Gradio Agent

Learn how to create web interfaces for your AI agents using Gradio

Quick Start

1. Install Dependencies

   First, install the required packages:

   pip install praisonaiagents gradio
   
2. Create Script

   Create a new file app.py:

   import gradio as gr
   from praisonaiagents import Agent, Tools
   from praisonaiagents import duckduckgo
   
   def research(query):
       agent = Agent(instructions="You are a Research Agent", tools=[duckduckgo])
       result = agent.start(query)
       # Format the result with enhanced markdown
       formatted_result = f"""
   {result}
   ----
   *Generated by PraisonAI Research Assistant*
       """
       return formatted_result
   
   # Create a simple Gradio interface
   demo = gr.Interface(
       fn=research,
       inputs=gr.Textbox(
           label="Research Query",
           placeholder="Enter your research topic...",
           lines=2
       ),
       outputs=gr.Markdown(
           show_copy_button=True,
           height=500,
           container=True
       ),
       title="AI Research Assistant",
       description="Enter your research query below to get started!",
   )
   
   if __name__ == "__main__":
       demo.launch()
   
3. Run Application

   Run your Gradio app:

   python app.py
   

Features

Simple Interface

Create beautiful UIs with minimal code.

Markdown Support

Rich text output with built-in markdown rendering.

Copy Button

One-click copying of results.

Responsive Design

Mobile-friendly interface out of the box.

Understanding the Code

The example demonstrates a simple research assistant with these key components:

1. Function Definition:

   • research() function that processes user input
   • Agent initialization and execution
   • Result formatting with markdown

2. Interface Setup:

   • Input textbox configuration
   • Markdown output with copy button
   • Title and description settings

3. Launch Configuration:

   • Main entry point check
   • Server launch with default settings

Customization

You can enhance the UI with additional Gradio components:

# Add multiple input types
demo = gr.Interface(
    fn=process_inputs,
    inputs=[
        gr.Textbox(label="Query"),
        gr.File(label="Upload Document"),
        gr.Dropdown(choices=["Option 1", "Option 2"])
    ],
    outputs=[
        gr.Markdown(label="Results"),
        gr.Plot(label="Visualization")
    ]
)

# Add themes and styling
demo = gr.Interface(
    ...
    theme="default",
    css=".gradio-container {background-color: #f0f0f0}"
)

# Add authentication
demo.launch(auth=("username", "password"))

Next Steps

• Learn about Prompt Chaining for complex UI workflows
• Explore Evaluator Optimizer for improving responses
• Check out Streamlit Integration for an alternative UI framework