HKUDS/DeepTutor · error · RuntimeError

PageIndex OSS indexing needs an API-key or local LLM profile

Error message

PageIndex OSS indexing needs an API-key or local LLM profile; the active OAuth-only provider cannot be used.

What it means

PageIndex OSS indexing requires an API-key or local LLM profile because the SDK must authenticate programmatically; OAuth-only providers (openai_codex, github_copilot, codebuddy) can't supply a stable API key and are rejected.

Source

Thrown at deeptutor/services/rag/pipelines/pageindex/client.py:56

    binding = str(
        getattr(cfg, "binding", None) or getattr(cfg, "provider_name", None) or "openai"
    ).strip()
    spec = find_by_name(binding)
    if not model:
        raise RuntimeError(
            "PageIndex OSS needs an active LLM. Configure one under Settings → Catalog."
        )
    if (
        spec is None
        or spec.is_oauth
        or spec.backend
        in {
            "openai_codex",
            "github_copilot",
            "codebuddy",
        }
    ):
        raise RuntimeError(
            "PageIndex OSS indexing needs an API-key or local LLM profile; "
            "the active OAuth-only provider cannot be used."
        )

    resolved_model = strip_provider_prefix(model, spec)
    prefix = {
        "anthropic": "anthropic",
        "azure_openai": "azure",
        "openai_compat": "openai",
    }.get(spec.backend)
    if prefix is None:
        raise RuntimeError("The active LLM transport is not supported by PageIndex OSS indexing.")

    sdk_model = _prefixed_model(prefix, resolved_model)
    backend: dict[str, Any] = {}
    api_key = str(getattr(cfg, "api_key", "") or "").strip()
    base_url = str(getattr(cfg, "base_url", "") or "").strip()
    api_version = str(getattr(cfg, "api_version", "") or "").strip()

View on GitHub (pinned to 3e82f13042)

Solutions

1. Switch the active LLM to an API-key provider (e.g., openai with an API key) or a local model (ollama/openai_compat with base_url), then retry.
2. If you must keep OAuth for chat, create a separate API-key profile and activate it just for PageIndex OSS indexing.

Example fix

# before
# active binding: github_copilot (OAuth)
await pageindex_client.local(...)  # RuntimeError: OAuth-only provider

# after
# active binding: openai_compat, api_key=..., base_url=http://localhost:11434/v1, model=llama3
await pageindex_client.local(...)

spec = find_by_name(active_binding())
assert not (spec and (spec.is_oauth or spec.backend in {"openai_codex", "github_copilot", "codebuddy"})), \
    "OAuth-only providers cannot drive PageIndex OSS"

def llm_supports_oss_indexing(spec) -> bool:
    return not (spec.is_oauth or spec.backend in {"openai_codex", "github_copilot", "codebuddy"})

try:
    cfg = resolve_oss_sdk_config()
except RuntimeError as e:
    if "OAuth-only" in str(e):
        switch_active_llm("openai_compat", api_key=os.environ["LOCAL_LLM_KEY"])
        cfg = resolve_oss_sdk_config()
    else:
        raise

When it happens

Trigger: resolve_oss_sdk_config runs with an active binding whose spec is OAuth-only (is_oauth true) or whose backend is in {openai_codex, github_copilot, codebuddy}, regardless of model being set.

Common situations: User signed in via Copilot/Codex OAuth in the UI and then attempts OSS indexing; defaults pointing at an OAuth provider after a provider catalog change.

Related errors

• Anthropic API key is missing from the active LLM profile.
• Cohere API key is missing from the active LLM profile.
• OpenAI API key is not configured. Set it in Settings > Catal
• PageIndex OSS needs an active LLM. Configure one under Setti
• The active LLM transport is not supported by PageIndex OSS i

AI-assisted analysis of HKUDS/DeepTutor@3e82f13042 (2026-08-27). Data as JSON: /api/errors/9d0196aeeacc27f3. Report an issue: GitHub.