n8n-io/n8n · error · NodeOperationError

Cannot embed empty or undefined text

Error message

Cannot embed empty or undefined text

What it means

validateEmbedQueryInput() guards embedQuery(): the query must be a non-empty string. If it is undefined, null, or '' the embedding call would send nothing meaningful to the provider, so it throws a NodeOperationError with a description explaining the common causes (expression evaluated to undefined, the agent called a tool without proper arguments, a required field is missing).

Source

Thrown at packages/@n8n/ai-utilities/src/utils/embeddings-input-validation.ts:15

import type { INode } from 'n8n-workflow';
import { NodeOperationError } from 'n8n-workflow';

/**
 * Validates query input for embedQuery operations.
 * Throws NodeOperationError if query is invalid (undefined, null, or empty string).
 *
 * @param query - The query to validate
 * @param node - The node for error context
 * @returns The validated query string
 * @throws NodeOperationError if query is invalid
 */
export function validateEmbedQueryInput(query: unknown, node: INode): string {
	if (typeof query !== 'string' || query === '') {
		throw new NodeOperationError(node, 'Cannot embed empty or undefined text', {
			description:
				'The text provided for embedding is empty or undefined. This can happen when: the input expression evaluates to undefined, the AI agent calls a tool without proper arguments, or a required field is missing.',
		});
	}
	return query;
}

/**
 * Validates documents input for embedDocuments operations.
 * Throws NodeOperationError if documents array is invalid or contains invalid entries.
 *
 * @param documents - The documents array to validate
 * @param node - The node for error context
 * @returns The validated documents array
 * @throws NodeOperationError if documents is not an array or contains invalid entries
 */
export function validateEmbedDocumentsInput(documents: unknown, node: INode): string[] {
	if (!Array.isArray(documents)) {

View on GitHub (pinned to 5ac6606e81)

Solutions

1. Ensure the field feeding the embedding input actually contains a non-empty string (use Set/Edit nodes to default it).
2. Guard upstream: skip the embedding node when the input is empty (`if ($json.text)`).
3. If the agent omitted the argument, fix the tool's parameter schema/description so the model supplies it.

Example fix

// before
await embedQuery($json.maybeMissing, ...);

// after
const text = typeof $json.text === 'string' ? $json.text.trim() : '';
if (!text) throw new Error('embedding input empty');
await embedQuery(text, ...);

import { validateEmbedQueryInput } from '@n8n/ai-utilities';
// or inline:
function nonEmptyString(v: unknown): v is string {
  return typeof v === 'string' && v.length > 0;
}
if (!nonEmptyString(query)) {
  throw new Error('embed query must be a non-empty string');
}

function isNonEmptyString(v: unknown): v is string {
  return typeof v === 'string' && v.trim().length > 0;
}

When it happens

Trigger: An embedding node/agent receives an undefined input because the source expression resolved to nothing; the AI agent invoked an embedding tool with no query argument; a previous node emitted an empty item field that is mapped to the embedding input.

Common situations: An expression like `{{ $json.missingField }}` returns undefined; a tool-calling LLM omitted the required text argument; a filter/transform step produced an empty string; first-run item with no payload.

Related errors

• Documents must be an array
• Unknown model discovery provider: "${provider}"
• Unsupported provider
• Invalid categor${invalidCategories.length > 1 ? 'ies' : 'y'}
• Provider connection data cannot be empty

AI-assisted analysis of n8n-io/n8n@5ac6606e81 (2026-08-12). Data as JSON: /api/errors/b51a69e7bd498146. Report an issue: GitHub.