"""Optional local Ollama embeddings for semantic knowledge retrieval."""

from __future__ import annotations

import math
import os
from typing import Sequence
import httpx


class EmbeddingUnavailable(RuntimeError):
    """The configured local embedding model is missing or cannot embed text."""


def embedding_model_name() -> str | None:
    return os.getenv("KNOWLEDGE_EMBEDDING_MODEL", "granite-embedding:278m").strip() or None


def _ollama_base_url() -> str:
    configured = os.getenv("LOCAL_LLM_BASE_URL", "http://127.0.0.1:11434/v1").rstrip("/")
    if configured.endswith("/v1"):
        configured = configured[:-3]
    return configured


async def embed_texts(texts: Sequence[str], *, model: str | None = None) -> list[list[float]]:
    """Generate bounded-size embedding batches through the local Ollama API."""
    if not texts:
        return []
    configured_model = model if model is not None else embedding_model_name()
    model_name = configured_model.strip() if configured_model else ""
    if not model_name:
        raise EmbeddingUnavailable("لم يُضبط نموذج التضمين المحلي.")
    endpoint = f"{_ollama_base_url()}/api/embed"
    results: list[list[float]] = []
    try:
        async with httpx.AsyncClient(timeout=httpx.Timeout(180.0, connect=5.0)) as client:
            for offset in range(0, len(texts), 32):
                batch = [str(text)[:4_000] for text in texts[offset : offset + 32]]
                response = await client.post(
                    endpoint,
                    json={"model": model_name, "input": batch, "keep_alive": "5m"},
                )
                response.raise_for_status()
                payload = response.json()
                vectors = payload.get("embeddings") if isinstance(payload, dict) else None
                if not isinstance(vectors, list) or len(vectors) != len(batch):
                    raise EmbeddingUnavailable("أعاد نموذج التضمين عدد متجهات غير متوقع.")
                dimension = None
                for vector in vectors:
                    if not isinstance(vector, list) or not vector:
                        raise EmbeddingUnavailable("أعاد نموذج التضمين متجهًا فارغًا.")
                    if dimension is None:
                        dimension = len(vector)
                    if len(vector) != dimension:
                        raise EmbeddingUnavailable("أبعاد متجهات التضمين غير متطابقة.")
                    numeric = [float(value) for value in vector]
                    if not all(math.isfinite(value) for value in numeric):
                        raise EmbeddingUnavailable("أعاد نموذج التضمين قيمًا غير صالحة.")
                    if not any(value != 0 for value in numeric):
                        raise EmbeddingUnavailable("أعاد نموذج التضمين متجهًا صفريًا.")
                    results.append(numeric)
    except EmbeddingUnavailable:
        raise
    except (httpx.HTTPError, ValueError, TypeError, KeyError) as exc:
        raise EmbeddingUnavailable("نموذج التضمين المحلي غير متاح؛ سيبقى البحث النصي مستخدمًا.") from exc
    return results