pip install -qU cassio datasets langchain openai tiktoken

# LangChain components to use
from langchain.vectorstores.cassandra import Cassandra
from langchain.indexes.vectorstore import VectorStoreIndexWrapper
from langchain.llms import OpenAI
from langchain.embeddings import OpenAIEmbeddings

# Support for dataset retrieval with Hugging Face
from datasets import load_dataset

# With CassIO, the engine powering the Astra DB integration in LangChain,
# you will also initialize the DB connection:
import cassio

pip install PyPDF2

from PyPDF2 import PdfReader

ASTRA_DB_APPLICATION_TOKEN =   "AstraCS:OsOjMKLLxkWFoUpmNbWeJwIP:d8b4df7fd17c288edd265f9d167fa821e97e9d97098842c2e3ed4140d756d02d"
ASTRA_DB_ID = "f97bbcce-b48b-4b42-8ad0-fdc38b2e165e" # enter your Database ID
OPENAI_API_KEY = "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" # enter your OpenAI key

# provide the path of  pdf file/files.
pdfreader = PdfReader('Ethics.pdf')

from typing_extensions import Concatenate
# read text from pdf
raw_text = ''
for i, page in enumerate(pdfreader.pages):
    content = page.extract_text()
    if content:
        raw_text += content


cassio.init(token=ASTRA_DB_APPLICATION_TOKEN, database_id=ASTRA_DB_ID)

llm = OpenAI(openai_api_key=OPENAI_API_KEY)
embedding = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY)

astra_vector_store = Cassandra(
    embedding=embedding,
    table_name="qa_mini_demo",
    session=None,
    keyspace=None,
)


from langchain.text_splitter import CharacterTextSplitter
# We need to split the text using Character Text Split such that it sshould not increse token size
text_splitter = CharacterTextSplitter(
    separator = "\n",
    chunk_size = 800,
    chunk_overlap  = 200,
    length_function = len,
)
texts = text_splitter.split_text(raw_text)



astra_vector_store.add_texts(texts[:])

print("Inserted %i headlines." % len(texts[:]))

astra_vector_index = VectorStoreIndexWrapper(vectorstore=astra_vector_store)

first_question = True
while True:
    if first_question:
        query_text = input("\nEnter your question (or type 'quit' to exit): ").strip()
    else:
        query_text = input("\nWhat's your next question (or type 'quit' to exit): ").strip()

    if query_text.lower() == "quit":
        break

    if query_text == "":
        continue

    first_question = False

    print("\nQUESTION: \"%s\"" % query_text)
    answer = astra_vector_index.query(query_text, llm=llm).strip()
    print("ANSWER: \"%s\"\n" % answer)