app.py

import os
import uuid
import base64
from IPython import display
from unstructured.partition.pdf import partition_pdf
from langchain.chat_models import ChatOpenAI
from langchain.embeddings import OpenAIEmbeddings
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain.schema.messages import HumanMessage, SystemMessage
from langchain.schema.document import Document
from langchain.vectorstores import FAISS
from langchain.retrievers.multi_vector import MultiVectorRetriever
# from google.colab import userdata
# openai_api_key = userdata.get('OPENAI_API_KEY')
openai_api_key = "sdhof"
output_path = "./images"
# Get elements
raw_pdf_elements = partition_pdf(
    filename="Bosso.pdf",
    extract_images_in_pdf=True,
    infer_table_structure=True,
    chunking_strategy="by_title",
    max_characters=4000,
    new_after_n_chars=3800,
    combine_text_under_n_chars=2000,
    extract_image_block_output_dir=output_path,
)