retriever/embedder.py

from sentence_transformers import SentenceTransformer
import faiss
import numpy as np
import pickle

def build_vector_store(docs, save_path="vector_store.pkl"):
    model = SentenceTransformer("all-MiniLM-L6-v2")
    embeddings = model.encode(docs)

    # FAISS index 생성
    index = faiss.IndexFlatL2(embeddings.shape[1])
    index.add(np.array(embeddings))

    # 튜플로 저장
    with open(save_path, "wb") as f:
        pickle.dump((index, docs, model), f)

    print(f"✅ 벡터 저장소가 {save_path}에 저장되었습니다.")