"""
Created By: ishwor subedi
Date: 2024-08-23
"""
import string
from uuid import uuid4
from langchain.docstore.document import Document
from langchain_text_splitters import RecursiveCharacterTextSplitter
from src.services.vector_db.qdrent.upload_document import upload_document_existing_collection


class AddDocument:
    def __init__(self, vector_embedding, sparse_embedding):
        self.vector_embed = vector_embedding
        self.sparse_embed = sparse_embedding

    def add_documents(self, texts: list[tuple[str]], vectorstore: str):
        splitter = RecursiveCharacterTextSplitter(
            chunk_size=400,
            chunk_overlap=100,
            add_start_index=True
        )
        sources = [textTuple[1] for textTuple in texts]
        texts = [textTuple[0].replace("\n", " ") for textTuple in texts]
        texts = [text.translate(str.maketrans('', '', string.punctuation.replace(".", ""))) for text in texts]
        texts = [Document(page_content=text, metadata={"source": source}) for text, source in zip(texts, sources)]
        documents = splitter.split_documents(texts)
        upload_document_existing_collection(vector_embed=self.vector_embed,
                                            sparse_embed=self.sparse_embed,
                                            vectorstore=vectorstore, documents=documents)