from __future__ import annotations
import requests


def get_embedding(text: str, base_url: str, model: str, timeout_sec: float = 15.0) -> list[float] | None:
    try:
        resp = requests.post(
            f"{base_url.rstrip('/')}/api/embeddings",
            # Short positive keep_alive keeps the embed model warm across the
            # consecutive turns of an active conversation. With keep_alive=0
            # Ollama unloads it ~2s after every call, so each turn after a brief
            # idle gap pays a cold reload of the embed model. The embed model is
            # tiny (~0.3 GB) and coexists in VRAM with the chat model (pinned at
            # keep_alive=30m in llm.py) with ample headroom, so holding it for a
            # few minutes is effectively free and removes the per-turn reload.
            json={"model": model, "prompt": text, "keep_alive": "5m"},
            timeout=timeout_sec,
        )
        resp.raise_for_status()
        data = resp.json()
        vec = data.get("embedding")
        if isinstance(vec, list):
            return [float(x) for x in vec]
    except Exception:
        return None
    return None