RocketChat/Rocket.Chat · error · Meteor.Error

error-ai-provider-request-failed

error-ai-provider-request-failed

Error message

error-ai-provider-request-failed

What it means

The catch-all failure of POST ai.search.answer: AISearch.answer() threw something other than the three recognized service errors (not-enabled, provider-not-configured, empty-response). Typically this is a network-level failure reaching the LLM provider: DNS, TLS, timeouts, HTTP 4xx/5xx from the provider, or an unexpected exception inside the AI integration.

Source

Thrown at apps/meteor/server/api/v1/ai-search.ts:382

		try {
			const answer = await AISearch.answer({
				query,
				messages: answerMessages,
			});

			return API.v1.success(answer);
		} catch (error) {
			const message = error instanceof Error ? error.message : '';
			if (message === 'error-ai-not-enabled') {
				throw new Meteor.Error('error-ai-not-enabled');
			}
			if (message === 'error-ai-provider-not-configured') {
				throw new Meteor.Error('error-ai-provider-not-configured');
			}
			if (message === 'error-ai-provider-empty-response') {
				throw new Meteor.Error('error-ai-provider-empty-response');
			}
			throw new Meteor.Error('error-ai-provider-request-failed');
		}
	},
);

View on GitHub (pinned to b2c16d5842)

Solutions

1. Check server-side logs for the underlying exception from AISearch.answer (the original message is swallowed by the mapping)
2. Verify network egress from the Rocket.Chat server to the provider base URL (curl from the server host)
3. Confirm provider API key validity and quota/plan status
4. Retry with backoff: 429s and transient 5xxs are common and recoverable

try { /* ai.search.answer */ } catch (e) {
  if (e.error === 'error-ai-provider-request-failed') {
    if (e.isRateLimited) return retryWithBackoff(); // 429
    throw e; // network/auth issues need server-side fixes
  }
}

When it happens

Trigger: POST /api/v1/ai.search.answer while the workspace server cannot reach the LLM endpoint (firewall, proxy, DNS), the provider returns 401/429/500, the request exceeds the provider timeout, or the AI service throws an unexpected internal error.

Common situations: Egress firewall blocks the AI gateway URL; provider rate limit or quota exhausted (429); expired/invalid API key producing 401; on-prem server without internet access; provider outage; self-hosted gateway down during the request.

Related errors

• error-ai-not-enabled
• error-ai-provider-not-configured
• error-ai-provider-empty-response
• Failed to retrieve registration confirmation poll data: ${re
• App package download failed

AI-assisted analysis of RocketChat/Rocket.Chat@b2c16d5842 (2026-08-18). Data as JSON: /api/errors/db2a25744459b144. Report an issue: GitHub.