Create Finance Agent
finance_agent = Agent(
    name="Finance Agent",  # Set financial agent name
    role="Get financial data",  # Set agent role to get financial data
    model=OpenAIChat(id="gpt-4o"),  # Use the same model
    tools=[YFinanceTools(stock_price=True, analyst_recommendations=True, company_info=True)],  # Use YFinanceTools for financial data retrieval
    instructions=["Use tables to display data"],  # Set instructions
    show_tool_calls=True,  # Show tool calls
    markdown=True,  # Enable markdown display
)

# Create agent team
agent_team = Agent(
    team=[web_agent, finance_agent],  # Combine Web Agent and Finance Agent 
    model=OpenAIChat(id="gpt-4o"),  # Use GPT-4 model
    instructions=["Always include sources", "Use tables to display data"],  # Set execution instructions for agent team
    show_tool_calls=True,  # Show call status
    markdown=True,  # Enable markdown
)

# Print response, asking for a summary of NVDA's analyst ratings and share the latest news
agent_team.print_response("Summarize analyst recommendations and share the latest news for NVDA", stream=True)

To run this agent team, you just need to enter:

python agent_team.py

With these vivid and interesting examples, you will quickly master Phidata, creating different types of intelligent agents, and even making the development process easier and more enjoyable!🎉