from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader , DirectoryLoader
from langchain_community.embeddings import HuggingFaceBgeEmbeddings
from langchain_community.vectorstores import FAISS

DATA_PATH = "data/"
DB_FAISS_PATH = 'vectorstores/'

# create a vector database
def create_vector_db():
    loader = DirectoryLoader(DATA_PATH,glob='*.pdf',loader_cls=PyPDFLoader)
    documents = loader.load()
    text_splitter = RecursiveCharacterTextSplitter(chunk_size = 500, chunk_overlap = 50)
    texts = text_splitter.split_documents(documents)

    embeddings = HuggingFaceBgeEmbeddings(model_name = 'sentence-transformers/all-MiniLM-L6-v2',
                                          model_kwargs = {'device':'cpu'})
    
    db = FAISS.from_documents(texts,embeddings)
    db.save_local('vectorstores/')

if __name__ == '__main__':
    create_vector_db()