app/vector_store.py

import os
from langchain.vectorstores import Chroma
from langchain.embeddings import SentenceTransformerEmbeddings
from langchain.document_loaders import PyMuPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter

CHROMA_DIR = "data/chroma_db"


def store_pdf(pdf_path):
    loader = PyMuPDFLoader(pdf_path)
    docs = loader.load()
    splitter = RecursiveCharacterTextSplitter(
        chunk_size=500, chunk_overlap=100)
    chunks = splitter.split_documents(docs)
    embeddings = SentenceTransformerEmbeddings(model_name='thenlper/gte-large')
    Chroma.from_documents(chunks, embeddings, persist_directory=CHROMA_DIR)