mem0ai/mem0 · error · ValueError

Query text is required for Delta Sync Index with model endpo

Error message

Query text is required for Delta Sync Index with model endpoint.

What it means

ValueError raised in Databricks search when the store is a DELTA_SYNC index with an embedding_model_endpoint_name configured (so Databricks does the embedding server-side) but the caller passed an empty/None query string. The endpoint needs the raw text to embed; without it the query cannot be formed, and vectors are NOT accepted as an alternative in this branch.

Source

Thrown at mem0/vector_stores/databricks.py:494

        try:
            filters_json = json.dumps(filters) if filters else None

            # Choose query mode per Databricks SDK contract:
            # - query_text: for Delta Sync Index with model endpoint
            # - query_vector: for Direct Access Index and Delta Sync Index with self-managed vectors
            query_kwargs = {
                "index_name": self.fully_qualified_index_name,
                "columns": self.column_names,
                "num_results": top_k,
                "query_type": self.query_type,
                "filters_json": filters_json,
            }
            uses_model_endpoint = (
                self.index_type == VectorIndexType.DELTA_SYNC and self.embedding_model_endpoint_name
            )
            if uses_model_endpoint:
                if not query:
                    raise ValueError("Query text is required for Delta Sync Index with model endpoint.")
                query_kwargs["query_text"] = query
            elif vectors:
                query_kwargs["query_vector"] = vectors
            else:
                raise ValueError("Must provide vectors for search.")

            sdk_results = self.client.vector_search_indexes.query_index(**query_kwargs)

            # Parse results
            result_data = sdk_results.result if hasattr(sdk_results, "result") else sdk_results
            data_array = result_data.data_array if getattr(result_data, "data_array", None) else []

            memory_results = []
            for row in data_array:
                # Map columns to values
                row_dict = dict(zip(self.column_names, row)) if isinstance(row, (list, tuple)) else row
                score = row_dict.get("score") or (
                    row[-1] if isinstance(row, (list, tuple)) and len(row) > len(self.column_names) else None

View on GitHub (pinned to 001c235229)

Solutions

1. Pass a non-empty query string; with a model endpoint the text is embedded by Databricks, so it is mandatory.
2. Validate/reject empty queries in your own layer before calling search.
3. If you want to search by precomputed vectors instead, remove embedding_model_endpoint_name (use DIRECT_ACCESS semantics) so the vectors branch is taken.

Example fix

# before
store.search(query="", vectors=emb, top_k=5)  # ValueError on DELTA_SYNC+endpoint

# after
store.search(query=user_text, top_k=5)  # endpoint embeds the text

def require_query_text(query: str) -> str:
    if not isinstance(query, str) or not query.strip():
        raise ValueError("non-empty query text is required for model-endpoint search")
    return query

results = store.search(query=require_query_text(user_query), top_k=5)

def has_nonempty_query(q) -> bool:
    return isinstance(q, str) and len(q.strip()) > 0

When it happens

Trigger: Calling search(query='', vectors=[...], top_k=...) or search(query=None, ...) on a DELTA_SYNC + model-endpoint setup. The check uses truthiness, so even whitespace-only handling matters only insofar as '' and None are falsy.

Common situations: Pipeline code written for a DIRECT_ACCESS store passing only vectors; user-supplied empty search strings not filtered upstream; search invoked programmatically with a default query=None.

Related errors

• Must provide vectors for search.
• threshold must be a valid number
• Invalid threshold: ${threshold}. Must be between 0 and 1 (in
• topK must be a valid integer
• Invalid topK: ${topK}. Must be a non-negative integer.

AI-assisted analysis of mem0ai/mem0@001c235229 (2026-08-15). Data as JSON: /api/errors/c51807087b67b193. Report an issue: GitHub.