app/models/retrieval/retriever.py

"""Simple lexical retriever."""

from __future__ import annotations

import json
from pathlib import Path


def retrieve(index_file: Path, query: str, top_k: int = 5) -> list[dict]:
    if not index_file.exists():
        return []
    docs = json.loads(index_file.read_text(encoding="utf-8"))
    q = query.lower().split()
    scored = []
    for doc in docs:
        text = doc["text"].lower()
        score = sum(1 for token in q if token in text)
        scored.append((score, doc))
    scored.sort(key=lambda x: x[0], reverse=True)
    return [doc for score, doc in scored[:top_k] if score > 0]