import chromadb
import os
import pymupdf4llm
from semantic_text_splitter import MarkdownSplitter
from _arango import ArangoDB
from pprint import pprint

class ChromaDB:
    def __init__(self):
        self.db = chromadb.PersistentClient("chroma_db")
        max_characters = 2200
        self.ts = MarkdownSplitter(max_characters)
        self.sci_articles = self.db.get_or_create_collection("sci_articles")