from sentence_transformers import SentenceTransformer
import faiss
import json

with open("chunks.json", "r", encoding="utf-8") as f:
    chunks = json.load(f)

model = SentenceTransformer("sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
embeddings = model.encode(chunks)

index = faiss.IndexFlatL2(embeddings.shape[1])
index.add(embeddings)
faiss.write_index(index, "vector_store.index")
print("向量資料庫建立完成 ✅")