from dotenv import load_dotenv
load_dotenv()

# bring in deps
from llama_cloud_services import LlamaParse
from llama_index.core import SimpleDirectoryReader
from langchain_community.docstore.in_memory import InMemoryDocstore
from langchain_community.vectorstores import FAISS
from langchain_ollama import OllamaEmbeddings
from langchain_ollama import ChatOllama
import os
import re
from langchain_text_splitters import MarkdownHeaderTextSplitter
from langchain_chroma import Chroma
#from langchain_experimental.text_splitter import SemanticChunker
#from langchain_openai import OpenAIEmbeddings
#from langchain_openai import OpenAI
from marker.converters.pdf import PdfConverter
from marker.models import create_model_dict
from marker.output import text_from_rendered

converter = PdfConverter(artifact_dict=create_model_dict())
rendered = converter("cyber.pdf")
text, _, images = text_from_rendered(rendered)
print(text)