import gradio as gr
from utils import SafeProgress, format_categories_html
from embeddings import create_product_embeddings
from similarity import compute_similarities
from chicory_api import call_chicory_parser

# Global variable for embeddings
embeddings = {}

def categorize_products(product_input, is_file=False, top_n=5, confidence_threshold=0.5, progress=None):
    """Categorize products from text input or file"""
    progress_tracker = SafeProgress(progress)
    progress_tracker(0, desc="Starting...")

    # Parse input
    if is_file:
        from utils import parse_product_file
        try:
            product_names = parse_product_file(product_input.name)
        except Exception as e:
            return f"<div style='color: #d32f2f; font-weight: bold;'>Error: {str(e)}</div>"
    else:
        product_names = [line.strip() for line in product_input.split("\n") if line.strip()]

    if not product_names:
        return "<div style='color: #d32f2f;'>No product names provided.</div>"

    # Create embeddings
    progress_tracker(0.2, desc="Generating product embeddings...")
    products_embeddings = create_product_embeddings(product_names)

    # Call Chicory Parser API
    progress_tracker(0.5, desc="Calling Chicory Parser API...")
    chicory_results = call_chicory_parser(product_names)

    # Compute similarities
    progress_tracker(0.7, desc="Computing similarities...")
    all_similarities = compute_similarities(embeddings, products_embeddings)

    # Format results
    progress_tracker(0.9, desc="Formatting results...")
    output_html = "<div style='font-family: Arial, sans-serif;'>"
    for product, similarities in all_similarities.items():
        filtered_similarities = [(ingredient, score) for ingredient, score in similarities if score >= confidence_threshold]
        top_similarities = filtered_similarities[:top_n]
        output_html += format_categories_html(product, top_similarities, chicory_result=chicory_results.get(product))
        output_html += "<hr style='margin: 15px 0; border: 0; border-top: 1px solid #eee;'>"
    output_html += "</div>"

    if not all_similarities:
        output_html = "<div style='color: #d32f2f; font-weight: bold; padding: 20px;'>No results found. Please check your input or try different products.</div>"

    progress_tracker(1.0, desc="Done!")
    return output_html

def create_demo():
    """Create the Gradio interface"""
    with gr.Blocks(css="""
        .results-container { min-height: 400px; }
        .chicory-result { visibility: visible !important; display: block !important; }
        .container { gap: 20px; }
    """) as demo:
        gr.Markdown("# Product Categorization Tool\nAnalyze products and find the most similar ingredients using AI embeddings.")
        
        with gr.Tabs():
            with gr.TabItem("Text Input"):
                with gr.Row():
                    with gr.Column(scale=1):
                        # Input section
                        text_input = gr.Textbox(lines=10, placeholder="Enter product names, one per line", label="Product Names")
                        input_controls = gr.Row()
                        with input_controls:
                            top_n = gr.Slider(1, 10, 5, label="Top N Results")
                            confidence = gr.Slider(0.1, 0.9, 0.5, label="Confidence Threshold")
                        categorize_btn = gr.Button("Categorize")
                    
                    with gr.Column(scale=1):
                        # Results section
                        text_output = gr.HTML(label="Categorization Results", elem_classes="results-container")
                
                categorize_btn.click(
                    fn=categorize_products,
                    inputs=[text_input, gr.State(False), top_n, confidence],
                    outputs=text_output
                )
            
            with gr.TabItem("File Upload"):
                with gr.Row():
                    with gr.Column(scale=1):
                        # Input section
                        file_input = gr.File(label="Upload JSON or text file with products", file_types=[".json", ".txt"])
                        file_controls = gr.Row()
                        with file_controls:
                            file_top_n = gr.Slider(1, 10, 5, label="Top N Results")
                            file_confidence = gr.Slider(0.1, 0.9, 0.5, label="Confidence Threshold")
                        process_btn = gr.Button("Process File")
                    
                    with gr.Column(scale=1):
                        # Results section
                        file_output = gr.HTML(label="Categorization Results", elem_classes="results-container")
                
                process_btn.click(
                    fn=categorize_products,
                    inputs=[file_input, gr.State(True), file_top_n, file_confidence],
                    outputs=file_output
                )
                
        gr.Markdown("Powered by Voyage AI embeddings • Built with Gradio")
    return demo