Read A PDF File And Store It In Datastax Astra DB

https://www.python.org/downloads/release/python-3110/

py -3.11 -m venv rag_env

rag_env\Scripts\activate

pip install -U langchain langchain-community langchain-openai langchain-text-splitters cassio cassandra-driver openai pypdf

from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_openai import OpenAIEmbeddings

from langchain_community.vectorstores.cassandra import Cassandra
import cassio

# =========================================
# CONFIG
# =========================================

OPENAI_API_KEY = "your_open_api_key"

ASTRA_DB_APPLICATION_TOKEN = "db_token"
ASTRA_DB_ID = "db_id"
ASTRA_DB_REGION = "us-east-2"
KEYSPACE = "default_keyspace"

PDF_FILE = "Access Resources In Android Studio.pdf"

# =========================================
# INIT ASTRA CONNECTION
# =========================================

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

loader = PyPDFLoader(PDF_FILE)
docs = loader.load()

splitter = RecursiveCharacterTextSplitter(
    chunk_size=500,
    chunk_overlap=50
)

chunks = splitter.split_documents(docs)

embeddings = OpenAIEmbeddings(
    api_key=OPENAI_API_KEY
)

vectorstore = Cassandra.from_documents(
    documents=chunks,
    embedding=embeddings,
    keyspace=KEYSPACE,
    table_name="pdf_vectors"  
)

print("PDF stored successfully in Astra DB!")

Query/Feedback