Upload 9 files

README.md

@@ -1,13 +1,14 @@
 ---
-title: Multi Agent Test
+title: MAC
 emoji: 👁
-colorFrom: pink
-colorTo: green
+colorFrom: blue
+colorTo: blue
 sdk: gradio
 sdk_version: 5.29.0
 app_file: app.py
 pinned: false
-short_description: enhancements
+license: mit
+short_description: MAC
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,21 @@
+import gradio as gr
+from utils.langgraph_pipeline import run_pipeline_and_save
+
+def handle_run(prompt):
+    chat_log, zip_path = run_pipeline_and_save(prompt)
+    return chat_log, zip_path
+
+with gr.Blocks() as demo:
+    gr.Markdown("# 🔧 Multi-Agent UI Generator")
+    input_box   = gr.Textbox(lines=4, label="Enter your product idea prompt")
+    run_btn     = gr.Button("Generate Website")
+    chatbox     = gr.Chatbot(label="Agent Conversation Log", type="messages")
+    file_output = gr.File(label="Download UI ZIP")
+
+    run_btn.click(
+        fn=handle_run,
+        inputs=[input_box],
+        outputs=[chatbox, file_output],
+    )
+
+demo.launch()

product_manager_agent.py

@@ -0,0 +1,27 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from langchain_core.messages import AIMessage
+
+MODEL_REPO = "Rahul-8799/product_manager_mistral"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_REPO,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def run(state: dict) -> dict:
+    """Generates structured product requirements from user input prompt."""
+    messages = state["messages"]
+    prompt = messages[-1].content
+
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
+    output_ids = model.generate(input_ids, max_new_tokens=3000)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    return {
+        "messages": [AIMessage(content=output)],
+        "chat_log": state["chat_log"] + [{"role": "Product Manager", "content": output}],
+        "pm_output": output,
+    }

project_manager_agent.py

@@ -0,0 +1,28 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from langchain_core.messages import AIMessage
+
+MODEL_REPO = "Rahul-8799/project_manager_gemma3"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_REPO,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+
+def run(state: dict) -> dict:
+    """Creates project plan based on product requirements."""
+    messages = state["messages"]
+    prompt = messages[-1].content
+
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
+    output_ids = model.generate(input_ids, max_new_tokens=3000)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    return {
+        "messages": [AIMessage(content=output)],
+        "chat_log": state["chat_log"] + [{"role": "Project Manager", "content": output}],
+        "proj_output": output,
+    }

quality_assurance_agent.py

@@ -0,0 +1,44 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from langchain_core.messages import AIMessage
+
+MODEL_REPO = "Rahul-8799/quality_assurance_stablecode"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_REPO,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def run(state: dict) -> dict:
+    """Reviews UI/UX implementation and suggests improvements for better user experience"""
+    messages = state["messages"]
+    prompt = messages[-1].content
+    
+    # Enhance the prompt with UI/UX quality checks
+    enhanced_prompt = f"""
+    Review the UI implementation and check for:
+    1. Proper spacing and alignment
+    2. Consistent styling and theming
+    3. Responsive design implementation
+    4. Accessibility compliance
+    5. Visual hierarchy
+    6. Component reusability
+    7. Performance optimization
+    8. Cross-browser compatibility
+    9. Mobile responsiveness
+    10. User interaction patterns
+    
+    Original code: {prompt}
+    """
+    
+    input_ids = tokenizer(enhanced_prompt, return_tensors="pt").input_ids.to(model.device)
+    output_ids = model.generate(input_ids, max_new_tokens=3000)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    return {
+        "messages": [AIMessage(content=output)],
+        "chat_log": state["chat_log"] + [{"role": "Quality Assurance", "content": output}],
+        "qa_output": output,
+    }

requirements.txt

@@ -0,0 +1,11 @@
+transformers>=4.38.0
+torch
+langgraph>=0.0.35
+langchain
+gradio
+peft
+huggingface_hub
+bitsandbytes
+accelerate
+sentencepiece
+protobuf

software_architect_agent.py

@@ -0,0 +1,27 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from langchain_core.messages import AIMessage
+
+MODEL_REPO = "Rahul-8799/software_architect_command_r"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_REPO,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def run(state: dict) -> dict:
+    """Software Architect designs overall system architecture"""
+    messages = state["messages"]
+    prompt = messages[-1].content
+
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
+    output_ids = model.generate(input_ids, max_new_tokens=3000)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    return {
+        "messages": [AIMessage(content=output)],
+        "chat_log": state["chat_log"] + [{"role": "Software Architect", "content": output}],
+        "arch_output": output,
+    }

software_engineer_agent.py

@@ -0,0 +1,42 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from langchain_core.messages import AIMessage
+
+MODEL_REPO = "Rahul-8799/software_engineer_mellum"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_REPO,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def run(state: dict) -> dict:
+    """Software Engineer generates clean, modern UI code using best practices"""
+    messages = state["messages"]
+    prompt = messages[-1].content
+    
+    # Enhance the prompt with UI implementation guidelines
+    enhanced_prompt = f"""
+    Generate modern, clean UI code following these guidelines:
+    1. Use Tailwind CSS for styling (recommended for consistent spacing and responsive design)
+    2. Implement proper semantic HTML structure
+    3. Use CSS Grid and Flexbox for layouts
+    4. Add proper ARIA labels for accessibility
+    5. Implement responsive breakpoints
+    6. Use CSS variables for consistent theming
+    7. Add proper error handling and loading states
+    8. Implement proper component structure
+    
+    Original requirements: {prompt}
+    """
+    
+    input_ids = tokenizer(enhanced_prompt, return_tensors="pt").input_ids.to(model.device)
+    output_ids = model.generate(input_ids, max_new_tokens=3000)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    return {
+        "messages": [AIMessage(content=output)],
+        "chat_log": state["chat_log"] + [{"role": "Software Engineer", "content": output}],
+        "dev_output": output,
+    }

ui_designer_agent.py

@@ -0,0 +1,42 @@
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from langchain_core.messages import AIMessage
+
+MODEL_REPO = "Rahul-8799/ui_designer_mistral"  # You'll need to fine-tune this model
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_REPO,
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+
+def run(state: dict) -> dict:
+    """UI Designer creates beautiful and structured UI designs with proper spacing and layout"""
+    messages = state["messages"]
+    prompt = messages[-1].content
+    
+    # Enhance the prompt with UI design principles
+    enhanced_prompt = f"""
+    Create a beautiful and well-structured UI design following these principles:
+    1. Use proper spacing and padding (recommended: 1rem/16px for padding, 2rem/32px for margins)
+    2. Implement a consistent color scheme
+    3. Ensure proper hierarchy with clear headings
+    4. Use responsive design principles
+    5. Implement proper grid system
+    6. Add smooth transitions and hover effects
+    7. Ensure proper contrast and readability
+    8. Use modern UI components and patterns
+    
+    Original requirements: {prompt}
+    """
+    
+    input_ids = tokenizer(enhanced_prompt, return_tensors="pt").input_ids.to(model.device)
+    output_ids = model.generate(input_ids, max_new_tokens=3000)
+    output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+
+    return {
+        "messages": [AIMessage(content=output)],
+        "chat_log": state["chat_log"] + [{"role": "UI Designer", "content": output}],
+        "ui_design_output": output,
+    }