app.py

import gradio as gr
import asyncio
from typing import Generator, List, Dict, Any
from utils.langgraph_pipeline import run_pipeline_and_save

class AgentInference:
    def __init__(self):
        self.current_agent = None
        self.chat_log = []
        self.is_running = False

    async def stream_agent_output(self, agent_name: str, prompt: str) -> Generator[str, None, None]:
        """Stream output from a single agent"""
        self.current_agent = agent_name
        # Simulate streaming output with delays
        yield f"🤖 {agent_name} is thinking..."
        await asyncio.sleep(1)
        
        # Get agent output
        result = await self.get_agent_output(agent_name, prompt)
        
        # Stream the output word by word
        words = result.split()
        for word in words:
            yield f"{word} "
            await asyncio.sleep(0.1)
        
        self.chat_log.append({"role": agent_name, "content": result})
        yield "\n\n"

    async def get_agent_output(self, agent_name: str, prompt: str) -> str:
        """Get output from a specific agent"""
        # This would be replaced with actual agent calls
        agents = {
            "Product Manager": "Analyzing requirements and defining product specifications...",
            "Project Manager": "Creating project timeline and resource allocation...",
            "Software Architect": "Designing system architecture and technical specifications...",
            "UI Designer": "Creating beautiful and user-friendly interface designs...",
            "Software Engineer": "Implementing the UI components and functionality...",
            "Quality Assurance": "Reviewing and testing the implementation..."
        }
        return agents.get(agent_name, "Processing...")

    async def run_inference(self, prompt: str) -> Generator[Dict[str, Any], None, None]:
        """Run inference through all agents with streaming output"""
        self.is_running = True
        self.chat_log = []
        
        agents = [
            "Product Manager",
            "Project Manager",
            "Software Architect",
            "UI Designer",
            "Software Engineer",
            "Quality Assurance"
        ]
        
        for agent in agents:
            if not self.is_running:
                break
                
            async for output in self.stream_agent_output(agent, prompt):
                yield {
                    "agent": agent,
                    "output": output,
                    "chat_log": self.chat_log
                }
            
            # Add a small delay between agents
            await asyncio.sleep(0.5)
        
        # Generate final output
        yield {
            "agent": "System",
            "output": "🎉 UI Generation Complete!",
            "chat_log": self.chat_log
        }

inference_engine = AgentInference()

def format_chat_log(chat_log: List[Dict[str, Any]]) -> List[tuple]:
    """Format chat log for display"""
    formatted_log = []
    for entry in chat_log:
        role = entry["role"]
        content = entry["content"]
        formatted_log.append((f"**{role}**:", content))
    return formatted_log

async def handle_run(prompt: str) -> Generator[tuple, None, None]:
    """Handle the run button click with streaming output"""
    async for update in inference_engine.run_inference(prompt):
        formatted_log = format_chat_log(update["chat_log"])
        yield formatted_log, None  # None for file_output until complete

with gr.Blocks() as demo:
    gr.Markdown("""
    # 🔧 Multi-Agent UI Generator (Real-time Inference)
    
    This system uses multiple AI agents working together to generate beautiful UI designs in real-time:
    1. Product Manager: Defines requirements
    2. Project Manager: Creates project plan
    3. Software Architect: Designs system architecture
    4. UI Designer: Creates beautiful UI design
    5. Software Engineer: Implements the code
    6. Quality Assurance: Reviews and suggests improvements
    
    Watch as each agent contributes to the design in real-time!
    """)
    
    with gr.Row():
        with gr.Column(scale=2):
            input_box = gr.Textbox(
                lines=4,
                label="Enter your product idea prompt",
                placeholder="Describe the website or UI you want to create..."
            )
            run_btn = gr.Button("Generate Website", variant="primary")
            stop_btn = gr.Button("Stop Generation", variant="stop")
        
        with gr.Column(scale=3):
            chatbox = gr.Chatbot(
                label="Agent Conversation Log",
                type="messages",
                height=600
            )
            file_output = gr.File(label="Download UI ZIP")
    
    # Handle run button click
    run_btn.click(
        fn=handle_run,
        inputs=[input_box],
        outputs=[chatbox, file_output],
        api_name="generate"
    )
    
    # Handle stop button click
    def stop_generation():
        inference_engine.is_running = False
        return "Generation stopped by user"
    
    stop_btn.click(
        fn=stop_generation,
        outputs=[chatbox]
    )

demo.queue()
demo.launch()