ingest.py

import os
from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings

def create_vector_store(pdf_path, db_dir="vectorstore/"):
    loader = PyPDFLoader(pdf_path)
    docs = loader.load()

    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
    chunks = splitter.split_documents(docs)

    embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
    vectordb = FAISS.from_documents(chunks, embedding=embeddings)

    os.makedirs(db_dir, exist_ok=True)
    vectordb.save_local(db_dir)
    return vectordb