ui_ingredient_matching.py

import gradio as gr
from utils import SafeProgress
from embeddings import create_product_embeddings
from similarity import compute_similarities
from chicory_api import call_chicory_parser
from ui_core import embeddings, parse_input
from ui_formatters import format_categories_html, create_results_container

def categorize_products(product_input, is_file=False, top_n=10, confidence_threshold=0.5, progress=gr.Progress()):
    """Categorize products from text input or file"""
    progress_tracker = SafeProgress(progress)
    progress_tracker(0, desc="Starting...")

    # Parse input
    product_names, error = parse_input(product_input, is_file)
    if error:
        return error

    # Validate embeddings are loaded
    if not embeddings:
        return "<div style='color: #d32f2f; font-weight: bold; padding: 20px;'>Error: No ingredient embeddings loaded. Please check that the embeddings file exists and is properly formatted.</div>"

    # Create embeddings
    progress_tracker(0.2, desc="Generating product embeddings...")
    products_embeddings = create_product_embeddings(product_names, progress=progress)
    
    if not products_embeddings:
        return "<div style='color: #d32f2f; font-weight: bold; padding: 20px;'>Error: Failed to generate product embeddings. Please try again with different product names.</div>"

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

    # 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; max-width: 100%; overflow-x: auto;'>"
    output_html += f"<p style='color: #555;'>Processing {len(product_names)} products.</p>"
    
    for product, similarities in all_similarities.items():
        filtered_similarities = [(ingredient, score) for ingredient, score in similarities if score >= confidence_threshold]
        top_similarities = filtered_similarities[:int(top_n)]
        
        # Debug info for Chicory results
        chicory_data = chicory_results.get(product, [])

        output_html += format_categories_html(product, top_similarities, chicory_result=chicory_data)
        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