Function fetch_embedding_models

deeptutor_cli/init_wizard.py:655–726

Live-list embedding models from the provider's ``/models`` endpoint. Returns ``[]`` on any failure so callers can fall back to the curated list. When the provider's ``/models`` includes non-embedding models (typical for OpenAI-compatible endpoints), the result is filtered down to en

(
    console: Console,
    strings: dict[str, str],
    *,
    endpoint: str,
    api_key: str,
    provider: str,
)

def fetch_embedding_models(
    console: Console,
    strings: dict[str, str],
    *,
    endpoint: str,
    api_key: str,
    provider: str,
) -> list[str]:
    """Live-list embedding models from the provider's ``/models`` endpoint.

    Returns ``[]`` on any failure so callers can fall back to the curated
    list. When the provider's ``/models`` includes non-embedding models
    (typical for OpenAI-compatible endpoints), the result is filtered down
    to entries whose name looks like an embedding model. If filtering
    leaves nothing, the unfiltered list is returned as a safety net.
    """
    if not endpoint:
        return []

    models_url = _derive_embedding_models_url(endpoint, provider)
    headers: dict[str, str] = {}
    if api_key:
        headers["Authorization"] = f"Bearer {api_key}"

    info(console, strings["init.fetch_models"].format(url=models_url))
    try:
        with httpx.Client(timeout=5.0) as client:
            response = client.get(models_url, headers=headers)
        response.raise_for_status()
        payload = response.json()
    except Exception as exc:
        warn(console, strings["init.fetch_models_fail"].format(error=str(exc)[:160]))
        return []

    raw_items: list[Any] = []
    if isinstance(payload, dict):
        for key in ("data", "models"):
            value = payload.get(key)
            if isinstance(value, list):
                raw_items = value
                break
    elif isinstance(payload, list):
        raw_items = payload

    names: list[str] = []
    for item in raw_items:
        if isinstance(item, str):
            names.append(item)
        elif isinstance(item, dict):
            name = item.get("id") or item.get("name") or item.get("model")
            if isinstance(name, str) and name:
                names.append(name)
    if not names:
        warn(console, strings["init.fetch_models_fail"].format(error="empty model list"))
        return []

    # Mixed lists (OpenAI returns gpt-4o, dall-e, etc. alongside embeddings).
    # Strict ``embed`` filter; if it matches nothing, return empty so the