lfnovo/open-notebook · warning · HTTPException

Vector search requires an embedding model. Please configure

Error message

Vector search requires an embedding model. Please configure one in the Models section.

What it means

400 raised when a vector search is requested but no embedding model is configured in Open Notebook's model manager. Vector search needs an embedding model to convert the query into a vector.

Source

Thrown at api/routers/search.py:28

from open_notebook.domain.notebook import text_search, vector_search
from open_notebook.exceptions import (
    DatabaseOperationError,
    InvalidInputError,
    OpenNotebookError,
)
from open_notebook.graphs.ask import graph as ask_graph

router = APIRouter()


@router.post("/search", response_model=SearchResponse)
async def search_knowledge_base(search_request: SearchRequest):
    """Search the knowledge base using text or vector search."""
    try:
        if search_request.type == "vector":
            # Check if embedding model is available for vector search
            if not await model_manager.get_embedding_model():
                raise HTTPException(
                    status_code=400,
                    detail="Vector search requires an embedding model. Please configure one in the Models section.",
                )

            results = await vector_search(
                keyword=search_request.query,
                results=search_request.limit,
                source=search_request.search_sources,
                note=search_request.search_notes,
                minimum_score=search_request.minimum_score,
            )
        else:
            # Text search
            results = await text_search(
                keyword=search_request.query,
                results=search_request.limit,
                source=search_request.search_sources,
                note=search_request.search_notes,

View on GitHub (pinned to a7de90d38a)

Solutions

Go to Settings → Models and add/select a default embedding model
Verify the provider credentials (e.g. OpenAI API key) are set and encrypted successfully
Retry the search with type 'text' if embeddings are not needed

Example fix

// before
{"query": "topic", "type": "vector"}
// after
// configure embedding model first, then:
{"query": "topic", "type": "vector"}

Defensive patterns

Strategy: validation

Validate before calling

const embedding = (await fetch('/api/models').json())
  .find(m => m.type === 'embedding' && m.is_default);
if (!embedding) useTextSearch();

Prevention

Check for a default embedding model on app startup and prompt configuration
Fall back to text search when embeddings are unavailable

When it happens

Trigger: POST /api/search with {"type": "vector", ...} when model_manager.get_embedding_model() returns None — i.e. no model of type 'embedding' is marked as default in Settings → Models.

Common situations: Fresh install without model setup, embedding model deleted or disabled, provider API keys missing so the model never became active.

Related errors

AI-assisted analysis of lfnovo/open-notebook@a7de90d38a (2026-08-27). Data as JSON: /api/errors/925934e4972d3a44. Report an issue: GitHub.