ingest.py

import os
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import HuggingFaceBgeEmbeddings
from langchain.document_loaders import PyPDFLoader

model_name = "jhgan/ko-sroberta-multitask"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': False}
embeddings = HuggingFaceBgeEmbeddings(
    model_name=model_name,
    model_kwargs=model_kwargs,
    encode_kwargs=encode_kwargs
)

loader = PyPDFLoader("23-24풋살경기규칙.pdf")
documents = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
texts = text_splitter.split_documents(documents)

vector_store = Chroma.from_documents(texts, embeddings, collection_metadata={"hnsw:space": "cosine"}, persist_directory="stores/pet_cosine")

print("Vector Store Created.......")