vector_emb.py

from pinecone_text.sparse import SpladeEncoder
import re
import torch
import torch.nn.functional as F
from transformers import CLIPModel, CLIPProcessor, CLIPTokenizer
import logging

class EmbeddingModels:
    def __init__(self, device="cuda" if torch.cuda.is_available() else "cpu"):
        self.device = device
        logging.info(f'Using Device {self.device}')
        self.sparse_model = SpladeEncoder(device=self.device)
        self.img_model_ID = "openai/clip-vit-large-patch14"
        self.img_model, self.img_processor, self.img_tokenizer = self.get_image_model_info(self.img_model_ID)
        logging.info("Model Loaded")

    def get_image_model_info(self, model_ID):
        model = CLIPModel.from_pretrained(model_ID).to(self.device)
        processor = CLIPProcessor.from_pretrained(model_ID)
        tokenizer = CLIPTokenizer.from_pretrained(model_ID)
        return model, processor, tokenizer

    def get_single_image_embedding(self, my_image):
        image = self.img_processor(
            text=None,
            images=my_image,
            return_tensors="pt"
        )["pixel_values"].to(self.device)

        embedding = self.img_model.get_image_features(image)
        logging.info("Embeddings Created")
        embeddings = F.normalize(embedding, p=2, dim=1)
        logging.info("Embeddings Normalized")
        values = embeddings[0].tolist()
        return values
    
    def preprocessing_patent_data(self,text):
    # Removing Common tags in patent
        pattern0 =  r'\b(SUBSTITUTE SHEET RULE 2 SUMMARY OF THE INVENTION|BRIEF DESCRIPTION OF PREFERRED EMBODIMENTS|BRIEF DESCRIPTION OF THE DRAWINGS/FIGURES|BEST MODE FOR CARRYING OUT THE INVENTION|BACKGROUND AND SUMMARY OF THE INVENTION|FIELD AND BACKGROUND OF THE INVENTION|BACKGROUND OF THE PRESENT INVENTION|FIELD AND BACKGROUND OF INVENTION|STAND DER TECHNIK- BACKGROUND ART|BRIEF DESCRIPTION OF THE DRAWINGS|DESCRIPTION OF THE RELATED ART|BRIEF SUMMARY OF THE INVENTION|UTILITY MODEL CLAIMS A CONTENT|DESCRIPTION OF BACKGROUND ART|BRIEF DESCRIPTION OF DRAWINGS|BACKGROUND OF THE INVENTION|BACKGROUND TO THE INVENTION|TÉCNICA ANTERIOR- PRIOR ART|DISCLOSURE OF THE INVENTION|BRIEF SUMMARY OF INVENTION|BACKGROUND OF RELATED ART|SUMMARY OF THE DISCLOSURE|SUMMARY OF THE INVENTIONS|SUMMARY OF THE INVENTION|OBJECTS OF THE INVENTION|THE CONTENT OF INVENTION|DISCLOSURE OF INVENTION|Disclosure of Invention|Complete Specification|RELATED BACKGROUND ART|BACKGROUND INFORMATION|BACKGROUND TECHNOLOGY|DETAILED DESCRIPTION|SUMMARY OF INVENTION|DETAILED DESCRIPTION|PROBLEM TO BE SOLVED|EFFECT OF INVENTION|WHAT IS CLAIMED IS|What is claimed is|What is Claim is|SUBSTITUTE SHEET|SELECTED DRAWING|BACK GROUND ART|BACKGROUND ART|Background Art|JPO&INPIT|CONSTITUTION|DEFINITIONS|Related Art|BACKGROUND|JPO&INPIT|JPO&NCIPI|COPYRIGHT|SOLUTION|SUMMARY)\b'
        text = re.sub(pattern0, '[SEP]', text, flags=re.IGNORECASE)
        text = ' '.join(text.split())
        # Removing all tags between Heading to /Heading and id= 
        regex = r'<\s*heading[^>]*>(.*?)<\s*/\s*heading>|<[^<]+>|id=\"p-\d+\"|:'
        result = re.sub(regex, '[SEP]', text, flags=re.IGNORECASE)
        # find_formula_names from pat text to exclude it from below logic regex
        chemical_list = []
        pattern1 = r'\b((?:(?:H|He|Li|Be|B|C|N|O|F|Ne|Na|Mg|Al|Si|P|S|Cl|Ar|K|Ca|Sc|Ti|V|Cr|Mn|Fe|Co|Ni|Cu|Zn|Ga|Ge|As|Se|Br|Kr|Rb|Sr|Y|Zr|Nb|Mo|Tc|Ru|Rh|Pd|Ag|Cd|In|Sn|Sb|Te|I|Xe|Cs|Ba|La|Hf|Ta|W|Re|Os|Ir|Pt|Au|Hg|Tl|Pb|Bi|Po|At|Rn|Fr|Ra|Ac|Rf|Db|Sg|Bh|Hs|Mt|Ds|Rg|Cn|Nh|Fl|Mc|Lv|Ts|Og|Ce|Pr|Nd|Pm|Sm|Eu|Gd|Tb|Dy|Ho|Er|Tm|Yb|Lu|Th|Pa|U|Np|Pu|Am|Cm|Bk|Cf|Es|Fm|Md|No|Lr)\d*)+)\b'
        
        formula_names = re.findall(pattern1, result)
        for formula in formula_names:
            if len(formula)>=2:
                chemical_list.append(formula)
        # print("chemical_list:", chemical_list)

        # Remove numbers and alphanum inside brackets excluding chemical forms
        pattern2 = r"\((?![A-Za-z]+\))[\w\d\s,-]+\)|\([A-Za-z]\)"
        def keep_strings(text):
            matched = text.group(0)
            if any(item in matched for item in chemical_list):
                return matched
            return ' '
        cleaned_text = re.sub(pattern2, keep_strings, result)
        cleaned_text = ' '.join(cleaned_text.split())
        cleaned_text= re.sub("(\[SEP\]+\s*)+", ' ', cleaned_text, flags=re.IGNORECASE)
        # below new logic to remove chemical compounds (eg.chemical- polymerizable compounds)
        p_text2=re.sub('[\—\-\═\=]', ' ', cleaned_text)
        pattern1 = r'\b((?:(?:H|He|Li|Be|B|C|N|O|F|Ne|Na|Mg|Al|Si|P|S|Cl|Ar|K|Ca|Sc|Ti|V|Cr|Mn|Fe|Co|Ni|Cu|Zn|Ga|Ge|As|Se|Br|Kr|Rb|Sr|Y|Zr|Nb|Mo|Tc|Ru|Rh|Pd|Ag|Cd|In|Sn|Sb|Te|I|Xe|Cs|Ba|La|Hf|Ta|W|Re|Os|Ir|Pt|Au|Hg|Tl|Pb|Bi|Po|At|Rn|Fr|Ra|Ac|Rf|Db|Sg|Bh|Hs|Mt|Ds|Rg|Cn|Nh|Fl|Mc|Lv|Ts|Og|Ce|Pr|Nd|Pm|Sm|Eu|Gd|Tb|Dy|Ho|Er|Tm|Yb|Lu|Th|Pa|U|Np|Pu|Am|Cm|Bk|Cf|Es|Fm|Md|No|Lr)\d*)+)\b'
        cleaned_text = re.sub(pattern1, "", p_text2)
        cleaned_text = re.sub('  ,+|,  +', ' ', cleaned_text)
        cleaned_text = re.sub(' +', ' ', cleaned_text)
        cleaned_text = re.sub('\.+', '.', cleaned_text)
        cleaned_text = re.sub('[0-9] [0-9] +', ' ', cleaned_text)
        cleaned_text = re.sub('( )', ' ', cleaned_text)
        cleaned_text=cleaned_text.strip()
        return cleaned_text 

    def get_single_sparse_text_embedding(self, df_chunk):
        df_chunk = self.preprocessing_patent_data(df_chunk)
        txt_sp = self.sparse_model.encode_documents(df_chunk)

        # tensor = torch.tensor(txt_sp['values'])
        # normalized_tensor = F.normalize(tensor, p=2.0, dim=0, eps=1e-12)
        # values = normalized_tensor.tolist()

        # # Update the sparse_vector with normalized values
        # normalized_sparse_vector = {
        #     'indices': txt_sp['indices'],
        #     'values': values
        # }
        return txt_sp
    
    def normalize_sparse_vector_values(self,sparse_vector):
        """
        Normalize the values of a sparse vector to a 0-1 range using min-max scaling,
        considering a known range of sparse scores.
        Args:
        sparse_vector: A dict representing a sparse vector with 'indices' and 'values'
        min_score: The minimum score in the range of sparse scores (default is 0)
        max_score: The maximum score in the range of sparse scores (default is 6000)
        Returns:
        A dict representing the sparse vector with normalized 'values'.
        """
        # normalized_values = [(value - min_score) / (max_score - min_score) for value in sparse_vector['values']]
        self.tensor = torch.tensor(sparse_vector['values'])
        self.normalized_tensor = F.normalize(self.tensor, p=2.0, dim=0, eps=1e-12)
        values = self.normalized_tensor.tolist()

        # Update the sparse_vector with normalized values
        self.normalized_sparse_vector = {
            'indices': sparse_vector['indices'],
            'values': values
        }
        return self.normalized_sparse_vector