from libs import ROOT_PATH, preprocess,normalize, get_embedding_model
from langchain_core.documents import Document
from services import document_loader, RAGService, load_model
from dotenv import load_dotenv
from langchain_google_genai import ChatGoogleGenerativeAI

load_dotenv()

pdf_path = ROOT_PATH / "comp.pdf"
# doc_obj = document_loader(filepath=pdf_path)
# docu: Document = doc_obj.load()
# print(docu)

model = ChatGoogleGenerativeAI(
    model="gemini-2.5-flash"
)

# model2 = load_model()

obj = RAGService(
    model=model,
    collection_name="demo",
    persist_directory="./demo",
    embedding_model=get_embedding_model(),
    k = 5
)

# obj.delete_database()
# obj.ingest(pdf_path)
response = obj.db.similarity_search_with_score(query="core members of computer department")
print(response)