ingest.py

from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.document_loaders import PyPDFLoader, DirectoryLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter, SpacyTextSplitter

DATA_PATH = 'data/geo-10'
DB_FAISS_PATH = 'refbooks-vectorstore/geo-10-1'

# Create vector database


def create_vector_db():
    loader = DirectoryLoader(DATA_PATH,
                             glob='geo-10-1.pdf',
                             loader_cls=PyPDFLoader)

    documents = loader.load()
    text_splitter = SpacyTextSplitter(chunk_size=500,
                                                   chunk_overlap=50)
    texts = text_splitter.split_documents(documents)

    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2',
                                       model_kwargs={'device': 'cpu'})

    db = FAISS.from_documents(texts, embeddings)
    db.save_local(DB_FAISS_PATH)


if __name__ == "__main__":
    create_vector_db()