import hashlib
import json
import sys
from pathlib import Path

import numpy as np
from sentence_transformers import SentenceTransformer

SOURCE = Path("chatbot_docs.jsonl")
INDEX = Path("chatbot_embeddings.npz")
MODEL_NAME = "sentence-transformers/multi-qa-MiniLM-L6-cos-v1"


def load_documents(path):
    return [json.loads(line) for line in path.read_text().splitlines() if line.strip()]


def text_hash(text):
    return hashlib.sha256(text.encode("utf-8")).hexdigest()