lfnovo/open-notebook · error · ValueError

No embedding model configured. Please configure one in the M

Error message

No embedding model configured. Please configure one in the Models section.

What it means

ValueError raised by rebuild_embeddings_command as a fail-fast check: model_manager.get_embedding_model() returned None, so no default embedding model is configured in the Models section. Rebuilding all embeddings requires a working embedding model up front.

Source

Thrown at commands/embedding_commands.py:638

    Retry Strategy:
    - Retries disabled (retry=None) for this coordinator command
    - Individual embed_* commands handle their own retries
    """
    start_time = time.time()

    try:
        logger.info("=" * 60)
        logger.info(f"Starting embedding rebuild with mode={input_data.mode}")
        logger.info(
            f"Include: sources={input_data.include_sources}, notes={input_data.include_notes}, insights={input_data.include_insights}"
        )
        logger.info("=" * 60)

        # Check embedding model availability (fail fast)
        EMBEDDING_MODEL = await model_manager.get_embedding_model()
        if not EMBEDDING_MODEL:
            raise ValueError(
                "No embedding model configured. Please configure one in the Models section."
            )

        logger.info(f"Embedding model configured: {EMBEDDING_MODEL}")

        # Collect items to process (returns IDs only)
        items = await collect_items_for_rebuild(
            input_data.mode,
            input_data.include_sources,
            input_data.include_notes,
            input_data.include_insights,
        )

        total_items = (
            len(items["sources"]) + len(items["notes"]) + len(items["insights"])
        )
        logger.info(f"Total items to rebuild: {total_items}")

View on GitHub (pinned to a7de90d38a)

Solutions

Open the Models section in the UI and set a default embedding model (with valid provider credentials)
Verify the provider's API key env var is set for the API and worker processes
Re-run the rebuild-embeddings command and confirm the log line 'Embedding model configured: ...' appears

Defensive patterns

Strategy: validation

Validate before calling

models = (await client.get('/models')).json()
if not any(m.get('is_default') or 'embed' in (m.get('mode') or '') for m in models):
    raise RuntimeError('no default embedding model configured')

Prevention

Configure a default embedding model in the Models section before running rebuild
Set provider API key env vars for both API and worker processes
Confirm startup logs show the embedding model resolved

When it happens

Trigger: Running the rebuild-embeddings command on a fresh install or after a DB reset where no model has been marked as the default embedding model, or where the model entry lacks provider credentials.

Common situations: Fresh setup that never completed model configuration, deleted/reassigned default embedding model, or environment variables for the model provider not set so the model is effectively unusable.

Related errors

AI-assisted analysis of lfnovo/open-notebook@a7de90d38a (2026-08-27). Data as JSON: /api/errors/fea85a1e7697de81. Report an issue: GitHub.