services/utils.py

import re
import numpy as np
import nltk
from nltk.tokenize import word_tokenize
from nltk.corpus import stopwords
from nltk.stem import WordNetLemmatizer
from sentence_transformers import SentenceTransformer

nltk.download('stopwords')
nltk.download('punkt')
nltk.download('wordnet')
stop_words = set(stopwords.words('english'))
lemmatizer = WordNetLemmatizer()
model = SentenceTransformer('all-mpnet-base-v2')
clip_model = SentenceTransformer('clip-ViT-B-32')

def clean_text(text):
    # Lowercase
    text = text.lower()
    # Remove special characters and digits
    text = re.sub(r'[^a-z\s]', '', text)
    # Tokenize
    words = word_tokenize(text)
    # Remove stopwords and lemmatize
    words = [lemmatizer.lemmatize(word)
             for word in words if word not in stop_words]
    # Join words back to a single string
    cleaned_text = ' '.join(words)
    return cleaned_text

def extract_order_id_from_query(text):
    match = re.search(r'\bB-\d+\b', text)
    if match:
        return match.group(0)
    return None

def generate_text_embedding(text):
    try:
        text_embedding = clip_model.encode(text, convert_to_tensor=True)
        return text_embedding.cpu().numpy() 
    except Exception as e:
        print(f"Error processing text '{text}': {e}")
        return np.zeros((512,))
    
def generate_image_embedding(image_path):
    try:
        image = Image.open(image_path)
        image = image.convert('RGB')
        image_embedding = clip_model.encode(image, convert_to_tensor=True)
        return image_embedding.cpu().numpy()  # Convert to numpy array for easy storage
    except Exception as e:
        print(f"Error processing image from {image_path}: {e}")
        return np.zeros((512,)) 

def clear_chat():
    return []


def undo_last_message(chatbot):
    if chatbot:
        chatbot.pop()
    return chatbot