spring-projects/spring-ai · warning

No chat completion returned for prompt: + prompt

Error message

No chat completion returned for prompt: + prompt

What it means

Warning logged by MistralAiChatModel.internalCall() when the ResponseEntity body from mistralAiApi.chatCompletionEntity() is null — Mistral returned no ChatCompletion object. The model returns an empty ChatResponse (empty generations) instead of throwing, so downstream code sees an apparently valid but content-less response.

Source

Thrown at models/spring-ai-mistral-ai/src/main/java/org/springframework/ai/mistralai/MistralAiChatModel.java:196

		ChatModelObservationContext observationContext = ChatModelObservationContext.builder()
			.prompt(prompt)
			.provider(MistralAiApi.PROVIDER_NAME)
			.build();

		ChatResponse response = ChatModelObservationDocumentation.CHAT_MODEL_OPERATION
			.observation(this.observationConvention, DEFAULT_OBSERVATION_CONVENTION, () -> observationContext,
					this.observationRegistry)
			.observe(() -> {

				ResponseEntity<ChatCompletion> completionEntity = RetryUtils.execute(this.retryTemplate,
						() -> this.mistralAiApi.chatCompletionEntity(request));

				ChatCompletion chatCompletion = completionEntity.getBody();

				if (chatCompletion == null) {
					if (logger.isWarnEnabled()) {
						logger.warn("No chat completion returned for prompt: " + prompt);
					}
					return new ChatResponse(List.of());
				}

				List<Generation> generations = chatCompletion.choices().stream().map(choice -> {
					var role = choice.message().role() != null ? choice.message().role().name() : "";
					var metadata = buildMetadata(choice, chatCompletion.id(), role);

					return buildGeneration(choice, metadata);
				}).toList();

				ChatCompletion completion = Objects.requireNonNull(completionEntity.getBody());
				var usage = Objects.requireNonNull(completion.usage());
				DefaultUsage defaultUsage = getDefaultUsage(usage);
				Usage cumulativeUsage = UsageCalculator.getCumulativeUsage(defaultUsage, previousChatResponse);
				ChatResponse chatResponse = new ChatResponse(generations,
						from(completionEntity.getBody(), cumulativeUsage));

View on GitHub (pinned to 98a7beda4f)

Solutions

1. Verify MISTRAL_AI_API_KEY validity and account/quota status.
2. Log the raw HTTP exchange (interceptor on RestClient) to see the actual status/body.
3. Check spring-ai-mistral-ai and Mistral API version compatibility.
4. Guard callers against empty ChatResponse.getResults() before accessing generations.

Example fix

// before
ChatResponse r = mistralChatModel.call(new Prompt(prompt));
String answer = r.getResult().getOutput().getText();
// after
String answer = r.getResults().isEmpty() ? fallbackAnswer : r.getResult().getOutput().getText();

Assert.hasText(mistralApiKey, "MISTRAL_AI_API_KEY must be set");

static boolean isEmpty(ChatResponse r) { return r == null || r.getResults() == null || r.getResults().isEmpty(); }

ChatResponse r = mistralChatModel.call(new Prompt(prompt));
if (isEmpty(r)) { log.error("Mistral returned no completion"); return retryOrFallback(); }

When it happens

Trigger: mistralAiApi.chatCompletionEntity(request) completes within RetryUtils but completionEntity.getBody() == null — empty HTTP body from the Mistral API or an unparseable payload.

Common situations: Invalid Mistral API key or exhausted rate limit returning an unexpected empty response; Mistral platform incidents; self-hosted/proxied endpoints (custom baseUrl) that return empty bodies; contract drift after Mistral API updates.

Related errors

• No chat completion returned for prompt: + prompt
• No embeddings returned for request: + request
• No moderation response returned for request: + mistralAiMode
• HTTP %s - %s
• Stateless Streamable-Http prompt method must not declare par

AI-assisted analysis of spring-projects/spring-ai@98a7beda4f (2026-09-11). Data as JSON: /api/errors/59f07728f6ada151. Report an issue: GitHub.