from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import HuggingFaceEmbeddings

DB_FAISS_PATH = 'vectorstore.faiss'

def retrieve_documents(query: str, k: int = 5):
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
                                       model_kwargs={'device': 'cpu'})
    db = FAISS.load_local(DB_FAISS_PATH, embeddings)
    
    results = db.similarity_search(query, k=k)
    return results

def get_relevant_documents(query: str):
    documents = retrieve_documents(query)
    return documents