spring-projects/spring-ai · warning

Media type String overrides the Document text content!

Error message

Media type String overrides the Document text content!

What it means

VertexAiMultimodalEmbeddingModel.doSingleDocumentPrediction (called from singleDocResponse) embeds a Document that carries both plain text content and text-typed media. When the document's Media is compatible with the TEXT mime type, the media data wins and the Document's own text content is discarded; this warning tells you the text content was overridden.

Source

Thrown at models/spring-ai-vertex-ai-embedding/src/main/java/org/springframework/ai/vertexai/embedding/multimodal/VertexAiMultimodalEmbeddingModel.java:183

			instanceBuilder.dimension(mergedOptions.getDimensions());
		}

		// optional text parameter
		String documentText = document.getText();
		if (StringUtils.hasText(documentText)) {
			instanceBuilder.text(documentText);
			documentMetadata.put(ModalityType.TEXT,
					new DocumentMetadata(document.getId(), MimeTypeUtils.TEXT_PLAIN, documentText));
		}

		Media media = document.getMedia();
		if (media != null) {
			if (media.getMimeType().isCompatibleWith(TEXT_MIME_TYPE)) {
				instanceBuilder.text(media.getData().toString());
				documentMetadata.put(ModalityType.TEXT,
						new DocumentMetadata(document.getId(), MimeTypeUtils.TEXT_PLAIN, media.getData()));
				if (logger.isWarnEnabled() && StringUtils.hasText(documentText)) {
					logger.warn("Media type String overrides the Document text content!");
				}
			}
			else if (media.getMimeType().isCompatibleWith(IMAGE_MIME_TYPE)) {
				if (SUPPORTED_IMAGE_MIME_SUB_TYPES.contains(media.getMimeType())) {
					instanceBuilder.image(ImageBuilder.of(media.getMimeType()).imageData(media.getData()).build());
					documentMetadata.put(ModalityType.IMAGE,
							new DocumentMetadata(document.getId(), media.getMimeType(), media.getData()));
				}
				else if (logger.isWarnEnabled()) {
					logger.warn("Unsupported image mime type: " + media.getMimeType());
					throw new IllegalArgumentException("Unsupported image mime type: " + media.getMimeType());
				}
			}
			else if (media.getMimeType().isCompatibleWith(VIDEO_MIME_TYPE)) {
				instanceBuilder.video(VideoBuilder.of(media.getMimeType())
					.videoData(media.getData())
					.startOffsetSec(mergedOptions.getVideoStartOffsetSec())
					.endOffsetSec(mergedOptions.getVideoEndOffsetSec())

View on GitHub (pinned to 98a7beda4f)

Solutions

1. Set the Document content to empty or rely solely on the Media field so only one text source exists.
2. Drop the Media when the text you want embedded is the Document content.
3. Verify the Media MimeType is correct; if the data is not really text, use the proper mime type so the intended branch runs.

Example fix

// before
new Document(text, Map.of(), List.of(Media.builder().mimeType(MimeTypeUtils.TEXT_PLAIN).data(text).build()));
// after
new Document(Media.builder().mimeType(MimeTypeUtils.TEXT_PLAIN).data(text).build());

if (doc.getMedia() != null && StringUtils.hasText(doc.getText())
        && doc.getMedia().getMimeType().isCompatibleWith(MimeTypeUtils.TEXT_PLAIN)) {
    throw new IllegalArgumentException("Document has both text content and text media; pick one");
}

boolean hasConflictingText(org.springframework.ai.document.Document d) {
    return d.getMedia() != null
        && d.getMedia().getMimeType().isCompatibleWith(MimeTypeUtils.TEXT_PLAIN)
        && StringUtils.hasText(d.getText());
}

When it happens

Trigger: Embedding a Document that has both non-empty text (documentText) and a Media field whose MimeType is compatible with text/plain, e.g. Media constructed from a string with MimeTypeUtils.TEXT_PLAIN.

Common situations: ETL pipelines that attach media to documents while keeping the original text; loaders that set both content and media; copying Document instances where the original text was left in place after media was added.

Related errors

• Unsupported image mime type: ${mimeType}
• Unsupported media type: ${mimeType}
• Unsupported media data type:
• Unsupported media data type:
• Required properties for TitanEmbeddingBedrockApi are missing

AI-assisted analysis of spring-projects/spring-ai@98a7beda4f (2026-09-11). Data as JSON: /api/errors/de093b96e8207264. Report an issue: GitHub.