HKUDS/DeepTutor · error · GraphRagNotConfiguredError

No active chat model. Configure one under Settings → Catalog

Error message

No active chat model. Configure one under Settings → Catalog before creating a GraphRAG knowledge base.

What it means

GraphRagNotConfiguredError from build_settings: no active chat model is configured (llm_cfg.model is empty), so GraphRAG settings cannot be generated. GraphRAG requires a chat model for entity extraction and querying.

Source

Thrown at deeptutor/services/rag/pipelines/graphrag/config.py:259

    ``llm_cfg`` / ``embedding_cfg`` are injectable for tests; in production they
    are resolved from DeepTutor's catalog. Raises
    :class:`GraphRagNotConfiguredError` if either side has no usable model.
    """
    if llm_cfg is None:
        from deeptutor.services.config import resolve_llm_runtime_config

        llm_cfg = resolve_llm_runtime_config()
    if embedding_cfg is None:
        from deeptutor.services.embedding import get_embedding_config

        embedding_cfg = get_embedding_config()

    chat_model = getattr(llm_cfg, "model", None)
    embed_model = getattr(embedding_cfg, "model", None)
    embed_dim = int(getattr(embedding_cfg, "dim", 0) or 0)
    if not chat_model:
        raise GraphRagNotConfiguredError(
            "No active chat model. Configure one under Settings → Catalog before "
            "creating a GraphRAG knowledge base."
        )
    if not embed_model:
        raise GraphRagNotConfiguredError(
            "No active embedding model. Configure one under Settings → Catalog "
            "before creating a GraphRAG knowledge base."
        )
    if not embed_dim:
        raise GraphRagNotConfiguredError(
            "No active embedding model with a known dimension. Configure one under "
            "Settings → Catalog before creating a GraphRAG knowledge base."
        )

    embedding_binding = str(getattr(embedding_cfg, "binding", "") or "")
    llm_base = getattr(llm_cfg, "effective_url", None) or getattr(llm_cfg, "base_url", None)
    embed_endpoint = getattr(embedding_cfg, "effective_url", None) or getattr(
        embedding_cfg, "base_url", None

View on GitHub (pinned to 3e82f13042)

Solutions

1. Open Settings → Catalog and activate a chat model.
2. Verify get_llm_config().model is non-empty in the running environment (not a stale .env).
3. Restart/retry the GraphRAG KB creation after activation.

Example fix

# before: no active model
# after (Settings → Catalog, or API)
await settings.set_active_chat_model("gpt-4o")

if not getattr(get_llm_config(), "model", None):
    raise ConfigError("activate a chat model first (Settings → Catalog)")

When it happens

Trigger: Calling write_settings or add_documents for a GraphRAG pipeline before any chat model has been activated in Settings → Catalog.

Common situations: Fresh install with no model selected; active model profile was deleted or its activation cleared; settings JSON reset.

Related errors

• No active embedding model. Configure one under Settings → Ca
• No active embedding model with a known dimension. Configure
• PageIndex OSS needs an active LLM. Configure one under Setti
• GraphRAG is not installed. Run `pip install 'deeptutor[graph
• GraphRAG preflight failed: {failure_details}

AI-assisted analysis of HKUDS/DeepTutor@3e82f13042 (2026-08-27). Data as JSON: /api/errors/f3a1c4b306174ed6. Report an issue: GitHub.